diff options
96 files changed, 15063 insertions, 518 deletions
@@ -1,4 +1,6 @@ -lib/psych/psych.bundle -lib/psych/psych.jar -tmp -pkg +*.swp +*.bundle +*.jar +*.class +/pkg +/tmp diff --git a/.travis.yml b/.travis.yml index 9dc61c1..2c45195 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,9 +1,11 @@ rvm: - 1.9.2 - 1.9.3 + - 2.0.0 + - 2.1.0 - ruby-head before_script: - - gem install isolate - gem install hoe - gem install rake-compiler -script: rake isolate test + - gem install minitest -v '~> 4.0' +script: rake test diff --git a/CHANGELOG.rdoc b/CHANGELOG.rdoc index c48b7aa..4c04f1a 100644 --- a/CHANGELOG.rdoc +++ b/CHANGELOG.rdoc @@ -1,3 +1,350 @@ +Fri Jan 9 07:13:55 2015 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: call `allocate` on hash + subclasses. Fixes github.com/tenderlove/psych/issues/196 + + * test/psych/test_hash.rb: test for change + +Fri Jan 9 06:58:43 2015 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: revive hashes with ivars + + * ext/psych/lib/psych/visitors/yaml_tree.rb: dump hashes with ivars. + Fixes github.com/psych/issues/43 + + * test/psych/test_hash.rb: test for change + +Sun Nov 23 13:11:24 2014 Sean Griffin <sean@thoughtbot.com> + + * lib/psych/visitors/to_ruby.rb: Allow loading any BasicObject that + defines #marshal_load, fixes #100 + * lib/psych/visitors/yaml_tree.rb: Allow dumping any BasicObject that + defines #marshal_dump + +Sat Aug 30 06:39:48 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: fix NameError dumping and + loading. Fixes GH #85. Thanks @brentdax for the patch! + * test/psych/test_exception.rb: test for fix + +Sat Aug 30 06:23:40 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: fix loading strings that + look like integers but have a newline. Fixes GH #189 + * test/psych/test_string.rb: test for fix + +Sat Aug 30 06:10:39 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: merge keys with a hash + should merge the hash in to the parent. + * test/psych/test_merge_keys.rb: test for change. Fixes GH #202 + +Sat Aug 30 06:00:26 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: quoted "<<" strings + should not be treated as merge keys. + * ext/psych/lib/psych/visitors/yaml_tree.rb: hashes with keys + containing "<<" should roundtrip. + * test/psych/test_merge_keys.rb: test for change. Fixes GH #203 + +Wed Aug 6 03:41:21 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: backwards compatibility for + hashes emitted by Syck. Github #198 + * test/psych/test_hash.rb: test for change. + +Fri Jun 6 07:41:41 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: dump empty symbols with a + tag so that they can be parsed on input. [Bug #9873] [ruby-core:62825] + * test/psych/test_symbol.rb: test for change + +Sun May 25 11:35:41 2014 Zachary Scott <e@zzak.io> + + * test/psych/*: YAML::ENGINE was removed in [Bug #8344] + +2014-03-27 SHIBATA Hiroshi <shibata.hiroshi@gmail.com> + + * ext/psych/yaml/scanner.c: merge libyaml 0.1.6 + * ext/psych/yaml/yaml_private.h: ditto + +Sat Mar 1 11:08:00 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: support dumping Encoding + objects. + + * ext/psych/lib/psych/visitors/to_ruby.rb: support loading Encoding + objects. + + * test/psych/test_encoding.rb: add test + + * ext/psych/lib/psych.rb: add version + +Wed Feb 5 10:11:36 2014 Zachary Scott <e@zzak.io> + + * ext/psych/yaml/config.h: bump libyaml to 0.1.5 + +Wed Feb 5 04:16:41 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/yaml/emitter.c: merge libyaml 0.1.5 + * ext/psych/yaml/loader.c: ditto + * ext/psych/yaml/parser.c: ditto + * ext/psych/yaml/reader.c: ditto + * ext/psych/yaml/scanner.c: ditto + * ext/psych/yaml/writer.c: ditto + * ext/psych/yaml/yaml_private.h: ditto + +Thu Jan 9 09:55:20 2014 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: dumping strings with + quotes should not have changed. [ruby-core:59316] [Bug #9300] + + * ext/psych/lib/psych.rb: fixed missing require. + + * test/psych/test_string.rb: test + +Wed Nov 27 06:40:18 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: fix support for negative + years. + * ext/psych/lib/psych/visitors/yaml_tree.rb: ditto + * test/psych/test_date_time.rb: test for change. + Fixes: https://github.com/tenderlove/psych/issues/168 + +Wed Nov 27 04:46:55 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: fix regexp for matching TIME + strings. + * test/psych/test_date_time.rb: test for change. + Fixes: https://github.com/tenderlove/psych/issues/171 + +Wed Nov 6 04:14:25 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: process merge keys before + reviving objects. Fixes GH psych #168 + * test/psych/test_merge_keys.rb: test for change + https://github.com/tenderlove/psych/issues/168 + +Wed Oct 30 03:25:10 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: make less garbage when + testing if a string is binary. + +Wed Oct 30 03:08:24 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: string subclasses should + not be considered to be binary. Fixes Psych / GH 166 + https://github.com/tenderlove/psych/issues/166 + + * test/psych/test_string.rb: test for fix + +Fri Sep 20 23:44:07 2013 Zachary Scott <e@zzak.io> + + * ext/psych/yaml/yaml.h: [DOC] fix typo by @GreenGeorge [Fixes GH-161] + https://github.com/tenderlove/psych/pull/161 + +Fri Sep 6 02:37:22 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: use double quotes when + strings start with special characters. + [Fixes GH-157] https://github.com/tenderlove/psych/issues/157 + + * test/psych/test_string.rb: test for change. + +Thu Aug 29 02:40:45 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: invalid floats should be + treated as strings. + [Fixes GH-156] https://github.com/tenderlove/psych/issues/156 + + * test/psych/test_string.rb: test for change + +Sat Jul 6 04:49:38 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: register time objects so + they are referenced as ids during output. + * test/psych/test_date_time.rb: corresponding test. + +Wed May 15 02:22:16 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych.rb: Adding Psych.safe_load for loading a user + defined, restricted subset of Ruby object types. + * ext/psych/lib/psych/class_loader.rb: A class loader for + encapsulating the logic for which objects are allowed to be + deserialized. + * ext/psych/lib/psych/deprecated.rb: Changes to use the class loader + * ext/psych/lib/psych/exception.rb: ditto + * ext/psych/lib/psych/json/stream.rb: ditto + * ext/psych/lib/psych/nodes/node.rb: ditto + * ext/psych/lib/psych/scalar_scanner.rb: ditto + * ext/psych/lib/psych/stream.rb: ditto + * ext/psych/lib/psych/streaming.rb: ditto + * ext/psych/lib/psych/visitors/json_tree.rb: ditto + * ext/psych/lib/psych/visitors/to_ruby.rb: ditto + * ext/psych/lib/psych/visitors/yaml_tree.rb: ditto + * ext/psych/psych_to_ruby.c: ditto + * test/psych/helper.rb: ditto + * test/psych/test_safe_load.rb: tests for restricted subset. + * test/psych/test_scalar_scanner.rb: ditto + * test/psych/visitors/test_to_ruby.rb: ditto + * test/psych/visitors/test_yaml_tree.rb: ditto + +Sat Apr 6 02:54:08 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/exception.rb: there should be only one exception + base class. Fixes tenderlove/psych #125 + * ext/psych/lib/psych.rb: require the correct exception class + * ext/psych/lib/psych/syntax_error.rb: ditto + * ext/psych/lib/psych/visitors/to_ruby.rb: ditto + +Sat Apr 6 02:06:04 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: correctly register + self-referential strings. Fixes tenderlove/psych #135 + + * test/psych/test_string.rb: appropriate test. + +Fri Mar 1 09:15:00 2013 Zachary Scott <zachary@zacharyscott.net> + + * lib/psych.rb: specify in rdoc what object is returned in parser + By Adam Stankiewicz [Github Fixes #133] + +Fri Mar 1 03:22:00 2013 Zachary Scott <zachary@zacharyscott.net> + + * lib/psych.rb: rdoc for Psych overview by Adam Stankiewicz + [Github Fixes #134] + +Sun Feb 17 01:13:00 2013 Zachary Scott <zachary@zacharyscott.net> + + * lib/psych/y.rb: Document Kernel#y by Adam Stankiewicz + [Github Fixes #127] + +Fri Feb 8 08:53:27 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: fixing string quotation + when dumping Ruby strings. Thanks Ingy + + * test/psych/test_psych.rb: appropriate tests. + + * test/psych/test_yaml.rb: ditto + +Fri Feb 8 08:50:42 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: change output reference + ids to be sequential numbers. + +Thu Jan 17 10:48:56 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: use constants rather than + calculating Inf and NaN. + +Sun Jan 13 16:40:00 2013 Zachary Scott <zachary@zacharyscott.net> + + * ext/psych/yaml/scanner.c: Typos by James Dabbs [Github Fixes #118] + +Sat Jan 12 08:58:47 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: merge key values that + contain something besides a hash should be left in tact. + + * test/psych/test_merge_keys.rb: test for change + +Thu Jan 10 04:23:07 2013 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: strip trailing dots from + floats so that Float() will not raise an exception. + + * test/psych/test_numeric.rb: test to ensure "1." can be loaded + + * test/psych/test_string.rb: make sure "1." can round trip + +Sat Nov 17 12:03:41 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/scalar_scanner.rb: avoid raising exceptions when + parsing Floats and Integers. Thanks riffraff [ruby-core:44426] + * test/psych/test_numeric.rb: associated test + +Sat Nov 17 11:26:36 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/core_ext.rb: move Kernel#y so that it can + manually be required as 'psych/y'. + + * ext/psych/lib/psych/y.rb: ditto + +Tue Nov 6 09:37:57 2012 NARUSE, Yui <naruse@ruby-lang.org> + + * ruby.c (load_file_internal): set default source encoding as + UTF-8 instead of US-ASCII. [ruby-core:46021] [Feature #6679] + + * parse.y (parser_initialize): set default parser encoding as + UTF-8 instead of US-ASCII. + +Mon Oct 29 10:22:00 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/handlers/recorder.rb: added a class for + recording YAML parse and emit events. + + * ext/psych/lib/psych/handler.rb: adding a list of events so that + handler classes can more easily be meta-programmed. + + * test/psych/handlers/test_recorder.rb: tests for the change. + +Sun Oct 28 10:12:15 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: `tree` should return the + same thing on every call. + + * test/psych/visitors/test_yaml_tree.rb: related test. + +Sun Oct 28 10:05:03 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: YAML Tree object should + be able to take an emitter object as it's output. + + * test/psych/visitors/test_yaml_tree.rb: related test. + +Thu Jul 19 09:33:46 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/emitter.c (initialize): allow a configuration object to be + passed to the constructor so that mutation isn't required after + instantiation. + + * ext/psych/lib/psych/handler.rb: add configuration object + + * ext/psych/lib/psych/visitors/emitter.rb: use configuration object if + extra configuration is present. + +Fri May 18 01:28:21 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/parser.c (transcode_string): fix encoding index names. + Thanks markizko for reporting. + +Wed May 16 05:11:29 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: fix a bug with string + subclass dumping and loading. + + * test/psych/test_array.rb: pertinent tests + + * test/psych/test_string.rb: ditto + +Wed May 16 01:31:21 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/to_ruby.rb: convert omap tagged maps to + Psych::Omap objects rather than hashes. [Bug #6425] + + * test/psych/test_omap.rb: pertinent test. + +Wed May 16 01:15:45 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/visitors/yaml_tree.rb: keep a reference to + custom coders so that GC does not impact dumped yaml reference ids. + +Mon Apr 30 04:43:53 2012 Aaron Patterson <aaron@tenderlovemaking.com> + + * ext/psych/lib/psych/json/yaml_events.rb: implicit styles should not + be changeable for JSON events. + Sat Apr 7 02:07:00 2012 Aaron Patterson <aaron@tenderlovemaking.com> * ext/psych/parser.c: fall back to any encoding if the external diff --git a/Manifest.txt b/Manifest.txt index e7c60c6..264b848 100644 --- a/Manifest.txt +++ b/Manifest.txt @@ -4,23 +4,39 @@ CHANGELOG.rdoc Manifest.txt README.rdoc Rakefile -ext/psych/emitter.c -ext/psych/emitter.h +ext/psych/depend ext/psych/extconf.rb -ext/psych/parser.c -ext/psych/parser.h ext/psych/psych.c ext/psych/psych.h -ext/psych/to_ruby.c -ext/psych/to_ruby.h -ext/psych/yaml_tree.c -ext/psych/yaml_tree.h +ext/psych/psych_emitter.c +ext/psych/psych_emitter.h +ext/psych/psych_parser.c +ext/psych/psych_parser.h +ext/psych/psych_to_ruby.c +ext/psych/psych_to_ruby.h +ext/psych/psych_yaml_tree.c +ext/psych/psych_yaml_tree.h +ext/psych/yaml/LICENSE +ext/psych/yaml/api.c +ext/psych/yaml/config.h +ext/psych/yaml/dumper.c +ext/psych/yaml/emitter.c +ext/psych/yaml/loader.c +ext/psych/yaml/parser.c +ext/psych/yaml/reader.c +ext/psych/yaml/scanner.c +ext/psych/yaml/writer.c +ext/psych/yaml/yaml.h +ext/psych/yaml/yaml_private.h lib/psych.rb +lib/psych/class_loader.rb lib/psych/coder.rb lib/psych/core_ext.rb lib/psych/deprecated.rb +lib/psych/exception.rb lib/psych/handler.rb lib/psych/handlers/document_stream.rb +lib/psych/handlers/recorder.rb lib/psych/json/ruby_events.rb lib/psych/json/stream.rb lib/psych/json/tree_builder.rb @@ -48,6 +64,8 @@ lib/psych/visitors/json_tree.rb lib/psych/visitors/to_ruby.rb lib/psych/visitors/visitor.rb lib/psych/visitors/yaml_tree.rb +lib/psych/y.rb +test/psych/handlers/test_recorder.rb test/psych/helper.rb test/psych/json/test_stream.rb test/psych/nodes/test_enumerable.rb @@ -61,7 +79,6 @@ test/psych/test_deprecated.rb test/psych/test_document.rb test/psych/test_emitter.rb test/psych/test_encoding.rb -test/psych/test_engine_manager.rb test/psych/test_exception.rb test/psych/test_hash.rb test/psych/test_json_tree.rb @@ -74,6 +91,7 @@ test/psych/test_object_references.rb test/psych/test_omap.rb test/psych/test_parser.rb test/psych/test_psych.rb +test/psych/test_safe_load.rb test/psych/test_scalar.rb test/psych/test_scalar_scanner.rb test/psych/test_serialize_subclasses.rb diff --git a/README.rdoc b/README.rdoc index 0294e31..47ff958 100644 --- a/README.rdoc +++ b/README.rdoc @@ -23,8 +23,29 @@ to and from the YAML format. == Installation -* sudo port install libyaml +universal -* sudo install_ruby.sh +Psych has been included with MRI since 1.9.2, +and is the default YAML parser in 1.9.3. + +If you want a newer gem release of Psych, you can use rubygems: + + gem install psych + +In order to use the gem release in your app, +and not the stdlib version, you'll need the following: + + gem 'psych' + require 'psych' + +Or if you use Bundler add this to your +Gemfile+: + + gem 'psych' + +JRuby ships with a pure Java implementation of Psych. + +If you're on Rubinius, Psych is available in 1.9 mode, please refer to the +Language Modes section of the {Rubinius +README}[https://github.com/rubinius/rubinius#readme] for more information on +building and 1.9 mode. == License @@ -16,11 +16,13 @@ class Hoe end gem 'rake-compiler', '>= 0.4.1' +gem 'minitest', '~> 4.0' require "rake/extensiontask" -Hoe.plugin :doofus, :git, :gemspec, :isolate +Hoe.plugin :doofus, :git, :gemspec $hoe = Hoe.spec 'psych' do + license 'MIT' developer 'Aaron Patterson', 'aaron@tenderlovemaking.com' self.extra_rdoc_files = Dir['*.rdoc'] @@ -29,6 +31,7 @@ $hoe = Hoe.spec 'psych' do self.testlib = :minitest extra_dev_deps << ['rake-compiler', '>= 0.4.1'] + extra_dev_deps << ['minitest', '~> 4.0'] self.spec_extras = { :extensions => ["ext/psych/extconf.rb"], @@ -71,7 +74,7 @@ namespace :merge do [basedir, 'test', 'psych/'] => [rubydir, 'test', 'psych/'], } - rsync = 'rsync -av --exclude extconf.rb --exclude lib --exclude ".*" --exclude "*.o" --exclude Makefile --exclude mkmf.log --delete' + rsync = 'rsync -av --exclude lib --exclude ".*" --exclude "*.o" --exclude Makefile --exclude mkmf.log --delete' task :to_ruby do mergedirs.each do |from, to| diff --git a/ext/psych/.gitignore b/ext/psych/.gitignore new file mode 100644 index 0000000..836058c --- /dev/null +++ b/ext/psych/.gitignore @@ -0,0 +1,11 @@ +/api.c +/config.h +/dumper.c +/emitter.c +/loader.c +/parser.c +/reader.c +/scanner.c +/writer.c +/yaml.h +/yaml_private.h diff --git a/ext/psych/depend b/ext/psych/depend new file mode 100644 index 0000000..79b6c53 --- /dev/null +++ b/ext/psych/depend @@ -0,0 +1,3 @@ +$(OBJS): $(HDRS) $(ruby_headers) \ + $(hdrdir)/ruby/encoding.h \ + $(hdrdir)/ruby/oniguruma.h diff --git a/ext/psych/extconf.rb b/ext/psych/extconf.rb index fe7795f..65e83a3 100644 --- a/ext/psych/extconf.rb +++ b/ext/psych/extconf.rb @@ -1,21 +1,37 @@ +# -*- coding: us-ascii -*- require 'mkmf' +require 'fileutils' # :stopdoc: -RbConfig::MAKEFILE_CONFIG['CC'] = ENV['CC'] if ENV['CC'] +dir_config 'libyaml' -INCLUDEDIR = Config::CONFIG['includedir'] -LIBDIR = Config::CONFIG['libdir'] -LIB_DIRS = ['/opt/local/lib', '/usr/local/lib', LIBDIR, '/usr/lib'] -libyaml = dir_config 'libyaml', '/opt/local/include', '/opt/local/lib' +if enable_config("bundled-libyaml", false) || !(find_header('yaml.h') && find_library('yaml', 'yaml_get_version')) + # Embed libyaml since we could not find it. -def asplode missing - abort "#{missing} is missing. Try 'port install libyaml +universal' " + - "or 'yum install libyaml-devel'" -end + $VPATH << "$(srcdir)/yaml" + $INCFLAGS << " -I$(srcdir)/yaml" + + $srcs = Dir.glob("#{$srcdir}/{,yaml/}*.c").map {|n| File.basename(n)} + + if have_macro("_WIN32") + $CPPFLAGS << " -DYAML_DECLARE_STATIC -DHAVE_CONFIG_H" + end -asplode('yaml.h') unless find_header 'yaml.h' -asplode('libyaml') unless find_library 'yaml', 'yaml_get_version' + have_header 'dlfcn.h' + have_header 'inttypes.h' + have_header 'memory.h' + have_header 'stdint.h' + have_header 'stdlib.h' + have_header 'strings.h' + have_header 'string.h' + have_header 'sys/stat.h' + have_header 'sys/types.h' + have_header 'unistd.h' + + find_header 'yaml.h' + have_header 'config.h' +end create_makefile 'psych' diff --git a/ext/psych/psych.c b/ext/psych/psych.c index 69ff1d8..3bb59bf 100644 --- a/ext/psych/psych.c +++ b/ext/psych/psych.c @@ -20,7 +20,7 @@ static VALUE libyaml_version(VALUE module) VALUE mPsych; -void Init_psych() +void Init_psych(void) { mPsych = rb_define_module("Psych"); diff --git a/ext/psych/psych.h b/ext/psych/psych.h index 9f1be44..1830ca4 100644 --- a/ext/psych/psych.h +++ b/ext/psych/psych.h @@ -9,10 +9,10 @@ #include <yaml.h> -#include <parser.h> -#include <emitter.h> -#include <to_ruby.h> -#include <yaml_tree.h> +#include <psych_parser.h> +#include <psych_emitter.h> +#include <psych_to_ruby.h> +#include <psych_yaml_tree.h> extern VALUE mPsych; diff --git a/ext/psych/emitter.c b/ext/psych/psych_emitter.c index 15fdcfe..4ba2381 100644 --- a/ext/psych/emitter.c +++ b/ext/psych/psych_emitter.c @@ -2,6 +2,9 @@ VALUE cPsychEmitter; static ID id_write; +static ID id_line_width; +static ID id_indentation; +static ID id_canonical; static void emit(yaml_emitter_t * emitter, yaml_event_t * event) { @@ -26,6 +29,24 @@ static void dealloc(void * ptr) xfree(emitter); } +#if 0 +static size_t memsize(const void *ptr) +{ + const yaml_emitter_t *emitter = ptr; + /* TODO: calculate emitter's size */ + return 0; +} +#endif + +static const rb_data_type_t psych_emitter_type = { + "Psych/emitter", + {0, dealloc, 0,}, + 0, 0, +#ifdef RUBY_TYPED_FREE_IMMEDIATELY + RUBY_TYPED_FREE_IMMEDIATELY, +#endif +}; + static VALUE allocate(VALUE klass) { yaml_emitter_t * emitter; @@ -36,17 +57,32 @@ static VALUE allocate(VALUE klass) yaml_emitter_set_unicode(emitter, 1); yaml_emitter_set_indent(emitter, 2); - return Data_Wrap_Struct(klass, 0, dealloc, emitter); + return TypedData_Wrap_Struct(klass, &psych_emitter_type, emitter); } -/* call-seq: Psych::Emitter.new(io) +/* call-seq: Psych::Emitter.new(io, options = Psych::Emitter::OPTIONS) * * Create a new Psych::Emitter that writes to +io+. */ -static VALUE initialize(VALUE self, VALUE io) +static VALUE initialize(int argc, VALUE *argv, VALUE self) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + VALUE io, options; + VALUE line_width; + VALUE indent; + VALUE canonical; + + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); + + if (rb_scan_args(argc, argv, "11", &io, &options) == 2) { + line_width = rb_funcall(options, id_line_width, 0); + indent = rb_funcall(options, id_indentation, 0); + canonical = rb_funcall(options, id_canonical, 0); + + yaml_emitter_set_width(emitter, NUM2INT(line_width)); + yaml_emitter_set_indent(emitter, NUM2INT(indent)); + yaml_emitter_set_canonical(emitter, Qtrue == canonical ? 1 : 0); + } yaml_emitter_set_output(emitter, writer, (void *)io); @@ -63,7 +99,7 @@ static VALUE start_stream(VALUE self, VALUE encoding) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); Check_Type(encoding, T_FIXNUM); yaml_stream_start_event_initialize(&event, (yaml_encoding_t)NUM2INT(encoding)); @@ -83,7 +119,7 @@ static VALUE end_stream(VALUE self) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_stream_end_event_initialize(&event); @@ -106,7 +142,7 @@ static VALUE start_document(VALUE self, VALUE version, VALUE tags, VALUE imp) yaml_tag_directive_t * tail = NULL; yaml_event_t event; yaml_version_directive_t version_directive; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); Check_Type(version, T_ARRAY); @@ -180,7 +216,7 @@ static VALUE end_document(VALUE self, VALUE imp) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_document_end_event_initialize(&event, imp ? 1 : 0); @@ -210,7 +246,7 @@ static VALUE scalar( #ifdef HAVE_RUBY_ENCODING_H rb_encoding *encoding; #endif - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); Check_Type(value, T_STRING); @@ -277,7 +313,7 @@ static VALUE start_sequence( } #endif - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_sequence_start_event_initialize( &event, @@ -302,7 +338,7 @@ static VALUE end_sequence(VALUE self) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_sequence_end_event_initialize(&event); @@ -330,7 +366,7 @@ static VALUE start_mapping( #ifdef HAVE_RUBY_ENCODING_H rb_encoding *encoding; #endif - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); #ifdef HAVE_RUBY_ENCODING_H encoding = rb_utf8_encoding(); @@ -369,7 +405,7 @@ static VALUE end_mapping(VALUE self) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_mapping_end_event_initialize(&event); @@ -388,7 +424,7 @@ static VALUE alias(VALUE self, VALUE anchor) { yaml_emitter_t * emitter; yaml_event_t event; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); #ifdef HAVE_RUBY_ENCODING_H if(!NIL_P(anchor)) { @@ -414,7 +450,7 @@ static VALUE alias(VALUE self, VALUE anchor) static VALUE set_canonical(VALUE self, VALUE style) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_emitter_set_canonical(emitter, Qtrue == style ? 1 : 0); @@ -428,7 +464,7 @@ static VALUE set_canonical(VALUE self, VALUE style) static VALUE canonical(VALUE self) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); return (emitter->canonical == 0) ? Qfalse : Qtrue; } @@ -441,7 +477,7 @@ static VALUE canonical(VALUE self) static VALUE set_indentation(VALUE self, VALUE level) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_emitter_set_indent(emitter, NUM2INT(level)); @@ -455,7 +491,7 @@ static VALUE set_indentation(VALUE self, VALUE level) static VALUE indentation(VALUE self) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); return INT2NUM(emitter->best_indent); } @@ -467,7 +503,7 @@ static VALUE indentation(VALUE self) static VALUE line_width(VALUE self) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); return INT2NUM(emitter->best_width); } @@ -479,14 +515,14 @@ static VALUE line_width(VALUE self) static VALUE set_line_width(VALUE self, VALUE width) { yaml_emitter_t * emitter; - Data_Get_Struct(self, yaml_emitter_t, emitter); + TypedData_Get_Struct(self, yaml_emitter_t, &psych_emitter_type, emitter); yaml_emitter_set_width(emitter, NUM2INT(width)); return width; } -void Init_psych_emitter() +void Init_psych_emitter(void) { VALUE psych = rb_define_module("Psych"); VALUE handler = rb_define_class_under(psych, "Handler", rb_cObject); @@ -494,7 +530,7 @@ void Init_psych_emitter() rb_define_alloc_func(cPsychEmitter, allocate); - rb_define_method(cPsychEmitter, "initialize", initialize, 1); + rb_define_method(cPsychEmitter, "initialize", initialize, -1); rb_define_method(cPsychEmitter, "start_stream", start_stream, 1); rb_define_method(cPsychEmitter, "end_stream", end_stream, 0); rb_define_method(cPsychEmitter, "start_document", start_document, 3); @@ -512,6 +548,9 @@ void Init_psych_emitter() rb_define_method(cPsychEmitter, "line_width", line_width, 0); rb_define_method(cPsychEmitter, "line_width=", set_line_width, 1); - id_write = rb_intern("write"); + id_write = rb_intern("write"); + id_line_width = rb_intern("line_width"); + id_indentation = rb_intern("indentation"); + id_canonical = rb_intern("canonical"); } /* vim: set noet sws=4 sw=4: */ diff --git a/ext/psych/emitter.h b/ext/psych/psych_emitter.h index 560451e..4c1482a 100644 --- a/ext/psych/emitter.h +++ b/ext/psych/psych_emitter.h @@ -3,6 +3,6 @@ #include <psych.h> -void Init_psych_emitter(); +void Init_psych_emitter(void); #endif diff --git a/ext/psych/parser.c b/ext/psych/psych_parser.c index 6f4c456..faae460 100644 --- a/ext/psych/parser.c +++ b/ext/psych/psych_parser.c @@ -49,6 +49,24 @@ static void dealloc(void * ptr) xfree(parser); } +#if 0 +static size_t memsize(const void *ptr) +{ + const yaml_parser_t *parser = ptr; + /* TODO: calculate parser's size */ + return 0; +} +#endif + +static const rb_data_type_t psych_parser_type = { + "Psych/parser", + {0, dealloc, 0,}, + 0, 0, +#ifdef RUBY_TYPED_FREE_IMMEDIATELY + RUBY_TYPED_FREE_IMMEDIATELY, +#endif +}; + static VALUE allocate(VALUE klass) { yaml_parser_t * parser; @@ -56,7 +74,7 @@ static VALUE allocate(VALUE klass) parser = xmalloc(sizeof(yaml_parser_t)); yaml_parser_initialize(parser); - return Data_Wrap_Struct(klass, 0, dealloc, parser); + return TypedData_Wrap_Struct(klass, &psych_parser_type, parser); } static VALUE make_exception(yaml_parser_t * parser, VALUE path) @@ -79,8 +97,8 @@ static VALUE make_exception(yaml_parser_t * parser, VALUE path) static VALUE transcode_string(VALUE src, int * parser_encoding) { int utf8 = rb_utf8_encindex(); - int utf16le = rb_enc_find_index("UTF16_LE"); - int utf16be = rb_enc_find_index("UTF16_BE"); + int utf16le = rb_enc_find_index("UTF-16LE"); + int utf16be = rb_enc_find_index("UTF-16BE"); int source_encoding = rb_enc_get_index(src); if (source_encoding == utf8) { @@ -248,7 +266,7 @@ static VALUE parse(int argc, VALUE *argv, VALUE self) path = rb_str_new2("<unknown>"); } - Data_Get_Struct(self, yaml_parser_t, parser); + TypedData_Get_Struct(self, yaml_parser_t, &psych_parser_type, parser); yaml_parser_delete(parser); yaml_parser_initialize(parser); @@ -526,7 +544,7 @@ static VALUE mark(VALUE self) VALUE args[3]; yaml_parser_t * parser; - Data_Get_Struct(self, yaml_parser_t, parser); + TypedData_Get_Struct(self, yaml_parser_t, &psych_parser_type, parser); mark_klass = rb_const_get_at(cPsychParser, rb_intern("Mark")); args[0] = INT2NUM(parser->mark.index); args[1] = INT2NUM(parser->mark.line); @@ -535,7 +553,7 @@ static VALUE mark(VALUE self) return rb_class_new_instance(3, args, mark_klass); } -void Init_psych_parser() +void Init_psych_parser(void) { #if 0 mPsych = rb_define_module("Psych"); @@ -557,7 +575,7 @@ void Init_psych_parser() rb_define_const(cPsychParser, "UTF16BE", INT2NUM(YAML_UTF16BE_ENCODING)); rb_require("psych/syntax_error"); - ePsychSyntaxError = rb_define_class_under(mPsych, "SyntaxError", rb_eSyntaxError); + ePsychSyntaxError = rb_const_get(mPsych, rb_intern("SyntaxError")); rb_define_method(cPsychParser, "parse", parse, -1); rb_define_method(cPsychParser, "mark", mark, 0); diff --git a/ext/psych/parser.h b/ext/psych/psych_parser.h index 25e896f..beb3dd0 100644 --- a/ext/psych/parser.h +++ b/ext/psych/psych_parser.h @@ -1,6 +1,6 @@ #ifndef PSYCH_PARSER_H #define PSYCH_PARSER_H -void Init_psych_parser(); +void Init_psych_parser(void); #endif diff --git a/ext/psych/to_ruby.c b/ext/psych/psych_to_ruby.c index ed5245e..3cc87a9 100644 --- a/ext/psych/to_ruby.c +++ b/ext/psych/psych_to_ruby.c @@ -31,11 +31,13 @@ static VALUE path2class(VALUE self, VALUE path) void Init_psych_to_ruby(void) { VALUE psych = rb_define_module("Psych"); + VALUE class_loader = rb_define_class_under(psych, "ClassLoader", rb_cObject); + VALUE visitors = rb_define_module_under(psych, "Visitors"); VALUE visitor = rb_define_class_under(visitors, "Visitor", rb_cObject); cPsychVisitorsToRuby = rb_define_class_under(visitors, "ToRuby", visitor); rb_define_private_method(cPsychVisitorsToRuby, "build_exception", build_exception, 2); - rb_define_private_method(cPsychVisitorsToRuby, "path2class", path2class, 1); + rb_define_private_method(class_loader, "path2class", path2class, 1); } /* vim: set noet sws=4 sw=4: */ diff --git a/ext/psych/to_ruby.h b/ext/psych/psych_to_ruby.h index 7b8e757..7b8e757 100644 --- a/ext/psych/to_ruby.h +++ b/ext/psych/psych_to_ruby.h diff --git a/ext/psych/yaml_tree.c b/ext/psych/psych_yaml_tree.c index bcf24d2..bcf24d2 100644 --- a/ext/psych/yaml_tree.c +++ b/ext/psych/psych_yaml_tree.c diff --git a/ext/psych/yaml_tree.h b/ext/psych/psych_yaml_tree.h index 4628a69..4628a69 100644 --- a/ext/psych/yaml_tree.h +++ b/ext/psych/psych_yaml_tree.h diff --git a/ext/psych/yaml/LICENSE b/ext/psych/yaml/LICENSE new file mode 100644 index 0000000..050ced2 --- /dev/null +++ b/ext/psych/yaml/LICENSE @@ -0,0 +1,19 @@ +Copyright (c) 2006 Kirill Simonov + +Permission is hereby granted, free of charge, to any person obtaining a copy of +this software and associated documentation files (the "Software"), to deal in +the Software without restriction, including without limitation the rights to +use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies +of the Software, and to permit persons to whom the Software is furnished to do +so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/ext/psych/yaml/api.c b/ext/psych/yaml/api.c new file mode 100644 index 0000000..e0b9d97 --- /dev/null +++ b/ext/psych/yaml/api.c @@ -0,0 +1,1415 @@ + +#include "yaml_private.h" + +/* + * Get the library version. + */ + +YAML_DECLARE(const char *) +yaml_get_version_string(void) +{ + return YAML_VERSION_STRING; +} + +/* + * Get the library version numbers. + */ + +YAML_DECLARE(void) +yaml_get_version(int *major, int *minor, int *patch) +{ + *major = YAML_VERSION_MAJOR; + *minor = YAML_VERSION_MINOR; + *patch = YAML_VERSION_PATCH; +} + +/* + * Allocate a dynamic memory block. + */ + +YAML_DECLARE(void *) +yaml_malloc(size_t size) +{ + return malloc(size ? size : 1); +} + +/* + * Reallocate a dynamic memory block. + */ + +YAML_DECLARE(void *) +yaml_realloc(void *ptr, size_t size) +{ + return ptr ? realloc(ptr, size ? size : 1) : malloc(size ? size : 1); +} + +/* + * Free a dynamic memory block. + */ + +YAML_DECLARE(void) +yaml_free(void *ptr) +{ + if (ptr) free(ptr); +} + +/* + * Duplicate a string. + */ + +YAML_DECLARE(yaml_char_t *) +yaml_strdup(const yaml_char_t *str) +{ + if (!str) + return NULL; + + return (yaml_char_t *)strdup((char *)str); +} + +/* + * Extend a string. + */ + +YAML_DECLARE(int) +yaml_string_extend(yaml_char_t **start, + yaml_char_t **pointer, yaml_char_t **end) +{ + yaml_char_t *new_start = yaml_realloc(*start, (*end - *start)*2); + + if (!new_start) return 0; + + memset(new_start + (*end - *start), 0, *end - *start); + + *pointer = new_start + (*pointer - *start); + *end = new_start + (*end - *start)*2; + *start = new_start; + + return 1; +} + +/* + * Append a string B to a string A. + */ + +YAML_DECLARE(int) +yaml_string_join( + yaml_char_t **a_start, yaml_char_t **a_pointer, yaml_char_t **a_end, + yaml_char_t **b_start, yaml_char_t **b_pointer, yaml_char_t **b_end) +{ + if (*b_start == *b_pointer) + return 1; + + while (*a_end - *a_pointer <= *b_pointer - *b_start) { + if (!yaml_string_extend(a_start, a_pointer, a_end)) + return 0; + } + + memcpy(*a_pointer, *b_start, *b_pointer - *b_start); + *a_pointer += *b_pointer - *b_start; + + return 1; +} + +/* + * Extend a stack. + */ + +YAML_DECLARE(int) +yaml_stack_extend(void **start, void **top, void **end) +{ + void *new_start = yaml_realloc(*start, ((char *)*end - (char *)*start)*2); + + if (!new_start) return 0; + + *top = (char *)new_start + ((char *)*top - (char *)*start); + *end = (char *)new_start + ((char *)*end - (char *)*start)*2; + *start = new_start; + + return 1; +} + +/* + * Extend or move a queue. + */ + +YAML_DECLARE(int) +yaml_queue_extend(void **start, void **head, void **tail, void **end) +{ + /* Check if we need to resize the queue. */ + + if (*start == *head && *tail == *end) { + void *new_start = yaml_realloc(*start, + ((char *)*end - (char *)*start)*2); + + if (!new_start) return 0; + + *head = (char *)new_start + ((char *)*head - (char *)*start); + *tail = (char *)new_start + ((char *)*tail - (char *)*start); + *end = (char *)new_start + ((char *)*end - (char *)*start)*2; + *start = new_start; + } + + /* Check if we need to move the queue at the beginning of the buffer. */ + + if (*tail == *end) { + if (*head != *tail) { + memmove(*start, *head, (char *)*tail - (char *)*head); + } + *tail = (char *)*tail - (char *)*head + (char *)*start; + *head = *start; + } + + return 1; +} + + +/* + * Create a new parser object. + */ + +YAML_DECLARE(int) +yaml_parser_initialize(yaml_parser_t *parser) +{ + assert(parser); /* Non-NULL parser object expected. */ + + memset(parser, 0, sizeof(yaml_parser_t)); + if (!BUFFER_INIT(parser, parser->raw_buffer, INPUT_RAW_BUFFER_SIZE)) + goto error; + if (!BUFFER_INIT(parser, parser->buffer, INPUT_BUFFER_SIZE)) + goto error; + if (!QUEUE_INIT(parser, parser->tokens, INITIAL_QUEUE_SIZE)) + goto error; + if (!STACK_INIT(parser, parser->indents, INITIAL_STACK_SIZE)) + goto error; + if (!STACK_INIT(parser, parser->simple_keys, INITIAL_STACK_SIZE)) + goto error; + if (!STACK_INIT(parser, parser->states, INITIAL_STACK_SIZE)) + goto error; + if (!STACK_INIT(parser, parser->marks, INITIAL_STACK_SIZE)) + goto error; + if (!STACK_INIT(parser, parser->tag_directives, INITIAL_STACK_SIZE)) + goto error; + + return 1; + +error: + + BUFFER_DEL(parser, parser->raw_buffer); + BUFFER_DEL(parser, parser->buffer); + QUEUE_DEL(parser, parser->tokens); + STACK_DEL(parser, parser->indents); + STACK_DEL(parser, parser->simple_keys); + STACK_DEL(parser, parser->states); + STACK_DEL(parser, parser->marks); + STACK_DEL(parser, parser->tag_directives); + + return 0; +} + +/* + * Destroy a parser object. + */ + +YAML_DECLARE(void) +yaml_parser_delete(yaml_parser_t *parser) +{ + assert(parser); /* Non-NULL parser object expected. */ + + BUFFER_DEL(parser, parser->raw_buffer); + BUFFER_DEL(parser, parser->buffer); + while (!QUEUE_EMPTY(parser, parser->tokens)) { + yaml_token_delete(&DEQUEUE(parser, parser->tokens)); + } + QUEUE_DEL(parser, parser->tokens); + STACK_DEL(parser, parser->indents); + STACK_DEL(parser, parser->simple_keys); + STACK_DEL(parser, parser->states); + STACK_DEL(parser, parser->marks); + while (!STACK_EMPTY(parser, parser->tag_directives)) { + yaml_tag_directive_t tag_directive = POP(parser, parser->tag_directives); + yaml_free(tag_directive.handle); + yaml_free(tag_directive.prefix); + } + STACK_DEL(parser, parser->tag_directives); + + memset(parser, 0, sizeof(yaml_parser_t)); +} + +/* + * String read handler. + */ + +static int +yaml_string_read_handler(void *data, unsigned char *buffer, size_t size, + size_t *size_read) +{ + yaml_parser_t *parser = data; + + if (parser->input.string.current == parser->input.string.end) { + *size_read = 0; + return 1; + } + + if (size > (size_t)(parser->input.string.end + - parser->input.string.current)) { + size = parser->input.string.end - parser->input.string.current; + } + + memcpy(buffer, parser->input.string.current, size); + parser->input.string.current += size; + *size_read = size; + return 1; +} + +/* + * File read handler. + */ + +static int +yaml_file_read_handler(void *data, unsigned char *buffer, size_t size, + size_t *size_read) +{ + yaml_parser_t *parser = data; + + *size_read = fread(buffer, 1, size, parser->input.file); + return !ferror(parser->input.file); +} + +/* + * Set a string input. + */ + +YAML_DECLARE(void) +yaml_parser_set_input_string(yaml_parser_t *parser, + const unsigned char *input, size_t size) +{ + assert(parser); /* Non-NULL parser object expected. */ + assert(!parser->read_handler); /* You can set the source only once. */ + assert(input); /* Non-NULL input string expected. */ + + parser->read_handler = yaml_string_read_handler; + parser->read_handler_data = parser; + + parser->input.string.start = input; + parser->input.string.current = input; + parser->input.string.end = input+size; +} + +/* + * Set a file input. + */ + +YAML_DECLARE(void) +yaml_parser_set_input_file(yaml_parser_t *parser, FILE *file) +{ + assert(parser); /* Non-NULL parser object expected. */ + assert(!parser->read_handler); /* You can set the source only once. */ + assert(file); /* Non-NULL file object expected. */ + + parser->read_handler = yaml_file_read_handler; + parser->read_handler_data = parser; + + parser->input.file = file; +} + +/* + * Set a generic input. + */ + +YAML_DECLARE(void) +yaml_parser_set_input(yaml_parser_t *parser, + yaml_read_handler_t *handler, void *data) +{ + assert(parser); /* Non-NULL parser object expected. */ + assert(!parser->read_handler); /* You can set the source only once. */ + assert(handler); /* Non-NULL read handler expected. */ + + parser->read_handler = handler; + parser->read_handler_data = data; +} + +/* + * Set the source encoding. + */ + +YAML_DECLARE(void) +yaml_parser_set_encoding(yaml_parser_t *parser, yaml_encoding_t encoding) +{ + assert(parser); /* Non-NULL parser object expected. */ + assert(!parser->encoding); /* Encoding is already set or detected. */ + + parser->encoding = encoding; +} + +/* + * Create a new emitter object. + */ + +YAML_DECLARE(int) +yaml_emitter_initialize(yaml_emitter_t *emitter) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + memset(emitter, 0, sizeof(yaml_emitter_t)); + if (!BUFFER_INIT(emitter, emitter->buffer, OUTPUT_BUFFER_SIZE)) + goto error; + if (!BUFFER_INIT(emitter, emitter->raw_buffer, OUTPUT_RAW_BUFFER_SIZE)) + goto error; + if (!STACK_INIT(emitter, emitter->states, INITIAL_STACK_SIZE)) + goto error; + if (!QUEUE_INIT(emitter, emitter->events, INITIAL_QUEUE_SIZE)) + goto error; + if (!STACK_INIT(emitter, emitter->indents, INITIAL_STACK_SIZE)) + goto error; + if (!STACK_INIT(emitter, emitter->tag_directives, INITIAL_STACK_SIZE)) + goto error; + + return 1; + +error: + + BUFFER_DEL(emitter, emitter->buffer); + BUFFER_DEL(emitter, emitter->raw_buffer); + STACK_DEL(emitter, emitter->states); + QUEUE_DEL(emitter, emitter->events); + STACK_DEL(emitter, emitter->indents); + STACK_DEL(emitter, emitter->tag_directives); + + return 0; +} + +/* + * Destroy an emitter object. + */ + +YAML_DECLARE(void) +yaml_emitter_delete(yaml_emitter_t *emitter) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + BUFFER_DEL(emitter, emitter->buffer); + BUFFER_DEL(emitter, emitter->raw_buffer); + STACK_DEL(emitter, emitter->states); + while (!QUEUE_EMPTY(emitter, emitter->events)) { + yaml_event_delete(&DEQUEUE(emitter, emitter->events)); + } + QUEUE_DEL(emitter, emitter->events); + STACK_DEL(emitter, emitter->indents); + while (!STACK_EMPTY(emitter, emitter->tag_directives)) { + yaml_tag_directive_t tag_directive = POP(emitter, emitter->tag_directives); + yaml_free(tag_directive.handle); + yaml_free(tag_directive.prefix); + } + STACK_DEL(emitter, emitter->tag_directives); + yaml_free(emitter->anchors); + + memset(emitter, 0, sizeof(yaml_emitter_t)); +} + +/* + * String write handler. + */ + +static int +yaml_string_write_handler(void *data, unsigned char *buffer, size_t size) +{ + yaml_emitter_t *emitter = data; + + if (emitter->output.string.size + *emitter->output.string.size_written + < size) { + memcpy(emitter->output.string.buffer + + *emitter->output.string.size_written, + buffer, + emitter->output.string.size + - *emitter->output.string.size_written); + *emitter->output.string.size_written = emitter->output.string.size; + return 0; + } + + memcpy(emitter->output.string.buffer + + *emitter->output.string.size_written, buffer, size); + *emitter->output.string.size_written += size; + return 1; +} + +/* + * File write handler. + */ + +static int +yaml_file_write_handler(void *data, unsigned char *buffer, size_t size) +{ + yaml_emitter_t *emitter = data; + + return (fwrite(buffer, 1, size, emitter->output.file) == size); +} +/* + * Set a string output. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output_string(yaml_emitter_t *emitter, + unsigned char *output, size_t size, size_t *size_written) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + assert(!emitter->write_handler); /* You can set the output only once. */ + assert(output); /* Non-NULL output string expected. */ + + emitter->write_handler = yaml_string_write_handler; + emitter->write_handler_data = emitter; + + emitter->output.string.buffer = output; + emitter->output.string.size = size; + emitter->output.string.size_written = size_written; + *size_written = 0; +} + +/* + * Set a file output. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output_file(yaml_emitter_t *emitter, FILE *file) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + assert(!emitter->write_handler); /* You can set the output only once. */ + assert(file); /* Non-NULL file object expected. */ + + emitter->write_handler = yaml_file_write_handler; + emitter->write_handler_data = emitter; + + emitter->output.file = file; +} + +/* + * Set a generic output handler. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output(yaml_emitter_t *emitter, + yaml_write_handler_t *handler, void *data) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + assert(!emitter->write_handler); /* You can set the output only once. */ + assert(handler); /* Non-NULL handler object expected. */ + + emitter->write_handler = handler; + emitter->write_handler_data = data; +} + +/* + * Set the output encoding. + */ + +YAML_DECLARE(void) +yaml_emitter_set_encoding(yaml_emitter_t *emitter, yaml_encoding_t encoding) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + assert(!emitter->encoding); /* You can set encoding only once. */ + + emitter->encoding = encoding; +} + +/* + * Set the canonical output style. + */ + +YAML_DECLARE(void) +yaml_emitter_set_canonical(yaml_emitter_t *emitter, int canonical) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + emitter->canonical = (canonical != 0); +} + +/* + * Set the indentation increment. + */ + +YAML_DECLARE(void) +yaml_emitter_set_indent(yaml_emitter_t *emitter, int indent) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + emitter->best_indent = (1 < indent && indent < 10) ? indent : 2; +} + +/* + * Set the preferred line width. + */ + +YAML_DECLARE(void) +yaml_emitter_set_width(yaml_emitter_t *emitter, int width) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + emitter->best_width = (width >= 0) ? width : -1; +} + +/* + * Set if unescaped non-ASCII characters are allowed. + */ + +YAML_DECLARE(void) +yaml_emitter_set_unicode(yaml_emitter_t *emitter, int unicode) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + emitter->unicode = (unicode != 0); +} + +/* + * Set the preferred line break character. + */ + +YAML_DECLARE(void) +yaml_emitter_set_break(yaml_emitter_t *emitter, yaml_break_t line_break) +{ + assert(emitter); /* Non-NULL emitter object expected. */ + + emitter->line_break = line_break; +} + +/* + * Destroy a token object. + */ + +YAML_DECLARE(void) +yaml_token_delete(yaml_token_t *token) +{ + assert(token); /* Non-NULL token object expected. */ + + switch (token->type) + { + case YAML_TAG_DIRECTIVE_TOKEN: + yaml_free(token->data.tag_directive.handle); + yaml_free(token->data.tag_directive.prefix); + break; + + case YAML_ALIAS_TOKEN: + yaml_free(token->data.alias.value); + break; + + case YAML_ANCHOR_TOKEN: + yaml_free(token->data.anchor.value); + break; + + case YAML_TAG_TOKEN: + yaml_free(token->data.tag.handle); + yaml_free(token->data.tag.suffix); + break; + + case YAML_SCALAR_TOKEN: + yaml_free(token->data.scalar.value); + break; + + default: + break; + } + + memset(token, 0, sizeof(yaml_token_t)); +} + +/* + * Check if a string is a valid UTF-8 sequence. + * + * Check 'reader.c' for more details on UTF-8 encoding. + */ + +static int +yaml_check_utf8(yaml_char_t *start, size_t length) +{ + yaml_char_t *end = start+length; + yaml_char_t *pointer = start; + + while (pointer < end) { + unsigned char octet; + unsigned int width; + unsigned int value; + size_t k; + + octet = pointer[0]; + width = (octet & 0x80) == 0x00 ? 1 : + (octet & 0xE0) == 0xC0 ? 2 : + (octet & 0xF0) == 0xE0 ? 3 : + (octet & 0xF8) == 0xF0 ? 4 : 0; + value = (octet & 0x80) == 0x00 ? octet & 0x7F : + (octet & 0xE0) == 0xC0 ? octet & 0x1F : + (octet & 0xF0) == 0xE0 ? octet & 0x0F : + (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; + if (!width) return 0; + if (pointer+width > end) return 0; + for (k = 1; k < width; k ++) { + octet = pointer[k]; + if ((octet & 0xC0) != 0x80) return 0; + value = (value << 6) + (octet & 0x3F); + } + if (!((width == 1) || + (width == 2 && value >= 0x80) || + (width == 3 && value >= 0x800) || + (width == 4 && value >= 0x10000))) return 0; + + pointer += width; + } + + return 1; +} + +/* + * Create STREAM-START. + */ + +YAML_DECLARE(int) +yaml_stream_start_event_initialize(yaml_event_t *event, + yaml_encoding_t encoding) +{ + yaml_mark_t mark = { 0, 0, 0 }; + + assert(event); /* Non-NULL event object is expected. */ + + STREAM_START_EVENT_INIT(*event, encoding, mark, mark); + + return 1; +} + +/* + * Create STREAM-END. + */ + +YAML_DECLARE(int) +yaml_stream_end_event_initialize(yaml_event_t *event) +{ + yaml_mark_t mark = { 0, 0, 0 }; + + assert(event); /* Non-NULL event object is expected. */ + + STREAM_END_EVENT_INIT(*event, mark, mark); + + return 1; +} + +/* + * Create DOCUMENT-START. + */ + +YAML_DECLARE(int) +yaml_document_start_event_initialize(yaml_event_t *event, + yaml_version_directive_t *version_directive, + yaml_tag_directive_t *tag_directives_start, + yaml_tag_directive_t *tag_directives_end, + int implicit) +{ + struct { + yaml_error_type_t error; + } context; + yaml_mark_t mark = { 0, 0, 0 }; + yaml_version_directive_t *version_directive_copy = NULL; + struct { + yaml_tag_directive_t *start; + yaml_tag_directive_t *end; + yaml_tag_directive_t *top; + } tag_directives_copy = { NULL, NULL, NULL }; + yaml_tag_directive_t value = { NULL, NULL }; + + assert(event); /* Non-NULL event object is expected. */ + assert((tag_directives_start && tag_directives_end) || + (tag_directives_start == tag_directives_end)); + /* Valid tag directives are expected. */ + + if (version_directive) { + version_directive_copy = yaml_malloc(sizeof(yaml_version_directive_t)); + if (!version_directive_copy) goto error; + version_directive_copy->major = version_directive->major; + version_directive_copy->minor = version_directive->minor; + } + + if (tag_directives_start != tag_directives_end) { + yaml_tag_directive_t *tag_directive; + if (!STACK_INIT(&context, tag_directives_copy, INITIAL_STACK_SIZE)) + goto error; + for (tag_directive = tag_directives_start; + tag_directive != tag_directives_end; tag_directive ++) { + assert(tag_directive->handle); + assert(tag_directive->prefix); + if (!yaml_check_utf8(tag_directive->handle, + strlen((char *)tag_directive->handle))) + goto error; + if (!yaml_check_utf8(tag_directive->prefix, + strlen((char *)tag_directive->prefix))) + goto error; + value.handle = yaml_strdup(tag_directive->handle); + value.prefix = yaml_strdup(tag_directive->prefix); + if (!value.handle || !value.prefix) goto error; + if (!PUSH(&context, tag_directives_copy, value)) + goto error; + value.handle = NULL; + value.prefix = NULL; + } + } + + DOCUMENT_START_EVENT_INIT(*event, version_directive_copy, + tag_directives_copy.start, tag_directives_copy.top, + implicit, mark, mark); + + return 1; + +error: + yaml_free(version_directive_copy); + while (!STACK_EMPTY(context, tag_directives_copy)) { + yaml_tag_directive_t value = POP(context, tag_directives_copy); + yaml_free(value.handle); + yaml_free(value.prefix); + } + STACK_DEL(context, tag_directives_copy); + yaml_free(value.handle); + yaml_free(value.prefix); + + return 0; +} + +/* + * Create DOCUMENT-END. + */ + +YAML_DECLARE(int) +yaml_document_end_event_initialize(yaml_event_t *event, int implicit) +{ + yaml_mark_t mark = { 0, 0, 0 }; + + assert(event); /* Non-NULL emitter object is expected. */ + + DOCUMENT_END_EVENT_INIT(*event, implicit, mark, mark); + + return 1; +} + +/* + * Create ALIAS. + */ + +YAML_DECLARE(int) +yaml_alias_event_initialize(yaml_event_t *event, yaml_char_t *anchor) +{ + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *anchor_copy = NULL; + + assert(event); /* Non-NULL event object is expected. */ + assert(anchor); /* Non-NULL anchor is expected. */ + + if (!yaml_check_utf8(anchor, strlen((char *)anchor))) return 0; + + anchor_copy = yaml_strdup(anchor); + if (!anchor_copy) + return 0; + + ALIAS_EVENT_INIT(*event, anchor_copy, mark, mark); + + return 1; +} + +/* + * Create SCALAR. + */ + +YAML_DECLARE(int) +yaml_scalar_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, + yaml_char_t *value, int length, + int plain_implicit, int quoted_implicit, + yaml_scalar_style_t style) +{ + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *anchor_copy = NULL; + yaml_char_t *tag_copy = NULL; + yaml_char_t *value_copy = NULL; + size_t value_length; + + assert(event); /* Non-NULL event object is expected. */ + assert(value); /* Non-NULL anchor is expected. */ + + if (anchor) { + if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; + anchor_copy = yaml_strdup(anchor); + if (!anchor_copy) goto error; + } + + if (tag) { + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + } + + if (length < 0) { + value_length = strlen((char *)value); + } + else { + value_length = (size_t)length; + } + + if (!yaml_check_utf8(value, value_length)) goto error; + value_copy = yaml_malloc(value_length+1); + if (!value_copy) goto error; + memcpy(value_copy, value, value_length); + value_copy[value_length] = '\0'; + + SCALAR_EVENT_INIT(*event, anchor_copy, tag_copy, value_copy, value_length, + plain_implicit, quoted_implicit, style, mark, mark); + + return 1; + +error: + yaml_free(anchor_copy); + yaml_free(tag_copy); + yaml_free(value_copy); + + return 0; +} + +/* + * Create SEQUENCE-START. + */ + +YAML_DECLARE(int) +yaml_sequence_start_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, int implicit, + yaml_sequence_style_t style) +{ + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *anchor_copy = NULL; + yaml_char_t *tag_copy = NULL; + + assert(event); /* Non-NULL event object is expected. */ + + if (anchor) { + if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; + anchor_copy = yaml_strdup(anchor); + if (!anchor_copy) goto error; + } + + if (tag) { + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + } + + SEQUENCE_START_EVENT_INIT(*event, anchor_copy, tag_copy, + implicit, style, mark, mark); + + return 1; + +error: + yaml_free(anchor_copy); + yaml_free(tag_copy); + + return 0; +} + +/* + * Create SEQUENCE-END. + */ + +YAML_DECLARE(int) +yaml_sequence_end_event_initialize(yaml_event_t *event) +{ + yaml_mark_t mark = { 0, 0, 0 }; + + assert(event); /* Non-NULL event object is expected. */ + + SEQUENCE_END_EVENT_INIT(*event, mark, mark); + + return 1; +} + +/* + * Create MAPPING-START. + */ + +YAML_DECLARE(int) +yaml_mapping_start_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, int implicit, + yaml_mapping_style_t style) +{ + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *anchor_copy = NULL; + yaml_char_t *tag_copy = NULL; + + assert(event); /* Non-NULL event object is expected. */ + + if (anchor) { + if (!yaml_check_utf8(anchor, strlen((char *)anchor))) goto error; + anchor_copy = yaml_strdup(anchor); + if (!anchor_copy) goto error; + } + + if (tag) { + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + } + + MAPPING_START_EVENT_INIT(*event, anchor_copy, tag_copy, + implicit, style, mark, mark); + + return 1; + +error: + yaml_free(anchor_copy); + yaml_free(tag_copy); + + return 0; +} + +/* + * Create MAPPING-END. + */ + +YAML_DECLARE(int) +yaml_mapping_end_event_initialize(yaml_event_t *event) +{ + yaml_mark_t mark = { 0, 0, 0 }; + + assert(event); /* Non-NULL event object is expected. */ + + MAPPING_END_EVENT_INIT(*event, mark, mark); + + return 1; +} + +/* + * Destroy an event object. + */ + +YAML_DECLARE(void) +yaml_event_delete(yaml_event_t *event) +{ + yaml_tag_directive_t *tag_directive; + + assert(event); /* Non-NULL event object expected. */ + + switch (event->type) + { + case YAML_DOCUMENT_START_EVENT: + yaml_free(event->data.document_start.version_directive); + for (tag_directive = event->data.document_start.tag_directives.start; + tag_directive != event->data.document_start.tag_directives.end; + tag_directive++) { + yaml_free(tag_directive->handle); + yaml_free(tag_directive->prefix); + } + yaml_free(event->data.document_start.tag_directives.start); + break; + + case YAML_ALIAS_EVENT: + yaml_free(event->data.alias.anchor); + break; + + case YAML_SCALAR_EVENT: + yaml_free(event->data.scalar.anchor); + yaml_free(event->data.scalar.tag); + yaml_free(event->data.scalar.value); + break; + + case YAML_SEQUENCE_START_EVENT: + yaml_free(event->data.sequence_start.anchor); + yaml_free(event->data.sequence_start.tag); + break; + + case YAML_MAPPING_START_EVENT: + yaml_free(event->data.mapping_start.anchor); + yaml_free(event->data.mapping_start.tag); + break; + + default: + break; + } + + memset(event, 0, sizeof(yaml_event_t)); +} + +/* + * Create a document object. + */ + +YAML_DECLARE(int) +yaml_document_initialize(yaml_document_t *document, + yaml_version_directive_t *version_directive, + yaml_tag_directive_t *tag_directives_start, + yaml_tag_directive_t *tag_directives_end, + int start_implicit, int end_implicit) +{ + struct { + yaml_error_type_t error; + } context; + struct { + yaml_node_t *start; + yaml_node_t *end; + yaml_node_t *top; + } nodes = { NULL, NULL, NULL }; + yaml_version_directive_t *version_directive_copy = NULL; + struct { + yaml_tag_directive_t *start; + yaml_tag_directive_t *end; + yaml_tag_directive_t *top; + } tag_directives_copy = { NULL, NULL, NULL }; + yaml_tag_directive_t value = { NULL, NULL }; + yaml_mark_t mark = { 0, 0, 0 }; + + assert(document); /* Non-NULL document object is expected. */ + assert((tag_directives_start && tag_directives_end) || + (tag_directives_start == tag_directives_end)); + /* Valid tag directives are expected. */ + + if (!STACK_INIT(&context, nodes, INITIAL_STACK_SIZE)) goto error; + + if (version_directive) { + version_directive_copy = yaml_malloc(sizeof(yaml_version_directive_t)); + if (!version_directive_copy) goto error; + version_directive_copy->major = version_directive->major; + version_directive_copy->minor = version_directive->minor; + } + + if (tag_directives_start != tag_directives_end) { + yaml_tag_directive_t *tag_directive; + if (!STACK_INIT(&context, tag_directives_copy, INITIAL_STACK_SIZE)) + goto error; + for (tag_directive = tag_directives_start; + tag_directive != tag_directives_end; tag_directive ++) { + assert(tag_directive->handle); + assert(tag_directive->prefix); + if (!yaml_check_utf8(tag_directive->handle, + strlen((char *)tag_directive->handle))) + goto error; + if (!yaml_check_utf8(tag_directive->prefix, + strlen((char *)tag_directive->prefix))) + goto error; + value.handle = yaml_strdup(tag_directive->handle); + value.prefix = yaml_strdup(tag_directive->prefix); + if (!value.handle || !value.prefix) goto error; + if (!PUSH(&context, tag_directives_copy, value)) + goto error; + value.handle = NULL; + value.prefix = NULL; + } + } + + DOCUMENT_INIT(*document, nodes.start, nodes.end, version_directive_copy, + tag_directives_copy.start, tag_directives_copy.top, + start_implicit, end_implicit, mark, mark); + + return 1; + +error: + STACK_DEL(&context, nodes); + yaml_free(version_directive_copy); + while (!STACK_EMPTY(&context, tag_directives_copy)) { + yaml_tag_directive_t value = POP(&context, tag_directives_copy); + yaml_free(value.handle); + yaml_free(value.prefix); + } + STACK_DEL(&context, tag_directives_copy); + yaml_free(value.handle); + yaml_free(value.prefix); + + return 0; +} + +/* + * Destroy a document object. + */ + +YAML_DECLARE(void) +yaml_document_delete(yaml_document_t *document) +{ + struct { + yaml_error_type_t error; + } context; + yaml_tag_directive_t *tag_directive; + + context.error = YAML_NO_ERROR; /* Eliminate a compliler warning. */ + + assert(document); /* Non-NULL document object is expected. */ + + while (!STACK_EMPTY(&context, document->nodes)) { + yaml_node_t node = POP(&context, document->nodes); + yaml_free(node.tag); + switch (node.type) { + case YAML_SCALAR_NODE: + yaml_free(node.data.scalar.value); + break; + case YAML_SEQUENCE_NODE: + STACK_DEL(&context, node.data.sequence.items); + break; + case YAML_MAPPING_NODE: + STACK_DEL(&context, node.data.mapping.pairs); + break; + default: + assert(0); /* Should not happen. */ + } + } + STACK_DEL(&context, document->nodes); + + yaml_free(document->version_directive); + for (tag_directive = document->tag_directives.start; + tag_directive != document->tag_directives.end; + tag_directive++) { + yaml_free(tag_directive->handle); + yaml_free(tag_directive->prefix); + } + yaml_free(document->tag_directives.start); + + memset(document, 0, sizeof(yaml_document_t)); +} + +/** + * Get a document node. + */ + +YAML_DECLARE(yaml_node_t *) +yaml_document_get_node(yaml_document_t *document, int index) +{ + assert(document); /* Non-NULL document object is expected. */ + + if (index > 0 && document->nodes.start + index <= document->nodes.top) { + return document->nodes.start + index - 1; + } + return NULL; +} + +/** + * Get the root object. + */ + +YAML_DECLARE(yaml_node_t *) +yaml_document_get_root_node(yaml_document_t *document) +{ + assert(document); /* Non-NULL document object is expected. */ + + if (document->nodes.top != document->nodes.start) { + return document->nodes.start; + } + return NULL; +} + +/* + * Add a scalar node to a document. + */ + +YAML_DECLARE(int) +yaml_document_add_scalar(yaml_document_t *document, + yaml_char_t *tag, yaml_char_t *value, int length, + yaml_scalar_style_t style) +{ + struct { + yaml_error_type_t error; + } context; + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *tag_copy = NULL; + yaml_char_t *value_copy = NULL; + yaml_node_t node; + size_t value_length; + ptrdiff_t ret; + + assert(document); /* Non-NULL document object is expected. */ + assert(value); /* Non-NULL value is expected. */ + + if (!tag) { + tag = (yaml_char_t *)YAML_DEFAULT_SCALAR_TAG; + } + + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + + if (length < 0) { + value_length = strlen((char *)value); + } + else { + value_length = (size_t)length; + } + + if (!yaml_check_utf8(value, value_length)) goto error; + value_copy = yaml_malloc(value_length+1); + if (!value_copy) goto error; + memcpy(value_copy, value, value_length); + value_copy[value_length] = '\0'; + + SCALAR_NODE_INIT(node, tag_copy, value_copy, value_length, style, mark, mark); + if (!PUSH(&context, document->nodes, node)) goto error; + + ret = document->nodes.top - document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (ret > INT_MAX) goto error; +#endif + return (int)ret; + +error: + yaml_free(tag_copy); + yaml_free(value_copy); + + return 0; +} + +/* + * Add a sequence node to a document. + */ + +YAML_DECLARE(int) +yaml_document_add_sequence(yaml_document_t *document, + yaml_char_t *tag, yaml_sequence_style_t style) +{ + struct { + yaml_error_type_t error; + } context; + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *tag_copy = NULL; + struct { + yaml_node_item_t *start; + yaml_node_item_t *end; + yaml_node_item_t *top; + } items = { NULL, NULL, NULL }; + yaml_node_t node; + ptrdiff_t ret; + + assert(document); /* Non-NULL document object is expected. */ + + if (!tag) { + tag = (yaml_char_t *)YAML_DEFAULT_SEQUENCE_TAG; + } + + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + + if (!STACK_INIT(&context, items, INITIAL_STACK_SIZE)) goto error; + + SEQUENCE_NODE_INIT(node, tag_copy, items.start, items.end, + style, mark, mark); + if (!PUSH(&context, document->nodes, node)) goto error; + + ret = document->nodes.top - document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (ret > INT_MAX) goto error; +#endif + return (int)ret; + +error: + STACK_DEL(&context, items); + yaml_free(tag_copy); + + return 0; +} + +/* + * Add a mapping node to a document. + */ + +YAML_DECLARE(int) +yaml_document_add_mapping(yaml_document_t *document, + yaml_char_t *tag, yaml_mapping_style_t style) +{ + struct { + yaml_error_type_t error; + } context; + yaml_mark_t mark = { 0, 0, 0 }; + yaml_char_t *tag_copy = NULL; + struct { + yaml_node_pair_t *start; + yaml_node_pair_t *end; + yaml_node_pair_t *top; + } pairs = { NULL, NULL, NULL }; + yaml_node_t node; + ptrdiff_t ret; + + assert(document); /* Non-NULL document object is expected. */ + + if (!tag) { + tag = (yaml_char_t *)YAML_DEFAULT_MAPPING_TAG; + } + + if (!yaml_check_utf8(tag, strlen((char *)tag))) goto error; + tag_copy = yaml_strdup(tag); + if (!tag_copy) goto error; + + if (!STACK_INIT(&context, pairs, INITIAL_STACK_SIZE)) goto error; + + MAPPING_NODE_INIT(node, tag_copy, pairs.start, pairs.end, + style, mark, mark); + if (!PUSH(&context, document->nodes, node)) goto error; + + ret = document->nodes.top - document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (ret > INT_MAX) goto error; +#endif + return (int)ret; + +error: + STACK_DEL(&context, pairs); + yaml_free(tag_copy); + + return 0; +} + +/* + * Append an item to a sequence node. + */ + +YAML_DECLARE(int) +yaml_document_append_sequence_item(yaml_document_t *document, + int sequence, int item) +{ + struct { + yaml_error_type_t error; + } context; + + assert(document); /* Non-NULL document is required. */ + assert(sequence > 0 + && document->nodes.start + sequence <= document->nodes.top); + /* Valid sequence id is required. */ + assert(document->nodes.start[sequence-1].type == YAML_SEQUENCE_NODE); + /* A sequence node is required. */ + assert(item > 0 && document->nodes.start + item <= document->nodes.top); + /* Valid item id is required. */ + + if (!PUSH(&context, + document->nodes.start[sequence-1].data.sequence.items, item)) + return 0; + + return 1; +} + +/* + * Append a pair of a key and a value to a mapping node. + */ + +YAML_DECLARE(int) +yaml_document_append_mapping_pair(yaml_document_t *document, + int mapping, int key, int value) +{ + struct { + yaml_error_type_t error; + } context; + + yaml_node_pair_t pair; + + assert(document); /* Non-NULL document is required. */ + assert(mapping > 0 + && document->nodes.start + mapping <= document->nodes.top); + /* Valid mapping id is required. */ + assert(document->nodes.start[mapping-1].type == YAML_MAPPING_NODE); + /* A mapping node is required. */ + assert(key > 0 && document->nodes.start + key <= document->nodes.top); + /* Valid key id is required. */ + assert(value > 0 && document->nodes.start + value <= document->nodes.top); + /* Valid value id is required. */ + + pair.key = key; + pair.value = value; + + if (!PUSH(&context, + document->nodes.start[mapping-1].data.mapping.pairs, pair)) + return 0; + + return 1; +} + + diff --git a/ext/psych/yaml/config.h b/ext/psych/yaml/config.h new file mode 100644 index 0000000..f54c27d --- /dev/null +++ b/ext/psych/yaml/config.h @@ -0,0 +1,10 @@ +#define PACKAGE_NAME "yaml" +#define PACKAGE_TARNAME "yaml" +#define PACKAGE_VERSION "0.1.6" +#define PACKAGE_STRING "yaml 0.1.6" +#define PACKAGE_BUGREPORT "http://pyyaml.org/newticket?component libyaml" +#define PACKAGE_URL "" +#define YAML_VERSION_MAJOR 0 +#define YAML_VERSION_MINOR 1 +#define YAML_VERSION_PATCH 6 +#define YAML_VERSION_STRING "0.1.6" diff --git a/ext/psych/yaml/dumper.c b/ext/psych/yaml/dumper.c new file mode 100644 index 0000000..203c6a7 --- /dev/null +++ b/ext/psych/yaml/dumper.c @@ -0,0 +1,394 @@ + +#include "yaml_private.h" + +/* + * API functions. + */ + +YAML_DECLARE(int) +yaml_emitter_open(yaml_emitter_t *emitter); + +YAML_DECLARE(int) +yaml_emitter_close(yaml_emitter_t *emitter); + +YAML_DECLARE(int) +yaml_emitter_dump(yaml_emitter_t *emitter, yaml_document_t *document); + +/* + * Clean up functions. + */ + +static void +yaml_emitter_delete_document_and_anchors(yaml_emitter_t *emitter); + +/* + * Anchor functions. + */ + +static void +yaml_emitter_anchor_node(yaml_emitter_t *emitter, int index); + +static yaml_char_t * +yaml_emitter_generate_anchor(yaml_emitter_t *emitter, int anchor_id); + + +/* + * Serialize functions. + */ + +static int +yaml_emitter_dump_node(yaml_emitter_t *emitter, int index); + +static int +yaml_emitter_dump_alias(yaml_emitter_t *emitter, yaml_char_t *anchor); + +static int +yaml_emitter_dump_scalar(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor); + +static int +yaml_emitter_dump_sequence(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor); + +static int +yaml_emitter_dump_mapping(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor); + +/* + * Issue a STREAM-START event. + */ + +YAML_DECLARE(int) +yaml_emitter_open(yaml_emitter_t *emitter) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + assert(emitter); /* Non-NULL emitter object is required. */ + assert(!emitter->opened); /* Emitter should not be opened yet. */ + + STREAM_START_EVENT_INIT(event, YAML_ANY_ENCODING, mark, mark); + + if (!yaml_emitter_emit(emitter, &event)) { + return 0; + } + + emitter->opened = 1; + + return 1; +} + +/* + * Issue a STREAM-END event. + */ + +YAML_DECLARE(int) +yaml_emitter_close(yaml_emitter_t *emitter) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + assert(emitter); /* Non-NULL emitter object is required. */ + assert(emitter->opened); /* Emitter should be opened. */ + + if (emitter->closed) return 1; + + STREAM_END_EVENT_INIT(event, mark, mark); + + if (!yaml_emitter_emit(emitter, &event)) { + return 0; + } + + emitter->closed = 1; + + return 1; +} + +/* + * Dump a YAML document. + */ + +YAML_DECLARE(int) +yaml_emitter_dump(yaml_emitter_t *emitter, yaml_document_t *document) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + assert(emitter); /* Non-NULL emitter object is required. */ + assert(document); /* Non-NULL emitter object is expected. */ + + emitter->document = document; + + if (!emitter->opened) { + if (!yaml_emitter_open(emitter)) goto error; + } + + if (STACK_EMPTY(emitter, document->nodes)) { + if (!yaml_emitter_close(emitter)) goto error; + yaml_emitter_delete_document_and_anchors(emitter); + return 1; + } + + assert(emitter->opened); /* Emitter should be opened. */ + + emitter->anchors = yaml_malloc(sizeof(*(emitter->anchors)) + * (document->nodes.top - document->nodes.start)); + if (!emitter->anchors) goto error; + memset(emitter->anchors, 0, sizeof(*(emitter->anchors)) + * (document->nodes.top - document->nodes.start)); + + DOCUMENT_START_EVENT_INIT(event, document->version_directive, + document->tag_directives.start, document->tag_directives.end, + document->start_implicit, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) goto error; + + yaml_emitter_anchor_node(emitter, 1); + if (!yaml_emitter_dump_node(emitter, 1)) goto error; + + DOCUMENT_END_EVENT_INIT(event, document->end_implicit, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) goto error; + + yaml_emitter_delete_document_and_anchors(emitter); + + return 1; + +error: + + yaml_emitter_delete_document_and_anchors(emitter); + + return 0; +} + +/* + * Clean up the emitter object after a document is dumped. + */ + +static void +yaml_emitter_delete_document_and_anchors(yaml_emitter_t *emitter) +{ + int index; + + if (!emitter->anchors) { + yaml_document_delete(emitter->document); + emitter->document = NULL; + return; + } + + for (index = 0; emitter->document->nodes.start + index + < emitter->document->nodes.top; index ++) { + yaml_node_t node = emitter->document->nodes.start[index]; + if (!emitter->anchors[index].serialized) { + yaml_free(node.tag); + if (node.type == YAML_SCALAR_NODE) { + yaml_free(node.data.scalar.value); + } + } + if (node.type == YAML_SEQUENCE_NODE) { + STACK_DEL(emitter, node.data.sequence.items); + } + if (node.type == YAML_MAPPING_NODE) { + STACK_DEL(emitter, node.data.mapping.pairs); + } + } + + STACK_DEL(emitter, emitter->document->nodes); + yaml_free(emitter->anchors); + + emitter->anchors = NULL; + emitter->last_anchor_id = 0; + emitter->document = NULL; +} + +/* + * Check the references of a node and assign the anchor id if needed. + */ + +static void +yaml_emitter_anchor_node(yaml_emitter_t *emitter, int index) +{ + yaml_node_t *node = emitter->document->nodes.start + index - 1; + yaml_node_item_t *item; + yaml_node_pair_t *pair; + + emitter->anchors[index-1].references ++; + + if (emitter->anchors[index-1].references == 1) { + switch (node->type) { + case YAML_SEQUENCE_NODE: + for (item = node->data.sequence.items.start; + item < node->data.sequence.items.top; item ++) { + yaml_emitter_anchor_node(emitter, *item); + } + break; + case YAML_MAPPING_NODE: + for (pair = node->data.mapping.pairs.start; + pair < node->data.mapping.pairs.top; pair ++) { + yaml_emitter_anchor_node(emitter, pair->key); + yaml_emitter_anchor_node(emitter, pair->value); + } + break; + default: + break; + } + } + + else if (emitter->anchors[index-1].references == 2) { + emitter->anchors[index-1].anchor = (++ emitter->last_anchor_id); + } +} + +/* + * Generate a textual representation for an anchor. + */ + +#define ANCHOR_TEMPLATE "id%03d" +#define ANCHOR_TEMPLATE_LENGTH 16 + +static yaml_char_t * +yaml_emitter_generate_anchor(yaml_emitter_t *emitter, int anchor_id) +{ + yaml_char_t *anchor = yaml_malloc(ANCHOR_TEMPLATE_LENGTH); + + if (!anchor) return NULL; + + sprintf((char *)anchor, ANCHOR_TEMPLATE, anchor_id); + + return anchor; +} + +/* + * Serialize a node. + */ + +static int +yaml_emitter_dump_node(yaml_emitter_t *emitter, int index) +{ + yaml_node_t *node = emitter->document->nodes.start + index - 1; + int anchor_id = emitter->anchors[index-1].anchor; + yaml_char_t *anchor = NULL; + + if (anchor_id) { + anchor = yaml_emitter_generate_anchor(emitter, anchor_id); + if (!anchor) return 0; + } + + if (emitter->anchors[index-1].serialized) { + return yaml_emitter_dump_alias(emitter, anchor); + } + + emitter->anchors[index-1].serialized = 1; + + switch (node->type) { + case YAML_SCALAR_NODE: + return yaml_emitter_dump_scalar(emitter, node, anchor); + case YAML_SEQUENCE_NODE: + return yaml_emitter_dump_sequence(emitter, node, anchor); + case YAML_MAPPING_NODE: + return yaml_emitter_dump_mapping(emitter, node, anchor); + default: + assert(0); /* Could not happen. */ + break; + } + + return 0; /* Could not happen. */ +} + +/* + * Serialize an alias. + */ + +static int +yaml_emitter_dump_alias(yaml_emitter_t *emitter, yaml_char_t *anchor) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + ALIAS_EVENT_INIT(event, anchor, mark, mark); + + return yaml_emitter_emit(emitter, &event); +} + +/* + * Serialize a scalar. + */ + +static int +yaml_emitter_dump_scalar(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + int plain_implicit = (strcmp((char *)node->tag, + YAML_DEFAULT_SCALAR_TAG) == 0); + int quoted_implicit = (strcmp((char *)node->tag, + YAML_DEFAULT_SCALAR_TAG) == 0); + + SCALAR_EVENT_INIT(event, anchor, node->tag, node->data.scalar.value, + node->data.scalar.length, plain_implicit, quoted_implicit, + node->data.scalar.style, mark, mark); + + return yaml_emitter_emit(emitter, &event); +} + +/* + * Serialize a sequence. + */ + +static int +yaml_emitter_dump_sequence(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + int implicit = (strcmp((char *)node->tag, YAML_DEFAULT_SEQUENCE_TAG) == 0); + + yaml_node_item_t *item; + + SEQUENCE_START_EVENT_INIT(event, anchor, node->tag, implicit, + node->data.sequence.style, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) return 0; + + for (item = node->data.sequence.items.start; + item < node->data.sequence.items.top; item ++) { + if (!yaml_emitter_dump_node(emitter, *item)) return 0; + } + + SEQUENCE_END_EVENT_INIT(event, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) return 0; + + return 1; +} + +/* + * Serialize a mapping. + */ + +static int +yaml_emitter_dump_mapping(yaml_emitter_t *emitter, yaml_node_t *node, + yaml_char_t *anchor) +{ + yaml_event_t event; + yaml_mark_t mark = { 0, 0, 0 }; + + int implicit = (strcmp((char *)node->tag, YAML_DEFAULT_MAPPING_TAG) == 0); + + yaml_node_pair_t *pair; + + MAPPING_START_EVENT_INIT(event, anchor, node->tag, implicit, + node->data.mapping.style, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) return 0; + + for (pair = node->data.mapping.pairs.start; + pair < node->data.mapping.pairs.top; pair ++) { + if (!yaml_emitter_dump_node(emitter, pair->key)) return 0; + if (!yaml_emitter_dump_node(emitter, pair->value)) return 0; + } + + MAPPING_END_EVENT_INIT(event, mark, mark); + if (!yaml_emitter_emit(emitter, &event)) return 0; + + return 1; +} + diff --git a/ext/psych/yaml/emitter.c b/ext/psych/yaml/emitter.c new file mode 100644 index 0000000..bf84faf --- /dev/null +++ b/ext/psych/yaml/emitter.c @@ -0,0 +1,2329 @@ + +#include "yaml_private.h" + +/* + * Flush the buffer if needed. + */ + +#define FLUSH(emitter) \ + ((emitter->buffer.pointer+5 < emitter->buffer.end) \ + || yaml_emitter_flush(emitter)) + +/* + * Put a character to the output buffer. + */ + +#define PUT(emitter,value) \ + (FLUSH(emitter) \ + && (*(emitter->buffer.pointer++) = (yaml_char_t)(value), \ + emitter->column ++, \ + 1)) + +/* + * Put a line break to the output buffer. + */ + +#define PUT_BREAK(emitter) \ + (FLUSH(emitter) \ + && ((emitter->line_break == YAML_CR_BREAK ? \ + (*(emitter->buffer.pointer++) = (yaml_char_t) '\r') : \ + emitter->line_break == YAML_LN_BREAK ? \ + (*(emitter->buffer.pointer++) = (yaml_char_t) '\n') : \ + emitter->line_break == YAML_CRLN_BREAK ? \ + (*(emitter->buffer.pointer++) = (yaml_char_t) '\r', \ + *(emitter->buffer.pointer++) = (yaml_char_t) '\n') : 0), \ + emitter->column = 0, \ + emitter->line ++, \ + 1)) + +/* + * Copy a character from a string into buffer. + */ + +#define WRITE(emitter,string) \ + (FLUSH(emitter) \ + && (COPY(emitter->buffer,string), \ + emitter->column ++, \ + 1)) + +/* + * Copy a line break character from a string into buffer. + */ + +#define WRITE_BREAK(emitter,string) \ + (FLUSH(emitter) \ + && (CHECK(string,'\n') ? \ + ((void)PUT_BREAK(emitter), \ + string.pointer ++, \ + 1) : \ + (COPY(emitter->buffer,string), \ + emitter->column = 0, \ + emitter->line ++, \ + 1))) + +/* + * API functions. + */ + +YAML_DECLARE(int) +yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event); + +/* + * Utility functions. + */ + +static int +yaml_emitter_set_emitter_error(yaml_emitter_t *emitter, const char *problem); + +static int +yaml_emitter_need_more_events(yaml_emitter_t *emitter); + +static int +yaml_emitter_append_tag_directive(yaml_emitter_t *emitter, + yaml_tag_directive_t value, int allow_duplicates); + +static int +yaml_emitter_increase_indent(yaml_emitter_t *emitter, + int flow, int indentless); + +/* + * State functions. + */ + +static int +yaml_emitter_state_machine(yaml_emitter_t *emitter, yaml_event_t *event); + +static int +yaml_emitter_emit_stream_start(yaml_emitter_t *emitter, + yaml_event_t *event); + +static int +yaml_emitter_emit_document_start(yaml_emitter_t *emitter, + yaml_event_t *event, int first); + +static int +yaml_emitter_emit_document_content(yaml_emitter_t *emitter, + yaml_event_t *event); + +static int +yaml_emitter_emit_document_end(yaml_emitter_t *emitter, + yaml_event_t *event); + +static int +yaml_emitter_emit_flow_sequence_item(yaml_emitter_t *emitter, + yaml_event_t *event, int first); + +static int +yaml_emitter_emit_flow_mapping_key(yaml_emitter_t *emitter, + yaml_event_t *event, int first); + +static int +yaml_emitter_emit_flow_mapping_value(yaml_emitter_t *emitter, + yaml_event_t *event, int simple); + +static int +yaml_emitter_emit_block_sequence_item(yaml_emitter_t *emitter, + yaml_event_t *event, int first); + +static int +yaml_emitter_emit_block_mapping_key(yaml_emitter_t *emitter, + yaml_event_t *event, int first); + +static int +yaml_emitter_emit_block_mapping_value(yaml_emitter_t *emitter, + yaml_event_t *event, int simple); + +static int +yaml_emitter_emit_node(yaml_emitter_t *emitter, yaml_event_t *event, + int root, int sequence, int mapping, int simple_key); + +static int +yaml_emitter_emit_alias(yaml_emitter_t *emitter, yaml_event_t *event); + +static int +yaml_emitter_emit_scalar(yaml_emitter_t *emitter, yaml_event_t *event); + +static int +yaml_emitter_emit_sequence_start(yaml_emitter_t *emitter, yaml_event_t *event); + +static int +yaml_emitter_emit_mapping_start(yaml_emitter_t *emitter, yaml_event_t *event); + +/* + * Checkers. + */ + +static int +yaml_emitter_check_empty_document(yaml_emitter_t *emitter); + +static int +yaml_emitter_check_empty_sequence(yaml_emitter_t *emitter); + +static int +yaml_emitter_check_empty_mapping(yaml_emitter_t *emitter); + +static int +yaml_emitter_check_simple_key(yaml_emitter_t *emitter); + +static int +yaml_emitter_select_scalar_style(yaml_emitter_t *emitter, yaml_event_t *event); + +/* + * Processors. + */ + +static int +yaml_emitter_process_anchor(yaml_emitter_t *emitter); + +static int +yaml_emitter_process_tag(yaml_emitter_t *emitter); + +static int +yaml_emitter_process_scalar(yaml_emitter_t *emitter); + +/* + * Analyzers. + */ + +static int +yaml_emitter_analyze_version_directive(yaml_emitter_t *emitter, + yaml_version_directive_t version_directive); + +static int +yaml_emitter_analyze_tag_directive(yaml_emitter_t *emitter, + yaml_tag_directive_t tag_directive); + +static int +yaml_emitter_analyze_anchor(yaml_emitter_t *emitter, + yaml_char_t *anchor, int alias); + +static int +yaml_emitter_analyze_tag(yaml_emitter_t *emitter, + yaml_char_t *tag); + +static int +yaml_emitter_analyze_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length); + +static int +yaml_emitter_analyze_event(yaml_emitter_t *emitter, + yaml_event_t *event); + +/* + * Writers. + */ + +static int +yaml_emitter_write_bom(yaml_emitter_t *emitter); + +static int +yaml_emitter_write_indent(yaml_emitter_t *emitter); + +static int +yaml_emitter_write_indicator(yaml_emitter_t *emitter, + const char *indicator, int need_whitespace, + int is_whitespace, int is_indention); + +static int +yaml_emitter_write_anchor(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length); + +static int +yaml_emitter_write_tag_handle(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length); + +static int +yaml_emitter_write_tag_content(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int need_whitespace); + +static int +yaml_emitter_write_plain_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks); + +static int +yaml_emitter_write_single_quoted_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks); + +static int +yaml_emitter_write_double_quoted_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks); + +static int +yaml_emitter_write_block_scalar_hints(yaml_emitter_t *emitter, + yaml_string_t string); + +static int +yaml_emitter_write_literal_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length); + +static int +yaml_emitter_write_folded_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length); + +/* + * Set an emitter error and return 0. + */ + +static int +yaml_emitter_set_emitter_error(yaml_emitter_t *emitter, const char *problem) +{ + emitter->error = YAML_EMITTER_ERROR; + emitter->problem = problem; + + return 0; +} + +/* + * Emit an event. + */ + +YAML_DECLARE(int) +yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event) +{ + if (!ENQUEUE(emitter, emitter->events, *event)) { + yaml_event_delete(event); + return 0; + } + + while (!yaml_emitter_need_more_events(emitter)) { + if (!yaml_emitter_analyze_event(emitter, emitter->events.head)) + return 0; + if (!yaml_emitter_state_machine(emitter, emitter->events.head)) + return 0; + yaml_event_delete(&DEQUEUE(emitter, emitter->events)); + } + + return 1; +} + +/* + * Check if we need to accumulate more events before emitting. + * + * We accumulate extra + * - 1 event for DOCUMENT-START + * - 2 events for SEQUENCE-START + * - 3 events for MAPPING-START + */ + +static int +yaml_emitter_need_more_events(yaml_emitter_t *emitter) +{ + int level = 0; + int accumulate = 0; + yaml_event_t *event; + + if (QUEUE_EMPTY(emitter, emitter->events)) + return 1; + + switch (emitter->events.head->type) { + case YAML_DOCUMENT_START_EVENT: + accumulate = 1; + break; + case YAML_SEQUENCE_START_EVENT: + accumulate = 2; + break; + case YAML_MAPPING_START_EVENT: + accumulate = 3; + break; + default: + return 0; + } + + if (emitter->events.tail - emitter->events.head > accumulate) + return 0; + + for (event = emitter->events.head; event != emitter->events.tail; event ++) { + switch (event->type) { + case YAML_STREAM_START_EVENT: + case YAML_DOCUMENT_START_EVENT: + case YAML_SEQUENCE_START_EVENT: + case YAML_MAPPING_START_EVENT: + level += 1; + break; + case YAML_STREAM_END_EVENT: + case YAML_DOCUMENT_END_EVENT: + case YAML_SEQUENCE_END_EVENT: + case YAML_MAPPING_END_EVENT: + level -= 1; + break; + default: + break; + } + if (!level) + return 0; + } + + return 1; +} + +/* + * Append a directive to the directives stack. + */ + +static int +yaml_emitter_append_tag_directive(yaml_emitter_t *emitter, + yaml_tag_directive_t value, int allow_duplicates) +{ + yaml_tag_directive_t *tag_directive; + yaml_tag_directive_t copy = { NULL, NULL }; + + for (tag_directive = emitter->tag_directives.start; + tag_directive != emitter->tag_directives.top; tag_directive ++) { + if (strcmp((char *)value.handle, (char *)tag_directive->handle) == 0) { + if (allow_duplicates) + return 1; + return yaml_emitter_set_emitter_error(emitter, + "duplicate %TAG directive"); + } + } + + copy.handle = yaml_strdup(value.handle); + copy.prefix = yaml_strdup(value.prefix); + if (!copy.handle || !copy.prefix) { + emitter->error = YAML_MEMORY_ERROR; + goto error; + } + + if (!PUSH(emitter, emitter->tag_directives, copy)) + goto error; + + return 1; + +error: + yaml_free(copy.handle); + yaml_free(copy.prefix); + return 0; +} + +/* + * Increase the indentation level. + */ + +static int +yaml_emitter_increase_indent(yaml_emitter_t *emitter, + int flow, int indentless) +{ + if (!PUSH(emitter, emitter->indents, emitter->indent)) + return 0; + + if (emitter->indent < 0) { + emitter->indent = flow ? emitter->best_indent : 0; + } + else if (!indentless) { + emitter->indent += emitter->best_indent; + } + + return 1; +} + +/* + * State dispatcher. + */ + +static int +yaml_emitter_state_machine(yaml_emitter_t *emitter, yaml_event_t *event) +{ + switch (emitter->state) + { + case YAML_EMIT_STREAM_START_STATE: + return yaml_emitter_emit_stream_start(emitter, event); + + case YAML_EMIT_FIRST_DOCUMENT_START_STATE: + return yaml_emitter_emit_document_start(emitter, event, 1); + + case YAML_EMIT_DOCUMENT_START_STATE: + return yaml_emitter_emit_document_start(emitter, event, 0); + + case YAML_EMIT_DOCUMENT_CONTENT_STATE: + return yaml_emitter_emit_document_content(emitter, event); + + case YAML_EMIT_DOCUMENT_END_STATE: + return yaml_emitter_emit_document_end(emitter, event); + + case YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE: + return yaml_emitter_emit_flow_sequence_item(emitter, event, 1); + + case YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE: + return yaml_emitter_emit_flow_sequence_item(emitter, event, 0); + + case YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE: + return yaml_emitter_emit_flow_mapping_key(emitter, event, 1); + + case YAML_EMIT_FLOW_MAPPING_KEY_STATE: + return yaml_emitter_emit_flow_mapping_key(emitter, event, 0); + + case YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE: + return yaml_emitter_emit_flow_mapping_value(emitter, event, 1); + + case YAML_EMIT_FLOW_MAPPING_VALUE_STATE: + return yaml_emitter_emit_flow_mapping_value(emitter, event, 0); + + case YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE: + return yaml_emitter_emit_block_sequence_item(emitter, event, 1); + + case YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE: + return yaml_emitter_emit_block_sequence_item(emitter, event, 0); + + case YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE: + return yaml_emitter_emit_block_mapping_key(emitter, event, 1); + + case YAML_EMIT_BLOCK_MAPPING_KEY_STATE: + return yaml_emitter_emit_block_mapping_key(emitter, event, 0); + + case YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE: + return yaml_emitter_emit_block_mapping_value(emitter, event, 1); + + case YAML_EMIT_BLOCK_MAPPING_VALUE_STATE: + return yaml_emitter_emit_block_mapping_value(emitter, event, 0); + + case YAML_EMIT_END_STATE: + return yaml_emitter_set_emitter_error(emitter, + "expected nothing after STREAM-END"); + + default: + assert(1); /* Invalid state. */ + } + + return 0; +} + +/* + * Expect STREAM-START. + */ + +static int +yaml_emitter_emit_stream_start(yaml_emitter_t *emitter, + yaml_event_t *event) +{ + if (event->type == YAML_STREAM_START_EVENT) + { + if (!emitter->encoding) { + emitter->encoding = event->data.stream_start.encoding; + } + + if (!emitter->encoding) { + emitter->encoding = YAML_UTF8_ENCODING; + } + + if (emitter->best_indent < 2 || emitter->best_indent > 9) { + emitter->best_indent = 2; + } + + if (emitter->best_width >= 0 + && emitter->best_width <= emitter->best_indent*2) { + emitter->best_width = 80; + } + + if (emitter->best_width < 0) { + emitter->best_width = INT_MAX; + } + + if (!emitter->line_break) { + emitter->line_break = YAML_LN_BREAK; + } + + emitter->indent = -1; + + emitter->line = 0; + emitter->column = 0; + emitter->whitespace = 1; + emitter->indention = 1; + + if (emitter->encoding != YAML_UTF8_ENCODING) { + if (!yaml_emitter_write_bom(emitter)) + return 0; + } + + emitter->state = YAML_EMIT_FIRST_DOCUMENT_START_STATE; + + return 1; + } + + return yaml_emitter_set_emitter_error(emitter, + "expected STREAM-START"); +} + +/* + * Expect DOCUMENT-START or STREAM-END. + */ + +static int +yaml_emitter_emit_document_start(yaml_emitter_t *emitter, + yaml_event_t *event, int first) +{ + if (event->type == YAML_DOCUMENT_START_EVENT) + { + yaml_tag_directive_t default_tag_directives[] = { + {(yaml_char_t *)"!", (yaml_char_t *)"!"}, + {(yaml_char_t *)"!!", (yaml_char_t *)"tag:yaml.org,2002:"}, + {NULL, NULL} + }; + yaml_tag_directive_t *tag_directive; + int implicit; + + if (event->data.document_start.version_directive) { + if (!yaml_emitter_analyze_version_directive(emitter, + *event->data.document_start.version_directive)) + return 0; + } + + for (tag_directive = event->data.document_start.tag_directives.start; + tag_directive != event->data.document_start.tag_directives.end; + tag_directive ++) { + if (!yaml_emitter_analyze_tag_directive(emitter, *tag_directive)) + return 0; + if (!yaml_emitter_append_tag_directive(emitter, *tag_directive, 0)) + return 0; + } + + for (tag_directive = default_tag_directives; + tag_directive->handle; tag_directive ++) { + if (!yaml_emitter_append_tag_directive(emitter, *tag_directive, 1)) + return 0; + } + + implicit = event->data.document_start.implicit; + if (!first || emitter->canonical) { + implicit = 0; + } + + if ((event->data.document_start.version_directive || + (event->data.document_start.tag_directives.start + != event->data.document_start.tag_directives.end)) && + emitter->open_ended) + { + if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + + if (event->data.document_start.version_directive) { + implicit = 0; + if (!yaml_emitter_write_indicator(emitter, "%YAML", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_indicator(emitter, "1.1", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + + if (event->data.document_start.tag_directives.start + != event->data.document_start.tag_directives.end) { + implicit = 0; + for (tag_directive = event->data.document_start.tag_directives.start; + tag_directive != event->data.document_start.tag_directives.end; + tag_directive ++) { + if (!yaml_emitter_write_indicator(emitter, "%TAG", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_tag_handle(emitter, tag_directive->handle, + strlen((char *)tag_directive->handle))) + return 0; + if (!yaml_emitter_write_tag_content(emitter, tag_directive->prefix, + strlen((char *)tag_directive->prefix), 1)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + } + + if (yaml_emitter_check_empty_document(emitter)) { + implicit = 0; + } + + if (!implicit) { + if (!yaml_emitter_write_indent(emitter)) + return 0; + if (!yaml_emitter_write_indicator(emitter, "---", 1, 0, 0)) + return 0; + if (emitter->canonical) { + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + } + + emitter->state = YAML_EMIT_DOCUMENT_CONTENT_STATE; + + return 1; + } + + else if (event->type == YAML_STREAM_END_EVENT) + { + if (emitter->open_ended) + { + if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + + if (!yaml_emitter_flush(emitter)) + return 0; + + emitter->state = YAML_EMIT_END_STATE; + + return 1; + } + + return yaml_emitter_set_emitter_error(emitter, + "expected DOCUMENT-START or STREAM-END"); +} + +/* + * Expect the root node. + */ + +static int +yaml_emitter_emit_document_content(yaml_emitter_t *emitter, + yaml_event_t *event) +{ + if (!PUSH(emitter, emitter->states, YAML_EMIT_DOCUMENT_END_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 1, 0, 0, 0); +} + +/* + * Expect DOCUMENT-END. + */ + +static int +yaml_emitter_emit_document_end(yaml_emitter_t *emitter, + yaml_event_t *event) +{ + if (event->type == YAML_DOCUMENT_END_EVENT) + { + if (!yaml_emitter_write_indent(emitter)) + return 0; + if (!event->data.document_end.implicit) { + if (!yaml_emitter_write_indicator(emitter, "...", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + if (!yaml_emitter_flush(emitter)) + return 0; + + emitter->state = YAML_EMIT_DOCUMENT_START_STATE; + + while (!STACK_EMPTY(emitter, emitter->tag_directives)) { + yaml_tag_directive_t tag_directive = POP(emitter, + emitter->tag_directives); + yaml_free(tag_directive.handle); + yaml_free(tag_directive.prefix); + } + + return 1; + } + + return yaml_emitter_set_emitter_error(emitter, + "expected DOCUMENT-END"); +} + +/* + * + * Expect a flow item node. + */ + +static int +yaml_emitter_emit_flow_sequence_item(yaml_emitter_t *emitter, + yaml_event_t *event, int first) +{ + if (first) + { + if (!yaml_emitter_write_indicator(emitter, "[", 1, 1, 0)) + return 0; + if (!yaml_emitter_increase_indent(emitter, 1, 0)) + return 0; + emitter->flow_level ++; + } + + if (event->type == YAML_SEQUENCE_END_EVENT) + { + emitter->flow_level --; + emitter->indent = POP(emitter, emitter->indents); + if (emitter->canonical && !first) { + if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + if (!yaml_emitter_write_indicator(emitter, "]", 0, 0, 0)) + return 0; + emitter->state = POP(emitter, emitter->states); + + return 1; + } + + if (!first) { + if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) + return 0; + } + + if (emitter->canonical || emitter->column > emitter->best_width) { + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + if (!PUSH(emitter, emitter->states, YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 1, 0, 0); +} + +/* + * Expect a flow key node. + */ + +static int +yaml_emitter_emit_flow_mapping_key(yaml_emitter_t *emitter, + yaml_event_t *event, int first) +{ + if (first) + { + if (!yaml_emitter_write_indicator(emitter, "{", 1, 1, 0)) + return 0; + if (!yaml_emitter_increase_indent(emitter, 1, 0)) + return 0; + emitter->flow_level ++; + } + + if (event->type == YAML_MAPPING_END_EVENT) + { + emitter->flow_level --; + emitter->indent = POP(emitter, emitter->indents); + if (emitter->canonical && !first) { + if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) + return 0; + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + if (!yaml_emitter_write_indicator(emitter, "}", 0, 0, 0)) + return 0; + emitter->state = POP(emitter, emitter->states); + + return 1; + } + + if (!first) { + if (!yaml_emitter_write_indicator(emitter, ",", 0, 0, 0)) + return 0; + } + if (emitter->canonical || emitter->column > emitter->best_width) { + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + + if (!emitter->canonical && yaml_emitter_check_simple_key(emitter)) + { + if (!PUSH(emitter, emitter->states, + YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 1); + } + else + { + if (!yaml_emitter_write_indicator(emitter, "?", 1, 0, 0)) + return 0; + if (!PUSH(emitter, emitter->states, + YAML_EMIT_FLOW_MAPPING_VALUE_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); + } +} + +/* + * Expect a flow value node. + */ + +static int +yaml_emitter_emit_flow_mapping_value(yaml_emitter_t *emitter, + yaml_event_t *event, int simple) +{ + if (simple) { + if (!yaml_emitter_write_indicator(emitter, ":", 0, 0, 0)) + return 0; + } + else { + if (emitter->canonical || emitter->column > emitter->best_width) { + if (!yaml_emitter_write_indent(emitter)) + return 0; + } + if (!yaml_emitter_write_indicator(emitter, ":", 1, 0, 0)) + return 0; + } + if (!PUSH(emitter, emitter->states, YAML_EMIT_FLOW_MAPPING_KEY_STATE)) + return 0; + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); +} + +/* + * Expect a block item node. + */ + +static int +yaml_emitter_emit_block_sequence_item(yaml_emitter_t *emitter, + yaml_event_t *event, int first) +{ + if (first) + { + if (!yaml_emitter_increase_indent(emitter, 0, + (emitter->mapping_context && !emitter->indention))) + return 0; + } + + if (event->type == YAML_SEQUENCE_END_EVENT) + { + emitter->indent = POP(emitter, emitter->indents); + emitter->state = POP(emitter, emitter->states); + + return 1; + } + + if (!yaml_emitter_write_indent(emitter)) + return 0; + if (!yaml_emitter_write_indicator(emitter, "-", 1, 0, 1)) + return 0; + if (!PUSH(emitter, emitter->states, + YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 1, 0, 0); +} + +/* + * Expect a block key node. + */ + +static int +yaml_emitter_emit_block_mapping_key(yaml_emitter_t *emitter, + yaml_event_t *event, int first) +{ + if (first) + { + if (!yaml_emitter_increase_indent(emitter, 0, 0)) + return 0; + } + + if (event->type == YAML_MAPPING_END_EVENT) + { + emitter->indent = POP(emitter, emitter->indents); + emitter->state = POP(emitter, emitter->states); + + return 1; + } + + if (!yaml_emitter_write_indent(emitter)) + return 0; + + if (yaml_emitter_check_simple_key(emitter)) + { + if (!PUSH(emitter, emitter->states, + YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 1); + } + else + { + if (!yaml_emitter_write_indicator(emitter, "?", 1, 0, 1)) + return 0; + if (!PUSH(emitter, emitter->states, + YAML_EMIT_BLOCK_MAPPING_VALUE_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); + } +} + +/* + * Expect a block value node. + */ + +static int +yaml_emitter_emit_block_mapping_value(yaml_emitter_t *emitter, + yaml_event_t *event, int simple) +{ + if (simple) { + if (!yaml_emitter_write_indicator(emitter, ":", 0, 0, 0)) + return 0; + } + else { + if (!yaml_emitter_write_indent(emitter)) + return 0; + if (!yaml_emitter_write_indicator(emitter, ":", 1, 0, 1)) + return 0; + } + if (!PUSH(emitter, emitter->states, + YAML_EMIT_BLOCK_MAPPING_KEY_STATE)) + return 0; + + return yaml_emitter_emit_node(emitter, event, 0, 0, 1, 0); +} + +/* + * Expect a node. + */ + +static int +yaml_emitter_emit_node(yaml_emitter_t *emitter, yaml_event_t *event, + int root, int sequence, int mapping, int simple_key) +{ + emitter->root_context = root; + emitter->sequence_context = sequence; + emitter->mapping_context = mapping; + emitter->simple_key_context = simple_key; + + switch (event->type) + { + case YAML_ALIAS_EVENT: + return yaml_emitter_emit_alias(emitter, event); + + case YAML_SCALAR_EVENT: + return yaml_emitter_emit_scalar(emitter, event); + + case YAML_SEQUENCE_START_EVENT: + return yaml_emitter_emit_sequence_start(emitter, event); + + case YAML_MAPPING_START_EVENT: + return yaml_emitter_emit_mapping_start(emitter, event); + + default: + return yaml_emitter_set_emitter_error(emitter, + "expected SCALAR, SEQUENCE-START, MAPPING-START, or ALIAS"); + } + + return 0; +} + +/* + * Expect ALIAS. + */ + +static int +yaml_emitter_emit_alias(yaml_emitter_t *emitter, yaml_event_t *event) +{ + if (!yaml_emitter_process_anchor(emitter)) + return 0; + emitter->state = POP(emitter, emitter->states); + + return 1; +} + +/* + * Expect SCALAR. + */ + +static int +yaml_emitter_emit_scalar(yaml_emitter_t *emitter, yaml_event_t *event) +{ + if (!yaml_emitter_select_scalar_style(emitter, event)) + return 0; + if (!yaml_emitter_process_anchor(emitter)) + return 0; + if (!yaml_emitter_process_tag(emitter)) + return 0; + if (!yaml_emitter_increase_indent(emitter, 1, 0)) + return 0; + if (!yaml_emitter_process_scalar(emitter)) + return 0; + emitter->indent = POP(emitter, emitter->indents); + emitter->state = POP(emitter, emitter->states); + + return 1; +} + +/* + * Expect SEQUENCE-START. + */ + +static int +yaml_emitter_emit_sequence_start(yaml_emitter_t *emitter, yaml_event_t *event) +{ + if (!yaml_emitter_process_anchor(emitter)) + return 0; + if (!yaml_emitter_process_tag(emitter)) + return 0; + + if (emitter->flow_level || emitter->canonical + || event->data.sequence_start.style == YAML_FLOW_SEQUENCE_STYLE + || yaml_emitter_check_empty_sequence(emitter)) { + emitter->state = YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE; + } + else { + emitter->state = YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE; + } + + return 1; +} + +/* + * Expect MAPPING-START. + */ + +static int +yaml_emitter_emit_mapping_start(yaml_emitter_t *emitter, yaml_event_t *event) +{ + if (!yaml_emitter_process_anchor(emitter)) + return 0; + if (!yaml_emitter_process_tag(emitter)) + return 0; + + if (emitter->flow_level || emitter->canonical + || event->data.mapping_start.style == YAML_FLOW_MAPPING_STYLE + || yaml_emitter_check_empty_mapping(emitter)) { + emitter->state = YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE; + } + else { + emitter->state = YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE; + } + + return 1; +} + +/* + * Check if the document content is an empty scalar. + */ + +static int +yaml_emitter_check_empty_document(yaml_emitter_t *emitter) +{ + return 0; +} + +/* + * Check if the next events represent an empty sequence. + */ + +static int +yaml_emitter_check_empty_sequence(yaml_emitter_t *emitter) +{ + if (emitter->events.tail - emitter->events.head < 2) + return 0; + + return (emitter->events.head[0].type == YAML_SEQUENCE_START_EVENT + && emitter->events.head[1].type == YAML_SEQUENCE_END_EVENT); +} + +/* + * Check if the next events represent an empty mapping. + */ + +static int +yaml_emitter_check_empty_mapping(yaml_emitter_t *emitter) +{ + if (emitter->events.tail - emitter->events.head < 2) + return 0; + + return (emitter->events.head[0].type == YAML_MAPPING_START_EVENT + && emitter->events.head[1].type == YAML_MAPPING_END_EVENT); +} + +/* + * Check if the next node can be expressed as a simple key. + */ + +static int +yaml_emitter_check_simple_key(yaml_emitter_t *emitter) +{ + yaml_event_t *event = emitter->events.head; + size_t length = 0; + + switch (event->type) + { + case YAML_ALIAS_EVENT: + length += emitter->anchor_data.anchor_length; + break; + + case YAML_SCALAR_EVENT: + if (emitter->scalar_data.multiline) + return 0; + length += emitter->anchor_data.anchor_length + + emitter->tag_data.handle_length + + emitter->tag_data.suffix_length + + emitter->scalar_data.length; + break; + + case YAML_SEQUENCE_START_EVENT: + if (!yaml_emitter_check_empty_sequence(emitter)) + return 0; + length += emitter->anchor_data.anchor_length + + emitter->tag_data.handle_length + + emitter->tag_data.suffix_length; + break; + + case YAML_MAPPING_START_EVENT: + if (!yaml_emitter_check_empty_mapping(emitter)) + return 0; + length += emitter->anchor_data.anchor_length + + emitter->tag_data.handle_length + + emitter->tag_data.suffix_length; + break; + + default: + return 0; + } + + if (length > 128) + return 0; + + return 1; +} + +/* + * Determine an acceptable scalar style. + */ + +static int +yaml_emitter_select_scalar_style(yaml_emitter_t *emitter, yaml_event_t *event) +{ + yaml_scalar_style_t style = event->data.scalar.style; + int no_tag = (!emitter->tag_data.handle && !emitter->tag_data.suffix); + + if (no_tag && !event->data.scalar.plain_implicit + && !event->data.scalar.quoted_implicit) { + return yaml_emitter_set_emitter_error(emitter, + "neither tag nor implicit flags are specified"); + } + + if (style == YAML_ANY_SCALAR_STYLE) + style = YAML_PLAIN_SCALAR_STYLE; + + if (emitter->canonical) + style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; + + if (emitter->simple_key_context && emitter->scalar_data.multiline) + style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; + + if (style == YAML_PLAIN_SCALAR_STYLE) + { + if ((emitter->flow_level && !emitter->scalar_data.flow_plain_allowed) + || (!emitter->flow_level && !emitter->scalar_data.block_plain_allowed)) + style = YAML_SINGLE_QUOTED_SCALAR_STYLE; + if (!emitter->scalar_data.length + && (emitter->flow_level || emitter->simple_key_context)) + style = YAML_SINGLE_QUOTED_SCALAR_STYLE; + if (no_tag && !event->data.scalar.plain_implicit) + style = YAML_SINGLE_QUOTED_SCALAR_STYLE; + } + + if (style == YAML_SINGLE_QUOTED_SCALAR_STYLE) + { + if (!emitter->scalar_data.single_quoted_allowed) + style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; + } + + if (style == YAML_LITERAL_SCALAR_STYLE || style == YAML_FOLDED_SCALAR_STYLE) + { + if (!emitter->scalar_data.block_allowed + || emitter->flow_level || emitter->simple_key_context) + style = YAML_DOUBLE_QUOTED_SCALAR_STYLE; + } + + if (no_tag && !event->data.scalar.quoted_implicit + && style != YAML_PLAIN_SCALAR_STYLE) + { + emitter->tag_data.handle = (yaml_char_t *)"!"; + emitter->tag_data.handle_length = 1; + } + + emitter->scalar_data.style = style; + + return 1; +} + +/* + * Write an achor. + */ + +static int +yaml_emitter_process_anchor(yaml_emitter_t *emitter) +{ + if (!emitter->anchor_data.anchor) + return 1; + + if (!yaml_emitter_write_indicator(emitter, + (emitter->anchor_data.alias ? "*" : "&"), 1, 0, 0)) + return 0; + + return yaml_emitter_write_anchor(emitter, + emitter->anchor_data.anchor, emitter->anchor_data.anchor_length); +} + +/* + * Write a tag. + */ + +static int +yaml_emitter_process_tag(yaml_emitter_t *emitter) +{ + if (!emitter->tag_data.handle && !emitter->tag_data.suffix) + return 1; + + if (emitter->tag_data.handle) + { + if (!yaml_emitter_write_tag_handle(emitter, emitter->tag_data.handle, + emitter->tag_data.handle_length)) + return 0; + if (emitter->tag_data.suffix) { + if (!yaml_emitter_write_tag_content(emitter, emitter->tag_data.suffix, + emitter->tag_data.suffix_length, 0)) + return 0; + } + } + else + { + if (!yaml_emitter_write_indicator(emitter, "!<", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_tag_content(emitter, emitter->tag_data.suffix, + emitter->tag_data.suffix_length, 0)) + return 0; + if (!yaml_emitter_write_indicator(emitter, ">", 0, 0, 0)) + return 0; + } + + return 1; +} + +/* + * Write a scalar. + */ + +static int +yaml_emitter_process_scalar(yaml_emitter_t *emitter) +{ + switch (emitter->scalar_data.style) + { + case YAML_PLAIN_SCALAR_STYLE: + return yaml_emitter_write_plain_scalar(emitter, + emitter->scalar_data.value, emitter->scalar_data.length, + !emitter->simple_key_context); + + case YAML_SINGLE_QUOTED_SCALAR_STYLE: + return yaml_emitter_write_single_quoted_scalar(emitter, + emitter->scalar_data.value, emitter->scalar_data.length, + !emitter->simple_key_context); + + case YAML_DOUBLE_QUOTED_SCALAR_STYLE: + return yaml_emitter_write_double_quoted_scalar(emitter, + emitter->scalar_data.value, emitter->scalar_data.length, + !emitter->simple_key_context); + + case YAML_LITERAL_SCALAR_STYLE: + return yaml_emitter_write_literal_scalar(emitter, + emitter->scalar_data.value, emitter->scalar_data.length); + + case YAML_FOLDED_SCALAR_STYLE: + return yaml_emitter_write_folded_scalar(emitter, + emitter->scalar_data.value, emitter->scalar_data.length); + + default: + assert(1); /* Impossible. */ + } + + return 0; +} + +/* + * Check if a %YAML directive is valid. + */ + +static int +yaml_emitter_analyze_version_directive(yaml_emitter_t *emitter, + yaml_version_directive_t version_directive) +{ + if (version_directive.major != 1 || version_directive.minor != 1) { + return yaml_emitter_set_emitter_error(emitter, + "incompatible %YAML directive"); + } + + return 1; +} + +/* + * Check if a %TAG directive is valid. + */ + +static int +yaml_emitter_analyze_tag_directive(yaml_emitter_t *emitter, + yaml_tag_directive_t tag_directive) +{ + yaml_string_t handle; + yaml_string_t prefix; + size_t handle_length; + size_t prefix_length; + + handle_length = strlen((char *)tag_directive.handle); + prefix_length = strlen((char *)tag_directive.prefix); + STRING_ASSIGN(handle, tag_directive.handle, handle_length); + STRING_ASSIGN(prefix, tag_directive.prefix, prefix_length); + + if (handle.start == handle.end) { + return yaml_emitter_set_emitter_error(emitter, + "tag handle must not be empty"); + } + + if (handle.start[0] != '!') { + return yaml_emitter_set_emitter_error(emitter, + "tag handle must start with '!'"); + } + + if (handle.end[-1] != '!') { + return yaml_emitter_set_emitter_error(emitter, + "tag handle must end with '!'"); + } + + handle.pointer ++; + + while (handle.pointer < handle.end-1) { + if (!IS_ALPHA(handle)) { + return yaml_emitter_set_emitter_error(emitter, + "tag handle must contain alphanumerical characters only"); + } + MOVE(handle); + } + + if (prefix.start == prefix.end) { + return yaml_emitter_set_emitter_error(emitter, + "tag prefix must not be empty"); + } + + return 1; +} + +/* + * Check if an anchor is valid. + */ + +static int +yaml_emitter_analyze_anchor(yaml_emitter_t *emitter, + yaml_char_t *anchor, int alias) +{ + size_t anchor_length; + yaml_string_t string; + + anchor_length = strlen((char *)anchor); + STRING_ASSIGN(string, anchor, anchor_length); + + if (string.start == string.end) { + return yaml_emitter_set_emitter_error(emitter, alias ? + "alias value must not be empty" : + "anchor value must not be empty"); + } + + while (string.pointer != string.end) { + if (!IS_ALPHA(string)) { + return yaml_emitter_set_emitter_error(emitter, alias ? + "alias value must contain alphanumerical characters only" : + "anchor value must contain alphanumerical characters only"); + } + MOVE(string); + } + + emitter->anchor_data.anchor = string.start; + emitter->anchor_data.anchor_length = string.end - string.start; + emitter->anchor_data.alias = alias; + + return 1; +} + +/* + * Check if a tag is valid. + */ + +static int +yaml_emitter_analyze_tag(yaml_emitter_t *emitter, + yaml_char_t *tag) +{ + size_t tag_length; + yaml_string_t string; + yaml_tag_directive_t *tag_directive; + + tag_length = strlen((char *)tag); + STRING_ASSIGN(string, tag, tag_length); + + if (string.start == string.end) { + return yaml_emitter_set_emitter_error(emitter, + "tag value must not be empty"); + } + + for (tag_directive = emitter->tag_directives.start; + tag_directive != emitter->tag_directives.top; tag_directive ++) { + size_t prefix_length = strlen((char *)tag_directive->prefix); + if (prefix_length < (size_t)(string.end - string.start) + && strncmp((char *)tag_directive->prefix, (char *)string.start, + prefix_length) == 0) + { + emitter->tag_data.handle = tag_directive->handle; + emitter->tag_data.handle_length = + strlen((char *)tag_directive->handle); + emitter->tag_data.suffix = string.start + prefix_length; + emitter->tag_data.suffix_length = + (string.end - string.start) - prefix_length; + return 1; + } + } + + emitter->tag_data.suffix = string.start; + emitter->tag_data.suffix_length = string.end - string.start; + + return 1; +} + +/* + * Check if a scalar is valid. + */ + +static int +yaml_emitter_analyze_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length) +{ + yaml_string_t string; + + int block_indicators = 0; + int flow_indicators = 0; + int line_breaks = 0; + int special_characters = 0; + + int leading_space = 0; + int leading_break = 0; + int trailing_space = 0; + int trailing_break = 0; + int break_space = 0; + int space_break = 0; + + int preceeded_by_whitespace = 0; + int followed_by_whitespace = 0; + int previous_space = 0; + int previous_break = 0; + + STRING_ASSIGN(string, value, length); + + emitter->scalar_data.value = value; + emitter->scalar_data.length = length; + + if (string.start == string.end) + { + emitter->scalar_data.multiline = 0; + emitter->scalar_data.flow_plain_allowed = 0; + emitter->scalar_data.block_plain_allowed = 1; + emitter->scalar_data.single_quoted_allowed = 1; + emitter->scalar_data.block_allowed = 0; + + return 1; + } + + if ((CHECK_AT(string, '-', 0) + && CHECK_AT(string, '-', 1) + && CHECK_AT(string, '-', 2)) + || (CHECK_AT(string, '.', 0) + && CHECK_AT(string, '.', 1) + && CHECK_AT(string, '.', 2))) { + block_indicators = 1; + flow_indicators = 1; + } + + preceeded_by_whitespace = 1; + followed_by_whitespace = IS_BLANKZ_AT(string, WIDTH(string)); + + while (string.pointer != string.end) + { + if (string.start == string.pointer) + { + if (CHECK(string, '#') || CHECK(string, ',') + || CHECK(string, '[') || CHECK(string, ']') + || CHECK(string, '{') || CHECK(string, '}') + || CHECK(string, '&') || CHECK(string, '*') + || CHECK(string, '!') || CHECK(string, '|') + || CHECK(string, '>') || CHECK(string, '\'') + || CHECK(string, '"') || CHECK(string, '%') + || CHECK(string, '@') || CHECK(string, '`')) { + flow_indicators = 1; + block_indicators = 1; + } + + if (CHECK(string, '?') || CHECK(string, ':')) { + flow_indicators = 1; + if (followed_by_whitespace) { + block_indicators = 1; + } + } + + if (CHECK(string, '-') && followed_by_whitespace) { + flow_indicators = 1; + block_indicators = 1; + } + } + else + { + if (CHECK(string, ',') || CHECK(string, '?') + || CHECK(string, '[') || CHECK(string, ']') + || CHECK(string, '{') || CHECK(string, '}')) { + flow_indicators = 1; + } + + if (CHECK(string, ':')) { + flow_indicators = 1; + if (followed_by_whitespace) { + block_indicators = 1; + } + } + + if (CHECK(string, '#') && preceeded_by_whitespace) { + flow_indicators = 1; + block_indicators = 1; + } + } + + if (!IS_PRINTABLE(string) + || (!IS_ASCII(string) && !emitter->unicode)) { + special_characters = 1; + } + + if (IS_BREAK(string)) { + line_breaks = 1; + } + + if (IS_SPACE(string)) + { + if (string.start == string.pointer) { + leading_space = 1; + } + if (string.pointer+WIDTH(string) == string.end) { + trailing_space = 1; + } + if (previous_break) { + break_space = 1; + } + previous_space = 1; + previous_break = 0; + } + else if (IS_BREAK(string)) + { + if (string.start == string.pointer) { + leading_break = 1; + } + if (string.pointer+WIDTH(string) == string.end) { + trailing_break = 1; + } + if (previous_space) { + space_break = 1; + } + previous_space = 0; + previous_break = 1; + } + else + { + previous_space = 0; + previous_break = 0; + } + + preceeded_by_whitespace = IS_BLANKZ(string); + MOVE(string); + if (string.pointer != string.end) { + followed_by_whitespace = IS_BLANKZ_AT(string, WIDTH(string)); + } + } + + emitter->scalar_data.multiline = line_breaks; + + emitter->scalar_data.flow_plain_allowed = 1; + emitter->scalar_data.block_plain_allowed = 1; + emitter->scalar_data.single_quoted_allowed = 1; + emitter->scalar_data.block_allowed = 1; + + if (leading_space || leading_break || trailing_space || trailing_break) { + emitter->scalar_data.flow_plain_allowed = 0; + emitter->scalar_data.block_plain_allowed = 0; + } + + if (trailing_space) { + emitter->scalar_data.block_allowed = 0; + } + + if (break_space) { + emitter->scalar_data.flow_plain_allowed = 0; + emitter->scalar_data.block_plain_allowed = 0; + emitter->scalar_data.single_quoted_allowed = 0; + } + + if (space_break || special_characters) { + emitter->scalar_data.flow_plain_allowed = 0; + emitter->scalar_data.block_plain_allowed = 0; + emitter->scalar_data.single_quoted_allowed = 0; + emitter->scalar_data.block_allowed = 0; + } + + if (line_breaks) { + emitter->scalar_data.flow_plain_allowed = 0; + emitter->scalar_data.block_plain_allowed = 0; + } + + if (flow_indicators) { + emitter->scalar_data.flow_plain_allowed = 0; + } + + if (block_indicators) { + emitter->scalar_data.block_plain_allowed = 0; + } + + return 1; +} + +/* + * Check if the event data is valid. + */ + +static int +yaml_emitter_analyze_event(yaml_emitter_t *emitter, + yaml_event_t *event) +{ + emitter->anchor_data.anchor = NULL; + emitter->anchor_data.anchor_length = 0; + emitter->tag_data.handle = NULL; + emitter->tag_data.handle_length = 0; + emitter->tag_data.suffix = NULL; + emitter->tag_data.suffix_length = 0; + emitter->scalar_data.value = NULL; + emitter->scalar_data.length = 0; + + switch (event->type) + { + case YAML_ALIAS_EVENT: + if (!yaml_emitter_analyze_anchor(emitter, + event->data.alias.anchor, 1)) + return 0; + return 1; + + case YAML_SCALAR_EVENT: + if (event->data.scalar.anchor) { + if (!yaml_emitter_analyze_anchor(emitter, + event->data.scalar.anchor, 0)) + return 0; + } + if (event->data.scalar.tag && (emitter->canonical || + (!event->data.scalar.plain_implicit + && !event->data.scalar.quoted_implicit))) { + if (!yaml_emitter_analyze_tag(emitter, event->data.scalar.tag)) + return 0; + } + if (!yaml_emitter_analyze_scalar(emitter, + event->data.scalar.value, event->data.scalar.length)) + return 0; + return 1; + + case YAML_SEQUENCE_START_EVENT: + if (event->data.sequence_start.anchor) { + if (!yaml_emitter_analyze_anchor(emitter, + event->data.sequence_start.anchor, 0)) + return 0; + } + if (event->data.sequence_start.tag && (emitter->canonical || + !event->data.sequence_start.implicit)) { + if (!yaml_emitter_analyze_tag(emitter, + event->data.sequence_start.tag)) + return 0; + } + return 1; + + case YAML_MAPPING_START_EVENT: + if (event->data.mapping_start.anchor) { + if (!yaml_emitter_analyze_anchor(emitter, + event->data.mapping_start.anchor, 0)) + return 0; + } + if (event->data.mapping_start.tag && (emitter->canonical || + !event->data.mapping_start.implicit)) { + if (!yaml_emitter_analyze_tag(emitter, + event->data.mapping_start.tag)) + return 0; + } + return 1; + + default: + return 1; + } +} + +/* + * Write the BOM character. + */ + +static int +yaml_emitter_write_bom(yaml_emitter_t *emitter) +{ + if (!FLUSH(emitter)) return 0; + + *(emitter->buffer.pointer++) = (yaml_char_t) '\xEF'; + *(emitter->buffer.pointer++) = (yaml_char_t) '\xBB'; + *(emitter->buffer.pointer++) = (yaml_char_t) '\xBF'; + + return 1; +} + +static int +yaml_emitter_write_indent(yaml_emitter_t *emitter) +{ + int indent = (emitter->indent >= 0) ? emitter->indent : 0; + + if (!emitter->indention || emitter->column > indent + || (emitter->column == indent && !emitter->whitespace)) { + if (!PUT_BREAK(emitter)) return 0; + } + + while (emitter->column < indent) { + if (!PUT(emitter, ' ')) return 0; + } + + emitter->whitespace = 1; + emitter->indention = 1; + + return 1; +} + +static int +yaml_emitter_write_indicator(yaml_emitter_t *emitter, + const char *indicator, int need_whitespace, + int is_whitespace, int is_indention) +{ + size_t indicator_length; + yaml_string_t string; + + indicator_length = strlen(indicator); + STRING_ASSIGN(string, (yaml_char_t *)indicator, indicator_length); + + if (need_whitespace && !emitter->whitespace) { + if (!PUT(emitter, ' ')) return 0; + } + + while (string.pointer != string.end) { + if (!WRITE(emitter, string)) return 0; + } + + emitter->whitespace = is_whitespace; + emitter->indention = (emitter->indention && is_indention); + emitter->open_ended = 0; + + return 1; +} + +static int +yaml_emitter_write_anchor(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length) +{ + yaml_string_t string; + STRING_ASSIGN(string, value, length); + + while (string.pointer != string.end) { + if (!WRITE(emitter, string)) return 0; + } + + emitter->whitespace = 0; + emitter->indention = 0; + + return 1; +} + +static int +yaml_emitter_write_tag_handle(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length) +{ + yaml_string_t string; + STRING_ASSIGN(string, value, length); + + if (!emitter->whitespace) { + if (!PUT(emitter, ' ')) return 0; + } + + while (string.pointer != string.end) { + if (!WRITE(emitter, string)) return 0; + } + + emitter->whitespace = 0; + emitter->indention = 0; + + return 1; +} + +static int +yaml_emitter_write_tag_content(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, + int need_whitespace) +{ + yaml_string_t string; + STRING_ASSIGN(string, value, length); + + if (need_whitespace && !emitter->whitespace) { + if (!PUT(emitter, ' ')) return 0; + } + + while (string.pointer != string.end) { + if (IS_ALPHA(string) + || CHECK(string, ';') || CHECK(string, '/') + || CHECK(string, '?') || CHECK(string, ':') + || CHECK(string, '@') || CHECK(string, '&') + || CHECK(string, '=') || CHECK(string, '+') + || CHECK(string, '$') || CHECK(string, ',') + || CHECK(string, '_') || CHECK(string, '.') + || CHECK(string, '~') || CHECK(string, '*') + || CHECK(string, '\'') || CHECK(string, '(') + || CHECK(string, ')') || CHECK(string, '[') + || CHECK(string, ']')) { + if (!WRITE(emitter, string)) return 0; + } + else { + int width = WIDTH(string); + unsigned int value; + while (width --) { + value = *(string.pointer++); + if (!PUT(emitter, '%')) return 0; + if (!PUT(emitter, (value >> 4) + + ((value >> 4) < 10 ? '0' : 'A' - 10))) + return 0; + if (!PUT(emitter, (value & 0x0F) + + ((value & 0x0F) < 10 ? '0' : 'A' - 10))) + return 0; + } + } + } + + emitter->whitespace = 0; + emitter->indention = 0; + + return 1; +} + +static int +yaml_emitter_write_plain_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks) +{ + yaml_string_t string; + int spaces = 0; + int breaks = 0; + + STRING_ASSIGN(string, value, length); + + if (!emitter->whitespace) { + if (!PUT(emitter, ' ')) return 0; + } + + while (string.pointer != string.end) + { + if (IS_SPACE(string)) + { + if (allow_breaks && !spaces + && emitter->column > emitter->best_width + && !IS_SPACE_AT(string, 1)) { + if (!yaml_emitter_write_indent(emitter)) return 0; + MOVE(string); + } + else { + if (!WRITE(emitter, string)) return 0; + } + spaces = 1; + } + else if (IS_BREAK(string)) + { + if (!breaks && CHECK(string, '\n')) { + if (!PUT_BREAK(emitter)) return 0; + } + if (!WRITE_BREAK(emitter, string)) return 0; + emitter->indention = 1; + breaks = 1; + } + else + { + if (breaks) { + if (!yaml_emitter_write_indent(emitter)) return 0; + } + if (!WRITE(emitter, string)) return 0; + emitter->indention = 0; + spaces = 0; + breaks = 0; + } + } + + emitter->whitespace = 0; + emitter->indention = 0; + if (emitter->root_context) + { + emitter->open_ended = 1; + } + + return 1; +} + +static int +yaml_emitter_write_single_quoted_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks) +{ + yaml_string_t string; + int spaces = 0; + int breaks = 0; + + STRING_ASSIGN(string, value, length); + + if (!yaml_emitter_write_indicator(emitter, "'", 1, 0, 0)) + return 0; + + while (string.pointer != string.end) + { + if (IS_SPACE(string)) + { + if (allow_breaks && !spaces + && emitter->column > emitter->best_width + && string.pointer != string.start + && string.pointer != string.end - 1 + && !IS_SPACE_AT(string, 1)) { + if (!yaml_emitter_write_indent(emitter)) return 0; + MOVE(string); + } + else { + if (!WRITE(emitter, string)) return 0; + } + spaces = 1; + } + else if (IS_BREAK(string)) + { + if (!breaks && CHECK(string, '\n')) { + if (!PUT_BREAK(emitter)) return 0; + } + if (!WRITE_BREAK(emitter, string)) return 0; + emitter->indention = 1; + breaks = 1; + } + else + { + if (breaks) { + if (!yaml_emitter_write_indent(emitter)) return 0; + } + if (CHECK(string, '\'')) { + if (!PUT(emitter, '\'')) return 0; + } + if (!WRITE(emitter, string)) return 0; + emitter->indention = 0; + spaces = 0; + breaks = 0; + } + } + + if (!yaml_emitter_write_indicator(emitter, "'", 0, 0, 0)) + return 0; + + emitter->whitespace = 0; + emitter->indention = 0; + + return 1; +} + +static int +yaml_emitter_write_double_quoted_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length, int allow_breaks) +{ + yaml_string_t string; + int spaces = 0; + + STRING_ASSIGN(string, value, length); + + if (!yaml_emitter_write_indicator(emitter, "\"", 1, 0, 0)) + return 0; + + while (string.pointer != string.end) + { + if (!IS_PRINTABLE(string) || (!emitter->unicode && !IS_ASCII(string)) + || IS_BOM(string) || IS_BREAK(string) + || CHECK(string, '"') || CHECK(string, '\\')) + { + unsigned char octet; + unsigned int width; + unsigned int value; + int k; + + octet = string.pointer[0]; + width = (octet & 0x80) == 0x00 ? 1 : + (octet & 0xE0) == 0xC0 ? 2 : + (octet & 0xF0) == 0xE0 ? 3 : + (octet & 0xF8) == 0xF0 ? 4 : 0; + value = (octet & 0x80) == 0x00 ? octet & 0x7F : + (octet & 0xE0) == 0xC0 ? octet & 0x1F : + (octet & 0xF0) == 0xE0 ? octet & 0x0F : + (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; + for (k = 1; k < (int)width; k ++) { + octet = string.pointer[k]; + value = (value << 6) + (octet & 0x3F); + } + string.pointer += width; + + if (!PUT(emitter, '\\')) return 0; + + switch (value) + { + case 0x00: + if (!PUT(emitter, '0')) return 0; + break; + + case 0x07: + if (!PUT(emitter, 'a')) return 0; + break; + + case 0x08: + if (!PUT(emitter, 'b')) return 0; + break; + + case 0x09: + if (!PUT(emitter, 't')) return 0; + break; + + case 0x0A: + if (!PUT(emitter, 'n')) return 0; + break; + + case 0x0B: + if (!PUT(emitter, 'v')) return 0; + break; + + case 0x0C: + if (!PUT(emitter, 'f')) return 0; + break; + + case 0x0D: + if (!PUT(emitter, 'r')) return 0; + break; + + case 0x1B: + if (!PUT(emitter, 'e')) return 0; + break; + + case 0x22: + if (!PUT(emitter, '\"')) return 0; + break; + + case 0x5C: + if (!PUT(emitter, '\\')) return 0; + break; + + case 0x85: + if (!PUT(emitter, 'N')) return 0; + break; + + case 0xA0: + if (!PUT(emitter, '_')) return 0; + break; + + case 0x2028: + if (!PUT(emitter, 'L')) return 0; + break; + + case 0x2029: + if (!PUT(emitter, 'P')) return 0; + break; + + default: + if (value <= 0xFF) { + if (!PUT(emitter, 'x')) return 0; + width = 2; + } + else if (value <= 0xFFFF) { + if (!PUT(emitter, 'u')) return 0; + width = 4; + } + else { + if (!PUT(emitter, 'U')) return 0; + width = 8; + } + for (k = (width-1)*4; k >= 0; k -= 4) { + int digit = (value >> k) & 0x0F; + if (!PUT(emitter, digit + (digit < 10 ? '0' : 'A'-10))) + return 0; + } + } + spaces = 0; + } + else if (IS_SPACE(string)) + { + if (allow_breaks && !spaces + && emitter->column > emitter->best_width + && string.pointer != string.start + && string.pointer != string.end - 1) { + if (!yaml_emitter_write_indent(emitter)) return 0; + if (IS_SPACE_AT(string, 1)) { + if (!PUT(emitter, '\\')) return 0; + } + MOVE(string); + } + else { + if (!WRITE(emitter, string)) return 0; + } + spaces = 1; + } + else + { + if (!WRITE(emitter, string)) return 0; + spaces = 0; + } + } + + if (!yaml_emitter_write_indicator(emitter, "\"", 0, 0, 0)) + return 0; + + emitter->whitespace = 0; + emitter->indention = 0; + + return 1; +} + +static int +yaml_emitter_write_block_scalar_hints(yaml_emitter_t *emitter, + yaml_string_t string) +{ + char indent_hint[2]; + const char *chomp_hint = NULL; + + if (IS_SPACE(string) || IS_BREAK(string)) + { + indent_hint[0] = '0' + (char)emitter->best_indent; + indent_hint[1] = '\0'; + if (!yaml_emitter_write_indicator(emitter, indent_hint, 0, 0, 0)) + return 0; + } + + emitter->open_ended = 0; + + string.pointer = string.end; + if (string.start == string.pointer) + { + chomp_hint = "-"; + } + else + { + do { + string.pointer --; + } while ((*string.pointer & 0xC0) == 0x80); + if (!IS_BREAK(string)) + { + chomp_hint = "-"; + } + else if (string.start == string.pointer) + { + chomp_hint = "+"; + emitter->open_ended = 1; + } + else + { + do { + string.pointer --; + } while ((*string.pointer & 0xC0) == 0x80); + if (IS_BREAK(string)) + { + chomp_hint = "+"; + emitter->open_ended = 1; + } + } + } + + if (chomp_hint) + { + if (!yaml_emitter_write_indicator(emitter, chomp_hint, 0, 0, 0)) + return 0; + } + + return 1; +} + +static int +yaml_emitter_write_literal_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length) +{ + yaml_string_t string; + int breaks = 1; + + STRING_ASSIGN(string, value, length); + + if (!yaml_emitter_write_indicator(emitter, "|", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_block_scalar_hints(emitter, string)) + return 0; + if (!PUT_BREAK(emitter)) return 0; + emitter->indention = 1; + emitter->whitespace = 1; + + while (string.pointer != string.end) + { + if (IS_BREAK(string)) + { + if (!WRITE_BREAK(emitter, string)) return 0; + emitter->indention = 1; + breaks = 1; + } + else + { + if (breaks) { + if (!yaml_emitter_write_indent(emitter)) return 0; + } + if (!WRITE(emitter, string)) return 0; + emitter->indention = 0; + breaks = 0; + } + } + + return 1; +} + +static int +yaml_emitter_write_folded_scalar(yaml_emitter_t *emitter, + yaml_char_t *value, size_t length) +{ + yaml_string_t string; + int breaks = 1; + int leading_spaces = 1; + + STRING_ASSIGN(string, value, length); + + if (!yaml_emitter_write_indicator(emitter, ">", 1, 0, 0)) + return 0; + if (!yaml_emitter_write_block_scalar_hints(emitter, string)) + return 0; + if (!PUT_BREAK(emitter)) return 0; + emitter->indention = 1; + emitter->whitespace = 1; + + while (string.pointer != string.end) + { + if (IS_BREAK(string)) + { + if (!breaks && !leading_spaces && CHECK(string, '\n')) { + int k = 0; + while (IS_BREAK_AT(string, k)) { + k += WIDTH_AT(string, k); + } + if (!IS_BLANKZ_AT(string, k)) { + if (!PUT_BREAK(emitter)) return 0; + } + } + if (!WRITE_BREAK(emitter, string)) return 0; + emitter->indention = 1; + breaks = 1; + } + else + { + if (breaks) { + if (!yaml_emitter_write_indent(emitter)) return 0; + leading_spaces = IS_BLANK(string); + } + if (!breaks && IS_SPACE(string) && !IS_SPACE_AT(string, 1) + && emitter->column > emitter->best_width) { + if (!yaml_emitter_write_indent(emitter)) return 0; + MOVE(string); + } + else { + if (!WRITE(emitter, string)) return 0; + } + emitter->indention = 0; + breaks = 0; + } + } + + return 1; +} + diff --git a/ext/psych/yaml/loader.c b/ext/psych/yaml/loader.c new file mode 100644 index 0000000..cb3ea93 --- /dev/null +++ b/ext/psych/yaml/loader.c @@ -0,0 +1,459 @@ + +#include "yaml_private.h" + +/* + * API functions. + */ + +YAML_DECLARE(int) +yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document); + +/* + * Error handling. + */ + +static int +yaml_parser_set_composer_error(yaml_parser_t *parser, + const char *problem, yaml_mark_t problem_mark); + +static int +yaml_parser_set_composer_error_context(yaml_parser_t *parser, + const char *context, yaml_mark_t context_mark, + const char *problem, yaml_mark_t problem_mark); + + +/* + * Alias handling. + */ + +static int +yaml_parser_register_anchor(yaml_parser_t *parser, + int index, yaml_char_t *anchor); + +/* + * Clean up functions. + */ + +static void +yaml_parser_delete_aliases(yaml_parser_t *parser); + +/* + * Composer functions. + */ + +static int +yaml_parser_load_document(yaml_parser_t *parser, yaml_event_t *first_event); + +static int +yaml_parser_load_node(yaml_parser_t *parser, yaml_event_t *first_event); + +static int +yaml_parser_load_alias(yaml_parser_t *parser, yaml_event_t *first_event); + +static int +yaml_parser_load_scalar(yaml_parser_t *parser, yaml_event_t *first_event); + +static int +yaml_parser_load_sequence(yaml_parser_t *parser, yaml_event_t *first_event); + +static int +yaml_parser_load_mapping(yaml_parser_t *parser, yaml_event_t *first_event); + +/* + * Load the next document of the stream. + */ + +YAML_DECLARE(int) +yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document) +{ + yaml_event_t event; + + assert(parser); /* Non-NULL parser object is expected. */ + assert(document); /* Non-NULL document object is expected. */ + + memset(document, 0, sizeof(yaml_document_t)); + if (!STACK_INIT(parser, document->nodes, INITIAL_STACK_SIZE)) + goto error; + + if (!parser->stream_start_produced) { + if (!yaml_parser_parse(parser, &event)) goto error; + assert(event.type == YAML_STREAM_START_EVENT); + /* STREAM-START is expected. */ + } + + if (parser->stream_end_produced) { + return 1; + } + + if (!yaml_parser_parse(parser, &event)) goto error; + if (event.type == YAML_STREAM_END_EVENT) { + return 1; + } + + if (!STACK_INIT(parser, parser->aliases, INITIAL_STACK_SIZE)) + goto error; + + parser->document = document; + + if (!yaml_parser_load_document(parser, &event)) goto error; + + yaml_parser_delete_aliases(parser); + parser->document = NULL; + + return 1; + +error: + + yaml_parser_delete_aliases(parser); + yaml_document_delete(document); + parser->document = NULL; + + return 0; +} + +/* + * Set composer error. + */ + +static int +yaml_parser_set_composer_error(yaml_parser_t *parser, + const char *problem, yaml_mark_t problem_mark) +{ + parser->error = YAML_COMPOSER_ERROR; + parser->problem = problem; + parser->problem_mark = problem_mark; + + return 0; +} + +/* + * Set composer error with context. + */ + +static int +yaml_parser_set_composer_error_context(yaml_parser_t *parser, + const char *context, yaml_mark_t context_mark, + const char *problem, yaml_mark_t problem_mark) +{ + parser->error = YAML_COMPOSER_ERROR; + parser->context = context; + parser->context_mark = context_mark; + parser->problem = problem; + parser->problem_mark = problem_mark; + + return 0; +} + +/* + * Delete the stack of aliases. + */ + +static void +yaml_parser_delete_aliases(yaml_parser_t *parser) +{ + while (!STACK_EMPTY(parser, parser->aliases)) { + yaml_free(POP(parser, parser->aliases).anchor); + } + STACK_DEL(parser, parser->aliases); +} + +/* + * Compose a document object. + */ + +static int +yaml_parser_load_document(yaml_parser_t *parser, yaml_event_t *first_event) +{ + yaml_event_t event; + + assert(first_event->type == YAML_DOCUMENT_START_EVENT); + /* DOCUMENT-START is expected. */ + + parser->document->version_directive + = first_event->data.document_start.version_directive; + parser->document->tag_directives.start + = first_event->data.document_start.tag_directives.start; + parser->document->tag_directives.end + = first_event->data.document_start.tag_directives.end; + parser->document->start_implicit + = first_event->data.document_start.implicit; + parser->document->start_mark = first_event->start_mark; + + if (!yaml_parser_parse(parser, &event)) return 0; + + if (!yaml_parser_load_node(parser, &event)) return 0; + + if (!yaml_parser_parse(parser, &event)) return 0; + assert(event.type == YAML_DOCUMENT_END_EVENT); + /* DOCUMENT-END is expected. */ + + parser->document->end_implicit = event.data.document_end.implicit; + parser->document->end_mark = event.end_mark; + + return 1; +} + +/* + * Compose a node. + */ + +static int +yaml_parser_load_node(yaml_parser_t *parser, yaml_event_t *first_event) +{ + switch (first_event->type) { + case YAML_ALIAS_EVENT: + return yaml_parser_load_alias(parser, first_event); + case YAML_SCALAR_EVENT: + return yaml_parser_load_scalar(parser, first_event); + case YAML_SEQUENCE_START_EVENT: + return yaml_parser_load_sequence(parser, first_event); + case YAML_MAPPING_START_EVENT: + return yaml_parser_load_mapping(parser, first_event); + default: + assert(0); /* Could not happen. */ + return 0; + } + + return 0; +} + +/* + * Add an anchor. + */ + +static int +yaml_parser_register_anchor(yaml_parser_t *parser, + int index, yaml_char_t *anchor) +{ + yaml_alias_data_t data; + yaml_alias_data_t *alias_data; + + if (!anchor) return 1; + + data.anchor = anchor; + data.index = index; + data.mark = parser->document->nodes.start[index-1].start_mark; + + for (alias_data = parser->aliases.start; + alias_data != parser->aliases.top; alias_data ++) { + if (strcmp((char *)alias_data->anchor, (char *)anchor) == 0) { + yaml_free(anchor); + return yaml_parser_set_composer_error_context(parser, + "found duplicate anchor; first occurence", + alias_data->mark, "second occurence", data.mark); + } + } + + if (!PUSH(parser, parser->aliases, data)) { + yaml_free(anchor); + return 0; + } + + return 1; +} + +/* + * Compose a node corresponding to an alias. + */ + +static int +yaml_parser_load_alias(yaml_parser_t *parser, yaml_event_t *first_event) +{ + yaml_char_t *anchor = first_event->data.alias.anchor; + yaml_alias_data_t *alias_data; + + for (alias_data = parser->aliases.start; + alias_data != parser->aliases.top; alias_data ++) { + if (strcmp((char *)alias_data->anchor, (char *)anchor) == 0) { + yaml_free(anchor); + return alias_data->index; + } + } + + yaml_free(anchor); + return yaml_parser_set_composer_error(parser, "found undefined alias", + first_event->start_mark); +} + +/* + * Compose a scalar node. + */ + +static int +yaml_parser_load_scalar(yaml_parser_t *parser, yaml_event_t *first_event) +{ + yaml_node_t node; + ptrdiff_t node_index; + int index; + yaml_char_t *tag = first_event->data.scalar.tag; + + if (!STACK_LIMIT(parser, parser->document->nodes, INT_MAX-1)) goto error; + + if (!tag || strcmp((char *)tag, "!") == 0) { + yaml_free(tag); + tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_SCALAR_TAG); + if (!tag) goto error; + } + + SCALAR_NODE_INIT(node, tag, first_event->data.scalar.value, + first_event->data.scalar.length, first_event->data.scalar.style, + first_event->start_mark, first_event->end_mark); + + if (!PUSH(parser, parser->document->nodes, node)) goto error; + + node_index = parser->document->nodes.top - parser->document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (node_index > INT_MAX) goto error; +#endif + index = (int)node_index; + + if (!yaml_parser_register_anchor(parser, index, + first_event->data.scalar.anchor)) return 0; + + return index; + +error: + yaml_free(tag); + yaml_free(first_event->data.scalar.anchor); + yaml_free(first_event->data.scalar.value); + return 0; +} + +/* + * Compose a sequence node. + */ + +static int +yaml_parser_load_sequence(yaml_parser_t *parser, yaml_event_t *first_event) +{ + yaml_event_t event; + yaml_node_t node; + struct { + yaml_node_item_t *start; + yaml_node_item_t *end; + yaml_node_item_t *top; + } items = { NULL, NULL, NULL }; + int index, item_index; + ptrdiff_t node_index; + yaml_char_t *tag = first_event->data.sequence_start.tag; + + if (!STACK_LIMIT(parser, parser->document->nodes, INT_MAX-1)) goto error; + + if (!tag || strcmp((char *)tag, "!") == 0) { + yaml_free(tag); + tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_SEQUENCE_TAG); + if (!tag) goto error; + } + + if (!STACK_INIT(parser, items, INITIAL_STACK_SIZE)) goto error; + + SEQUENCE_NODE_INIT(node, tag, items.start, items.end, + first_event->data.sequence_start.style, + first_event->start_mark, first_event->end_mark); + + if (!PUSH(parser, parser->document->nodes, node)) goto error; + + node_index = parser->document->nodes.top - parser->document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (node_index > INT_MAX) goto error; +#endif + index = (int)node_index; + + if (!yaml_parser_register_anchor(parser, index, + first_event->data.sequence_start.anchor)) return 0; + + if (!yaml_parser_parse(parser, &event)) return 0; + + while (event.type != YAML_SEQUENCE_END_EVENT) { + if (!STACK_LIMIT(parser, + parser->document->nodes.start[index-1].data.sequence.items, + INT_MAX-1)) return 0; + item_index = yaml_parser_load_node(parser, &event); + if (!item_index) return 0; + if (!PUSH(parser, + parser->document->nodes.start[index-1].data.sequence.items, + item_index)) return 0; + if (!yaml_parser_parse(parser, &event)) return 0; + } + + parser->document->nodes.start[index-1].end_mark = event.end_mark; + + return index; + +error: + yaml_free(tag); + yaml_free(first_event->data.sequence_start.anchor); + return 0; +} + +/* + * Compose a mapping node. + */ + +static int +yaml_parser_load_mapping(yaml_parser_t *parser, yaml_event_t *first_event) +{ + yaml_event_t event; + yaml_node_t node; + struct { + yaml_node_pair_t *start; + yaml_node_pair_t *end; + yaml_node_pair_t *top; + } pairs = { NULL, NULL, NULL }; + int index; + ptrdiff_t node_index; + yaml_node_pair_t pair; + yaml_char_t *tag = first_event->data.mapping_start.tag; + + if (!STACK_LIMIT(parser, parser->document->nodes, INT_MAX-1)) goto error; + + if (!tag || strcmp((char *)tag, "!") == 0) { + yaml_free(tag); + tag = yaml_strdup((yaml_char_t *)YAML_DEFAULT_MAPPING_TAG); + if (!tag) goto error; + } + + if (!STACK_INIT(parser, pairs, INITIAL_STACK_SIZE)) goto error; + + MAPPING_NODE_INIT(node, tag, pairs.start, pairs.end, + first_event->data.mapping_start.style, + first_event->start_mark, first_event->end_mark); + + if (!PUSH(parser, parser->document->nodes, node)) goto error; + + node_index = parser->document->nodes.top - parser->document->nodes.start; +#if PTRDIFF_MAX > INT_MAX + if (node_index > INT_MAX) goto error; +#endif + index = (int)node_index; + + if (!yaml_parser_register_anchor(parser, index, + first_event->data.mapping_start.anchor)) return 0; + + if (!yaml_parser_parse(parser, &event)) return 0; + + while (event.type != YAML_MAPPING_END_EVENT) { + if (!STACK_LIMIT(parser, + parser->document->nodes.start[index-1].data.mapping.pairs, + INT_MAX-1)) return 0; + pair.key = yaml_parser_load_node(parser, &event); + if (!pair.key) return 0; + if (!yaml_parser_parse(parser, &event)) return 0; + pair.value = yaml_parser_load_node(parser, &event); + if (!pair.value) return 0; + if (!PUSH(parser, + parser->document->nodes.start[index-1].data.mapping.pairs, + pair)) return 0; + if (!yaml_parser_parse(parser, &event)) return 0; + } + + parser->document->nodes.start[index-1].end_mark = event.end_mark; + + return index; + +error: + yaml_free(tag); + yaml_free(first_event->data.mapping_start.anchor); + return 0; +} + diff --git a/ext/psych/yaml/parser.c b/ext/psych/yaml/parser.c new file mode 100644 index 0000000..32671b2 --- /dev/null +++ b/ext/psych/yaml/parser.c @@ -0,0 +1,1370 @@ + +/* + * The parser implements the following grammar: + * + * stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + * implicit_document ::= block_node DOCUMENT-END* + * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + * block_node_or_indentless_sequence ::= + * ALIAS + * | properties (block_content | indentless_block_sequence)? + * | block_content + * | indentless_block_sequence + * block_node ::= ALIAS + * | properties block_content? + * | block_content + * flow_node ::= ALIAS + * | properties flow_content? + * | flow_content + * properties ::= TAG ANCHOR? | ANCHOR TAG? + * block_content ::= block_collection | flow_collection | SCALAR + * flow_content ::= flow_collection | SCALAR + * block_collection ::= block_sequence | block_mapping + * flow_collection ::= flow_sequence | flow_mapping + * block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + * indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + * block_mapping ::= BLOCK-MAPPING_START + * ((KEY block_node_or_indentless_sequence?)? + * (VALUE block_node_or_indentless_sequence?)?)* + * BLOCK-END + * flow_sequence ::= FLOW-SEQUENCE-START + * (flow_sequence_entry FLOW-ENTRY)* + * flow_sequence_entry? + * FLOW-SEQUENCE-END + * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * flow_mapping ::= FLOW-MAPPING-START + * (flow_mapping_entry FLOW-ENTRY)* + * flow_mapping_entry? + * FLOW-MAPPING-END + * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + */ + +#include "yaml_private.h" + +/* + * Peek the next token in the token queue. + */ + +#define PEEK_TOKEN(parser) \ + ((parser->token_available || yaml_parser_fetch_more_tokens(parser)) ? \ + parser->tokens.head : NULL) + +/* + * Remove the next token from the queue (must be called after PEEK_TOKEN). + */ + +#define SKIP_TOKEN(parser) \ + (parser->token_available = 0, \ + parser->tokens_parsed ++, \ + parser->stream_end_produced = \ + (parser->tokens.head->type == YAML_STREAM_END_TOKEN), \ + parser->tokens.head ++) + +/* + * Public API declarations. + */ + +YAML_DECLARE(int) +yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event); + +/* + * Error handling. + */ + +static int +yaml_parser_set_parser_error(yaml_parser_t *parser, + const char *problem, yaml_mark_t problem_mark); + +static int +yaml_parser_set_parser_error_context(yaml_parser_t *parser, + const char *context, yaml_mark_t context_mark, + const char *problem, yaml_mark_t problem_mark); + +/* + * State functions. + */ + +static int +yaml_parser_state_machine(yaml_parser_t *parser, yaml_event_t *event); + +static int +yaml_parser_parse_stream_start(yaml_parser_t *parser, yaml_event_t *event); + +static int +yaml_parser_parse_document_start(yaml_parser_t *parser, yaml_event_t *event, + int implicit); + +static int +yaml_parser_parse_document_content(yaml_parser_t *parser, yaml_event_t *event); + +static int +yaml_parser_parse_document_end(yaml_parser_t *parser, yaml_event_t *event); + +static int +yaml_parser_parse_node(yaml_parser_t *parser, yaml_event_t *event, + int block, int indentless_sequence); + +static int +yaml_parser_parse_block_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event, int first); + +static int +yaml_parser_parse_indentless_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event); + +static int +yaml_parser_parse_block_mapping_key(yaml_parser_t *parser, + yaml_event_t *event, int first); + +static int +yaml_parser_parse_block_mapping_value(yaml_parser_t *parser, + yaml_event_t *event); + +static int +yaml_parser_parse_flow_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event, int first); + +static int +yaml_parser_parse_flow_sequence_entry_mapping_key(yaml_parser_t *parser, + yaml_event_t *event); + +static int +yaml_parser_parse_flow_sequence_entry_mapping_value(yaml_parser_t *parser, + yaml_event_t *event); + +static int +yaml_parser_parse_flow_sequence_entry_mapping_end(yaml_parser_t *parser, + yaml_event_t *event); + +static int +yaml_parser_parse_flow_mapping_key(yaml_parser_t *parser, + yaml_event_t *event, int first); + +static int +yaml_parser_parse_flow_mapping_value(yaml_parser_t *parser, + yaml_event_t *event, int empty); + +/* + * Utility functions. + */ + +static int +yaml_parser_process_empty_scalar(yaml_parser_t *parser, + yaml_event_t *event, yaml_mark_t mark); + +static int +yaml_parser_process_directives(yaml_parser_t *parser, + yaml_version_directive_t **version_directive_ref, + yaml_tag_directive_t **tag_directives_start_ref, + yaml_tag_directive_t **tag_directives_end_ref); + +static int +yaml_parser_append_tag_directive(yaml_parser_t *parser, + yaml_tag_directive_t value, int allow_duplicates, yaml_mark_t mark); + +/* + * Get the next event. + */ + +YAML_DECLARE(int) +yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event) +{ + assert(parser); /* Non-NULL parser object is expected. */ + assert(event); /* Non-NULL event object is expected. */ + + /* Erase the event object. */ + + memset(event, 0, sizeof(yaml_event_t)); + + /* No events after the end of the stream or error. */ + + if (parser->stream_end_produced || parser->error || + parser->state == YAML_PARSE_END_STATE) { + return 1; + } + + /* Generate the next event. */ + + return yaml_parser_state_machine(parser, event); +} + +/* + * Set parser error. + */ + +static int +yaml_parser_set_parser_error(yaml_parser_t *parser, + const char *problem, yaml_mark_t problem_mark) +{ + parser->error = YAML_PARSER_ERROR; + parser->problem = problem; + parser->problem_mark = problem_mark; + + return 0; +} + +static int +yaml_parser_set_parser_error_context(yaml_parser_t *parser, + const char *context, yaml_mark_t context_mark, + const char *problem, yaml_mark_t problem_mark) +{ + parser->error = YAML_PARSER_ERROR; + parser->context = context; + parser->context_mark = context_mark; + parser->problem = problem; + parser->problem_mark = problem_mark; + + return 0; +} + + +/* + * State dispatcher. + */ + +static int +yaml_parser_state_machine(yaml_parser_t *parser, yaml_event_t *event) +{ + switch (parser->state) + { + case YAML_PARSE_STREAM_START_STATE: + return yaml_parser_parse_stream_start(parser, event); + + case YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE: + return yaml_parser_parse_document_start(parser, event, 1); + + case YAML_PARSE_DOCUMENT_START_STATE: + return yaml_parser_parse_document_start(parser, event, 0); + + case YAML_PARSE_DOCUMENT_CONTENT_STATE: + return yaml_parser_parse_document_content(parser, event); + + case YAML_PARSE_DOCUMENT_END_STATE: + return yaml_parser_parse_document_end(parser, event); + + case YAML_PARSE_BLOCK_NODE_STATE: + return yaml_parser_parse_node(parser, event, 1, 0); + + case YAML_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE: + return yaml_parser_parse_node(parser, event, 1, 1); + + case YAML_PARSE_FLOW_NODE_STATE: + return yaml_parser_parse_node(parser, event, 0, 0); + + case YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE: + return yaml_parser_parse_block_sequence_entry(parser, event, 1); + + case YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE: + return yaml_parser_parse_block_sequence_entry(parser, event, 0); + + case YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE: + return yaml_parser_parse_indentless_sequence_entry(parser, event); + + case YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE: + return yaml_parser_parse_block_mapping_key(parser, event, 1); + + case YAML_PARSE_BLOCK_MAPPING_KEY_STATE: + return yaml_parser_parse_block_mapping_key(parser, event, 0); + + case YAML_PARSE_BLOCK_MAPPING_VALUE_STATE: + return yaml_parser_parse_block_mapping_value(parser, event); + + case YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE: + return yaml_parser_parse_flow_sequence_entry(parser, event, 1); + + case YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE: + return yaml_parser_parse_flow_sequence_entry(parser, event, 0); + + case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE: + return yaml_parser_parse_flow_sequence_entry_mapping_key(parser, event); + + case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE: + return yaml_parser_parse_flow_sequence_entry_mapping_value(parser, event); + + case YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE: + return yaml_parser_parse_flow_sequence_entry_mapping_end(parser, event); + + case YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE: + return yaml_parser_parse_flow_mapping_key(parser, event, 1); + + case YAML_PARSE_FLOW_MAPPING_KEY_STATE: + return yaml_parser_parse_flow_mapping_key(parser, event, 0); + + case YAML_PARSE_FLOW_MAPPING_VALUE_STATE: + return yaml_parser_parse_flow_mapping_value(parser, event, 0); + + case YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE: + return yaml_parser_parse_flow_mapping_value(parser, event, 1); + + default: + assert(1); /* Invalid state. */ + } + + return 0; +} + +/* + * Parse the production: + * stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + * ************ + */ + +static int +yaml_parser_parse_stream_start(yaml_parser_t *parser, yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type != YAML_STREAM_START_TOKEN) { + return yaml_parser_set_parser_error(parser, + "did not find expected <stream-start>", token->start_mark); + } + + parser->state = YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE; + STREAM_START_EVENT_INIT(*event, token->data.stream_start.encoding, + token->start_mark, token->start_mark); + SKIP_TOKEN(parser); + + return 1; +} + +/* + * Parse the productions: + * implicit_document ::= block_node DOCUMENT-END* + * * + * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + * ************************* + */ + +static int +yaml_parser_parse_document_start(yaml_parser_t *parser, yaml_event_t *event, + int implicit) +{ + yaml_token_t *token; + yaml_version_directive_t *version_directive = NULL; + struct { + yaml_tag_directive_t *start; + yaml_tag_directive_t *end; + } tag_directives = { NULL, NULL }; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + /* Parse extra document end indicators. */ + + if (!implicit) + { + while (token->type == YAML_DOCUMENT_END_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + } + } + + /* Parse an implicit document. */ + + if (implicit && token->type != YAML_VERSION_DIRECTIVE_TOKEN && + token->type != YAML_TAG_DIRECTIVE_TOKEN && + token->type != YAML_DOCUMENT_START_TOKEN && + token->type != YAML_STREAM_END_TOKEN) + { + if (!yaml_parser_process_directives(parser, NULL, NULL, NULL)) + return 0; + if (!PUSH(parser, parser->states, YAML_PARSE_DOCUMENT_END_STATE)) + return 0; + parser->state = YAML_PARSE_BLOCK_NODE_STATE; + DOCUMENT_START_EVENT_INIT(*event, NULL, NULL, NULL, 1, + token->start_mark, token->start_mark); + return 1; + } + + /* Parse an explicit document. */ + + else if (token->type != YAML_STREAM_END_TOKEN) + { + yaml_mark_t start_mark, end_mark; + start_mark = token->start_mark; + if (!yaml_parser_process_directives(parser, &version_directive, + &tag_directives.start, &tag_directives.end)) + return 0; + token = PEEK_TOKEN(parser); + if (!token) goto error; + if (token->type != YAML_DOCUMENT_START_TOKEN) { + yaml_parser_set_parser_error(parser, + "did not find expected <document start>", token->start_mark); + goto error; + } + if (!PUSH(parser, parser->states, YAML_PARSE_DOCUMENT_END_STATE)) + goto error; + parser->state = YAML_PARSE_DOCUMENT_CONTENT_STATE; + end_mark = token->end_mark; + DOCUMENT_START_EVENT_INIT(*event, version_directive, + tag_directives.start, tag_directives.end, 0, + start_mark, end_mark); + SKIP_TOKEN(parser); + version_directive = NULL; + tag_directives.start = tag_directives.end = NULL; + return 1; + } + + /* Parse the stream end. */ + + else + { + parser->state = YAML_PARSE_END_STATE; + STREAM_END_EVENT_INIT(*event, token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; + } + +error: + yaml_free(version_directive); + while (tag_directives.start != tag_directives.end) { + yaml_free(tag_directives.end[-1].handle); + yaml_free(tag_directives.end[-1].prefix); + tag_directives.end --; + } + yaml_free(tag_directives.start); + return 0; +} + +/* + * Parse the productions: + * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + * *********** + */ + +static int +yaml_parser_parse_document_content(yaml_parser_t *parser, yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_VERSION_DIRECTIVE_TOKEN || + token->type == YAML_TAG_DIRECTIVE_TOKEN || + token->type == YAML_DOCUMENT_START_TOKEN || + token->type == YAML_DOCUMENT_END_TOKEN || + token->type == YAML_STREAM_END_TOKEN) { + parser->state = POP(parser, parser->states); + return yaml_parser_process_empty_scalar(parser, event, + token->start_mark); + } + else { + return yaml_parser_parse_node(parser, event, 1, 0); + } +} + +/* + * Parse the productions: + * implicit_document ::= block_node DOCUMENT-END* + * ************* + * explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + * ************* + */ + +static int +yaml_parser_parse_document_end(yaml_parser_t *parser, yaml_event_t *event) +{ + yaml_token_t *token; + yaml_mark_t start_mark, end_mark; + int implicit = 1; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + start_mark = end_mark = token->start_mark; + + if (token->type == YAML_DOCUMENT_END_TOKEN) { + end_mark = token->end_mark; + SKIP_TOKEN(parser); + implicit = 0; + } + + while (!STACK_EMPTY(parser, parser->tag_directives)) { + yaml_tag_directive_t tag_directive = POP(parser, parser->tag_directives); + yaml_free(tag_directive.handle); + yaml_free(tag_directive.prefix); + } + + parser->state = YAML_PARSE_DOCUMENT_START_STATE; + DOCUMENT_END_EVENT_INIT(*event, implicit, start_mark, end_mark); + + return 1; +} + +/* + * Parse the productions: + * block_node_or_indentless_sequence ::= + * ALIAS + * ***** + * | properties (block_content | indentless_block_sequence)? + * ********** * + * | block_content | indentless_block_sequence + * * + * block_node ::= ALIAS + * ***** + * | properties block_content? + * ********** * + * | block_content + * * + * flow_node ::= ALIAS + * ***** + * | properties flow_content? + * ********** * + * | flow_content + * * + * properties ::= TAG ANCHOR? | ANCHOR TAG? + * ************************* + * block_content ::= block_collection | flow_collection | SCALAR + * ****** + * flow_content ::= flow_collection | SCALAR + * ****** + */ + +static int +yaml_parser_parse_node(yaml_parser_t *parser, yaml_event_t *event, + int block, int indentless_sequence) +{ + yaml_token_t *token; + yaml_char_t *anchor = NULL; + yaml_char_t *tag_handle = NULL; + yaml_char_t *tag_suffix = NULL; + yaml_char_t *tag = NULL; + yaml_mark_t start_mark, end_mark, tag_mark; + int implicit; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_ALIAS_TOKEN) + { + parser->state = POP(parser, parser->states); + ALIAS_EVENT_INIT(*event, token->data.alias.value, + token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; + } + + else + { + start_mark = end_mark = token->start_mark; + + if (token->type == YAML_ANCHOR_TOKEN) + { + anchor = token->data.anchor.value; + start_mark = token->start_mark; + end_mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) goto error; + if (token->type == YAML_TAG_TOKEN) + { + tag_handle = token->data.tag.handle; + tag_suffix = token->data.tag.suffix; + tag_mark = token->start_mark; + end_mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) goto error; + } + } + else if (token->type == YAML_TAG_TOKEN) + { + tag_handle = token->data.tag.handle; + tag_suffix = token->data.tag.suffix; + start_mark = tag_mark = token->start_mark; + end_mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) goto error; + if (token->type == YAML_ANCHOR_TOKEN) + { + anchor = token->data.anchor.value; + end_mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) goto error; + } + } + + if (tag_handle) { + if (!*tag_handle) { + tag = tag_suffix; + yaml_free(tag_handle); + tag_handle = tag_suffix = NULL; + } + else { + yaml_tag_directive_t *tag_directive; + for (tag_directive = parser->tag_directives.start; + tag_directive != parser->tag_directives.top; + tag_directive ++) { + if (strcmp((char *)tag_directive->handle, (char *)tag_handle) == 0) { + size_t prefix_len = strlen((char *)tag_directive->prefix); + size_t suffix_len = strlen((char *)tag_suffix); + tag = yaml_malloc(prefix_len+suffix_len+1); + if (!tag) { + parser->error = YAML_MEMORY_ERROR; + goto error; + } + memcpy(tag, tag_directive->prefix, prefix_len); + memcpy(tag+prefix_len, tag_suffix, suffix_len); + tag[prefix_len+suffix_len] = '\0'; + yaml_free(tag_handle); + yaml_free(tag_suffix); + tag_handle = tag_suffix = NULL; + break; + } + } + if (!tag) { + yaml_parser_set_parser_error_context(parser, + "while parsing a node", start_mark, + "found undefined tag handle", tag_mark); + goto error; + } + } + } + + implicit = (!tag || !*tag); + if (indentless_sequence && token->type == YAML_BLOCK_ENTRY_TOKEN) { + end_mark = token->end_mark; + parser->state = YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE; + SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, + YAML_BLOCK_SEQUENCE_STYLE, start_mark, end_mark); + return 1; + } + else { + if (token->type == YAML_SCALAR_TOKEN) { + int plain_implicit = 0; + int quoted_implicit = 0; + end_mark = token->end_mark; + if ((token->data.scalar.style == YAML_PLAIN_SCALAR_STYLE && !tag) + || (tag && strcmp((char *)tag, "!") == 0)) { + plain_implicit = 1; + } + else if (!tag) { + quoted_implicit = 1; + } + parser->state = POP(parser, parser->states); + SCALAR_EVENT_INIT(*event, anchor, tag, + token->data.scalar.value, token->data.scalar.length, + plain_implicit, quoted_implicit, + token->data.scalar.style, start_mark, end_mark); + SKIP_TOKEN(parser); + return 1; + } + else if (token->type == YAML_FLOW_SEQUENCE_START_TOKEN) { + end_mark = token->end_mark; + parser->state = YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE; + SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, + YAML_FLOW_SEQUENCE_STYLE, start_mark, end_mark); + return 1; + } + else if (token->type == YAML_FLOW_MAPPING_START_TOKEN) { + end_mark = token->end_mark; + parser->state = YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE; + MAPPING_START_EVENT_INIT(*event, anchor, tag, implicit, + YAML_FLOW_MAPPING_STYLE, start_mark, end_mark); + return 1; + } + else if (block && token->type == YAML_BLOCK_SEQUENCE_START_TOKEN) { + end_mark = token->end_mark; + parser->state = YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE; + SEQUENCE_START_EVENT_INIT(*event, anchor, tag, implicit, + YAML_BLOCK_SEQUENCE_STYLE, start_mark, end_mark); + return 1; + } + else if (block && token->type == YAML_BLOCK_MAPPING_START_TOKEN) { + end_mark = token->end_mark; + parser->state = YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE; + MAPPING_START_EVENT_INIT(*event, anchor, tag, implicit, + YAML_BLOCK_MAPPING_STYLE, start_mark, end_mark); + return 1; + } + else if (anchor || tag) { + yaml_char_t *value = yaml_malloc(1); + if (!value) { + parser->error = YAML_MEMORY_ERROR; + goto error; + } + value[0] = '\0'; + parser->state = POP(parser, parser->states); + SCALAR_EVENT_INIT(*event, anchor, tag, value, 0, + implicit, 0, YAML_PLAIN_SCALAR_STYLE, + start_mark, end_mark); + return 1; + } + else { + yaml_parser_set_parser_error_context(parser, + (block ? "while parsing a block node" + : "while parsing a flow node"), start_mark, + "did not find expected node content", token->start_mark); + goto error; + } + } + } + +error: + yaml_free(anchor); + yaml_free(tag_handle); + yaml_free(tag_suffix); + yaml_free(tag); + + return 0; +} + +/* + * Parse the productions: + * block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + * ******************** *********** * ********* + */ + +static int +yaml_parser_parse_block_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event, int first) +{ + yaml_token_t *token; + + if (first) { + token = PEEK_TOKEN(parser); + if (!PUSH(parser, parser->marks, token->start_mark)) + return 0; + SKIP_TOKEN(parser); + } + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_BLOCK_ENTRY_TOKEN) + { + yaml_mark_t mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_BLOCK_ENTRY_TOKEN && + token->type != YAML_BLOCK_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 1, 0); + } + else { + parser->state = YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE; + return yaml_parser_process_empty_scalar(parser, event, mark); + } + } + + else if (token->type == YAML_BLOCK_END_TOKEN) + { + parser->state = POP(parser, parser->states); + (void)POP(parser, parser->marks); + SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; + } + + else + { + return yaml_parser_set_parser_error_context(parser, + "while parsing a block collection", POP(parser, parser->marks), + "did not find expected '-' indicator", token->start_mark); + } +} + +/* + * Parse the productions: + * indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + * *********** * + */ + +static int +yaml_parser_parse_indentless_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_BLOCK_ENTRY_TOKEN) + { + yaml_mark_t mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_BLOCK_ENTRY_TOKEN && + token->type != YAML_KEY_TOKEN && + token->type != YAML_VALUE_TOKEN && + token->type != YAML_BLOCK_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 1, 0); + } + else { + parser->state = YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE; + return yaml_parser_process_empty_scalar(parser, event, mark); + } + } + + else + { + parser->state = POP(parser, parser->states); + SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->start_mark); + return 1; + } +} + +/* + * Parse the productions: + * block_mapping ::= BLOCK-MAPPING_START + * ******************* + * ((KEY block_node_or_indentless_sequence?)? + * *** * + * (VALUE block_node_or_indentless_sequence?)?)* + * + * BLOCK-END + * ********* + */ + +static int +yaml_parser_parse_block_mapping_key(yaml_parser_t *parser, + yaml_event_t *event, int first) +{ + yaml_token_t *token; + + if (first) { + token = PEEK_TOKEN(parser); + if (!PUSH(parser, parser->marks, token->start_mark)) + return 0; + SKIP_TOKEN(parser); + } + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_KEY_TOKEN) + { + yaml_mark_t mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_KEY_TOKEN && + token->type != YAML_VALUE_TOKEN && + token->type != YAML_BLOCK_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_BLOCK_MAPPING_VALUE_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 1, 1); + } + else { + parser->state = YAML_PARSE_BLOCK_MAPPING_VALUE_STATE; + return yaml_parser_process_empty_scalar(parser, event, mark); + } + } + + else if (token->type == YAML_BLOCK_END_TOKEN) + { + parser->state = POP(parser, parser->states); + (void)POP(parser, parser->marks); + MAPPING_END_EVENT_INIT(*event, token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; + } + + else + { + return yaml_parser_set_parser_error_context(parser, + "while parsing a block mapping", POP(parser, parser->marks), + "did not find expected key", token->start_mark); + } +} + +/* + * Parse the productions: + * block_mapping ::= BLOCK-MAPPING_START + * + * ((KEY block_node_or_indentless_sequence?)? + * + * (VALUE block_node_or_indentless_sequence?)?)* + * ***** * + * BLOCK-END + * + */ + +static int +yaml_parser_parse_block_mapping_value(yaml_parser_t *parser, + yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_VALUE_TOKEN) + { + yaml_mark_t mark = token->end_mark; + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_KEY_TOKEN && + token->type != YAML_VALUE_TOKEN && + token->type != YAML_BLOCK_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_BLOCK_MAPPING_KEY_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 1, 1); + } + else { + parser->state = YAML_PARSE_BLOCK_MAPPING_KEY_STATE; + return yaml_parser_process_empty_scalar(parser, event, mark); + } + } + + else + { + parser->state = YAML_PARSE_BLOCK_MAPPING_KEY_STATE; + return yaml_parser_process_empty_scalar(parser, event, token->start_mark); + } +} + +/* + * Parse the productions: + * flow_sequence ::= FLOW-SEQUENCE-START + * ******************* + * (flow_sequence_entry FLOW-ENTRY)* + * * ********** + * flow_sequence_entry? + * * + * FLOW-SEQUENCE-END + * ***************** + * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * * + */ + +static int +yaml_parser_parse_flow_sequence_entry(yaml_parser_t *parser, + yaml_event_t *event, int first) +{ + yaml_token_t *token; + + if (first) { + token = PEEK_TOKEN(parser); + if (!PUSH(parser, parser->marks, token->start_mark)) + return 0; + SKIP_TOKEN(parser); + } + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type != YAML_FLOW_SEQUENCE_END_TOKEN) + { + if (!first) { + if (token->type == YAML_FLOW_ENTRY_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + } + else { + return yaml_parser_set_parser_error_context(parser, + "while parsing a flow sequence", POP(parser, parser->marks), + "did not find expected ',' or ']'", token->start_mark); + } + } + + if (token->type == YAML_KEY_TOKEN) { + parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE; + MAPPING_START_EVENT_INIT(*event, NULL, NULL, + 1, YAML_FLOW_MAPPING_STYLE, + token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; + } + + else if (token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + } + + parser->state = POP(parser, parser->states); + (void)POP(parser, parser->marks); + SEQUENCE_END_EVENT_INIT(*event, token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; +} + +/* + * Parse the productions: + * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * *** * + */ + +static int +yaml_parser_parse_flow_sequence_entry_mapping_key(yaml_parser_t *parser, + yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type != YAML_VALUE_TOKEN && token->type != YAML_FLOW_ENTRY_TOKEN + && token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + else { + yaml_mark_t mark = token->end_mark; + SKIP_TOKEN(parser); + parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE; + return yaml_parser_process_empty_scalar(parser, event, mark); + } +} + +/* + * Parse the productions: + * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * ***** * + */ + +static int +yaml_parser_parse_flow_sequence_entry_mapping_value(yaml_parser_t *parser, + yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type == YAML_VALUE_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_FLOW_ENTRY_TOKEN + && token->type != YAML_FLOW_SEQUENCE_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + } + parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE; + return yaml_parser_process_empty_scalar(parser, event, token->start_mark); +} + +/* + * Parse the productions: + * flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * * + */ + +static int +yaml_parser_parse_flow_sequence_entry_mapping_end(yaml_parser_t *parser, + yaml_event_t *event) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + parser->state = YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE; + + MAPPING_END_EVENT_INIT(*event, token->start_mark, token->start_mark); + return 1; +} + +/* + * Parse the productions: + * flow_mapping ::= FLOW-MAPPING-START + * ****************** + * (flow_mapping_entry FLOW-ENTRY)* + * * ********** + * flow_mapping_entry? + * ****************** + * FLOW-MAPPING-END + * **************** + * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * * *** * + */ + +static int +yaml_parser_parse_flow_mapping_key(yaml_parser_t *parser, + yaml_event_t *event, int first) +{ + yaml_token_t *token; + + if (first) { + token = PEEK_TOKEN(parser); + if (!PUSH(parser, parser->marks, token->start_mark)) + return 0; + SKIP_TOKEN(parser); + } + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (token->type != YAML_FLOW_MAPPING_END_TOKEN) + { + if (!first) { + if (token->type == YAML_FLOW_ENTRY_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + } + else { + return yaml_parser_set_parser_error_context(parser, + "while parsing a flow mapping", POP(parser, parser->marks), + "did not find expected ',' or '}'", token->start_mark); + } + } + + if (token->type == YAML_KEY_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_VALUE_TOKEN + && token->type != YAML_FLOW_ENTRY_TOKEN + && token->type != YAML_FLOW_MAPPING_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_MAPPING_VALUE_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + else { + parser->state = YAML_PARSE_FLOW_MAPPING_VALUE_STATE; + return yaml_parser_process_empty_scalar(parser, event, + token->start_mark); + } + } + else if (token->type != YAML_FLOW_MAPPING_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + } + + parser->state = POP(parser, parser->states); + (void)POP(parser, parser->marks); + MAPPING_END_EVENT_INIT(*event, token->start_mark, token->end_mark); + SKIP_TOKEN(parser); + return 1; +} + +/* + * Parse the productions: + * flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + * * ***** * + */ + +static int +yaml_parser_parse_flow_mapping_value(yaml_parser_t *parser, + yaml_event_t *event, int empty) +{ + yaml_token_t *token; + + token = PEEK_TOKEN(parser); + if (!token) return 0; + + if (empty) { + parser->state = YAML_PARSE_FLOW_MAPPING_KEY_STATE; + return yaml_parser_process_empty_scalar(parser, event, + token->start_mark); + } + + if (token->type == YAML_VALUE_TOKEN) { + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) return 0; + if (token->type != YAML_FLOW_ENTRY_TOKEN + && token->type != YAML_FLOW_MAPPING_END_TOKEN) { + if (!PUSH(parser, parser->states, + YAML_PARSE_FLOW_MAPPING_KEY_STATE)) + return 0; + return yaml_parser_parse_node(parser, event, 0, 0); + } + } + + parser->state = YAML_PARSE_FLOW_MAPPING_KEY_STATE; + return yaml_parser_process_empty_scalar(parser, event, token->start_mark); +} + +/* + * Generate an empty scalar event. + */ + +static int +yaml_parser_process_empty_scalar(yaml_parser_t *parser, yaml_event_t *event, + yaml_mark_t mark) +{ + yaml_char_t *value; + + value = yaml_malloc(1); + if (!value) { + parser->error = YAML_MEMORY_ERROR; + return 0; + } + value[0] = '\0'; + + SCALAR_EVENT_INIT(*event, NULL, NULL, value, 0, + 1, 0, YAML_PLAIN_SCALAR_STYLE, mark, mark); + + return 1; +} + +/* + * Parse directives. + */ + +static int +yaml_parser_process_directives(yaml_parser_t *parser, + yaml_version_directive_t **version_directive_ref, + yaml_tag_directive_t **tag_directives_start_ref, + yaml_tag_directive_t **tag_directives_end_ref) +{ + yaml_tag_directive_t default_tag_directives[] = { + {(yaml_char_t *)"!", (yaml_char_t *)"!"}, + {(yaml_char_t *)"!!", (yaml_char_t *)"tag:yaml.org,2002:"}, + {NULL, NULL} + }; + yaml_tag_directive_t *default_tag_directive; + yaml_version_directive_t *version_directive = NULL; + struct { + yaml_tag_directive_t *start; + yaml_tag_directive_t *end; + yaml_tag_directive_t *top; + } tag_directives = { NULL, NULL, NULL }; + yaml_token_t *token; + + if (!STACK_INIT(parser, tag_directives, INITIAL_STACK_SIZE)) + goto error; + + token = PEEK_TOKEN(parser); + if (!token) goto error; + + while (token->type == YAML_VERSION_DIRECTIVE_TOKEN || + token->type == YAML_TAG_DIRECTIVE_TOKEN) + { + if (token->type == YAML_VERSION_DIRECTIVE_TOKEN) { + if (version_directive) { + yaml_parser_set_parser_error(parser, + "found duplicate %YAML directive", token->start_mark); + goto error; + } + if (token->data.version_directive.major != 1 + || token->data.version_directive.minor != 1) { + yaml_parser_set_parser_error(parser, + "found incompatible YAML document", token->start_mark); + goto error; + } + version_directive = yaml_malloc(sizeof(yaml_version_directive_t)); + if (!version_directive) { + parser->error = YAML_MEMORY_ERROR; + goto error; + } + version_directive->major = token->data.version_directive.major; + version_directive->minor = token->data.version_directive.minor; + } + + else if (token->type == YAML_TAG_DIRECTIVE_TOKEN) { + yaml_tag_directive_t value; + value.handle = token->data.tag_directive.handle; + value.prefix = token->data.tag_directive.prefix; + + if (!yaml_parser_append_tag_directive(parser, value, 0, + token->start_mark)) + goto error; + if (!PUSH(parser, tag_directives, value)) + goto error; + } + + SKIP_TOKEN(parser); + token = PEEK_TOKEN(parser); + if (!token) goto error; + } + + for (default_tag_directive = default_tag_directives; + default_tag_directive->handle; default_tag_directive++) { + if (!yaml_parser_append_tag_directive(parser, *default_tag_directive, 1, + token->start_mark)) + goto error; + } + + if (version_directive_ref) { + *version_directive_ref = version_directive; + } + if (tag_directives_start_ref) { + if (STACK_EMPTY(parser, tag_directives)) { + *tag_directives_start_ref = *tag_directives_end_ref = NULL; + STACK_DEL(parser, tag_directives); + } + else { + *tag_directives_start_ref = tag_directives.start; + *tag_directives_end_ref = tag_directives.top; + } + } + else { + STACK_DEL(parser, tag_directives); + } + + return 1; + +error: + yaml_free(version_directive); + while (!STACK_EMPTY(parser, tag_directives)) { + yaml_tag_directive_t tag_directive = POP(parser, tag_directives); + yaml_free(tag_directive.handle); + yaml_free(tag_directive.prefix); + } + STACK_DEL(parser, tag_directives); + return 0; +} + +/* + * Append a tag directive to the directives stack. + */ + +static int +yaml_parser_append_tag_directive(yaml_parser_t *parser, + yaml_tag_directive_t value, int allow_duplicates, yaml_mark_t mark) +{ + yaml_tag_directive_t *tag_directive; + yaml_tag_directive_t copy = { NULL, NULL }; + + for (tag_directive = parser->tag_directives.start; + tag_directive != parser->tag_directives.top; tag_directive ++) { + if (strcmp((char *)value.handle, (char *)tag_directive->handle) == 0) { + if (allow_duplicates) + return 1; + return yaml_parser_set_parser_error(parser, + "found duplicate %TAG directive", mark); + } + } + + copy.handle = yaml_strdup(value.handle); + copy.prefix = yaml_strdup(value.prefix); + if (!copy.handle || !copy.prefix) { + parser->error = YAML_MEMORY_ERROR; + goto error; + } + + if (!PUSH(parser, parser->tag_directives, copy)) + goto error; + + return 1; + +error: + yaml_free(copy.handle); + yaml_free(copy.prefix); + return 0; +} + diff --git a/ext/psych/yaml/reader.c b/ext/psych/yaml/reader.c new file mode 100644 index 0000000..f1a06de --- /dev/null +++ b/ext/psych/yaml/reader.c @@ -0,0 +1,469 @@ + +#include "yaml_private.h" + +/* + * Declarations. + */ + +static int +yaml_parser_set_reader_error(yaml_parser_t *parser, const char *problem, + size_t offset, int value); + +static int +yaml_parser_update_raw_buffer(yaml_parser_t *parser); + +static int +yaml_parser_determine_encoding(yaml_parser_t *parser); + +YAML_DECLARE(int) +yaml_parser_update_buffer(yaml_parser_t *parser, size_t length); + +/* + * Set the reader error and return 0. + */ + +static int +yaml_parser_set_reader_error(yaml_parser_t *parser, const char *problem, + size_t offset, int value) +{ + parser->error = YAML_READER_ERROR; + parser->problem = problem; + parser->problem_offset = offset; + parser->problem_value = value; + + return 0; +} + +/* + * Byte order marks. + */ + +#define BOM_UTF8 "\xef\xbb\xbf" +#define BOM_UTF16LE "\xff\xfe" +#define BOM_UTF16BE "\xfe\xff" + +/* + * Determine the input stream encoding by checking the BOM symbol. If no BOM is + * found, the UTF-8 encoding is assumed. Return 1 on success, 0 on failure. + */ + +static int +yaml_parser_determine_encoding(yaml_parser_t *parser) +{ + /* Ensure that we had enough bytes in the raw buffer. */ + + while (!parser->eof + && parser->raw_buffer.last - parser->raw_buffer.pointer < 3) { + if (!yaml_parser_update_raw_buffer(parser)) { + return 0; + } + } + + /* Determine the encoding. */ + + if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 2 + && !memcmp(parser->raw_buffer.pointer, BOM_UTF16LE, 2)) { + parser->encoding = YAML_UTF16LE_ENCODING; + parser->raw_buffer.pointer += 2; + parser->offset += 2; + } + else if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 2 + && !memcmp(parser->raw_buffer.pointer, BOM_UTF16BE, 2)) { + parser->encoding = YAML_UTF16BE_ENCODING; + parser->raw_buffer.pointer += 2; + parser->offset += 2; + } + else if (parser->raw_buffer.last - parser->raw_buffer.pointer >= 3 + && !memcmp(parser->raw_buffer.pointer, BOM_UTF8, 3)) { + parser->encoding = YAML_UTF8_ENCODING; + parser->raw_buffer.pointer += 3; + parser->offset += 3; + } + else { + parser->encoding = YAML_UTF8_ENCODING; + } + + return 1; +} + +/* + * Update the raw buffer. + */ + +static int +yaml_parser_update_raw_buffer(yaml_parser_t *parser) +{ + size_t size_read = 0; + + /* Return if the raw buffer is full. */ + + if (parser->raw_buffer.start == parser->raw_buffer.pointer + && parser->raw_buffer.last == parser->raw_buffer.end) + return 1; + + /* Return on EOF. */ + + if (parser->eof) return 1; + + /* Move the remaining bytes in the raw buffer to the beginning. */ + + if (parser->raw_buffer.start < parser->raw_buffer.pointer + && parser->raw_buffer.pointer < parser->raw_buffer.last) { + memmove(parser->raw_buffer.start, parser->raw_buffer.pointer, + parser->raw_buffer.last - parser->raw_buffer.pointer); + } + parser->raw_buffer.last -= + parser->raw_buffer.pointer - parser->raw_buffer.start; + parser->raw_buffer.pointer = parser->raw_buffer.start; + + /* Call the read handler to fill the buffer. */ + + if (!parser->read_handler(parser->read_handler_data, parser->raw_buffer.last, + parser->raw_buffer.end - parser->raw_buffer.last, &size_read)) { + return yaml_parser_set_reader_error(parser, "input error", + parser->offset, -1); + } + parser->raw_buffer.last += size_read; + if (!size_read) { + parser->eof = 1; + } + + return 1; +} + +/* + * Ensure that the buffer contains at least `length` characters. + * Return 1 on success, 0 on failure. + * + * The length is supposed to be significantly less that the buffer size. + */ + +YAML_DECLARE(int) +yaml_parser_update_buffer(yaml_parser_t *parser, size_t length) +{ + int first = 1; + + assert(parser->read_handler); /* Read handler must be set. */ + + /* If the EOF flag is set and the raw buffer is empty, do nothing. */ + + if (parser->eof && parser->raw_buffer.pointer == parser->raw_buffer.last) + return 1; + + /* Return if the buffer contains enough characters. */ + + if (parser->unread >= length) + return 1; + + /* Determine the input encoding if it is not known yet. */ + + if (!parser->encoding) { + if (!yaml_parser_determine_encoding(parser)) + return 0; + } + + /* Move the unread characters to the beginning of the buffer. */ + + if (parser->buffer.start < parser->buffer.pointer + && parser->buffer.pointer < parser->buffer.last) { + size_t size = parser->buffer.last - parser->buffer.pointer; + memmove(parser->buffer.start, parser->buffer.pointer, size); + parser->buffer.pointer = parser->buffer.start; + parser->buffer.last = parser->buffer.start + size; + } + else if (parser->buffer.pointer == parser->buffer.last) { + parser->buffer.pointer = parser->buffer.start; + parser->buffer.last = parser->buffer.start; + } + + /* Fill the buffer until it has enough characters. */ + + while (parser->unread < length) + { + /* Fill the raw buffer if necessary. */ + + if (!first || parser->raw_buffer.pointer == parser->raw_buffer.last) { + if (!yaml_parser_update_raw_buffer(parser)) return 0; + } + first = 0; + + /* Decode the raw buffer. */ + + while (parser->raw_buffer.pointer != parser->raw_buffer.last) + { + unsigned int value = 0, value2 = 0; + int incomplete = 0; + unsigned char octet; + unsigned int width = 0; + int low, high; + size_t k; + size_t raw_unread = parser->raw_buffer.last - parser->raw_buffer.pointer; + + /* Decode the next character. */ + + switch (parser->encoding) + { + case YAML_UTF8_ENCODING: + + /* + * Decode a UTF-8 character. Check RFC 3629 + * (http://www.ietf.org/rfc/rfc3629.txt) for more details. + * + * The following table (taken from the RFC) is used for + * decoding. + * + * Char. number range | UTF-8 octet sequence + * (hexadecimal) | (binary) + * --------------------+------------------------------------ + * 0000 0000-0000 007F | 0xxxxxxx + * 0000 0080-0000 07FF | 110xxxxx 10xxxxxx + * 0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx + * 0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx + * + * Additionally, the characters in the range 0xD800-0xDFFF + * are prohibited as they are reserved for use with UTF-16 + * surrogate pairs. + */ + + /* Determine the length of the UTF-8 sequence. */ + + octet = parser->raw_buffer.pointer[0]; + width = (octet & 0x80) == 0x00 ? 1 : + (octet & 0xE0) == 0xC0 ? 2 : + (octet & 0xF0) == 0xE0 ? 3 : + (octet & 0xF8) == 0xF0 ? 4 : 0; + + /* Check if the leading octet is valid. */ + + if (!width) + return yaml_parser_set_reader_error(parser, + "invalid leading UTF-8 octet", + parser->offset, octet); + + /* Check if the raw buffer contains an incomplete character. */ + + if (width > raw_unread) { + if (parser->eof) { + return yaml_parser_set_reader_error(parser, + "incomplete UTF-8 octet sequence", + parser->offset, -1); + } + incomplete = 1; + break; + } + + /* Decode the leading octet. */ + + value = (octet & 0x80) == 0x00 ? octet & 0x7F : + (octet & 0xE0) == 0xC0 ? octet & 0x1F : + (octet & 0xF0) == 0xE0 ? octet & 0x0F : + (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; + + /* Check and decode the trailing octets. */ + + for (k = 1; k < width; k ++) + { + octet = parser->raw_buffer.pointer[k]; + + /* Check if the octet is valid. */ + + if ((octet & 0xC0) != 0x80) + return yaml_parser_set_reader_error(parser, + "invalid trailing UTF-8 octet", + parser->offset+k, octet); + + /* Decode the octet. */ + + value = (value << 6) + (octet & 0x3F); + } + + /* Check the length of the sequence against the value. */ + + if (!((width == 1) || + (width == 2 && value >= 0x80) || + (width == 3 && value >= 0x800) || + (width == 4 && value >= 0x10000))) + return yaml_parser_set_reader_error(parser, + "invalid length of a UTF-8 sequence", + parser->offset, -1); + + /* Check the range of the value. */ + + if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) + return yaml_parser_set_reader_error(parser, + "invalid Unicode character", + parser->offset, value); + + break; + + case YAML_UTF16LE_ENCODING: + case YAML_UTF16BE_ENCODING: + + low = (parser->encoding == YAML_UTF16LE_ENCODING ? 0 : 1); + high = (parser->encoding == YAML_UTF16LE_ENCODING ? 1 : 0); + + /* + * The UTF-16 encoding is not as simple as one might + * naively think. Check RFC 2781 + * (http://www.ietf.org/rfc/rfc2781.txt). + * + * Normally, two subsequent bytes describe a Unicode + * character. However a special technique (called a + * surrogate pair) is used for specifying character + * values larger than 0xFFFF. + * + * A surrogate pair consists of two pseudo-characters: + * high surrogate area (0xD800-0xDBFF) + * low surrogate area (0xDC00-0xDFFF) + * + * The following formulas are used for decoding + * and encoding characters using surrogate pairs: + * + * U = U' + 0x10000 (0x01 00 00 <= U <= 0x10 FF FF) + * U' = yyyyyyyyyyxxxxxxxxxx (0 <= U' <= 0x0F FF FF) + * W1 = 110110yyyyyyyyyy + * W2 = 110111xxxxxxxxxx + * + * where U is the character value, W1 is the high surrogate + * area, W2 is the low surrogate area. + */ + + /* Check for incomplete UTF-16 character. */ + + if (raw_unread < 2) { + if (parser->eof) { + return yaml_parser_set_reader_error(parser, + "incomplete UTF-16 character", + parser->offset, -1); + } + incomplete = 1; + break; + } + + /* Get the character. */ + + value = parser->raw_buffer.pointer[low] + + (parser->raw_buffer.pointer[high] << 8); + + /* Check for unexpected low surrogate area. */ + + if ((value & 0xFC00) == 0xDC00) + return yaml_parser_set_reader_error(parser, + "unexpected low surrogate area", + parser->offset, value); + + /* Check for a high surrogate area. */ + + if ((value & 0xFC00) == 0xD800) { + + width = 4; + + /* Check for incomplete surrogate pair. */ + + if (raw_unread < 4) { + if (parser->eof) { + return yaml_parser_set_reader_error(parser, + "incomplete UTF-16 surrogate pair", + parser->offset, -1); + } + incomplete = 1; + break; + } + + /* Get the next character. */ + + value2 = parser->raw_buffer.pointer[low+2] + + (parser->raw_buffer.pointer[high+2] << 8); + + /* Check for a low surrogate area. */ + + if ((value2 & 0xFC00) != 0xDC00) + return yaml_parser_set_reader_error(parser, + "expected low surrogate area", + parser->offset+2, value2); + + /* Generate the value of the surrogate pair. */ + + value = 0x10000 + ((value & 0x3FF) << 10) + (value2 & 0x3FF); + } + + else { + width = 2; + } + + break; + + default: + assert(1); /* Impossible. */ + } + + /* Check if the raw buffer contains enough bytes to form a character. */ + + if (incomplete) break; + + /* + * Check if the character is in the allowed range: + * #x9 | #xA | #xD | [#x20-#x7E] (8 bit) + * | #x85 | [#xA0-#xD7FF] | [#xE000-#xFFFD] (16 bit) + * | [#x10000-#x10FFFF] (32 bit) + */ + + if (! (value == 0x09 || value == 0x0A || value == 0x0D + || (value >= 0x20 && value <= 0x7E) + || (value == 0x85) || (value >= 0xA0 && value <= 0xD7FF) + || (value >= 0xE000 && value <= 0xFFFD) + || (value >= 0x10000 && value <= 0x10FFFF))) + return yaml_parser_set_reader_error(parser, + "control characters are not allowed", + parser->offset, value); + + /* Move the raw pointers. */ + + parser->raw_buffer.pointer += width; + parser->offset += width; + + /* Finally put the character into the buffer. */ + + /* 0000 0000-0000 007F -> 0xxxxxxx */ + if (value <= 0x7F) { + *(parser->buffer.last++) = value; + } + /* 0000 0080-0000 07FF -> 110xxxxx 10xxxxxx */ + else if (value <= 0x7FF) { + *(parser->buffer.last++) = 0xC0 + (value >> 6); + *(parser->buffer.last++) = 0x80 + (value & 0x3F); + } + /* 0000 0800-0000 FFFF -> 1110xxxx 10xxxxxx 10xxxxxx */ + else if (value <= 0xFFFF) { + *(parser->buffer.last++) = 0xE0 + (value >> 12); + *(parser->buffer.last++) = 0x80 + ((value >> 6) & 0x3F); + *(parser->buffer.last++) = 0x80 + (value & 0x3F); + } + /* 0001 0000-0010 FFFF -> 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */ + else { + *(parser->buffer.last++) = 0xF0 + (value >> 18); + *(parser->buffer.last++) = 0x80 + ((value >> 12) & 0x3F); + *(parser->buffer.last++) = 0x80 + ((value >> 6) & 0x3F); + *(parser->buffer.last++) = 0x80 + (value & 0x3F); + } + + parser->unread ++; + } + + /* On EOF, put NUL into the buffer and return. */ + + if (parser->eof) { + *(parser->buffer.last++) = '\0'; + parser->unread ++; + return 1; + } + + } + + if (parser->offset >= PTRDIFF_MAX) + return yaml_parser_set_reader_error(parser, "input is too long", + PTRDIFF_MAX, -1); + + return 1; +} + diff --git a/ext/psych/yaml/scanner.c b/ext/psych/yaml/scanner.c new file mode 100644 index 0000000..08ad8ed --- /dev/null +++ b/ext/psych/yaml/scanner.c @@ -0,0 +1,3583 @@ + +/* + * Introduction + * ************ + * + * The following notes assume that you are familiar with the YAML specification + * (http://yaml.org/spec/cvs/current.html). We mostly follow it, although in + * some cases we are less restrictive that it requires. + * + * The process of transforming a YAML stream into a sequence of events is + * divided on two steps: Scanning and Parsing. + * + * The Scanner transforms the input stream into a sequence of tokens, while the + * parser transform the sequence of tokens produced by the Scanner into a + * sequence of parsing events. + * + * The Scanner is rather clever and complicated. The Parser, on the contrary, + * is a straightforward implementation of a recursive-descendant parser (or, + * LL(1) parser, as it is usually called). + * + * Actually there are two issues of Scanning that might be called "clever", the + * rest is quite straightforward. The issues are "block collection start" and + * "simple keys". Both issues are explained below in details. + * + * Here the Scanning step is explained and implemented. We start with the list + * of all the tokens produced by the Scanner together with short descriptions. + * + * Now, tokens: + * + * STREAM-START(encoding) # The stream start. + * STREAM-END # The stream end. + * VERSION-DIRECTIVE(major,minor) # The '%YAML' directive. + * TAG-DIRECTIVE(handle,prefix) # The '%TAG' directive. + * DOCUMENT-START # '---' + * DOCUMENT-END # '...' + * BLOCK-SEQUENCE-START # Indentation increase denoting a block + * BLOCK-MAPPING-START # sequence or a block mapping. + * BLOCK-END # Indentation decrease. + * FLOW-SEQUENCE-START # '[' + * FLOW-SEQUENCE-END # ']' + * BLOCK-SEQUENCE-START # '{' + * BLOCK-SEQUENCE-END # '}' + * BLOCK-ENTRY # '-' + * FLOW-ENTRY # ',' + * KEY # '?' or nothing (simple keys). + * VALUE # ':' + * ALIAS(anchor) # '*anchor' + * ANCHOR(anchor) # '&anchor' + * TAG(handle,suffix) # '!handle!suffix' + * SCALAR(value,style) # A scalar. + * + * The following two tokens are "virtual" tokens denoting the beginning and the + * end of the stream: + * + * STREAM-START(encoding) + * STREAM-END + * + * We pass the information about the input stream encoding with the + * STREAM-START token. + * + * The next two tokens are responsible for tags: + * + * VERSION-DIRECTIVE(major,minor) + * TAG-DIRECTIVE(handle,prefix) + * + * Example: + * + * %YAML 1.1 + * %TAG ! !foo + * %TAG !yaml! tag:yaml.org,2002: + * --- + * + * The corresponding sequence of tokens: + * + * STREAM-START(utf-8) + * VERSION-DIRECTIVE(1,1) + * TAG-DIRECTIVE("!","!foo") + * TAG-DIRECTIVE("!yaml","tag:yaml.org,2002:") + * DOCUMENT-START + * STREAM-END + * + * Note that the VERSION-DIRECTIVE and TAG-DIRECTIVE tokens occupy a whole + * line. + * + * The document start and end indicators are represented by: + * + * DOCUMENT-START + * DOCUMENT-END + * + * Note that if a YAML stream contains an implicit document (without '---' + * and '...' indicators), no DOCUMENT-START and DOCUMENT-END tokens will be + * produced. + * + * In the following examples, we present whole documents together with the + * produced tokens. + * + * 1. An implicit document: + * + * 'a scalar' + * + * Tokens: + * + * STREAM-START(utf-8) + * SCALAR("a scalar",single-quoted) + * STREAM-END + * + * 2. An explicit document: + * + * --- + * 'a scalar' + * ... + * + * Tokens: + * + * STREAM-START(utf-8) + * DOCUMENT-START + * SCALAR("a scalar",single-quoted) + * DOCUMENT-END + * STREAM-END + * + * 3. Several documents in a stream: + * + * 'a scalar' + * --- + * 'another scalar' + * --- + * 'yet another scalar' + * + * Tokens: + * + * STREAM-START(utf-8) + * SCALAR("a scalar",single-quoted) + * DOCUMENT-START + * SCALAR("another scalar",single-quoted) + * DOCUMENT-START + * SCALAR("yet another scalar",single-quoted) + * STREAM-END + * + * We have already introduced the SCALAR token above. The following tokens are + * used to describe aliases, anchors, tag, and scalars: + * + * ALIAS(anchor) + * ANCHOR(anchor) + * TAG(handle,suffix) + * SCALAR(value,style) + * + * The following series of examples illustrate the usage of these tokens: + * + * 1. A recursive sequence: + * + * &A [ *A ] + * + * Tokens: + * + * STREAM-START(utf-8) + * ANCHOR("A") + * FLOW-SEQUENCE-START + * ALIAS("A") + * FLOW-SEQUENCE-END + * STREAM-END + * + * 2. A tagged scalar: + * + * !!float "3.14" # A good approximation. + * + * Tokens: + * + * STREAM-START(utf-8) + * TAG("!!","float") + * SCALAR("3.14",double-quoted) + * STREAM-END + * + * 3. Various scalar styles: + * + * --- # Implicit empty plain scalars do not produce tokens. + * --- a plain scalar + * --- 'a single-quoted scalar' + * --- "a double-quoted scalar" + * --- |- + * a literal scalar + * --- >- + * a folded + * scalar + * + * Tokens: + * + * STREAM-START(utf-8) + * DOCUMENT-START + * DOCUMENT-START + * SCALAR("a plain scalar",plain) + * DOCUMENT-START + * SCALAR("a single-quoted scalar",single-quoted) + * DOCUMENT-START + * SCALAR("a double-quoted scalar",double-quoted) + * DOCUMENT-START + * SCALAR("a literal scalar",literal) + * DOCUMENT-START + * SCALAR("a folded scalar",folded) + * STREAM-END + * + * Now it's time to review collection-related tokens. We will start with + * flow collections: + * + * FLOW-SEQUENCE-START + * FLOW-SEQUENCE-END + * FLOW-MAPPING-START + * FLOW-MAPPING-END + * FLOW-ENTRY + * KEY + * VALUE + * + * The tokens FLOW-SEQUENCE-START, FLOW-SEQUENCE-END, FLOW-MAPPING-START, and + * FLOW-MAPPING-END represent the indicators '[', ']', '{', and '}' + * correspondingly. FLOW-ENTRY represent the ',' indicator. Finally the + * indicators '?' and ':', which are used for denoting mapping keys and values, + * are represented by the KEY and VALUE tokens. + * + * The following examples show flow collections: + * + * 1. A flow sequence: + * + * [item 1, item 2, item 3] + * + * Tokens: + * + * STREAM-START(utf-8) + * FLOW-SEQUENCE-START + * SCALAR("item 1",plain) + * FLOW-ENTRY + * SCALAR("item 2",plain) + * FLOW-ENTRY + * SCALAR("item 3",plain) + * FLOW-SEQUENCE-END + * STREAM-END + * + * 2. A flow mapping: + * + * { + * a simple key: a value, # Note that the KEY token is produced. + * ? a complex key: another value, + * } + * + * Tokens: + * + * STREAM-START(utf-8) + * FLOW-MAPPING-START + * KEY + * SCALAR("a simple key",plain) + * VALUE + * SCALAR("a value",plain) + * FLOW-ENTRY + * KEY + * SCALAR("a complex key",plain) + * VALUE + * SCALAR("another value",plain) + * FLOW-ENTRY + * FLOW-MAPPING-END + * STREAM-END + * + * A simple key is a key which is not denoted by the '?' indicator. Note that + * the Scanner still produce the KEY token whenever it encounters a simple key. + * + * For scanning block collections, the following tokens are used (note that we + * repeat KEY and VALUE here): + * + * BLOCK-SEQUENCE-START + * BLOCK-MAPPING-START + * BLOCK-END + * BLOCK-ENTRY + * KEY + * VALUE + * + * The tokens BLOCK-SEQUENCE-START and BLOCK-MAPPING-START denote indentation + * increase that precedes a block collection (cf. the INDENT token in Python). + * The token BLOCK-END denote indentation decrease that ends a block collection + * (cf. the DEDENT token in Python). However YAML has some syntax pecularities + * that makes detections of these tokens more complex. + * + * The tokens BLOCK-ENTRY, KEY, and VALUE are used to represent the indicators + * '-', '?', and ':' correspondingly. + * + * The following examples show how the tokens BLOCK-SEQUENCE-START, + * BLOCK-MAPPING-START, and BLOCK-END are emitted by the Scanner: + * + * 1. Block sequences: + * + * - item 1 + * - item 2 + * - + * - item 3.1 + * - item 3.2 + * - + * key 1: value 1 + * key 2: value 2 + * + * Tokens: + * + * STREAM-START(utf-8) + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * SCALAR("item 1",plain) + * BLOCK-ENTRY + * SCALAR("item 2",plain) + * BLOCK-ENTRY + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * SCALAR("item 3.1",plain) + * BLOCK-ENTRY + * SCALAR("item 3.2",plain) + * BLOCK-END + * BLOCK-ENTRY + * BLOCK-MAPPING-START + * KEY + * SCALAR("key 1",plain) + * VALUE + * SCALAR("value 1",plain) + * KEY + * SCALAR("key 2",plain) + * VALUE + * SCALAR("value 2",plain) + * BLOCK-END + * BLOCK-END + * STREAM-END + * + * 2. Block mappings: + * + * a simple key: a value # The KEY token is produced here. + * ? a complex key + * : another value + * a mapping: + * key 1: value 1 + * key 2: value 2 + * a sequence: + * - item 1 + * - item 2 + * + * Tokens: + * + * STREAM-START(utf-8) + * BLOCK-MAPPING-START + * KEY + * SCALAR("a simple key",plain) + * VALUE + * SCALAR("a value",plain) + * KEY + * SCALAR("a complex key",plain) + * VALUE + * SCALAR("another value",plain) + * KEY + * SCALAR("a mapping",plain) + * BLOCK-MAPPING-START + * KEY + * SCALAR("key 1",plain) + * VALUE + * SCALAR("value 1",plain) + * KEY + * SCALAR("key 2",plain) + * VALUE + * SCALAR("value 2",plain) + * BLOCK-END + * KEY + * SCALAR("a sequence",plain) + * VALUE + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * SCALAR("item 1",plain) + * BLOCK-ENTRY + * SCALAR("item 2",plain) + * BLOCK-END + * BLOCK-END + * STREAM-END + * + * YAML does not always require to start a new block collection from a new + * line. If the current line contains only '-', '?', and ':' indicators, a new + * block collection may start at the current line. The following examples + * illustrate this case: + * + * 1. Collections in a sequence: + * + * - - item 1 + * - item 2 + * - key 1: value 1 + * key 2: value 2 + * - ? complex key + * : complex value + * + * Tokens: + * + * STREAM-START(utf-8) + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * SCALAR("item 1",plain) + * BLOCK-ENTRY + * SCALAR("item 2",plain) + * BLOCK-END + * BLOCK-ENTRY + * BLOCK-MAPPING-START + * KEY + * SCALAR("key 1",plain) + * VALUE + * SCALAR("value 1",plain) + * KEY + * SCALAR("key 2",plain) + * VALUE + * SCALAR("value 2",plain) + * BLOCK-END + * BLOCK-ENTRY + * BLOCK-MAPPING-START + * KEY + * SCALAR("complex key") + * VALUE + * SCALAR("complex value") + * BLOCK-END + * BLOCK-END + * STREAM-END + * + * 2. Collections in a mapping: + * + * ? a sequence + * : - item 1 + * - item 2 + * ? a mapping + * : key 1: value 1 + * key 2: value 2 + * + * Tokens: + * + * STREAM-START(utf-8) + * BLOCK-MAPPING-START + * KEY + * SCALAR("a sequence",plain) + * VALUE + * BLOCK-SEQUENCE-START + * BLOCK-ENTRY + * SCALAR("item 1",plain) + * BLOCK-ENTRY + * SCALAR("item 2",plain) + * BLOCK-END + * KEY + * SCALAR("a mapping",plain) + * VALUE + * BLOCK-MAPPING-START + * KEY + * SCALAR("key 1",plain) + * VALUE + * SCALAR("value 1",plain) + * KEY + * SCALAR("key 2",plain) + * VALUE + * SCALAR("value 2",plain) + * BLOCK-END + * BLOCK-END + * STREAM-END + * + * YAML also permits non-indented sequences if they are included into a block + * mapping. In this case, the token BLOCK-SEQUENCE-START is not produced: + * + * key: + * - item 1 # BLOCK-SEQUENCE-START is NOT produced here. + * - item 2 + * + * Tokens: + * + * STREAM-START(utf-8) + * BLOCK-MAPPING-START + * KEY + * SCALAR("key",plain) + * VALUE + * BLOCK-ENTRY + * SCALAR("item 1",plain) + * BLOCK-ENTRY + * SCALAR("item 2",plain) + * BLOCK-END + */ + +#include "yaml_private.h" + +/* + * Ensure that the buffer contains the required number of characters. + * Return 1 on success, 0 on failure (reader error or memory error). + */ + +#define CACHE(parser,length) \ + (parser->unread >= (length) \ + ? 1 \ + : yaml_parser_update_buffer(parser, (length))) + +/* + * Advance the buffer pointer. + */ + +#define SKIP(parser) \ + (parser->mark.index ++, \ + parser->mark.column ++, \ + parser->unread --, \ + parser->buffer.pointer += WIDTH(parser->buffer)) + +#define SKIP_LINE(parser) \ + (IS_CRLF(parser->buffer) ? \ + (parser->mark.index += 2, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread -= 2, \ + parser->buffer.pointer += 2) : \ + IS_BREAK(parser->buffer) ? \ + (parser->mark.index ++, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread --, \ + parser->buffer.pointer += WIDTH(parser->buffer)) : 0) + +/* + * Copy a character to a string buffer and advance pointers. + */ + +#define READ(parser,string) \ + (STRING_EXTEND(parser,string) ? \ + (COPY(string,parser->buffer), \ + parser->mark.index ++, \ + parser->mark.column ++, \ + parser->unread --, \ + 1) : 0) + +/* + * Copy a line break character to a string buffer and advance pointers. + */ + +#define READ_LINE(parser,string) \ + (STRING_EXTEND(parser,string) ? \ + (((CHECK_AT(parser->buffer,'\r',0) \ + && CHECK_AT(parser->buffer,'\n',1)) ? /* CR LF -> LF */ \ + (*((string).pointer++) = (yaml_char_t) '\n', \ + parser->buffer.pointer += 2, \ + parser->mark.index += 2, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread -= 2) : \ + (CHECK_AT(parser->buffer,'\r',0) \ + || CHECK_AT(parser->buffer,'\n',0)) ? /* CR|LF -> LF */ \ + (*((string).pointer++) = (yaml_char_t) '\n', \ + parser->buffer.pointer ++, \ + parser->mark.index ++, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread --) : \ + (CHECK_AT(parser->buffer,'\xC2',0) \ + && CHECK_AT(parser->buffer,'\x85',1)) ? /* NEL -> LF */ \ + (*((string).pointer++) = (yaml_char_t) '\n', \ + parser->buffer.pointer += 2, \ + parser->mark.index ++, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread --) : \ + (CHECK_AT(parser->buffer,'\xE2',0) && \ + CHECK_AT(parser->buffer,'\x80',1) && \ + (CHECK_AT(parser->buffer,'\xA8',2) || \ + CHECK_AT(parser->buffer,'\xA9',2))) ? /* LS|PS -> LS|PS */ \ + (*((string).pointer++) = *(parser->buffer.pointer++), \ + *((string).pointer++) = *(parser->buffer.pointer++), \ + *((string).pointer++) = *(parser->buffer.pointer++), \ + parser->mark.index ++, \ + parser->mark.column = 0, \ + parser->mark.line ++, \ + parser->unread --) : 0), \ + 1) : 0) + +/* + * Public API declarations. + */ + +YAML_DECLARE(int) +yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token); + +/* + * Error handling. + */ + +static int +yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, + yaml_mark_t context_mark, const char *problem); + +/* + * High-level token API. + */ + +YAML_DECLARE(int) +yaml_parser_fetch_more_tokens(yaml_parser_t *parser); + +static int +yaml_parser_fetch_next_token(yaml_parser_t *parser); + +/* + * Potential simple keys. + */ + +static int +yaml_parser_stale_simple_keys(yaml_parser_t *parser); + +static int +yaml_parser_save_simple_key(yaml_parser_t *parser); + +static int +yaml_parser_remove_simple_key(yaml_parser_t *parser); + +static int +yaml_parser_increase_flow_level(yaml_parser_t *parser); + +static int +yaml_parser_decrease_flow_level(yaml_parser_t *parser); + +/* + * Indentation treatment. + */ + +static int +yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column, + ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark); + +static int +yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column); + +/* + * Token fetchers. + */ + +static int +yaml_parser_fetch_stream_start(yaml_parser_t *parser); + +static int +yaml_parser_fetch_stream_end(yaml_parser_t *parser); + +static int +yaml_parser_fetch_directive(yaml_parser_t *parser); + +static int +yaml_parser_fetch_document_indicator(yaml_parser_t *parser, + yaml_token_type_t type); + +static int +yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, + yaml_token_type_t type); + +static int +yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, + yaml_token_type_t type); + +static int +yaml_parser_fetch_flow_entry(yaml_parser_t *parser); + +static int +yaml_parser_fetch_block_entry(yaml_parser_t *parser); + +static int +yaml_parser_fetch_key(yaml_parser_t *parser); + +static int +yaml_parser_fetch_value(yaml_parser_t *parser); + +static int +yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type); + +static int +yaml_parser_fetch_tag(yaml_parser_t *parser); + +static int +yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal); + +static int +yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single); + +static int +yaml_parser_fetch_plain_scalar(yaml_parser_t *parser); + +/* + * Token scanners. + */ + +static int +yaml_parser_scan_to_next_token(yaml_parser_t *parser); + +static int +yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token); + +static int +yaml_parser_scan_directive_name(yaml_parser_t *parser, + yaml_mark_t start_mark, yaml_char_t **name); + +static int +yaml_parser_scan_version_directive_value(yaml_parser_t *parser, + yaml_mark_t start_mark, int *major, int *minor); + +static int +yaml_parser_scan_version_directive_number(yaml_parser_t *parser, + yaml_mark_t start_mark, int *number); + +static int +yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, + yaml_mark_t mark, yaml_char_t **handle, yaml_char_t **prefix); + +static int +yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, + yaml_token_type_t type); + +static int +yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token); + +static int +yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, + yaml_mark_t start_mark, yaml_char_t **handle); + +static int +yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, + yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri); + +static int +yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, + yaml_mark_t start_mark, yaml_string_t *string); + +static int +yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, + int literal); + +static int +yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, + int *indent, yaml_string_t *breaks, + yaml_mark_t start_mark, yaml_mark_t *end_mark); + +static int +yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, + int single); + +static int +yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token); + +/* + * Get the next token. + */ + +YAML_DECLARE(int) +yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token) +{ + assert(parser); /* Non-NULL parser object is expected. */ + assert(token); /* Non-NULL token object is expected. */ + + /* Erase the token object. */ + + memset(token, 0, sizeof(yaml_token_t)); + + /* No tokens after STREAM-END or error. */ + + if (parser->stream_end_produced || parser->error) { + return 1; + } + + /* Ensure that the tokens queue contains enough tokens. */ + + if (!parser->token_available) { + if (!yaml_parser_fetch_more_tokens(parser)) + return 0; + } + + /* Fetch the next token from the queue. */ + + *token = DEQUEUE(parser, parser->tokens); + parser->token_available = 0; + parser->tokens_parsed ++; + + if (token->type == YAML_STREAM_END_TOKEN) { + parser->stream_end_produced = 1; + } + + return 1; +} + +/* + * Set the scanner error and return 0. + */ + +static int +yaml_parser_set_scanner_error(yaml_parser_t *parser, const char *context, + yaml_mark_t context_mark, const char *problem) +{ + parser->error = YAML_SCANNER_ERROR; + parser->context = context; + parser->context_mark = context_mark; + parser->problem = problem; + parser->problem_mark = parser->mark; + + return 0; +} + +/* + * Ensure that the tokens queue contains at least one token which can be + * returned to the Parser. + */ + +YAML_DECLARE(int) +yaml_parser_fetch_more_tokens(yaml_parser_t *parser) +{ + int need_more_tokens; + + /* While we need more tokens to fetch, do it. */ + + while (1) + { + /* + * Check if we really need to fetch more tokens. + */ + + need_more_tokens = 0; + + if (parser->tokens.head == parser->tokens.tail) + { + /* Queue is empty. */ + + need_more_tokens = 1; + } + else + { + yaml_simple_key_t *simple_key; + + /* Check if any potential simple key may occupy the head position. */ + + if (!yaml_parser_stale_simple_keys(parser)) + return 0; + + for (simple_key = parser->simple_keys.start; + simple_key != parser->simple_keys.top; simple_key++) { + if (simple_key->possible + && simple_key->token_number == parser->tokens_parsed) { + need_more_tokens = 1; + break; + } + } + } + + /* We are finished. */ + + if (!need_more_tokens) + break; + + /* Fetch the next token. */ + + if (!yaml_parser_fetch_next_token(parser)) + return 0; + } + + parser->token_available = 1; + + return 1; +} + +/* + * The dispatcher for token fetchers. + */ + +static int +yaml_parser_fetch_next_token(yaml_parser_t *parser) +{ + /* Ensure that the buffer is initialized. */ + + if (!CACHE(parser, 1)) + return 0; + + /* Check if we just started scanning. Fetch STREAM-START then. */ + + if (!parser->stream_start_produced) + return yaml_parser_fetch_stream_start(parser); + + /* Eat whitespaces and comments until we reach the next token. */ + + if (!yaml_parser_scan_to_next_token(parser)) + return 0; + + /* Remove obsolete potential simple keys. */ + + if (!yaml_parser_stale_simple_keys(parser)) + return 0; + + /* Check the indentation level against the current column. */ + + if (!yaml_parser_unroll_indent(parser, parser->mark.column)) + return 0; + + /* + * Ensure that the buffer contains at least 4 characters. 4 is the length + * of the longest indicators ('--- ' and '... '). + */ + + if (!CACHE(parser, 4)) + return 0; + + /* Is it the end of the stream? */ + + if (IS_Z(parser->buffer)) + return yaml_parser_fetch_stream_end(parser); + + /* Is it a directive? */ + + if (parser->mark.column == 0 && CHECK(parser->buffer, '%')) + return yaml_parser_fetch_directive(parser); + + /* Is it the document start indicator? */ + + if (parser->mark.column == 0 + && CHECK_AT(parser->buffer, '-', 0) + && CHECK_AT(parser->buffer, '-', 1) + && CHECK_AT(parser->buffer, '-', 2) + && IS_BLANKZ_AT(parser->buffer, 3)) + return yaml_parser_fetch_document_indicator(parser, + YAML_DOCUMENT_START_TOKEN); + + /* Is it the document end indicator? */ + + if (parser->mark.column == 0 + && CHECK_AT(parser->buffer, '.', 0) + && CHECK_AT(parser->buffer, '.', 1) + && CHECK_AT(parser->buffer, '.', 2) + && IS_BLANKZ_AT(parser->buffer, 3)) + return yaml_parser_fetch_document_indicator(parser, + YAML_DOCUMENT_END_TOKEN); + + /* Is it the flow sequence start indicator? */ + + if (CHECK(parser->buffer, '[')) + return yaml_parser_fetch_flow_collection_start(parser, + YAML_FLOW_SEQUENCE_START_TOKEN); + + /* Is it the flow mapping start indicator? */ + + if (CHECK(parser->buffer, '{')) + return yaml_parser_fetch_flow_collection_start(parser, + YAML_FLOW_MAPPING_START_TOKEN); + + /* Is it the flow sequence end indicator? */ + + if (CHECK(parser->buffer, ']')) + return yaml_parser_fetch_flow_collection_end(parser, + YAML_FLOW_SEQUENCE_END_TOKEN); + + /* Is it the flow mapping end indicator? */ + + if (CHECK(parser->buffer, '}')) + return yaml_parser_fetch_flow_collection_end(parser, + YAML_FLOW_MAPPING_END_TOKEN); + + /* Is it the flow entry indicator? */ + + if (CHECK(parser->buffer, ',')) + return yaml_parser_fetch_flow_entry(parser); + + /* Is it the block entry indicator? */ + + if (CHECK(parser->buffer, '-') && IS_BLANKZ_AT(parser->buffer, 1)) + return yaml_parser_fetch_block_entry(parser); + + /* Is it the key indicator? */ + + if (CHECK(parser->buffer, '?') + && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) + return yaml_parser_fetch_key(parser); + + /* Is it the value indicator? */ + + if (CHECK(parser->buffer, ':') + && (parser->flow_level || IS_BLANKZ_AT(parser->buffer, 1))) + return yaml_parser_fetch_value(parser); + + /* Is it an alias? */ + + if (CHECK(parser->buffer, '*')) + return yaml_parser_fetch_anchor(parser, YAML_ALIAS_TOKEN); + + /* Is it an anchor? */ + + if (CHECK(parser->buffer, '&')) + return yaml_parser_fetch_anchor(parser, YAML_ANCHOR_TOKEN); + + /* Is it a tag? */ + + if (CHECK(parser->buffer, '!')) + return yaml_parser_fetch_tag(parser); + + /* Is it a literal scalar? */ + + if (CHECK(parser->buffer, '|') && !parser->flow_level) + return yaml_parser_fetch_block_scalar(parser, 1); + + /* Is it a folded scalar? */ + + if (CHECK(parser->buffer, '>') && !parser->flow_level) + return yaml_parser_fetch_block_scalar(parser, 0); + + /* Is it a single-quoted scalar? */ + + if (CHECK(parser->buffer, '\'')) + return yaml_parser_fetch_flow_scalar(parser, 1); + + /* Is it a double-quoted scalar? */ + + if (CHECK(parser->buffer, '"')) + return yaml_parser_fetch_flow_scalar(parser, 0); + + /* + * Is it a plain scalar? + * + * A plain scalar may start with any non-blank characters except + * + * '-', '?', ':', ',', '[', ']', '{', '}', + * '#', '&', '*', '!', '|', '>', '\'', '\"', + * '%', '@', '`'. + * + * In the block context (and, for the '-' indicator, in the flow context + * too), it may also start with the characters + * + * '-', '?', ':' + * + * if it is followed by a non-space character. + * + * The last rule is more restrictive than the specification requires. + */ + + if (!(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '-') + || CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':') + || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '[') + || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') + || CHECK(parser->buffer, '}') || CHECK(parser->buffer, '#') + || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '*') + || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '|') + || CHECK(parser->buffer, '>') || CHECK(parser->buffer, '\'') + || CHECK(parser->buffer, '"') || CHECK(parser->buffer, '%') + || CHECK(parser->buffer, '@') || CHECK(parser->buffer, '`')) || + (CHECK(parser->buffer, '-') && !IS_BLANK_AT(parser->buffer, 1)) || + (!parser->flow_level && + (CHECK(parser->buffer, '?') || CHECK(parser->buffer, ':')) + && !IS_BLANKZ_AT(parser->buffer, 1))) + return yaml_parser_fetch_plain_scalar(parser); + + /* + * If we don't determine the token type so far, it is an error. + */ + + return yaml_parser_set_scanner_error(parser, + "while scanning for the next token", parser->mark, + "found character that cannot start any token"); +} + +/* + * Check the list of potential simple keys and remove the positions that + * cannot contain simple keys anymore. + */ + +static int +yaml_parser_stale_simple_keys(yaml_parser_t *parser) +{ + yaml_simple_key_t *simple_key; + + /* Check for a potential simple key for each flow level. */ + + for (simple_key = parser->simple_keys.start; + simple_key != parser->simple_keys.top; simple_key ++) + { + /* + * The specification requires that a simple key + * + * - is limited to a single line, + * - is shorter than 1024 characters. + */ + + if (simple_key->possible + && (simple_key->mark.line < parser->mark.line + || simple_key->mark.index+1024 < parser->mark.index)) { + + /* Check if the potential simple key to be removed is required. */ + + if (simple_key->required) { + return yaml_parser_set_scanner_error(parser, + "while scanning a simple key", simple_key->mark, + "could not find expected ':'"); + } + + simple_key->possible = 0; + } + } + + return 1; +} + +/* + * Check if a simple key may start at the current position and add it if + * needed. + */ + +static int +yaml_parser_save_simple_key(yaml_parser_t *parser) +{ + /* + * A simple key is required at the current position if the scanner is in + * the block context and the current column coincides with the indentation + * level. + */ + + int required = (!parser->flow_level + && parser->indent == (ptrdiff_t)parser->mark.column); + + /* + * A simple key is required only when it is the first token in the current + * line. Therefore it is always allowed. But we add a check anyway. + */ + + assert(parser->simple_key_allowed || !required); /* Impossible. */ + + /* + * If the current position may start a simple key, save it. + */ + + if (parser->simple_key_allowed) + { + yaml_simple_key_t simple_key; + simple_key.possible = 1; + simple_key.required = required; + simple_key.token_number = + parser->tokens_parsed + (parser->tokens.tail - parser->tokens.head); + simple_key.mark = parser->mark; + + if (!yaml_parser_remove_simple_key(parser)) return 0; + + *(parser->simple_keys.top-1) = simple_key; + } + + return 1; +} + +/* + * Remove a potential simple key at the current flow level. + */ + +static int +yaml_parser_remove_simple_key(yaml_parser_t *parser) +{ + yaml_simple_key_t *simple_key = parser->simple_keys.top-1; + + if (simple_key->possible) + { + /* If the key is required, it is an error. */ + + if (simple_key->required) { + return yaml_parser_set_scanner_error(parser, + "while scanning a simple key", simple_key->mark, + "could not find expected ':'"); + } + } + + /* Remove the key from the stack. */ + + simple_key->possible = 0; + + return 1; +} + +/* + * Increase the flow level and resize the simple key list if needed. + */ + +static int +yaml_parser_increase_flow_level(yaml_parser_t *parser) +{ + yaml_simple_key_t empty_simple_key = { 0, 0, 0, { 0, 0, 0 } }; + + /* Reset the simple key on the next level. */ + + if (!PUSH(parser, parser->simple_keys, empty_simple_key)) + return 0; + + /* Increase the flow level. */ + + if (parser->flow_level == INT_MAX) { + parser->error = YAML_MEMORY_ERROR; + return 0; + } + + parser->flow_level++; + + return 1; +} + +/* + * Decrease the flow level. + */ + +static int +yaml_parser_decrease_flow_level(yaml_parser_t *parser) +{ + if (parser->flow_level) { + parser->flow_level --; + (void)POP(parser, parser->simple_keys); + } + + return 1; +} + +/* + * Push the current indentation level to the stack and set the new level + * the current column is greater than the indentation level. In this case, + * append or insert the specified token into the token queue. + * + */ + +static int +yaml_parser_roll_indent(yaml_parser_t *parser, ptrdiff_t column, + ptrdiff_t number, yaml_token_type_t type, yaml_mark_t mark) +{ + yaml_token_t token; + + /* In the flow context, do nothing. */ + + if (parser->flow_level) + return 1; + + if (parser->indent < column) + { + /* + * Push the current indentation level to the stack and set the new + * indentation level. + */ + + if (!PUSH(parser, parser->indents, parser->indent)) + return 0; + +#if PTRDIFF_MAX > INT_MAX + if (column > INT_MAX) { + parser->error = YAML_MEMORY_ERROR; + return 0; + } +#endif + + parser->indent = (int)column; + + /* Create a token and insert it into the queue. */ + + TOKEN_INIT(token, type, mark, mark); + + if (number == -1) { + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + } + else { + if (!QUEUE_INSERT(parser, + parser->tokens, number - parser->tokens_parsed, token)) + return 0; + } + } + + return 1; +} + +/* + * Pop indentation levels from the indents stack until the current level + * becomes less or equal to the column. For each intendation level, append + * the BLOCK-END token. + */ + + +static int +yaml_parser_unroll_indent(yaml_parser_t *parser, ptrdiff_t column) +{ + yaml_token_t token; + + /* In the flow context, do nothing. */ + + if (parser->flow_level) + return 1; + + /* Loop through the intendation levels in the stack. */ + + while (parser->indent > column) + { + /* Create a token and append it to the queue. */ + + TOKEN_INIT(token, YAML_BLOCK_END_TOKEN, parser->mark, parser->mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + /* Pop the indentation level. */ + + parser->indent = POP(parser, parser->indents); + } + + return 1; +} + +/* + * Initialize the scanner and produce the STREAM-START token. + */ + +static int +yaml_parser_fetch_stream_start(yaml_parser_t *parser) +{ + yaml_simple_key_t simple_key = { 0, 0, 0, { 0, 0, 0 } }; + yaml_token_t token; + + /* Set the initial indentation. */ + + parser->indent = -1; + + /* Initialize the simple key stack. */ + + if (!PUSH(parser, parser->simple_keys, simple_key)) + return 0; + + /* A simple key is allowed at the beginning of the stream. */ + + parser->simple_key_allowed = 1; + + /* We have started. */ + + parser->stream_start_produced = 1; + + /* Create the STREAM-START token and append it to the queue. */ + + STREAM_START_TOKEN_INIT(token, parser->encoding, + parser->mark, parser->mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the STREAM-END token and shut down the scanner. + */ + +static int +yaml_parser_fetch_stream_end(yaml_parser_t *parser) +{ + yaml_token_t token; + + /* Force new line. */ + + if (parser->mark.column != 0) { + parser->mark.column = 0; + parser->mark.line ++; + } + + /* Reset the indentation level. */ + + if (!yaml_parser_unroll_indent(parser, -1)) + return 0; + + /* Reset simple keys. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + parser->simple_key_allowed = 0; + + /* Create the STREAM-END token and append it to the queue. */ + + STREAM_END_TOKEN_INIT(token, parser->mark, parser->mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce a VERSION-DIRECTIVE or TAG-DIRECTIVE token. + */ + +static int +yaml_parser_fetch_directive(yaml_parser_t *parser) +{ + yaml_token_t token; + + /* Reset the indentation level. */ + + if (!yaml_parser_unroll_indent(parser, -1)) + return 0; + + /* Reset simple keys. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + parser->simple_key_allowed = 0; + + /* Create the YAML-DIRECTIVE or TAG-DIRECTIVE token. */ + + if (!yaml_parser_scan_directive(parser, &token)) + return 0; + + /* Append the token to the queue. */ + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + + return 1; +} + +/* + * Produce the DOCUMENT-START or DOCUMENT-END token. + */ + +static int +yaml_parser_fetch_document_indicator(yaml_parser_t *parser, + yaml_token_type_t type) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* Reset the indentation level. */ + + if (!yaml_parser_unroll_indent(parser, -1)) + return 0; + + /* Reset simple keys. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + parser->simple_key_allowed = 0; + + /* Consume the token. */ + + start_mark = parser->mark; + + SKIP(parser); + SKIP(parser); + SKIP(parser); + + end_mark = parser->mark; + + /* Create the DOCUMENT-START or DOCUMENT-END token. */ + + TOKEN_INIT(token, type, start_mark, end_mark); + + /* Append the token to the queue. */ + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the FLOW-SEQUENCE-START or FLOW-MAPPING-START token. + */ + +static int +yaml_parser_fetch_flow_collection_start(yaml_parser_t *parser, + yaml_token_type_t type) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* The indicators '[' and '{' may start a simple key. */ + + if (!yaml_parser_save_simple_key(parser)) + return 0; + + /* Increase the flow level. */ + + if (!yaml_parser_increase_flow_level(parser)) + return 0; + + /* A simple key may follow the indicators '[' and '{'. */ + + parser->simple_key_allowed = 1; + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the FLOW-SEQUENCE-START of FLOW-MAPPING-START token. */ + + TOKEN_INIT(token, type, start_mark, end_mark); + + /* Append the token to the queue. */ + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the FLOW-SEQUENCE-END or FLOW-MAPPING-END token. + */ + +static int +yaml_parser_fetch_flow_collection_end(yaml_parser_t *parser, + yaml_token_type_t type) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* Reset any potential simple key on the current flow level. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + /* Decrease the flow level. */ + + if (!yaml_parser_decrease_flow_level(parser)) + return 0; + + /* No simple keys after the indicators ']' and '}'. */ + + parser->simple_key_allowed = 0; + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the FLOW-SEQUENCE-END of FLOW-MAPPING-END token. */ + + TOKEN_INIT(token, type, start_mark, end_mark); + + /* Append the token to the queue. */ + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the FLOW-ENTRY token. + */ + +static int +yaml_parser_fetch_flow_entry(yaml_parser_t *parser) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* Reset any potential simple keys on the current flow level. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + /* Simple keys are allowed after ','. */ + + parser->simple_key_allowed = 1; + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the FLOW-ENTRY token and append it to the queue. */ + + TOKEN_INIT(token, YAML_FLOW_ENTRY_TOKEN, start_mark, end_mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the BLOCK-ENTRY token. + */ + +static int +yaml_parser_fetch_block_entry(yaml_parser_t *parser) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* Check if the scanner is in the block context. */ + + if (!parser->flow_level) + { + /* Check if we are allowed to start a new entry. */ + + if (!parser->simple_key_allowed) { + return yaml_parser_set_scanner_error(parser, NULL, parser->mark, + "block sequence entries are not allowed in this context"); + } + + /* Add the BLOCK-SEQUENCE-START token if needed. */ + + if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, + YAML_BLOCK_SEQUENCE_START_TOKEN, parser->mark)) + return 0; + } + else + { + /* + * It is an error for the '-' indicator to occur in the flow context, + * but we let the Parser detect and report about it because the Parser + * is able to point to the context. + */ + } + + /* Reset any potential simple keys on the current flow level. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + /* Simple keys are allowed after '-'. */ + + parser->simple_key_allowed = 1; + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the BLOCK-ENTRY token and append it to the queue. */ + + TOKEN_INIT(token, YAML_BLOCK_ENTRY_TOKEN, start_mark, end_mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the KEY token. + */ + +static int +yaml_parser_fetch_key(yaml_parser_t *parser) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + + /* In the block context, additional checks are required. */ + + if (!parser->flow_level) + { + /* Check if we are allowed to start a new key (not nessesary simple). */ + + if (!parser->simple_key_allowed) { + return yaml_parser_set_scanner_error(parser, NULL, parser->mark, + "mapping keys are not allowed in this context"); + } + + /* Add the BLOCK-MAPPING-START token if needed. */ + + if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, + YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) + return 0; + } + + /* Reset any potential simple keys on the current flow level. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + /* Simple keys are allowed after '?' in the block context. */ + + parser->simple_key_allowed = (!parser->flow_level); + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the KEY token and append it to the queue. */ + + TOKEN_INIT(token, YAML_KEY_TOKEN, start_mark, end_mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the VALUE token. + */ + +static int +yaml_parser_fetch_value(yaml_parser_t *parser) +{ + yaml_mark_t start_mark, end_mark; + yaml_token_t token; + yaml_simple_key_t *simple_key = parser->simple_keys.top-1; + + /* Have we found a simple key? */ + + if (simple_key->possible) + { + + /* Create the KEY token and insert it into the queue. */ + + TOKEN_INIT(token, YAML_KEY_TOKEN, simple_key->mark, simple_key->mark); + + if (!QUEUE_INSERT(parser, parser->tokens, + simple_key->token_number - parser->tokens_parsed, token)) + return 0; + + /* In the block context, we may need to add the BLOCK-MAPPING-START token. */ + + if (!yaml_parser_roll_indent(parser, simple_key->mark.column, + simple_key->token_number, + YAML_BLOCK_MAPPING_START_TOKEN, simple_key->mark)) + return 0; + + /* Remove the simple key. */ + + simple_key->possible = 0; + + /* A simple key cannot follow another simple key. */ + + parser->simple_key_allowed = 0; + } + else + { + /* The ':' indicator follows a complex key. */ + + /* In the block context, extra checks are required. */ + + if (!parser->flow_level) + { + /* Check if we are allowed to start a complex value. */ + + if (!parser->simple_key_allowed) { + return yaml_parser_set_scanner_error(parser, NULL, parser->mark, + "mapping values are not allowed in this context"); + } + + /* Add the BLOCK-MAPPING-START token if needed. */ + + if (!yaml_parser_roll_indent(parser, parser->mark.column, -1, + YAML_BLOCK_MAPPING_START_TOKEN, parser->mark)) + return 0; + } + + /* Simple keys after ':' are allowed in the block context. */ + + parser->simple_key_allowed = (!parser->flow_level); + } + + /* Consume the token. */ + + start_mark = parser->mark; + SKIP(parser); + end_mark = parser->mark; + + /* Create the VALUE token and append it to the queue. */ + + TOKEN_INIT(token, YAML_VALUE_TOKEN, start_mark, end_mark); + + if (!ENQUEUE(parser, parser->tokens, token)) + return 0; + + return 1; +} + +/* + * Produce the ALIAS or ANCHOR token. + */ + +static int +yaml_parser_fetch_anchor(yaml_parser_t *parser, yaml_token_type_t type) +{ + yaml_token_t token; + + /* An anchor or an alias could be a simple key. */ + + if (!yaml_parser_save_simple_key(parser)) + return 0; + + /* A simple key cannot follow an anchor or an alias. */ + + parser->simple_key_allowed = 0; + + /* Create the ALIAS or ANCHOR token and append it to the queue. */ + + if (!yaml_parser_scan_anchor(parser, &token, type)) + return 0; + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + return 1; +} + +/* + * Produce the TAG token. + */ + +static int +yaml_parser_fetch_tag(yaml_parser_t *parser) +{ + yaml_token_t token; + + /* A tag could be a simple key. */ + + if (!yaml_parser_save_simple_key(parser)) + return 0; + + /* A simple key cannot follow a tag. */ + + parser->simple_key_allowed = 0; + + /* Create the TAG token and append it to the queue. */ + + if (!yaml_parser_scan_tag(parser, &token)) + return 0; + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + + return 1; +} + +/* + * Produce the SCALAR(...,literal) or SCALAR(...,folded) tokens. + */ + +static int +yaml_parser_fetch_block_scalar(yaml_parser_t *parser, int literal) +{ + yaml_token_t token; + + /* Remove any potential simple keys. */ + + if (!yaml_parser_remove_simple_key(parser)) + return 0; + + /* A simple key may follow a block scalar. */ + + parser->simple_key_allowed = 1; + + /* Create the SCALAR token and append it to the queue. */ + + if (!yaml_parser_scan_block_scalar(parser, &token, literal)) + return 0; + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + + return 1; +} + +/* + * Produce the SCALAR(...,single-quoted) or SCALAR(...,double-quoted) tokens. + */ + +static int +yaml_parser_fetch_flow_scalar(yaml_parser_t *parser, int single) +{ + yaml_token_t token; + + /* A plain scalar could be a simple key. */ + + if (!yaml_parser_save_simple_key(parser)) + return 0; + + /* A simple key cannot follow a flow scalar. */ + + parser->simple_key_allowed = 0; + + /* Create the SCALAR token and append it to the queue. */ + + if (!yaml_parser_scan_flow_scalar(parser, &token, single)) + return 0; + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + + return 1; +} + +/* + * Produce the SCALAR(...,plain) token. + */ + +static int +yaml_parser_fetch_plain_scalar(yaml_parser_t *parser) +{ + yaml_token_t token; + + /* A plain scalar could be a simple key. */ + + if (!yaml_parser_save_simple_key(parser)) + return 0; + + /* A simple key cannot follow a flow scalar. */ + + parser->simple_key_allowed = 0; + + /* Create the SCALAR token and append it to the queue. */ + + if (!yaml_parser_scan_plain_scalar(parser, &token)) + return 0; + + if (!ENQUEUE(parser, parser->tokens, token)) { + yaml_token_delete(&token); + return 0; + } + + return 1; +} + +/* + * Eat whitespaces and comments until the next token is found. + */ + +static int +yaml_parser_scan_to_next_token(yaml_parser_t *parser) +{ + /* Until the next token is not found. */ + + while (1) + { + /* Allow the BOM mark to start a line. */ + + if (!CACHE(parser, 1)) return 0; + + if (parser->mark.column == 0 && IS_BOM(parser->buffer)) + SKIP(parser); + + /* + * Eat whitespaces. + * + * Tabs are allowed: + * + * - in the flow context; + * - in the block context, but not at the beginning of the line or + * after '-', '?', or ':' (complex value). + */ + + if (!CACHE(parser, 1)) return 0; + + while (CHECK(parser->buffer,' ') || + ((parser->flow_level || !parser->simple_key_allowed) && + CHECK(parser->buffer, '\t'))) { + SKIP(parser); + if (!CACHE(parser, 1)) return 0; + } + + /* Eat a comment until a line break. */ + + if (CHECK(parser->buffer, '#')) { + while (!IS_BREAKZ(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) return 0; + } + } + + /* If it is a line break, eat it. */ + + if (IS_BREAK(parser->buffer)) + { + if (!CACHE(parser, 2)) return 0; + SKIP_LINE(parser); + + /* In the block context, a new line may start a simple key. */ + + if (!parser->flow_level) { + parser->simple_key_allowed = 1; + } + } + else + { + /* We have found a token. */ + + break; + } + } + + return 1; +} + +/* + * Scan a YAML-DIRECTIVE or TAG-DIRECTIVE token. + * + * Scope: + * %YAML 1.1 # a comment \n + * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + * %TAG !yaml! tag:yaml.org,2002: \n + * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + */ + +int +yaml_parser_scan_directive(yaml_parser_t *parser, yaml_token_t *token) +{ + yaml_mark_t start_mark, end_mark; + yaml_char_t *name = NULL; + int major, minor; + yaml_char_t *handle = NULL, *prefix = NULL; + + /* Eat '%'. */ + + start_mark = parser->mark; + + SKIP(parser); + + /* Scan the directive name. */ + + if (!yaml_parser_scan_directive_name(parser, start_mark, &name)) + goto error; + + /* Is it a YAML directive? */ + + if (strcmp((char *)name, "YAML") == 0) + { + /* Scan the VERSION directive value. */ + + if (!yaml_parser_scan_version_directive_value(parser, start_mark, + &major, &minor)) + goto error; + + end_mark = parser->mark; + + /* Create a VERSION-DIRECTIVE token. */ + + VERSION_DIRECTIVE_TOKEN_INIT(*token, major, minor, + start_mark, end_mark); + } + + /* Is it a TAG directive? */ + + else if (strcmp((char *)name, "TAG") == 0) + { + /* Scan the TAG directive value. */ + + if (!yaml_parser_scan_tag_directive_value(parser, start_mark, + &handle, &prefix)) + goto error; + + end_mark = parser->mark; + + /* Create a TAG-DIRECTIVE token. */ + + TAG_DIRECTIVE_TOKEN_INIT(*token, handle, prefix, + start_mark, end_mark); + } + + /* Unknown directive. */ + + else + { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "found uknown directive name"); + goto error; + } + + /* Eat the rest of the line including any comments. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_BLANK(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + + if (CHECK(parser->buffer, '#')) { + while (!IS_BREAKZ(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + } + + /* Check if we are at the end of the line. */ + + if (!IS_BREAKZ(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "did not find expected comment or line break"); + goto error; + } + + /* Eat a line break. */ + + if (IS_BREAK(parser->buffer)) { + if (!CACHE(parser, 2)) goto error; + SKIP_LINE(parser); + } + + yaml_free(name); + + return 1; + +error: + yaml_free(prefix); + yaml_free(handle); + yaml_free(name); + return 0; +} + +/* + * Scan the directive name. + * + * Scope: + * %YAML 1.1 # a comment \n + * ^^^^ + * %TAG !yaml! tag:yaml.org,2002: \n + * ^^^ + */ + +static int +yaml_parser_scan_directive_name(yaml_parser_t *parser, + yaml_mark_t start_mark, yaml_char_t **name) +{ + yaml_string_t string = NULL_STRING; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + + /* Consume the directive name. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_ALPHA(parser->buffer)) + { + if (!READ(parser, string)) goto error; + if (!CACHE(parser, 1)) goto error; + } + + /* Check if the name is empty. */ + + if (string.start == string.pointer) { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "could not find expected directive name"); + goto error; + } + + /* Check for an blank character after the name. */ + + if (!IS_BLANKZ(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a directive", + start_mark, "found unexpected non-alphabetical character"); + goto error; + } + + *name = string.start; + + return 1; + +error: + STRING_DEL(parser, string); + return 0; +} + +/* + * Scan the value of VERSION-DIRECTIVE. + * + * Scope: + * %YAML 1.1 # a comment \n + * ^^^^^^ + */ + +static int +yaml_parser_scan_version_directive_value(yaml_parser_t *parser, + yaml_mark_t start_mark, int *major, int *minor) +{ + /* Eat whitespaces. */ + + if (!CACHE(parser, 1)) return 0; + + while (IS_BLANK(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) return 0; + } + + /* Consume the major version number. */ + + if (!yaml_parser_scan_version_directive_number(parser, start_mark, major)) + return 0; + + /* Eat '.'. */ + + if (!CHECK(parser->buffer, '.')) { + return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", + start_mark, "did not find expected digit or '.' character"); + } + + SKIP(parser); + + /* Consume the minor version number. */ + + if (!yaml_parser_scan_version_directive_number(parser, start_mark, minor)) + return 0; + + return 1; +} + +#define MAX_NUMBER_LENGTH 9 + +/* + * Scan the version number of VERSION-DIRECTIVE. + * + * Scope: + * %YAML 1.1 # a comment \n + * ^ + * %YAML 1.1 # a comment \n + * ^ + */ + +static int +yaml_parser_scan_version_directive_number(yaml_parser_t *parser, + yaml_mark_t start_mark, int *number) +{ + int value = 0; + size_t length = 0; + + /* Repeat while the next character is digit. */ + + if (!CACHE(parser, 1)) return 0; + + while (IS_DIGIT(parser->buffer)) + { + /* Check if the number is too long. */ + + if (++length > MAX_NUMBER_LENGTH) { + return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", + start_mark, "found extremely long version number"); + } + + value = value*10 + AS_DIGIT(parser->buffer); + + SKIP(parser); + + if (!CACHE(parser, 1)) return 0; + } + + /* Check if the number was present. */ + + if (!length) { + return yaml_parser_set_scanner_error(parser, "while scanning a %YAML directive", + start_mark, "did not find expected version number"); + } + + *number = value; + + return 1; +} + +/* + * Scan the value of a TAG-DIRECTIVE token. + * + * Scope: + * %TAG !yaml! tag:yaml.org,2002: \n + * ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + */ + +static int +yaml_parser_scan_tag_directive_value(yaml_parser_t *parser, + yaml_mark_t start_mark, yaml_char_t **handle, yaml_char_t **prefix) +{ + yaml_char_t *handle_value = NULL; + yaml_char_t *prefix_value = NULL; + + /* Eat whitespaces. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_BLANK(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + + /* Scan a handle. */ + + if (!yaml_parser_scan_tag_handle(parser, 1, start_mark, &handle_value)) + goto error; + + /* Expect a whitespace. */ + + if (!CACHE(parser, 1)) goto error; + + if (!IS_BLANK(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", + start_mark, "did not find expected whitespace"); + goto error; + } + + /* Eat whitespaces. */ + + while (IS_BLANK(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + + /* Scan a prefix. */ + + if (!yaml_parser_scan_tag_uri(parser, 1, NULL, start_mark, &prefix_value)) + goto error; + + /* Expect a whitespace or line break. */ + + if (!CACHE(parser, 1)) goto error; + + if (!IS_BLANKZ(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a %TAG directive", + start_mark, "did not find expected whitespace or line break"); + goto error; + } + + *handle = handle_value; + *prefix = prefix_value; + + return 1; + +error: + yaml_free(handle_value); + yaml_free(prefix_value); + return 0; +} + +static int +yaml_parser_scan_anchor(yaml_parser_t *parser, yaml_token_t *token, + yaml_token_type_t type) +{ + int length = 0; + yaml_mark_t start_mark, end_mark; + yaml_string_t string = NULL_STRING; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + + /* Eat the indicator character. */ + + start_mark = parser->mark; + + SKIP(parser); + + /* Consume the value. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_ALPHA(parser->buffer)) { + if (!READ(parser, string)) goto error; + if (!CACHE(parser, 1)) goto error; + length ++; + } + + end_mark = parser->mark; + + /* + * Check if length of the anchor is greater than 0 and it is followed by + * a whitespace character or one of the indicators: + * + * '?', ':', ',', ']', '}', '%', '@', '`'. + */ + + if (!length || !(IS_BLANKZ(parser->buffer) || CHECK(parser->buffer, '?') + || CHECK(parser->buffer, ':') || CHECK(parser->buffer, ',') + || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '}') + || CHECK(parser->buffer, '%') || CHECK(parser->buffer, '@') + || CHECK(parser->buffer, '`'))) { + yaml_parser_set_scanner_error(parser, type == YAML_ANCHOR_TOKEN ? + "while scanning an anchor" : "while scanning an alias", start_mark, + "did not find expected alphabetic or numeric character"); + goto error; + } + + /* Create a token. */ + + if (type == YAML_ANCHOR_TOKEN) { + ANCHOR_TOKEN_INIT(*token, string.start, start_mark, end_mark); + } + else { + ALIAS_TOKEN_INIT(*token, string.start, start_mark, end_mark); + } + + return 1; + +error: + STRING_DEL(parser, string); + return 0; +} + +/* + * Scan a TAG token. + */ + +static int +yaml_parser_scan_tag(yaml_parser_t *parser, yaml_token_t *token) +{ + yaml_char_t *handle = NULL; + yaml_char_t *suffix = NULL; + yaml_mark_t start_mark, end_mark; + + start_mark = parser->mark; + + /* Check if the tag is in the canonical form. */ + + if (!CACHE(parser, 2)) goto error; + + if (CHECK_AT(parser->buffer, '<', 1)) + { + /* Set the handle to '' */ + + handle = yaml_malloc(1); + if (!handle) goto error; + handle[0] = '\0'; + + /* Eat '!<' */ + + SKIP(parser); + SKIP(parser); + + /* Consume the tag value. */ + + if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) + goto error; + + /* Check for '>' and eat it. */ + + if (!CHECK(parser->buffer, '>')) { + yaml_parser_set_scanner_error(parser, "while scanning a tag", + start_mark, "did not find the expected '>'"); + goto error; + } + + SKIP(parser); + } + else + { + /* The tag has either the '!suffix' or the '!handle!suffix' form. */ + + /* First, try to scan a handle. */ + + if (!yaml_parser_scan_tag_handle(parser, 0, start_mark, &handle)) + goto error; + + /* Check if it is, indeed, handle. */ + + if (handle[0] == '!' && handle[1] != '\0' && handle[strlen((char *)handle)-1] == '!') + { + /* Scan the suffix now. */ + + if (!yaml_parser_scan_tag_uri(parser, 0, NULL, start_mark, &suffix)) + goto error; + } + else + { + /* It wasn't a handle after all. Scan the rest of the tag. */ + + if (!yaml_parser_scan_tag_uri(parser, 0, handle, start_mark, &suffix)) + goto error; + + /* Set the handle to '!'. */ + + yaml_free(handle); + handle = yaml_malloc(2); + if (!handle) goto error; + handle[0] = '!'; + handle[1] = '\0'; + + /* + * A special case: the '!' tag. Set the handle to '' and the + * suffix to '!'. + */ + + if (suffix[0] == '\0') { + yaml_char_t *tmp = handle; + handle = suffix; + suffix = tmp; + } + } + } + + /* Check the character which ends the tag. */ + + if (!CACHE(parser, 1)) goto error; + + if (!IS_BLANKZ(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a tag", + start_mark, "did not find expected whitespace or line break"); + goto error; + } + + end_mark = parser->mark; + + /* Create a token. */ + + TAG_TOKEN_INIT(*token, handle, suffix, start_mark, end_mark); + + return 1; + +error: + yaml_free(handle); + yaml_free(suffix); + return 0; +} + +/* + * Scan a tag handle. + */ + +static int +yaml_parser_scan_tag_handle(yaml_parser_t *parser, int directive, + yaml_mark_t start_mark, yaml_char_t **handle) +{ + yaml_string_t string = NULL_STRING; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + + /* Check the initial '!' character. */ + + if (!CACHE(parser, 1)) goto error; + + if (!CHECK(parser->buffer, '!')) { + yaml_parser_set_scanner_error(parser, directive ? + "while scanning a tag directive" : "while scanning a tag", + start_mark, "did not find expected '!'"); + goto error; + } + + /* Copy the '!' character. */ + + if (!READ(parser, string)) goto error; + + /* Copy all subsequent alphabetical and numerical characters. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_ALPHA(parser->buffer)) + { + if (!READ(parser, string)) goto error; + if (!CACHE(parser, 1)) goto error; + } + + /* Check if the trailing character is '!' and copy it. */ + + if (CHECK(parser->buffer, '!')) + { + if (!READ(parser, string)) goto error; + } + else + { + /* + * It's either the '!' tag or not really a tag handle. If it's a %TAG + * directive, it's an error. If it's a tag token, it must be a part of + * URI. + */ + + if (directive && !(string.start[0] == '!' && string.start[1] == '\0')) { + yaml_parser_set_scanner_error(parser, "while parsing a tag directive", + start_mark, "did not find expected '!'"); + goto error; + } + } + + *handle = string.start; + + return 1; + +error: + STRING_DEL(parser, string); + return 0; +} + +/* + * Scan a tag. + */ + +static int +yaml_parser_scan_tag_uri(yaml_parser_t *parser, int directive, + yaml_char_t *head, yaml_mark_t start_mark, yaml_char_t **uri) +{ + size_t length = head ? strlen((char *)head) : 0; + yaml_string_t string = NULL_STRING; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + + /* Resize the string to include the head. */ + + while ((size_t)(string.end - string.start) <= length) { + if (!yaml_string_extend(&string.start, &string.pointer, &string.end)) { + parser->error = YAML_MEMORY_ERROR; + goto error; + } + } + + /* + * Copy the head if needed. + * + * Note that we don't copy the leading '!' character. + */ + + if (length > 1) { + memcpy(string.start, head+1, length-1); + string.pointer += length-1; + } + + /* Scan the tag. */ + + if (!CACHE(parser, 1)) goto error; + + /* + * The set of characters that may appear in URI is as follows: + * + * '0'-'9', 'A'-'Z', 'a'-'z', '_', '-', ';', '/', '?', ':', '@', '&', + * '=', '+', '$', ',', '.', '!', '~', '*', '\'', '(', ')', '[', ']', + * '%'. + */ + + while (IS_ALPHA(parser->buffer) || CHECK(parser->buffer, ';') + || CHECK(parser->buffer, '/') || CHECK(parser->buffer, '?') + || CHECK(parser->buffer, ':') || CHECK(parser->buffer, '@') + || CHECK(parser->buffer, '&') || CHECK(parser->buffer, '=') + || CHECK(parser->buffer, '+') || CHECK(parser->buffer, '$') + || CHECK(parser->buffer, ',') || CHECK(parser->buffer, '.') + || CHECK(parser->buffer, '!') || CHECK(parser->buffer, '~') + || CHECK(parser->buffer, '*') || CHECK(parser->buffer, '\'') + || CHECK(parser->buffer, '(') || CHECK(parser->buffer, ')') + || CHECK(parser->buffer, '[') || CHECK(parser->buffer, ']') + || CHECK(parser->buffer, '%')) + { + /* Check if it is a URI-escape sequence. */ + + if (CHECK(parser->buffer, '%')) { + if (!STRING_EXTEND(parser, string)) + goto error; + + if (!yaml_parser_scan_uri_escapes(parser, + directive, start_mark, &string)) goto error; + } + else { + if (!READ(parser, string)) goto error; + } + + length ++; + if (!CACHE(parser, 1)) goto error; + } + + /* Check if the tag is non-empty. */ + + if (!length) { + if (!STRING_EXTEND(parser, string)) + goto error; + + yaml_parser_set_scanner_error(parser, directive ? + "while parsing a %TAG directive" : "while parsing a tag", + start_mark, "did not find expected tag URI"); + goto error; + } + + *uri = string.start; + + return 1; + +error: + STRING_DEL(parser, string); + return 0; +} + +/* + * Decode an URI-escape sequence corresponding to a single UTF-8 character. + */ + +static int +yaml_parser_scan_uri_escapes(yaml_parser_t *parser, int directive, + yaml_mark_t start_mark, yaml_string_t *string) +{ + int width = 0; + + /* Decode the required number of characters. */ + + do { + + unsigned char octet = 0; + + /* Check for a URI-escaped octet. */ + + if (!CACHE(parser, 3)) return 0; + + if (!(CHECK(parser->buffer, '%') + && IS_HEX_AT(parser->buffer, 1) + && IS_HEX_AT(parser->buffer, 2))) { + return yaml_parser_set_scanner_error(parser, directive ? + "while parsing a %TAG directive" : "while parsing a tag", + start_mark, "did not find URI escaped octet"); + } + + /* Get the octet. */ + + octet = (AS_HEX_AT(parser->buffer, 1) << 4) + AS_HEX_AT(parser->buffer, 2); + + /* If it is the leading octet, determine the length of the UTF-8 sequence. */ + + if (!width) + { + width = (octet & 0x80) == 0x00 ? 1 : + (octet & 0xE0) == 0xC0 ? 2 : + (octet & 0xF0) == 0xE0 ? 3 : + (octet & 0xF8) == 0xF0 ? 4 : 0; + if (!width) { + return yaml_parser_set_scanner_error(parser, directive ? + "while parsing a %TAG directive" : "while parsing a tag", + start_mark, "found an incorrect leading UTF-8 octet"); + } + } + else + { + /* Check if the trailing octet is correct. */ + + if ((octet & 0xC0) != 0x80) { + return yaml_parser_set_scanner_error(parser, directive ? + "while parsing a %TAG directive" : "while parsing a tag", + start_mark, "found an incorrect trailing UTF-8 octet"); + } + } + + /* Copy the octet and move the pointers. */ + + *(string->pointer++) = octet; + SKIP(parser); + SKIP(parser); + SKIP(parser); + + } while (--width); + + return 1; +} + +/* + * Scan a block scalar. + */ + +static int +yaml_parser_scan_block_scalar(yaml_parser_t *parser, yaml_token_t *token, + int literal) +{ + yaml_mark_t start_mark; + yaml_mark_t end_mark; + yaml_string_t string = NULL_STRING; + yaml_string_t leading_break = NULL_STRING; + yaml_string_t trailing_breaks = NULL_STRING; + int chomping = 0; + int increment = 0; + int indent = 0; + int leading_blank = 0; + int trailing_blank = 0; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; + + /* Eat the indicator '|' or '>'. */ + + start_mark = parser->mark; + + SKIP(parser); + + /* Scan the additional block scalar indicators. */ + + if (!CACHE(parser, 1)) goto error; + + /* Check for a chomping indicator. */ + + if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) + { + /* Set the chomping method and eat the indicator. */ + + chomping = CHECK(parser->buffer, '+') ? +1 : -1; + + SKIP(parser); + + /* Check for an indentation indicator. */ + + if (!CACHE(parser, 1)) goto error; + + if (IS_DIGIT(parser->buffer)) + { + /* Check that the intendation is greater than 0. */ + + if (CHECK(parser->buffer, '0')) { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "found an intendation indicator equal to 0"); + goto error; + } + + /* Get the intendation level and eat the indicator. */ + + increment = AS_DIGIT(parser->buffer); + + SKIP(parser); + } + } + + /* Do the same as above, but in the opposite order. */ + + else if (IS_DIGIT(parser->buffer)) + { + if (CHECK(parser->buffer, '0')) { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "found an intendation indicator equal to 0"); + goto error; + } + + increment = AS_DIGIT(parser->buffer); + + SKIP(parser); + + if (!CACHE(parser, 1)) goto error; + + if (CHECK(parser->buffer, '+') || CHECK(parser->buffer, '-')) { + chomping = CHECK(parser->buffer, '+') ? +1 : -1; + + SKIP(parser); + } + } + + /* Eat whitespaces and comments to the end of the line. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_BLANK(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + + if (CHECK(parser->buffer, '#')) { + while (!IS_BREAKZ(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) goto error; + } + } + + /* Check if we are at the end of the line. */ + + if (!IS_BREAKZ(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "did not find expected comment or line break"); + goto error; + } + + /* Eat a line break. */ + + if (IS_BREAK(parser->buffer)) { + if (!CACHE(parser, 2)) goto error; + SKIP_LINE(parser); + } + + end_mark = parser->mark; + + /* Set the intendation level if it was specified. */ + + if (increment) { + indent = parser->indent >= 0 ? parser->indent+increment : increment; + } + + /* Scan the leading line breaks and determine the indentation level if needed. */ + + if (!yaml_parser_scan_block_scalar_breaks(parser, &indent, &trailing_breaks, + start_mark, &end_mark)) goto error; + + /* Scan the block scalar content. */ + + if (!CACHE(parser, 1)) goto error; + + while ((int)parser->mark.column == indent && !IS_Z(parser->buffer)) + { + /* + * We are at the beginning of a non-empty line. + */ + + /* Is it a trailing whitespace? */ + + trailing_blank = IS_BLANK(parser->buffer); + + /* Check if we need to fold the leading line break. */ + + if (!literal && (*leading_break.start == '\n') + && !leading_blank && !trailing_blank) + { + /* Do we need to join the lines by space? */ + + if (*trailing_breaks.start == '\0') { + if (!STRING_EXTEND(parser, string)) goto error; + *(string.pointer ++) = ' '; + } + + CLEAR(parser, leading_break); + } + else { + if (!JOIN(parser, string, leading_break)) goto error; + CLEAR(parser, leading_break); + } + + /* Append the remaining line breaks. */ + + if (!JOIN(parser, string, trailing_breaks)) goto error; + CLEAR(parser, trailing_breaks); + + /* Is it a leading whitespace? */ + + leading_blank = IS_BLANK(parser->buffer); + + /* Consume the current line. */ + + while (!IS_BREAKZ(parser->buffer)) { + if (!READ(parser, string)) goto error; + if (!CACHE(parser, 1)) goto error; + } + + /* Consume the line break. */ + + if (!CACHE(parser, 2)) goto error; + + if (!READ_LINE(parser, leading_break)) goto error; + + /* Eat the following intendation spaces and line breaks. */ + + if (!yaml_parser_scan_block_scalar_breaks(parser, + &indent, &trailing_breaks, start_mark, &end_mark)) goto error; + } + + /* Chomp the tail. */ + + if (chomping != -1) { + if (!JOIN(parser, string, leading_break)) goto error; + } + if (chomping == 1) { + if (!JOIN(parser, string, trailing_breaks)) goto error; + } + + /* Create a token. */ + + SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, + literal ? YAML_LITERAL_SCALAR_STYLE : YAML_FOLDED_SCALAR_STYLE, + start_mark, end_mark); + + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + + return 1; + +error: + STRING_DEL(parser, string); + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + + return 0; +} + +/* + * Scan intendation spaces and line breaks for a block scalar. Determine the + * intendation level if needed. + */ + +static int +yaml_parser_scan_block_scalar_breaks(yaml_parser_t *parser, + int *indent, yaml_string_t *breaks, + yaml_mark_t start_mark, yaml_mark_t *end_mark) +{ + int max_indent = 0; + + *end_mark = parser->mark; + + /* Eat the intendation spaces and line breaks. */ + + while (1) + { + /* Eat the intendation spaces. */ + + if (!CACHE(parser, 1)) return 0; + + while ((!*indent || (int)parser->mark.column < *indent) + && IS_SPACE(parser->buffer)) { + SKIP(parser); + if (!CACHE(parser, 1)) return 0; + } + + if ((int)parser->mark.column > max_indent) + max_indent = (int)parser->mark.column; + + /* Check for a tab character messing the intendation. */ + + if ((!*indent || (int)parser->mark.column < *indent) + && IS_TAB(parser->buffer)) { + return yaml_parser_set_scanner_error(parser, "while scanning a block scalar", + start_mark, "found a tab character where an intendation space is expected"); + } + + /* Have we found a non-empty line? */ + + if (!IS_BREAK(parser->buffer)) break; + + /* Consume the line break. */ + + if (!CACHE(parser, 2)) return 0; + if (!READ_LINE(parser, *breaks)) return 0; + *end_mark = parser->mark; + } + + /* Determine the indentation level if needed. */ + + if (!*indent) { + *indent = max_indent; + if (*indent < parser->indent + 1) + *indent = parser->indent + 1; + if (*indent < 1) + *indent = 1; + } + + return 1; +} + +/* + * Scan a quoted scalar. + */ + +static int +yaml_parser_scan_flow_scalar(yaml_parser_t *parser, yaml_token_t *token, + int single) +{ + yaml_mark_t start_mark; + yaml_mark_t end_mark; + yaml_string_t string = NULL_STRING; + yaml_string_t leading_break = NULL_STRING; + yaml_string_t trailing_breaks = NULL_STRING; + yaml_string_t whitespaces = NULL_STRING; + int leading_blanks; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; + + /* Eat the left quote. */ + + start_mark = parser->mark; + + SKIP(parser); + + /* Consume the content of the quoted scalar. */ + + while (1) + { + /* Check that there are no document indicators at the beginning of the line. */ + + if (!CACHE(parser, 4)) goto error; + + if (parser->mark.column == 0 && + ((CHECK_AT(parser->buffer, '-', 0) && + CHECK_AT(parser->buffer, '-', 1) && + CHECK_AT(parser->buffer, '-', 2)) || + (CHECK_AT(parser->buffer, '.', 0) && + CHECK_AT(parser->buffer, '.', 1) && + CHECK_AT(parser->buffer, '.', 2))) && + IS_BLANKZ_AT(parser->buffer, 3)) + { + yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", + start_mark, "found unexpected document indicator"); + goto error; + } + + /* Check for EOF. */ + + if (IS_Z(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a quoted scalar", + start_mark, "found unexpected end of stream"); + goto error; + } + + /* Consume non-blank characters. */ + + if (!CACHE(parser, 2)) goto error; + + leading_blanks = 0; + + while (!IS_BLANKZ(parser->buffer)) + { + /* Check for an escaped single quote. */ + + if (single && CHECK_AT(parser->buffer, '\'', 0) + && CHECK_AT(parser->buffer, '\'', 1)) + { + if (!STRING_EXTEND(parser, string)) goto error; + *(string.pointer++) = '\''; + SKIP(parser); + SKIP(parser); + } + + /* Check for the right quote. */ + + else if (CHECK(parser->buffer, single ? '\'' : '"')) + { + break; + } + + /* Check for an escaped line break. */ + + else if (!single && CHECK(parser->buffer, '\\') + && IS_BREAK_AT(parser->buffer, 1)) + { + if (!CACHE(parser, 3)) goto error; + SKIP(parser); + SKIP_LINE(parser); + leading_blanks = 1; + break; + } + + /* Check for an escape sequence. */ + + else if (!single && CHECK(parser->buffer, '\\')) + { + size_t code_length = 0; + + if (!STRING_EXTEND(parser, string)) goto error; + + /* Check the escape character. */ + + switch (parser->buffer.pointer[1]) + { + case '0': + *(string.pointer++) = '\0'; + break; + + case 'a': + *(string.pointer++) = '\x07'; + break; + + case 'b': + *(string.pointer++) = '\x08'; + break; + + case 't': + case '\t': + *(string.pointer++) = '\x09'; + break; + + case 'n': + *(string.pointer++) = '\x0A'; + break; + + case 'v': + *(string.pointer++) = '\x0B'; + break; + + case 'f': + *(string.pointer++) = '\x0C'; + break; + + case 'r': + *(string.pointer++) = '\x0D'; + break; + + case 'e': + *(string.pointer++) = '\x1B'; + break; + + case ' ': + *(string.pointer++) = '\x20'; + break; + + case '"': + *(string.pointer++) = '"'; + break; + + case '\'': + *(string.pointer++) = '\''; + break; + + case '\\': + *(string.pointer++) = '\\'; + break; + + case 'N': /* NEL (#x85) */ + *(string.pointer++) = '\xC2'; + *(string.pointer++) = '\x85'; + break; + + case '_': /* #xA0 */ + *(string.pointer++) = '\xC2'; + *(string.pointer++) = '\xA0'; + break; + + case 'L': /* LS (#x2028) */ + *(string.pointer++) = '\xE2'; + *(string.pointer++) = '\x80'; + *(string.pointer++) = '\xA8'; + break; + + case 'P': /* PS (#x2029) */ + *(string.pointer++) = '\xE2'; + *(string.pointer++) = '\x80'; + *(string.pointer++) = '\xA9'; + break; + + case 'x': + code_length = 2; + break; + + case 'u': + code_length = 4; + break; + + case 'U': + code_length = 8; + break; + + default: + yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", + start_mark, "found unknown escape character"); + goto error; + } + + SKIP(parser); + SKIP(parser); + + /* Consume an arbitrary escape code. */ + + if (code_length) + { + unsigned int value = 0; + size_t k; + + /* Scan the character value. */ + + if (!CACHE(parser, code_length)) goto error; + + for (k = 0; k < code_length; k ++) { + if (!IS_HEX_AT(parser->buffer, k)) { + yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", + start_mark, "did not find expected hexdecimal number"); + goto error; + } + value = (value << 4) + AS_HEX_AT(parser->buffer, k); + } + + /* Check the value and write the character. */ + + if ((value >= 0xD800 && value <= 0xDFFF) || value > 0x10FFFF) { + yaml_parser_set_scanner_error(parser, "while parsing a quoted scalar", + start_mark, "found invalid Unicode character escape code"); + goto error; + } + + if (value <= 0x7F) { + *(string.pointer++) = value; + } + else if (value <= 0x7FF) { + *(string.pointer++) = 0xC0 + (value >> 6); + *(string.pointer++) = 0x80 + (value & 0x3F); + } + else if (value <= 0xFFFF) { + *(string.pointer++) = 0xE0 + (value >> 12); + *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); + *(string.pointer++) = 0x80 + (value & 0x3F); + } + else { + *(string.pointer++) = 0xF0 + (value >> 18); + *(string.pointer++) = 0x80 + ((value >> 12) & 0x3F); + *(string.pointer++) = 0x80 + ((value >> 6) & 0x3F); + *(string.pointer++) = 0x80 + (value & 0x3F); + } + + /* Advance the pointer. */ + + for (k = 0; k < code_length; k ++) { + SKIP(parser); + } + } + } + + else + { + /* It is a non-escaped non-blank character. */ + + if (!READ(parser, string)) goto error; + } + + if (!CACHE(parser, 2)) goto error; + } + + /* Check if we are at the end of the scalar. */ + + if (CHECK(parser->buffer, single ? '\'' : '"')) + break; + + /* Consume blank characters. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) + { + if (IS_BLANK(parser->buffer)) + { + /* Consume a space or a tab character. */ + + if (!leading_blanks) { + if (!READ(parser, whitespaces)) goto error; + } + else { + SKIP(parser); + } + } + else + { + if (!CACHE(parser, 2)) goto error; + + /* Check if it is a first line break. */ + + if (!leading_blanks) + { + CLEAR(parser, whitespaces); + if (!READ_LINE(parser, leading_break)) goto error; + leading_blanks = 1; + } + else + { + if (!READ_LINE(parser, trailing_breaks)) goto error; + } + } + if (!CACHE(parser, 1)) goto error; + } + + /* Join the whitespaces or fold line breaks. */ + + if (leading_blanks) + { + /* Do we need to fold line breaks? */ + + if (leading_break.start[0] == '\n') { + if (trailing_breaks.start[0] == '\0') { + if (!STRING_EXTEND(parser, string)) goto error; + *(string.pointer++) = ' '; + } + else { + if (!JOIN(parser, string, trailing_breaks)) goto error; + CLEAR(parser, trailing_breaks); + } + CLEAR(parser, leading_break); + } + else { + if (!JOIN(parser, string, leading_break)) goto error; + if (!JOIN(parser, string, trailing_breaks)) goto error; + CLEAR(parser, leading_break); + CLEAR(parser, trailing_breaks); + } + } + else + { + if (!JOIN(parser, string, whitespaces)) goto error; + CLEAR(parser, whitespaces); + } + } + + /* Eat the right quote. */ + + SKIP(parser); + + end_mark = parser->mark; + + /* Create a token. */ + + SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, + single ? YAML_SINGLE_QUOTED_SCALAR_STYLE : YAML_DOUBLE_QUOTED_SCALAR_STYLE, + start_mark, end_mark); + + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + STRING_DEL(parser, whitespaces); + + return 1; + +error: + STRING_DEL(parser, string); + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + STRING_DEL(parser, whitespaces); + + return 0; +} + +/* + * Scan a plain scalar. + */ + +static int +yaml_parser_scan_plain_scalar(yaml_parser_t *parser, yaml_token_t *token) +{ + yaml_mark_t start_mark; + yaml_mark_t end_mark; + yaml_string_t string = NULL_STRING; + yaml_string_t leading_break = NULL_STRING; + yaml_string_t trailing_breaks = NULL_STRING; + yaml_string_t whitespaces = NULL_STRING; + int leading_blanks = 0; + int indent = parser->indent+1; + + if (!STRING_INIT(parser, string, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, leading_break, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, trailing_breaks, INITIAL_STRING_SIZE)) goto error; + if (!STRING_INIT(parser, whitespaces, INITIAL_STRING_SIZE)) goto error; + + start_mark = end_mark = parser->mark; + + /* Consume the content of the plain scalar. */ + + while (1) + { + /* Check for a document indicator. */ + + if (!CACHE(parser, 4)) goto error; + + if (parser->mark.column == 0 && + ((CHECK_AT(parser->buffer, '-', 0) && + CHECK_AT(parser->buffer, '-', 1) && + CHECK_AT(parser->buffer, '-', 2)) || + (CHECK_AT(parser->buffer, '.', 0) && + CHECK_AT(parser->buffer, '.', 1) && + CHECK_AT(parser->buffer, '.', 2))) && + IS_BLANKZ_AT(parser->buffer, 3)) break; + + /* Check for a comment. */ + + if (CHECK(parser->buffer, '#')) + break; + + /* Consume non-blank characters. */ + + while (!IS_BLANKZ(parser->buffer)) + { + /* Check for 'x:x' in the flow context. TODO: Fix the test "spec-08-13". */ + + if (parser->flow_level + && CHECK(parser->buffer, ':') + && !IS_BLANKZ_AT(parser->buffer, 1)) { + yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", + start_mark, "found unexpected ':'"); + goto error; + } + + /* Check for indicators that may end a plain scalar. */ + + if ((CHECK(parser->buffer, ':') && IS_BLANKZ_AT(parser->buffer, 1)) + || (parser->flow_level && + (CHECK(parser->buffer, ',') || CHECK(parser->buffer, ':') + || CHECK(parser->buffer, '?') || CHECK(parser->buffer, '[') + || CHECK(parser->buffer, ']') || CHECK(parser->buffer, '{') + || CHECK(parser->buffer, '}')))) + break; + + /* Check if we need to join whitespaces and breaks. */ + + if (leading_blanks || whitespaces.start != whitespaces.pointer) + { + if (leading_blanks) + { + /* Do we need to fold line breaks? */ + + if (leading_break.start[0] == '\n') { + if (trailing_breaks.start[0] == '\0') { + if (!STRING_EXTEND(parser, string)) goto error; + *(string.pointer++) = ' '; + } + else { + if (!JOIN(parser, string, trailing_breaks)) goto error; + CLEAR(parser, trailing_breaks); + } + CLEAR(parser, leading_break); + } + else { + if (!JOIN(parser, string, leading_break)) goto error; + if (!JOIN(parser, string, trailing_breaks)) goto error; + CLEAR(parser, leading_break); + CLEAR(parser, trailing_breaks); + } + + leading_blanks = 0; + } + else + { + if (!JOIN(parser, string, whitespaces)) goto error; + CLEAR(parser, whitespaces); + } + } + + /* Copy the character. */ + + if (!READ(parser, string)) goto error; + + end_mark = parser->mark; + + if (!CACHE(parser, 2)) goto error; + } + + /* Is it the end? */ + + if (!(IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer))) + break; + + /* Consume blank characters. */ + + if (!CACHE(parser, 1)) goto error; + + while (IS_BLANK(parser->buffer) || IS_BREAK(parser->buffer)) + { + if (IS_BLANK(parser->buffer)) + { + /* Check for tab character that abuse intendation. */ + + if (leading_blanks && (int)parser->mark.column < indent + && IS_TAB(parser->buffer)) { + yaml_parser_set_scanner_error(parser, "while scanning a plain scalar", + start_mark, "found a tab character that violate intendation"); + goto error; + } + + /* Consume a space or a tab character. */ + + if (!leading_blanks) { + if (!READ(parser, whitespaces)) goto error; + } + else { + SKIP(parser); + } + } + else + { + if (!CACHE(parser, 2)) goto error; + + /* Check if it is a first line break. */ + + if (!leading_blanks) + { + CLEAR(parser, whitespaces); + if (!READ_LINE(parser, leading_break)) goto error; + leading_blanks = 1; + } + else + { + if (!READ_LINE(parser, trailing_breaks)) goto error; + } + } + if (!CACHE(parser, 1)) goto error; + } + + /* Check intendation level. */ + + if (!parser->flow_level && (int)parser->mark.column < indent) + break; + } + + /* Create a token. */ + + SCALAR_TOKEN_INIT(*token, string.start, string.pointer-string.start, + YAML_PLAIN_SCALAR_STYLE, start_mark, end_mark); + + /* Note that we change the 'simple_key_allowed' flag. */ + + if (leading_blanks) { + parser->simple_key_allowed = 1; + } + + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + STRING_DEL(parser, whitespaces); + + return 1; + +error: + STRING_DEL(parser, string); + STRING_DEL(parser, leading_break); + STRING_DEL(parser, trailing_breaks); + STRING_DEL(parser, whitespaces); + + return 0; +} + diff --git a/ext/psych/yaml/writer.c b/ext/psych/yaml/writer.c new file mode 100644 index 0000000..5d57f39 --- /dev/null +++ b/ext/psych/yaml/writer.c @@ -0,0 +1,141 @@ + +#include "yaml_private.h" + +/* + * Declarations. + */ + +static int +yaml_emitter_set_writer_error(yaml_emitter_t *emitter, const char *problem); + +YAML_DECLARE(int) +yaml_emitter_flush(yaml_emitter_t *emitter); + +/* + * Set the writer error and return 0. + */ + +static int +yaml_emitter_set_writer_error(yaml_emitter_t *emitter, const char *problem) +{ + emitter->error = YAML_WRITER_ERROR; + emitter->problem = problem; + + return 0; +} + +/* + * Flush the output buffer. + */ + +YAML_DECLARE(int) +yaml_emitter_flush(yaml_emitter_t *emitter) +{ + int low, high; + + assert(emitter); /* Non-NULL emitter object is expected. */ + assert(emitter->write_handler); /* Write handler must be set. */ + assert(emitter->encoding); /* Output encoding must be set. */ + + emitter->buffer.last = emitter->buffer.pointer; + emitter->buffer.pointer = emitter->buffer.start; + + /* Check if the buffer is empty. */ + + if (emitter->buffer.start == emitter->buffer.last) { + return 1; + } + + /* If the output encoding is UTF-8, we don't need to recode the buffer. */ + + if (emitter->encoding == YAML_UTF8_ENCODING) + { + if (emitter->write_handler(emitter->write_handler_data, + emitter->buffer.start, + emitter->buffer.last - emitter->buffer.start)) { + emitter->buffer.last = emitter->buffer.start; + emitter->buffer.pointer = emitter->buffer.start; + return 1; + } + else { + return yaml_emitter_set_writer_error(emitter, "write error"); + } + } + + /* Recode the buffer into the raw buffer. */ + + low = (emitter->encoding == YAML_UTF16LE_ENCODING ? 0 : 1); + high = (emitter->encoding == YAML_UTF16LE_ENCODING ? 1 : 0); + + while (emitter->buffer.pointer != emitter->buffer.last) + { + unsigned char octet; + unsigned int width; + unsigned int value; + size_t k; + + /* + * See the "reader.c" code for more details on UTF-8 encoding. Note + * that we assume that the buffer contains a valid UTF-8 sequence. + */ + + /* Read the next UTF-8 character. */ + + octet = emitter->buffer.pointer[0]; + + width = (octet & 0x80) == 0x00 ? 1 : + (octet & 0xE0) == 0xC0 ? 2 : + (octet & 0xF0) == 0xE0 ? 3 : + (octet & 0xF8) == 0xF0 ? 4 : 0; + + value = (octet & 0x80) == 0x00 ? octet & 0x7F : + (octet & 0xE0) == 0xC0 ? octet & 0x1F : + (octet & 0xF0) == 0xE0 ? octet & 0x0F : + (octet & 0xF8) == 0xF0 ? octet & 0x07 : 0; + + for (k = 1; k < width; k ++) { + octet = emitter->buffer.pointer[k]; + value = (value << 6) + (octet & 0x3F); + } + + emitter->buffer.pointer += width; + + /* Write the character. */ + + if (value < 0x10000) + { + emitter->raw_buffer.last[high] = value >> 8; + emitter->raw_buffer.last[low] = value & 0xFF; + + emitter->raw_buffer.last += 2; + } + else + { + /* Write the character using a surrogate pair (check "reader.c"). */ + + value -= 0x10000; + emitter->raw_buffer.last[high] = 0xD8 + (value >> 18); + emitter->raw_buffer.last[low] = (value >> 10) & 0xFF; + emitter->raw_buffer.last[high+2] = 0xDC + ((value >> 8) & 0xFF); + emitter->raw_buffer.last[low+2] = value & 0xFF; + + emitter->raw_buffer.last += 4; + } + } + + /* Write the raw buffer. */ + + if (emitter->write_handler(emitter->write_handler_data, + emitter->raw_buffer.start, + emitter->raw_buffer.last - emitter->raw_buffer.start)) { + emitter->buffer.last = emitter->buffer.start; + emitter->buffer.pointer = emitter->buffer.start; + emitter->raw_buffer.last = emitter->raw_buffer.start; + emitter->raw_buffer.pointer = emitter->raw_buffer.start; + return 1; + } + else { + return yaml_emitter_set_writer_error(emitter, "write error"); + } +} + diff --git a/ext/psych/yaml/yaml.h b/ext/psych/yaml/yaml.h new file mode 100644 index 0000000..f33a152 --- /dev/null +++ b/ext/psych/yaml/yaml.h @@ -0,0 +1,1971 @@ +/** + * @file yaml.h + * @brief Public interface for libyaml. + * + * Include the header file with the code: + * @code + * #include <yaml.h> + * @endcode + */ + +#ifndef YAML_H +#define YAML_H + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +/** + * @defgroup export Export Definitions + * @{ + */ + +/** The public API declaration. */ + +#ifdef _WIN32 +# if defined(YAML_DECLARE_STATIC) +# define YAML_DECLARE(type) type +# elif defined(YAML_DECLARE_EXPORT) +# define YAML_DECLARE(type) __declspec(dllexport) type +# else +# define YAML_DECLARE(type) __declspec(dllimport) type +# endif +#else +# define YAML_DECLARE(type) type +#endif + +/** @} */ + +/** + * @defgroup version Version Information + * @{ + */ + +/** + * Get the library version as a string. + * + * @returns The function returns the pointer to a static string of the form + * @c "X.Y.Z", where @c X is the major version number, @c Y is a minor version + * number, and @c Z is the patch version number. + */ + +YAML_DECLARE(const char *) +yaml_get_version_string(void); + +/** + * Get the library version numbers. + * + * @param[out] major Major version number. + * @param[out] minor Minor version number. + * @param[out] patch Patch version number. + */ + +YAML_DECLARE(void) +yaml_get_version(int *major, int *minor, int *patch); + +/** @} */ + +/** + * @defgroup basic Basic Types + * @{ + */ + +/** The character type (UTF-8 octet). */ +typedef unsigned char yaml_char_t; + +/** The version directive data. */ +typedef struct yaml_version_directive_s { + /** The major version number. */ + int major; + /** The minor version number. */ + int minor; +} yaml_version_directive_t; + +/** The tag directive data. */ +typedef struct yaml_tag_directive_s { + /** The tag handle. */ + yaml_char_t *handle; + /** The tag prefix. */ + yaml_char_t *prefix; +} yaml_tag_directive_t; + +/** The stream encoding. */ +typedef enum yaml_encoding_e { + /** Let the parser choose the encoding. */ + YAML_ANY_ENCODING, + /** The default UTF-8 encoding. */ + YAML_UTF8_ENCODING, + /** The UTF-16-LE encoding with BOM. */ + YAML_UTF16LE_ENCODING, + /** The UTF-16-BE encoding with BOM. */ + YAML_UTF16BE_ENCODING +} yaml_encoding_t; + +/** Line break types. */ + +typedef enum yaml_break_e { + /** Let the parser choose the break type. */ + YAML_ANY_BREAK, + /** Use CR for line breaks (Mac style). */ + YAML_CR_BREAK, + /** Use LN for line breaks (Unix style). */ + YAML_LN_BREAK, + /** Use CR LN for line breaks (DOS style). */ + YAML_CRLN_BREAK +} yaml_break_t; + +/** Many bad things could happen with the parser and emitter. */ +typedef enum yaml_error_type_e { + /** No error is produced. */ + YAML_NO_ERROR, + + /** Cannot allocate or reallocate a block of memory. */ + YAML_MEMORY_ERROR, + + /** Cannot read or decode the input stream. */ + YAML_READER_ERROR, + /** Cannot scan the input stream. */ + YAML_SCANNER_ERROR, + /** Cannot parse the input stream. */ + YAML_PARSER_ERROR, + /** Cannot compose a YAML document. */ + YAML_COMPOSER_ERROR, + + /** Cannot write to the output stream. */ + YAML_WRITER_ERROR, + /** Cannot emit a YAML stream. */ + YAML_EMITTER_ERROR +} yaml_error_type_t; + +/** The pointer position. */ +typedef struct yaml_mark_s { + /** The position index. */ + size_t index; + + /** The position line. */ + size_t line; + + /** The position column. */ + size_t column; +} yaml_mark_t; + +/** @} */ + +/** + * @defgroup styles Node Styles + * @{ + */ + +/** Scalar styles. */ +typedef enum yaml_scalar_style_e { + /** Let the emitter choose the style. */ + YAML_ANY_SCALAR_STYLE, + + /** The plain scalar style. */ + YAML_PLAIN_SCALAR_STYLE, + + /** The single-quoted scalar style. */ + YAML_SINGLE_QUOTED_SCALAR_STYLE, + /** The double-quoted scalar style. */ + YAML_DOUBLE_QUOTED_SCALAR_STYLE, + + /** The literal scalar style. */ + YAML_LITERAL_SCALAR_STYLE, + /** The folded scalar style. */ + YAML_FOLDED_SCALAR_STYLE +} yaml_scalar_style_t; + +/** Sequence styles. */ +typedef enum yaml_sequence_style_e { + /** Let the emitter choose the style. */ + YAML_ANY_SEQUENCE_STYLE, + + /** The block sequence style. */ + YAML_BLOCK_SEQUENCE_STYLE, + /** The flow sequence style. */ + YAML_FLOW_SEQUENCE_STYLE +} yaml_sequence_style_t; + +/** Mapping styles. */ +typedef enum yaml_mapping_style_e { + /** Let the emitter choose the style. */ + YAML_ANY_MAPPING_STYLE, + + /** The block mapping style. */ + YAML_BLOCK_MAPPING_STYLE, + /** The flow mapping style. */ + YAML_FLOW_MAPPING_STYLE +/* YAML_FLOW_SET_MAPPING_STYLE */ +} yaml_mapping_style_t; + +/** @} */ + +/** + * @defgroup tokens Tokens + * @{ + */ + +/** Token types. */ +typedef enum yaml_token_type_e { + /** An empty token. */ + YAML_NO_TOKEN, + + /** A STREAM-START token. */ + YAML_STREAM_START_TOKEN, + /** A STREAM-END token. */ + YAML_STREAM_END_TOKEN, + + /** A VERSION-DIRECTIVE token. */ + YAML_VERSION_DIRECTIVE_TOKEN, + /** A TAG-DIRECTIVE token. */ + YAML_TAG_DIRECTIVE_TOKEN, + /** A DOCUMENT-START token. */ + YAML_DOCUMENT_START_TOKEN, + /** A DOCUMENT-END token. */ + YAML_DOCUMENT_END_TOKEN, + + /** A BLOCK-SEQUENCE-START token. */ + YAML_BLOCK_SEQUENCE_START_TOKEN, + /** A BLOCK-SEQUENCE-END token. */ + YAML_BLOCK_MAPPING_START_TOKEN, + /** A BLOCK-END token. */ + YAML_BLOCK_END_TOKEN, + + /** A FLOW-SEQUENCE-START token. */ + YAML_FLOW_SEQUENCE_START_TOKEN, + /** A FLOW-SEQUENCE-END token. */ + YAML_FLOW_SEQUENCE_END_TOKEN, + /** A FLOW-MAPPING-START token. */ + YAML_FLOW_MAPPING_START_TOKEN, + /** A FLOW-MAPPING-END token. */ + YAML_FLOW_MAPPING_END_TOKEN, + + /** A BLOCK-ENTRY token. */ + YAML_BLOCK_ENTRY_TOKEN, + /** A FLOW-ENTRY token. */ + YAML_FLOW_ENTRY_TOKEN, + /** A KEY token. */ + YAML_KEY_TOKEN, + /** A VALUE token. */ + YAML_VALUE_TOKEN, + + /** An ALIAS token. */ + YAML_ALIAS_TOKEN, + /** An ANCHOR token. */ + YAML_ANCHOR_TOKEN, + /** A TAG token. */ + YAML_TAG_TOKEN, + /** A SCALAR token. */ + YAML_SCALAR_TOKEN +} yaml_token_type_t; + +/** The token structure. */ +typedef struct yaml_token_s { + + /** The token type. */ + yaml_token_type_t type; + + /** The token data. */ + union { + + /** The stream start (for @c YAML_STREAM_START_TOKEN). */ + struct { + /** The stream encoding. */ + yaml_encoding_t encoding; + } stream_start; + + /** The alias (for @c YAML_ALIAS_TOKEN). */ + struct { + /** The alias value. */ + yaml_char_t *value; + } alias; + + /** The anchor (for @c YAML_ANCHOR_TOKEN). */ + struct { + /** The anchor value. */ + yaml_char_t *value; + } anchor; + + /** The tag (for @c YAML_TAG_TOKEN). */ + struct { + /** The tag handle. */ + yaml_char_t *handle; + /** The tag suffix. */ + yaml_char_t *suffix; + } tag; + + /** The scalar value (for @c YAML_SCALAR_TOKEN). */ + struct { + /** The scalar value. */ + yaml_char_t *value; + /** The length of the scalar value. */ + size_t length; + /** The scalar style. */ + yaml_scalar_style_t style; + } scalar; + + /** The version directive (for @c YAML_VERSION_DIRECTIVE_TOKEN). */ + struct { + /** The major version number. */ + int major; + /** The minor version number. */ + int minor; + } version_directive; + + /** The tag directive (for @c YAML_TAG_DIRECTIVE_TOKEN). */ + struct { + /** The tag handle. */ + yaml_char_t *handle; + /** The tag prefix. */ + yaml_char_t *prefix; + } tag_directive; + + } data; + + /** The beginning of the token. */ + yaml_mark_t start_mark; + /** The end of the token. */ + yaml_mark_t end_mark; + +} yaml_token_t; + +/** + * Free any memory allocated for a token object. + * + * @param[in,out] token A token object. + */ + +YAML_DECLARE(void) +yaml_token_delete(yaml_token_t *token); + +/** @} */ + +/** + * @defgroup events Events + * @{ + */ + +/** Event types. */ +typedef enum yaml_event_type_e { + /** An empty event. */ + YAML_NO_EVENT, + + /** A STREAM-START event. */ + YAML_STREAM_START_EVENT, + /** A STREAM-END event. */ + YAML_STREAM_END_EVENT, + + /** A DOCUMENT-START event. */ + YAML_DOCUMENT_START_EVENT, + /** A DOCUMENT-END event. */ + YAML_DOCUMENT_END_EVENT, + + /** An ALIAS event. */ + YAML_ALIAS_EVENT, + /** A SCALAR event. */ + YAML_SCALAR_EVENT, + + /** A SEQUENCE-START event. */ + YAML_SEQUENCE_START_EVENT, + /** A SEQUENCE-END event. */ + YAML_SEQUENCE_END_EVENT, + + /** A MAPPING-START event. */ + YAML_MAPPING_START_EVENT, + /** A MAPPING-END event. */ + YAML_MAPPING_END_EVENT +} yaml_event_type_t; + +/** The event structure. */ +typedef struct yaml_event_s { + + /** The event type. */ + yaml_event_type_t type; + + /** The event data. */ + union { + + /** The stream parameters (for @c YAML_STREAM_START_EVENT). */ + struct { + /** The document encoding. */ + yaml_encoding_t encoding; + } stream_start; + + /** The document parameters (for @c YAML_DOCUMENT_START_EVENT). */ + struct { + /** The version directive. */ + yaml_version_directive_t *version_directive; + + /** The list of tag directives. */ + struct { + /** The beginning of the tag directives list. */ + yaml_tag_directive_t *start; + /** The end of the tag directives list. */ + yaml_tag_directive_t *end; + } tag_directives; + + /** Is the document indicator implicit? */ + int implicit; + } document_start; + + /** The document end parameters (for @c YAML_DOCUMENT_END_EVENT). */ + struct { + /** Is the document end indicator implicit? */ + int implicit; + } document_end; + + /** The alias parameters (for @c YAML_ALIAS_EVENT). */ + struct { + /** The anchor. */ + yaml_char_t *anchor; + } alias; + + /** The scalar parameters (for @c YAML_SCALAR_EVENT). */ + struct { + /** The anchor. */ + yaml_char_t *anchor; + /** The tag. */ + yaml_char_t *tag; + /** The scalar value. */ + yaml_char_t *value; + /** The length of the scalar value. */ + size_t length; + /** Is the tag optional for the plain style? */ + int plain_implicit; + /** Is the tag optional for any non-plain style? */ + int quoted_implicit; + /** The scalar style. */ + yaml_scalar_style_t style; + } scalar; + + /** The sequence parameters (for @c YAML_SEQUENCE_START_EVENT). */ + struct { + /** The anchor. */ + yaml_char_t *anchor; + /** The tag. */ + yaml_char_t *tag; + /** Is the tag optional? */ + int implicit; + /** The sequence style. */ + yaml_sequence_style_t style; + } sequence_start; + + /** The mapping parameters (for @c YAML_MAPPING_START_EVENT). */ + struct { + /** The anchor. */ + yaml_char_t *anchor; + /** The tag. */ + yaml_char_t *tag; + /** Is the tag optional? */ + int implicit; + /** The mapping style. */ + yaml_mapping_style_t style; + } mapping_start; + + } data; + + /** The beginning of the event. */ + yaml_mark_t start_mark; + /** The end of the event. */ + yaml_mark_t end_mark; + +} yaml_event_t; + +/** + * Create the STREAM-START event. + * + * @param[out] event An empty event object. + * @param[in] encoding The stream encoding. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_stream_start_event_initialize(yaml_event_t *event, + yaml_encoding_t encoding); + +/** + * Create the STREAM-END event. + * + * @param[out] event An empty event object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_stream_end_event_initialize(yaml_event_t *event); + +/** + * Create the DOCUMENT-START event. + * + * The @a implicit argument is considered as a stylistic parameter and may be + * ignored by the emitter. + * + * @param[out] event An empty event object. + * @param[in] version_directive The %YAML directive value or + * @c NULL. + * @param[in] tag_directives_start The beginning of the %TAG + * directives list. + * @param[in] tag_directives_end The end of the %TAG directives + * list. + * @param[in] implicit If the document start indicator is + * implicit. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_start_event_initialize(yaml_event_t *event, + yaml_version_directive_t *version_directive, + yaml_tag_directive_t *tag_directives_start, + yaml_tag_directive_t *tag_directives_end, + int implicit); + +/** + * Create the DOCUMENT-END event. + * + * The @a implicit argument is considered as a stylistic parameter and may be + * ignored by the emitter. + * + * @param[out] event An empty event object. + * @param[in] implicit If the document end indicator is implicit. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_end_event_initialize(yaml_event_t *event, int implicit); + +/** + * Create an ALIAS event. + * + * @param[out] event An empty event object. + * @param[in] anchor The anchor value. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_alias_event_initialize(yaml_event_t *event, yaml_char_t *anchor); + +/** + * Create a SCALAR event. + * + * The @a style argument may be ignored by the emitter. + * + * Either the @a tag attribute or one of the @a plain_implicit and + * @a quoted_implicit flags must be set. + * + * @param[out] event An empty event object. + * @param[in] anchor The scalar anchor or @c NULL. + * @param[in] tag The scalar tag or @c NULL. + * @param[in] value The scalar value. + * @param[in] length The length of the scalar value. + * @param[in] plain_implicit If the tag may be omitted for the plain + * style. + * @param[in] quoted_implicit If the tag may be omitted for any + * non-plain style. + * @param[in] style The scalar style. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_scalar_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, + yaml_char_t *value, int length, + int plain_implicit, int quoted_implicit, + yaml_scalar_style_t style); + +/** + * Create a SEQUENCE-START event. + * + * The @a style argument may be ignored by the emitter. + * + * Either the @a tag attribute or the @a implicit flag must be set. + * + * @param[out] event An empty event object. + * @param[in] anchor The sequence anchor or @c NULL. + * @param[in] tag The sequence tag or @c NULL. + * @param[in] implicit If the tag may be omitted. + * @param[in] style The sequence style. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_sequence_start_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, int implicit, + yaml_sequence_style_t style); + +/** + * Create a SEQUENCE-END event. + * + * @param[out] event An empty event object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_sequence_end_event_initialize(yaml_event_t *event); + +/** + * Create a MAPPING-START event. + * + * The @a style argument may be ignored by the emitter. + * + * Either the @a tag attribute or the @a implicit flag must be set. + * + * @param[out] event An empty event object. + * @param[in] anchor The mapping anchor or @c NULL. + * @param[in] tag The mapping tag or @c NULL. + * @param[in] implicit If the tag may be omitted. + * @param[in] style The mapping style. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_mapping_start_event_initialize(yaml_event_t *event, + yaml_char_t *anchor, yaml_char_t *tag, int implicit, + yaml_mapping_style_t style); + +/** + * Create a MAPPING-END event. + * + * @param[out] event An empty event object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_mapping_end_event_initialize(yaml_event_t *event); + +/** + * Free any memory allocated for an event object. + * + * @param[in,out] event An event object. + */ + +YAML_DECLARE(void) +yaml_event_delete(yaml_event_t *event); + +/** @} */ + +/** + * @defgroup nodes Nodes + * @{ + */ + +/** The tag @c !!null with the only possible value: @c null. */ +#define YAML_NULL_TAG "tag:yaml.org,2002:null" +/** The tag @c !!bool with the values: @c true and @c falce. */ +#define YAML_BOOL_TAG "tag:yaml.org,2002:bool" +/** The tag @c !!str for string values. */ +#define YAML_STR_TAG "tag:yaml.org,2002:str" +/** The tag @c !!int for integer values. */ +#define YAML_INT_TAG "tag:yaml.org,2002:int" +/** The tag @c !!float for float values. */ +#define YAML_FLOAT_TAG "tag:yaml.org,2002:float" +/** The tag @c !!timestamp for date and time values. */ +#define YAML_TIMESTAMP_TAG "tag:yaml.org,2002:timestamp" + +/** The tag @c !!seq is used to denote sequences. */ +#define YAML_SEQ_TAG "tag:yaml.org,2002:seq" +/** The tag @c !!map is used to denote mapping. */ +#define YAML_MAP_TAG "tag:yaml.org,2002:map" + +/** The default scalar tag is @c !!str. */ +#define YAML_DEFAULT_SCALAR_TAG YAML_STR_TAG +/** The default sequence tag is @c !!seq. */ +#define YAML_DEFAULT_SEQUENCE_TAG YAML_SEQ_TAG +/** The default mapping tag is @c !!map. */ +#define YAML_DEFAULT_MAPPING_TAG YAML_MAP_TAG + +/** Node types. */ +typedef enum yaml_node_type_e { + /** An empty node. */ + YAML_NO_NODE, + + /** A scalar node. */ + YAML_SCALAR_NODE, + /** A sequence node. */ + YAML_SEQUENCE_NODE, + /** A mapping node. */ + YAML_MAPPING_NODE +} yaml_node_type_t; + +/** The forward definition of a document node structure. */ +typedef struct yaml_node_s yaml_node_t; + +/** An element of a sequence node. */ +typedef int yaml_node_item_t; + +/** An element of a mapping node. */ +typedef struct yaml_node_pair_s { + /** The key of the element. */ + int key; + /** The value of the element. */ + int value; +} yaml_node_pair_t; + +/** The node structure. */ +struct yaml_node_s { + + /** The node type. */ + yaml_node_type_t type; + + /** The node tag. */ + yaml_char_t *tag; + + /** The node data. */ + union { + + /** The scalar parameters (for @c YAML_SCALAR_NODE). */ + struct { + /** The scalar value. */ + yaml_char_t *value; + /** The length of the scalar value. */ + size_t length; + /** The scalar style. */ + yaml_scalar_style_t style; + } scalar; + + /** The sequence parameters (for @c YAML_SEQUENCE_NODE). */ + struct { + /** The stack of sequence items. */ + struct { + /** The beginning of the stack. */ + yaml_node_item_t *start; + /** The end of the stack. */ + yaml_node_item_t *end; + /** The top of the stack. */ + yaml_node_item_t *top; + } items; + /** The sequence style. */ + yaml_sequence_style_t style; + } sequence; + + /** The mapping parameters (for @c YAML_MAPPING_NODE). */ + struct { + /** The stack of mapping pairs (key, value). */ + struct { + /** The beginning of the stack. */ + yaml_node_pair_t *start; + /** The end of the stack. */ + yaml_node_pair_t *end; + /** The top of the stack. */ + yaml_node_pair_t *top; + } pairs; + /** The mapping style. */ + yaml_mapping_style_t style; + } mapping; + + } data; + + /** The beginning of the node. */ + yaml_mark_t start_mark; + /** The end of the node. */ + yaml_mark_t end_mark; + +}; + +/** The document structure. */ +typedef struct yaml_document_s { + + /** The document nodes. */ + struct { + /** The beginning of the stack. */ + yaml_node_t *start; + /** The end of the stack. */ + yaml_node_t *end; + /** The top of the stack. */ + yaml_node_t *top; + } nodes; + + /** The version directive. */ + yaml_version_directive_t *version_directive; + + /** The list of tag directives. */ + struct { + /** The beginning of the tag directives list. */ + yaml_tag_directive_t *start; + /** The end of the tag directives list. */ + yaml_tag_directive_t *end; + } tag_directives; + + /** Is the document start indicator implicit? */ + int start_implicit; + /** Is the document end indicator implicit? */ + int end_implicit; + + /** The beginning of the document. */ + yaml_mark_t start_mark; + /** The end of the document. */ + yaml_mark_t end_mark; + +} yaml_document_t; + +/** + * Create a YAML document. + * + * @param[out] document An empty document object. + * @param[in] version_directive The %YAML directive value or + * @c NULL. + * @param[in] tag_directives_start The beginning of the %TAG + * directives list. + * @param[in] tag_directives_end The end of the %TAG directives + * list. + * @param[in] start_implicit If the document start indicator is + * implicit. + * @param[in] end_implicit If the document end indicator is + * implicit. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_initialize(yaml_document_t *document, + yaml_version_directive_t *version_directive, + yaml_tag_directive_t *tag_directives_start, + yaml_tag_directive_t *tag_directives_end, + int start_implicit, int end_implicit); + +/** + * Delete a YAML document and all its nodes. + * + * @param[in,out] document A document object. + */ + +YAML_DECLARE(void) +yaml_document_delete(yaml_document_t *document); + +/** + * Get a node of a YAML document. + * + * The pointer returned by this function is valid until any of the functions + * modifying the documents are called. + * + * @param[in] document A document object. + * @param[in] index The node id. + * + * @returns the node objct or @c NULL if @c node_id is out of range. + */ + +YAML_DECLARE(yaml_node_t *) +yaml_document_get_node(yaml_document_t *document, int index); + +/** + * Get the root of a YAML document node. + * + * The root object is the first object added to the document. + * + * The pointer returned by this function is valid until any of the functions + * modifying the documents are called. + * + * An empty document produced by the parser signifies the end of a YAML + * stream. + * + * @param[in] document A document object. + * + * @returns the node object or @c NULL if the document is empty. + */ + +YAML_DECLARE(yaml_node_t *) +yaml_document_get_root_node(yaml_document_t *document); + +/** + * Create a SCALAR node and attach it to the document. + * + * The @a style argument may be ignored by the emitter. + * + * @param[in,out] document A document object. + * @param[in] tag The scalar tag. + * @param[in] value The scalar value. + * @param[in] length The length of the scalar value. + * @param[in] style The scalar style. + * + * @returns the node id or @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_add_scalar(yaml_document_t *document, + yaml_char_t *tag, yaml_char_t *value, int length, + yaml_scalar_style_t style); + +/** + * Create a SEQUENCE node and attach it to the document. + * + * The @a style argument may be ignored by the emitter. + * + * @param[in,out] document A document object. + * @param[in] tag The sequence tag. + * @param[in] style The sequence style. + * + * @returns the node id or @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_add_sequence(yaml_document_t *document, + yaml_char_t *tag, yaml_sequence_style_t style); + +/** + * Create a MAPPING node and attach it to the document. + * + * The @a style argument may be ignored by the emitter. + * + * @param[in,out] document A document object. + * @param[in] tag The sequence tag. + * @param[in] style The sequence style. + * + * @returns the node id or @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_add_mapping(yaml_document_t *document, + yaml_char_t *tag, yaml_mapping_style_t style); + +/** + * Add an item to a SEQUENCE node. + * + * @param[in,out] document A document object. + * @param[in] sequence The sequence node id. + * @param[in] item The item node id. +* + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_append_sequence_item(yaml_document_t *document, + int sequence, int item); + +/** + * Add a pair of a key and a value to a MAPPING node. + * + * @param[in,out] document A document object. + * @param[in] mapping The mapping node id. + * @param[in] key The key node id. + * @param[in] value The value node id. +* + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_document_append_mapping_pair(yaml_document_t *document, + int mapping, int key, int value); + +/** @} */ + +/** + * @defgroup parser Parser Definitions + * @{ + */ + +/** + * The prototype of a read handler. + * + * The read handler is called when the parser needs to read more bytes from the + * source. The handler should write not more than @a size bytes to the @a + * buffer. The number of written bytes should be set to the @a length variable. + * + * @param[in,out] data A pointer to an application data specified by + * yaml_parser_set_input(). + * @param[out] buffer The buffer to write the data from the source. + * @param[in] size The size of the buffer. + * @param[out] size_read The actual number of bytes read from the source. + * + * @returns On success, the handler should return @c 1. If the handler failed, + * the returned value should be @c 0. On EOF, the handler should set the + * @a size_read to @c 0 and return @c 1. + */ + +typedef int yaml_read_handler_t(void *data, unsigned char *buffer, size_t size, + size_t *size_read); + +/** + * This structure holds information about a potential simple key. + */ + +typedef struct yaml_simple_key_s { + /** Is a simple key possible? */ + int possible; + + /** Is a simple key required? */ + int required; + + /** The number of the token. */ + size_t token_number; + + /** The position mark. */ + yaml_mark_t mark; +} yaml_simple_key_t; + +/** + * The states of the parser. + */ +typedef enum yaml_parser_state_e { + /** Expect STREAM-START. */ + YAML_PARSE_STREAM_START_STATE, + /** Expect the beginning of an implicit document. */ + YAML_PARSE_IMPLICIT_DOCUMENT_START_STATE, + /** Expect DOCUMENT-START. */ + YAML_PARSE_DOCUMENT_START_STATE, + /** Expect the content of a document. */ + YAML_PARSE_DOCUMENT_CONTENT_STATE, + /** Expect DOCUMENT-END. */ + YAML_PARSE_DOCUMENT_END_STATE, + /** Expect a block node. */ + YAML_PARSE_BLOCK_NODE_STATE, + /** Expect a block node or indentless sequence. */ + YAML_PARSE_BLOCK_NODE_OR_INDENTLESS_SEQUENCE_STATE, + /** Expect a flow node. */ + YAML_PARSE_FLOW_NODE_STATE, + /** Expect the first entry of a block sequence. */ + YAML_PARSE_BLOCK_SEQUENCE_FIRST_ENTRY_STATE, + /** Expect an entry of a block sequence. */ + YAML_PARSE_BLOCK_SEQUENCE_ENTRY_STATE, + /** Expect an entry of an indentless sequence. */ + YAML_PARSE_INDENTLESS_SEQUENCE_ENTRY_STATE, + /** Expect the first key of a block mapping. */ + YAML_PARSE_BLOCK_MAPPING_FIRST_KEY_STATE, + /** Expect a block mapping key. */ + YAML_PARSE_BLOCK_MAPPING_KEY_STATE, + /** Expect a block mapping value. */ + YAML_PARSE_BLOCK_MAPPING_VALUE_STATE, + /** Expect the first entry of a flow sequence. */ + YAML_PARSE_FLOW_SEQUENCE_FIRST_ENTRY_STATE, + /** Expect an entry of a flow sequence. */ + YAML_PARSE_FLOW_SEQUENCE_ENTRY_STATE, + /** Expect a key of an ordered mapping. */ + YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_KEY_STATE, + /** Expect a value of an ordered mapping. */ + YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_VALUE_STATE, + /** Expect the and of an ordered mapping entry. */ + YAML_PARSE_FLOW_SEQUENCE_ENTRY_MAPPING_END_STATE, + /** Expect the first key of a flow mapping. */ + YAML_PARSE_FLOW_MAPPING_FIRST_KEY_STATE, + /** Expect a key of a flow mapping. */ + YAML_PARSE_FLOW_MAPPING_KEY_STATE, + /** Expect a value of a flow mapping. */ + YAML_PARSE_FLOW_MAPPING_VALUE_STATE, + /** Expect an empty value of a flow mapping. */ + YAML_PARSE_FLOW_MAPPING_EMPTY_VALUE_STATE, + /** Expect nothing. */ + YAML_PARSE_END_STATE +} yaml_parser_state_t; + +/** + * This structure holds aliases data. + */ + +typedef struct yaml_alias_data_s { + /** The anchor. */ + yaml_char_t *anchor; + /** The node id. */ + int index; + /** The anchor mark. */ + yaml_mark_t mark; +} yaml_alias_data_t; + +/** + * The parser structure. + * + * All members are internal. Manage the structure using the @c yaml_parser_ + * family of functions. + */ + +typedef struct yaml_parser_s { + + /** + * @name Error handling + * @{ + */ + + /** Error type. */ + yaml_error_type_t error; + /** Error description. */ + const char *problem; + /** The byte about which the problem occurred. */ + size_t problem_offset; + /** The problematic value (@c -1 is none). */ + int problem_value; + /** The problem position. */ + yaml_mark_t problem_mark; + /** The error context. */ + const char *context; + /** The context position. */ + yaml_mark_t context_mark; + + /** + * @} + */ + + /** + * @name Reader stuff + * @{ + */ + + /** Read handler. */ + yaml_read_handler_t *read_handler; + + /** A pointer for passing to the read handler. */ + void *read_handler_data; + + /** Standard (string or file) input data. */ + union { + /** String input data. */ + struct { + /** The string start pointer. */ + const unsigned char *start; + /** The string end pointer. */ + const unsigned char *end; + /** The string current position. */ + const unsigned char *current; + } string; + + /** File input data. */ + FILE *file; + } input; + + /** EOF flag */ + int eof; + + /** The working buffer. */ + struct { + /** The beginning of the buffer. */ + yaml_char_t *start; + /** The end of the buffer. */ + yaml_char_t *end; + /** The current position of the buffer. */ + yaml_char_t *pointer; + /** The last filled position of the buffer. */ + yaml_char_t *last; + } buffer; + + /* The number of unread characters in the buffer. */ + size_t unread; + + /** The raw buffer. */ + struct { + /** The beginning of the buffer. */ + unsigned char *start; + /** The end of the buffer. */ + unsigned char *end; + /** The current position of the buffer. */ + unsigned char *pointer; + /** The last filled position of the buffer. */ + unsigned char *last; + } raw_buffer; + + /** The input encoding. */ + yaml_encoding_t encoding; + + /** The offset of the current position (in bytes). */ + size_t offset; + + /** The mark of the current position. */ + yaml_mark_t mark; + + /** + * @} + */ + + /** + * @name Scanner stuff + * @{ + */ + + /** Have we started to scan the input stream? */ + int stream_start_produced; + + /** Have we reached the end of the input stream? */ + int stream_end_produced; + + /** The number of unclosed '[' and '{' indicators. */ + int flow_level; + + /** The tokens queue. */ + struct { + /** The beginning of the tokens queue. */ + yaml_token_t *start; + /** The end of the tokens queue. */ + yaml_token_t *end; + /** The head of the tokens queue. */ + yaml_token_t *head; + /** The tail of the tokens queue. */ + yaml_token_t *tail; + } tokens; + + /** The number of tokens fetched from the queue. */ + size_t tokens_parsed; + + /* Does the tokens queue contain a token ready for dequeueing. */ + int token_available; + + /** The indentation levels stack. */ + struct { + /** The beginning of the stack. */ + int *start; + /** The end of the stack. */ + int *end; + /** The top of the stack. */ + int *top; + } indents; + + /** The current indentation level. */ + int indent; + + /** May a simple key occur at the current position? */ + int simple_key_allowed; + + /** The stack of simple keys. */ + struct { + /** The beginning of the stack. */ + yaml_simple_key_t *start; + /** The end of the stack. */ + yaml_simple_key_t *end; + /** The top of the stack. */ + yaml_simple_key_t *top; + } simple_keys; + + /** + * @} + */ + + /** + * @name Parser stuff + * @{ + */ + + /** The parser states stack. */ + struct { + /** The beginning of the stack. */ + yaml_parser_state_t *start; + /** The end of the stack. */ + yaml_parser_state_t *end; + /** The top of the stack. */ + yaml_parser_state_t *top; + } states; + + /** The current parser state. */ + yaml_parser_state_t state; + + /** The stack of marks. */ + struct { + /** The beginning of the stack. */ + yaml_mark_t *start; + /** The end of the stack. */ + yaml_mark_t *end; + /** The top of the stack. */ + yaml_mark_t *top; + } marks; + + /** The list of TAG directives. */ + struct { + /** The beginning of the list. */ + yaml_tag_directive_t *start; + /** The end of the list. */ + yaml_tag_directive_t *end; + /** The top of the list. */ + yaml_tag_directive_t *top; + } tag_directives; + + /** + * @} + */ + + /** + * @name Dumper stuff + * @{ + */ + + /** The alias data. */ + struct { + /** The beginning of the list. */ + yaml_alias_data_t *start; + /** The end of the list. */ + yaml_alias_data_t *end; + /** The top of the list. */ + yaml_alias_data_t *top; + } aliases; + + /** The currently parsed document. */ + yaml_document_t *document; + + /** + * @} + */ + +} yaml_parser_t; + +/** + * Initialize a parser. + * + * This function creates a new parser object. An application is responsible + * for destroying the object using the yaml_parser_delete() function. + * + * @param[out] parser An empty parser object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_parser_initialize(yaml_parser_t *parser); + +/** + * Destroy a parser. + * + * @param[in,out] parser A parser object. + */ + +YAML_DECLARE(void) +yaml_parser_delete(yaml_parser_t *parser); + +/** + * Set a string input. + * + * Note that the @a input pointer must be valid while the @a parser object + * exists. The application is responsible for destroing @a input after + * destroying the @a parser. + * + * @param[in,out] parser A parser object. + * @param[in] input A source data. + * @param[in] size The length of the source data in bytes. + */ + +YAML_DECLARE(void) +yaml_parser_set_input_string(yaml_parser_t *parser, + const unsigned char *input, size_t size); + +/** + * Set a file input. + * + * @a file should be a file object open for reading. The application is + * responsible for closing the @a file. + * + * @param[in,out] parser A parser object. + * @param[in] file An open file. + */ + +YAML_DECLARE(void) +yaml_parser_set_input_file(yaml_parser_t *parser, FILE *file); + +/** + * Set a generic input handler. + * + * @param[in,out] parser A parser object. + * @param[in] handler A read handler. + * @param[in] data Any application data for passing to the read + * handler. + */ + +YAML_DECLARE(void) +yaml_parser_set_input(yaml_parser_t *parser, + yaml_read_handler_t *handler, void *data); + +/** + * Set the source encoding. + * + * @param[in,out] parser A parser object. + * @param[in] encoding The source encoding. + */ + +YAML_DECLARE(void) +yaml_parser_set_encoding(yaml_parser_t *parser, yaml_encoding_t encoding); + +/** + * Scan the input stream and produce the next token. + * + * Call the function subsequently to produce a sequence of tokens corresponding + * to the input stream. The initial token has the type + * @c YAML_STREAM_START_TOKEN while the ending token has the type + * @c YAML_STREAM_END_TOKEN. + * + * An application is responsible for freeing any buffers associated with the + * produced token object using the @c yaml_token_delete function. + * + * An application must not alternate the calls of yaml_parser_scan() with the + * calls of yaml_parser_parse() or yaml_parser_load(). Doing this will break + * the parser. + * + * @param[in,out] parser A parser object. + * @param[out] token An empty token object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_parser_scan(yaml_parser_t *parser, yaml_token_t *token); + +/** + * Parse the input stream and produce the next parsing event. + * + * Call the function subsequently to produce a sequence of events corresponding + * to the input stream. The initial event has the type + * @c YAML_STREAM_START_EVENT while the ending event has the type + * @c YAML_STREAM_END_EVENT. + * + * An application is responsible for freeing any buffers associated with the + * produced event object using the yaml_event_delete() function. + * + * An application must not alternate the calls of yaml_parser_parse() with the + * calls of yaml_parser_scan() or yaml_parser_load(). Doing this will break the + * parser. + * + * @param[in,out] parser A parser object. + * @param[out] event An empty event object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_parser_parse(yaml_parser_t *parser, yaml_event_t *event); + +/** + * Parse the input stream and produce the next YAML document. + * + * Call this function subsequently to produce a sequence of documents + * constituting the input stream. + * + * If the produced document has no root node, it means that the document + * end has been reached. + * + * An application is responsible for freeing any data associated with the + * produced document object using the yaml_document_delete() function. + * + * An application must not alternate the calls of yaml_parser_load() with the + * calls of yaml_parser_scan() or yaml_parser_parse(). Doing this will break + * the parser. + * + * @param[in,out] parser A parser object. + * @param[out] document An empty document object. + * + * @return @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_parser_load(yaml_parser_t *parser, yaml_document_t *document); + +/** @} */ + +/** + * @defgroup emitter Emitter Definitions + * @{ + */ + +/** + * The prototype of a write handler. + * + * The write handler is called when the emitter needs to flush the accumulated + * characters to the output. The handler should write @a size bytes of the + * @a buffer to the output. + * + * @param[in,out] data A pointer to an application data specified by + * yaml_emitter_set_output(). + * @param[in] buffer The buffer with bytes to be written. + * @param[in] size The size of the buffer. + * + * @returns On success, the handler should return @c 1. If the handler failed, + * the returned value should be @c 0. + */ + +typedef int yaml_write_handler_t(void *data, unsigned char *buffer, size_t size); + +/** The emitter states. */ +typedef enum yaml_emitter_state_e { + /** Expect STREAM-START. */ + YAML_EMIT_STREAM_START_STATE, + /** Expect the first DOCUMENT-START or STREAM-END. */ + YAML_EMIT_FIRST_DOCUMENT_START_STATE, + /** Expect DOCUMENT-START or STREAM-END. */ + YAML_EMIT_DOCUMENT_START_STATE, + /** Expect the content of a document. */ + YAML_EMIT_DOCUMENT_CONTENT_STATE, + /** Expect DOCUMENT-END. */ + YAML_EMIT_DOCUMENT_END_STATE, + /** Expect the first item of a flow sequence. */ + YAML_EMIT_FLOW_SEQUENCE_FIRST_ITEM_STATE, + /** Expect an item of a flow sequence. */ + YAML_EMIT_FLOW_SEQUENCE_ITEM_STATE, + /** Expect the first key of a flow mapping. */ + YAML_EMIT_FLOW_MAPPING_FIRST_KEY_STATE, + /** Expect a key of a flow mapping. */ + YAML_EMIT_FLOW_MAPPING_KEY_STATE, + /** Expect a value for a simple key of a flow mapping. */ + YAML_EMIT_FLOW_MAPPING_SIMPLE_VALUE_STATE, + /** Expect a value of a flow mapping. */ + YAML_EMIT_FLOW_MAPPING_VALUE_STATE, + /** Expect the first item of a block sequence. */ + YAML_EMIT_BLOCK_SEQUENCE_FIRST_ITEM_STATE, + /** Expect an item of a block sequence. */ + YAML_EMIT_BLOCK_SEQUENCE_ITEM_STATE, + /** Expect the first key of a block mapping. */ + YAML_EMIT_BLOCK_MAPPING_FIRST_KEY_STATE, + /** Expect the key of a block mapping. */ + YAML_EMIT_BLOCK_MAPPING_KEY_STATE, + /** Expect a value for a simple key of a block mapping. */ + YAML_EMIT_BLOCK_MAPPING_SIMPLE_VALUE_STATE, + /** Expect a value of a block mapping. */ + YAML_EMIT_BLOCK_MAPPING_VALUE_STATE, + /** Expect nothing. */ + YAML_EMIT_END_STATE +} yaml_emitter_state_t; + +/** + * The emitter structure. + * + * All members are internal. Manage the structure using the @c yaml_emitter_ + * family of functions. + */ + +typedef struct yaml_emitter_s { + + /** + * @name Error handling + * @{ + */ + + /** Error type. */ + yaml_error_type_t error; + /** Error description. */ + const char *problem; + + /** + * @} + */ + + /** + * @name Writer stuff + * @{ + */ + + /** Write handler. */ + yaml_write_handler_t *write_handler; + + /** A pointer for passing to the white handler. */ + void *write_handler_data; + + /** Standard (string or file) output data. */ + union { + /** String output data. */ + struct { + /** The buffer pointer. */ + unsigned char *buffer; + /** The buffer size. */ + size_t size; + /** The number of written bytes. */ + size_t *size_written; + } string; + + /** File output data. */ + FILE *file; + } output; + + /** The working buffer. */ + struct { + /** The beginning of the buffer. */ + yaml_char_t *start; + /** The end of the buffer. */ + yaml_char_t *end; + /** The current position of the buffer. */ + yaml_char_t *pointer; + /** The last filled position of the buffer. */ + yaml_char_t *last; + } buffer; + + /** The raw buffer. */ + struct { + /** The beginning of the buffer. */ + unsigned char *start; + /** The end of the buffer. */ + unsigned char *end; + /** The current position of the buffer. */ + unsigned char *pointer; + /** The last filled position of the buffer. */ + unsigned char *last; + } raw_buffer; + + /** The stream encoding. */ + yaml_encoding_t encoding; + + /** + * @} + */ + + /** + * @name Emitter stuff + * @{ + */ + + /** If the output is in the canonical style? */ + int canonical; + /** The number of indentation spaces. */ + int best_indent; + /** The preferred width of the output lines. */ + int best_width; + /** Allow unescaped non-ASCII characters? */ + int unicode; + /** The preferred line break. */ + yaml_break_t line_break; + + /** The stack of states. */ + struct { + /** The beginning of the stack. */ + yaml_emitter_state_t *start; + /** The end of the stack. */ + yaml_emitter_state_t *end; + /** The top of the stack. */ + yaml_emitter_state_t *top; + } states; + + /** The current emitter state. */ + yaml_emitter_state_t state; + + /** The event queue. */ + struct { + /** The beginning of the event queue. */ + yaml_event_t *start; + /** The end of the event queue. */ + yaml_event_t *end; + /** The head of the event queue. */ + yaml_event_t *head; + /** The tail of the event queue. */ + yaml_event_t *tail; + } events; + + /** The stack of indentation levels. */ + struct { + /** The beginning of the stack. */ + int *start; + /** The end of the stack. */ + int *end; + /** The top of the stack. */ + int *top; + } indents; + + /** The list of tag directives. */ + struct { + /** The beginning of the list. */ + yaml_tag_directive_t *start; + /** The end of the list. */ + yaml_tag_directive_t *end; + /** The top of the list. */ + yaml_tag_directive_t *top; + } tag_directives; + + /** The current indentation level. */ + int indent; + + /** The current flow level. */ + int flow_level; + + /** Is it the document root context? */ + int root_context; + /** Is it a sequence context? */ + int sequence_context; + /** Is it a mapping context? */ + int mapping_context; + /** Is it a simple mapping key context? */ + int simple_key_context; + + /** The current line. */ + int line; + /** The current column. */ + int column; + /** If the last character was a whitespace? */ + int whitespace; + /** If the last character was an indentation character (' ', '-', '?', ':')? */ + int indention; + /** If an explicit document end is required? */ + int open_ended; + + /** Anchor analysis. */ + struct { + /** The anchor value. */ + yaml_char_t *anchor; + /** The anchor length. */ + size_t anchor_length; + /** Is it an alias? */ + int alias; + } anchor_data; + + /** Tag analysis. */ + struct { + /** The tag handle. */ + yaml_char_t *handle; + /** The tag handle length. */ + size_t handle_length; + /** The tag suffix. */ + yaml_char_t *suffix; + /** The tag suffix length. */ + size_t suffix_length; + } tag_data; + + /** Scalar analysis. */ + struct { + /** The scalar value. */ + yaml_char_t *value; + /** The scalar length. */ + size_t length; + /** Does the scalar contain line breaks? */ + int multiline; + /** Can the scalar be expessed in the flow plain style? */ + int flow_plain_allowed; + /** Can the scalar be expressed in the block plain style? */ + int block_plain_allowed; + /** Can the scalar be expressed in the single quoted style? */ + int single_quoted_allowed; + /** Can the scalar be expressed in the literal or folded styles? */ + int block_allowed; + /** The output style. */ + yaml_scalar_style_t style; + } scalar_data; + + /** + * @} + */ + + /** + * @name Dumper stuff + * @{ + */ + + /** If the stream was already opened? */ + int opened; + /** If the stream was already closed? */ + int closed; + + /** The information associated with the document nodes. */ + struct { + /** The number of references. */ + int references; + /** The anchor id. */ + int anchor; + /** If the node has been emitted? */ + int serialized; + } *anchors; + + /** The last assigned anchor id. */ + int last_anchor_id; + + /** The currently emitted document. */ + yaml_document_t *document; + + /** + * @} + */ + +} yaml_emitter_t; + +/** + * Initialize an emitter. + * + * This function creates a new emitter object. An application is responsible + * for destroying the object using the yaml_emitter_delete() function. + * + * @param[out] emitter An empty parser object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_initialize(yaml_emitter_t *emitter); + +/** + * Destroy an emitter. + * + * @param[in,out] emitter An emitter object. + */ + +YAML_DECLARE(void) +yaml_emitter_delete(yaml_emitter_t *emitter); + +/** + * Set a string output. + * + * The emitter will write the output characters to the @a output buffer of the + * size @a size. The emitter will set @a size_written to the number of written + * bytes. If the buffer is smaller than required, the emitter produces the + * YAML_WRITE_ERROR error. + * + * @param[in,out] emitter An emitter object. + * @param[in] output An output buffer. + * @param[in] size The buffer size. + * @param[in] size_written The pointer to save the number of written + * bytes. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output_string(yaml_emitter_t *emitter, + unsigned char *output, size_t size, size_t *size_written); + +/** + * Set a file output. + * + * @a file should be a file object open for writing. The application is + * responsible for closing the @a file. + * + * @param[in,out] emitter An emitter object. + * @param[in] file An open file. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output_file(yaml_emitter_t *emitter, FILE *file); + +/** + * Set a generic output handler. + * + * @param[in,out] emitter An emitter object. + * @param[in] handler A write handler. + * @param[in] data Any application data for passing to the write + * handler. + */ + +YAML_DECLARE(void) +yaml_emitter_set_output(yaml_emitter_t *emitter, + yaml_write_handler_t *handler, void *data); + +/** + * Set the output encoding. + * + * @param[in,out] emitter An emitter object. + * @param[in] encoding The output encoding. + */ + +YAML_DECLARE(void) +yaml_emitter_set_encoding(yaml_emitter_t *emitter, yaml_encoding_t encoding); + +/** + * Set if the output should be in the "canonical" format as in the YAML + * specification. + * + * @param[in,out] emitter An emitter object. + * @param[in] canonical If the output is canonical. + */ + +YAML_DECLARE(void) +yaml_emitter_set_canonical(yaml_emitter_t *emitter, int canonical); + +/** + * Set the indentation increment. + * + * @param[in,out] emitter An emitter object. + * @param[in] indent The indentation increment (1 < . < 10). + */ + +YAML_DECLARE(void) +yaml_emitter_set_indent(yaml_emitter_t *emitter, int indent); + +/** + * Set the preferred line width. @c -1 means unlimited. + * + * @param[in,out] emitter An emitter object. + * @param[in] width The preferred line width. + */ + +YAML_DECLARE(void) +yaml_emitter_set_width(yaml_emitter_t *emitter, int width); + +/** + * Set if unescaped non-ASCII characters are allowed. + * + * @param[in,out] emitter An emitter object. + * @param[in] unicode If unescaped Unicode characters are allowed. + */ + +YAML_DECLARE(void) +yaml_emitter_set_unicode(yaml_emitter_t *emitter, int unicode); + +/** + * Set the preferred line break. + * + * @param[in,out] emitter An emitter object. + * @param[in] line_break The preferred line break. + */ + +YAML_DECLARE(void) +yaml_emitter_set_break(yaml_emitter_t *emitter, yaml_break_t line_break); + +/** + * Emit an event. + * + * The event object may be generated using the yaml_parser_parse() function. + * The emitter takes the responsibility for the event object and destroys its + * content after it is emitted. The event object is destroyed even if the + * function fails. + * + * @param[in,out] emitter An emitter object. + * @param[in,out] event An event object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_emit(yaml_emitter_t *emitter, yaml_event_t *event); + +/** + * Start a YAML stream. + * + * This function should be used before yaml_emitter_dump() is called. + * + * @param[in,out] emitter An emitter object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_open(yaml_emitter_t *emitter); + +/** + * Finish a YAML stream. + * + * This function should be used after yaml_emitter_dump() is called. + * + * @param[in,out] emitter An emitter object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_close(yaml_emitter_t *emitter); + +/** + * Emit a YAML document. + * + * The documen object may be generated using the yaml_parser_load() function + * or the yaml_document_initialize() function. The emitter takes the + * responsibility for the document object and destoys its content after + * it is emitted. The document object is destroyedeven if the function fails. + * + * @param[in,out] emitter An emitter object. + * @param[in,out] document A document object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_dump(yaml_emitter_t *emitter, yaml_document_t *document); + +/** + * Flush the accumulated characters to the output. + * + * @param[in,out] emitter An emitter object. + * + * @returns @c 1 if the function succeeded, @c 0 on error. + */ + +YAML_DECLARE(int) +yaml_emitter_flush(yaml_emitter_t *emitter); + +/** @} */ + +#ifdef __cplusplus +} +#endif + +#endif /* #ifndef YAML_H */ + diff --git a/ext/psych/yaml/yaml_private.h b/ext/psych/yaml/yaml_private.h new file mode 100644 index 0000000..944499c --- /dev/null +++ b/ext/psych/yaml/yaml_private.h @@ -0,0 +1,664 @@ +#ifdef RUBY_EXTCONF_H +#include RUBY_EXTCONF_H +#endif + +#if HAVE_CONFIG_H +#include <config.h> +#endif + +#include <yaml.h> + +#include <assert.h> +#include <limits.h> +#include <stddef.h> + +#ifndef _MSC_VER +#include <stdint.h> +#else +#ifdef _WIN64 +#define PTRDIFF_MAX _I64_MAX +#else +#define PTRDIFF_MAX INT_MAX +#endif +#endif + +/* + * Memory management. + */ + +YAML_DECLARE(void *) +yaml_malloc(size_t size); + +YAML_DECLARE(void *) +yaml_realloc(void *ptr, size_t size); + +YAML_DECLARE(void) +yaml_free(void *ptr); + +YAML_DECLARE(yaml_char_t *) +yaml_strdup(const yaml_char_t *); + +/* + * Reader: Ensure that the buffer contains at least `length` characters. + */ + +YAML_DECLARE(int) +yaml_parser_update_buffer(yaml_parser_t *parser, size_t length); + +/* + * Scanner: Ensure that the token stack contains at least one token ready. + */ + +YAML_DECLARE(int) +yaml_parser_fetch_more_tokens(yaml_parser_t *parser); + +/* + * The size of the input raw buffer. + */ + +#define INPUT_RAW_BUFFER_SIZE 16384 + +/* + * The size of the input buffer. + * + * It should be possible to decode the whole raw buffer. + */ + +#define INPUT_BUFFER_SIZE (INPUT_RAW_BUFFER_SIZE*3) + +/* + * The size of the output buffer. + */ + +#define OUTPUT_BUFFER_SIZE 16384 + +/* + * The size of the output raw buffer. + * + * It should be possible to encode the whole output buffer. + */ + +#define OUTPUT_RAW_BUFFER_SIZE (OUTPUT_BUFFER_SIZE*2+2) + +/* + * The size of other stacks and queues. + */ + +#define INITIAL_STACK_SIZE 16 +#define INITIAL_QUEUE_SIZE 16 +#define INITIAL_STRING_SIZE 16 + +/* + * Buffer management. + */ + +#define BUFFER_INIT(context,buffer,size) \ + (((buffer).start = yaml_malloc(size)) ? \ + ((buffer).last = (buffer).pointer = (buffer).start, \ + (buffer).end = (buffer).start+(size), \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define BUFFER_DEL(context,buffer) \ + (yaml_free((buffer).start), \ + (buffer).start = (buffer).pointer = (buffer).end = 0) + +/* + * String management. + */ + +typedef struct { + yaml_char_t *start; + yaml_char_t *end; + yaml_char_t *pointer; +} yaml_string_t; + +YAML_DECLARE(int) +yaml_string_extend(yaml_char_t **start, + yaml_char_t **pointer, yaml_char_t **end); + +YAML_DECLARE(int) +yaml_string_join( + yaml_char_t **a_start, yaml_char_t **a_pointer, yaml_char_t **a_end, + yaml_char_t **b_start, yaml_char_t **b_pointer, yaml_char_t **b_end); + +#define NULL_STRING { NULL, NULL, NULL } + +#define STRING(string,length) { (string), (string)+(length), (string) } + +#define STRING_ASSIGN(value,string,length) \ + ((value).start = (string), \ + (value).end = (string)+(length), \ + (value).pointer = (string)) + +#define STRING_INIT(context,string,size) \ + (((string).start = yaml_malloc(size)) ? \ + ((string).pointer = (string).start, \ + (string).end = (string).start+(size), \ + memset((string).start, 0, (size)), \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define STRING_DEL(context,string) \ + (yaml_free((string).start), \ + (string).start = (string).pointer = (string).end = 0) + +#define STRING_EXTEND(context,string) \ + ((((string).pointer+5 < (string).end) \ + || yaml_string_extend(&(string).start, \ + &(string).pointer, &(string).end)) ? \ + 1 : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define CLEAR(context,string) \ + ((string).pointer = (string).start, \ + memset((string).start, 0, (string).end-(string).start)) + +#define JOIN(context,string_a,string_b) \ + ((yaml_string_join(&(string_a).start, &(string_a).pointer, \ + &(string_a).end, &(string_b).start, \ + &(string_b).pointer, &(string_b).end)) ? \ + ((string_b).pointer = (string_b).start, \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +/* + * String check operations. + */ + +/* + * Check the octet at the specified position. + */ + +#define CHECK_AT(string,octet,offset) \ + ((string).pointer[offset] == (yaml_char_t)(octet)) + +/* + * Check the current octet in the buffer. + */ + +#define CHECK(string,octet) CHECK_AT((string),(octet),0) + +/* + * Check if the character at the specified position is an alphabetical + * character, a digit, '_', or '-'. + */ + +#define IS_ALPHA_AT(string,offset) \ + (((string).pointer[offset] >= (yaml_char_t) '0' && \ + (string).pointer[offset] <= (yaml_char_t) '9') || \ + ((string).pointer[offset] >= (yaml_char_t) 'A' && \ + (string).pointer[offset] <= (yaml_char_t) 'Z') || \ + ((string).pointer[offset] >= (yaml_char_t) 'a' && \ + (string).pointer[offset] <= (yaml_char_t) 'z') || \ + (string).pointer[offset] == '_' || \ + (string).pointer[offset] == '-') + +#define IS_ALPHA(string) IS_ALPHA_AT((string),0) + +/* + * Check if the character at the specified position is a digit. + */ + +#define IS_DIGIT_AT(string,offset) \ + (((string).pointer[offset] >= (yaml_char_t) '0' && \ + (string).pointer[offset] <= (yaml_char_t) '9')) + +#define IS_DIGIT(string) IS_DIGIT_AT((string),0) + +/* + * Get the value of a digit. + */ + +#define AS_DIGIT_AT(string,offset) \ + ((string).pointer[offset] - (yaml_char_t) '0') + +#define AS_DIGIT(string) AS_DIGIT_AT((string),0) + +/* + * Check if the character at the specified position is a hex-digit. + */ + +#define IS_HEX_AT(string,offset) \ + (((string).pointer[offset] >= (yaml_char_t) '0' && \ + (string).pointer[offset] <= (yaml_char_t) '9') || \ + ((string).pointer[offset] >= (yaml_char_t) 'A' && \ + (string).pointer[offset] <= (yaml_char_t) 'F') || \ + ((string).pointer[offset] >= (yaml_char_t) 'a' && \ + (string).pointer[offset] <= (yaml_char_t) 'f')) + +#define IS_HEX(string) IS_HEX_AT((string),0) + +/* + * Get the value of a hex-digit. + */ + +#define AS_HEX_AT(string,offset) \ + (((string).pointer[offset] >= (yaml_char_t) 'A' && \ + (string).pointer[offset] <= (yaml_char_t) 'F') ? \ + ((string).pointer[offset] - (yaml_char_t) 'A' + 10) : \ + ((string).pointer[offset] >= (yaml_char_t) 'a' && \ + (string).pointer[offset] <= (yaml_char_t) 'f') ? \ + ((string).pointer[offset] - (yaml_char_t) 'a' + 10) : \ + ((string).pointer[offset] - (yaml_char_t) '0')) + +#define AS_HEX(string) AS_HEX_AT((string),0) + +/* + * Check if the character is ASCII. + */ + +#define IS_ASCII_AT(string,offset) \ + ((string).pointer[offset] <= (yaml_char_t) '\x7F') + +#define IS_ASCII(string) IS_ASCII_AT((string),0) + +/* + * Check if the character can be printed unescaped. + */ + +#define IS_PRINTABLE_AT(string,offset) \ + (((string).pointer[offset] == 0x0A) /* . == #x0A */ \ + || ((string).pointer[offset] >= 0x20 /* #x20 <= . <= #x7E */ \ + && (string).pointer[offset] <= 0x7E) \ + || ((string).pointer[offset] == 0xC2 /* #0xA0 <= . <= #xD7FF */ \ + && (string).pointer[offset+1] >= 0xA0) \ + || ((string).pointer[offset] > 0xC2 \ + && (string).pointer[offset] < 0xED) \ + || ((string).pointer[offset] == 0xED \ + && (string).pointer[offset+1] < 0xA0) \ + || ((string).pointer[offset] == 0xEE) \ + || ((string).pointer[offset] == 0xEF /* #xE000 <= . <= #xFFFD */ \ + && !((string).pointer[offset+1] == 0xBB /* && . != #xFEFF */ \ + && (string).pointer[offset+2] == 0xBF) \ + && !((string).pointer[offset+1] == 0xBF \ + && ((string).pointer[offset+2] == 0xBE \ + || (string).pointer[offset+2] == 0xBF)))) + +#define IS_PRINTABLE(string) IS_PRINTABLE_AT((string),0) + +/* + * Check if the character at the specified position is NUL. + */ + +#define IS_Z_AT(string,offset) CHECK_AT((string),'\0',(offset)) + +#define IS_Z(string) IS_Z_AT((string),0) + +/* + * Check if the character at the specified position is BOM. + */ + +#define IS_BOM_AT(string,offset) \ + (CHECK_AT((string),'\xEF',(offset)) \ + && CHECK_AT((string),'\xBB',(offset)+1) \ + && CHECK_AT((string),'\xBF',(offset)+2)) /* BOM (#xFEFF) */ + +#define IS_BOM(string) IS_BOM_AT(string,0) + +/* + * Check if the character at the specified position is space. + */ + +#define IS_SPACE_AT(string,offset) CHECK_AT((string),' ',(offset)) + +#define IS_SPACE(string) IS_SPACE_AT((string),0) + +/* + * Check if the character at the specified position is tab. + */ + +#define IS_TAB_AT(string,offset) CHECK_AT((string),'\t',(offset)) + +#define IS_TAB(string) IS_TAB_AT((string),0) + +/* + * Check if the character at the specified position is blank (space or tab). + */ + +#define IS_BLANK_AT(string,offset) \ + (IS_SPACE_AT((string),(offset)) || IS_TAB_AT((string),(offset))) + +#define IS_BLANK(string) IS_BLANK_AT((string),0) + +/* + * Check if the character at the specified position is a line break. + */ + +#define IS_BREAK_AT(string,offset) \ + (CHECK_AT((string),'\r',(offset)) /* CR (#xD)*/ \ + || CHECK_AT((string),'\n',(offset)) /* LF (#xA) */ \ + || (CHECK_AT((string),'\xC2',(offset)) \ + && CHECK_AT((string),'\x85',(offset)+1)) /* NEL (#x85) */ \ + || (CHECK_AT((string),'\xE2',(offset)) \ + && CHECK_AT((string),'\x80',(offset)+1) \ + && CHECK_AT((string),'\xA8',(offset)+2)) /* LS (#x2028) */ \ + || (CHECK_AT((string),'\xE2',(offset)) \ + && CHECK_AT((string),'\x80',(offset)+1) \ + && CHECK_AT((string),'\xA9',(offset)+2))) /* PS (#x2029) */ + +#define IS_BREAK(string) IS_BREAK_AT((string),0) + +#define IS_CRLF_AT(string,offset) \ + (CHECK_AT((string),'\r',(offset)) && CHECK_AT((string),'\n',(offset)+1)) + +#define IS_CRLF(string) IS_CRLF_AT((string),0) + +/* + * Check if the character is a line break or NUL. + */ + +#define IS_BREAKZ_AT(string,offset) \ + (IS_BREAK_AT((string),(offset)) || IS_Z_AT((string),(offset))) + +#define IS_BREAKZ(string) IS_BREAKZ_AT((string),0) + +/* + * Check if the character is a line break, space, or NUL. + */ + +#define IS_SPACEZ_AT(string,offset) \ + (IS_SPACE_AT((string),(offset)) || IS_BREAKZ_AT((string),(offset))) + +#define IS_SPACEZ(string) IS_SPACEZ_AT((string),0) + +/* + * Check if the character is a line break, space, tab, or NUL. + */ + +#define IS_BLANKZ_AT(string,offset) \ + (IS_BLANK_AT((string),(offset)) || IS_BREAKZ_AT((string),(offset))) + +#define IS_BLANKZ(string) IS_BLANKZ_AT((string),0) + +/* + * Determine the width of the character. + */ + +#define WIDTH_AT(string,offset) \ + (((string).pointer[offset] & 0x80) == 0x00 ? 1 : \ + ((string).pointer[offset] & 0xE0) == 0xC0 ? 2 : \ + ((string).pointer[offset] & 0xF0) == 0xE0 ? 3 : \ + ((string).pointer[offset] & 0xF8) == 0xF0 ? 4 : 0) + +#define WIDTH(string) WIDTH_AT((string),0) + +/* + * Move the string pointer to the next character. + */ + +#define MOVE(string) ((string).pointer += WIDTH((string))) + +/* + * Copy a character and move the pointers of both strings. + */ + +#define COPY(string_a,string_b) \ + ((*(string_b).pointer & 0x80) == 0x00 ? \ + (*((string_a).pointer++) = *((string_b).pointer++)) : \ + (*(string_b).pointer & 0xE0) == 0xC0 ? \ + (*((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++)) : \ + (*(string_b).pointer & 0xF0) == 0xE0 ? \ + (*((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++)) : \ + (*(string_b).pointer & 0xF8) == 0xF0 ? \ + (*((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++), \ + *((string_a).pointer++) = *((string_b).pointer++)) : 0) + +/* + * Stack and queue management. + */ + +YAML_DECLARE(int) +yaml_stack_extend(void **start, void **top, void **end); + +YAML_DECLARE(int) +yaml_queue_extend(void **start, void **head, void **tail, void **end); + +#define STACK_INIT(context,stack,size) \ + (((stack).start = yaml_malloc((size)*sizeof(*(stack).start))) ? \ + ((stack).top = (stack).start, \ + (stack).end = (stack).start+(size), \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define STACK_DEL(context,stack) \ + (yaml_free((stack).start), \ + (stack).start = (stack).top = (stack).end = 0) + +#define STACK_EMPTY(context,stack) \ + ((void)(context), \ + ((stack).start == (stack).top)) + +#define STACK_LIMIT(context,stack,size) \ + ((stack).top - (stack).start < (size) ? \ + 1 : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define PUSH(context,stack,value) \ + (((stack).top != (stack).end \ + || yaml_stack_extend((void **)&(stack).start, \ + (void **)&(stack).top, (void **)&(stack).end)) ? \ + (*((stack).top++) = value, \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define POP(context,stack) \ + (*(--(stack).top)) + +#define QUEUE_INIT(context,queue,size) \ + (((queue).start = yaml_malloc((size)*sizeof(*(queue).start))) ? \ + ((queue).head = (queue).tail = (queue).start, \ + (queue).end = (queue).start+(size), \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define QUEUE_DEL(context,queue) \ + (yaml_free((queue).start), \ + (queue).start = (queue).head = (queue).tail = (queue).end = 0) + +#define QUEUE_EMPTY(context,queue) \ + ((queue).head == (queue).tail) + +#define ENQUEUE(context,queue,value) \ + (((queue).tail != (queue).end \ + || yaml_queue_extend((void **)&(queue).start, (void **)&(queue).head, \ + (void **)&(queue).tail, (void **)&(queue).end)) ? \ + (*((queue).tail++) = value, \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +#define DEQUEUE(context,queue) \ + (*((queue).head++)) + +#define QUEUE_INSERT(context,queue,index,value) \ + (((queue).tail != (queue).end \ + || yaml_queue_extend((void **)&(queue).start, (void **)&(queue).head, \ + (void **)&(queue).tail, (void **)&(queue).end)) ? \ + (memmove((queue).head+(index)+1,(queue).head+(index), \ + ((queue).tail-(queue).head-(index))*sizeof(*(queue).start)), \ + *((queue).head+(index)) = value, \ + (queue).tail++, \ + 1) : \ + ((context)->error = YAML_MEMORY_ERROR, \ + 0)) + +/* + * Token initializers. + */ + +#define TOKEN_INIT(token,token_type,token_start_mark,token_end_mark) \ + (memset(&(token), 0, sizeof(yaml_token_t)), \ + (token).type = (token_type), \ + (token).start_mark = (token_start_mark), \ + (token).end_mark = (token_end_mark)) + +#define STREAM_START_TOKEN_INIT(token,token_encoding,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_STREAM_START_TOKEN,(start_mark),(end_mark)), \ + (token).data.stream_start.encoding = (token_encoding)) + +#define STREAM_END_TOKEN_INIT(token,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_STREAM_END_TOKEN,(start_mark),(end_mark))) + +#define ALIAS_TOKEN_INIT(token,token_value,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_ALIAS_TOKEN,(start_mark),(end_mark)), \ + (token).data.alias.value = (token_value)) + +#define ANCHOR_TOKEN_INIT(token,token_value,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_ANCHOR_TOKEN,(start_mark),(end_mark)), \ + (token).data.anchor.value = (token_value)) + +#define TAG_TOKEN_INIT(token,token_handle,token_suffix,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_TAG_TOKEN,(start_mark),(end_mark)), \ + (token).data.tag.handle = (token_handle), \ + (token).data.tag.suffix = (token_suffix)) + +#define SCALAR_TOKEN_INIT(token,token_value,token_length,token_style,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_SCALAR_TOKEN,(start_mark),(end_mark)), \ + (token).data.scalar.value = (token_value), \ + (token).data.scalar.length = (token_length), \ + (token).data.scalar.style = (token_style)) + +#define VERSION_DIRECTIVE_TOKEN_INIT(token,token_major,token_minor,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_VERSION_DIRECTIVE_TOKEN,(start_mark),(end_mark)), \ + (token).data.version_directive.major = (token_major), \ + (token).data.version_directive.minor = (token_minor)) + +#define TAG_DIRECTIVE_TOKEN_INIT(token,token_handle,token_prefix,start_mark,end_mark) \ + (TOKEN_INIT((token),YAML_TAG_DIRECTIVE_TOKEN,(start_mark),(end_mark)), \ + (token).data.tag_directive.handle = (token_handle), \ + (token).data.tag_directive.prefix = (token_prefix)) + +/* + * Event initializers. + */ + +#define EVENT_INIT(event,event_type,event_start_mark,event_end_mark) \ + (memset(&(event), 0, sizeof(yaml_event_t)), \ + (event).type = (event_type), \ + (event).start_mark = (event_start_mark), \ + (event).end_mark = (event_end_mark)) + +#define STREAM_START_EVENT_INIT(event,event_encoding,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_STREAM_START_EVENT,(start_mark),(end_mark)), \ + (event).data.stream_start.encoding = (event_encoding)) + +#define STREAM_END_EVENT_INIT(event,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_STREAM_END_EVENT,(start_mark),(end_mark))) + +#define DOCUMENT_START_EVENT_INIT(event,event_version_directive, \ + event_tag_directives_start,event_tag_directives_end,event_implicit,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_DOCUMENT_START_EVENT,(start_mark),(end_mark)), \ + (event).data.document_start.version_directive = (event_version_directive), \ + (event).data.document_start.tag_directives.start = (event_tag_directives_start), \ + (event).data.document_start.tag_directives.end = (event_tag_directives_end), \ + (event).data.document_start.implicit = (event_implicit)) + +#define DOCUMENT_END_EVENT_INIT(event,event_implicit,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_DOCUMENT_END_EVENT,(start_mark),(end_mark)), \ + (event).data.document_end.implicit = (event_implicit)) + +#define ALIAS_EVENT_INIT(event,event_anchor,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_ALIAS_EVENT,(start_mark),(end_mark)), \ + (event).data.alias.anchor = (event_anchor)) + +#define SCALAR_EVENT_INIT(event,event_anchor,event_tag,event_value,event_length, \ + event_plain_implicit, event_quoted_implicit,event_style,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_SCALAR_EVENT,(start_mark),(end_mark)), \ + (event).data.scalar.anchor = (event_anchor), \ + (event).data.scalar.tag = (event_tag), \ + (event).data.scalar.value = (event_value), \ + (event).data.scalar.length = (event_length), \ + (event).data.scalar.plain_implicit = (event_plain_implicit), \ + (event).data.scalar.quoted_implicit = (event_quoted_implicit), \ + (event).data.scalar.style = (event_style)) + +#define SEQUENCE_START_EVENT_INIT(event,event_anchor,event_tag, \ + event_implicit,event_style,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_SEQUENCE_START_EVENT,(start_mark),(end_mark)), \ + (event).data.sequence_start.anchor = (event_anchor), \ + (event).data.sequence_start.tag = (event_tag), \ + (event).data.sequence_start.implicit = (event_implicit), \ + (event).data.sequence_start.style = (event_style)) + +#define SEQUENCE_END_EVENT_INIT(event,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_SEQUENCE_END_EVENT,(start_mark),(end_mark))) + +#define MAPPING_START_EVENT_INIT(event,event_anchor,event_tag, \ + event_implicit,event_style,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_MAPPING_START_EVENT,(start_mark),(end_mark)), \ + (event).data.mapping_start.anchor = (event_anchor), \ + (event).data.mapping_start.tag = (event_tag), \ + (event).data.mapping_start.implicit = (event_implicit), \ + (event).data.mapping_start.style = (event_style)) + +#define MAPPING_END_EVENT_INIT(event,start_mark,end_mark) \ + (EVENT_INIT((event),YAML_MAPPING_END_EVENT,(start_mark),(end_mark))) + +/* + * Document initializer. + */ + +#define DOCUMENT_INIT(document,document_nodes_start,document_nodes_end, \ + document_version_directive,document_tag_directives_start, \ + document_tag_directives_end,document_start_implicit, \ + document_end_implicit,document_start_mark,document_end_mark) \ + (memset(&(document), 0, sizeof(yaml_document_t)), \ + (document).nodes.start = (document_nodes_start), \ + (document).nodes.end = (document_nodes_end), \ + (document).nodes.top = (document_nodes_start), \ + (document).version_directive = (document_version_directive), \ + (document).tag_directives.start = (document_tag_directives_start), \ + (document).tag_directives.end = (document_tag_directives_end), \ + (document).start_implicit = (document_start_implicit), \ + (document).end_implicit = (document_end_implicit), \ + (document).start_mark = (document_start_mark), \ + (document).end_mark = (document_end_mark)) + +/* + * Node initializers. + */ + +#define NODE_INIT(node,node_type,node_tag,node_start_mark,node_end_mark) \ + (memset(&(node), 0, sizeof(yaml_node_t)), \ + (node).type = (node_type), \ + (node).tag = (node_tag), \ + (node).start_mark = (node_start_mark), \ + (node).end_mark = (node_end_mark)) + +#define SCALAR_NODE_INIT(node,node_tag,node_value,node_length, \ + node_style,start_mark,end_mark) \ + (NODE_INIT((node),YAML_SCALAR_NODE,(node_tag),(start_mark),(end_mark)), \ + (node).data.scalar.value = (node_value), \ + (node).data.scalar.length = (node_length), \ + (node).data.scalar.style = (node_style)) + +#define SEQUENCE_NODE_INIT(node,node_tag,node_items_start,node_items_end, \ + node_style,start_mark,end_mark) \ + (NODE_INIT((node),YAML_SEQUENCE_NODE,(node_tag),(start_mark),(end_mark)), \ + (node).data.sequence.items.start = (node_items_start), \ + (node).data.sequence.items.end = (node_items_end), \ + (node).data.sequence.items.top = (node_items_start), \ + (node).data.sequence.style = (node_style)) + +#define MAPPING_NODE_INIT(node,node_tag,node_pairs_start,node_pairs_end, \ + node_style,start_mark,end_mark) \ + (NODE_INIT((node),YAML_MAPPING_NODE,(node_tag),(start_mark),(end_mark)), \ + (node).data.mapping.pairs.start = (node_pairs_start), \ + (node).data.mapping.pairs.end = (node_pairs_end), \ + (node).data.mapping.pairs.top = (node_pairs_start), \ + (node).data.mapping.style = (node_style)) + diff --git a/lib/psych.rb b/lib/psych.rb index 80fbfff..efcb142 100644 --- a/lib/psych.rb +++ b/lib/psych.rb @@ -20,14 +20,17 @@ require 'psych/stream' require 'psych/json/tree_builder' require 'psych/json/stream' require 'psych/handlers/document_stream' +require 'psych/class_loader' ### # = Overview # -# Psych is a YAML parser and emitter. Psych leverages -# libyaml[http://libyaml.org] for it's YAML parsing and emitting capabilities. -# In addition to wrapping libyaml, Psych also knows how to serialize and -# de-serialize most Ruby objects to and from the YAML format. +# Psych is a YAML parser and emitter. +# Psych leverages libyaml [Home page: http://pyyaml.org/wiki/LibYAML] +# or [HG repo: https://bitbucket.org/xi/libyaml] for its YAML parsing +# and emitting capabilities. In addition to wrapping libyaml, Psych also +# knows how to serialize and de-serialize most Ruby objects to and from +# the YAML format. # # = I NEED TO PARSE OR EMIT YAML RIGHT NOW! # @@ -45,16 +48,74 @@ require 'psych/handlers/document_stream' # Psych provides a range of interfaces for parsing a YAML document ranging from # low level to high level, depending on your parsing needs. At the lowest # level, is an event based parser. Mid level is access to the raw YAML AST, -# and at the highest level is the ability to unmarshal YAML to ruby objects. +# and at the highest level is the ability to unmarshal YAML to Ruby objects. # -# === Low level parsing +# == YAML Emitting # -# The lowest level parser should be used when the YAML input is already known, -# and the developer does not want to pay the price of building an AST or -# automatic detection and conversion to ruby objects. See Psych::Parser for -# more information on using the event based parser. +# Psych provides a range of interfaces ranging from low to high level for +# producing YAML documents. Very similar to the YAML parsing interfaces, Psych +# provides at the lowest level, an event based system, mid-level is building +# a YAML AST, and the highest level is converting a Ruby object straight to +# a YAML document. +# +# == High-level API +# +# === Parsing +# +# The high level YAML parser provided by Psych simply takes YAML as input and +# returns a Ruby data structure. For information on using the high level parser +# see Psych.load +# +# ==== Reading from a string +# +# Psych.load("--- a") # => 'a' +# Psych.load("---\n - a\n - b") # => ['a', 'b'] +# +# ==== Reading from a file +# +# Psych.load_file("database.yml") +# +# ==== Exception handling +# +# begin +# # The second argument changes only the exception contents +# Psych.parse("--- `", "file.txt") +# rescue Psych::SyntaxError => ex +# ex.file # => 'file.txt' +# ex.message # => "(file.txt): found character that cannot start any token" +# end +# +# === Emitting +# +# The high level emitter has the easiest interface. Psych simply takes a Ruby +# data structure and converts it to a YAML document. See Psych.dump for more +# information on dumping a Ruby data structure. +# +# ==== Writing to a string +# +# # Dump an array, get back a YAML string +# Psych.dump(['a', 'b']) # => "---\n- a\n- b\n" +# +# # Dump an array to an IO object +# Psych.dump(['a', 'b'], StringIO.new) # => #<StringIO:0x000001009d0890> +# +# # Dump an array with indentation set +# Psych.dump(['a', ['b']], :indentation => 3) # => "---\n- a\n- - b\n" +# +# # Dump an array to an IO with indentation set +# Psych.dump(['a', ['b']], StringIO.new, :indentation => 3) +# +# ==== Writing to a file # -# === Mid level parsing +# Currently there is no direct API for dumping Ruby structure to file: +# +# File.open('database.yml', 'w') do |file| +# file.write(Psych.dump(['a', 'b'])) +# end +# +# == Mid-level API +# +# === Parsing # # Psych provides access to an AST produced from parsing a YAML document. This # tree is built using the Psych::Parser and Psych::TreeBuilder. The AST can @@ -62,28 +123,33 @@ require 'psych/handlers/document_stream' # Psych::Nodes, and Psych::Nodes::Node for more information on dealing with # YAML syntax trees. # -# === High level parsing +# ==== Reading from a string # -# The high level YAML parser provided by Psych simply takes YAML as input and -# returns a Ruby data structure. For information on using the high level parser -# see Psych.load +# # Returns Psych::Nodes::Stream +# Psych.parse_stream("---\n - a\n - b") # -# == YAML Emitting +# # Returns Psych::Nodes::Document +# Psych.parse("---\n - a\n - b") # -# Psych provides a range of interfaces ranging from low to high level for -# producing YAML documents. Very similar to the YAML parsing interfaces, Psych -# provides at the lowest level, an event based system, mid-level is building -# a YAML AST, and the highest level is converting a Ruby object straight to -# a YAML document. +# ==== Reading from a file # -# === Low level emitting +# # Returns Psych::Nodes::Stream +# Psych.parse_stream(File.read('database.yml')) # -# The lowest level emitter is an event based system. Events are sent to a -# Psych::Emitter object. That object knows how to convert the events to a YAML -# document. This interface should be used when document format is known in -# advance or speed is a concern. See Psych::Emitter for more information. +# # Returns Psych::Nodes::Document +# Psych.parse_file('database.yml') +# +# ==== Exception handling +# +# begin +# # The second argument changes only the exception contents +# Psych.parse("--- `", "file.txt") +# rescue Psych::SyntaxError => ex +# ex.file # => 'file.txt' +# ex.message # => "(file.txt): found character that cannot start any token" +# end # -# === Mid level emitting +# === Emitting # # At the mid level is building an AST. This AST is exactly the same as the AST # used when parsing a YAML document. Users can build an AST by hand and the @@ -91,25 +157,77 @@ require 'psych/handlers/document_stream' # Psych::Nodes::Node, and Psych::TreeBuilder for more information on building # a YAML AST. # -# === High level emitting +# ==== Writing to a string # -# The high level emitter has the easiest interface. Psych simply takes a Ruby -# data structure and converts it to a YAML document. See Psych.dump for more -# information on dumping a Ruby data structure. +# # We need Psych::Nodes::Stream (not Psych::Nodes::Document) +# stream = Psych.parse_stream("---\n - a\n - b") +# +# stream.to_yaml # => "---\n- a\n- b\n" +# +# ==== Writing to a file +# +# # We need Psych::Nodes::Stream (not Psych::Nodes::Document) +# stream = Psych.parse_stream(File.read('database.yml')) +# +# File.open('database.yml', 'w') do |file| +# file.write(stream.to_yaml) +# end +# +# == Low-level API +# +# === Parsing +# +# The lowest level parser should be used when the YAML input is already known, +# and the developer does not want to pay the price of building an AST or +# automatic detection and conversion to Ruby objects. See Psych::Parser for +# more information on using the event based parser. +# +# ==== Reading to Psych::Nodes::Stream structure +# +# parser = Psych::Parser.new(TreeBuilder.new) # => #<Psych::Parser> +# parser = Psych.parser # it's an alias for the above +# +# parser.parse("---\n - a\n - b") # => #<Psych::Parser> +# parser.handler # => #<Psych::TreeBuilder> +# parser.handler.root # => #<Psych::Nodes::Stream> +# +# ==== Receiving an events stream +# +# parser = Psych::Parser.new(Psych::Handlers::Recorder.new) +# +# parser.parse("---\n - a\n - b") +# parser.events # => [list of [event, args] lists] +# # event is one of: Psych::Handler::EVENTS +# # args are the arguments passed to the event +# +# === Emitting +# +# The lowest level emitter is an event based system. Events are sent to a +# Psych::Emitter object. That object knows how to convert the events to a YAML +# document. This interface should be used when document format is known in +# advance or speed is a concern. See Psych::Emitter for more information. +# +# ==== Writing to a Ruby structure +# +# Psych.parser.parse("--- a") # => #<Psych::Parser> +# +# parser.handler.first # => #<Psych::Nodes::Stream> +# parser.handler.first.to_ruby # => ["a"] +# +# parser.handler.root.first # => #<Psych::Nodes::Document> +# parser.handler.root.first.to_ruby # => "a" +# +# # You can instantiate an Emitter manually +# Psych::Visitors::ToRuby.new.accept(parser.handler.root.first) +# # => "a" module Psych # The version is Psych you're using - VERSION = '1.3.2' + VERSION = '2.0.9' # The version of libyaml Psych is using LIBYAML_VERSION = Psych.libyaml_version.join '.' - class Exception < RuntimeError - end - - class BadAlias < Exception - end - ### # Load +yaml+ in to a Ruby data structure. If multiple documents are # provided, the object contained in the first document will be returned. @@ -127,7 +245,7 @@ module Psych # Psych.load("--- `", "file.txt") # rescue Psych::SyntaxError => ex # ex.file # => 'file.txt' - # ex.message # => "(foo.txt): found character that cannot start any token" + # ex.message # => "(file.txt): found character that cannot start any token" # end def self.load yaml, filename = nil result = parse(yaml, filename) @@ -135,7 +253,56 @@ module Psych end ### - # Parse a YAML string in +yaml+. Returns the first object of a YAML AST. + # Safely load the yaml string in +yaml+. By default, only the following + # classes are allowed to be deserialized: + # + # * TrueClass + # * FalseClass + # * NilClass + # * Numeric + # * String + # * Array + # * Hash + # + # Recursive data structures are not allowed by default. Arbitrary classes + # can be allowed by adding those classes to the +whitelist+. They are + # additive. For example, to allow Date deserialization: + # + # Psych.safe_load(yaml, [Date]) + # + # Now the Date class can be loaded in addition to the classes listed above. + # + # Aliases can be explicitly allowed by changing the +aliases+ parameter. + # For example: + # + # x = [] + # x << x + # yaml = Psych.dump x + # Psych.safe_load yaml # => raises an exception + # Psych.safe_load yaml, [], [], true # => loads the aliases + # + # A Psych::DisallowedClass exception will be raised if the yaml contains a + # class that isn't in the whitelist. + # + # A Psych::BadAlias exception will be raised if the yaml contains aliases + # but the +aliases+ parameter is set to false. + def self.safe_load yaml, whitelist_classes = [], whitelist_symbols = [], aliases = false, filename = nil + result = parse(yaml, filename) + return unless result + + class_loader = ClassLoader::Restricted.new(whitelist_classes.map(&:to_s), + whitelist_symbols.map(&:to_s)) + scanner = ScalarScanner.new class_loader + if aliases + visitor = Visitors::ToRuby.new scanner, class_loader + else + visitor = Visitors::NoAliasRuby.new scanner, class_loader + end + visitor.accept result + end + + ### + # Parse a YAML string in +yaml+. Returns the Psych::Nodes::Document. # +filename+ is used in the exception message if a Psych::SyntaxError is # raised. # @@ -143,13 +310,13 @@ module Psych # # Example: # - # Psych.parse("---\n - a\n - b") # => #<Psych::Nodes::Sequence:0x00> + # Psych.parse("---\n - a\n - b") # => #<Psych::Nodes::Document:0x00> # # begin # Psych.parse("--- `", "file.txt") # rescue Psych::SyntaxError => ex # ex.file # => 'file.txt' - # ex.message # => "(foo.txt): found character that cannot start any token" + # ex.message # => "(file.txt): found character that cannot start any token" # end # # See Psych::Nodes for more information about YAML AST. @@ -161,7 +328,7 @@ module Psych end ### - # Parse a file at +filename+. Returns the YAML AST. + # Parse a file at +filename+. Returns the Psych::Nodes::Document. # # Raises a Psych::SyntaxError when a YAML syntax error is detected. def self.parse_file filename @@ -177,7 +344,7 @@ module Psych end ### - # Parse a YAML string in +yaml+. Returns the full AST for the YAML document. + # Parse a YAML string in +yaml+. Returns the Psych::Nodes::Stream. # This method can handle multiple YAML documents contained in +yaml+. # +filename+ is used in the exception message if a Psych::SyntaxError is # raised. @@ -199,7 +366,7 @@ module Psych # Psych.parse_stream("--- `", "file.txt") # rescue Psych::SyntaxError => ex # ex.file # => 'file.txt' - # ex.message # => "(foo.txt): found character that cannot start any token" + # ex.message # => "(file.txt): found character that cannot start any token" # end # # See Psych::Nodes for more information about YAML AST. @@ -244,7 +411,7 @@ module Psych io = nil end - visitor = Psych::Visitors::YAMLTree.new options + visitor = Psych::Visitors::YAMLTree.create options visitor << o visitor.tree.yaml io, options end @@ -256,7 +423,7 @@ module Psych # # Psych.dump_stream("foo\n ", {}) # => "--- ! \"foo\\n \"\n--- {}\n" def self.dump_stream *objects - visitor = Psych::Visitors::YAMLTree.new {} + visitor = Psych::Visitors::YAMLTree.create({}) objects.each do |o| visitor << o end @@ -264,16 +431,16 @@ module Psych end ### - # Dump Ruby object +o+ to a JSON string. - def self.to_json o - visitor = Psych::Visitors::JSONTree.new - visitor << o + # Dump Ruby +object+ to a JSON string. + def self.to_json object + visitor = Psych::Visitors::JSONTree.create + visitor << object visitor.tree.yaml end ### # Load multiple documents given in +yaml+. Returns the parsed documents - # as a list. If a block is given, each document will be converted to ruby + # as a list. If a block is given, each document will be converted to Ruby # and passed to the block during parsing # # Example: @@ -298,7 +465,7 @@ module Psych ### # Load the document contained in +filename+. Returns the yaml contained in - # +filename+ as a ruby object + # +filename+ as a Ruby object def self.load_file filename File.open(filename, 'r:bom|utf-8') { |f| self.load f, filename } end @@ -324,7 +491,7 @@ module Psych @load_tags = {} @dump_tags = {} def self.add_tag tag, klass - @load_tags[tag] = klass + @load_tags[tag] = klass.name @dump_tags[klass] = tag end diff --git a/lib/psych/class_loader.rb b/lib/psych/class_loader.rb new file mode 100644 index 0000000..46c6b93 --- /dev/null +++ b/lib/psych/class_loader.rb @@ -0,0 +1,101 @@ +require 'psych/omap' +require 'psych/set' + +module Psych + class ClassLoader # :nodoc: + BIG_DECIMAL = 'BigDecimal' + COMPLEX = 'Complex' + DATE = 'Date' + DATE_TIME = 'DateTime' + EXCEPTION = 'Exception' + OBJECT = 'Object' + PSYCH_OMAP = 'Psych::Omap' + PSYCH_SET = 'Psych::Set' + RANGE = 'Range' + RATIONAL = 'Rational' + REGEXP = 'Regexp' + STRUCT = 'Struct' + SYMBOL = 'Symbol' + + def initialize + @cache = CACHE.dup + end + + def load klassname + return nil if !klassname || klassname.empty? + + find klassname + end + + def symbolize sym + symbol + sym.to_sym + end + + constants.each do |const| + konst = const_get const + define_method(const.to_s.downcase) do + load konst + end + end + + private + + def find klassname + @cache[klassname] ||= resolve(klassname) + end + + def resolve klassname + name = klassname + retried = false + + begin + path2class(name) + rescue ArgumentError, NameError => ex + unless retried + name = "Struct::#{name}" + retried = ex + retry + end + raise retried + end + end + + CACHE = Hash[constants.map { |const| + val = const_get const + begin + [val, ::Object.const_get(val)] + rescue + nil + end + }.compact] + + class Restricted < ClassLoader + def initialize classes, symbols + @classes = classes + @symbols = symbols + super() + end + + def symbolize sym + return super if @symbols.empty? + + if @symbols.include? sym + super + else + raise DisallowedClass, 'Symbol' + end + end + + private + + def find klassname + if @classes.include? klassname + super + else + raise DisallowedClass, klassname + end + end + end + end +end diff --git a/lib/psych/core_ext.rb b/lib/psych/core_ext.rb index 4a04c2d..9c8134d 100644 --- a/lib/psych/core_ext.rb +++ b/lib/psych/core_ext.rb @@ -31,12 +31,5 @@ class Module end if defined?(::IRB) -module Kernel - def psych_y *objects - puts Psych.dump_stream(*objects) - end - remove_method :y rescue nil - alias y psych_y - private :y -end + require 'psych/y' end diff --git a/lib/psych/deprecated.rb b/lib/psych/deprecated.rb index 333c3a1..8c310b3 100644 --- a/lib/psych/deprecated.rb +++ b/lib/psych/deprecated.rb @@ -21,6 +21,7 @@ module Psych target.psych_to_yaml unless opts[:nodump] end + # This method is deprecated, use Psych.load_stream instead. def self.load_documents yaml, &block if $VERBOSE warn "#{caller[0]}: load_documents is deprecated, use load_stream" @@ -34,7 +35,8 @@ module Psych warn "#{caller[0]}: detect_implicit is deprecated" if $VERBOSE return '' unless String === thing return 'null' if '' == thing - ScalarScanner.new.tokenize(thing).class.name.downcase + ss = ScalarScanner.new(ClassLoader.new) + ss.tokenize(thing).class.name.downcase end def self.add_ruby_type type_tag, &block diff --git a/lib/psych/exception.rb b/lib/psych/exception.rb new file mode 100644 index 0000000..ce9d2ca --- /dev/null +++ b/lib/psych/exception.rb @@ -0,0 +1,13 @@ +module Psych + class Exception < RuntimeError + end + + class BadAlias < Exception + end + + class DisallowedClass < Exception + def initialize klass_name + super "Tried to load unspecified class: #{klass_name}" + end + end +end diff --git a/lib/psych/handler.rb b/lib/psych/handler.rb index a2aa6bb..c55afe7 100644 --- a/lib/psych/handler.rb +++ b/lib/psych/handler.rb @@ -11,6 +11,34 @@ module Psych # See Psych::Parser for more details class Handler ### + # Configuration options for dumping YAML. + class DumperOptions + attr_accessor :line_width, :indentation, :canonical + + def initialize + @line_width = 0 + @indentation = 2 + @canonical = false + end + end + + # Default dumping options + OPTIONS = DumperOptions.new + + # Events that a Handler should respond to. + EVENTS = [ :alias, + :empty, + :end_document, + :end_mapping, + :end_sequence, + :end_stream, + :scalar, + :start_document, + :start_mapping, + :start_sequence, + :start_stream ] + + ### # Called with +encoding+ when the YAML stream starts. This method is # called once per stream. A stream may contain multiple documents. # diff --git a/lib/psych/handlers/recorder.rb b/lib/psych/handlers/recorder.rb new file mode 100644 index 0000000..4eae62e --- /dev/null +++ b/lib/psych/handlers/recorder.rb @@ -0,0 +1,39 @@ +require 'psych/handler' + +module Psych + module Handlers + ### + # This handler will capture an event and record the event. Recorder events + # are available vial Psych::Handlers::Recorder#events. + # + # For example: + # + # recorder = Psych::Handlers::Recorder.new + # parser = Psych::Parser.new recorder + # parser.parse '--- foo' + # + # recorder.events # => [list of events] + # + # # Replay the events + # + # emitter = Psych::Emitter.new $stdout + # recorder.events.each do |m, args| + # emitter.send m, *args + # end + + class Recorder < Psych::Handler + attr_reader :events + + def initialize + @events = [] + super + end + + EVENTS.each do |event| + define_method event do |*args| + @events << [event, args] + end + end + end + end +end diff --git a/lib/psych/json/stream.rb b/lib/psych/json/stream.rb index be1a0a8..fe2a6e9 100644 --- a/lib/psych/json/stream.rb +++ b/lib/psych/json/stream.rb @@ -6,6 +6,7 @@ module Psych class Stream < Psych::Visitors::JSONTree include Psych::JSON::RubyEvents include Psych::Streaming + extend Psych::Streaming::ClassMethods class Emitter < Psych::Stream::Emitter # :nodoc: include Psych::JSON::YAMLEvents diff --git a/lib/psych/json/yaml_events.rb b/lib/psych/json/yaml_events.rb index 01d4660..d054d9b 100644 --- a/lib/psych/json/yaml_events.rb +++ b/lib/psych/json/yaml_events.rb @@ -10,11 +10,11 @@ module Psych end def start_mapping anchor, tag, implicit, style - super(anchor, nil, implicit, Nodes::Mapping::FLOW) + super(anchor, nil, true, Nodes::Mapping::FLOW) end def start_sequence anchor, tag, implicit, style - super(anchor, nil, implicit, Nodes::Sequence::FLOW) + super(anchor, nil, true, Nodes::Sequence::FLOW) end def scalar value, anchor, tag, plain, quoted, style diff --git a/lib/psych/nodes/node.rb b/lib/psych/nodes/node.rb index 0cefe44..83233a6 100644 --- a/lib/psych/nodes/node.rb +++ b/lib/psych/nodes/node.rb @@ -1,4 +1,6 @@ require 'stringio' +require 'psych/class_loader' +require 'psych/scalar_scanner' module Psych module Nodes @@ -32,7 +34,7 @@ module Psych # # See also Psych::Visitors::ToRuby def to_ruby - Visitors::ToRuby.new.accept self + Visitors::ToRuby.create.accept(self) end alias :transform :to_ruby diff --git a/lib/psych/nodes/sequence.rb b/lib/psych/nodes/sequence.rb index e4b833d..7e907fe 100644 --- a/lib/psych/nodes/sequence.rb +++ b/lib/psych/nodes/sequence.rb @@ -56,7 +56,7 @@ module Psych # Is this sequence started implicitly? attr_accessor :implicit - # The sequece style used + # The sequence style used attr_accessor :style ### diff --git a/lib/psych/scalar_scanner.rb b/lib/psych/scalar_scanner.rb index fa2d385..9300790 100644 --- a/lib/psych/scalar_scanner.rb +++ b/lib/psych/scalar_scanner.rb @@ -5,26 +5,39 @@ module Psych # Scan scalars for built in types class ScalarScanner # Taken from http://yaml.org/type/timestamp.html - TIME = /^\d{4}-\d{1,2}-\d{1,2}([Tt]|\s+)\d{1,2}:\d\d:\d\d(\.\d*)?(\s*Z|[-+]\d{1,2}(:\d\d)?)?/ + TIME = /^-?\d{4}-\d{1,2}-\d{1,2}(?:[Tt]|\s+)\d{1,2}:\d\d:\d\d(?:\.\d*)?(?:\s*(?:Z|[-+]\d{1,2}:?(?:\d\d)?))?$/ # Taken from http://yaml.org/type/float.html - FLOAT = /^(?:[-+]?([0-9][0-9_,]*)?\.[0-9.]*([eE][-+][0-9]+)?(?# base 10) + FLOAT = /^(?:[-+]?([0-9][0-9_,]*)?\.[0-9]*([eE][-+][0-9]+)?(?# base 10) |[-+]?[0-9][0-9_,]*(:[0-5]?[0-9])+\.[0-9_]*(?# base 60) |[-+]?\.(inf|Inf|INF)(?# infinity) |\.(nan|NaN|NAN)(?# not a number))$/x + # Taken from http://yaml.org/type/int.html + INTEGER = /^(?:[-+]?0b[0-1_]+ (?# base 2) + |[-+]?0[0-7_]+ (?# base 8) + |[-+]?(?:0|[1-9][0-9_]*) (?# base 10) + |[-+]?0x[0-9a-fA-F_]+ (?# base 16))$/x + + attr_reader :class_loader + # Create a new scanner - def initialize + def initialize class_loader @string_cache = {} + @symbol_cache = {} + @class_loader = class_loader end - # Tokenize +string+ returning the ruby object + # Tokenize +string+ returning the Ruby object def tokenize string return nil if string.empty? return string if @string_cache.key?(string) + return @symbol_cache[string] if @symbol_cache.key?(string) case string - when /^[A-Za-z~]/ + # Check for a String type, being careful not to get caught by hash keys, hex values, and + # special floats (e.g., -.inf). + when /^[^\d\.:-]?[A-Za-z_\s!@#\$%\^&\*\(\)\{\}\<\>\|\/\\~;=]+/, /\n/ if string.length > 5 @string_cache[string] = true return string @@ -45,25 +58,29 @@ module Psych string end when TIME - parse_time string + begin + parse_time string + rescue ArgumentError + string + end when /^\d{4}-(?:1[012]|0\d|\d)-(?:[12]\d|3[01]|0\d|\d)$/ require 'date' begin - Date.strptime(string, '%Y-%m-%d') + class_loader.date.strptime(string, '%Y-%m-%d') rescue ArgumentError string end when /^\.inf$/i - 1 / 0.0 + Float::INFINITY when /^-\.inf$/i - -1 / 0.0 + -Float::INFINITY when /^\.nan$/i - 0.0 / 0.0 + Float::NAN when /^:./ if string =~ /^:(["'])(.*)\1/ - $2.sub(/^:/, '').to_sym + @symbol_cache[string] = class_loader.symbolize($2.sub(/^:/, '')) else - string.sub(/^:/, '').to_sym + @symbol_cache[string] = class_loader.symbolize(string.sub(/^:/, '')) end when /^[-+]?[0-9][0-9_]*(:[0-5]?[0-9])+$/ i = 0 @@ -78,20 +95,15 @@ module Psych end i when FLOAT - begin - return Float(string.gsub(/[,_]/, '')) - rescue ArgumentError + if string =~ /\A[-+]?\.\Z/ + @string_cache[string] = true + string + else + Float(string.gsub(/[,_]|\.$/, '')) end - - @string_cache[string] = true - string else - if string.count('.') < 2 - begin - return Integer(string.gsub(/[,_]/, '')) - rescue ArgumentError - end - end + int = parse_int string.gsub(/[,_]/, '') + return int if int @string_cache[string] = true string @@ -99,19 +111,28 @@ module Psych end ### + # Parse and return an int from +string+ + def parse_int string + return unless INTEGER === string + Integer(string) + end + + ### # Parse and return a Time from +string+ def parse_time string + klass = class_loader.load 'Time' + date, time = *(string.split(/[ tT]/, 2)) - (yy, m, dd) = date.split('-').map { |x| x.to_i } + (yy, m, dd) = date.match(/^(-?\d{4})-(\d{1,2})-(\d{1,2})/).captures.map { |x| x.to_i } md = time.match(/(\d+:\d+:\d+)(?:\.(\d*))?\s*(Z|[-+]\d+(:\d\d)?)?/) (hh, mm, ss) = md[1].split(':').map { |x| x.to_i } us = (md[2] ? Rational("0.#{md[2]}") : 0) * 1000000 - time = Time.utc(yy, m, dd, hh, mm, ss, us) + time = klass.utc(yy, m, dd, hh, mm, ss, us) return time if 'Z' == md[3] - return Time.at(time.to_i, us) unless md[3] + return klass.at(time.to_i, us) unless md[3] tz = md[3].match(/^([+\-]?\d{1,2})\:?(\d{1,2})?$/)[1..-1].compact.map { |digit| Integer(digit, 10) } offset = tz.first * 3600 @@ -122,7 +143,7 @@ module Psych offset += ((tz[1] || 0) * 60) end - Time.at((time - offset).to_i, us) + klass.at((time - offset).to_i, us) end end end diff --git a/lib/psych/stream.rb b/lib/psych/stream.rb index 567c1bb..88c4c4c 100644 --- a/lib/psych/stream.rb +++ b/lib/psych/stream.rb @@ -32,5 +32,6 @@ module Psych end include Psych::Streaming + extend Psych::Streaming::ClassMethods end end diff --git a/lib/psych/streaming.rb b/lib/psych/streaming.rb index c6fa109..9d94eb5 100644 --- a/lib/psych/streaming.rb +++ b/lib/psych/streaming.rb @@ -1,10 +1,15 @@ module Psych module Streaming - ### - # Create a new streaming emitter. Emitter will print to +io+. See - # Psych::Stream for an example. - def initialize io - super({}, self.class.const_get(:Emitter).new(io)) + module ClassMethods + ### + # Create a new streaming emitter. Emitter will print to +io+. See + # Psych::Stream for an example. + def new io + emitter = const_get(:Emitter).new(io) + class_loader = ClassLoader.new + ss = ScalarScanner.new class_loader + super(emitter, ss, {}) + end end ### diff --git a/lib/psych/syntax_error.rb b/lib/psych/syntax_error.rb index f79743d..e200ef0 100644 --- a/lib/psych/syntax_error.rb +++ b/lib/psych/syntax_error.rb @@ -1,5 +1,7 @@ +require 'psych/exception' + module Psych - class SyntaxError < ::SyntaxError + class SyntaxError < Psych::Exception attr_reader :file, :line, :column, :offset, :problem, :context def initialize file, line, col, offset, problem, context diff --git a/lib/psych/visitors/emitter.rb b/lib/psych/visitors/emitter.rb index 30db176..c886e50 100644 --- a/lib/psych/visitors/emitter.rb +++ b/lib/psych/visitors/emitter.rb @@ -2,10 +2,17 @@ module Psych module Visitors class Emitter < Psych::Visitors::Visitor def initialize io, options = {} - @handler = Psych::Emitter.new io - @handler.indentation = options[:indentation] if options[:indentation] - @handler.canonical = options[:canonical] if options[:canonical] - @handler.line_width = options[:line_width] if options[:line_width] + opts = [:indentation, :canonical, :line_width].find_all { |opt| + options.key?(opt) + } + + if opts.empty? + @handler = Psych::Emitter.new io + else + du = Handler::DumperOptions.new + opts.each { |option| du.send :"#{option}=", options[option] } + @handler = Psych::Emitter.new io, du + end end def visit_Psych_Nodes_Stream o diff --git a/lib/psych/visitors/json_tree.rb b/lib/psych/visitors/json_tree.rb index 0350dd1..0127ac8 100644 --- a/lib/psych/visitors/json_tree.rb +++ b/lib/psych/visitors/json_tree.rb @@ -5,8 +5,11 @@ module Psych class JSONTree < YAMLTree include Psych::JSON::RubyEvents - def initialize options = {}, emitter = Psych::JSON::TreeBuilder.new - super + def self.create options = {} + emitter = Psych::JSON::TreeBuilder.new + class_loader = ClassLoader.new + ss = ScalarScanner.new class_loader + new(emitter, ss, options) end def accept target diff --git a/lib/psych/visitors/to_ruby.rb b/lib/psych/visitors/to_ruby.rb index 2e082f9..f353e9c 100644 --- a/lib/psych/visitors/to_ruby.rb +++ b/lib/psych/visitors/to_ruby.rb @@ -1,4 +1,6 @@ require 'psych/scalar_scanner' +require 'psych/class_loader' +require 'psych/exception' unless defined?(Regexp::NOENCODING) Regexp::NOENCODING = 32 @@ -7,13 +9,22 @@ end module Psych module Visitors ### - # This class walks a YAML AST, converting each node to ruby + # This class walks a YAML AST, converting each node to Ruby class ToRuby < Psych::Visitors::Visitor - def initialize ss = ScalarScanner.new + def self.create + class_loader = ClassLoader.new + scanner = ScalarScanner.new class_loader + new(scanner, class_loader) + end + + attr_reader :class_loader + + def initialize ss, class_loader super() @st = {} @ss = ss @domain_types = Psych.domain_types + @class_loader = class_loader end def accept target @@ -32,7 +43,7 @@ module Psych end def deserialize o - if klass = Psych.load_tags[o.tag] + if klass = resolve_class(Psych.load_tags[o.tag]) instance = klass.allocate if instance.respond_to?(:init_with) @@ -59,19 +70,25 @@ module Psych end when '!ruby/object:BigDecimal' require 'bigdecimal' - BigDecimal._load o.value + class_loader.big_decimal._load o.value when "!ruby/object:DateTime" + class_loader.date_time require 'date' @ss.parse_time(o.value).to_datetime + when '!ruby/encoding' + ::Encoding.find o.value when "!ruby/object:Complex" + class_loader.complex Complex(o.value) when "!ruby/object:Rational" + class_loader.rational Rational(o.value) when "!ruby/class", "!ruby/module" resolve_class o.value when "tag:yaml.org,2002:float", "!float" Float(@ss.tokenize(o.value)) when "!ruby/regexp" + klass = class_loader.regexp o.value =~ /^\/(.*)\/([mixn]*)$/ source = $1 options = 0 @@ -85,15 +102,16 @@ module Psych else lang = option end end - Regexp.new(*[source, options, lang].compact) + klass.new(*[source, options, lang].compact) when "!ruby/range" + klass = class_loader.range args = o.value.split(/([.]{2,3})/, 2).map { |s| accept Nodes::Scalar.new(s) } args.push(args.delete_at(1) == '...') - Range.new(*args) + klass.new(*args) when /^!ruby\/sym(bol)?:?(.*)?$/ - o.value.to_sym + class_loader.symbolize o.value else @ss.tokenize o.value end @@ -105,7 +123,7 @@ module Psych end def visit_Psych_Nodes_Sequence o - if klass = Psych.load_tags[o.tag] + if klass = resolve_class(Psych.load_tags[o.tag]) instance = klass.allocate if instance.respond_to?(:init_with) @@ -118,6 +136,8 @@ module Psych end case o.tag + when nil + register_empty(o) when '!omap', 'tag:yaml.org,2002:omap' map = register(o, Psych::Omap.new) o.children.each { |a| @@ -130,51 +150,29 @@ module Psych o.children.each { |c| list.push accept c } list else - list = register(o, []) - o.children.each { |c| list.push accept c } - list + register_empty(o) end end def visit_Psych_Nodes_Mapping o - return revive(Psych.load_tags[o.tag], o) if Psych.load_tags[o.tag] - return revive_hash({}, o) unless o.tag + if Psych.load_tags[o.tag] + return revive(resolve_class(Psych.load_tags[o.tag]), o) + end + return revive_hash(register(o, {}), o) unless o.tag case o.tag - when /^!(?:str|ruby\/string)(?::(.*))?/, 'tag:yaml.org,2002:str' - klass = resolve_class($1) - members = Hash[*o.children.map { |c| accept c }] - string = members.delete 'str' - - if klass - string = klass.allocate - string.replace string - end - - init_with(string, members.map { |k,v| [k.to_s.sub(/^@/, ''),v] }, o) - when /^!ruby\/array:(.*)$/ - klass = resolve_class($1) - list = register(o, klass.allocate) - - members = Hash[o.children.map { |c| accept c }.each_slice(2).to_a] - list.replace members['internal'] - - members['ivars'].each do |ivar, v| - list.instance_variable_set ivar, v - end - list when /^!ruby\/struct:?(.*)?$/ - klass = resolve_class($1) + klass = resolve_class($1) if $1 if klass s = register(o, klass.allocate) members = {} - struct_members = s.members.map { |x| x.to_sym } + struct_members = s.members.map { |x| class_loader.symbolize x } o.children.each_slice(2) do |k,v| member = accept(k) value = accept(v) - if struct_members.include?(member.to_sym) + if struct_members.include?(class_loader.symbolize(member)) s.send("#{member}=", value) else members[member.to_s.sub(/^@/, '')] = value @@ -182,48 +180,128 @@ module Psych end init_with(s, members, o) else + klass = class_loader.struct members = o.children.map { |c| accept c } h = Hash[*members] - Struct.new(*h.map { |k,v| k.to_sym }).new(*h.map { |k,v| v }) + s = klass.new(*h.map { |k,v| + class_loader.symbolize k + }).new(*h.map { |k,v| v }) + register(o, s) + s + end + + when /^!ruby\/object:?(.*)?$/ + name = $1 || 'Object' + + if name == 'Complex' + class_loader.complex + h = Hash[*o.children.map { |c| accept c }] + register o, Complex(h['real'], h['image']) + elsif name == 'Rational' + class_loader.rational + h = Hash[*o.children.map { |c| accept c }] + register o, Rational(h['numerator'], h['denominator']) + elsif name == 'Hash' + revive_hash(register(o, {}), o) + else + obj = revive((resolve_class(name) || class_loader.object), o) + obj end + when /^!(?:str|ruby\/string)(?::(.*))?/, 'tag:yaml.org,2002:str' + klass = resolve_class($1) + members = {} + string = nil + + o.children.each_slice(2) do |k,v| + key = accept k + value = accept v + + if key == 'str' + if klass + string = klass.allocate.replace value + else + string = value + end + register(o, string) + else + members[key] = value + end + end + init_with(string, members.map { |k,v| [k.to_s.sub(/^@/, ''),v] }, o) + when /^!ruby\/array:(.*)$/ + klass = resolve_class($1) + list = register(o, klass.allocate) + + members = Hash[o.children.map { |c| accept c }.each_slice(2).to_a] + list.replace members['internal'] + + members['ivars'].each do |ivar, v| + list.instance_variable_set ivar, v + end + list + when '!ruby/range' + klass = class_loader.range h = Hash[*o.children.map { |c| accept c }] - register o, Range.new(h['begin'], h['end'], h['excl']) + register o, klass.new(h['begin'], h['end'], h['excl']) when /^!ruby\/exception:?(.*)?$/ h = Hash[*o.children.map { |c| accept c }] - e = build_exception((resolve_class($1) || Exception), + e = build_exception((resolve_class($1) || class_loader.exception), h.delete('message')) init_with(e, h, o) when '!set', 'tag:yaml.org,2002:set' - set = Psych::Set.new + set = class_loader.psych_set.new @st[o.anchor] = set if o.anchor o.children.each_slice(2) do |k,v| set[accept(k)] = accept(v) end set - when '!ruby/object:Complex' - h = Hash[*o.children.map { |c| accept c }] - register o, Complex(h['real'], h['image']) + when /^!ruby\/hash-with-ivars(?::(.*))?$/ + hash = $1 ? resolve_class($1).allocate : {} + o.children.each_slice(2) do |key, value| + case key.value + when 'elements' + revive_hash hash, value + when 'ivars' + value.children.each_slice(2) do |k,v| + hash.instance_variable_set accept(k), accept(v) + end + end + end + hash - when '!ruby/object:Rational' - h = Hash[*o.children.map { |c| accept c }] - register o, Rational(h['numerator'], h['denominator']) + when /^!map:(.*)$/, /^!ruby\/hash:(.*)$/ + revive_hash register(o, resolve_class($1).allocate), o - when /^!ruby\/object:?(.*)?$/ - name = $1 || 'Object' - obj = revive((resolve_class(name) || Object), o) - obj + when '!omap', 'tag:yaml.org,2002:omap' + map = register(o, class_loader.psych_omap.new) + o.children.each_slice(2) do |l,r| + map[accept(l)] = accept r + end + map - when /^!map:(.*)$/, /^!ruby\/hash:(.*)$/ - revive_hash resolve_class($1).new, o + when /^!ruby\/marshalable:(.*)$/ + name = $1 + klass = resolve_class(name) + obj = register(o, klass.allocate) + + if obj.respond_to?(:init_with) + init_with(obj, revive_hash({}, o), o) + elsif obj.respond_to?(:marshal_load) + marshal_data = o.children.map(&method(:accept)) + obj.marshal_load(marshal_data) + obj + else + raise ArgumentError, "Cannot deserialize #{name}" + end else - revive_hash({}, o) + revive_hash(register(o, {}), o) end end @@ -245,36 +323,52 @@ module Psych object end - def revive_hash hash, o - @st[o.anchor] = hash if o.anchor + def register_empty object + list = register(object, []) + object.children.each { |c| list.push accept c } + list + end - o.children.each_slice(2) { |k,v| + def revive_hash hash, o + o.children.each_slice(2) { |k,v| key = accept(k) + val = accept(v) - if key == '<<' + if key == '<<' && k.tag != "tag:yaml.org,2002:str" case v - when Nodes::Alias - hash.merge! accept(v) + when Nodes::Alias, Nodes::Mapping + begin + hash.merge! val + rescue TypeError + hash[key] = val + end when Nodes::Sequence - accept(v).reverse_each do |value| - hash.merge! value + begin + h = {} + val.reverse_each do |value| + h.merge! value + end + hash.merge! h + rescue TypeError + hash[key] = val end else - hash[key] = accept(v) + hash[key] = val end else - hash[key] = accept(v) + hash[key] = val end } hash end + def merge_key hash, key, val + end + def revive klass, node - s = klass.allocate - @st[node.anchor] = s if node.anchor - h = Hash[*node.children.map { |c| accept c }] - init_with(s, h, node) + s = register(node, klass.allocate) + init_with(s, revive_hash({}, node), node) end def init_with o, h, node @@ -296,21 +390,13 @@ module Psych # Convert +klassname+ to a Class def resolve_class klassname - return nil unless klassname and not klassname.empty? - - name = klassname - retried = false - - begin - path2class(name) - rescue ArgumentError, NameError => ex - unless retried - name = "Struct::#{name}" - retried = ex - retry - end - raise retried - end + class_loader.load klassname + end + end + + class NoAliasRuby < ToRuby + def visit_Psych_Nodes_Alias o + raise BadAlias, "Unknown alias: #{o.anchor}" end end end diff --git a/lib/psych/visitors/yaml_tree.rb b/lib/psych/visitors/yaml_tree.rb index 80af046..3a6bd1d 100644 --- a/lib/psych/visitors/yaml_tree.rb +++ b/lib/psych/visitors/yaml_tree.rb @@ -1,25 +1,74 @@ +require 'psych/tree_builder' +require 'psych/scalar_scanner' +require 'psych/class_loader' + module Psych module Visitors ### - # YAMLTree builds a YAML ast given a ruby object. For example: + # YAMLTree builds a YAML ast given a Ruby object. For example: # # builder = Psych::Visitors::YAMLTree.new # builder << { :foo => 'bar' } # builder.tree # => #<Psych::Nodes::Stream .. } # class YAMLTree < Psych::Visitors::Visitor + class Registrar # :nodoc: + def initialize + @obj_to_id = {} + @obj_to_node = {} + @targets = [] + @counter = 0 + end + + def register target, node + @targets << target + @obj_to_node[target.object_id] = node + end + + def key? target + @obj_to_node.key? target.object_id + rescue NoMethodError + false + end + + def id_for target + @obj_to_id[target.object_id] ||= (@counter += 1) + end + + def node_for target + @obj_to_node[target.object_id] + end + end + attr_reader :started, :finished alias :finished? :finished alias :started? :started - def initialize options = {}, emitter = TreeBuilder.new, ss = ScalarScanner.new + def self.create options = {}, emitter = nil + emitter ||= TreeBuilder.new + class_loader = ClassLoader.new + ss = ScalarScanner.new class_loader + new(emitter, ss, options) + end + + def self.new emitter = nil, ss = nil, options = nil + return super if emitter && ss && options + + if $VERBOSE + warn "This API is deprecated, please pass an emitter, scalar scanner, and options or call #{self}.create() (#{caller.first})" + end + create emitter, ss + end + + def initialize emitter, ss, options super() @started = false @finished = false @emitter = emitter - @st = {} + @st = Registrar.new @ss = ss @options = options + @coders = [] @dispatch_cache = Hash.new do |h,klass| method = "visit_#{(klass.name || '').split('::').join('_')}" @@ -46,6 +95,7 @@ module Psych def tree finish unless finished? + @emitter.root end def push object @@ -64,15 +114,15 @@ module Psych @emitter.start_document version, [], false accept object - @emitter.end_document + @emitter.end_document !@emitter.streaming? end alias :<< :push def accept target # return any aliases we find - if @st.key? target.object_id - oid = target.object_id - node = @st[oid] + if @st.key? target + oid = @st.id_for target + node = @st.node_for target anchor = oid.to_s node.anchor = anchor return @emitter.alias anchor @@ -111,6 +161,11 @@ module Psych @emitter.end_sequence end + def visit_Encoding o + tag = "!ruby/encoding" + @emitter.scalar o.name, nil, tag, false, false, Nodes::Scalar::ANY + end + def visit_Object o tag = Psych.dump_tags[o.class] unless tag @@ -158,19 +213,42 @@ module Psych @emitter.end_mapping end + def visit_NameError o + tag = ['!ruby/exception', o.class.name].join ':' + + @emitter.start_mapping nil, tag, false, Nodes::Mapping::BLOCK + + { + 'message' => o.message.to_s, + 'backtrace' => private_iv_get(o, 'backtrace'), + }.each do |k,v| + next unless v + @emitter.scalar k, nil, nil, true, false, Nodes::Scalar::ANY + accept v + end + + dump_ivars o + + @emitter.end_mapping + end + def visit_Regexp o register o, @emitter.scalar(o.inspect, nil, '!ruby/regexp', false, false, Nodes::Scalar::ANY) end def visit_DateTime o - formatted = format_time o.to_time + formatted = if o.offset.zero? + o.strftime("%Y-%m-%d %H:%M:%S.%9N Z".freeze) + else + o.strftime("%Y-%m-%d %H:%M:%S.%9N %:z".freeze) + end tag = '!ruby/object:DateTime' register o, @emitter.scalar(formatted, nil, tag, false, false, Nodes::Scalar::ANY) end def visit_Time o formatted = format_time o - @emitter.scalar formatted, nil, nil, true, false, Nodes::Scalar::ANY + register o, @emitter.scalar(formatted, nil, nil, true, false, Nodes::Scalar::ANY) end def visit_Rational o @@ -218,28 +296,33 @@ module Psych @emitter.scalar o._dump, nil, '!ruby/object:BigDecimal', false, false, Nodes::Scalar::ANY end - def binary? string - string.encoding == Encoding::ASCII_8BIT || - string.index("\x00") || - string.count("\x00-\x7F", "^ -~\t\r\n").fdiv(string.length) > 0.3 - end - private :binary? - def visit_String o - plain = false - quote = false - style = Nodes::Scalar::ANY + plain = true + quote = true + style = Nodes::Scalar::PLAIN + tag = nil + str = o if binary?(o) str = [o].pack('m').chomp tag = '!binary' # FIXME: change to below when syck is removed #tag = 'tag:yaml.org,2002:binary' style = Nodes::Scalar::LITERAL + plain = false + quote = false + elsif o =~ /\n/ + style = Nodes::Scalar::LITERAL + elsif o == '<<' + style = Nodes::Scalar::SINGLE_QUOTED + tag = 'tag:yaml.org,2002:str' + plain = false + quote = false + elsif o =~ /^[^[:word:]][^"]*$/ + style = Nodes::Scalar::DOUBLE_QUOTED else - str = o - tag = nil - quote = !(String === @ss.tokenize(o)) - plain = !quote + unless String === @ss.tokenize(o) + style = Nodes::Scalar::SINGLE_QUOTED + end end ivars = find_ivars o @@ -247,13 +330,15 @@ module Psych if ivars.empty? unless o.class == ::String tag = "!ruby/string:#{o.class}" + plain = false + quote = false end @emitter.scalar str, nil, tag, plain, quote, style else maptag = '!ruby/string' maptag << ":#{o.class}" unless o.class == ::String - @emitter.start_mapping nil, maptag, false, Nodes::Mapping::BLOCK + register o, @emitter.start_mapping(nil, maptag, false, Nodes::Mapping::BLOCK) @emitter.scalar 'str', nil, nil, true, false, Nodes::Scalar::ANY @emitter.scalar str, nil, tag, plain, quote, style @@ -282,17 +367,46 @@ module Psych end def visit_Hash o - tag = o.class == ::Hash ? nil : "!ruby/hash:#{o.class}" - implicit = !tag + ivars = o.instance_variables - register(o, @emitter.start_mapping(nil, tag, implicit, Psych::Nodes::Mapping::BLOCK)) + if ivars.any? + tag = "!ruby/hash-with-ivars" + tag << ":#{o.class}" unless o.class == ::Hash - o.each do |k,v| - accept k - accept v - end + register(o, @emitter.start_mapping(nil, tag, false, Psych::Nodes::Mapping::BLOCK)) - @emitter.end_mapping + @emitter.scalar 'elements', nil, nil, true, false, Nodes::Scalar::ANY + + @emitter.start_mapping nil, nil, true, Nodes::Mapping::BLOCK + o.each do |k,v| + accept k + accept v + end + @emitter.end_mapping + + @emitter.scalar 'ivars', nil, nil, true, false, Nodes::Scalar::ANY + + @emitter.start_mapping nil, nil, true, Nodes::Mapping::BLOCK + o.instance_variables.each do |ivar| + accept ivar + accept o.instance_variable_get ivar + end + @emitter.end_mapping + + @emitter.end_mapping + else + tag = o.class == ::Hash ? nil : "!ruby/hash:#{o.class}" + implicit = !tag + + register(o, @emitter.start_mapping(nil, tag, implicit, Psych::Nodes::Mapping::BLOCK)) + + o.each do |k,v| + accept k + accept v + end + + @emitter.end_mapping + end end def visit_Psych_Set o @@ -321,10 +435,37 @@ module Psych end def visit_Symbol o - @emitter.scalar ":#{o}", nil, nil, true, false, Nodes::Scalar::ANY + if o.empty? + @emitter.scalar "", nil, '!ruby/symbol', false, false, Nodes::Scalar::ANY + else + @emitter.scalar ":#{o}", nil, nil, true, false, Nodes::Scalar::ANY + end + end + + def visit_BasicObject o + tag = Psych.dump_tags[o.class] + tag ||= "!ruby/marshalable:#{o.class.name}" + + map = @emitter.start_mapping(nil, tag, false, Nodes::Mapping::BLOCK) + register(o, map) + + o.marshal_dump.each(&method(:accept)) + + @emitter.end_mapping end private + # FIXME: Remove the index and count checks in Psych 3.0 + NULL = "\x00" + BINARY_RANGE = "\x00-\x7F" + WS_RANGE = "^ -~\t\r\n" + + def binary? string + (string.encoding == Encoding::ASCII_8BIT && !string.ascii_only?) || + string.index(NULL) || + string.count(BINARY_RANGE, WS_RANGE).fdiv(string.length) > 0.3 + end + def visit_array_subclass o tag = "!ruby/array:#{o.class}" if o.instance_variables.empty? @@ -401,11 +542,12 @@ module Psych end def register target, yaml_obj - @st[target.object_id] = yaml_obj + @st.register target, yaml_obj yaml_obj end def dump_coder o + @coders << o tag = Psych.dump_tags[o.class] unless tag klass = o.class == Object ? nil : o.class.name @@ -430,7 +572,7 @@ module Psych when :map @emitter.start_mapping nil, c.tag, c.implicit, c.style c.map.each do |k,v| - @emitter.scalar k, nil, nil, true, false, Nodes::Scalar::ANY + accept k accept v end @emitter.end_mapping diff --git a/lib/psych/y.rb b/lib/psych/y.rb new file mode 100644 index 0000000..d0e049d --- /dev/null +++ b/lib/psych/y.rb @@ -0,0 +1,9 @@ +module Kernel + ### + # An alias for Psych.dump_stream meant to be used with IRB. + def y *objects + puts Psych.dump_stream(*objects) + end + private :y +end + diff --git a/test/psych/.swp b/test/psych/.swp Binary files differdeleted file mode 100644 index ea9da4d..0000000 --- a/test/psych/.swp +++ /dev/null diff --git a/test/psych/handlers/test_recorder.rb b/test/psych/handlers/test_recorder.rb new file mode 100644 index 0000000..96b8eac --- /dev/null +++ b/test/psych/handlers/test_recorder.rb @@ -0,0 +1,25 @@ +require 'psych/helper' +require 'psych/handlers/recorder' + +module Psych + module Handlers + class TestRecorder < TestCase + def test_replay + yaml = "--- foo\n...\n" + output = StringIO.new + + recorder = Psych::Handlers::Recorder.new + parser = Psych::Parser.new recorder + parser.parse yaml + + assert_equal 5, recorder.events.length + + emitter = Psych::Emitter.new output + recorder.events.each do |m, args| + emitter.send m, *args + end + assert_equal yaml, output.string + end + end + end +end diff --git a/test/psych/helper.rb b/test/psych/helper.rb index 1c57556..468beac 100644 --- a/test/psych/helper.rb +++ b/test/psych/helper.rb @@ -7,6 +7,35 @@ require 'psych' module Psych class TestCase < MiniTest::Unit::TestCase + def self.suppress_warning + verbose, $VERBOSE = $VERBOSE, nil + yield + ensure + $VERBOSE = verbose + end + + def with_default_external(enc) + verbose, $VERBOSE = $VERBOSE, nil + origenc, Encoding.default_external = Encoding.default_external, enc + $VERBOSE = verbose + yield + ensure + verbose, $VERBOSE = $VERBOSE, nil + Encoding.default_external = origenc + $VERBOSE = verbose + end + + def with_default_internal(enc) + verbose, $VERBOSE = $VERBOSE, nil + origenc, Encoding.default_internal = Encoding.default_internal, enc + $VERBOSE = verbose + yield + ensure + verbose, $VERBOSE = $VERBOSE, nil + Encoding.default_internal = origenc + $VERBOSE = verbose + end + # # Convert between Psych and the object to verify correct parsing and # emitting @@ -32,7 +61,7 @@ module Psych end def assert_cycle( obj ) - v = Visitors::YAMLTree.new + v = Visitors::YAMLTree.create v << obj assert_equal(obj, Psych.load(v.tree.yaml)) assert_equal( obj, Psych::load(Psych.dump(obj))) @@ -55,3 +84,32 @@ module Psych end end end + +# backport so that tests will run on 1.9 and 2.0.0 +unless Tempfile.respond_to? :create + def Tempfile.create(basename, *rest) + tmpfile = nil + Dir::Tmpname.create(basename, *rest) do |tmpname, n, opts| + mode = File::RDWR|File::CREAT|File::EXCL + perm = 0600 + if opts + mode |= opts.delete(:mode) || 0 + opts[:perm] = perm + perm = nil + else + opts = perm + end + tmpfile = File.open(tmpname, mode, opts) + end + if block_given? + begin + yield tmpfile + ensure + tmpfile.close if !tmpfile.closed? + File.unlink tmpfile + end + else + tmpfile + end + end +end diff --git a/test/psych/json/test_stream.rb b/test/psych/json/test_stream.rb index 4690ad2..b0c33e6 100644 --- a/test/psych/json/test_stream.rb +++ b/test/psych/json/test_stream.rb @@ -65,7 +65,7 @@ module Psych @stream.push list json = @io.string - assert_match(/]$/, json) + assert_match(/\]$/, json) assert_match(/^--- \[/, json) assert_match(/["]one["]/, json) assert_match(/["]two["]/, json) diff --git a/test/psych/test_alias_and_anchor.rb b/test/psych/test_alias_and_anchor.rb index 48771d6..9e2c240 100644 --- a/test/psych/test_alias_and_anchor.rb +++ b/test/psych/test_alias_and_anchor.rb @@ -1,4 +1,12 @@ -require 'psych/helper' +require_relative 'helper' + +class ObjectWithInstanceVariables + attr_accessor :var1, :var2 +end + +class SubStringWithInstanceVariables < String + attr_accessor :var1 +end module Psych class TestAliasAndAnchor < TestCase @@ -14,6 +22,40 @@ EOYAML result.each {|el| assert_same(result[0], el) } end + def test_mri_compatibility_object_with_ivars + yaml = <<EOYAML +--- +- &id001 !ruby/object:ObjectWithInstanceVariables + var1: test1 + var2: test2 +- *id001 +- *id001 +EOYAML + + result = Psych.load yaml + result.each do |el| + assert_same(result[0], el) + assert_equal('test1', el.var1) + assert_equal('test2', el.var2) + end + end + + def test_mri_compatibility_substring_with_ivars + yaml = <<EOYAML +--- +- &id001 !str:SubStringWithInstanceVariables + str: test + "@var1": test +- *id001 +- *id001 +EOYAML + result = Psych.load yaml + result.each do |el| + assert_same(result[0], el) + assert_equal('test', el.var1) + end + end + def test_anchor_alias_round_trip o = Object.new original = [o,o,o] @@ -22,5 +64,33 @@ EOYAML result = Psych.load yaml result.each {|el| assert_same(result[0], el) } end + + def test_anchor_alias_round_trip_object_with_ivars + o = ObjectWithInstanceVariables.new + o.var1 = 'test1' + o.var2 = 'test2' + original = [o,o,o] + + yaml = Psych.dump original + result = Psych.load yaml + result.each do |el| + assert_same(result[0], el) + assert_equal('test1', el.var1) + assert_equal('test2', el.var2) + end + end + + def test_anchor_alias_round_trip_substring_with_ivars + o = SubStringWithInstanceVariables.new + o.var1 = 'test' + original = [o,o,o] + + yaml = Psych.dump original + result = Psych.load yaml + result.each do |el| + assert_same(result[0], el) + assert_equal('test', el.var1) + end + end end end diff --git a/test/psych/test_array.rb b/test/psych/test_array.rb index 9eedbb4..960ffd7 100644 --- a/test/psych/test_array.rb +++ b/test/psych/test_array.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestArray < TestCase @@ -14,6 +14,16 @@ module Psych @list = [{ :a => 'b' }, 'foo'] end + def test_another_subclass_with_attributes + y = Y.new.tap {|y| y.val = 1} + y << "foo" << "bar" + y = Psych.load Psych.dump y + + assert_equal %w{foo bar}, y + assert_equal Y, y.class + assert_equal 1, y.val + end + def test_subclass yaml = Psych.dump X.new assert_match X.name, yaml diff --git a/test/psych/test_boolean.rb b/test/psych/test_boolean.rb index ebfa25e..b656f4f 100644 --- a/test/psych/test_boolean.rb +++ b/test/psych/test_boolean.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych ### diff --git a/test/psych/test_class.rb b/test/psych/test_class.rb index 156f2fb..c7f964c 100644 --- a/test/psych/test_class.rb +++ b/test/psych/test_class.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestClass < TestCase diff --git a/test/psych/test_coder.rb b/test/psych/test_coder.rb index 7539c7d..7571e89 100644 --- a/test/psych/test_coder.rb +++ b/test/psych/test_coder.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestCoder < TestCase @@ -85,7 +85,7 @@ module Psych end def encode_with coder - coder.represent_map self.class.name, { 'a' => 'b' } + coder.represent_map self.class.name, { "string" => 'a', :symbol => 'b' } end end @@ -131,7 +131,7 @@ module Psych def test_represent_map thing = Psych.load(Psych.dump(RepresentWithMap.new)) - assert_equal({ 'a' => 'b' }, thing.map) + assert_equal({ "string" => 'a', :symbol => 'b' }, thing.map) end def test_represent_sequence diff --git a/test/psych/test_date_time.rb b/test/psych/test_date_time.rb index fb76cb3..72150ad 100644 --- a/test/psych/test_date_time.rb +++ b/test/psych/test_date_time.rb @@ -1,8 +1,21 @@ -require 'psych/helper' +require_relative 'helper' require 'date' module Psych class TestDateTime < TestCase + def test_negative_year + time = Time.utc -1, 12, 16 + assert_cycle time + end + + def test_new_datetime + assert_cycle DateTime.new + end + + def test_invalid_date + assert_cycle "2013-10-31T10:40:07-000000000000033" + end + def test_string_tag dt = DateTime.now yaml = Psych.dump dt @@ -13,5 +26,13 @@ module Psych dt = DateTime.now assert_cycle dt end + + def test_alias_with_time + t = Time.now + h = {:a => t, :b => t} + yaml = Psych.dump h + assert_match('&', yaml) + assert_match('*', yaml) + end end end diff --git a/test/psych/test_deprecated.rb b/test/psych/test_deprecated.rb index 3740b6f..fd2d329 100644 --- a/test/psych/test_deprecated.rb +++ b/test/psych/test_deprecated.rb @@ -1,8 +1,9 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestDeprecated < TestCase def teardown + $VERBOSE = @orig_verbose Psych.domain_types.clear end @@ -27,6 +28,7 @@ module Psych def setup @qe = QuickEmitter.new + @orig_verbose, $VERBOSE = $VERBOSE, false end def test_quick_emit @@ -145,7 +147,9 @@ module Psych end class YamlAs - psych_yaml_as 'helloworld' # this should be yaml_as but to avoid syck + TestCase.suppress_warning do + psych_yaml_as 'helloworld' # this should be yaml_as but to avoid syck + end end def test_yaml_as diff --git a/test/psych/test_document.rb b/test/psych/test_document.rb index 05d9bbf..bd77d60 100644 --- a/test/psych/test_document.rb +++ b/test/psych/test_document.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestDocument < TestCase diff --git a/test/psych/test_emitter.rb b/test/psych/test_emitter.rb index dfd20e1..1c96c12 100644 --- a/test/psych/test_emitter.rb +++ b/test/psych/test_emitter.rb @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -require 'psych/helper' +require_relative 'helper' module Psych class TestEmitter < TestCase @@ -11,8 +11,7 @@ module Psych end def test_line_width - assert_equal 0, @emitter.line_width - assert_equal 10, @emitter.line_width = 10 + @emitter.line_width = 10 assert_equal 10, @emitter.line_width end diff --git a/test/psych/test_encoding.rb b/test/psych/test_encoding.rb index 1abee0d..517cae2 100644 --- a/test/psych/test_encoding.rb +++ b/test/psych/test_encoding.rb @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -require 'psych/helper' +require_relative 'helper' module Psych class TestEncoding < TestCase @@ -31,6 +31,11 @@ module Psych @emitter = Psych::Emitter.new @buffer end + def test_dump_load_encoding_object + assert_cycle Encoding::US_ASCII + assert_cycle Encoding::UTF_8 + end + def test_transcode_shiftjis str = "こんにちは！" loaded = Psych.load("--- こんにちは！".encode('SHIFT_JIS')) @@ -50,58 +55,54 @@ module Psych end def test_io_shiftjis - t = Tempfile.new(['shiftjis', 'yml'], :encoding => 'SHIFT_JIS') - t.write '--- こんにちは！' - t.close - - # If the external encoding isn't utf8, utf16le, or utf16be, we cannot - # process the file. - File.open(t.path, 'r', :encoding => 'SHIFT_JIS') do |f| - assert_raises Psych::SyntaxError do - Psych.load(f) + Tempfile.create(['shiftjis', 'yml'], :encoding => 'SHIFT_JIS') {|t| + t.write '--- こんにちは！' + t.close + + # If the external encoding isn't utf8, utf16le, or utf16be, we cannot + # process the file. + File.open(t.path, 'r', :encoding => 'SHIFT_JIS') do |f| + assert_raises Psych::SyntaxError do + Psych.load(f) + end end - end - - t.close(true) + } end def test_io_utf16le - t = Tempfile.new(['utf16le', 'yml']) - t.binmode - t.write '--- こんにちは！'.encode('UTF-16LE') - t.close + Tempfile.create(['utf16le', 'yml']) {|t| + t.binmode + t.write '--- こんにちは！'.encode('UTF-16LE') + t.close - File.open(t.path, 'rb', :encoding => 'UTF-16LE') do |f| - assert_equal "こんにちは！", Psych.load(f) - end - - t.close(true) + File.open(t.path, 'rb', :encoding => 'UTF-16LE') do |f| + assert_equal "こんにちは！", Psych.load(f) + end + } end def test_io_utf16be - t = Tempfile.new(['utf16be', 'yml']) - t.binmode - t.write '--- こんにちは！'.encode('UTF-16BE') - t.close - - File.open(t.path, 'rb', :encoding => 'UTF-16BE') do |f| - assert_equal "こんにちは！", Psych.load(f) - end + Tempfile.create(['utf16be', 'yml']) {|t| + t.binmode + t.write '--- こんにちは！'.encode('UTF-16BE') + t.close - t.close(true) + File.open(t.path, 'rb', :encoding => 'UTF-16BE') do |f| + assert_equal "こんにちは！", Psych.load(f) + end + } end def test_io_utf8 - t = Tempfile.new(['utf8', 'yml']) - t.binmode - t.write '--- こんにちは！'.encode('UTF-8') - t.close - - File.open(t.path, 'rb', :encoding => 'UTF-8') do |f| - assert_equal "こんにちは！", Psych.load(f) - end + Tempfile.create(['utf8', 'yml']) {|t| + t.binmode + t.write '--- こんにちは！'.encode('UTF-8') + t.close - t.close(true) + File.open(t.path, 'rb', :encoding => 'UTF-8') do |f| + assert_equal "こんにちは！", Psych.load(f) + end + } end def test_emit_alias @@ -114,19 +115,14 @@ module Psych end def test_to_yaml_is_valid - ext_before = Encoding.default_external - int_before = Encoding.default_internal - - Encoding.default_external = Encoding::US_ASCII - Encoding.default_internal = nil - - s = "こんにちは！" - # If no encoding is specified, use UTF-8 - assert_equal Encoding::UTF_8, Psych.dump(s).encoding - assert_equal s, Psych.load(Psych.dump(s)) - ensure - Encoding.default_external = ext_before - Encoding.default_internal = int_before + with_default_external(Encoding::US_ASCII) do + with_default_internal(nil) do + s = "こんにちは！" + # If no encoding is specified, use UTF-8 + assert_equal Encoding::UTF_8, Psych.dump(s).encoding + assert_equal s, Psych.load(Psych.dump(s)) + end + end end def test_start_mapping @@ -191,19 +187,14 @@ module Psych end def test_default_internal - before = Encoding.default_internal - - Encoding.default_internal = 'EUC-JP' + with_default_internal(Encoding::EUC_JP) do + str = "壁に耳あり、障子に目あり" + assert_equal @utf8, str.encoding - str = "壁に耳あり、障子に目あり" - yaml = "--- #{str}" - assert_equal @utf8, str.encoding - - @parser.parse str - assert_encodings Encoding.find('EUC-JP'), @handler.strings - assert_equal str, @handler.strings.first.encode('UTF-8') - ensure - Encoding.default_internal = before + @parser.parse str + assert_encodings Encoding::EUC_JP, @handler.strings + assert_equal str, @handler.strings.first.encode('UTF-8') + end end def test_scalar diff --git a/test/psych/test_engine_manager.rb b/test/psych/test_engine_manager.rb deleted file mode 100644 index b52fd09..0000000 --- a/test/psych/test_engine_manager.rb +++ /dev/null @@ -1,57 +0,0 @@ -require 'psych/helper' -require 'yaml' - -module Psych - class TestEngineManager < TestCase - def teardown - YAML::ENGINE.yamler = 'syck' - end - - def test_bad_engine - assert_raises(ArgumentError) do - YAML::ENGINE.yamler = 'foooo' - end - end - - def test_set_psych - YAML::ENGINE.yamler = 'psych' - assert_equal Psych, YAML - assert_equal 'psych', YAML::ENGINE.yamler - end - - def test_set_syck - YAML::ENGINE.yamler = 'syck' - assert_equal ::Syck, YAML - assert_equal 'syck', YAML::ENGINE.yamler - end - - A = Struct.new(:name) - - def test_dump_types - YAML::ENGINE.yamler = 'psych' - - assert_to_yaml ::Object.new - assert_to_yaml Time.now - assert_to_yaml Date.today - assert_to_yaml('a' => 'b') - assert_to_yaml A.new('foo') - assert_to_yaml %w{a b} - assert_to_yaml Exception.new('foo') - assert_to_yaml "hello!" - assert_to_yaml :fooo - assert_to_yaml(1..10) - assert_to_yaml(/hello!~/) - assert_to_yaml 1 - assert_to_yaml 1.2 - assert_to_yaml Rational(1, 2) - assert_to_yaml Complex(1, 2) - assert_to_yaml true - assert_to_yaml false - assert_to_yaml nil - end - - def assert_to_yaml obj - assert obj.to_yaml, "#{obj.class} to_yaml works" - end - end -end diff --git a/test/psych/test_exception.rb b/test/psych/test_exception.rb index c6d98d7..30dfb24 100644 --- a/test/psych/test_exception.rb +++ b/test/psych/test_exception.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestException < TestCase @@ -16,6 +16,12 @@ module Psych @wups = Wups.new end + def test_naming_exception + err = String.xxx rescue $! + new_err = Psych.load(Psych.dump(err)) + assert_equal err.message, new_err.message + end + def test_load_takes_file ex = assert_raises(Psych::SyntaxError) do Psych.load '--- `' @@ -56,27 +62,27 @@ module Psych end def test_parse_file_exception - t = Tempfile.new(['parsefile', 'yml']) - t.binmode - t.write '--- `' - t.close - ex = assert_raises(Psych::SyntaxError) do - Psych.parse_file t.path - end - assert_equal t.path, ex.file - t.close(true) + Tempfile.create(['parsefile', 'yml']) {|t| + t.binmode + t.write '--- `' + t.close + ex = assert_raises(Psych::SyntaxError) do + Psych.parse_file t.path + end + assert_equal t.path, ex.file + } end def test_load_file_exception - t = Tempfile.new(['loadfile', 'yml']) - t.binmode - t.write '--- `' - t.close - ex = assert_raises(Psych::SyntaxError) do - Psych.load_file t.path - end - assert_equal t.path, ex.file - t.close(true) + Tempfile.create(['loadfile', 'yml']) {|t| + t.binmode + t.write '--- `' + t.close + ex = assert_raises(Psych::SyntaxError) do + Psych.load_file t.path + end + assert_equal t.path, ex.file + } end def test_psych_parse_takes_file @@ -126,5 +132,26 @@ module Psych assert_equal 1, w.foo assert_nil w.bar end + + def test_psych_syntax_error + Tempfile.create(['parsefile', 'yml']) do |t| + t.binmode + t.write '--- `' + t.close + + begin + Psych.parse_file t.path + rescue StandardError + assert true # count assertion + ensure + return unless $! + + ancestors = $!.class.ancestors.inspect + + flunk "Psych::SyntaxError not rescued by StandardError: #{ancestors}" + end + end + end + end end diff --git a/test/psych/test_hash.rb b/test/psych/test_hash.rb index 4bd4edf..066df66 100644 --- a/test/psych/test_hash.rb +++ b/test/psych/test_hash.rb @@ -1,15 +1,64 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestHash < TestCase class X < Hash end + class HashWithCustomInit < Hash + attr_reader :obj + def initialize(obj) + @obj = obj + end + end + + class HashWithCustomInitNoIvar < Hash + def initialize(obj) + # *shrug* + end + end + def setup super @hash = { :a => 'b' } end + def test_custom_initialized + a = [1,2,3,4,5] + t1 = HashWithCustomInit.new(a) + t2 = Psych.load(Psych.dump(t1)) + assert_equal t1, t2 + assert_cycle t1 + end + + def test_custom_initialize_no_ivar + t1 = HashWithCustomInitNoIvar.new(nil) + t2 = Psych.load(Psych.dump(t1)) + assert_equal t1, t2 + assert_cycle t1 + end + + def test_hash_with_ivars + @hash.instance_variable_set :@foo, 'bar' + dup = Psych.load Psych.dump @hash + assert_equal 'bar', dup.instance_variable_get(:@foo) + end + + def test_hash_subclass_with_ivars + x = X.new + x[:a] = 'b' + x.instance_variable_set :@foo, 'bar' + dup = Psych.load Psych.dump x + assert_cycle x + assert_equal 'bar', dup.instance_variable_get(:@foo) + assert_equal X, dup.class + end + + def test_load_with_class_syck_compatibility + hash = Psych.load "--- !ruby/object:Hash\n:user_id: 7\n:username: Lucas\n" + assert_equal({ user_id: 7, username: 'Lucas'}, hash) + end + def test_empty_subclass assert_match "!ruby/hash:#{X}", Psych.dump(X.new) x = Psych.load Psych.dump X.new diff --git a/test/psych/test_json_tree.rb b/test/psych/test_json_tree.rb index eed8cf3..a23fc1a 100644 --- a/test/psych/test_json_tree.rb +++ b/test/psych/test_json_tree.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestJSONTree < TestCase @@ -45,7 +45,7 @@ module Psych def test_list_to_json list = %w{ one two } json = Psych.to_json(list) - assert_match(/]$/, json) + assert_match(/\]$/, json) assert_match(/^\[/, json) assert_match(/"one"/, json) assert_match(/"two"/, json) diff --git a/test/psych/test_marshalable.rb b/test/psych/test_marshalable.rb new file mode 100644 index 0000000..7df74ee --- /dev/null +++ b/test/psych/test_marshalable.rb @@ -0,0 +1,54 @@ +require_relative 'helper' +require 'delegate' + +module Psych + class TestMarshalable < TestCase + def test_objects_defining_marshal_dump_and_marshal_load_can_be_dumped + sd = SimpleDelegator.new(1) + loaded = Psych.load(Psych.dump(sd)) + + assert_instance_of(SimpleDelegator, loaded) + assert_equal(sd, loaded) + end + + class PsychCustomMarshalable < BasicObject + attr_reader :foo + + def initialize(foo) + @foo = foo + end + + def marshal_dump + [foo] + end + + def mashal_load(data) + @foo = data[0] + end + + def init_with(coder) + @foo = coder['foo'] + end + + def encode_with(coder) + coder['foo'] = 2 + end + + def respond_to?(method) + [:marshal_dump, :marshal_load, :init_with, :encode_with].include?(method) + end + + def class + PsychCustomMarshalable + end + end + + def test_init_with_takes_priority_over_marshal_methods + obj = PsychCustomMarshalable.new(1) + loaded = Psych.load(Psych.dump(obj)) + + assert(PsychCustomMarshalable === loaded) + assert_equal(2, loaded.foo) + end + end +end diff --git a/test/psych/test_merge_keys.rb b/test/psych/test_merge_keys.rb index bf5968f..1620a6a 100644 --- a/test/psych/test_merge_keys.rb +++ b/test/psych/test_merge_keys.rb @@ -1,7 +1,106 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestMergeKeys < TestCase + class Product + attr_reader :bar + end + + def test_merge_key_with_bare_hash + doc = Psych.load <<-eodoc +map: + <<: + hello: world + eodoc + hash = { "map" => { "hello" => "world" } } + assert_equal hash, doc + end + + def test_roundtrip_with_chevron_key + h = {} + v = { 'a' => h, '<<' => h } + assert_cycle v + end + + def test_explicit_string + doc = Psych.load <<-eoyml +a: &me { hello: world } +b: { !!str '<<': *me } +eoyml + expected = { + "a" => { "hello" => "world" }, + "b" => { + "<<" => { "hello" => "world" } + } + } + assert_equal expected, doc + end + + def test_mergekey_with_object + s = <<-eoyml +foo: &foo + bar: 10 +product: + !ruby/object:#{Product.name} + <<: *foo + eoyml + hash = Psych.load s + assert_equal({"bar" => 10}, hash["foo"]) + product = hash["product"] + assert_equal 10, product.bar + end + + def test_merge_nil + yaml = <<-eoyml +defaults: &defaults +development: + <<: *defaults + eoyml + assert_equal({'<<' => nil }, Psych.load(yaml)['development']) + end + + def test_merge_array + yaml = <<-eoyml +foo: &hello +- 1 +baz: + <<: *hello + eoyml + assert_equal({'<<' => [1]}, Psych.load(yaml)['baz']) + end + + def test_merge_is_not_partial + yaml = <<-eoyml +default: &default + hello: world +foo: &hello +- 1 +baz: + <<: [*hello, *default] + eoyml + doc = Psych.load yaml + refute doc['baz'].key? 'hello' + assert_equal({'<<' => [[1], {"hello"=>"world"}]}, Psych.load(yaml)['baz']) + end + + def test_merge_seq_nil + yaml = <<-eoyml +foo: &hello +baz: + <<: [*hello] + eoyml + assert_equal({'<<' => [nil]}, Psych.load(yaml)['baz']) + end + + def test_bad_seq_merge + yaml = <<-eoyml +defaults: &defaults [1, 2, 3] +development: + <<: *defaults + eoyml + assert_equal({'<<' => [1,2,3]}, Psych.load(yaml)['development']) + end + def test_missing_merge_key yaml = <<-eoyml bar: diff --git a/test/psych/test_nil.rb b/test/psych/test_nil.rb index 4f32b77..3dbf562 100644 --- a/test/psych/test_nil.rb +++ b/test/psych/test_nil.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestNil < TestCase diff --git a/test/psych/test_null.rb b/test/psych/test_null.rb index 0fee1d2..1725550 100644 --- a/test/psych/test_null.rb +++ b/test/psych/test_null.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych ### diff --git a/test/psych/test_numeric.rb b/test/psych/test_numeric.rb index bae723a..5378b4a 100644 --- a/test/psych/test_numeric.rb +++ b/test/psych/test_numeric.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' require 'bigdecimal' module Psych @@ -7,6 +7,19 @@ module Psych # http://yaml.org/type/float.html # http://yaml.org/type/int.html class TestNumeric < TestCase + def setup + @old_debug = $DEBUG + $DEBUG = true + end + + def teardown + $DEBUG = @old_debug + end + + def test_load_float_with_dot + assert_equal 1.0, Psych.load('--- 1.') + end + def test_non_float_with_0 str = Psych.load('--- 090') assert_equal '090', str @@ -21,5 +34,12 @@ module Psych decimal = BigDecimal("12.34") assert_cycle decimal end + + def test_does_not_attempt_numeric + str = Psych.load('--- 4 roses') + assert_equal '4 roses', str + str = Psych.load('--- 1.1.1') + assert_equal '1.1.1', str + end end end diff --git a/test/psych/test_object.rb b/test/psych/test_object.rb index 6145bb6..5e3ce82 100644 --- a/test/psych/test_object.rb +++ b/test/psych/test_object.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class Tagged diff --git a/test/psych/test_object_references.rb b/test/psych/test_object_references.rb index 2a659a3..273b466 100644 --- a/test/psych/test_object_references.rb +++ b/test/psych/test_object_references.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestObjectReferences < TestCase @@ -26,6 +26,10 @@ module Psych assert_reference_trip DateTime.now end + def test_struct_has_references + assert_reference_trip Struct.new(:foo).new(1) + end + def assert_reference_trip obj yml = Psych.dump([obj, obj]) assert_match(/\*-?\d+/, yml) @@ -35,7 +39,7 @@ module Psych def test_float_references data = Psych.load <<-eoyml ---- +---\s - &name 1.2 - *name eoyml @@ -56,7 +60,7 @@ module Psych def test_regexp_references data = Psych.load <<-eoyml ---- +---\s - &name !ruby/regexp /pattern/i - *name eoyml diff --git a/test/psych/test_omap.rb b/test/psych/test_omap.rb index 53f55f5..36edc26 100644 --- a/test/psych/test_omap.rb +++ b/test/psych/test_omap.rb @@ -1,7 +1,14 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestOmap < TestCase + def test_parse_as_map + o = Psych.load "--- !!omap\na: 1\nb: 2" + assert_kind_of Psych::Omap, o + assert_equal 1, o['a'] + assert_equal 2, o['b'] + end + def test_self_referential map = Psych::Omap.new map['foo'] = 'bar' diff --git a/test/psych/test_parser.rb b/test/psych/test_parser.rb index acbdd96..0abe0dd 100644 --- a/test/psych/test_parser.rb +++ b/test/psych/test_parser.rb @@ -1,6 +1,6 @@ # coding: utf-8 -require 'psych/helper' +require_relative 'helper' module Psych class TestParser < TestCase diff --git a/test/psych/test_psych.rb b/test/psych/test_psych.rb index 9986699..8054bd6 100644 --- a/test/psych/test_psych.rb +++ b/test/psych/test_psych.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' require 'stringio' require 'tempfile' @@ -20,7 +20,7 @@ class TestPsych < Psych::TestCase def test_canonical yml = Psych.dump({:a => {'b' => 'c'}}, {:canonical => true}) - assert_match(/\? ! "b/, yml) + assert_match(/\? "b/, yml) end def test_header @@ -64,7 +64,7 @@ class TestPsych < Psych::TestCase def test_dump_file hash = {'hello' => 'TGIF!'} - Tempfile.open('fun.yml') do |io| + Tempfile.create('fun.yml') do |io| assert_equal io, Psych.dump(hash, io) io.rewind assert_equal Psych.dump(hash), io.read @@ -125,21 +125,21 @@ class TestPsych < Psych::TestCase end def test_load_file - t = Tempfile.new(['yikes', 'yml']) - t.binmode - t.write('--- hello world') - t.close - assert_equal 'hello world', Psych.load_file(t.path) - t.close(true) + Tempfile.create(['yikes', 'yml']) {|t| + t.binmode + t.write('--- hello world') + t.close + assert_equal 'hello world', Psych.load_file(t.path) + } end def test_parse_file - t = Tempfile.new(['yikes', 'yml']) - t.binmode - t.write('--- hello world') - t.close - assert_equal 'hello world', Psych.parse_file(t.path).transform - t.close(true) + Tempfile.create(['yikes', 'yml']) {|t| + t.binmode + t.write('--- hello world') + t.close + assert_equal 'hello world', Psych.parse_file(t.path).transform + } end def test_degenerate_strings diff --git a/test/psych/test_safe_load.rb b/test/psych/test_safe_load.rb new file mode 100644 index 0000000..dd299c0 --- /dev/null +++ b/test/psych/test_safe_load.rb @@ -0,0 +1,97 @@ +require 'psych/helper' + +module Psych + class TestSafeLoad < TestCase + class Foo; end + + [1, 2.2, {}, [], "foo"].each do |obj| + define_method(:"test_basic_#{obj.class}") do + assert_safe_cycle obj + end + end + + def test_no_recursion + x = [] + x << x + assert_raises(Psych::BadAlias) do + Psych.safe_load Psych.dump(x) + end + end + + def test_explicit_recursion + x = [] + x << x + assert_equal(x, Psych.safe_load(Psych.dump(x), [], [], true)) + end + + def test_symbol_whitelist + yml = Psych.dump :foo + assert_raises(Psych::DisallowedClass) do + Psych.safe_load yml + end + assert_equal(:foo, Psych.safe_load(yml, [Symbol], [:foo])) + end + + def test_symbol + assert_raises(Psych::DisallowedClass) do + assert_safe_cycle :foo + end + assert_raises(Psych::DisallowedClass) do + Psych.safe_load '--- !ruby/symbol foo', [] + end + assert_safe_cycle :foo, [Symbol] + assert_safe_cycle :foo, %w{ Symbol } + assert_equal :foo, Psych.safe_load('--- !ruby/symbol foo', [Symbol]) + end + + def test_foo + assert_raises(Psych::DisallowedClass) do + Psych.safe_load '--- !ruby/object:Foo {}', [Foo] + end + assert_raises(Psych::DisallowedClass) do + assert_safe_cycle Foo.new + end + assert_kind_of(Foo, Psych.safe_load(Psych.dump(Foo.new), [Foo])) + end + + X = Struct.new(:x) + def test_struct_depends_on_sym + assert_safe_cycle(X.new, [X, Symbol]) + assert_raises(Psych::DisallowedClass) do + cycle X.new, [X] + end + end + + def test_anon_struct + assert Psych.safe_load(<<-eoyml, [Struct, Symbol]) +--- !ruby/struct + foo: bar + eoyml + + assert_raises(Psych::DisallowedClass) do + Psych.safe_load(<<-eoyml, [Struct]) +--- !ruby/struct + foo: bar + eoyml + end + + assert_raises(Psych::DisallowedClass) do + Psych.safe_load(<<-eoyml, [Symbol]) +--- !ruby/struct + foo: bar + eoyml + end + end + + private + + def cycle object, whitelist = [] + Psych.safe_load(Psych.dump(object), whitelist) + end + + def assert_safe_cycle object, whitelist = [] + other = cycle object, whitelist + assert_equal object, other + end + end +end diff --git a/test/psych/test_scalar.rb b/test/psych/test_scalar.rb index 3cf6b09..e6b7697 100644 --- a/test/psych/test_scalar.rb +++ b/test/psych/test_scalar.rb @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -require 'psych/helper' +require_relative 'helper' module Psych class TestScalar < TestCase diff --git a/test/psych/test_scalar_scanner.rb b/test/psych/test_scalar_scanner.rb index cf0dfff..e8e423c 100644 --- a/test/psych/test_scalar_scanner.rb +++ b/test/psych/test_scalar_scanner.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' require 'date' module Psych @@ -7,7 +7,7 @@ module Psych def setup super - @ss = Psych::ScalarScanner.new + @ss = Psych::ScalarScanner.new ClassLoader.new end def test_scan_time @@ -21,6 +21,17 @@ module Psych end end + def test_scan_bad_time + [ '2001-12-15T02:59:73.1Z', + '2001-12-14t90:59:43.10-05:00', + '2001-92-14 21:59:43.10 -5', + '2001-12-15 92:59:43.10', + '2011-02-24 81:17:06 -0800', + ].each do |time_str| + assert_equal time_str, @ss.tokenize(time_str) + end + end + def test_scan_bad_dates x = '2000-15-01' assert_equal x, @ss.tokenize(x) @@ -87,5 +98,9 @@ module Psych def test_scan_true assert_equal true, ss.tokenize('true') end + + def test_scan_strings_starting_with_underscores + assert_equal "_100", ss.tokenize('_100') + end end end diff --git a/test/psych/test_serialize_subclasses.rb b/test/psych/test_serialize_subclasses.rb index c822192..f597b7a 100644 --- a/test/psych/test_serialize_subclasses.rb +++ b/test/psych/test_serialize_subclasses.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestSerializeSubclasses < TestCase diff --git a/test/psych/test_set.rb b/test/psych/test_set.rb index bea67d9..921fe22 100644 --- a/test/psych/test_set.rb +++ b/test/psych/test_set.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestSet < TestCase diff --git a/test/psych/test_stream.rb b/test/psych/test_stream.rb index beca365..7e41178 100644 --- a/test/psych/test_stream.rb +++ b/test/psych/test_stream.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestStream < TestCase diff --git a/test/psych/test_string.rb b/test/psych/test_string.rb index c7d5c60..26a4e20 100644 --- a/test/psych/test_string.rb +++ b/test/psych/test_string.rb @@ -1,4 +1,5 @@ -require 'psych/helper' +# encoding: UTF-8 +require_relative 'helper' module Psych class TestString < TestCase @@ -9,6 +10,72 @@ module Psych attr_accessor :val end + class Z < String + def initialize + force_encoding Encoding::US_ASCII + end + end + + def test_string_with_newline + assert_equal "1\n2", Psych.load("--- ! '1\n\n 2'\n") + end + + def test_no_doublequotes_with_special_characters + assert_equal 2, Psych.dump(%Q{<%= ENV["PATH"] %>}).count('"') + end + + def test_no_quotes_when_start_with_non_ascii_character + yaml = Psych.dump 'Český non-ASCII'.encode(Encoding::UTF_8) + assert_match(/---\s*[^"'!]+$/, yaml) + end + + def test_doublequotes_when_there_is_a_single + yaml = Psych.dump "@123'abc" + assert_match(/---\s*"/, yaml) + end + + def test_cycle_x + str = X.new 'abc' + assert_cycle str + end + + def test_dash_dot + assert_cycle '-.' + assert_cycle '+.' + end + + def test_string_subclass_with_anchor + y = Psych.load <<-eoyml +--- +body: + string: &70121654388580 !ruby/string + str: ! 'foo' + x: + body: *70121654388580 + eoyml + assert_equal({"body"=>{"string"=>"foo", "x"=>{"body"=>"foo"}}}, y) + end + + def test_self_referential_string + y = Psych.load <<-eoyml +--- +string: &70121654388580 !ruby/string + str: ! 'foo' + body: *70121654388580 + eoyml + + assert_equal({"string"=>"foo"}, y) + value = y['string'] + assert_equal value, value.instance_variable_get(:@body) + end + + def test_another_subclass_with_attributes + y = Psych.load Psych.dump Y.new("foo").tap {|y| y.val = 1} + assert_equal "foo", y + assert_equal Y, y.class + assert_equal 1, y.val + end + def test_backwards_with_syck x = Psych.load "--- !str:#{X.name} foo\n\n" assert_equal X, x.class @@ -21,6 +88,12 @@ module Psych assert_equal X, x.class end + def test_empty_character_subclass + assert_match "!ruby/string:#{Z}", Psych.dump(Z.new) + x = Psych.load Psych.dump Z.new + assert_equal Z, x.class + end + def test_subclass_with_attributes y = Psych.load Psych.dump Y.new.tap {|y| y.val = 1} assert_equal Y, y.class @@ -33,8 +106,8 @@ module Psych assert_equal '01:03:05', Psych.load(yaml) end - def test_tagged_binary_should_be_dumped_as_binary - string = "hello world!" + def test_nonascii_string_as_binary + string = "hello \x80 world!" string.force_encoding 'ascii-8bit' yml = Psych.dump string assert_match(/binary/, yml) @@ -62,12 +135,19 @@ module Psych assert_equal string, Psych.load(yml) end + def test_ascii_only_8bit_string + string = "abc".encode(Encoding::ASCII_8BIT) + yml = Psych.dump string + refute_match(/binary/, yml) + assert_equal string, Psych.load(yml) + end + def test_string_with_ivars food = "is delicious" ivar = "on rock and roll" food.instance_variable_set(:@we_built_this_city, ivar) - str = Psych.load Psych.dump food + Psych.load Psych.dump food assert_equal ivar, food.instance_variable_get(:@we_built_this_city) end @@ -76,6 +156,10 @@ module Psych assert_cycle string end + def test_float_confusion + assert_cycle '1.' + end + def binary_string percentage = 0.31, length = 100 string = '' (percentage * length).to_i.times do |i| diff --git a/test/psych/test_struct.rb b/test/psych/test_struct.rb index 977aae0..8c7f251 100644 --- a/test/psych/test_struct.rb +++ b/test/psych/test_struct.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' class PsychStructWithIvar < Struct.new(:foo) attr_reader :bar diff --git a/test/psych/test_symbol.rb b/test/psych/test_symbol.rb index 3226141..558a672 100644 --- a/test/psych/test_symbol.rb +++ b/test/psych/test_symbol.rb @@ -1,7 +1,15 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestSymbol < TestCase + def test_cycle_empty + assert_cycle :'' + end + + def test_cycle_colon + assert_cycle :':' + end + def test_cycle assert_cycle :a end diff --git a/test/psych/test_tainted.rb b/test/psych/test_tainted.rb index fdcced4..37fc5b2 100644 --- a/test/psych/test_tainted.rb +++ b/test/psych/test_tainted.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestStringTainted < TestCase @@ -117,14 +117,14 @@ module Psych class TestIOTainted < TestStringTainted def assert_taintedness string - t = Tempfile.new(['something', 'yml']) - t.binmode - t.write string - t.close - File.open(t.path, 'r:bom|utf-8') { |f| - @parser.parse f + Tempfile.create(['something', 'yml']) {|t| + t.binmode + t.write string + t.close + File.open(t.path, 'r:bom|utf-8') { |f| + @parser.parse f + } } - t.close(true) end end end diff --git a/test/psych/test_to_yaml_properties.rb b/test/psych/test_to_yaml_properties.rb index 2636bec..5b4860c 100644 --- a/test/psych/test_to_yaml_properties.rb +++ b/test/psych/test_to_yaml_properties.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestToYamlProperties < MiniTest::Unit::TestCase diff --git a/test/psych/test_tree_builder.rb b/test/psych/test_tree_builder.rb index 9a134d5..7ad3ddd 100644 --- a/test/psych/test_tree_builder.rb +++ b/test/psych/test_tree_builder.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' module Psych class TestTreeBuilder < TestCase diff --git a/test/psych/test_yaml.rb b/test/psych/test_yaml.rb index 807c058..cd3e8ee 100644 --- a/test/psych/test_yaml.rb +++ b/test/psych/test_yaml.rb @@ -1,8 +1,8 @@ -# -*- mode: ruby; ruby-indent-level: 4; tab-width: 4 -*- +# -*- coding: us-ascii; mode: ruby; ruby-indent-level: 4; tab-width: 4 -*- # vim:sw=4:ts=4 # $Id$ # -require 'psych/helper' +require_relative 'helper' require 'ostruct' # [ruby-core:01946] @@ -250,7 +250,6 @@ EOY def test_spec_mapping_between_sequences # Complex key #1 - dj = Date.new( 2001, 7, 23 ) assert_parse_only( { [ 'Detroit Tigers', 'Chicago Cubs' ] => [ Date.new( 2001, 7, 23 ) ], [ 'New York Yankees', 'Atlanta Braves' ] => [ Date.new( 2001, 7, 2 ), Date.new( 2001, 8, 12 ), Date.new( 2001, 8, 14 ) ] }, <<EOY @@ -606,7 +605,7 @@ EOY def test_spec_domain_prefix customer_proc = proc { |type, val| if Hash === val - scheme, domain, type = type.split( ':', 3 ) + _, _, type = type.split( ':', 3 ) val['type'] = "domain #{type}" val else @@ -1266,4 +1265,24 @@ EOY Psych.load("2000-01-01 00:00:00.#{"0"*1000} +00:00\n") # '[ruby-core:13735]' end + + def test_multiline_string_uses_literal_style + yaml = Psych.dump("multi\nline\nstring") + assert_match("|", yaml) + end + + def test_string_starting_with_non_word_character_uses_double_quotes_without_exclamation_mark + yaml = Psych.dump("@123'abc") + refute_match("!", yaml) + end + + def test_string_dump_with_colon + yaml = Psych.dump 'x: foo' + refute_match '!', yaml + end + + def test_string_dump_starting_with_star + yaml = Psych.dump '*foo' + refute_match '!', yaml + end end diff --git a/test/psych/test_yamldbm.rb b/test/psych/test_yamldbm.rb index d978003..7853658 100644 --- a/test/psych/test_yamldbm.rb +++ b/test/psych/test_yamldbm.rb @@ -1,6 +1,4 @@ -# -*- coding: UTF-8 -*- - -require 'psych/helper' +require_relative 'helper' require 'tmpdir' begin @@ -13,7 +11,6 @@ module Psych class YAMLDBMTest < TestCase def setup - @engine, YAML::ENGINE.yamler = YAML::ENGINE.yamler, 'psych' @dir = Dir.mktmpdir("rubytest-file") File.chown(-1, Process.gid, @dir) @yamldbm_file = make_tmp_filename("yamldbm") @@ -21,7 +18,6 @@ module Psych end def teardown - YAML::ENGINE.yamler = @engine @yamldbm.clear @yamldbm.close FileUtils.remove_entry_secure @dir diff --git a/test/psych/test_yamlstore.rb b/test/psych/test_yamlstore.rb index 5d6fcb7..94f1330 100644 --- a/test/psych/test_yamlstore.rb +++ b/test/psych/test_yamlstore.rb @@ -1,4 +1,4 @@ -require 'psych/helper' +require_relative 'helper' require 'yaml/store' require 'tmpdir' @@ -7,7 +7,6 @@ module Psych class YAMLStoreTest < TestCase def setup - @engine, YAML::ENGINE.yamler = YAML::ENGINE.yamler, 'psych' @dir = Dir.mktmpdir("rubytest-file") File.chown(-1, Process.gid, @dir) @yamlstore_file = make_tmp_filename("yamlstore") @@ -15,7 +14,6 @@ module Psych end def teardown - YAML::ENGINE.yamler = @engine FileUtils.remove_entry_secure @dir end diff --git a/test/psych/visitors/test_to_ruby.rb b/test/psych/visitors/test_to_ruby.rb index 5b0702c..c13d980 100644 --- a/test/psych/visitors/test_to_ruby.rb +++ b/test/psych/visitors/test_to_ruby.rb @@ -1,3 +1,4 @@ +# coding: US-ASCII require 'psych/helper' module Psych @@ -5,7 +6,7 @@ module Psych class TestToRuby < TestCase def setup super - @visitor = ToRuby.new + @visitor = ToRuby.create end def test_object @@ -17,8 +18,8 @@ module Psych assert_equal 'bar', o.instance_variable_get(:@foo) end - def test_awesome - Psych.load('1900-01-01T00:00:00+00:00') + def test_tz_00_00_loads_without_error + assert Psych.load('1900-01-01T00:00:00+00:00') end def test_legacy_struct @@ -87,7 +88,7 @@ description: end def test_exception - exc = Exception.new 'hello' + exc = ::Exception.new 'hello' mapping = Nodes::Mapping.new nil, '!ruby/exception' mapping.children << Nodes::Scalar.new('message') diff --git a/test/psych/visitors/test_yaml_tree.rb b/test/psych/visitors/test_yaml_tree.rb index df77563..40702bc 100644 --- a/test/psych/visitors/test_yaml_tree.rb +++ b/test/psych/visitors/test_yaml_tree.rb @@ -5,7 +5,25 @@ module Psych class TestYAMLTree < TestCase def setup super - @v = Visitors::YAMLTree.new + @v = Visitors::YAMLTree.create + end + + def test_tree_can_be_called_twice + @v.start + @v << Object.new + t = @v.tree + assert_equal t, @v.tree + end + + def test_yaml_tree_can_take_an_emitter + io = StringIO.new + e = Psych::Emitter.new io + v = Visitors::YAMLTree.create({}, e) + v.start + v << "hello world" + v.finish + + assert_match "hello world", io.string end def test_binary_formatting |