1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-18 07:46:11 +02:00

Merge branch 'nd/icase' into maint

"git grep -i" has been taught to fold case in non-ascii locales
correctly.

* nd/icase:
  grep.c: reuse "icase" variable
  diffcore-pickaxe: support case insensitive match on non-ascii
  diffcore-pickaxe: Add regcomp_or_die()
  grep/pcre: support utf-8
  gettext: add is_utf8_locale()
  grep/pcre: prepare locale-dependent tables for icase matching
  grep: rewrite an if/else condition to avoid duplicate expression
  grep/icase: avoid kwsset when -F is specified
  grep/icase: avoid kwsset on literal non-ascii strings
  test-regex: expose full regcomp() to the command line
  test-regex: isolate the bug test code
  grep: break down an "if" stmt in preparation for next changes
This commit is contained in:
Junio C Hamano 2016-07-28 11:26:03 -07:00
commit 6cbec0da47
11 changed files with 291 additions and 21 deletions

View File

@ -7,6 +7,8 @@
#include "diffcore.h"
#include "xdiff-interface.h"
#include "kwset.h"
#include "commit.h"
#include "quote.h"
typedef int (*pickaxe_fn)(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
@ -198,6 +200,18 @@ static void pickaxe(struct diff_queue_struct *q, struct diff_options *o,
*q = outq;
}
static void regcomp_or_die(regex_t *regex, const char *needle, int cflags)
{
int err = regcomp(regex, needle, cflags);
if (err) {
/* The POSIX.2 people are surely sick */
char errbuf[1024];
regerror(err, regex, errbuf, 1024);
regfree(regex);
die("invalid regex: %s", errbuf);
}
}
void diffcore_pickaxe(struct diff_options *o)
{
const char *needle = o->pickaxe;
@ -206,18 +220,19 @@ void diffcore_pickaxe(struct diff_options *o)
kwset_t kws = NULL;
if (opts & (DIFF_PICKAXE_REGEX | DIFF_PICKAXE_KIND_G)) {
int err;
int cflags = REG_EXTENDED | REG_NEWLINE;
if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE))
cflags |= REG_ICASE;
err = regcomp(&regex, needle, cflags);
if (err) {
/* The POSIX.2 people are surely sick */
char errbuf[1024];
regerror(err, &regex, errbuf, 1024);
regfree(&regex);
die("invalid regex: %s", errbuf);
}
regcomp_or_die(&regex, needle, cflags);
regexp = &regex;
} else if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE) &&
has_non_ascii(needle)) {
struct strbuf sb = STRBUF_INIT;
int cflags = REG_NEWLINE | REG_ICASE;
basic_regex_quote_buf(&sb, needle);
regcomp_or_die(&regex, sb.buf, cflags);
strbuf_release(&sb);
regexp = &regex;
} else {
kws = kwsalloc(DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE)

View File

@ -18,6 +18,8 @@
# endif
#endif
static const char *charset;
/*
* Guess the user's preferred languages from the value in LANGUAGE environment
* variable and LC_MESSAGES locale category if NO_GETTEXT is not defined.
@ -65,7 +67,6 @@ static int test_vsnprintf(const char *fmt, ...)
return ret;
}
static const char *charset;
static void init_gettext_charset(const char *domain)
{
/*
@ -172,8 +173,27 @@ int gettext_width(const char *s)
{
static int is_utf8 = -1;
if (is_utf8 == -1)
is_utf8 = !strcmp(charset, "UTF-8");
is_utf8 = is_utf8_locale();
return is_utf8 ? utf8_strwidth(s) : strlen(s);
}
#endif
int is_utf8_locale(void)
{
#ifdef NO_GETTEXT
if (!charset) {
const char *env = getenv("LC_ALL");
if (!env || !*env)
env = getenv("LC_CTYPE");
if (!env || !*env)
env = getenv("LANG");
if (!env)
env = "";
if (strchr(env, '.'))
env = strchr(env, '.') + 1;
charset = xstrdup(env);
}
#endif
return is_encoding_utf8(charset);
}

View File

@ -90,5 +90,6 @@ const char *Q_(const char *msgid, const char *plu, unsigned long n)
#endif
const char *get_preferred_languages(void);
extern int is_utf8_locale(void);
#endif

64
grep.c
View File

@ -4,6 +4,8 @@
#include "xdiff-interface.h"
#include "diff.h"
#include "diffcore.h"
#include "commit.h"
#include "quote.h"
static int grep_source_load(struct grep_source *gs);
static int grep_source_is_binary(struct grep_source *gs);
@ -322,11 +324,16 @@ static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
int erroffset;
int options = PCRE_MULTILINE;
if (opt->ignore_case)
if (opt->ignore_case) {
if (has_non_ascii(p->pattern))
p->pcre_tables = pcre_maketables();
options |= PCRE_CASELESS;
}
if (is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE_UTF8;
p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
NULL);
p->pcre_tables);
if (!p->pcre_regexp)
compile_regexp_failed(p, error);
@ -360,6 +367,7 @@ static void free_pcre_regexp(struct grep_pat *p)
{
pcre_free(p->pcre_regexp);
pcre_free(p->pcre_extra_info);
pcre_free((void *)p->pcre_tables);
}
#else /* !USE_LIBPCRE */
static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
@ -396,26 +404,68 @@ static int is_fixed(const char *s, size_t len)
return 1;
}
static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
{
struct strbuf sb = STRBUF_INIT;
int err;
int regflags;
basic_regex_quote_buf(&sb, p->pattern);
regflags = opt->regflags & ~REG_EXTENDED;
if (opt->ignore_case)
regflags |= REG_ICASE;
err = regcomp(&p->regexp, sb.buf, regflags);
if (opt->debug)
fprintf(stderr, "fixed %s\n", sb.buf);
strbuf_release(&sb);
if (err) {
char errbuf[1024];
regerror(err, &p->regexp, errbuf, sizeof(errbuf));
regfree(&p->regexp);
compile_regexp_failed(p, errbuf);
}
}
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
int icase, ascii_only;
int err;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
icase = opt->regflags & REG_ICASE || p->ignore_case;
ascii_only = !has_non_ascii(p->pattern);
/*
* Even when -F (fixed) asks us to do a non-regexp search, we
* may not be able to correctly case-fold when -i
* (ignore-case) is asked (in which case, we'll synthesize a
* regexp to match the pattern that matches regexp special
* characters literally, while ignoring case differences). On
* the other hand, even without -F, if the pattern does not
* have any regexp special characters and there is no need for
* case-folding search, we can internally turn it into a
* simple string match using kws. p->fixed tells us if we
* want to use kws.
*/
if (opt->fixed || is_fixed(p->pattern, p->patternlen))
p->fixed = 1;
p->fixed = !icase || ascii_only;
else
p->fixed = 0;
if (p->fixed) {
if (opt->regflags & REG_ICASE || p->ignore_case)
p->kws = kwsalloc(tolower_trans_tbl);
else
p->kws = kwsalloc(NULL);
p->kws = kwsalloc(icase ? tolower_trans_tbl : NULL);
kwsincr(p->kws, p->pattern, p->patternlen);
kwsprep(p->kws);
return;
} else if (opt->fixed) {
/*
* We come here when the pattern has the non-ascii
* characters we cannot case-fold, and asked to
* ignore-case.
*/
compile_fixed_regexp(p, opt);
return;
}
if (opt->pcre) {

1
grep.h
View File

@ -48,6 +48,7 @@ struct grep_pat {
regex_t regexp;
pcre *pcre_regexp;
pcre_extra *pcre_extra_info;
const unsigned char *pcre_tables;
kwset_t kws;
unsigned fixed:1;
unsigned ignore_case:1;

37
quote.c
View File

@ -453,3 +453,40 @@ void tcl_quote_buf(struct strbuf *sb, const char *src)
}
strbuf_addch(sb, '"');
}
void basic_regex_quote_buf(struct strbuf *sb, const char *src)
{
char c;
if (*src == '^') {
/* only beginning '^' is special and needs quoting */
strbuf_addch(sb, '\\');
strbuf_addch(sb, *src++);
}
if (*src == '*')
/* beginning '*' is not special, no quoting */
strbuf_addch(sb, *src++);
while ((c = *src++)) {
switch (c) {
case '[':
case '.':
case '\\':
case '*':
strbuf_addch(sb, '\\');
strbuf_addch(sb, c);
break;
case '$':
/* only the end '$' is special and needs quoting */
if (*src == '\0')
strbuf_addch(sb, '\\');
strbuf_addch(sb, c);
break;
default:
strbuf_addch(sb, c);
break;
}
}
}

View File

@ -70,5 +70,6 @@ extern char *quote_path_relative(const char *in, const char *prefix,
extern void perl_quote_buf(struct strbuf *sb, const char *src);
extern void python_quote_buf(struct strbuf *sb, const char *src);
extern void tcl_quote_buf(struct strbuf *sb, const char *src);
extern void basic_regex_quote_buf(struct strbuf *sb, const char *src);
#endif

View File

@ -1,6 +1,23 @@
#include "git-compat-util.h"
#include "gettext.h"
int main(int argc, char **argv)
struct reg_flag {
const char *name;
int flag;
};
static struct reg_flag reg_flags[] = {
{ "EXTENDED", REG_EXTENDED },
{ "NEWLINE", REG_NEWLINE },
{ "ICASE", REG_ICASE },
{ "NOTBOL", REG_NOTBOL },
#ifdef REG_STARTEND
{ "STARTEND", REG_STARTEND },
#endif
{ NULL, 0 }
};
static int test_regex_bug(void)
{
char *pat = "[^={} \t]+";
char *str = "={}\nfred";
@ -16,5 +33,43 @@ int main(int argc, char **argv)
if (m[0].rm_so == 3) /* matches '\n' when it should not */
die("regex bug confirmed: re-build git with NO_REGEX=1");
exit(0);
return 0;
}
int main(int argc, char **argv)
{
const char *pat;
const char *str;
int flags = 0;
regex_t r;
regmatch_t m[1];
if (argc == 2 && !strcmp(argv[1], "--bug"))
return test_regex_bug();
else if (argc < 3)
usage("test-regex --bug\n"
"test-regex <pattern> <string> [<options>]");
argv++;
pat = *argv++;
str = *argv++;
while (*argv) {
struct reg_flag *rf;
for (rf = reg_flags; rf->name; rf++)
if (!strcmp(*argv, rf->name)) {
flags |= rf->flag;
break;
}
if (!rf->name)
die("do not recognize %s", *argv);
argv++;
}
git_setup_gettext();
if (regcomp(&r, pat, flags))
die("failed regcomp() for pattern '%s'", pat);
if (regexec(&r, str, 1, m, 0))
return 1;
return 0;
}

View File

@ -31,7 +31,7 @@ test_expect_success 'git_mkstemps_mode does not fail if fd 0 is not open' '
test_expect_success 'check for a bug in the regex routines' '
# if this test fails, re-build git with NO_REGEX=1
test-regex
test-regex --bug
'
test_done

71
t/t7812-grep-icase-non-ascii.sh Executable file
View File

@ -0,0 +1,71 @@
#!/bin/sh
test_description='grep icase on non-English locales'
. ./lib-gettext.sh
test_expect_success GETTEXT_LOCALE 'setup' '
test_write_lines "TILRAUN: Halló Heimur!" >file &&
git add file &&
LC_ALL="$is_IS_locale" &&
export LC_ALL
'
test_have_prereq GETTEXT_LOCALE &&
test-regex "HALLÓ" "Halló" ICASE &&
test_set_prereq REGEX_LOCALE
test_expect_success REGEX_LOCALE 'grep literal string, no -F' '
git grep -i "TILRAUN: Halló Heimur!" &&
git grep -i "TILRAUN: HALLÓ HEIMUR!"
'
test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 icase' '
git grep --perl-regexp "TILRAUN: H.lló Heimur!" &&
git grep --perl-regexp -i "TILRAUN: H.lló Heimur!" &&
git grep --perl-regexp -i "TILRAUN: H.LLÓ HEIMUR!"
'
test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' '
test_write_lines "TILRAUN: Hallóó Heimur!" >file2 &&
git add file2 &&
git grep -l --perl-regexp "TILRAUN: H.lló+ Heimur!" >actual &&
echo file >expected &&
echo file2 >>expected &&
test_cmp expected actual
'
test_expect_success REGEX_LOCALE 'grep literal string, with -F' '
git grep --debug -i -F "TILRAUN: Halló Heimur!" 2>&1 >/dev/null |
grep fixed >debug1 &&
test_write_lines "fixed TILRAUN: Halló Heimur!" >expect1 &&
test_cmp expect1 debug1 &&
git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!" 2>&1 >/dev/null |
grep fixed >debug2 &&
test_write_lines "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 &&
test_cmp expect2 debug2
'
test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
test_write_lines "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file &&
git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null |
grep fixed >debug1 &&
test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 &&
test_cmp expect1 debug1 &&
git grep --debug -i -F "^*TILR^AUN:.* \\HALLÓ \$HE[]IMUR!\$" 2>&1 >/dev/null |
grep fixed >debug2 &&
test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
test_cmp expect2 debug2
'
test_expect_success REGEX_LOCALE 'pickaxe -i on non-ascii' '
git commit -m first &&
git log --format=%f -i -S"TILRAUN: HALLÓ HEIMUR!" >actual &&
echo first >expected &&
test_cmp expected actual
'
test_done

19
t/t7813-grep-icase-iso.sh Executable file
View File

@ -0,0 +1,19 @@
#!/bin/sh
test_description='grep icase on non-English locales'
. ./lib-gettext.sh
test_expect_success GETTEXT_ISO_LOCALE 'setup' '
printf "TILRAUN: Halló Heimur!" >file &&
git add file &&
LC_ALL="$is_IS_iso_locale" &&
export LC_ALL
'
test_expect_success GETTEXT_ISO_LOCALE,LIBPCRE 'grep pcre string' '
git grep --perl-regexp -i "TILRAUN: H.lló Heimur!" &&
git grep --perl-regexp -i "TILRAUN: H.LLÓ HEIMUR!"
'
test_done