From: "Ævar Arnfjörð Bjarmason" <avarab@gmail.com>
To: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Cc: git@vger.kernel.org, Junio C Hamano <gitster@pobox.com>,
Wayne Davison <wayned@samba.org>
Subject: Re: [PATCH 1/5] Import wildmatch from rsync
Date: Tue, 2 Oct 2012 16:07:00 +0200 [thread overview]
Message-ID: <CACBZZX6CLZAcUG2GjBt4brF9dGr1Zvj1HMTV=U-AXFZhzR=39Q@mail.gmail.com> (raw)
In-Reply-To: <1348658741-8146-2-git-send-email-pclouds@gmail.com>
On Wed, Sep 26, 2012 at 1:25 PM, Nguyễn Thái Ngọc Duy <pclouds@gmail.com> wrote:
> These files are from rsync.git commit
> f92f5b166e3019db42bc7fe1aa2f1a9178cd215d, which was the last commit
> before rsync turned GPL-3. All files are imported as-is and
> no-op. Adaptation is done in a separate patch.
Perhaps Wayne Davison (added to CC) wouldn't mind giving us permission
to use the subsequent changes to these files under the GPLv2?
rsync.git $ git --no-pager log --pretty="%h %an %s\n" --reverse
f92f5b166e3019db42bc7fe1aa2f1a9178cd215d.. -- '*wild*'
4fd842f Wayne Davison Switching to GPL 3.\n
8e41b68 Wayne Davison Tweaking the license text a bit more.\n
d3d07a5 Wayne Davison Include 2008 in the copyright years.\n
adc2476 Wayne Davison Output numbers in 3-digit groups by default
(e.g. 1,234,567). Also improved the human-readable output functions,
including adding the ability to output negative numbers.\n
b3bf9b9 Wayne Davison Update the copyright year.\n
fd91c3b Wayne Davison Fix two unused-variable compiler warnings.\n
>
> rsync.git -> git.git
> lib/wildmatch.[ch] wildmatch.[ch]
> wildtest.c test-wildmatch.c
> wildtest.txt t/t3070/wildtest.txt
>
> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> ---
> t/t3070/wildtest.txt | 165 +++++++++++++++++++++++
> test-wildmatch.c | 222 +++++++++++++++++++++++++++++++
> wildmatch.c | 368 +++++++++++++++++++++++++++++++++++++++++++++++++++
> wildmatch.h | 6 +
> 4 files changed, 761 insertions(+)
> create mode 100644 t/t3070/wildtest.txt
> create mode 100644 test-wildmatch.c
> create mode 100644 wildmatch.c
> create mode 100644 wildmatch.h
>
> diff --git a/t/t3070/wildtest.txt b/t/t3070/wildtest.txt
> new file mode 100644
> index 0000000..42c1678
> --- /dev/null
> +++ b/t/t3070/wildtest.txt
> @@ -0,0 +1,165 @@
> +# Input is in the following format (all items white-space separated):
> +#
> +# The first two items are 1 or 0 indicating if the wildmat call is expected to
> +# succeed and if fnmatch works the same way as wildmat, respectively. After
> +# that is a text string for the match, and a pattern string. Strings can be
> +# quoted (if desired) in either double or single quotes, as well as backticks.
> +#
> +# MATCH FNMATCH_SAME "text to match" 'pattern to use'
> +
> +# Basic wildmat features
> +1 1 foo foo
> +0 1 foo bar
> +1 1 '' ""
> +1 1 foo ???
> +0 1 foo ??
> +1 1 foo *
> +1 1 foo f*
> +0 1 foo *f
> +1 1 foo *foo*
> +1 1 foobar *ob*a*r*
> +1 1 aaaaaaabababab *ab
> +1 1 foo* foo\*
> +0 1 foobar foo\*bar
> +1 1 f\oo f\\oo
> +1 1 ball *[al]?
> +0 1 ten [ten]
> +1 1 ten **[!te]
> +0 1 ten **[!ten]
> +1 1 ten t[a-g]n
> +0 1 ten t[!a-g]n
> +1 1 ton t[!a-g]n
> +1 1 ton t[^a-g]n
> +1 1 a]b a[]]b
> +1 1 a-b a[]-]b
> +1 1 a]b a[]-]b
> +0 1 aab a[]-]b
> +1 1 aab a[]a-]b
> +1 1 ] ]
> +
> +# Extended slash-matching features
> +0 1 foo/baz/bar foo*bar
> +1 1 foo/baz/bar foo**bar
> +0 1 foo/bar foo?bar
> +0 1 foo/bar foo[/]bar
> +0 1 foo/bar f[^eiu][^eiu][^eiu][^eiu][^eiu]r
> +1 1 foo-bar f[^eiu][^eiu][^eiu][^eiu][^eiu]r
> +0 1 foo **/foo
> +1 1 /foo **/foo
> +1 1 bar/baz/foo **/foo
> +0 1 bar/baz/foo */foo
> +0 0 foo/bar/baz **/bar*
> +1 1 deep/foo/bar/baz **/bar/*
> +0 1 deep/foo/bar/baz/ **/bar/*
> +1 1 deep/foo/bar/baz/ **/bar/**
> +0 1 deep/foo/bar **/bar/*
> +1 1 deep/foo/bar/ **/bar/**
> +1 1 foo/bar/baz **/bar**
> +1 1 foo/bar/baz/x */bar/**
> +0 0 deep/foo/bar/baz/x */bar/**
> +1 1 deep/foo/bar/baz/x **/bar/*/*
> +
> +# Various additional tests
> +0 1 acrt a[c-c]st
> +1 1 acrt a[c-c]rt
> +0 1 ] [!]-]
> +1 1 a [!]-]
> +0 1 '' \
> +0 1 \ \
> +0 1 /\ */\
> +1 1 /\ */\\
> +1 1 foo foo
> +1 1 @foo @foo
> +0 1 foo @foo
> +1 1 [ab] \[ab]
> +1 1 [ab] [[]ab]
> +1 1 [ab] [[:]ab]
> +0 1 [ab] [[::]ab]
> +1 1 [ab] [[:digit]ab]
> +1 1 [ab] [\[:]ab]
> +1 1 ?a?b \??\?b
> +1 1 abc \a\b\c
> +0 1 foo ''
> +1 1 foo/bar/baz/to **/t[o]
> +
> +# Character class tests
> +1 1 a1B [[:alpha:]][[:digit:]][[:upper:]]
> +0 1 a [[:digit:][:upper:][:space:]]
> +1 1 A [[:digit:][:upper:][:space:]]
> +1 1 1 [[:digit:][:upper:][:space:]]
> +0 1 1 [[:digit:][:upper:][:spaci:]]
> +1 1 ' ' [[:digit:][:upper:][:space:]]
> +0 1 . [[:digit:][:upper:][:space:]]
> +1 1 . [[:digit:][:punct:][:space:]]
> +1 1 5 [[:xdigit:]]
> +1 1 f [[:xdigit:]]
> +1 1 D [[:xdigit:]]
> +1 1 _ [[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]
> +#1 1 … [^[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]
> +1 1 [^[:alnum:][:alpha:][:blank:][:digit:][:graph:][:lower:][:print:][:punct:][:space:][:upper:][:xdigit:]]
> +1 1 . [^[:alnum:][:alpha:][:blank:][:cntrl:][:digit:][:lower:][:space:][:upper:][:xdigit:]]
> +1 1 5 [a-c[:digit:]x-z]
> +1 1 b [a-c[:digit:]x-z]
> +1 1 y [a-c[:digit:]x-z]
> +0 1 q [a-c[:digit:]x-z]
> +
> +# Additional tests, including some malformed wildmats
> +1 1 ] [\\-^]
> +0 1 [ [\\-^]
> +1 1 - [\-_]
> +1 1 ] [\]]
> +0 1 \] [\]]
> +0 1 \ [\]]
> +0 1 ab a[]b
> +0 1 a[]b a[]b
> +0 1 ab[ ab[
> +0 1 ab [!
> +0 1 ab [-
> +1 1 - [-]
> +0 1 - [a-
> +0 1 - [!a-
> +1 1 - [--A]
> +1 1 5 [--A]
> +1 1 ' ' '[ --]'
> +1 1 $ '[ --]'
> +1 1 - '[ --]'
> +0 1 0 '[ --]'
> +1 1 - [---]
> +1 1 - [------]
> +0 1 j [a-e-n]
> +1 1 - [a-e-n]
> +1 1 a [!------]
> +0 1 [ []-a]
> +1 1 ^ []-a]
> +0 1 ^ [!]-a]
> +1 1 [ [!]-a]
> +1 1 ^ [a^bc]
> +1 1 -b] [a-]b]
> +0 1 \ [\]
> +1 1 \ [\\]
> +0 1 \ [!\\]
> +1 1 G [A-\\]
> +0 1 aaabbb b*a
> +0 1 aabcaa *ba*
> +1 1 , [,]
> +1 1 , [\\,]
> +1 1 \ [\\,]
> +1 1 - [,-.]
> +0 1 + [,-.]
> +0 1 -.] [,-.]
> +1 1 2 [\1-\3]
> +1 1 3 [\1-\3]
> +0 1 4 [\1-\3]
> +1 1 \ [[-\]]
> +1 1 [ [[-\]]
> +1 1 ] [[-\]]
> +0 1 - [[-\]]
> +
> +# Test recursion and the abort code (use "wildtest -i" to see iteration counts)
> +1 1 -adobe-courier-bold-o-normal--12-120-75-75-m-70-iso8859-1 -*-*-*-*-*-*-12-*-*-*-m-*-*-*
> +0 1 -adobe-courier-bold-o-normal--12-120-75-75-X-70-iso8859-1 -*-*-*-*-*-*-12-*-*-*-m-*-*-*
> +0 1 -adobe-courier-bold-o-normal--12-120-75-75-/-70-iso8859-1 -*-*-*-*-*-*-12-*-*-*-m-*-*-*
> +1 1 /adobe/courier/bold/o/normal//12/120/75/75/m/70/iso8859/1 /*/*/*/*/*/*/12/*/*/*/m/*/*/*
> +0 1 /adobe/courier/bold/o/normal//12/120/75/75/X/70/iso8859/1 /*/*/*/*/*/*/12/*/*/*/m/*/*/*
> +1 1 abcd/abcdefg/abcdefghijk/abcdefghijklmnop.txt **/*a*b*g*n*t
> +0 1 abcd/abcdefg/abcdefghijk/abcdefghijklmnop.txtz **/*a*b*g*n*t
> diff --git a/test-wildmatch.c b/test-wildmatch.c
> new file mode 100644
> index 0000000..88585c2
> --- /dev/null
> +++ b/test-wildmatch.c
> @@ -0,0 +1,222 @@
> +/*
> + * Test suite for the wildmatch code.
> + *
> + * Copyright (C) 2003-2009 Wayne Davison
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 3 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License along
> + * with this program; if not, visit the http://fsf.org website.
> + */
> +
> +/*#define COMPARE_WITH_FNMATCH*/
> +
> +#define WILD_TEST_ITERATIONS
> +#include "lib/wildmatch.c"
> +
> +#include <popt.h>
> +
> +#ifdef COMPARE_WITH_FNMATCH
> +#include <fnmatch.h>
> +
> +int fnmatch_errors = 0;
> +#endif
> +
> +int wildmatch_errors = 0;
> +char number_separator = ',';
> +
> +typedef char bool;
> +
> +int output_iterations = 0;
> +int explode_mod = 0;
> +int empties_mod = 0;
> +int empty_at_start = 0;
> +int empty_at_end = 0;
> +
> +static struct poptOption long_options[] = {
> + /* longName, shortName, argInfo, argPtr, value, descrip, argDesc */
> + {"iterations", 'i', POPT_ARG_NONE, &output_iterations, 0, 0, 0},
> + {"empties", 'e', POPT_ARG_STRING, 0, 'e', 0, 0},
> + {"explode", 'x', POPT_ARG_INT, &explode_mod, 0, 0, 0},
> + {0,0,0,0, 0, 0, 0}
> +};
> +
> +/* match just at the start of string (anchored tests) */
> +static void
> +run_test(int line, bool matches,
> +#ifdef COMPARE_WITH_FNMATCH
> + bool same_as_fnmatch,
> +#endif
> + const char *text, const char *pattern)
> +{
> + bool matched;
> +#ifdef COMPARE_WITH_FNMATCH
> + bool fn_matched;
> + int flags = strstr(pattern, "**")? 0 : FNM_PATHNAME;
> +#endif
> +
> + if (explode_mod) {
> + char buf[MAXPATHLEN*2], *texts[MAXPATHLEN];
> + int pos = 0, cnt = 0, ndx = 0, len = strlen(text);
> +
> + if (empty_at_start)
> + texts[ndx++] = "";
> + /* An empty string must turn into at least one empty array item. */
> + while (1) {
> + texts[ndx] = buf + ndx * (explode_mod + 1);
> + strlcpy(texts[ndx++], text + pos, explode_mod + 1);
> + if (pos + explode_mod >= len)
> + break;
> + pos += explode_mod;
> + if (!(++cnt % empties_mod))
> + texts[ndx++] = "";
> + }
> + if (empty_at_end)
> + texts[ndx++] = "";
> + texts[ndx] = NULL;
> + matched = wildmatch_array(pattern, (const char**)texts, 0);
> + } else
> + matched = wildmatch(pattern, text);
> +#ifdef COMPARE_WITH_FNMATCH
> + fn_matched = !fnmatch(pattern, text, flags);
> +#endif
> + if (matched != matches) {
> + printf("wildmatch failure on line %d:\n %s\n %s\n expected %s match\n",
> + line, text, pattern, matches? "a" : "NO");
> + wildmatch_errors++;
> + }
> +#ifdef COMPARE_WITH_FNMATCH
> + if (fn_matched != (matches ^ !same_as_fnmatch)) {
> + printf("fnmatch disagreement on line %d:\n %s\n %s\n expected %s match\n",
> + line, text, pattern, matches ^ !same_as_fnmatch? "a" : "NO");
> + fnmatch_errors++;
> + }
> +#endif
> + if (output_iterations) {
> + printf("%d: \"%s\" iterations = %d\n", line, pattern,
> + wildmatch_iteration_count);
> + }
> +}
> +
> +int
> +main(int argc, char **argv)
> +{
> + char buf[2048], *s, *string[2], *end[2];
> + const char *arg;
> + FILE *fp;
> + int opt, line, i, flag[2];
> + poptContext pc = poptGetContext("wildtest", argc, (const char**)argv,
> + long_options, 0);
> +
> + while ((opt = poptGetNextOpt(pc)) != -1) {
> + switch (opt) {
> + case 'e':
> + arg = poptGetOptArg(pc);
> + empties_mod = atoi(arg);
> + if (strchr(arg, 's'))
> + empty_at_start = 1;
> + if (strchr(arg, 'e'))
> + empty_at_end = 1;
> + if (!explode_mod)
> + explode_mod = 1024;
> + break;
> + default:
> + fprintf(stderr, "%s: %s\n",
> + poptBadOption(pc, POPT_BADOPTION_NOALIAS),
> + poptStrerror(opt));
> + exit(1);
> + }
> + }
> +
> + if (explode_mod && !empties_mod)
> + empties_mod = 1024;
> +
> + argv = (char**)poptGetArgs(pc);
> + if (!argv || argv[1]) {
> + fprintf(stderr, "Usage: wildtest [OPTIONS] TESTFILE\n");
> + exit(1);
> + }
> +
> + if ((fp = fopen(*argv, "r")) == NULL) {
> + fprintf(stderr, "Unable to open %s\n", *argv);
> + exit(1);
> + }
> +
> + line = 0;
> + while (fgets(buf, sizeof buf, fp)) {
> + line++;
> + if (*buf == '#' || *buf == '\n')
> + continue;
> + for (s = buf, i = 0; i <= 1; i++) {
> + if (*s == '1')
> + flag[i] = 1;
> + else if (*s == '0')
> + flag[i] = 0;
> + else
> + flag[i] = -1;
> + if (*++s != ' ' && *s != '\t')
> + flag[i] = -1;
> + if (flag[i] < 0) {
> + fprintf(stderr, "Invalid flag syntax on line %d of %s:\n%s",
> + line, *argv, buf);
> + exit(1);
> + }
> + while (*++s == ' ' || *s == '\t') {}
> + }
> + for (i = 0; i <= 1; i++) {
> + if (*s == '\'' || *s == '"' || *s == '`') {
> + char quote = *s++;
> + string[i] = s;
> + while (*s && *s != quote) s++;
> + if (!*s) {
> + fprintf(stderr, "Unmatched quote on line %d of %s:\n%s",
> + line, *argv, buf);
> + exit(1);
> + }
> + end[i] = s;
> + }
> + else {
> + if (!*s || *s == '\n') {
> + fprintf(stderr, "Not enough strings on line %d of %s:\n%s",
> + line, *argv, buf);
> + exit(1);
> + }
> + string[i] = s;
> + while (*++s && *s != ' ' && *s != '\t' && *s != '\n') {}
> + end[i] = s;
> + }
> + while (*++s == ' ' || *s == '\t') {}
> + }
> + *end[0] = *end[1] = '\0';
> + run_test(line, flag[0],
> +#ifdef COMPARE_WITH_FNMATCH
> + flag[1],
> +#endif
> + string[0], string[1]);
> + }
> +
> + if (!wildmatch_errors)
> + fputs("No", stdout);
> + else
> + printf("%d", wildmatch_errors);
> + printf(" wildmatch error%s found.\n", wildmatch_errors == 1? "" : "s");
> +
> +#ifdef COMPARE_WITH_FNMATCH
> + if (!fnmatch_errors)
> + fputs("No", stdout);
> + else
> + printf("%d", fnmatch_errors);
> + printf(" fnmatch error%s found.\n", fnmatch_errors == 1? "" : "s");
> +
> +#endif
> +
> + return 0;
> +}
> diff --git a/wildmatch.c b/wildmatch.c
> new file mode 100644
> index 0000000..f3a1731
> --- /dev/null
> +++ b/wildmatch.c
> @@ -0,0 +1,368 @@
> +/*
> +** 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 "rsync.h"
> +
> +/* What character marks an inverted character class? */
> +#define NEGATE_CLASS '!'
> +#define NEGATE_CLASS2 '^'
> +
> +#define FALSE 0
> +#define TRUE 1
> +#define ABORT_ALL -1
> +#define ABORT_TO_STARSTAR -2
> +
> +#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))
> +
> +#ifdef WILD_TEST_ITERATIONS
> +int wildmatch_iteration_count;
> +#endif
> +
> +static int force_lower_case = 0;
> +
> +/* Match pattern "p" against the a virtually-joined string consisting
> + * of "text" and any strings in array "a". */
> +static int dowild(const uchar *p, const uchar *text, const uchar*const *a)
> +{
> + uchar p_ch;
> +
> +#ifdef WILD_TEST_ITERATIONS
> + wildmatch_iteration_count++;
> +#endif
> +
> + for ( ; (p_ch = *p) != '\0'; text++, p++) {
> + int matched, special;
> + uchar t_ch, prev_ch;
> + while ((t_ch = *text) == '\0') {
> + if (*a == NULL) {
> + if (p_ch != '*')
> + return ABORT_ALL;
> + break;
> + }
> + text = *a++;
> + }
> + if (force_lower_case && ISUPPER(t_ch))
> + t_ch = tolower(t_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 FALSE;
> + continue;
> + case '?':
> + /* Match anything but '/'. */
> + if (t_ch == '/')
> + return FALSE;
> + continue;
> + case '*':
> + if (*++p == '*') {
> + while (*++p == '*') {}
> + special = TRUE;
> + } else
> + special = FALSE;
> + if (*p == '\0') {
> + /* Trailing "**" matches everything. Trailing "*" matches
> + * only if there are no more slash characters. */
> + if (!special) {
> + do {
> + if (strchr((char*)text, '/') != NULL)
> + return FALSE;
> + } while ((text = *a++) != NULL);
> + }
> + return TRUE;
> + }
> + while (1) {
> + if (t_ch == '\0') {
> + if ((text = *a++) == NULL)
> + break;
> + t_ch = *text;
> + continue;
> + }
> + if ((matched = dowild(p, text, a)) != FALSE) {
> + if (!special || matched != ABORT_TO_STARSTAR)
> + return matched;
> + } else if (!special && 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. */
> + special = p_ch == NEGATE_CLASS? TRUE : FALSE;
> + if (special) {
> + /* 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 == special || t_ch == '/')
> + return FALSE;
> + continue;
> + }
> + }
> +
> + do {
> + if (*text)
> + return FALSE;
> + } while ((text = *a++) != NULL);
> +
> + return TRUE;
> +}
> +
> +/* Match literal string "s" against the a virtually-joined string consisting
> + * of "text" and any strings in array "a". */
> +static int doliteral(const uchar *s, const uchar *text, const uchar*const *a)
> +{
> + for ( ; *s != '\0'; text++, s++) {
> + while (*text == '\0') {
> + if ((text = *a++) == NULL)
> + return FALSE;
> + }
> + if (*text != *s)
> + return FALSE;
> + }
> +
> + do {
> + if (*text)
> + return FALSE;
> + } while ((text = *a++) != NULL);
> +
> + return TRUE;
> +}
> +
> +/* Return the last "count" path elements from the concatenated string.
> + * We return a string pointer to the start of the string, and update the
> + * array pointer-pointer to point to any remaining string elements. */
> +static const uchar *trailing_N_elements(const uchar*const **a_ptr, int count)
> +{
> + const uchar*const *a = *a_ptr;
> + const uchar*const *first_a = a;
> +
> + while (*a)
> + a++;
> +
> + while (a != first_a) {
> + const uchar *s = *--a;
> + s += strlen((char*)s);
> + while (--s >= *a) {
> + if (*s == '/' && !--count) {
> + *a_ptr = a+1;
> + return s+1;
> + }
> + }
> + }
> +
> + if (count == 1) {
> + *a_ptr = a+1;
> + return *a;
> + }
> +
> + return NULL;
> +}
> +
> +/* Match the "pattern" against the "text" string. */
> +int wildmatch(const char *pattern, const char *text)
> +{
> + static const uchar *nomore[1]; /* A NULL pointer. */
> +#ifdef WILD_TEST_ITERATIONS
> + wildmatch_iteration_count = 0;
> +#endif
> + return dowild((const uchar*)pattern, (const uchar*)text, nomore) == TRUE;
> +}
> +
> +/* Match the "pattern" against the forced-to-lower-case "text" string. */
> +int iwildmatch(const char *pattern, const char *text)
> +{
> + static const uchar *nomore[1]; /* A NULL pointer. */
> + int ret;
> +#ifdef WILD_TEST_ITERATIONS
> + wildmatch_iteration_count = 0;
> +#endif
> + force_lower_case = 1;
> + ret = dowild((const uchar*)pattern, (const uchar*)text, nomore) == TRUE;
> + force_lower_case = 0;
> + return ret;
> +}
> +
> +/* Match pattern "p" against the a virtually-joined string consisting
> + * of all the pointers in array "texts" (which has a NULL pointer at the
> + * end). The int "where" can be 0 (normal matching), > 0 (match only
> + * the trailing N slash-separated filename components of "texts"), or < 0
> + * (match the "pattern" at the start or after any slash in "texts"). */
> +int wildmatch_array(const char *pattern, const char*const *texts, int where)
> +{
> + const uchar *p = (const uchar*)pattern;
> + const uchar*const *a = (const uchar*const*)texts;
> + const uchar *text;
> + int matched;
> +
> +#ifdef WILD_TEST_ITERATIONS
> + wildmatch_iteration_count = 0;
> +#endif
> +
> + if (where > 0)
> + text = trailing_N_elements(&a, where);
> + else
> + text = *a++;
> + if (!text)
> + return FALSE;
> +
> + if ((matched = dowild(p, text, a)) != TRUE && where < 0
> + && matched != ABORT_ALL) {
> + while (1) {
> + if (*text == '\0') {
> + if ((text = (uchar*)*a++) == NULL)
> + return FALSE;
> + continue;
> + }
> + if (*text++ == '/' && (matched = dowild(p, text, a)) != FALSE
> + && matched != ABORT_TO_STARSTAR)
> + break;
> + }
> + }
> + return matched == TRUE;
> +}
> +
> +/* Match literal string "s" against the a virtually-joined string consisting
> + * of all the pointers in array "texts" (which has a NULL pointer at the
> + * end). The int "where" can be 0 (normal matching), or > 0 (match
> + * only the trailing N slash-separated filename components of "texts"). */
> +int litmatch_array(const char *string, const char*const *texts, int where)
> +{
> + const uchar *s = (const uchar*)string;
> + const uchar*const *a = (const uchar* const*)texts;
> + const uchar *text;
> +
> + if (where > 0)
> + text = trailing_N_elements(&a, where);
> + else
> + text = *a++;
> + if (!text)
> + return FALSE;
> +
> + return doliteral(s, text, a) == TRUE;
> +}
> diff --git a/wildmatch.h b/wildmatch.h
> new file mode 100644
> index 0000000..e7f1a35
> --- /dev/null
> +++ b/wildmatch.h
> @@ -0,0 +1,6 @@
> +/* wildmatch.h */
> +
> +int wildmatch(const char *pattern, const char *text);
> +int iwildmatch(const char *pattern, const char *text);
> +int wildmatch_array(const char *pattern, const char*const *texts, int where);
> +int litmatch_array(const char *string, const char*const *texts, int where);
> --
> 1.7.12.1.406.g6ab07c4
>
> --
> To unsubscribe from this list: send the line "unsubscribe git" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2012-10-02 14:07 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-26 11:25 [PATCH 0/5] wildmatch series update Nguyễn Thái Ngọc Duy
2012-09-26 11:25 ` [PATCH 1/5] Import wildmatch from rsync Nguyễn Thái Ngọc Duy
2012-10-02 14:07 ` Ævar Arnfjörð Bjarmason [this message]
[not found] ` <CAHSx_SsnSAV7SVLRnAFvS7AmdRgPkPX3NEM+6HTjfW5r8hXeig@mail.gmail.com>
2012-10-02 18:26 ` Junio C Hamano
2012-09-26 11:25 ` [PATCH 2/5] compat/wildmatch: remove static variable force_lower_case Nguyễn Thái Ngọc Duy
2012-09-26 11:25 ` [PATCH 3/5] compat/wildmatch: fix case-insensitive matching Nguyễn Thái Ngọc Duy
2012-09-26 11:25 ` [PATCH 4/5] Integrate wildmatch to git Nguyễn Thái Ngọc Duy
2012-09-26 11:25 ` [PATCH 5/5] Support "**" in .gitignore and .gitattributes patterns using wildmatch() Nguyễn Thái Ngọc Duy
2012-09-27 18:08 ` [PATCH 0/5] wildmatch series update Junio C Hamano
-- strict thread matches above, loose matches on Subject: below --
2012-09-15 12:01 [PATCH 0/5] Support matching "**" in .gitattributes and .gitignore Nguyễn Thái Ngọc Duy
2012-09-15 12:02 ` [PATCH 1/5] Import wildmatch from rsync Nguyễn Thái Ngọc Duy
2012-09-16 6:49 ` Junio C Hamano
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CACBZZX6CLZAcUG2GjBt4brF9dGr1Zvj1HMTV=U-AXFZhzR=39Q@mail.gmail.com' \
--to=avarab@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=pclouds@gmail.com \
--cc=wayned@samba.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).