grep: add support for PCRE v2

Add support for v2 of the PCRE API. This is a new major version of
PCRE that came out in early 2015[1].

The regular expression syntax is the same, but while the API is
similar, pretty much every function is either renamed or takes
different arguments. Thus using it via entirely new functions makes
sense, as opposed to trying to e.g. have one compile_pcre_pattern()
that would call either PCRE v1 or v2 functions.

Git can now be compiled with either USE_LIBPCRE1=YesPlease or
USE_LIBPCRE2=YesPlease, with USE_LIBPCRE=YesPlease currently being a
synonym for the former. Providing both is a compile-time error.

With earlier patches to enable JIT for PCRE v1 the performance of the
release versions of both libraries is almost exactly the same, with
PCRE v2 being around 1% slower.

However after I reported this to the pcre-dev mailing list[2] I got a
lot of help with the API use from Zoltán Herczeg, he subsequently
optimized some of the JIT functionality in v2 of the library.

Running the p7820-grep-engines.sh performance test against the latest
Subversion trunk of both, with both them and git compiled as -O3, and
the test run against linux.git, gives the following results. Just the
/perl/ tests shown:

    $ GIT_PERF_REPEAT_COUNT=30 GIT_PERF_LARGE_REPO=~/g/linux GIT_PERF_MAKE_COMMAND='grep -q LIBPCRE2 Makefile && make -j8 USE_LIBPCRE2=YesPlease CC=~/perl5/installed/bin/gcc NO_R_TO_GCC_LINKER=YesPlease CFLAGS=-O3 LIBPCREDIR=/home/avar/g/pcre2/inst LDFLAGS=-Wl,-rpath,/home/avar/g/pcre2/inst/lib || make -j8 USE_LIBPCRE=YesPlease CC=~/perl5/installed/bin/gcc NO_R_TO_GCC_LINKER=YesPlease CFLAGS=-O3 LIBPCREDIR=/home/avar/g/pcre/inst LDFLAGS=-Wl,-rpath,/home/avar/g/pcre/inst/lib' ./run HEAD~5 HEAD~ HEAD p7820-grep-engines.sh
    [...]
    Test                                            HEAD~5            HEAD~                    HEAD
    -----------------------------------------------------------------------------------------------------------------
    7820.3: perl grep 'how.to'                      0.31(1.10+0.48)   0.21(0.35+0.56) -32.3%   0.21(0.34+0.55) -32.3%
    7820.7: perl grep '^how to'                     0.56(2.70+0.40)   0.24(0.64+0.52) -57.1%   0.20(0.28+0.60) -64.3%
    7820.11: perl grep '[how] to'                   0.56(2.66+0.38)   0.29(0.95+0.45) -48.2%   0.23(0.45+0.54) -58.9%
    7820.15: perl grep '(e.t[^ ]*|v.ry) rare'       1.02(5.77+0.42)   0.31(1.02+0.54) -69.6%   0.23(0.50+0.54) -77.5%
    7820.19: perl grep 'm(ú|u)lt.b(æ|y)te'          0.38(1.57+0.42)   0.27(0.85+0.46) -28.9%   0.21(0.33+0.57) -44.7%

See commit ("perf: add a comparison test of grep regex engines",
2017-04-19) for details on the machine the above test run was executed
on.

Here HEAD~2 is git with PCRE v1 without JIT, HEAD~ is PCRE v1 with
JIT, and HEAD is PCRE v2 (also with JIT). See previous commits of mine
mentioning p7820-grep-engines.sh for more details on the test setup.

For ease of readability, a different run just of HEAD~ (PCRE v1 with
JIT v.s. PCRE v2), again with just the /perl/ tests shown:

    [...]
    Test                                            HEAD~             HEAD
    ----------------------------------------------------------------------------------------
    7820.3: perl grep 'how.to'                      0.21(0.42+0.52)   0.21(0.31+0.58) +0.0%
    7820.7: perl grep '^how to'                     0.25(0.65+0.50)   0.20(0.31+0.57) -20.0%
    7820.11: perl grep '[how] to'                   0.30(0.90+0.50)   0.23(0.46+0.53) -23.3%
    7820.15: perl grep '(e.t[^ ]*|v.ry) rare'       0.30(1.19+0.38)   0.23(0.51+0.51) -23.3%
    7820.19: perl grep 'm(ú|u)lt.b(æ|y)te'          0.27(0.84+0.48)   0.21(0.34+0.57) -22.2%

I.e. the two are either neck-to-neck, but PCRE v2 usually pulls ahead,
when it does it's around 20% faster.

A brief note on thread safety: As noted in pcre2api(3) & pcre2jit(3)
the compiled pattern can be shared between threads, but not some of
the JIT context, however the grep threading support does all pattern &
JIT compilation in separate threads, so this code doesn't need to
concern itself with thread safety.

See commit 63e7e9d8b6 ("git-grep: Learn PCRE", 2011-05-09) for the
initial addition of PCRE v1. This change follows some of the same
patterns it did (and which were discussed on list at the time),
e.g. mocking up types with typedef instead of ifdef-ing them out when
USE_LIBPCRE2 isn't defined. This adds some trivial memory use to the
program, but makes the code look nicer.

1. https://lists.exim.org/lurker/message/20150105.162835.0666407a.en.html
2. https://lists.exim.org/lurker/thread/20170419.172322.833ee099.en.html

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 145 insertions, 0 deletions

diff --git a/grep.c b/grep.c
index 19fa67c..d0bf378 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;
 	}
 }
@@ -446,6 +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;
@@ -511,6 +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;
@@ -870,6 +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);
@@ -950,6 +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);