grep: support newline separated pattern list

Currently, patterns that contain newline characters don't match anything
when given to git grep.  Regular grep(1) interprets patterns as lists of
newline separated search strings instead.

Implement this functionality by creating and inserting extra grep_pat
structures for patterns consisting of multiple lines when appending to
the pattern lists.  For simplicity, all pattern strings are duplicated.
The original pattern is truncated in place to make it contain only the
first line.

Requested-by: Torne (Richard Coles) <torne@google.com>
Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
René Scharfe 2012-05-20 16:33:07 +02:00 committed by Junio C Hamano
parent 2b3873ff34
commit 526a858a99
4 changed files with 41 additions and 3 deletions

View File

@ -29,7 +29,9 @@ SYNOPSIS
DESCRIPTION DESCRIPTION
----------- -----------
Look for specified patterns in the tracked files in the work tree, blobs Look for specified patterns in the tracked files in the work tree, blobs
registered in the index file, or blobs in given tree objects. registered in the index file, or blobs in given tree objects. Patterns
are lists of one or more search expressions separated by newline
characters. An empty string as search expression matches all lines.
CONFIGURATION CONFIGURATION

33
grep.c
View File

@ -9,7 +9,7 @@ static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
enum grep_header_field field) enum grep_header_field field)
{ {
struct grep_pat *p = xcalloc(1, sizeof(*p)); struct grep_pat *p = xcalloc(1, sizeof(*p));
p->pattern = pat; p->pattern = xmemdupz(pat, patlen);
p->patternlen = patlen; p->patternlen = patlen;
p->origin = origin; p->origin = origin;
p->no = no; p->no = no;
@ -23,6 +23,36 @@ static void do_append_grep_pat(struct grep_pat ***tail, struct grep_pat *p)
**tail = p; **tail = p;
*tail = &p->next; *tail = &p->next;
p->next = NULL; p->next = NULL;
switch (p->token) {
case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
for (;;) {
struct grep_pat *new_pat;
size_t len = 0;
char *cp = p->pattern + p->patternlen, *nl = NULL;
while (++len <= p->patternlen) {
if (*(--cp) == '\n') {
nl = cp;
break;
}
}
if (!nl)
break;
new_pat = create_grep_pat(nl + 1, len - 1, p->origin,
p->no, p->token, p->field);
new_pat->next = p->next;
if (!p->next)
*tail = &new_pat->next;
p->next = new_pat;
*nl = '\0';
p->patternlen -= len;
}
break;
default:
break;
}
} }
void append_header_grep_pattern(struct grep_opt *opt, void append_header_grep_pattern(struct grep_opt *opt,
@ -408,6 +438,7 @@ void free_grep_patterns(struct grep_opt *opt)
free_pcre_regexp(p); free_pcre_regexp(p);
else else
regfree(&p->regexp); regfree(&p->regexp);
free(p->pattern);
break; break;
default: default:
break; break;

2
grep.h
View File

@ -35,7 +35,7 @@ struct grep_pat {
const char *origin; const char *origin;
int no; int no;
enum grep_pat_token token; enum grep_pat_token token;
const char *pattern; char *pattern;
size_t patternlen; size_t patternlen;
enum grep_header_field field; enum grep_header_field field;
regex_t regexp; regex_t regexp;

View File

@ -322,6 +322,11 @@ test_expect_success 'grep -f, multiple patterns' '
test_cmp expected actual test_cmp expected actual
' '
test_expect_success 'grep, multiple patterns' '
git grep "$(cat patterns)" >actual &&
test_cmp expected actual
'
cat >expected <<EOF cat >expected <<EOF
file:foo mmap bar file:foo mmap bar
file:foo_mmap bar file:foo_mmap bar