Merge branch 'ab/pcre-v2'

Update "perl-compatible regular expression" support to enable JIT
and also allow linking with the newer PCRE v2 library.

* ab/pcre-v2:
  grep: add support for PCRE v2
  grep: un-break building with PCRE >= 8.32 without --enable-jit
  grep: un-break building with PCRE < 8.20
  grep: un-break building with PCRE < 8.32
  grep: add support for the PCRE v1 JIT API
  log: add -P as a synonym for --perl-regexp
  grep: skip pthreads overhead when using one thread
  grep: don't redundantly compile throwaway patterns under threading

1 files changed, 181 insertions, 4 deletions

diff --git a/grep.c b/grep.c
index d03d424e5c..d0bf37858a 100644
--- a/grep.c
+++ b/grep.c
@@ -179,22 +179,37 @@ static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, st
 	case GREP_PATTERN_TYPE_BRE:
 		opt->fixed = 0;
 		opt->pcre1 = 0;
+		opt->pcre2 = 0;
 		break;
 
 	case GREP_PATTERN_TYPE_ERE:
 		opt->fixed = 0;
 		opt->pcre1 = 0;
+		opt->pcre2 = 0;
 		opt->regflags |= REG_EXTENDED;
 		break;
 
 	case GREP_PATTERN_TYPE_FIXED:
 		opt->fixed = 1;
 		opt->pcre1 = 0;
+		opt->pcre2 = 0;
 		break;
 
 	case GREP_PATTERN_TYPE_PCRE:
 		opt->fixed = 0;
+#ifdef USE_LIBPCRE2
+		opt->pcre1 = 0;
+		opt->pcre2 = 1;
+#else
+		/*
+		 * It's important that pcre1 always be assigned to
+		 * even when there's no USE_LIBPCRE* defined. We still
+		 * call the PCRE stub function, it just dies with
+		 * "cannot use Perl-compatible regexes[...]".
+		 */
 		opt->pcre1 = 1;
+		opt->pcre2 = 0;
+#endif
 		break;
 	}
 }
@@ -365,9 +380,22 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 	if (!p->pcre1_regexp)
 		compile_regexp_failed(p, error);
 
-	p->pcre1_extra_info = pcre_study(p->pcre1_regexp, 0, &error);
+	p->pcre1_extra_info = pcre_study(p->pcre1_regexp, PCRE_STUDY_JIT_COMPILE, &error);
 	if (!p->pcre1_extra_info && error)
 		die("%s", error);
+
+#ifdef GIT_PCRE1_USE_JIT
+	pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on);
+	if (p->pcre1_jit_on == 1) {
+		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) {
+		die("BUG: The pcre1_jit_on variable should be 0 or 1, not %d",
+		    p->pcre1_jit_on);
+	}
+#endif
 }
 
 static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
@@ -378,8 +406,19 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 	if (eflags & REG_NOTBOL)
 		flags |= PCRE_NOTBOL;
 
-	ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line, eol - line,
-			0, flags, ovector, ARRAY_SIZE(ovector));
+#ifdef GIT_PCRE1_USE_JIT
+	if (p->pcre1_jit_on) {
+		ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+				    eol - line, 0, flags, ovector,
+				    ARRAY_SIZE(ovector), p->pcre1_jit_stack);
+	} else
+#endif
+	{
+		ret = pcre_exec(p->pcre1_regexp, p->pcre1_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) {
@@ -394,7 +433,15 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 static void free_pcre1_regexp(struct grep_pat *p)
 {
 	pcre_free(p->pcre1_regexp);
-	pcre_free(p->pcre1_extra_info);
+#ifdef GIT_PCRE1_USE_JIT
+	if (p->pcre1_jit_on) {
+		pcre_free_study(p->pcre1_extra_info);
+		pcre_jit_stack_free(p->pcre1_jit_stack);
+	} else
+#endif
+	{
+		pcre_free(p->pcre1_extra_info);
+	}
 	pcre_free((void *)p->pcre1_tables);
 }
 #else /* !USE_LIBPCRE1 */
@@ -414,6 +461,127 @@ static void free_pcre1_regexp(struct grep_pat *p)
 }
 #endif /* !USE_LIBPCRE1 */
 
+#ifdef USE_LIBPCRE2
+static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
+{
+	int error;
+	PCRE2_UCHAR errbuf[256];
+	PCRE2_SIZE erroffset;
+	int options = PCRE2_MULTILINE;
+	const uint8_t *character_tables = NULL;
+	int jitret;
+
+	assert(opt->pcre2);
+
+	p->pcre2_compile_context = NULL;
+
+	if (opt->ignore_case) {
+		if (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))
+		options |= PCRE2_UTF;
+
+	p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
+					 p->patternlen, options, &error, &erroffset,
+					 p->pcre2_compile_context);
+
+	if (p->pcre2_pattern) {
+		p->pcre2_match_data = pcre2_match_data_create_from_pattern(p->pcre2_pattern, NULL);
+		if (!p->pcre2_match_data)
+			die("Couldn't allocate PCRE2 match data");
+	} else {
+		pcre2_get_error_message(error, errbuf, sizeof(errbuf));
+		compile_regexp_failed(p, (const char *)&errbuf);
+	}
+
+	pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
+	if (p->pcre2_jit_on == 1) {
+		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);
+		p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
+		if (!p->pcre2_jit_stack)
+			die("Couldn't allocate PCRE2 JIT stack");
+		p->pcre2_match_context = pcre2_match_context_create(NULL);
+		if (!p->pcre2_jit_stack)
+			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) {
+		die("BUG: The pcre2_jit_on variable should be 0 or 1, not %d",
+		    p->pcre1_jit_on);
+	}
+}
+
+static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
+		regmatch_t *match, int eflags)
+{
+	int ret, flags = 0;
+	PCRE2_SIZE *ovector;
+	PCRE2_UCHAR errbuf[256];
+
+	if (eflags & REG_NOTBOL)
+		flags |= PCRE2_NOTBOL;
+
+	if (p->pcre2_jit_on)
+		ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line,
+				      eol - line, 0, flags, p->pcre2_match_data,
+				      NULL);
+	else
+		ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line,
+				  eol - line, 0, flags, p->pcre2_match_data,
+				  NULL);
+
+	if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) {
+		pcre2_get_error_message(ret, errbuf, sizeof(errbuf));
+		die("%s failed with error code %d: %s",
+		    (p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret,
+		    errbuf);
+	}
+	if (ret > 0) {
+		ovector = pcre2_get_ovector_pointer(p->pcre2_match_data);
+		ret = 0;
+		match->rm_so = (int)ovector[0];
+		match->rm_eo = (int)ovector[1];
+	}
+
+	return ret;
+}
+
+static void free_pcre2_pattern(struct grep_pat *p)
+{
+	pcre2_compile_context_free(p->pcre2_compile_context);
+	pcre2_code_free(p->pcre2_pattern);
+	pcre2_match_data_free(p->pcre2_match_data);
+	pcre2_jit_stack_free(p->pcre2_jit_stack);
+	pcre2_match_context_free(p->pcre2_match_context);
+}
+#else /* !USE_LIBPCRE2 */
+static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
+{
+	/*
+	 * Unreachable until USE_LIBPCRE2 becomes synonymous with
+	 * USE_LIBPCRE. See the sibling comment in
+	 * grep_set_pattern_type_option().
+	 */
+	die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE");
+}
+
+static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
+		regmatch_t *match, int eflags)
+{
+	return 1;
+}
+
+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)
 {
 	struct strbuf sb = STRBUF_INIT;
@@ -479,6 +647,11 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 		return;
 	}
 
+	if (opt->pcre2) {
+		compile_pcre2_pattern(p, opt);
+		return;
+	}
+
 	if (opt->pcre1) {
 		compile_pcre1_regexp(p, opt);
 		return;
@@ -838,6 +1011,8 @@ void free_grep_patterns(struct grep_opt *opt)
 				kwsfree(p->kws);
 			else if (p->pcre1_regexp)
 				free_pcre1_regexp(p);
+			else if (p->pcre2_pattern)
+				free_pcre2_pattern(p);
 			else
 				regfree(&p->regexp);
 			free(p->pattern);
@@ -918,6 +1093,8 @@ static int patmatch(struct grep_pat *p, char *line, char *eol,
 		hit = !fixmatch(p, line, eol, match);
 	else if (p->pcre1_regexp)
 		hit = !pcre1match(p, line, eol, match, eflags);
+	else if (p->pcre2_pattern)
+		hit = !pcre2match(p, line, eol, match, eflags);
 	else
 		hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
 				   eflags);