summaryrefslogtreecommitdiff
path: root/grep.c
diff options
context:
space:
mode:
Diffstat (limited to 'grep.c')
-rw-r--r--grep.c227
1 files changed, 177 insertions, 50 deletions
diff --git a/grep.c b/grep.c
index 82fb349be6..d03d9e24c2 100644
--- a/grep.c
+++ b/grep.c
@@ -59,6 +59,84 @@ struct grep_opt *grep_opt_dup(const struct grep_opt *opt)
return ret;
}
+static NORETURN void compile_regexp_failed(const struct grep_pat *p,
+ const char *error)
+{
+ char where[1024];
+
+ if (p->no)
+ sprintf(where, "In '%s' at %d, ", p->origin, p->no);
+ else if (p->origin)
+ sprintf(where, "%s, ", p->origin);
+ else
+ where[0] = 0;
+
+ die("%s'%s': %s", where, p->pattern, error);
+}
+
+#ifdef USE_LIBPCRE
+static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+{
+ const char *error;
+ int erroffset;
+ int options = 0;
+
+ if (opt->ignore_case)
+ options |= PCRE_CASELESS;
+
+ p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
+ NULL);
+ if (!p->pcre_regexp)
+ compile_regexp_failed(p, error);
+
+ p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error);
+ if (!p->pcre_extra_info && error)
+ die("%s", error);
+}
+
+static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+ regmatch_t *match, int eflags)
+{
+ int ovector[30], ret, flags = 0;
+
+ if (eflags & REG_NOTBOL)
+ flags |= PCRE_NOTBOL;
+
+ ret = pcre_exec(p->pcre_regexp, p->pcre_extra_info, line, eol - line,
+ 0, flags, ovector, ARRAY_SIZE(ovector));
+ if (ret < 0 && ret != PCRE_ERROR_NOMATCH)
+ die("pcre_exec failed with error code %d", ret);
+ if (ret > 0) {
+ ret = 0;
+ match->rm_so = ovector[0];
+ match->rm_eo = ovector[1];
+ }
+
+ return ret;
+}
+
+static void free_pcre_regexp(struct grep_pat *p)
+{
+ pcre_free(p->pcre_regexp);
+ pcre_free(p->pcre_extra_info);
+}
+#else /* !USE_LIBPCRE */
+static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+{
+ die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE");
+}
+
+static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+ regmatch_t *match, int eflags)
+{
+ return 1;
+}
+
+static void free_pcre_regexp(struct grep_pat *p)
+{
+}
+#endif /* !USE_LIBPCRE */
+
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
int err;
@@ -70,20 +148,17 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
if (p->fixed)
return;
+ if (opt->pcre) {
+ compile_pcre_regexp(p, opt);
+ return;
+ }
+
err = regcomp(&p->regexp, p->pattern, opt->regflags);
if (err) {
char errbuf[1024];
- char where[1024];
- if (p->no)
- sprintf(where, "In '%s' at %d, ",
- p->origin, p->no);
- else if (p->origin)
- sprintf(where, "%s, ", p->origin);
- else
- where[0] = 0;
regerror(err, &p->regexp, errbuf, 1024);
regfree(&p->regexp);
- die("%s'%s': %s", where, p->pattern, errbuf);
+ compile_regexp_failed(p, errbuf);
}
}
@@ -189,29 +264,73 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
return compile_pattern_or(list);
}
-void compile_grep_patterns(struct grep_opt *opt)
+static struct grep_expr *grep_true_expr(void)
+{
+ struct grep_expr *z = xcalloc(1, sizeof(*z));
+ z->node = GREP_NODE_TRUE;
+ return z;
+}
+
+static struct grep_expr *grep_or_expr(struct grep_expr *left, struct grep_expr *right)
+{
+ struct grep_expr *z = xcalloc(1, sizeof(*z));
+ z->node = GREP_NODE_OR;
+ z->u.binary.left = left;
+ z->u.binary.right = right;
+ return z;
+}
+
+static struct grep_expr *prep_header_patterns(struct grep_opt *opt)
{
struct grep_pat *p;
- struct grep_expr *header_expr = NULL;
-
- if (opt->header_list) {
- p = opt->header_list;
- header_expr = compile_pattern_expr(&p);
- if (p)
- die("incomplete pattern expression: %s", p->pattern);
- for (p = opt->header_list; p; p = p->next) {
- switch (p->token) {
- case GREP_PATTERN: /* atom */
- case GREP_PATTERN_HEAD:
- case GREP_PATTERN_BODY:
- compile_regexp(p, opt);
- break;
- default:
- opt->extended = 1;
- break;
- }
+ struct grep_expr *header_expr;
+ struct grep_expr *(header_group[GREP_HEADER_FIELD_MAX]);
+ enum grep_header_field fld;
+
+ if (!opt->header_list)
+ return NULL;
+ p = opt->header_list;
+ for (p = opt->header_list; p; p = p->next) {
+ if (p->token != GREP_PATTERN_HEAD)
+ die("bug: a non-header pattern in grep header list.");
+ if (p->field < 0 || GREP_HEADER_FIELD_MAX <= p->field)
+ die("bug: unknown header field %d", p->field);
+ compile_regexp(p, opt);
+ }
+
+ for (fld = 0; fld < GREP_HEADER_FIELD_MAX; fld++)
+ header_group[fld] = NULL;
+
+ for (p = opt->header_list; p; p = p->next) {
+ struct grep_expr *h;
+ struct grep_pat *pp = p;
+
+ h = compile_pattern_atom(&pp);
+ if (!h || pp != p->next)
+ die("bug: malformed header expr");
+ if (!header_group[p->field]) {
+ header_group[p->field] = h;
+ continue;
}
+ header_group[p->field] = grep_or_expr(h, header_group[p->field]);
+ }
+
+ header_expr = NULL;
+
+ for (fld = 0; fld < GREP_HEADER_FIELD_MAX; fld++) {
+ if (!header_group[fld])
+ continue;
+ if (!header_expr)
+ header_expr = grep_true_expr();
+ header_expr = grep_or_expr(header_group[fld], header_expr);
}
+ return header_expr;
+}
+
+void compile_grep_patterns(struct grep_opt *opt)
+{
+ struct grep_pat *p;
+ struct grep_expr *header_expr = prep_header_patterns(opt);
for (p = opt->pattern_list; p; p = p->next) {
switch (p->token) {
@@ -231,9 +350,6 @@ void compile_grep_patterns(struct grep_opt *opt)
else if (!opt->extended)
return;
- /* Then bundle them up in an expression.
- * A classic recursive descent parser would do.
- */
p = opt->pattern_list;
if (p)
opt->pattern_expression = compile_pattern_expr(&p);
@@ -243,22 +359,18 @@ void compile_grep_patterns(struct grep_opt *opt)
if (!header_expr)
return;
- if (opt->pattern_expression) {
- struct grep_expr *z;
- z = xcalloc(1, sizeof(*z));
- z->node = GREP_NODE_OR;
- z->u.binary.left = opt->pattern_expression;
- z->u.binary.right = header_expr;
- opt->pattern_expression = z;
- } else {
+ if (!opt->pattern_expression)
opt->pattern_expression = header_expr;
- }
+ else
+ opt->pattern_expression = grep_or_expr(opt->pattern_expression,
+ header_expr);
opt->all_match = 1;
}
static void free_pattern_expr(struct grep_expr *x)
{
switch (x->node) {
+ case GREP_NODE_TRUE:
case GREP_NODE_ATOM:
break;
case GREP_NODE_NOT:
@@ -283,7 +395,10 @@ void free_grep_patterns(struct grep_opt *opt)
case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
- regfree(&p->regexp);
+ if (p->pcre_regexp)
+ free_pcre_regexp(p);
+ else
+ regfree(&p->regexp);
break;
default:
break;
@@ -375,6 +490,21 @@ static int regmatch(const regex_t *preg, char *line, char *eol,
return regexec(preg, line, 1, match, eflags);
}
+static int patmatch(struct grep_pat *p, char *line, char *eol,
+ regmatch_t *match, int eflags)
+{
+ int hit;
+
+ if (p->fixed)
+ hit = !fixmatch(p, line, eol, match);
+ else if (p->pcre_regexp)
+ hit = !pcrematch(p, line, eol, match, eflags);
+ else
+ hit = !regmatch(&p->regexp, line, eol, match, eflags);
+
+ return hit;
+}
+
static int strip_timestamp(char *bol, char **eol_p)
{
char *eol = *eol_p;
@@ -424,10 +554,7 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
}
again:
- if (p->fixed)
- hit = !fixmatch(p, bol, eol, pmatch);
- else
- hit = !regmatch(&p->regexp, bol, eol, pmatch, eflags);
+ hit = patmatch(p, bol, eol, pmatch, eflags);
if (hit && p->word_regexp) {
if ((pmatch[0].rm_so < 0) ||
@@ -487,6 +614,9 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
if (!x)
die("Not a valid grep expression");
switch (x->node) {
+ case GREP_NODE_TRUE:
+ h = 1;
+ break;
case GREP_NODE_ATOM:
h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0);
break;
@@ -751,10 +881,7 @@ static int look_ahead(struct grep_opt *opt,
int hit;
regmatch_t m;
- if (p->fixed)
- hit = !fixmatch(p, bol, bol + *left_p, &m);
- else
- hit = !regmatch(&p->regexp, bol, bol + *left_p, &m, 0);
+ hit = patmatch(p, bol, bol + *left_p, &m, 0);
if (!hit || m.rm_so < 0 || m.rm_eo < 0)
continue;
if (earliest < 0 || m.rm_so < earliest)
@@ -851,7 +978,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
int hit;
/*
- * look_ahead() skips quicly to the line that possibly
+ * look_ahead() skips quickly to the line that possibly
* has the next hit; don't call it if we need to do
* something more than just skipping the current line
* in response to an unmatch for the current line. E.g.