summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c200
1 files changed, 150 insertions, 50 deletions
diff --git a/grep.c b/grep.c
index a4edacad8b..92a47c71e7 100644
--- a/grep.c
+++ b/grep.c
@@ -28,9 +28,27 @@ void append_grep_pattern(struct grep_opt *opt, const char *pat,
p->next = NULL;
}
+static int is_fixed(const char *s)
+{
+ while (*s && !is_regex_special(*s))
+ s++;
+ return !*s;
+}
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
- int err = regcomp(&p->regexp, p->pattern, opt->regflags);
+ int err;
+
+ p->word_regexp = opt->word_regexp;
+
+ if (opt->fixed || is_fixed(p->pattern))
+ p->fixed = 1;
+ if (opt->regflags & REG_ICASE)
+ p->fixed = 0;
+ if (p->fixed)
+ return;
+
+ err = regcomp(&p->regexp, p->pattern, opt->regflags);
if (err) {
char errbuf[1024];
char where[1024];
@@ -161,8 +179,7 @@ void compile_grep_patterns(struct grep_opt *opt)
case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
- if (!opt->fixed)
- compile_regexp(p, opt);
+ compile_regexp(p, opt);
break;
default:
opt->extended = 1;
@@ -177,7 +194,8 @@ void compile_grep_patterns(struct grep_opt *opt)
* A classic recursive descent parser would do.
*/
p = opt->pattern_list;
- opt->pattern_expression = compile_pattern_expr(&p);
+ if (p)
+ opt->pattern_expression = compile_pattern_expr(&p);
if (p)
die("incomplete pattern expression: %s", p->pattern);
}
@@ -238,14 +256,9 @@ static int word_char(char ch)
return isalnum(ch) || ch == '_';
}
-static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
- const char *name, unsigned lno, char sign)
+static void show_name(struct grep_opt *opt, const char *name)
{
- if (opt->pathname)
- printf("%s%c", name, sign);
- if (opt->linenum)
- printf("%d%c", lno, sign);
- printf("%.*s\n", (int)(eol-bol), bol);
+ printf("%s%c", name, opt->null_following_name ? '\0' : '\n');
}
static int fixmatch(const char *pattern, char *line, regmatch_t *match)
@@ -286,12 +299,13 @@ static struct {
{ "committer ", 10 },
};
-static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol, enum grep_context ctx)
+static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
+ enum grep_context ctx,
+ regmatch_t *pmatch, int eflags)
{
int hit = 0;
- int at_true_bol = 1;
int saved_ch = 0;
- regmatch_t pmatch[10];
+ const char *start = bol;
if ((p->token != GREP_PATTERN) &&
((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
@@ -310,18 +324,14 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
}
again:
- if (!opt->fixed) {
- regex_t *exp = &p->regexp;
- hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
- pmatch, 0);
- }
- else {
+ if (p->fixed)
hit = !fixmatch(p->pattern, bol, pmatch);
- }
+ else
+ hit = !regexec(&p->regexp, bol, 1, pmatch, eflags);
- if (hit && opt->word_regexp) {
+ if (hit && p->word_regexp) {
if ((pmatch[0].rm_so < 0) ||
- (eol - bol) <= pmatch[0].rm_so ||
+ (eol - bol) < pmatch[0].rm_so ||
(pmatch[0].rm_eo < 0) ||
(eol - bol) < pmatch[0].rm_eo)
die("regexp returned nonsense");
@@ -332,7 +342,7 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
* either end of the line, or at word boundary
* (i.e. the next char must not be a word char).
*/
- if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
+ if ( ((pmatch[0].rm_so == 0) ||
!word_char(bol[pmatch[0].rm_so-1])) &&
((pmatch[0].rm_eo == (eol-bol)) ||
!word_char(bol[pmatch[0].rm_eo])) )
@@ -340,59 +350,66 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
else
hit = 0;
+ /* Words consist of at least one character. */
+ if (pmatch->rm_so == pmatch->rm_eo)
+ hit = 0;
+
if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
/* There could be more than one match on the
* line, and the first match might not be
* strict word match. But later ones could be!
+ * Forward to the next possible start, i.e. the
+ * next position following a non-word char.
*/
bol = pmatch[0].rm_so + bol + 1;
- at_true_bol = 0;
- goto again;
+ while (word_char(bol[-1]) && bol < eol)
+ bol++;
+ eflags |= REG_NOTBOL;
+ if (bol < eol)
+ goto again;
}
}
if (p->token == GREP_PATTERN_HEAD && saved_ch)
*eol = saved_ch;
+ if (hit) {
+ pmatch[0].rm_so += bol - start;
+ pmatch[0].rm_eo += bol - start;
+ }
return hit;
}
-static int match_expr_eval(struct grep_opt *o,
- struct grep_expr *x,
- char *bol, char *eol,
- enum grep_context ctx,
- int collect_hits)
+static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
+ enum grep_context ctx, int collect_hits)
{
int h = 0;
+ regmatch_t match;
if (!x)
die("Not a valid grep expression");
switch (x->node) {
case GREP_NODE_ATOM:
- h = match_one_pattern(o, x->u.atom, bol, eol, ctx);
+ h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0);
break;
case GREP_NODE_NOT:
- h = !match_expr_eval(o, x->u.unary, bol, eol, ctx, 0);
+ h = !match_expr_eval(x->u.unary, bol, eol, ctx, 0);
break;
case GREP_NODE_AND:
- if (!collect_hits)
- return (match_expr_eval(o, x->u.binary.left,
- bol, eol, ctx, 0) &&
- match_expr_eval(o, x->u.binary.right,
- bol, eol, ctx, 0));
- h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0);
- h &= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 0);
+ if (!match_expr_eval(x->u.binary.left, bol, eol, ctx, 0))
+ return 0;
+ h = match_expr_eval(x->u.binary.right, bol, eol, ctx, 0);
break;
case GREP_NODE_OR:
if (!collect_hits)
- return (match_expr_eval(o, x->u.binary.left,
+ return (match_expr_eval(x->u.binary.left,
bol, eol, ctx, 0) ||
- match_expr_eval(o, x->u.binary.right,
+ match_expr_eval(x->u.binary.right,
bol, eol, ctx, 0));
- h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0);
+ h = match_expr_eval(x->u.binary.left, bol, eol, ctx, 0);
x->u.binary.left->hit |= h;
- h |= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 1);
+ h |= match_expr_eval(x->u.binary.right, bol, eol, ctx, 1);
break;
default:
- die("Unexpected node type (internal error) %d\n", x->node);
+ die("Unexpected node type (internal error) %d", x->node);
}
if (collect_hits)
x->hit |= h;
@@ -403,24 +420,106 @@ static int match_expr(struct grep_opt *opt, char *bol, char *eol,
enum grep_context ctx, int collect_hits)
{
struct grep_expr *x = opt->pattern_expression;
- return match_expr_eval(opt, x, bol, eol, ctx, collect_hits);
+ return match_expr_eval(x, bol, eol, ctx, collect_hits);
}
static int match_line(struct grep_opt *opt, char *bol, char *eol,
enum grep_context ctx, int collect_hits)
{
struct grep_pat *p;
+ regmatch_t match;
+
if (opt->extended)
return match_expr(opt, bol, eol, ctx, collect_hits);
/* we do not call with collect_hits without being extended */
for (p = opt->pattern_list; p; p = p->next) {
- if (match_one_pattern(opt, p, bol, eol, ctx))
+ if (match_one_pattern(p, bol, eol, ctx, &match, 0))
return 1;
}
return 0;
}
+static int match_next_pattern(struct grep_pat *p, char *bol, char *eol,
+ enum grep_context ctx,
+ regmatch_t *pmatch, int eflags)
+{
+ regmatch_t match;
+
+ if (!match_one_pattern(p, bol, eol, ctx, &match, eflags))
+ return 0;
+ if (match.rm_so < 0 || match.rm_eo < 0)
+ return 0;
+ if (pmatch->rm_so >= 0 && pmatch->rm_eo >= 0) {
+ if (match.rm_so > pmatch->rm_so)
+ return 1;
+ if (match.rm_so == pmatch->rm_so && match.rm_eo < pmatch->rm_eo)
+ return 1;
+ }
+ pmatch->rm_so = match.rm_so;
+ pmatch->rm_eo = match.rm_eo;
+ return 1;
+}
+
+static int next_match(struct grep_opt *opt, char *bol, char *eol,
+ enum grep_context ctx, regmatch_t *pmatch, int eflags)
+{
+ struct grep_pat *p;
+ int hit = 0;
+
+ pmatch->rm_so = pmatch->rm_eo = -1;
+ if (bol < eol) {
+ for (p = opt->pattern_list; p; p = p->next) {
+ switch (p->token) {
+ case GREP_PATTERN: /* atom */
+ case GREP_PATTERN_HEAD:
+ case GREP_PATTERN_BODY:
+ hit |= match_next_pattern(p, bol, eol, ctx,
+ pmatch, eflags);
+ break;
+ default:
+ break;
+ }
+ }
+ }
+ return hit;
+}
+
+static void show_line(struct grep_opt *opt, char *bol, char *eol,
+ const char *name, unsigned lno, char sign)
+{
+ int rest = eol - bol;
+
+ if (opt->null_following_name)
+ sign = '\0';
+ if (opt->pathname)
+ printf("%s%c", name, sign);
+ if (opt->linenum)
+ printf("%d%c", lno, sign);
+ if (opt->color) {
+ regmatch_t match;
+ enum grep_context ctx = GREP_CONTEXT_BODY;
+ int ch = *eol;
+ int eflags = 0;
+
+ *eol = '\0';
+ while (next_match(opt, bol, eol, ctx, &match, eflags)) {
+ if (match.rm_so == match.rm_eo)
+ break;
+ printf("%.*s%s%.*s%s",
+ (int)match.rm_so, bol,
+ opt->color_match,
+ (int)(match.rm_eo - match.rm_so), bol + match.rm_so,
+ GIT_COLOR_RESET);
+ bol += match.rm_eo;
+ rest -= match.rm_eo;
+ eflags = REG_NOTBOL;
+ }
+ *eol = ch;
+ }
+ printf("%.*s\n", rest, bol);
+}
+
static int grep_buffer_1(struct grep_opt *opt, const char *name,
char *buf, unsigned long size, int collect_hits)
{
@@ -493,7 +592,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
return 1;
}
if (opt->name_only) {
- printf("%s\n", name);
+ show_name(opt, name);
return 1;
}
/* Hit at this line. If we haven't shown the
@@ -559,7 +658,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
return 0;
if (opt->unmatch_name_only) {
/* We did not see any hit, so we want to show this */
- printf("%s\n", name);
+ show_name(opt, name);
return 1;
}
@@ -569,7 +668,8 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
* make it another option? For now suppress them.
*/
if (opt->count && count)
- printf("%s:%u\n", name, count);
+ printf("%s%c%u\n", name,
+ opt->null_following_name ? '\0' : ':', count);
return !!last_hit;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-13 12:42:36 +0000