diff options
author | Junio C Hamano <gitster@pobox.com> | 2013-01-10 13:47:15 -0800 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2013-01-10 13:47:20 -0800 |
commit | 2adf7247ec1f82032f52682918c200716145bffd (patch) | |
tree | 2af5f520d874aa11b668138aebecce58da3256eb | |
parent | 4249d850cff0d1d36b3a9c4cf38066c50365cfd1 (diff) | |
parent | b6a3d3353f799c8c5afedb2da4df6e7cdc5d00c9 (diff) | |
download | git-2adf7247ec1f82032f52682918c200716145bffd.tar.gz |
Merge branch 'nd/wildmatch'
Allows pathname patterns in .gitignore and .gitattributes files
with double-asterisks "foo/**/bar" to match any number of directory
hierarchies.
* nd/wildmatch:
wildmatch: replace variable 'special' with better named ones
compat/fnmatch: respect NO_FNMATCH* even on glibc
wildmatch: fix "**" special case
t3070: Disable some failing fnmatch tests
test-wildmatch: avoid Windows path mangling
Support "**" wildcard in .gitignore and .gitattributes
wildmatch: make /**/ match zero or more directories
wildmatch: adjust "**" behavior
wildmatch: fix case-insensitive matching
wildmatch: remove static variable force_lower_case
wildmatch: make wildmatch's return value compatible with fnmatch
t3070: disable unreliable fnmatch tests
Integrate wildmatch to git
wildmatch: follow Git's coding convention
wildmatch: remove unnecessary functions
Import wildmatch from rsync
ctype: support iscntrl, ispunct, isxdigit and isprint
ctype: make sane_ctype[] const array
Conflicts:
Makefile
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | Documentation/gitignore.txt | 19 | ||||
-rw-r--r-- | Makefile | 3 | ||||
-rw-r--r-- | compat/fnmatch/fnmatch.c | 3 | ||||
-rw-r--r-- | ctype.c | 15 | ||||
-rw-r--r-- | dir.c | 4 | ||||
-rw-r--r-- | git-compat-util.h | 12 | ||||
-rwxr-xr-x | t/t0003-attributes.sh | 37 | ||||
-rwxr-xr-x | t/t3001-ls-files-others-exclude.sh | 18 | ||||
-rwxr-xr-x | t/t3070-wildmatch.sh | 195 | ||||
-rw-r--r-- | test-wildmatch.c | 22 | ||||
-rw-r--r-- | wildmatch.c | 235 | ||||
-rw-r--r-- | wildmatch.h | 9 |
13 files changed, 564 insertions, 9 deletions
diff --git a/.gitignore b/.gitignore index 8e8dc275db..aa258a6bcf 100644 --- a/.gitignore +++ b/.gitignore @@ -197,6 +197,7 @@ /test-string-list /test-subprocess /test-svn-fe +/test-wildmatch /common-cmds.h *.tar.gz *.dsc diff --git a/Documentation/gitignore.txt b/Documentation/gitignore.txt index 1b82fe1969..91a6438031 100644 --- a/Documentation/gitignore.txt +++ b/Documentation/gitignore.txt @@ -108,6 +108,25 @@ PATTERN FORMAT For example, "/{asterisk}.c" matches "cat-file.c" but not "mozilla-sha1/sha1.c". +Two consecutive asterisks ("`**`") in patterns matched against +full pathname may have special meaning: + + - A leading "`**`" followed by a slash means match in all + directories. For example, "`**/foo`" matches file or directory + "`foo`" anywhere, the same as pattern "`foo`". "**/foo/bar" + matches file or directory "`bar`" anywhere that is directly + under directory "`foo`". + + - A trailing "/**" matches everything inside. For example, + "abc/**" matches all files inside directory "abc", relative + to the location of the `.gitignore` file, with infinite depth. + + - A slash followed by two consecutive asterisks then a slash + matches zero or more directories. For example, "`a/**/b`" + matches "`a/b`", "`a/x/b`", "`a/x/y/b`" and so on. + + - Other consecutive asterisks are considered invalid. + NOTES ----- @@ -532,6 +532,7 @@ TEST_PROGRAMS_NEED_X += test-sigchain TEST_PROGRAMS_NEED_X += test-string-list TEST_PROGRAMS_NEED_X += test-subprocess TEST_PROGRAMS_NEED_X += test-svn-fe +TEST_PROGRAMS_NEED_X += test-wildmatch TEST_PROGRAMS = $(patsubst %,%$X,$(TEST_PROGRAMS_NEED_X)) @@ -704,6 +705,7 @@ LIB_H += userdiff.h LIB_H += utf8.h LIB_H += varint.h LIB_H += walker.h +LIB_H += wildmatch.h LIB_H += wt-status.h LIB_H += xdiff-interface.h LIB_H += xdiff/xdiff.h @@ -838,6 +840,7 @@ LIB_OBJS += utf8.o LIB_OBJS += varint.o LIB_OBJS += version.o LIB_OBJS += walker.o +LIB_OBJS += wildmatch.o LIB_OBJS += wrapper.o LIB_OBJS += write_or_die.o LIB_OBJS += ws.o diff --git a/compat/fnmatch/fnmatch.c b/compat/fnmatch/fnmatch.c index b8b7dc2543..5ef0685135 100644 --- a/compat/fnmatch/fnmatch.c +++ b/compat/fnmatch/fnmatch.c @@ -55,7 +55,8 @@ program understand `configure --with-gnu-libc' and omit the object files, it is simpler to just do this in the source for each such file. */ -#if defined _LIBC || !defined __GNU_LIBRARY__ +#if defined NO_FNMATCH || defined NO_FNMATCH_CASEFOLD || \ + defined _LIBC || !defined __GNU_LIBRARY__ # if defined STDC_HEADERS || !defined isascii @@ -11,18 +11,21 @@ enum { D = GIT_DIGIT, G = GIT_GLOB_SPECIAL, /* *, ?, [, \\ */ R = GIT_REGEX_SPECIAL, /* $, (, ), +, ., ^, {, | */ - P = GIT_PATHSPEC_MAGIC /* other non-alnum, except for ] and } */ + P = GIT_PATHSPEC_MAGIC, /* other non-alnum, except for ] and } */ + X = GIT_CNTRL, + U = GIT_PUNCT, + Z = GIT_CNTRL | GIT_SPACE }; -unsigned char sane_ctype[256] = { - 0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0, /* 0.. 15 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16.. 31 */ +const unsigned char sane_ctype[256] = { + X, X, X, X, X, X, X, X, X, Z, Z, X, X, Z, X, X, /* 0.. 15 */ + X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, /* 16.. 31 */ S, P, P, P, R, P, P, P, R, R, G, R, P, P, R, P, /* 32.. 47 */ D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, G, /* 48.. 63 */ P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 64.. 79 */ - A, A, A, A, A, A, A, A, A, A, A, G, G, 0, R, P, /* 80.. 95 */ + A, A, A, A, A, A, A, A, A, A, A, G, G, U, R, P, /* 80.. 95 */ P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A, /* 96..111 */ - A, A, A, A, A, A, A, A, A, A, A, R, R, 0, P, 0, /* 112..127 */ + A, A, A, A, A, A, A, A, A, A, A, R, R, U, P, X, /* 112..127 */ /* Nothing in the 128.. range */ }; @@ -8,6 +8,7 @@ #include "cache.h" #include "dir.h" #include "refs.h" +#include "wildmatch.h" struct path_simplify { int len; @@ -624,7 +625,8 @@ int match_pathname(const char *pathname, int pathlen, namelen -= prefix; } - return fnmatch_icase(pattern, name, FNM_PATHNAME) == 0; + return wildmatch(pattern, name, + ignore_case ? FNM_CASEFOLD : 0) == 0; } /* Scan the list and let the last match determine the fate. diff --git a/git-compat-util.h b/git-compat-util.h index 2cecf56eb3..e5a4b7450b 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -528,13 +528,19 @@ extern const char tolower_trans_tbl[256]; #undef isupper #undef tolower #undef toupper -extern unsigned char sane_ctype[256]; +#undef iscntrl +#undef ispunct +#undef isxdigit + +extern const unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 #define GIT_ALPHA 0x04 #define GIT_GLOB_SPECIAL 0x08 #define GIT_REGEX_SPECIAL 0x10 #define GIT_PATHSPEC_MAGIC 0x20 +#define GIT_CNTRL 0x40 +#define GIT_PUNCT 0x80 #define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) #define isascii(x) (((x) & ~0x7f) == 0) #define isspace(x) sane_istest(x,GIT_SPACE) @@ -546,6 +552,10 @@ extern unsigned char sane_ctype[256]; #define isupper(x) sane_iscase(x, 0) #define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL) #define is_regex_special(x) sane_istest(x,GIT_GLOB_SPECIAL | GIT_REGEX_SPECIAL) +#define iscntrl(x) (sane_istest(x,GIT_CNTRL)) +#define ispunct(x) sane_istest(x, GIT_PUNCT | GIT_REGEX_SPECIAL | \ + GIT_GLOB_SPECIAL | GIT_PATHSPEC_MAGIC) +#define isxdigit(x) (hexval_table[x] != -1) #define tolower(x) sane_case((unsigned char)(x), 0x20) #define toupper(x) sane_case((unsigned char)(x), 0) #define is_pathspec_magic(x) sane_istest(x,GIT_PATHSPEC_MAGIC) diff --git a/t/t0003-attributes.sh b/t/t0003-attributes.sh index 807b8b88e2..43b25137e9 100755 --- a/t/t0003-attributes.sh +++ b/t/t0003-attributes.sh @@ -206,6 +206,43 @@ test_expect_success 'patterns starting with exclamation' ' attr_check "!f" foo ' +test_expect_success '"**" test' ' + echo "**/f foo=bar" >.gitattributes && + cat <<\EOF >expect && +f: foo: bar +a/f: foo: bar +a/b/f: foo: bar +a/b/c/f: foo: bar +EOF + git check-attr foo -- "f" >actual 2>err && + git check-attr foo -- "a/f" >>actual 2>>err && + git check-attr foo -- "a/b/f" >>actual 2>>err && + git check-attr foo -- "a/b/c/f" >>actual 2>>err && + test_cmp expect actual && + test_line_count = 0 err +' + +test_expect_success '"**" with no slashes test' ' + echo "a**f foo=bar" >.gitattributes && + git check-attr foo -- "f" >actual && + cat <<\EOF >expect && +f: foo: unspecified +af: foo: bar +axf: foo: bar +a/f: foo: unspecified +a/b/f: foo: unspecified +a/b/c/f: foo: unspecified +EOF + git check-attr foo -- "f" >actual 2>err && + git check-attr foo -- "af" >>actual 2>err && + git check-attr foo -- "axf" >>actual 2>err && + git check-attr foo -- "a/f" >>actual 2>>err && + git check-attr foo -- "a/b/f" >>actual 2>>err && + git check-attr foo -- "a/b/c/f" >>actual 2>>err && + test_cmp expect actual && + test_line_count = 0 err +' + test_expect_success 'setup bare' ' git clone --bare . bare.git && cd bare.git diff --git a/t/t3001-ls-files-others-exclude.sh b/t/t3001-ls-files-others-exclude.sh index dc2f0458fd..efb7ebc91f 100755 --- a/t/t3001-ls-files-others-exclude.sh +++ b/t/t3001-ls-files-others-exclude.sh @@ -220,4 +220,22 @@ test_expect_success 'pattern matches prefix completely' ' test_cmp expect actual ' +test_expect_success 'ls-files with "**" patterns' ' + cat <<\EOF >expect && +a.1 +one/a.1 +one/two/a.1 +three/a.1 +EOF + git ls-files -o -i --exclude "**/a.1" >actual + test_cmp expect actual +' + + +test_expect_success 'ls-files with "**" patterns and no slashes' ' + : >expect && + git ls-files -o -i --exclude "one**a.1" >actual && + test_cmp expect actual +' + test_done diff --git a/t/t3070-wildmatch.sh b/t/t3070-wildmatch.sh new file mode 100755 index 0000000000..af54c83111 --- /dev/null +++ b/t/t3070-wildmatch.sh @@ -0,0 +1,195 @@ +#!/bin/sh + +test_description='wildmatch tests' + +. ./test-lib.sh + +match() { + if [ $1 = 1 ]; then + test_expect_success "wildmatch: match '$3' '$4'" " + test-wildmatch wildmatch '$3' '$4' + " + else + test_expect_success "wildmatch: no match '$3' '$4'" " + ! test-wildmatch wildmatch '$3' '$4' + " + fi + if [ $2 = 1 ]; then + test_expect_success "fnmatch: match '$3' '$4'" " + test-wildmatch fnmatch '$3' '$4' + " + elif [ $2 = 0 ]; then + test_expect_success "fnmatch: no match '$3' '$4'" " + ! test-wildmatch fnmatch '$3' '$4' + " +# else +# test_expect_success BROKEN_FNMATCH "fnmatch: '$3' '$4'" " +# ! test-wildmatch fnmatch '$3' '$4' +# " + fi +} + +# Basic wildmat features +match 1 1 foo foo +match 0 0 foo bar +match 1 1 '' "" +match 1 1 foo '???' +match 0 0 foo '??' +match 1 1 foo '*' +match 1 1 foo 'f*' +match 0 0 foo '*f' +match 1 1 foo '*foo*' +match 1 1 foobar '*ob*a*r*' +match 1 1 aaaaaaabababab '*ab' +match 1 1 'foo*' 'foo\*' +match 0 0 foobar 'foo\*bar' +match 1 1 'f\oo' 'f\\oo' +match 1 1 ball '*[al]?' +match 0 0 ten '[ten]' +match 0 1 ten '**[!te]' +match 0 0 ten '**[!ten]' +match 1 1 ten 't[a-g]n' +match 0 0 ten 't[!a-g]n' +match 1 1 ton 't[!a-g]n' +match 1 1 ton 't[^a-g]n' +match 1 x 'a]b' 'a[]]b' +match 1 x a-b 'a[]-]b' +match 1 x 'a]b' 'a[]-]b' +match 0 x aab 'a[]-]b' +match 1 x aab 'a[]a-]b' +match 1 1 ']' ']' + +# Extended slash-matching features +match 0 0 'foo/baz/bar' 'foo*bar' +match 0 0 'foo/baz/bar' 'foo**bar' +match 0 1 'foobazbar' 'foo**bar' +match 1 1 'foo/baz/bar' 'foo/**/bar' +match 1 0 'foo/baz/bar' 'foo/**/**/bar' +match 1 0 'foo/b/a/z/bar' 'foo/**/bar' +match 1 0 'foo/b/a/z/bar' 'foo/**/**/bar' +match 1 0 'foo/bar' 'foo/**/bar' +match 1 0 'foo/bar' 'foo/**/**/bar' +match 0 0 'foo/bar' 'foo?bar' +match 0 0 'foo/bar' 'foo[/]bar' +match 0 0 'foo/bar' 'f[^eiu][^eiu][^eiu][^eiu][^eiu]r' +match 1 1 'foo-bar' 'f[^eiu][^eiu][^eiu][^eiu][^eiu]r' +match 1 0 'foo' '**/foo' +match 1 x 'XXX/foo' '**/foo' +match 1 0 'bar/baz/foo' '**/foo' +match 0 0 'bar/baz/foo' '*/foo' +match 0 0 'foo/bar/baz' '**/bar*' +match 1 0 'deep/foo/bar/baz' '**/bar/*' +match 0 0 'deep/foo/bar/baz/' '**/bar/*' +match 1 0 'deep/foo/bar/baz/' '**/bar/**' +match 0 0 'deep/foo/bar' '**/bar/*' +match 1 0 'deep/foo/bar/' '**/bar/**' +match 0 0 'foo/bar/baz' '**/bar**' +match 1 0 'foo/bar/baz/x' '*/bar/**' +match 0 0 'deep/foo/bar/baz/x' '*/bar/**' +match 1 0 'deep/foo/bar/baz/x' '**/bar/*/*' + +# Various additional tests +match 0 0 'acrt' 'a[c-c]st' +match 1 1 'acrt' 'a[c-c]rt' +match 0 0 ']' '[!]-]' +match 1 x 'a' '[!]-]' +match 0 0 '' '\' +match 0 x '\' '\' +match 0 x 'XXX/\' '*/\' +match 1 x 'XXX/\' '*/\\' +match 1 1 'foo' 'foo' +match 1 1 '@foo' '@foo' +match 0 0 'foo' '@foo' +match 1 1 '[ab]' '\[ab]' +match 1 1 '[ab]' '[[]ab]' +match 1 x '[ab]' '[[:]ab]' +match 0 x '[ab]' '[[::]ab]' +match 1 x '[ab]' '[[:digit]ab]' +match 1 x '[ab]' '[\[:]ab]' +match 1 1 '?a?b' '\??\?b' +match 1 1 'abc' '\a\b\c' +match 0 0 'foo' '' +match 1 0 'foo/bar/baz/to' '**/t[o]' + +# Character class tests +match 1 x 'a1B' '[[:alpha:]][[:digit:]][[:upper:]]' +match 0 x 'a' '[[:digit:][:upper:][:space:]]' +match 1 x 'A' '[[:digit:][:upper:][:space:]]' +match 1 x '1' '[[:digit:][:upper:][:space:]]' +match 0 x '1' '[[:digit:][:upper:][:spaci:]]' +match 1 x ' ' '[[:digit:][:upper:][:space:]]' +match 0 x '.' '[[:digit:][:upper:][:space:]]' +match 1 x '.' '[[:digit:][:punct:][:space:]]' +match 1 x '5' '[[:xdigit:]]' +match 1 x 'f' '[[:xdigit:]]' +match 1 x 'D' '[[:xdigit:]]' +match 1 x '_' '[[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]' +match 1 x '_' '[[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]' +match 1 x '.' '[^[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:lower:][:space:][:upper:][:xdigit:]]' +match 1 x '5' '[a-c[:digit:]x-z]' +match 1 x 'b' '[a-c[:digit:]x-z]' +match 1 x 'y' '[a-c[:digit:]x-z]' +match 0 x 'q' '[a-c[:digit:]x-z]' + +# Additional tests, including some malformed wildmats +match 1 x ']' '[\\-^]' +match 0 0 '[' '[\\-^]' +match 1 x '-' '[\-_]' +match 1 x ']' '[\]]' +match 0 0 '\]' '[\]]' +match 0 0 '\' '[\]]' +match 0 0 'ab' 'a[]b' +match 0 x 'a[]b' 'a[]b' +match 0 x 'ab[' 'ab[' +match 0 0 'ab' '[!' +match 0 0 'ab' '[-' +match 1 1 '-' '[-]' +match 0 0 '-' '[a-' +match 0 0 '-' '[!a-' +match 1 x '-' '[--A]' +match 1 x '5' '[--A]' +match 1 1 ' ' '[ --]' +match 1 1 '$' '[ --]' +match 1 1 '-' '[ --]' +match 0 0 '0' '[ --]' +match 1 x '-' '[---]' +match 1 x '-' '[------]' +match 0 0 'j' '[a-e-n]' +match 1 x '-' '[a-e-n]' +match 1 x 'a' '[!------]' +match 0 0 '[' '[]-a]' +match 1 x '^' '[]-a]' +match 0 0 '^' '[!]-a]' +match 1 x '[' '[!]-a]' +match 1 1 '^' '[a^bc]' +match 1 x '-b]' '[a-]b]' +match 0 0 '\' '[\]' +match 1 1 '\' '[\\]' +match 0 0 '\' '[!\\]' +match 1 1 'G' '[A-\\]' +match 0 0 'aaabbb' 'b*a' +match 0 0 'aabcaa' '*ba*' +match 1 1 ',' '[,]' +match 1 1 ',' '[\\,]' +match 1 1 '\' '[\\,]' +match 1 1 '-' '[,-.]' +match 0 0 '+' '[,-.]' +match 0 0 '-.]' '[,-.]' +match 1 1 '2' '[\1-\3]' +match 1 1 '3' '[\1-\3]' +match 0 0 '4' '[\1-\3]' +match 1 1 '\' '[[-\]]' +match 1 1 '[' '[[-\]]' +match 1 1 ']' '[[-\]]' +match 0 0 '-' '[[-\]]' + +# Test recursion and the abort code (use "wildtest -i" to see iteration counts) +match 1 1 '-adobe-courier-bold-o-normal--12-120-75-75-m-70-iso8859-1' '-*-*-*-*-*-*-12-*-*-*-m-*-*-*' +match 0 0 '-adobe-courier-bold-o-normal--12-120-75-75-X-70-iso8859-1' '-*-*-*-*-*-*-12-*-*-*-m-*-*-*' +match 0 0 '-adobe-courier-bold-o-normal--12-120-75-75-/-70-iso8859-1' '-*-*-*-*-*-*-12-*-*-*-m-*-*-*' +match 1 1 'XXX/adobe/courier/bold/o/normal//12/120/75/75/m/70/iso8859/1' 'XXX/*/*/*/*/*/*/12/*/*/*/m/*/*/*' +match 0 0 'XXX/adobe/courier/bold/o/normal//12/120/75/75/X/70/iso8859/1' 'XXX/*/*/*/*/*/*/12/*/*/*/m/*/*/*' +match 1 0 'abcd/abcdefg/abcdefghijk/abcdefghijklmnop.txt' '**/*a*b*g*n*t' +match 0 0 'abcd/abcdefg/abcdefghijk/abcdefghijklmnop.txtz' '**/*a*b*g*n*t' + +test_done diff --git a/test-wildmatch.c b/test-wildmatch.c new file mode 100644 index 0000000000..e384c8edb1 --- /dev/null +++ b/test-wildmatch.c @@ -0,0 +1,22 @@ +#include "cache.h" +#include "wildmatch.h" + +int main(int argc, char **argv) +{ + int i; + for (i = 2; i < argc; i++) { + if (argv[i][0] == '/') + die("Forward slash is not allowed at the beginning of the\n" + "pattern because Windows does not like it. Use `XXX/' instead."); + else if (!strncmp(argv[i], "XXX/", 4)) + argv[i] += 3; + } + if (!strcmp(argv[1], "wildmatch")) + return !!wildmatch(argv[3], argv[2], 0); + else if (!strcmp(argv[1], "iwildmatch")) + return !!wildmatch(argv[3], argv[2], FNM_CASEFOLD); + else if (!strcmp(argv[1], "fnmatch")) + return !!fnmatch(argv[3], argv[2], FNM_PATHNAME); + else + return 1; +} diff --git a/wildmatch.c b/wildmatch.c new file mode 100644 index 0000000000..2d3ed84364 --- /dev/null +++ b/wildmatch.c @@ -0,0 +1,235 @@ +/* +** Do shell-style pattern matching for ?, \, [], and * characters. +** It is 8bit clean. +** +** Written by Rich $alz, mirror!rs, Wed Nov 26 19:03:17 EST 1986. +** Rich $alz is now <rsalz@bbn.com>. +** +** Modified by Wayne Davison to special-case '/' matching, to make '**' +** work differently than '*', and to fix the character-class code. +*/ + +#include "cache.h" +#include "wildmatch.h" + +typedef unsigned char uchar; + +/* What character marks an inverted character class? */ +#define NEGATE_CLASS '!' +#define NEGATE_CLASS2 '^' + +#define FALSE 0 +#define TRUE 1 + +#define CC_EQ(class, len, litmatch) ((len) == sizeof (litmatch)-1 \ + && *(class) == *(litmatch) \ + && strncmp((char*)class, litmatch, len) == 0) + +#if defined STDC_HEADERS || !defined isascii +# define ISASCII(c) 1 +#else +# define ISASCII(c) isascii(c) +#endif + +#ifdef isblank +# define ISBLANK(c) (ISASCII(c) && isblank(c)) +#else +# define ISBLANK(c) ((c) == ' ' || (c) == '\t') +#endif + +#ifdef isgraph +# define ISGRAPH(c) (ISASCII(c) && isgraph(c)) +#else +# define ISGRAPH(c) (ISASCII(c) && isprint(c) && !isspace(c)) +#endif + +#define ISPRINT(c) (ISASCII(c) && isprint(c)) +#define ISDIGIT(c) (ISASCII(c) && isdigit(c)) +#define ISALNUM(c) (ISASCII(c) && isalnum(c)) +#define ISALPHA(c) (ISASCII(c) && isalpha(c)) +#define ISCNTRL(c) (ISASCII(c) && iscntrl(c)) +#define ISLOWER(c) (ISASCII(c) && islower(c)) +#define ISPUNCT(c) (ISASCII(c) && ispunct(c)) +#define ISSPACE(c) (ISASCII(c) && isspace(c)) +#define ISUPPER(c) (ISASCII(c) && isupper(c)) +#define ISXDIGIT(c) (ISASCII(c) && isxdigit(c)) + +/* Match pattern "p" against "text" */ +static int dowild(const uchar *p, const uchar *text, int force_lower_case) +{ + uchar p_ch; + const uchar *pattern = p; + + for ( ; (p_ch = *p) != '\0'; text++, p++) { + int matched, match_slash, negated; + uchar t_ch, prev_ch; + if ((t_ch = *text) == '\0' && p_ch != '*') + return ABORT_ALL; + if (force_lower_case && ISUPPER(t_ch)) + t_ch = tolower(t_ch); + if (force_lower_case && ISUPPER(p_ch)) + p_ch = tolower(p_ch); + switch (p_ch) { + case '\\': + /* Literal match with following character. Note that the test + * in "default" handles the p[1] == '\0' failure case. */ + p_ch = *++p; + /* FALLTHROUGH */ + default: + if (t_ch != p_ch) + return NOMATCH; + continue; + case '?': + /* Match anything but '/'. */ + if (t_ch == '/') + return NOMATCH; + continue; + case '*': + if (*++p == '*') { + const uchar *prev_p = p - 2; + while (*++p == '*') {} + if ((prev_p < pattern || *prev_p == '/') && + (*p == '\0' || *p == '/' || + (p[0] == '\\' && p[1] == '/'))) { + /* + * Assuming we already match 'foo/' and are at + * <star star slash>, just assume it matches + * nothing and go ahead match the rest of the + * pattern with the remaining string. This + * helps make foo/<*><*>/bar (<> because + * otherwise it breaks C comment syntax) match + * both foo/bar and foo/a/bar. + */ + if (p[0] == '/' && + dowild(p + 1, text, force_lower_case) == MATCH) + return MATCH; + match_slash = TRUE; + } else + return ABORT_MALFORMED; + } else + match_slash = FALSE; + if (*p == '\0') { + /* Trailing "**" matches everything. Trailing "*" matches + * only if there are no more slash characters. */ + if (!match_slash) { + if (strchr((char*)text, '/') != NULL) + return NOMATCH; + } + return MATCH; + } + while (1) { + if (t_ch == '\0') + break; + if ((matched = dowild(p, text, force_lower_case)) != NOMATCH) { + if (!match_slash || matched != ABORT_TO_STARSTAR) + return matched; + } else if (!match_slash && t_ch == '/') + return ABORT_TO_STARSTAR; + t_ch = *++text; + } + return ABORT_ALL; + case '[': + p_ch = *++p; +#ifdef NEGATE_CLASS2 + if (p_ch == NEGATE_CLASS2) + p_ch = NEGATE_CLASS; +#endif + /* Assign literal TRUE/FALSE because of "matched" comparison. */ + negated = p_ch == NEGATE_CLASS? TRUE : FALSE; + if (negated) { + /* Inverted character class. */ + p_ch = *++p; + } + prev_ch = 0; + matched = FALSE; + do { + if (!p_ch) + return ABORT_ALL; + if (p_ch == '\\') { + p_ch = *++p; + if (!p_ch) + return ABORT_ALL; + if (t_ch == p_ch) + matched = TRUE; + } else if (p_ch == '-' && prev_ch && p[1] && p[1] != ']') { + p_ch = *++p; + if (p_ch == '\\') { + p_ch = *++p; + if (!p_ch) + return ABORT_ALL; + } + if (t_ch <= p_ch && t_ch >= prev_ch) + matched = TRUE; + p_ch = 0; /* This makes "prev_ch" get set to 0. */ + } else if (p_ch == '[' && p[1] == ':') { + const uchar *s; + int i; + for (s = p += 2; (p_ch = *p) && p_ch != ']'; p++) {} /*SHARED ITERATOR*/ + if (!p_ch) + return ABORT_ALL; + i = p - s - 1; + if (i < 0 || p[-1] != ':') { + /* Didn't find ":]", so treat like a normal set. */ + p = s - 2; + p_ch = '['; + if (t_ch == p_ch) + matched = TRUE; + continue; + } + if (CC_EQ(s,i, "alnum")) { + if (ISALNUM(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "alpha")) { + if (ISALPHA(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "blank")) { + if (ISBLANK(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "cntrl")) { + if (ISCNTRL(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "digit")) { + if (ISDIGIT(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "graph")) { + if (ISGRAPH(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "lower")) { + if (ISLOWER(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "print")) { + if (ISPRINT(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "punct")) { + if (ISPUNCT(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "space")) { + if (ISSPACE(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "upper")) { + if (ISUPPER(t_ch)) + matched = TRUE; + } else if (CC_EQ(s,i, "xdigit")) { + if (ISXDIGIT(t_ch)) + matched = TRUE; + } else /* malformed [:class:] string */ + return ABORT_ALL; + p_ch = 0; /* This makes "prev_ch" get set to 0. */ + } else if (t_ch == p_ch) + matched = TRUE; + } while (prev_ch = p_ch, (p_ch = *++p) != ']'); + if (matched == negated || t_ch == '/') + return NOMATCH; + continue; + } + } + + return *text ? NOMATCH : MATCH; +} + +/* Match the "pattern" against the "text" string. */ +int wildmatch(const char *pattern, const char *text, int flags) +{ + return dowild((const uchar*)pattern, (const uchar*)text, + flags & FNM_CASEFOLD ? 1 :0); +} diff --git a/wildmatch.h b/wildmatch.h new file mode 100644 index 0000000000..984a38cdc2 --- /dev/null +++ b/wildmatch.h @@ -0,0 +1,9 @@ +/* wildmatch.h */ + +#define ABORT_MALFORMED 2 +#define NOMATCH 1 +#define MATCH 0 +#define ABORT_ALL -1 +#define ABORT_TO_STARSTAR -2 + +int wildmatch(const char *pattern, const char *text, int flags); |