diff options
author | Junio C Hamano <junkio@cox.net> | 2007-04-21 17:38:00 -0700 |
---|---|---|
committer | Junio C Hamano <junkio@cox.net> | 2007-04-21 17:38:00 -0700 |
commit | a2d7c6c62080b542007f9787342aa1e57b95f50c (patch) | |
tree | 22348e2f38132cd45dcf74cf0c02475d95dbce5b | |
parent | afb5b6a24bd333d298d10acac731f1c127bbb82d (diff) | |
parent | 5e635e396020cc08bc21a3e67c20c5294d6d13fd (diff) | |
download | git-a2d7c6c62080b542007f9787342aa1e57b95f50c.tar.gz |
Merge branch 'jc/attr'
* 'jc/attr': (28 commits)
lockfile: record the primary process.
convert.c: restructure the attribute checking part.
Fix bogus linked-list management for user defined merge drivers.
Simplify calling of CR/LF conversion routines
Document gitattributes(5)
Update 'crlf' attribute semantics.
Documentation: support manual section (5) - file formats.
Simplify code to find recursive merge driver.
Counto-fix in merge-recursive
Fix funny types used in attribute value representation
Allow low-level driver to specify different behaviour during internal merge.
Custom low-level merge driver: change the configuration scheme.
Allow the default low-level merge driver to be configured.
Custom low-level merge driver support.
Add a demonstration/test of customized merge.
Allow specifying specialized merge-backend per path.
merge-recursive: separate out xdl_merge() interface.
Allow more than true/false to attributes.
Document git-check-attr
Change attribute negation marker from '!' to '-'.
...
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | Documentation/Makefile | 19 | ||||
-rwxr-xr-x | Documentation/cmd-list.perl | 1 | ||||
-rw-r--r-- | Documentation/config.txt | 13 | ||||
-rw-r--r-- | Documentation/git-check-attr.txt | 37 | ||||
-rw-r--r-- | Documentation/gitattributes.txt | 285 | ||||
-rw-r--r-- | Makefile | 8 | ||||
-rw-r--r-- | attr.c | 563 | ||||
-rw-r--r-- | attr.h | 34 | ||||
-rw-r--r-- | builtin-apply.c | 18 | ||||
-rw-r--r-- | builtin-check-attr.c | 59 | ||||
-rw-r--r-- | builtin.h | 1 | ||||
-rw-r--r-- | cache.h | 8 | ||||
-rw-r--r-- | convert.c | 183 | ||||
-rw-r--r-- | diff.c | 54 | ||||
-rw-r--r-- | entry.c | 8 | ||||
-rw-r--r-- | git.c | 1 | ||||
-rw-r--r-- | lockfile.c | 6 | ||||
-rw-r--r-- | merge-recursive.c | 403 | ||||
-rw-r--r-- | sha1_file.c | 7 | ||||
-rwxr-xr-x | t/t0020-crlf.sh | 96 | ||||
-rwxr-xr-x | t/t6026-merge-attr.sh | 145 |
22 files changed, 1816 insertions, 134 deletions
diff --git a/.gitignore b/.gitignore index fa7ac93594..4dc0c395fa 100644 --- a/.gitignore +++ b/.gitignore @@ -16,6 +16,7 @@ git-blame git-branch git-bundle git-cat-file +git-check-attr git-check-ref-format git-checkout git-checkout-index diff --git a/Documentation/Makefile b/Documentation/Makefile index a637d8d559..8d3617db97 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -2,9 +2,10 @@ MAN1_TXT= \ $(filter-out $(addsuffix .txt, $(ARTICLES) $(SP_ARTICLES)), \ $(wildcard git-*.txt)) \ gitk.txt +MAN5_TXT=gitattributes.txt MAN7_TXT=git.txt -DOC_HTML=$(patsubst %.txt,%.html,$(MAN1_TXT) $(MAN7_TXT)) +DOC_HTML=$(patsubst %.txt,%.html,$(MAN1_TXT) $(MAN5_TXT) $(MAN7_TXT)) ARTICLES = tutorial ARTICLES += tutorial-2 @@ -23,12 +24,14 @@ SP_ARTICLES = howto/revert-branch-rebase user-manual DOC_HTML += $(patsubst %,%.html,$(ARTICLES) $(SP_ARTICLES)) DOC_MAN1=$(patsubst %.txt,%.1,$(MAN1_TXT)) +DOC_MAN5=$(patsubst %.txt,%.5,$(MAN1_TXT)) DOC_MAN7=$(patsubst %.txt,%.7,$(MAN7_TXT)) prefix?=$(HOME) bindir?=$(prefix)/bin mandir?=$(prefix)/man man1dir=$(mandir)/man1 +man5dir=$(mandir)/man5 man7dir=$(mandir)/man7 # DESTDIR= @@ -53,15 +56,19 @@ all: html man html: $(DOC_HTML) -$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN7): asciidoc.conf +$(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7): asciidoc.conf -man: man1 man7 +man: man1 man5 man7 man1: $(DOC_MAN1) +man5: $(DOC_MAN5) man7: $(DOC_MAN7) install: man - $(INSTALL) -d -m755 $(DESTDIR)$(man1dir) $(DESTDIR)$(man7dir) + $(INSTALL) -d -m755 $(DESTDIR)$(man1dir) + $(INSTALL) -d -m755 $(DESTDIR)$(man5dir) + $(INSTALL) -d -m755 $(DESTDIR)$(man7dir) $(INSTALL) -m644 $(DOC_MAN1) $(DESTDIR)$(man1dir) + $(INSTALL) -m644 $(DOC_MAN5) $(DESTDIR)$(man5dir) $(INSTALL) -m644 $(DOC_MAN7) $(DESTDIR)$(man7dir) @@ -99,7 +106,7 @@ cmd-list.made: cmd-list.perl $(MAN1_TXT) git.7 git.html: git.txt core-intro.txt clean: - rm -f *.xml *.xml+ *.html *.html+ *.1 *.7 howto-index.txt howto/*.html doc.dep + rm -f *.xml *.xml+ *.html *.html+ *.1 *.5 *.7 howto-index.txt howto/*.html doc.dep rm -f $(cmds_txt) *.made %.html : %.txt @@ -109,7 +116,7 @@ clean: sed -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' >$@+ mv $@+ $@ -%.1 %.7 : %.xml +%.1 %.5 %.7 : %.xml xmlto -m callouts.xsl man $< %.xml : %.txt diff --git a/Documentation/cmd-list.perl b/Documentation/cmd-list.perl index 0381590d38..443802a9a3 100755 --- a/Documentation/cmd-list.perl +++ b/Documentation/cmd-list.perl @@ -84,6 +84,7 @@ git-bundle mainporcelain git-cat-file plumbinginterrogators git-checkout-index plumbingmanipulators git-checkout mainporcelain +git-check-attr purehelpers git-check-ref-format purehelpers git-cherry ancillaryinterrogators git-cherry-pick mainporcelain diff --git a/Documentation/config.txt b/Documentation/config.txt index 2c0a666323..b13ff3a1bb 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -525,6 +525,19 @@ merge.verbosity:: conflicts, 2 outputs conflicts and file changes. Level 5 and above outputs debugging information. The default is level 2. +merge.<driver>.name:: + Defines a human readable name for a custom low-level + merge driver. See gitlink:gitattributes[5] for details. + +merge.<driver>.driver:: + Defines the command that implements a custom low-level + merge driver. See gitlink:gitattributes[5] for details. + +merge.<driver>.recursive:: + Names a low-level merge driver to be used when + performing an internal merge between common ancestors. + See gitlink:gitattributes[5] for details. + pack.window:: The size of the window used by gitlink:git-pack-objects[1] when no window size is given on the command line. Defaults to 10. diff --git a/Documentation/git-check-attr.txt b/Documentation/git-check-attr.txt new file mode 100644 index 0000000000..ceb51959b1 --- /dev/null +++ b/Documentation/git-check-attr.txt @@ -0,0 +1,37 @@ +git-check-attr(1) +================= + +NAME +---- +git-check-attr - Display gitattributes information. + + +SYNOPSIS +-------- +'git-check-attr' attr... [--] pathname... + +DESCRIPTION +----------- +For every pathname, this command will list if each attr is 'unspecified', +'set', or 'unset' as a gitattribute on that pathname. + +OPTIONS +------- +\--:: + Interpret all preceding arguments as attributes, and all following + arguments as path names. If not supplied, only the first argument will + be treated as an attribute. + + +Author +------ +Written by Junio C Hamano <junkio@cox.net> + +Documentation +-------------- +Documentation by James Bowes. + +GIT +--- +Part of the gitlink:git[7] suite + diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt new file mode 100644 index 0000000000..ece58abee2 --- /dev/null +++ b/Documentation/gitattributes.txt @@ -0,0 +1,285 @@ +gitattributes(5) +================ + +NAME +---- +gitattributes - defining attributes per path + +SYNOPSIS +-------- +.gitattributes + + +DESCRIPTION +----------- + +A `gitattributes` file is a simple text file that gives +`attributes` to pathnames. + +Each line in `gitattributes` file is of form: + + glob attr1 attr2 ... + +That is, a glob pattern followed by an attributes list, +separated by whitespaces. When the glob pattern matches the +path in question, the attributes listed on the line are given to +the path. + +Each attribute can be in one of these states for a given path: + +Set:: + + The path has the attribute with special value "true"; + this is specified by listing only the name of the + attribute in the attribute list. + +Unset:: + + The path has the attribute with special value "false"; + this is specified by listing the name of the attribute + prefixed with a dash `-` in the attribute list. + +Set to a value:: + + The path has the attribute with specified string value; + this is specified by listing the name of the attribute + followed by an equal sign `=` and its value in the + attribute list. + +Unspecified:: + + No glob pattern matches the path, and nothing says if + the path has or does not have the attribute. + +When more than one glob pattern matches the path, a later line +overrides an earlier line. + +When deciding what attributes are assigned to a path, git +consults `$GIT_DIR/info/attributes` file (which has the highest +precedence), `.gitattributes` file in the same directory as the +path in question, and its parent directories (the further the +directory that contains `.gitattributes` is from the path in +question, the lower its precedence). + +Sometimes you would need to override an setting of an attribute +for a path to `unspecified` state. This can be done by listing +the name of the attribute prefixed with an exclamation point `!`. + + +EFFECTS +------- + +Certain operations by git can be influenced by assigning +particular attributes to a path. Currently, three operations +are attributes-aware. + +Checking-out and checking-in +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The attribute `crlf` affects how the contents stored in the +repository are copied to the working tree files when commands +such as `git checkout` and `git merge` run. It also affects how +git stores the contents you prepare in the working tree in the +repository upon `git add` and `git commit`. + +Set:: + + Setting the `crlf` attribute on a path is meant to mark + the path as a "text" file. 'core.autocrlf' conversion + takes place without guessing the content type by + inspection. + +Unset:: + + Unsetting the `crlf` attribute on a path is meant to + mark the path as a "binary" file. The path never goes + through line endings conversion upon checkin/checkout. + +Unspecified:: + + Unspecified `crlf` attribute tells git to apply the + `core.autocrlf` conversion when the file content looks + like text. + +Set to string value "input":: + + This is similar to setting the attribute to `true`, but + also forces git to act as if `core.autocrlf` is set to + `input` for the path. + +Any other value set to `crlf` attribute is ignored and git acts +as if the attribute is left unspecified. + + +The `core.autocrlf` conversion +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If the configuration variable `core.autocrlf` is false, no +conversion is done. + +When `core.autocrlf` is true, it means that the platform wants +CRLF line endings for files in the working tree, and you want to +convert them back to the normal LF line endings when checking +in to the repository. + +When `core.autocrlf` is set to "input", line endings are +converted to LF upon checkin, but there is no conversion done +upon checkout. + + +Generating diff text +~~~~~~~~~~~~~~~~~~~~ + +The attribute `diff` affects if `git diff` generates textual +patch for the path or just says `Binary files differ`. + +Set:: + + A path to which the `diff` attribute is set is treated + as text, even when they contain byte values that + normally never appear in text files, such as NUL. + +Unset:: + + A path to which the `diff` attribute is unset will + generate `Binary files differ`. + +Unspecified:: + + A path to which the `diff` attribute is unspecified + first gets its contents inspected, and if it looks like + text, it is treated as text. Otherwise it would + generate `Binary files differ`. + +Any other value set to `diff` attribute is ignored and git acts +as if the attribute is left unspecified. + + +Performing a three-way merge +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The attribute `merge` affects how three versions of a file is +merged when a file-level merge is necessary during `git merge`, +and other programs such as `git revert` and `git cherry-pick`. + +Set:: + + Built-in 3-way merge driver is used to merge the + contents in a way similar to `merge` command of `RCS` + suite. This is suitable for ordinary text files. + +Unset:: + + Take the version from the current branch as the + tentative merge result, and declare that the merge has + conflicts. This is suitable for binary files that does + not have a well-defined merge semantics. + +Unspecified:: + + By default, this uses the same built-in 3-way merge + driver as is the case the `merge` attribute is set. + However, `merge.default` configuration variable can name + different merge driver to be used for paths to which the + `merge` attribute is unspecified. + +Any other string value:: + + 3-way merge is performed using the specified custom + merge driver. The built-in 3-way merge driver can be + explicitly specified by asking for "text" driver; the + built-in "take the current branch" driver can be + requested by "binary". + + +Defining a custom merge driver +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The definition of a merge driver is done in `gitconfig` not +`gitattributes` file, so strictly speaking this manual page is a +wrong place to talk about it. However... + +To define a custom merge driver `filfre`, add a section to your +`$GIT_DIR/config` file (or `$HOME/.gitconfig` file) like this: + +---------------------------------------------------------------- +[merge "filfre"] + name = feel-free merge driver + driver = filfre %O %A %B + recursive = binary +---------------------------------------------------------------- + +The `merge.*.name` variable gives the driver a human-readable +name. + +The `merge.*.driver` variable's value is used to construct a +command to run to merge ancestor's version (`%O`), current +version (`%A`) and the other branches' version (`%B`). These +three tokens are replaced with the names of temporary files that +hold the contents of these versions when the command line is +built. + +The merge driver is expected to leave the result of the merge in +the file named with `%A` by overwriting it, and exit with zero +status if it managed to merge them cleanly, or non-zero if there +were conflicts. + +The `merge.*.recursive` variable specifies what other merge +driver to use when the merge driver is called for an internal +merge between common ancestors, when there are more than one. +When left unspecified, the driver itself is used for both +internal merge and the final merge. + + +EXAMPLE +------- + +If you have these three `gitattributes` file: + +---------------------------------------------------------------- +(in $GIT_DIR/info/attributes) + +a* foo !bar -baz + +(in .gitattributes) +abc foo bar baz + +(in t/.gitattributes) +ab* merge=filfre +abc -foo -bar +*.c frotz +---------------------------------------------------------------- + +the attributes given to path `t/abc` are computed as follows: + +1. By examining `t/.gitattributes` (which is in the same + diretory as the path in question), git finds that the first + line matches. `merge` attribute is set. It also finds that + the second line matches, and attributes `foo` and `bar` + are unset. + +2. Then it examines `.gitattributes` (which is in the parent + directory), and finds that the first line matches, but + `t/.gitattributes` file already decided how `merge`, `foo` + and `bar` attributes should be given to this path, so it + leaves `foo` and `bar` unset. Attribute `baz` is set. + +3. Finally it examines `$GIT_DIR/info/gitattributes`. This file + is used to override the in-tree settings. The first line is + a match, and `foo` is set, `bar` is reverted to unspecified + state, and `baz` is unset. + +As the result, the attributes assignement to `t/abc` becomes: + +---------------------------------------------------------------- +foo set to true +bar unspecified +baz set to false +merge set to string value "filfre" +frotz unspecified +---------------------------------------------------------------- + + +GIT +--- +Part of the gitlink:git[7] suite @@ -283,7 +283,7 @@ LIB_H = \ diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h sideband.h \ run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \ tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h \ - utf8.h reflog-walk.h patch-ids.h decorate.h + utf8.h reflog-walk.h patch-ids.h attr.h decorate.h DIFF_OBJS = \ diff.o diff-lib.o diffcore-break.o diffcore-order.o \ @@ -305,7 +305,7 @@ LIB_OBJS = \ write_or_die.o trace.o list-objects.o grep.o match-trees.o \ alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \ color.o wt-status.o archive-zip.o archive-tar.o shallow.o utf8.o \ - convert.o decorate.o + convert.o attr.o decorate.o BUILTIN_OBJS = \ builtin-add.o \ @@ -316,6 +316,7 @@ BUILTIN_OBJS = \ builtin-branch.o \ builtin-bundle.o \ builtin-cat-file.o \ + builtin-check-attr.o \ builtin-checkout-index.o \ builtin-check-ref-format.o \ builtin-commit-tree.o \ @@ -1032,9 +1033,10 @@ dist-doc: gzip -n -9 -f $(htmldocs).tar : rm -fr .doc-tmp-dir - mkdir .doc-tmp-dir .doc-tmp-dir/man1 .doc-tmp-dir/man7 + mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7 $(MAKE) -C Documentation DESTDIR=./ \ man1dir=../.doc-tmp-dir/man1 \ + man5dir=../.doc-tmp-dir/man5 \ man7dir=../.doc-tmp-dir/man7 \ install cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar . diff --git a/attr.c b/attr.c new file mode 100644 index 0000000000..285e689e5a --- /dev/null +++ b/attr.c @@ -0,0 +1,563 @@ +#include "cache.h" +#include "attr.h" + +const char git_attr__true[] = "(builtin)true"; +const char git_attr__false[] = "\0(builtin)false"; +static const char git_attr__unknown[] = "(builtin)unknown"; +#define ATTR__TRUE git_attr__true +#define ATTR__FALSE git_attr__false +#define ATTR__UNSET NULL +#define ATTR__UNKNOWN git_attr__unknown + +/* + * The basic design decision here is that we are not going to have + * insanely large number of attributes. + * + * This is a randomly chosen prime. + */ +#define HASHSIZE 257 + +#ifndef DEBUG_ATTR +#define DEBUG_ATTR 0 +#endif + +struct git_attr { + struct git_attr *next; + unsigned h; + int attr_nr; + char name[FLEX_ARRAY]; +}; +static int attr_nr; + +static struct git_attr_check *check_all_attr; +static struct git_attr *(git_attr_hash[HASHSIZE]); + +static unsigned hash_name(const char *name, int namelen) +{ + unsigned val = 0; + unsigned char c; + + while (namelen--) { + c = *name++; + val = ((val << 7) | (val >> 22)) ^ c; + } + return val; +} + +static int invalid_attr_name(const char *name, int namelen) +{ + /* + * Attribute name cannot begin with '-' and from + * [-A-Za-z0-9_.]. We'd specifically exclude '=' for now, + * as we might later want to allow non-binary value for + * attributes, e.g. "*.svg merge=special-merge-program-for-svg" + */ + if (*name == '-') + return -1; + while (namelen--) { + char ch = *name++; + if (! (ch == '-' || ch == '.' || ch == '_' || + ('0' <= ch && ch <= '9') || + ('a' <= ch && ch <= 'z') || + ('A' <= ch && ch <= 'Z')) ) + return -1; + } + return 0; +} + +struct git_attr *git_attr(const char *name, int len) +{ + unsigned hval = hash_name(name, len); + unsigned pos = hval % HASHSIZE; + struct git_attr *a; + + for (a = git_attr_hash[pos]; a; a = a->next) { + if (a->h == hval && + !memcmp(a->name, name, len) && !a->name[len]) + return a; + } + + if (invalid_attr_name(name, len)) + return NULL; + + a = xmalloc(sizeof(*a) + len + 1); + memcpy(a->name, name, len); + a->name[len] = 0; + a->h = hval; + a->next = git_attr_hash[pos]; + a->attr_nr = attr_nr++; + git_attr_hash[pos] = a; + + check_all_attr = xrealloc(check_all_attr, + sizeof(*check_all_attr) * attr_nr); + check_all_attr[a->attr_nr].attr = a; + check_all_attr[a->attr_nr].value = ATTR__UNKNOWN; + return a; +} + +/* + * .gitattributes file is one line per record, each of which is + * + * (1) glob pattern. + * (2) whitespace + * (3) whitespace separated list of attribute names, each of which + * could be prefixed with '-' to mean "set to false", '!' to mean + * "unset". + */ + +/* What does a matched pattern decide? */ +struct attr_state { + struct git_attr *attr; + const char *setto; +}; + +struct match_attr { + union { + char *pattern; + struct git_attr *attr; + } u; + char is_macro; + unsigned num_attr; + struct attr_state state[FLEX_ARRAY]; +}; + +static const char blank[] = " \t\r\n"; + +static const char *parse_attr(const char *src, int lineno, const char *cp, + int *num_attr, struct match_attr *res) +{ + const char *ep, *equals; + int len; + + ep = cp + strcspn(cp, blank); + equals = strchr(cp, '='); + if (equals && ep < equals) + equals = NULL; + if (equals) + len = equals - cp; + else + len = ep - cp; + if (!res) { + if (*cp == '-' || *cp == '!') { + cp++; + len--; + } + if (invalid_attr_name(cp, len)) { + fprintf(stderr, + "%.*s is not a valid attribute name: %s:%d\n", + len, cp, src, lineno); + return NULL; + } + } else { + struct attr_state *e; + + e = &(res->state[*num_attr]); + if (*cp == '-' || *cp == '!') { + e->setto = (*cp == '-') ? ATTR__FALSE : ATTR__UNSET; + cp++; + len--; + } + else if (!equals) + e->setto = ATTR__TRUE; + else { + char *value; + int vallen = ep - equals; + value = xmalloc(vallen); + memcpy(value, equals+1, vallen-1); + value[vallen-1] = 0; + e->setto = value; + } + e->attr = git_attr(cp, len); + } + (*num_attr)++; + return ep + strspn(ep, blank); +} + +static struct match_attr *parse_attr_line(const char *line, const char *src, + int lineno, int macro_ok) +{ + int namelen; + int num_attr; + const char *cp, *name; + struct match_attr *res = NULL; + int pass; + int is_macro; + + cp = line + strspn(line, blank); + if (!*cp || *cp == '#') + return NULL; + name = cp; + namelen = strcspn(name, blank); + if (strlen(ATTRIBUTE_MACRO_PREFIX) < namelen && + !prefixcmp(name, ATTRIBUTE_MACRO_PREFIX)) { + if (!macro_ok) { + fprintf(stderr, "%s not allowed: %s:%d\n", + name, src, lineno); + return NULL; + } + is_macro = 1; + name += strlen(ATTRIBUTE_MACRO_PREFIX); + name += strspn(name, blank); + namelen = strcspn(name, blank); + if (invalid_attr_name(name, namelen)) { + fprintf(stderr, + "%.*s is not a valid attribute name: %s:%d\n", + namelen, name, src, lineno); + return NULL; + } + } + else + is_macro = 0; + + for (pass = 0; pass < 2; pass++) { + /* pass 0 counts and allocates, pass 1 fills */ + num_attr = 0; + cp = name + namelen; + cp = cp + strspn(cp, blank); + while (*cp) + cp = parse_attr(src, lineno, cp, &num_attr, res); + if (pass) + break; + res = xcalloc(1, + sizeof(*res) + + sizeof(struct attr_state) * num_attr + + (is_macro ? 0 : namelen + 1)); + if (is_macro) + res->u.attr = git_attr(name, namelen); + else { + res->u.pattern = (char*)&(res->state[num_attr]); + memcpy(res->u.pattern, name, namelen); + res->u.pattern[namelen] = 0; + } + res->is_macro = is_macro; + res->num_attr = num_attr; + } + return res; +} + +/* + * Like info/exclude and .gitignore, the attribute information can + * come from many places. + * + * (1) .gitattribute file of the same directory; + * (2) .gitattribute file of the parent directory if (1) does not have + * any match; this goes recursively upwards, just like .gitignore. + * (3) $GIT_DIR/info/attributes, which overrides both of the above. + * + * In the same file, later entries override the earlier match, so in the + * global list, we would have entries from info/attributes the earliest + * (reading the file from top to bottom), .gitattribute of the root + * directory (again, reading the file from top to bottom) down to the + * current directory, and then scan the list backwards to find the first match. + * This is exactly the same as what excluded() does in dir.c to deal with + * .gitignore + */ + +static struct attr_stack { + struct attr_stack *prev; + char *origin; + unsigned num_matches; + struct match_attr **attrs; +} *attr_stack; + +static void free_attr_elem(struct attr_stack *e) +{ + int i; + free(e->origin); + for (i = 0; i < e->num_matches; i++) { + struct match_attr *a = e->attrs[i]; + int j; + for (j = 0; j < a->num_attr; j++) { + const char *setto = a->state[j].setto; + if (setto == ATTR__TRUE || + setto == ATTR__FALSE || + setto == ATTR__UNSET || + setto == ATTR__UNKNOWN) + ; + else + free((char*) setto); + } + free(a); + } + free(e); +} + +static const char *builtin_attr[] = { + "[attr]binary -diff -crlf", + NULL, +}; + +static struct attr_stack *read_attr_from_array(const char **list) +{ + struct attr_stack *res; + const char *line; + int lineno = 0; + + res = xcalloc(1, sizeof(*res)); + while ((line = *(list++)) != NULL) { + struct match_attr *a; + + a = parse_attr_line(line, "[builtin]", ++lineno, 1); + if (!a) + continue; + res->attrs = xrealloc(res->attrs, res->num_matches + 1); + res->attrs[res->num_matches++] = a; + } + return res; +} + +static struct attr_stack *read_attr_from_file(const char *path, int macro_ok) +{ + FILE *fp; + struct attr_stack *res; + char buf[2048]; + int lineno = 0; + + res = xcalloc(1, sizeof(*res)); + fp = fopen(path, "r"); + if (!fp) + return res; + + while (fgets(buf, sizeof(buf), fp)) { + struct match_attr *a; + + a = parse_attr_line(buf, path, ++lineno, macro_ok); + if (!a) + continue; + res->attrs = xrealloc(res->attrs, res->num_matches + 1); + res->attrs[res->num_matches++] = a; + } + fclose(fp); + return res; +} + +#if DEBUG_ATTR +static void debug_info(const char *what, struct attr_stack *elem) +{ + fprintf(stderr, "%s: %s\n", what, elem->origin ? elem->origin : "()"); +} +static void debug_set(const char *what, const char *match, struct git_attr *attr, void *v) +{ + const char *value = v; + + if (ATTR_TRUE(value)) + value = "set"; + else if (ATTR_FALSE(value)) + value = "unset"; + else if (ATTR_UNSET(value)) + value = "unspecified"; + + fprintf(stderr, "%s: %s => %s (%s)\n", + what, attr->name, (char *) value, match); +} +#define debug_push(a) debug_info("push", (a)) +#define debug_pop(a) debug_info("pop", (a)) +#else +#define debug_push(a) do { ; } while (0) +#define debug_pop(a) do { ; } while (0) +#define debug_set(a,b,c,d) do { ; } while (0) +#endif + +static void bootstrap_attr_stack(void) +{ + if (!attr_stack) { + struct attr_stack *elem; + + elem = read_attr_from_array(builtin_attr); + elem->origin = NULL; + elem->prev = attr_stack; + attr_stack = elem; + + elem = read_attr_from_file(GITATTRIBUTES_FILE, 1); + elem->origin = strdup(""); + elem->prev = attr_stack; + attr_stack = elem; + debug_push(elem); + + elem = read_attr_from_file(git_path(INFOATTRIBUTES_FILE), 1); + elem->origin = NULL; + elem->prev = attr_stack; + attr_stack = elem; + } +} + +static void prepare_attr_stack(const char *path, int dirlen) +{ + struct attr_stack *elem, *info; + int len; + char pathbuf[PATH_MAX]; + + /* + * At the bottom of the attribute stack is the built-in + * set of attribute definitions. Then, contents from + * .gitattribute files from directories closer to the + * root to the ones in deeper directories are pushed + * to the stack. Finally, at the very top of the stack + * we always keep the contents of $GIT_DIR/info/attributes. + * + * When checking, we use entries from near the top of the + * stack, preferring $GIT_DIR/info/attributes, then + * .gitattributes in deeper directories to shallower ones, + * and finally use the built-in set as the default. + */ + if (!attr_stack) + bootstrap_attr_stack(); + + /* + * Pop the "info" one that is always at the top of the stack. + */ + info = attr_stack; + attr_stack = info->prev; + + /* + * Pop the ones from directories that are not the prefix of + * the path we are checking. + */ + while (attr_stack && attr_stack->origin) { + int namelen = strlen(attr_stack->origin); + + elem = attr_stack; + if (namelen <= dirlen && + !strncmp(elem->origin, path, namelen)) + break; + + debug_pop(elem); + attr_stack = elem->prev; + free_attr_elem(elem); + } + + /* + * Read from parent directories and push them down + */ + while (1) { + char *cp; + + len = strlen(attr_stack->origin); + if (dirlen <= len) + break; + memcpy(pathbuf, path, dirlen); + memcpy(pathbuf + dirlen, "/", 2); + cp = strchr(pathbuf + len + 1, '/'); + strcpy(cp + 1, GITATTRIBUTES_FILE); + elem = read_attr_from_file(pathbuf, 0); + *cp = '\0'; + elem->origin = strdup(pathbuf); + elem->prev = attr_stack; + attr_stack = elem; + debug_push(elem); + } + + /* + * Finally push the "info" one at the top of the stack. + */ + info->prev = attr_stack; + attr_stack = info; +} + +static int path_matches(const char *pathname, int pathlen, + const char *pattern, + const char *base, int baselen) +{ + if (!strchr(pattern, '/')) { + /* match basename */ + const char *basename = strrchr(pathname, '/'); + basename = basename ? basename + 1 : pathname; + return (fnmatch(pattern, basename, 0) == 0); + } + /* + * match with FNM_PATHNAME; the pattern has base implicitly + * in front of it. + */ + if (*pattern == '/') + pattern++; + if (pathlen < baselen || + (baselen && pathname[baselen - 1] != '/') || + strncmp(pathname, base, baselen)) + return 0; + return fnmatch(pattern, pathname + baselen, FNM_PATHNAME) == 0; +} + +static int fill_one(const char *what, struct match_attr *a, int rem) +{ + struct git_attr_check *check = check_all_attr; + int i; + + for (i = 0; 0 < rem && i < a->num_attr; i++) { + struct git_attr *attr = a->state[i].attr; + const char **n = &(check[attr->attr_nr].value); + const char *v = a->state[i].setto; + + if (*n == ATTR__UNKNOWN) { + debug_set(what, a->u.pattern, attr, v); + *n = v; + rem--; + } + } + return rem; +} + +static int fill(const char *path, int pathlen, struct attr_stack *stk, int rem) +{ + int i; + const char *base = stk->origin ? stk->origin : ""; + + for (i = stk->num_matches - 1; 0 < rem && 0 <= i; i--) { + struct match_attr *a = stk->attrs[i]; + if (a->is_macro) + continue; + if (path_matches(path, pathlen, + a->u.pattern, base, strlen(base))) + rem = fill_one("fill", a, rem); + } + return rem; +} + +static int macroexpand(struct attr_stack *stk, int rem) +{ + int i; + struct git_attr_check *check = check_all_attr; + + for (i = stk->num_matches - 1; 0 < rem && 0 <= i; i--) { + struct match_attr *a = stk->attrs[i]; + if (!a->is_macro) + continue; + if (check[a->u.attr->attr_nr].value != ATTR__TRUE) + continue; + rem = fill_one("expand", a, rem); + } + return rem; +} + +int git_checkattr(const char *path, int num, struct git_attr_check *check) +{ + struct attr_stack *stk; + const char *cp; + int dirlen, pathlen, i, rem; + + bootstrap_attr_stack(); + for (i = 0; i < attr_nr; i++) + check_all_attr[i].value = ATTR__UNKNOWN; + + pathlen = strlen(path); + cp = strrchr(path, '/'); + if (!cp) + dirlen = 0; + else + dirlen = cp - path; + prepare_attr_stack(path, dirlen); + rem = attr_nr; + for (stk = attr_stack; 0 < rem && stk; stk = stk->prev) + rem = fill(path, pathlen, stk, rem); + + for (stk = attr_stack; 0 < rem && stk; stk = stk->prev) + rem = macroexpand(stk, rem); + + for (i = 0; i < num; i++) { + const char *value = check_all_attr[check[i].attr->attr_nr].value; + if (value == ATTR__UNKNOWN) + value = ATTR__UNSET; + check[i].value = value; + } + + return 0; +} diff --git a/attr.h b/attr.h new file mode 100644 index 0000000000..f1c2038b09 --- /dev/null +++ b/attr.h @@ -0,0 +1,34 @@ +#ifndef ATTR_H +#define ATTR_H + +/* An attribute is a pointer to this opaque structure */ +struct git_attr; + +/* + * Given a string, return the gitattribute object that + * corresponds to it. + */ +struct git_attr *git_attr(const char *, int); + +/* Internal use */ +extern const char git_attr__true[]; +extern const char git_attr__false[]; + +/* For public to check git_attr_check results */ +#define ATTR_TRUE(v) ((v) == git_attr__true) +#define ATTR_FALSE(v) ((v) == git_attr__false) +#define ATTR_UNSET(v) ((v) == NULL) + +/* + * Send one or more git_attr_check to git_checkattr(), and + * each 'value' member tells what its value is. + * Unset one is returned as NULL. + */ +struct git_attr_check { + struct git_attr *attr; + const char *value; +}; + +int git_checkattr(const char *path, int, struct git_attr_check *); + +#endif /* ATTR_H */ diff --git a/builtin-apply.c b/builtin-apply.c index 94311e7af4..f94d0dbf48 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -1475,8 +1475,8 @@ static int read_old_data(struct stat *st, const char *path, char **buf_p, unsign } close(fd); nsize = got; - nbuf = buf; - if (convert_to_git(path, &nbuf, &nsize)) { + nbuf = convert_to_git(path, buf, &nsize); + if (nbuf) { free(buf); *buf_p = nbuf; *alloc_p = nsize; @@ -2355,9 +2355,8 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned static int try_create_file(const char *path, unsigned int mode, const char *buf, unsigned long size) { - int fd, converted; + int fd; char *nbuf; - unsigned long nsize; if (has_symlinks && S_ISLNK(mode)) /* Although buf:size is counted string, it also is NUL @@ -2369,13 +2368,10 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf, if (fd < 0) return -1; - nsize = size; - nbuf = (char *) buf; - converted = convert_to_working_tree(path, &nbuf, &nsize); - if (converted) { + nbuf = convert_to_working_tree(path, buf, &size); + if (nbuf) buf = nbuf; - size = nsize; - } + while (size) { int written = xwrite(fd, buf, size); if (written < 0) @@ -2387,7 +2383,7 @@ static int try_create_file(const char *path, unsigned int mode, const char *buf, } if (close(fd) < 0) die("closing file %s: %s", path, strerror(errno)); - if (converted) + if (nbuf) free(nbuf); return 0; } diff --git a/builtin-check-attr.c b/builtin-check-attr.c new file mode 100644 index 0000000000..9d77f76ff1 --- /dev/null +++ b/builtin-check-attr.c @@ -0,0 +1,59 @@ +#include "builtin.h" +#include "attr.h" +#include "quote.h" + +static const char check_attr_usage[] = +"git-check-attr attr... [--] pathname..."; + +int cmd_check_attr(int argc, const char **argv, const char *prefix) +{ + struct git_attr_check *check; + int cnt, i, doubledash; + + doubledash = -1; + for (i = 1; doubledash < 0 && i < argc; i++) { + if (!strcmp(argv[i], "--")) + doubledash = i; + } + + /* If there is no double dash, we handle only one attribute */ + if (doubledash < 0) { + cnt = 1; + doubledash = 1; + } else + cnt = doubledash - 1; + doubledash++; + + if (cnt <= 0 || argc < doubledash) + usage(check_attr_usage); + check = xcalloc(cnt, sizeof(*check)); + for (i = 0; i < cnt; i++) { + const char *name; + struct git_attr *a; + name = argv[i + 1]; + a = git_attr(name, strlen(name)); + if (!a) + return error("%s: not a valid attribute name", name); + check[i].attr = a; + } + + for (i = doubledash; i < argc; i++) { + int j; + if (git_checkattr(argv[i], cnt, check)) + die("git_checkattr died"); + for (j = 0; j < cnt; j++) { + const char *value = check[j].value; + + if (ATTR_TRUE(value)) + value = "set"; + else if (ATTR_FALSE(value)) + value = "unset"; + else if (ATTR_UNSET(value)) + value = "unspecified"; + + write_name_quoted("", 0, argv[i], 1, stdout); + printf(": %s: %s\n", argv[j+1], value); + } + } + return 0; +} @@ -22,6 +22,7 @@ extern int cmd_branch(int argc, const char **argv, const char *prefix); extern int cmd_bundle(int argc, const char **argv, const char *prefix); extern int cmd_cat_file(int argc, const char **argv, const char *prefix); extern int cmd_checkout_index(int argc, const char **argv, const char *prefix); +extern int cmd_check_attr(int argc, const char **argv, const char *prefix); extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix); extern int cmd_cherry(int argc, const char **argv, const char *prefix); extern int cmd_cherry_pick(int argc, const char **argv, const char *prefix); @@ -169,6 +169,9 @@ enum object_type { #define CONFIG_ENVIRONMENT "GIT_CONFIG" #define CONFIG_LOCAL_ENVIRONMENT "GIT_CONFIG_LOCAL" #define EXEC_PATH_ENVIRONMENT "GIT_EXEC_PATH" +#define GITATTRIBUTES_FILE ".gitattributes" +#define INFOATTRIBUTES_FILE "info/attributes" +#define ATTRIBUTE_MACRO_PREFIX "[attr]" extern int is_bare_repository_cfg; extern int is_bare_repository(void); @@ -224,6 +227,7 @@ extern int refresh_cache(unsigned int flags); struct lock_file { struct lock_file *next; + pid_t owner; char on_list; char filename[PATH_MAX]; }; @@ -512,8 +516,8 @@ extern void trace_printf(const char *format, ...); extern void trace_argv_printf(const char **argv, int count, const char *format, ...); /* convert.c */ -extern int convert_to_git(const char *path, char **bufp, unsigned long *sizep); -extern int convert_to_working_tree(const char *path, char **bufp, unsigned long *sizep); +extern char *convert_to_git(const char *path, const char *src, unsigned long *sizep); +extern char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep); /* match-trees.c */ void shift_tree(const unsigned char *, const unsigned char *, unsigned char *, int); @@ -1,4 +1,6 @@ #include "cache.h" +#include "attr.h" + /* * convert.c - convert a file when checking it out and checking it in. * @@ -8,6 +10,11 @@ * translation when the "auto_crlf" option is set. */ +#define CRLF_GUESS (-1) +#define CRLF_BINARY 0 +#define CRLF_TEXT 1 +#define CRLF_INPUT 2 + struct text_stat { /* CR, LF and CRLF counts */ unsigned cr, lf, crlf; @@ -72,115 +79,171 @@ static int is_binary(unsigned long size, struct text_stat *stats) return 0; } -int convert_to_git(const char *path, char **bufp, unsigned long *sizep) +static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep, int action) { - char *buffer, *nbuf; + char *buffer, *dst; unsigned long size, nsize; struct text_stat stats; - /* - * FIXME! Other pluggable conversions should go here, - * based on filename patterns. Right now we just do the - * stupid auto-CRLF one. - */ - if (!auto_crlf) - return 0; + if ((action == CRLF_BINARY) || (action == CRLF_GUESS && !auto_crlf)) + return NULL; size = *sizep; if (!size) - return 0; - buffer = *bufp; + return NULL; - gather_stats(buffer, size, &stats); + gather_stats(src, size, &stats); /* No CR? Nothing to convert, regardless. */ if (!stats.cr) - return 0; - - /* - * We're currently not going to even try to convert stuff - * that has bare CR characters. Does anybody do that crazy - * stuff? - */ - if (stats.cr != stats.crlf) - return 0; - - /* - * And add some heuristics for binary vs text, of course... - */ - if (is_binary(size, &stats)) - return 0; + return NULL; + + if (action == CRLF_GUESS) { + /* + * We're currently not going to even try to convert stuff + * that has bare CR characters. Does anybody do that crazy + * stuff? + */ + if (stats.cr != stats.crlf) + return NULL; + + /* + * And add some heuristics for binary vs text, of course... + */ + if (is_binary(size, &stats)) + return NULL; + } /* * Ok, allocate a new buffer, fill it in, and return true * to let the caller know that we switched buffers on it. */ nsize = size - stats.crlf; - nbuf = xmalloc(nsize); - *bufp = nbuf; + buffer = xmalloc(nsize); *sizep = nsize; - do { - unsigned char c = *buffer++; - if (c != '\r') - *nbuf++ = c; - } while (--size); - return 1; + dst = buffer; + if (action == CRLF_GUESS) { + /* + * If we guessed, we already know we rejected a file with + * lone CR, and we can strip a CR without looking at what + * follow it. + */ + do { + unsigned char c = *src++; + if (c != '\r') + *dst++ = c; + } while (--size); + } else { + do { + unsigned char c = *src++; + if (! (c == '\r' && (1 < size && *buffer == '\n'))) + *dst++ = c; + } while (--size); + } + + return buffer; } -int convert_to_working_tree(const char *path, char **bufp, unsigned long *sizep) +static char *crlf_to_worktree(const char *path, const char *src, unsigned long *sizep, int action) { - char *buffer, *nbuf; + char *buffer, *dst; unsigned long size, nsize; struct text_stat stats; unsigned char last; - /* - * FIXME! Other pluggable conversions should go here, - * based on filename patterns. Right now we just do the - * stupid auto-CRLF one. - */ - if (auto_crlf <= 0) - return 0; + if ((action == CRLF_BINARY) || (action == CRLF_INPUT) || + (action == CRLF_GUESS && auto_crlf <= 0)) + return NULL; size = *sizep; if (!size) - return 0; - buffer = *bufp; + return NULL; - gather_stats(buffer, size, &stats); + gather_stats(src, size, &stats); /* No LF? Nothing to convert, regardless. */ if (!stats.lf) - return 0; + return NULL; /* Was it already in CRLF format? */ if (stats.lf == stats.crlf) - return 0; + return NULL; - /* If we have any bare CR characters, we're not going to touch it */ - if (stats.cr != stats.crlf) - return 0; + if (action == CRLF_GUESS) { + /* If we have any bare CR characters, we're not going to touch it */ + if (stats.cr != stats.crlf) + return NULL; - if (is_binary(size, &stats)) - return 0; + if (is_binary(size, &stats)) + return NULL; + } /* * Ok, allocate a new buffer, fill it in, and return true * to let the caller know that we switched buffers on it. */ nsize = size + stats.lf - stats.crlf; - nbuf = xmalloc(nsize); - *bufp = nbuf; + buffer = xmalloc(nsize); *sizep = nsize; last = 0; + + dst = buffer; do { - unsigned char c = *buffer++; + unsigned char c = *src++; if (c == '\n' && last != '\r') - *nbuf++ = '\r'; - *nbuf++ = c; + *dst++ = '\r'; + *dst++ = c; last = c; } while (--size); - return 1; + return buffer; +} + +static void setup_convert_check(struct git_attr_check *check) +{ + static struct git_attr *attr_crlf; + + if (!attr_crlf) + attr_crlf = git_attr("crlf", 4); + check->attr = attr_crlf; +} + +static int git_path_check_crlf(const char *path, struct git_attr_check *check) +{ + const char *value = check->value; + + if (ATTR_TRUE(value)) + return CRLF_TEXT; + else if (ATTR_FALSE(value)) + return CRLF_BINARY; + else if (ATTR_UNSET(value)) + ; + else if (!strcmp(value, "input")) + return CRLF_INPUT; + return CRLF_GUESS; +} + +char *convert_to_git(const char *path, const char *src, unsigned long *sizep) +{ + struct git_attr_check check[1]; + int crlf = CRLF_GUESS; + + setup_convert_check(check); + if (!git_checkattr(path, 1, check)) { + crlf = git_path_check_crlf(path, check); + } + return crlf_to_git(path, src, sizep, crlf); +} + +char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep) +{ + struct git_attr_check check[1]; + int crlf = CRLF_GUESS; + + setup_convert_check(check); + if (!git_checkattr(path, 1, check)) { + crlf = git_path_check_crlf(path, check); + } + return crlf_to_worktree(path, src, sizep, crlf); } @@ -8,6 +8,7 @@ #include "delta.h" #include "xdiff-interface.h" #include "color.h" +#include "attr.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 @@ -1051,13 +1052,44 @@ static void emit_binary_diff(mmfile_t *one, mmfile_t *two) emit_binary_diff_body(two, one); } +static void setup_diff_attr_check(struct git_attr_check *check) +{ + static struct git_attr *attr_diff; + + if (!attr_diff) + attr_diff = git_attr("diff", 4); + check->attr = attr_diff; +} + #define FIRST_FEW_BYTES 8000 -static int mmfile_is_binary(mmfile_t *mf) +static int file_is_binary(struct diff_filespec *one) { - long sz = mf->size; + unsigned long sz; + struct git_attr_check attr_diff_check; + + setup_diff_attr_check(&attr_diff_check); + if (!git_checkattr(one->path, 1, &attr_diff_check)) { + const char *value = attr_diff_check.value; + if (ATTR_TRUE(value)) + return 0; + else if (ATTR_FALSE(value)) + return 1; + else if (ATTR_UNSET(value)) + ; + else + die("unknown value %s given to 'diff' attribute", + value); + } + + if (!one->data) { + if (!DIFF_FILE_VALID(one)) + return 0; + diff_populate_filespec(one, 0); + } + sz = one->size; if (FIRST_FEW_BYTES < sz) sz = FIRST_FEW_BYTES; - return !!memchr(mf->ptr, 0, sz); + return !!memchr(one->data, 0, sz); } static void builtin_diff(const char *name_a, @@ -1114,7 +1146,7 @@ static void builtin_diff(const char *name_a, if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); - if (!o->text && (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2))) { + if (!o->text && (file_is_binary(one) || file_is_binary(two))) { /* Quite common confusing case */ if (mf1.size == mf2.size && !memcmp(mf1.ptr, mf2.ptr, mf1.size)) @@ -1190,7 +1222,7 @@ static void builtin_diffstat(const char *name_a, const char *name_b, if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); - if (mmfile_is_binary(&mf1) || mmfile_is_binary(&mf2)) { + if (file_is_binary(one) || file_is_binary(two)) { data->is_binary = 1; data->added = mf2.size; data->deleted = mf1.size; @@ -1228,7 +1260,7 @@ static void builtin_checkdiff(const char *name_a, const char *name_b, if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); - if (mmfile_is_binary(&mf2)) + if (file_is_binary(two)) return; else { /* Crazy xdl interfaces.. */ @@ -1481,9 +1513,9 @@ int diff_populate_filespec(struct diff_filespec *s, int size_only) /* * Convert from working tree format to canonical git format */ - buf = s->data; size = s->size; - if (convert_to_git(s->path, &buf, &size)) { + buf = convert_to_git(s->path, s->data, &size); + if (buf) { munmap(s->data, s->size); s->should_munmap = 0; s->data = buf; @@ -1825,8 +1857,8 @@ static void run_diff(struct diff_filepair *p, struct diff_options *o) if (o->binary) { mmfile_t mf; - if ((!fill_mmfile(&mf, one) && mmfile_is_binary(&mf)) || - (!fill_mmfile(&mf, two) && mmfile_is_binary(&mf))) + if ((!fill_mmfile(&mf, one) && file_is_binary(one)) || + (!fill_mmfile(&mf, two) && file_is_binary(two))) abbrev = 40; } len += snprintf(msg + len, sizeof(msg) - len, @@ -2721,7 +2753,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) return error("unable to read files to diff"); /* Maybe hash p->two? into the patch id? */ - if (mmfile_is_binary(&mf2)) + if (file_is_binary(p->two)) continue; len1 = remove_space(p->one->path, strlen(p->one->path)); @@ -82,7 +82,7 @@ static int write_entry(struct cache_entry *ce, char *path, struct checkout *stat switch (ntohl(ce->ce_mode) & S_IFMT) { char *buf, *new; - unsigned long size, nsize; + unsigned long size; case S_IFREG: new = read_blob_entry(ce, path, &size); @@ -103,12 +103,10 @@ static int write_entry(struct cache_entry *ce, char *path, struct checkout *stat /* * Convert from git internal format to working tree format */ - buf = new; - nsize = size; - if (convert_to_working_tree(ce->name, &buf, &nsize)) { + buf = convert_to_working_tree(ce->name, new, &size); + if (buf) { free(new); new = buf; - size = nsize; } wrote = write_in_full(fd, new, size); @@ -234,6 +234,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "cat-file", cmd_cat_file, RUN_SETUP }, { "checkout-index", cmd_checkout_index, RUN_SETUP }, { "check-ref-format", cmd_check_ref_format }, + { "check-attr", cmd_check_attr, RUN_SETUP | NOT_BARE }, { "cherry", cmd_cherry, RUN_SETUP }, { "cherry-pick", cmd_cherry_pick, RUN_SETUP | NOT_BARE }, { "commit-tree", cmd_commit_tree, RUN_SETUP }, diff --git a/lockfile.c b/lockfile.c index bed6b21daf..23db35aff2 100644 --- a/lockfile.c +++ b/lockfile.c @@ -8,8 +8,11 @@ static const char *alternate_index_output; static void remove_lock_file(void) { + pid_t me = getpid(); + while (lock_file_list) { - if (lock_file_list->filename[0]) + if (lock_file_list->owner == me && + lock_file_list->filename[0]) unlink(lock_file_list->filename); lock_file_list = lock_file_list->next; } @@ -28,6 +31,7 @@ static int lock_file(struct lock_file *lk, const char *path) sprintf(lk->filename, "%s.lock", path); fd = open(lk->filename, O_RDWR | O_CREAT | O_EXCL, 0666); if (0 <= fd) { + lk->owner = getpid(); if (!lk->on_list) { lk->next = lock_file_list; lock_file_list = lk; diff --git a/merge-recursive.c b/merge-recursive.c index 31e66e5ca3..403a4c8bca 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -15,6 +15,8 @@ #include "unpack-trees.h" #include "path-list.h" #include "xdiff-interface.h" +#include "interpolate.h" +#include "attr.h" static int subtree_merge; @@ -645,6 +647,384 @@ static void fill_mm(const unsigned char *sha1, mmfile_t *mm) mm->size = size; } +/* + * Customizable low-level merge drivers support. + */ + +struct ll_merge_driver; +typedef int (*ll_merge_fn)(const struct ll_merge_driver *, + const char *path, + mmfile_t *orig, + mmfile_t *src1, const char *name1, + mmfile_t *src2, const char *name2, + mmbuffer_t *result); + +struct ll_merge_driver { + const char *name; + const char *description; + ll_merge_fn fn; + const char *recursive; + struct ll_merge_driver *next; + char *cmdline; +}; + +/* + * Built-in low-levels + */ +static int ll_xdl_merge(const struct ll_merge_driver *drv_unused, + const char *path_unused, + mmfile_t *orig, + mmfile_t *src1, const char *name1, + mmfile_t *src2, const char *name2, + mmbuffer_t *result) +{ + xpparam_t xpp; + + memset(&xpp, 0, sizeof(xpp)); + return xdl_merge(orig, + src1, name1, + src2, name2, + &xpp, XDL_MERGE_ZEALOUS, + result); +} + +static int ll_union_merge(const struct ll_merge_driver *drv_unused, + const char *path_unused, + mmfile_t *orig, + mmfile_t *src1, const char *name1, + mmfile_t *src2, const char *name2, + mmbuffer_t *result) +{ + char *src, *dst; + long size; + const int marker_size = 7; + + int status = ll_xdl_merge(drv_unused, path_unused, + orig, src1, NULL, src2, NULL, result); + if (status <= 0) + return status; + size = result->size; + src = dst = result->ptr; + while (size) { + char ch; + if ((marker_size < size) && + (*src == '<' || *src == '=' || *src == '>')) { + int i; + ch = *src; + for (i = 0; i < marker_size; i++) + if (src[i] != ch) + goto not_a_marker; + if (src[marker_size] != '\n') + goto not_a_marker; + src += marker_size + 1; + size -= marker_size + 1; + continue; + } + not_a_marker: + do { + ch = *src++; + *dst++ = ch; + size--; + } while (ch != '\n' && size); + } + result->size = dst - result->ptr; + return 0; +} + +static int ll_binary_merge(const struct ll_merge_driver *drv_unused, + const char *path_unused, + mmfile_t *orig, + mmfile_t *src1, const char *name1, + mmfile_t *src2, const char *name2, + mmbuffer_t *result) +{ + /* + * The tentative merge result is "ours" for the final round, + * or common ancestor for an internal merge. Still return + * "conflicted merge" status. + */ + mmfile_t *stolen = index_only ? orig : src1; + + result->ptr = stolen->ptr; + result->size = stolen->size; + stolen->ptr = NULL; + return 1; +} + +#define LL_BINARY_MERGE 0 +#define LL_TEXT_MERGE 1 +#define LL_UNION_MERGE 2 +static struct ll_merge_driver ll_merge_drv[] = { + { "binary", "built-in binary merge", ll_binary_merge }, + { "text", "built-in 3-way text merge", ll_xdl_merge }, + { "union", "built-in union merge", ll_union_merge }, +}; + +static void create_temp(mmfile_t *src, char *path) +{ + int fd; + + strcpy(path, ".merge_file_XXXXXX"); + fd = mkstemp(path); + if (fd < 0) + die("unable to create temp-file"); + if (write_in_full(fd, src->ptr, src->size) != src->size) + die("unable to write temp-file"); + close(fd); +} + +/* + * User defined low-level merge driver support. + */ +static int ll_ext_merge(const struct ll_merge_driver *fn, + const char *path, + mmfile_t *orig, + mmfile_t *src1, const char *name1, + mmfile_t *src2, const char *name2, + mmbuffer_t *result) +{ + char temp[3][50]; + char cmdbuf[2048]; + struct interp table[] = { + { "%O" }, + { "%A" }, + { "%B" }, + }; + struct child_process child; + const char *args[20]; + int status, fd, i; + struct stat st; + + if (fn->cmdline == NULL) + die("custom merge driver %s lacks command line.", fn->name); + + result->ptr = NULL; + result->size = 0; + create_temp(orig, temp[0]); + create_temp(src1, temp[1]); + create_temp(src2, temp[2]); + + interp_set_entry(table, 0, temp[0]); + interp_set_entry(table, 1, temp[1]); + interp_set_entry(table, 2, temp[2]); + + output(1, "merging %s using %s", path, + fn->description ? fn->description : fn->name); + + interpolate(cmdbuf, sizeof(cmdbuf), fn->cmdline, table, 3); + + memset(&child, 0, sizeof(child)); + child.argv = args; + args[0] = "sh"; + args[1] = "-c"; + args[2] = cmdbuf; + args[3] = NULL; + + status = run_command(&child); + if (status < -ERR_RUN_COMMAND_FORK) + ; /* failure in run-command */ + else + status = -status; + fd = open(temp[1], O_RDONLY); + if (fd < 0) + goto bad; + if (fstat(fd, &st)) + goto close_bad; + result->size = st.st_size; + result->ptr = xmalloc(result->size + 1); + if (read_in_full(fd, result->ptr, result->size) != result->size) { + free(result->ptr); + result->ptr = NULL; + result->size = 0; + } + close_bad: + close(fd); + bad: + for (i = 0; i < 3; i++) + unlink(temp[i]); + return status; +} + +/* + * merge.default and merge.driver configuration items + */ +static struct ll_merge_driver *ll_user_merge, **ll_user_merge_tail; +static const char *default_ll_merge; + +static int read_merge_config(const char *var, const char *value) +{ + struct ll_merge_driver *fn; + const char *ep, *name; + int namelen; + + if (!strcmp(var, "merge.default")) { + if (value) + default_ll_merge = strdup(value); + return 0; + } + + /* + * We are not interested in anything but "merge.<name>.variable"; + * especially, we do not want to look at variables such as + * "merge.summary", "merge.tool", and "merge.verbosity". + */ + if (prefixcmp(var, "merge.") || (ep = strrchr(var, '.')) == var + 5) + return 0; + + /* + * Find existing one as we might be processing merge.<name>.var2 + * after seeing merge.<name>.var1. + */ + name = var + 6; + namelen = ep - name; + for (fn = ll_user_merge; fn; fn = fn->next) + if (!strncmp(fn->name, name, namelen) && !fn->name[namelen]) + break; + if (!fn) { + char *namebuf; + fn = xcalloc(1, sizeof(struct ll_merge_driver)); + namebuf = xmalloc(namelen + 1); + memcpy(namebuf, name, namelen); + namebuf[namelen] = 0; + fn->name = namebuf; + fn->fn = ll_ext_merge; + fn->next = NULL; + *ll_user_merge_tail = fn; + ll_user_merge_tail = &(fn->next); + } + + ep++; + + if (!strcmp("name", ep)) { + if (!value) + return error("%s: lacks value", var); + fn->description = strdup(value); + return 0; + } + + if (!strcmp("driver", ep)) { + if (!value) + return error("%s: lacks value", var); + /* + * merge.<name>.driver specifies the command line: + * + * command-line + * + * The command-line will be interpolated with the following + * tokens and is given to the shell: + * + * %O - temporary file name for the merge base. + * %A - temporary file name for our version. + * %B - temporary file name for the other branches' version. + * + * The external merge driver should write the results in the + * file named by %A, and signal that it has done with zero exit + * status. + */ + fn->cmdline = strdup(value); + return 0; + } + + if (!strcmp("recursive", ep)) { + if (!value) + return error("%s: lacks value", var); + fn->recursive = strdup(value); + return 0; + } + + return 0; +} + +static void initialize_ll_merge(void) +{ + if (ll_user_merge_tail) + return; + ll_user_merge_tail = &ll_user_merge; + git_config(read_merge_config); +} + +static const struct ll_merge_driver *find_ll_merge_driver(const char *merge_attr) +{ + struct ll_merge_driver *fn; + const char *name; + int i; + + initialize_ll_merge(); + + if (ATTR_TRUE(merge_attr)) + return &ll_merge_drv[LL_TEXT_MERGE]; + else if (ATTR_FALSE(merge_attr)) + return &ll_merge_drv[LL_BINARY_MERGE]; + else if (ATTR_UNSET(merge_attr)) { + if (!default_ll_merge) + return &ll_merge_drv[LL_TEXT_MERGE]; + else + name = default_ll_merge; + } + else + name = merge_attr; + + for (fn = ll_user_merge; fn; fn = fn->next) + if (!strcmp(fn->name, name)) + return fn; + + for (i = 0; i < ARRAY_SIZE(ll_merge_drv); i++) + if (!strcmp(ll_merge_drv[i].name, name)) + return &ll_merge_drv[i]; + + /* default to the 3-way */ + return &ll_merge_drv[LL_TEXT_MERGE]; +} + +static const char *git_path_check_merge(const char *path) +{ + static struct git_attr_check attr_merge_check; + + if (!attr_merge_check.attr) + attr_merge_check.attr = git_attr("merge", 5); + + if (git_checkattr(path, 1, &attr_merge_check)) + return NULL; + return attr_merge_check.value; +} + +static int ll_merge(mmbuffer_t *result_buf, + struct diff_filespec *o, + struct diff_filespec *a, + struct diff_filespec *b, + const char *branch1, + const char *branch2) +{ + mmfile_t orig, src1, src2; + char *name1, *name2; + int merge_status; + const char *ll_driver_name; + const struct ll_merge_driver *driver; + + name1 = xstrdup(mkpath("%s:%s", branch1, a->path)); + name2 = xstrdup(mkpath("%s:%s", branch2, b->path)); + + fill_mm(o->sha1, &orig); + fill_mm(a->sha1, &src1); + fill_mm(b->sha1, &src2); + + ll_driver_name = git_path_check_merge(a->path); + driver = find_ll_merge_driver(ll_driver_name); + + if (index_only && driver->recursive) + driver = find_ll_merge_driver(driver->recursive); + merge_status = driver->fn(driver, a->path, + &orig, &src1, name1, &src2, name2, + result_buf); + + free(name1); + free(name2); + free(orig.ptr); + free(src1.ptr); + free(src2.ptr); + return merge_status; +} + static struct merge_file_info merge_file(struct diff_filespec *o, struct diff_filespec *a, struct diff_filespec *b, const char *branch1, const char *branch2) @@ -673,30 +1053,11 @@ static struct merge_file_info merge_file(struct diff_filespec *o, else if (sha_eq(b->sha1, o->sha1)) hashcpy(result.sha, a->sha1); else if (S_ISREG(a->mode)) { - mmfile_t orig, src1, src2; mmbuffer_t result_buf; - xpparam_t xpp; - char *name1, *name2; int merge_status; - name1 = xstrdup(mkpath("%s:%s", branch1, a->path)); - name2 = xstrdup(mkpath("%s:%s", branch2, b->path)); - - fill_mm(o->sha1, &orig); - fill_mm(a->sha1, &src1); - fill_mm(b->sha1, &src2); - - memset(&xpp, 0, sizeof(xpp)); - merge_status = xdl_merge(&orig, - &src1, name1, - &src2, name2, - &xpp, XDL_MERGE_ZEALOUS, - &result_buf); - free(name1); - free(name2); - free(orig.ptr); - free(src1.ptr); - free(src2.ptr); + merge_status = ll_merge(&result_buf, o, a, b, + branch1, branch2); if ((merge_status < 0) || !result_buf.ptr) die("Failed to execute internal merge"); diff --git a/sha1_file.c b/sha1_file.c index 0c0fcc597d..06426640ea 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -2338,10 +2338,9 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, */ if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) { unsigned long nsize = size; - char *nbuf = buf; - if (convert_to_git(path, &nbuf, &nsize)) { - if (size) - munmap(buf, size); + char *nbuf = convert_to_git(path, buf, &nsize); + if (nbuf) { + munmap(buf, size); size = nsize; buf = nbuf; re_allocated = 1; diff --git a/t/t0020-crlf.sh b/t/t0020-crlf.sh index 723b29ad17..fe1dfd08a0 100755 --- a/t/t0020-crlf.sh +++ b/t/t0020-crlf.sh @@ -4,6 +4,10 @@ test_description='CRLF conversion' . ./test-lib.sh +q_to_nul () { + tr Q '\0' +} + append_cr () { sed -e 's/$/Q/' | tr Q '\015' } @@ -20,6 +24,7 @@ test_expect_success setup ' for w in Hello world how are you; do echo $w; done >one && mkdir dir && for w in I am very very fine thank you; do echo $w; done >dir/two && + for w in Oh here is NULQin text here; do echo $w; done | q_to_nul >three && git add . && git commit -m initial && @@ -27,6 +32,7 @@ test_expect_success setup ' one=`git rev-parse HEAD:one` && dir=`git rev-parse HEAD:dir` && two=`git rev-parse HEAD:dir/two` && + three=`git rev-parse HEAD:three` && for w in Some extra lines here; do echo $w; done >>one && git diff >patch.file && @@ -38,7 +44,7 @@ test_expect_success setup ' test_expect_success 'update with autocrlf=input' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git read-tree --reset -u HEAD && git repo-config core.autocrlf input && @@ -62,7 +68,7 @@ test_expect_success 'update with autocrlf=input' ' test_expect_success 'update with autocrlf=true' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git read-tree --reset -u HEAD && git repo-config core.autocrlf true && @@ -86,7 +92,7 @@ test_expect_success 'update with autocrlf=true' ' test_expect_success 'checkout with autocrlf=true' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf true && git read-tree --reset -u HEAD && @@ -110,7 +116,7 @@ test_expect_success 'checkout with autocrlf=true' ' test_expect_success 'checkout with autocrlf=input' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf input && git read-tree --reset -u HEAD && @@ -136,7 +142,7 @@ test_expect_success 'checkout with autocrlf=input' ' test_expect_success 'apply patch (autocrlf=input)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf input && git read-tree --reset -u HEAD && @@ -149,7 +155,7 @@ test_expect_success 'apply patch (autocrlf=input)' ' test_expect_success 'apply patch --cached (autocrlf=input)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf input && git read-tree --reset -u HEAD && @@ -162,7 +168,7 @@ test_expect_success 'apply patch --cached (autocrlf=input)' ' test_expect_success 'apply patch --index (autocrlf=input)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf input && git read-tree --reset -u HEAD && @@ -176,7 +182,7 @@ test_expect_success 'apply patch --index (autocrlf=input)' ' test_expect_success 'apply patch (autocrlf=true)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf true && git read-tree --reset -u HEAD && @@ -189,7 +195,7 @@ test_expect_success 'apply patch (autocrlf=true)' ' test_expect_success 'apply patch --cached (autocrlf=true)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf true && git read-tree --reset -u HEAD && @@ -202,7 +208,7 @@ test_expect_success 'apply patch --cached (autocrlf=true)' ' test_expect_success 'apply patch --index (autocrlf=true)' ' - rm -f tmp one dir/two && + rm -f tmp one dir/two three && git repo-config core.autocrlf true && git read-tree --reset -u HEAD && @@ -214,4 +220,74 @@ test_expect_success 'apply patch --index (autocrlf=true)' ' } ' +test_expect_success '.gitattributes says two is binary' ' + + rm -f tmp one dir/two three && + echo "two -crlf" >.gitattributes && + git repo-config core.autocrlf true && + git read-tree --reset -u HEAD && + + if remove_cr dir/two >/dev/null + then + echo "Huh?" + false + else + : happy + fi && + + if remove_cr one >/dev/null + then + : happy + else + echo "Huh?" + false + fi && + + if remove_cr three >/dev/null + then + echo "Huh?" + false + else + : happy + fi +' + +test_expect_success '.gitattributes says two is input' ' + + rm -f tmp one dir/two three && + echo "two crlf=input" >.gitattributes && + git read-tree --reset -u HEAD && + + if remove_cr dir/two >/dev/null + then + echo "Huh?" + false + else + : happy + fi +' + +test_expect_success '.gitattributes says two and three are text' ' + + rm -f tmp one dir/two three && + echo "t* crlf" >.gitattributes && + git read-tree --reset -u HEAD && + + if remove_cr dir/two >/dev/null + then + : happy + else + echo "Huh?" + false + fi && + + if remove_cr three >/dev/null + then + : happy + else + echo "Huh?" + false + fi +' + test_done diff --git a/t/t6026-merge-attr.sh b/t/t6026-merge-attr.sh new file mode 100755 index 0000000000..56fc341768 --- /dev/null +++ b/t/t6026-merge-attr.sh @@ -0,0 +1,145 @@ +#!/bin/sh +# +# Copyright (c) 2007 Junio C Hamano +# + +test_description='per path merge controlled by merge attribute' + +. ./test-lib.sh + +test_expect_success setup ' + + for f in text binary union + do + echo Initial >$f && git add $f || break + done && + test_tick && + git commit -m Initial && + + git branch side && + for f in text binary union + do + echo Master >>$f && git add $f || break + done && + test_tick && + git commit -m Master && + + git checkout side && + for f in text binary union + do + echo Side >>$f && git add $f || break + done && + test_tick && + git commit -m Side && + + git tag anchor +' + +test_expect_success merge ' + + { + echo "binary -merge" + echo "union merge=union" + } >.gitattributes && + + if git merge master + then + echo Gaah, should have conflicted + false + else + echo Ok, conflicted. + fi +' + +test_expect_success 'check merge result in index' ' + + git ls-files -u | grep binary && + git ls-files -u | grep text && + ! (git ls-files -u | grep union) + +' + +test_expect_success 'check merge result in working tree' ' + + git cat-file -p HEAD:binary >binary-orig && + grep "<<<<<<<" text && + cmp binary-orig binary && + ! grep "<<<<<<<" union && + grep Master union && + grep Side union + +' + +cat >./custom-merge <<\EOF +#!/bin/sh + +orig="$1" ours="$2" theirs="$3" exit="$4" +( + echo "orig is $orig" + echo "ours is $ours" + echo "theirs is $theirs" + echo "=== orig ===" + cat "$orig" + echo "=== ours ===" + cat "$ours" + echo "=== theirs ===" + cat "$theirs" +) >"$ours+" +cat "$ours+" >"$ours" +rm -f "$ours+" +exit "$exit" +EOF +chmod +x ./custom-merge + +test_expect_success 'custom merge backend' ' + + echo "* merge=union" >.gitattributes && + echo "text merge=custom" >>.gitattributes && + + git reset --hard anchor && + git config --replace-all \ + merge.custom.driver "./custom-merge %O %A %B 0" && + git config --replace-all \ + merge.custom.name "custom merge driver for testing" && + + git merge master && + + cmp binary union && + sed -e 1,3d text >check-1 && + o=$(git-unpack-file master^:text) && + a=$(git-unpack-file side^:text) && + b=$(git-unpack-file master:text) && + sh -c "./custom-merge $o $a $b 0" && + sed -e 1,3d $a >check-2 && + cmp check-1 check-2 && + rm -f $o $a $b +' + +test_expect_success 'custom merge backend' ' + + git reset --hard anchor && + git config --replace-all \ + merge.custom.driver "./custom-merge %O %A %B 1" && + git config --replace-all \ + merge.custom.name "custom merge driver for testing" && + + if git merge master + then + echo "Eh? should have conflicted" + false + else + echo "Ok, conflicted" + fi && + + cmp binary union && + sed -e 1,3d text >check-1 && + o=$(git-unpack-file master^:text) && + a=$(git-unpack-file anchor:text) && + b=$(git-unpack-file master:text) && + sh -c "./custom-merge $o $a $b 0" && + sed -e 1,3d $a >check-2 && + cmp check-1 check-2 && + rm -f $o $a $b +' + +test_done |