Browse Source
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: Makefilemaint
Junio C Hamano
12 years ago
13 changed files with 564 additions and 9 deletions
@ -0,0 +1,195 @@
@@ -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 |
||||
@ -0,0 +1,22 @@
@@ -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; |
||||
} |
||||
@ -0,0 +1,235 @@
@@ -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); |
||||
} |
||||
Loading…
Reference in new issue