diff --git a/Makefile b/Makefile index 11e85a6396..731b6a8834 100644 --- a/Makefile +++ b/Makefile @@ -105,6 +105,9 @@ all:: # Define NO_FNMATCH_CASEFOLD if your fnmatch function doesn't have the # FNM_CASEFOLD GNU extension. # +# Define USE_WILDMATCH if you want to use Git's wildmatch +# implementation as fnmatch +# # Define NO_GECOS_IN_PWENT if you don't have pw_gecos in struct passwd # in the C library. # @@ -1225,6 +1228,9 @@ ifdef NO_FNMATCH_CASEFOLD COMPAT_OBJS += compat/fnmatch/fnmatch.o endif endif +ifdef USE_WILDMATCH + COMPAT_CFLAGS += -DUSE_WILDMATCH +endif ifdef NO_SETENV COMPAT_CFLAGS += -DNO_SETENV COMPAT_OBJS += compat/setenv.o diff --git a/dir.c b/dir.c index cf1e6b0082..57394e452e 100644 --- a/dir.c +++ b/dir.c @@ -685,7 +685,8 @@ int match_pathname(const char *pathname, int pathlen, } return wildmatch(pattern, name, - ignore_case ? FNM_CASEFOLD : 0) == 0; + WM_PATHNAME | (ignore_case ? WM_CASEFOLD : 0), + NULL) == 0; } /* diff --git a/git-compat-util.h b/git-compat-util.h index dab545e02e..cc2abeea0d 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -112,7 +112,9 @@ #include #include #include +#ifndef USE_WILDMATCH #include +#endif #include #include #include @@ -280,6 +282,17 @@ extern char *gitbasename(char *); #include "compat/bswap.h" +#ifdef USE_WILDMATCH +#include "wildmatch.h" +#define FNM_PATHNAME WM_PATHNAME +#define FNM_CASEFOLD WM_CASEFOLD +#define FNM_NOMATCH WM_NOMATCH +static inline int fnmatch(const char *pattern, const char *string, int flags) +{ + return wildmatch(pattern, string, flags, NULL); +} +#endif + /* General helper functions */ extern void vreportf(const char *prefix, const char *err, va_list params); extern void vwritef(int fd, const char *prefix, const char *err, va_list params); diff --git a/t/t3070-wildmatch.sh b/t/t3070-wildmatch.sh index af54c83111..4c37057ddf 100755 --- a/t/t3070-wildmatch.sh +++ b/t/t3070-wildmatch.sh @@ -29,6 +29,18 @@ match() { fi } +pathmatch() { + if [ $1 = 1 ]; then + test_expect_success "pathmatch: match '$2' '$3'" " + test-wildmatch pathmatch '$2' '$3' + " + else + test_expect_success "pathmatch: no match '$2' '$3'" " + ! test-wildmatch pathmatch '$2' '$3' + " + fi +} + # Basic wildmat features match 1 1 foo foo match 0 0 foo bar @@ -191,5 +203,36 @@ match 1 1 'XXX/adobe/courier/bold/o/normal//12/120/75/75/m/70/iso8859/1' 'XXX/*/ 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' +match 0 x foo '*/*/*' +match 0 x foo/bar '*/*/*' +match 1 x foo/bba/arr '*/*/*' +match 0 x foo/bb/aa/rr '*/*/*' +match 1 x foo/bb/aa/rr '**/**/**' +match 1 x abcXdefXghi '*X*i' +match 0 x ab/cXd/efXg/hi '*X*i' +match 1 x ab/cXd/efXg/hi '*/*X*/*/*i' +match 1 x ab/cXd/efXg/hi '**/*X*/**/*i' + +pathmatch 1 foo foo +pathmatch 0 foo fo +pathmatch 1 foo/bar foo/bar +pathmatch 1 foo/bar 'foo/*' +pathmatch 1 foo/bba/arr 'foo/*' +pathmatch 1 foo/bba/arr 'foo/**' +pathmatch 1 foo/bba/arr 'foo*' +pathmatch 1 foo/bba/arr 'foo**' +pathmatch 1 foo/bba/arr 'foo/*arr' +pathmatch 1 foo/bba/arr 'foo/**arr' +pathmatch 0 foo/bba/arr 'foo/*z' +pathmatch 0 foo/bba/arr 'foo/**z' +pathmatch 1 foo/bar 'foo?bar' +pathmatch 1 foo/bar 'foo[/]bar' +pathmatch 0 foo '*/*/*' +pathmatch 0 foo/bar '*/*/*' +pathmatch 1 foo/bba/arr '*/*/*' +pathmatch 1 foo/bb/aa/rr '*/*/*' +pathmatch 1 abcXdefXghi '*X*i' +pathmatch 1 ab/cXd/efXg/hi '*/*X*/*/*i' +pathmatch 1 ab/cXd/efXg/hi '*Xg*i' test_done diff --git a/test-wildmatch.c b/test-wildmatch.c index e384c8edb1..a3e2643fbc 100644 --- a/test-wildmatch.c +++ b/test-wildmatch.c @@ -1,9 +1,85 @@ +#ifdef USE_WILDMATCH +#undef USE_WILDMATCH /* We need real fnmatch implementation here */ +#endif #include "cache.h" #include "wildmatch.h" +static int perf(int ac, char **av) +{ + struct timeval tv1, tv2; + struct stat st; + int fd, i, n, flags1 = 0, flags2 = 0; + char *buffer, *p; + uint32_t usec1, usec2; + const char *lang; + const char *file = av[0]; + const char *pattern = av[1]; + + lang = getenv("LANG"); + if (lang && strcmp(lang, "C")) + die("Please test it on C locale."); + + if ((fd = open(file, O_RDONLY)) == -1 || fstat(fd, &st)) + die_errno("file open"); + + buffer = xmalloc(st.st_size + 2); + if (read(fd, buffer, st.st_size) != st.st_size) + die_errno("read"); + + buffer[st.st_size] = '\0'; + buffer[st.st_size + 1] = '\0'; + for (i = 0; i < st.st_size; i++) + if (buffer[i] == '\n') + buffer[i] = '\0'; + + n = atoi(av[2]); + if (av[3] && !strcmp(av[3], "pathname")) { + flags1 = WM_PATHNAME; + flags2 = FNM_PATHNAME; + } + + gettimeofday(&tv1, NULL); + for (i = 0; i < n; i++) { + for (p = buffer; *p; p += strlen(p) + 1) + wildmatch(pattern, p, flags1, NULL); + } + gettimeofday(&tv2, NULL); + + usec1 = (uint32_t)tv2.tv_sec * 1000000 + tv2.tv_usec; + usec1 -= (uint32_t)tv1.tv_sec * 1000000 + tv1.tv_usec; + printf("wildmatch %ds %dus\n", + (int)(usec1 / 1000000), + (int)(usec1 % 1000000)); + + gettimeofday(&tv1, NULL); + for (i = 0; i < n; i++) { + for (p = buffer; *p; p += strlen(p) + 1) + fnmatch(pattern, p, flags2); + } + gettimeofday(&tv2, NULL); + + usec2 = (uint32_t)tv2.tv_sec * 1000000 + tv2.tv_usec; + usec2 -= (uint32_t)tv1.tv_sec * 1000000 + tv1.tv_usec; + if (usec2 > usec1) + printf("fnmatch %ds %dus or %.2f%% slower\n", + (int)((usec2 - usec1) / 1000000), + (int)((usec2 - usec1) % 1000000), + (float)(usec2 - usec1) / usec1 * 100); + else + printf("fnmatch %ds %dus or %.2f%% faster\n", + (int)((usec1 - usec2) / 1000000), + (int)((usec1 - usec2) % 1000000), + (float)(usec1 - usec2) / usec1 * 100); + return 0; +} + int main(int argc, char **argv) { int i; + + if (!strcmp(argv[1], "perf")) + return perf(argc - 2, argv + 2); + for (i = 2; i < argc; i++) { if (argv[i][0] == '/') die("Forward slash is not allowed at the beginning of the\n" @@ -12,9 +88,11 @@ int main(int argc, char **argv) argv[i] += 3; } if (!strcmp(argv[1], "wildmatch")) - return !!wildmatch(argv[3], argv[2], 0); + return !!wildmatch(argv[3], argv[2], WM_PATHNAME, NULL); else if (!strcmp(argv[1], "iwildmatch")) - return !!wildmatch(argv[3], argv[2], FNM_CASEFOLD); + return !!wildmatch(argv[3], argv[2], WM_PATHNAME | WM_CASEFOLD, NULL); + else if (!strcmp(argv[1], "pathmatch")) + return !!wildmatch(argv[3], argv[2], 0, NULL); else if (!strcmp(argv[1], "fnmatch")) return !!fnmatch(argv[3], argv[2], FNM_PATHNAME); else diff --git a/wildmatch.c b/wildmatch.c index 2d3ed84364..7192bdc1b8 100644 --- a/wildmatch.c +++ b/wildmatch.c @@ -18,9 +18,6 @@ typedef unsigned char uchar; #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) @@ -55,7 +52,7 @@ typedef unsigned char uchar; #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) +static int dowild(const uchar *p, const uchar *text, unsigned int flags) { uchar p_ch; const uchar *pattern = p; @@ -64,10 +61,10 @@ static int dowild(const uchar *p, const uchar *text, int force_lower_case) 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)) + return WM_ABORT_ALL; + if ((flags & WM_CASEFOLD) && ISUPPER(t_ch)) t_ch = tolower(t_ch); - if (force_lower_case && ISUPPER(p_ch)) + if ((flags & WM_CASEFOLD) && ISUPPER(p_ch)) p_ch = tolower(p_ch); switch (p_ch) { case '\\': @@ -77,18 +74,21 @@ static int dowild(const uchar *p, const uchar *text, int force_lower_case) /* FALLTHROUGH */ default: if (t_ch != p_ch) - return NOMATCH; + return WM_NOMATCH; continue; case '?': /* Match anything but '/'. */ - if (t_ch == '/') - return NOMATCH; + if ((flags & WM_PATHNAME) && t_ch == '/') + return WM_NOMATCH; continue; case '*': if (*++p == '*') { const uchar *prev_p = p - 2; while (*++p == '*') {} - if ((prev_p < pattern || *prev_p == '/') && + if (!(flags & WM_PATHNAME)) + /* without WM_PATHNAME, '*' == '**' */ + match_slash = 1; + else if ((prev_p < pattern || *prev_p == '/') && (*p == '\0' || *p == '/' || (p[0] == '\\' && p[1] == '/'))) { /* @@ -101,135 +101,172 @@ static int dowild(const uchar *p, const uchar *text, int force_lower_case) * both foo/bar and foo/a/bar. */ if (p[0] == '/' && - dowild(p + 1, text, force_lower_case) == MATCH) - return MATCH; - match_slash = TRUE; + dowild(p + 1, text, flags) == WM_MATCH) + return WM_MATCH; + match_slash = 1; } else - return ABORT_MALFORMED; + return WM_ABORT_MALFORMED; } else - match_slash = FALSE; + /* without WM_PATHNAME, '*' == '**' */ + match_slash = flags & WM_PATHNAME ? 0 : 1; 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 WM_NOMATCH; } - return MATCH; + return WM_MATCH; + } else if (!match_slash && *p == '/') { + /* + * _one_ asterisk followed by a slash + * with WM_PATHNAME matches the next + * directory + */ + const char *slash = strchr((char*)text, '/'); + if (!slash) + return WM_NOMATCH; + text = (const uchar*)slash; + /* the slash is consumed by the top-level for loop */ + break; } while (1) { if (t_ch == '\0') break; - if ((matched = dowild(p, text, force_lower_case)) != NOMATCH) { - if (!match_slash || matched != ABORT_TO_STARSTAR) + /* + * Try to advance faster when an asterisk is + * followed by a literal. We know in this case + * that the the string before the literal + * must belong to "*". + * If match_slash is false, do not look past + * the first slash as it cannot belong to '*'. + */ + if (!is_glob_special(*p)) { + p_ch = *p; + if ((flags & WM_CASEFOLD) && ISUPPER(p_ch)) + p_ch = tolower(p_ch); + while ((t_ch = *text) != '\0' && + (match_slash || t_ch != '/')) { + if ((flags & WM_CASEFOLD) && ISUPPER(t_ch)) + t_ch = tolower(t_ch); + if (t_ch == p_ch) + break; + text++; + } + if (t_ch != p_ch) + return WM_NOMATCH; + } + if ((matched = dowild(p, text, flags)) != WM_NOMATCH) { + if (!match_slash || matched != WM_ABORT_TO_STARSTAR) return matched; } else if (!match_slash && t_ch == '/') - return ABORT_TO_STARSTAR; + return WM_ABORT_TO_STARSTAR; t_ch = *++text; } - return ABORT_ALL; + return WM_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; + /* Assign literal 1/0 because of "matched" comparison. */ + negated = p_ch == NEGATE_CLASS ? 1 : 0; if (negated) { /* Inverted character class. */ p_ch = *++p; } prev_ch = 0; - matched = FALSE; + matched = 0; do { if (!p_ch) - return ABORT_ALL; + return WM_ABORT_ALL; if (p_ch == '\\') { p_ch = *++p; if (!p_ch) - return ABORT_ALL; + return WM_ABORT_ALL; if (t_ch == p_ch) - matched = TRUE; + matched = 1; } 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; + return WM_ABORT_ALL; } if (t_ch <= p_ch && t_ch >= prev_ch) - matched = TRUE; + matched = 1; 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; + return WM_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; + matched = 1; continue; } if (CC_EQ(s,i, "alnum")) { if (ISALNUM(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "alpha")) { if (ISALPHA(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "blank")) { if (ISBLANK(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "cntrl")) { if (ISCNTRL(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "digit")) { if (ISDIGIT(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "graph")) { if (ISGRAPH(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "lower")) { if (ISLOWER(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "print")) { if (ISPRINT(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "punct")) { if (ISPUNCT(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "space")) { if (ISSPACE(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "upper")) { if (ISUPPER(t_ch)) - matched = TRUE; + matched = 1; } else if (CC_EQ(s,i, "xdigit")) { if (ISXDIGIT(t_ch)) - matched = TRUE; + matched = 1; } else /* malformed [:class:] string */ - return ABORT_ALL; + return WM_ABORT_ALL; p_ch = 0; /* This makes "prev_ch" get set to 0. */ } else if (t_ch == p_ch) - matched = TRUE; + matched = 1; } while (prev_ch = p_ch, (p_ch = *++p) != ']'); - if (matched == negated || t_ch == '/') - return NOMATCH; + if (matched == negated || + ((flags & WM_PATHNAME) && t_ch == '/')) + return WM_NOMATCH; continue; } } - return *text ? NOMATCH : MATCH; + return *text ? WM_NOMATCH : WM_MATCH; } /* Match the "pattern" against the "text" string. */ -int wildmatch(const char *pattern, const char *text, int flags) +int wildmatch(const char *pattern, const char *text, + unsigned int flags, struct wildopts *wo) { - return dowild((const uchar*)pattern, (const uchar*)text, - flags & FNM_CASEFOLD ? 1 :0); + return dowild((const uchar*)pattern, (const uchar*)text, flags); } diff --git a/wildmatch.h b/wildmatch.h index 984a38cdc2..4090c8f4bb 100644 --- a/wildmatch.h +++ b/wildmatch.h @@ -1,9 +1,18 @@ -/* wildmatch.h */ +#ifndef WILDMATCH_H +#define WILDMATCH_H -#define ABORT_MALFORMED 2 -#define NOMATCH 1 -#define MATCH 0 -#define ABORT_ALL -1 -#define ABORT_TO_STARSTAR -2 +#define WM_CASEFOLD 1 +#define WM_PATHNAME 2 -int wildmatch(const char *pattern, const char *text, int flags); +#define WM_ABORT_MALFORMED 2 +#define WM_NOMATCH 1 +#define WM_MATCH 0 +#define WM_ABORT_ALL -1 +#define WM_ABORT_TO_STARSTAR -2 + +struct wildopts; + +int wildmatch(const char *pattern, const char *text, + unsigned int flags, + struct wildopts *wo); +#endif