grep/icase: avoid kwsset when -F is specified
Similar to the previous commit, we can't use kws on icase search outside ascii range. But we can't simply pass the pattern to regcomp/pcre like the previous commit because it may contain regex special characters, so we need to quote the regex first. To avoid misquote traps that could lead to undefined behavior, we always stick to basic regex engine in this case. We don't need fancy features for grepping a literal string anyway. basic_regex_quote_buf() assumes that if the pattern is in a multibyte encoding, ascii chars must be unambiguously encoded as single bytes. This is true at least for UTF-8. For others, let's wait until people yell up. Chances are nobody uses multibyte, non utf-8 charsets anymore. Noticed-by: Plamen Totev <plamen.totev@abv.bg> Helped-by: René Scharfe <l.s.r@web.de> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Nguyễn Thái Ngọc Duy committed
Jun 25, 2016 at 07:22 UTC
793dc676e08394ed15bffe0ed66606ff9ced1c6a
4 files changed
+108
-1
grep.c
+44
-1
@@ -5,6 +5,7 @@
5
#include "diff.h"
6
#include "diffcore.h"
7
#include "commit.h"
8
+#include "quote.h"
9
10
static int grep_source_load(struct grep_source *gs);
11
static int grep_source_is_binary(struct grep_source *gs);
@@ -397,6 +398,28 @@ static int is_fixed(const char *s, size_t len)
398
return 1;
399
}
400
401
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
402
+{
403
+ struct strbuf sb = STRBUF_INIT;
404
+ int err;
405
+ int regflags;
406
+
407
+ basic_regex_quote_buf(&sb, p->pattern);
408
+ regflags = opt->regflags & ~REG_EXTENDED;
409
+ if (opt->ignore_case)
410
+ regflags |= REG_ICASE;
411
+ err = regcomp(&p->regexp, sb.buf, regflags);
412
+ if (opt->debug)
413
+ fprintf(stderr, "fixed %s\n", sb.buf);
414
+ strbuf_release(&sb);
415
+ if (err) {
416
+ char errbuf[1024];
417
+ regerror(err, &p->regexp, errbuf, sizeof(errbuf));
418
+ regfree(&p->regexp);
419
+ compile_regexp_failed(p, errbuf);
420
+ }
421
+}
422
+
423
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
424
{
425
int icase, ascii_only;
@@ -407,8 +430,20 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
430
icase = opt->regflags & REG_ICASE || p->ignore_case;
431
ascii_only = !has_non_ascii(p->pattern);
432
433
+ /*
434
+ * Even when -F (fixed) asks us to do a non-regexp search, we
435
+ * may not be able to correctly case-fold when -i
436
+ * (ignore-case) is asked (in which case, we'll synthesize a
437
+ * regexp to match the pattern that matches regexp special
438
+ * characters literally, while ignoring case differences). On
439
+ * the other hand, even without -F, if the pattern does not
440
+ * have any regexp special characters and there is no need for
441
+ * case-folding search, we can internally turn it into a
442
+ * simple string match using kws. p->fixed tells us if we
443
+ * want to use kws.
444
+ */
445
if (opt->fixed)
411
- p->fixed = 1;
446
+ p->fixed = !icase || ascii_only;
447
else if ((!icase || ascii_only) &&
448
is_fixed(p->pattern, p->patternlen))
449
p->fixed = 1;
@@ -423,6 +458,14 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
458
kwsincr(p->kws, p->pattern, p->patternlen);
459
kwsprep(p->kws);
460
return;
461
+ } else if (opt->fixed) {
462
+ /*
463
+ * We come here when the pattern has the non-ascii
464
+ * characters we cannot case-fold, and asked to
465
+ * ignore-case.
466
+ */
467
+ compile_fixed_regexp(p, opt);
468
+ return;
469
}
470
471
if (opt->pcre) {
quote.c
+37
@@ -440,3 +440,40 @@ void tcl_quote_buf(struct strbuf *sb, const char *src)
440
}
441
strbuf_addch(sb, '"');
442
}
443
+
444
+void basic_regex_quote_buf(struct strbuf *sb, const char *src)
445
+{
446
+ char c;
447
+
448
+ if (*src == '^') {
449
+ /* only beginning '^' is special and needs quoting */
450
+ strbuf_addch(sb, '\\');
451
+ strbuf_addch(sb, *src++);
452
+ }
453
+ if (*src == '*')
454
+ /* beginning '*' is not special, no quoting */
455
+ strbuf_addch(sb, *src++);
456
+
457
+ while ((c = *src++)) {
458
+ switch (c) {
459
+ case '[':
460
+ case '.':
461
+ case '\\':
462
+ case '*':
463
+ strbuf_addch(sb, '\\');
464
+ strbuf_addch(sb, c);
465
+ break;
466
+
467
+ case '$':
468
+ /* only the end '$' is special and needs quoting */
469
+ if (*src == '\0')
470
+ strbuf_addch(sb, '\\');
471
+ strbuf_addch(sb, c);
472
+ break;
473
+
474
+ default:
475
+ strbuf_addch(sb, c);
476
+ break;
477
+ }
478
+ }
479
+}
quote.h
+1
@@ -67,5 +67,6 @@ extern char *quote_path_relative(const char *in, const char *prefix,
67
extern void perl_quote_buf(struct strbuf *sb, const char *src);
68
extern void python_quote_buf(struct strbuf *sb, const char *src);
69
extern void tcl_quote_buf(struct strbuf *sb, const char *src);
70
+extern void basic_regex_quote_buf(struct strbuf *sb, const char *src);
71
72
#endif
t/t7812-grep-icase-non-ascii.sh
+26
@@ -20,4 +20,30 @@ test_expect_success REGEX_LOCALE 'grep literal string, no -F' '
20
git grep -i "TILRAUN: HALLÓ HEIMUR!"
21
'
22
23
+test_expect_success REGEX_LOCALE 'grep literal string, with -F' '
24
+ git grep --debug -i -F "TILRAUN: Halló Heimur!" 2>&1 >/dev/null |
25
+ grep fixed >debug1 &&
26
+ test_write_lines "fixed TILRAUN: Halló Heimur!" >expect1 &&
27
+ test_cmp expect1 debug1 &&
28
+
29
+ git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!" 2>&1 >/dev/null |
30
+ grep fixed >debug2 &&
31
+ test_write_lines "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 &&
32
+ test_cmp expect2 debug2
33
+'
34
+
35
+test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
36
+ test_write_lines "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file &&
37
+
38
+ git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null |
39
+ grep fixed >debug1 &&
40
+ test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 &&
41
+ test_cmp expect1 debug1 &&
42
+
43
+ git grep --debug -i -F "^*TILR^AUN:.* \\HALLÓ \$HE[]IMUR!\$" 2>&1 >/dev/null |
44
+ grep fixed >debug2 &&
45
+ test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
46
+ test_cmp expect2 debug2
47
+'
48
+
49
test_done