return 1;
}
-static int has_null(const char *s, size_t len)
-{
- /*
- * regcomp cannot accept patterns with NULs so when using it
- * we consider any pattern containing a NUL fixed.
- */
- if (memchr(s, 0, len))
- return 1;
-
- return 0;
-}
-
#ifdef USE_LIBPCRE1
static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
{
int options = PCRE_MULTILINE;
if (opt->ignore_case) {
- if (has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && has_non_ascii(p->pattern))
p->pcre1_tables = pcre_maketables();
options |= PCRE_CASELESS;
}
- if (is_utf8_locale() && has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE_UTF8;
p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
#ifdef GIT_PCRE1_USE_JIT
pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on);
- if (p->pcre1_jit_on == 1) {
+ if (p->pcre1_jit_on) {
p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024);
if (!p->pcre1_jit_stack)
die("Couldn't allocate PCRE JIT stack");
pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack);
- } else if (p->pcre1_jit_on != 0) {
- BUG("The pcre1_jit_on variable should be 0 or 1, not %d",
- p->pcre1_jit_on);
}
#endif
}
p->pcre2_compile_context = NULL;
if (opt->ignore_case) {
- if (has_non_ascii(p->pattern)) {
+ if (!opt->ignore_locale && has_non_ascii(p->pattern)) {
character_tables = pcre2_maketables(NULL);
p->pcre2_compile_context = pcre2_compile_context_create(NULL);
pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
}
options |= PCRE2_CASELESS;
}
- if (is_utf8_locale() && has_non_ascii(p->pattern))
+ if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern))
options |= PCRE2_UTF;
p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
}
pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
- if (p->pcre2_jit_on == 1) {
+ if (p->pcre2_jit_on) {
jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE);
if (jitret)
die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret);
if (!p->pcre2_match_context)
die("Couldn't allocate PCRE2 match context");
pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack);
- } else if (p->pcre2_jit_on != 0) {
- BUG("The pcre2_jit_on variable should be 0 or 1, not %d",
- p->pcre1_jit_on);
}
}
static void free_pcre2_pattern(struct grep_pat *p)
{
}
-#endif /* !USE_LIBPCRE2 */
static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
{
compile_regexp_failed(p, errbuf);
}
}
+#endif /* !USE_LIBPCRE2 */
static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
{
- int ascii_only;
int err;
int regflags = REG_NEWLINE;
+ int pat_is_fixed;
p->word_regexp = opt->word_regexp;
p->ignore_case = opt->ignore_case;
- ascii_only = !has_non_ascii(p->pattern);
+ p->fixed = opt->fixed;
- /*
- * 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 ||
- has_null(p->pattern, p->patternlen) ||
- is_fixed(p->pattern, p->patternlen))
- p->fixed = !p->ignore_case || ascii_only;
-
- if (p->fixed) {
- p->kws = kwsalloc(p->ignore_case ? 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.
- */
+ if (memchr(p->pattern, 0, p->patternlen) && !opt->pcre2)
+ die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
+
+ pat_is_fixed = is_fixed(p->pattern, p->patternlen);
+ if (opt->fixed || pat_is_fixed) {
+#ifdef USE_LIBPCRE2
+ opt->pcre2 = 1;
+ if (pat_is_fixed) {
+ compile_pcre2_pattern(p, opt);
+ } else {
+ /*
+ * E.g. t7811-grep-open.sh relies on the
+ * pattern being restored.
+ */
+ char *old_pattern = p->pattern;
+ size_t old_patternlen = p->patternlen;
+ struct strbuf sb = STRBUF_INIT;
+
+ /*
+ * There is the PCRE2_LITERAL flag, but it's
+ * only in PCRE v2 10.30 and later. Needing to
+ * ifdef our way around that and dealing with
+ * it + PCRE2_MULTILINE being an error is more
+ * complex than just quoting this ourselves.
+ */
+ strbuf_add(&sb, "\\Q", 2);
+ strbuf_add(&sb, p->pattern, p->patternlen);
+ strbuf_add(&sb, "\\E", 2);
+
+ p->pattern = sb.buf;
+ p->patternlen = sb.len;
+ compile_pcre2_pattern(p, opt);
+ p->pattern = old_pattern;
+ p->patternlen = old_patternlen;
+ strbuf_release(&sb);
+ }
+#else /* !USE_LIBPCRE2 */
compile_fixed_regexp(p, opt);
+#endif /* !USE_LIBPCRE2 */
return;
}
case GREP_PATTERN: /* atom */
case GREP_PATTERN_HEAD:
case GREP_PATTERN_BODY:
- if (p->kws)
- kwsfree(p->kws);
- else if (p->pcre1_regexp)
+ if (p->pcre1_regexp)
free_pcre1_regexp(p);
else if (p->pcre2_pattern)
free_pcre2_pattern(p);
opt->output(opt, opt->null_following_name ? "\0" : "\n", 1);
}
-static int fixmatch(struct grep_pat *p, char *line, char *eol,
- regmatch_t *match)
-{
- struct kwsmatch kwsm;
- size_t offset = kwsexec(p->kws, line, eol - line, &kwsm);
- if (offset == -1) {
- match->rm_so = match->rm_eo = -1;
- return REG_NOMATCH;
- } else {
- match->rm_so = offset;
- match->rm_eo = match->rm_so + kwsm.size[0];
- return 0;
- }
-}
-
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->pcre1_regexp)
+ if (p->pcre1_regexp)
hit = !pcre1match(p, line, eol, match, eflags);
else if (p->pcre2_pattern)
hit = !pcre2match(p, line, eol, match, eflags);
enum grep_context ctx = GREP_CONTEXT_HEAD;
xdemitconf_t xecfg;
+ if (!opt->status_only && gs->name == NULL)
+ BUG("grep call which could print a name requires "
+ "grep_source.name be non-NULL");
+
if (!opt->output)
opt->output = std_output;