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

Author: gitster

Documentation/rev-list-options.txt

@@ -91,6 +91,7 @@ endif::git-rev-list[]
 	Consider the limiting patterns to be fixed strings (don't interpret
 	pattern as a regular expression).
 
+-P::
 --perl-regexp::
 	Consider the limiting patterns to be Perl-compatible regular
 	expressions.

Makefile

@@ -29,8 +29,23 @@ all::
 # Perl-compatible regular expressions instead of standard or extended
 # POSIX regular expressions.
 #
-# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
+# Currently USE_LIBPCRE is a synonym for USE_LIBPCRE1, define
+# USE_LIBPCRE2 instead if you'd like to use version 2 of the PCRE
+# library. The USE_LIBPCRE flag will likely be changed to mean v2 by
+# default in future releases.
+#
+# When using USE_LIBPCRE1, define NO_LIBPCRE1_JIT if the PCRE v1
+# library is compiled without --enable-jit. We will auto-detect
+# whether the version of the PCRE v1 library in use has JIT support at
+# all, but we unfortunately can't auto-detect whether JIT support
+# hasn't been compiled in in an otherwise JIT-supporting version. If
+# you have link-time errors about a missing `pcre_jit_exec` define
+# this, or recompile PCRE v1 with --enable-jit.
+#
+# Define LIBPCREDIR=/foo/bar if your PCRE header and library files are
+# in /foo/bar/include and /foo/bar/lib directories. Which version of
+# PCRE this points to determined by the USE_LIBPCRE1 and USE_LIBPCRE2
+# variables.
 #
 # Define HAVE_ALLOCA_H if you have working alloca(3) defined in that header.
 #
@@ -1089,13 +1104,29 @@ ifdef NO_LIBGEN_H
 	COMPAT_OBJS += compat/basename.o
 endif
 
-ifdef USE_LIBPCRE
-	BASIC_CFLAGS += -DUSE_LIBPCRE1
-	ifdef LIBPCREDIR
-		BASIC_CFLAGS += -I$(LIBPCREDIR)/include
-		EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib)
+USE_LIBPCRE1 ?= $(USE_LIBPCRE)
+
+ifneq (,$(USE_LIBPCRE1))
+	ifdef USE_LIBPCRE2
+$(error Only set USE_LIBPCRE1 (or its alias USE_LIBPCRE) or USE_LIBPCRE2, not both!)
 	endif
+
+	BASIC_CFLAGS += -DUSE_LIBPCRE1
 	EXTLIBS += -lpcre
+
+ifdef NO_LIBPCRE1_JIT
+	BASIC_CFLAGS += -DNO_LIBPCRE1_JIT
+endif
+endif
+
+ifdef USE_LIBPCRE2
+	BASIC_CFLAGS += -DUSE_LIBPCRE2
+	EXTLIBS += -lpcre2-8
+endif
+
+ifdef LIBPCREDIR
+	BASIC_CFLAGS += -I$(LIBPCREDIR)/include
+	EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib)
 endif
 
 ifdef HAVE_ALLOCA_H
@@ -2249,7 +2280,9 @@ GIT-BUILD-OPTIONS: FORCE
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@+
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@+
 	@echo NO_EXPAT=\''$(subst ','\'',$(subst ','\'',$(NO_EXPAT)))'\' >>$@+
-	@echo USE_LIBPCRE1=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE)))'\' >>$@+
+	@echo USE_LIBPCRE1=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE1)))'\' >>$@+
+	@echo USE_LIBPCRE2=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE2)))'\' >>$@+
+	@echo NO_LIBPCRE1_JIT=\''$(subst ','\'',$(subst ','\'',$(NO_LIBPCRE1_JIT)))'\' >>$@+
 	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@+
 	@echo NO_PTHREADS=\''$(subst ','\'',$(subst ','\'',$(NO_PTHREADS)))'\' >>$@+
 	@echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@+

builtin/grep.c

@@ -224,7 +224,8 @@ static void start_threads(struct grep_opt *opt)
 		int err;
 		struct grep_opt *o = grep_opt_dup(opt);
 		o->output = strbuf_out;
-		o->debug = 0;
+		if (i)
+			o->debug = 0;
 		compile_grep_patterns(o);
 		err = pthread_create(&threads[i], NULL, run, o);
 
@@ -1170,8 +1171,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	if (!opt.fixed && opt.ignore_case)
 		opt.regflags |= REG_ICASE;
 
-	compile_grep_patterns(&opt);
-
 	/*
 	 * We have to find "--" in a separate pass, because its presence
 	 * influences how we will parse arguments that come before it.
@@ -1244,12 +1243,23 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		num_threads = GREP_NUM_THREADS_DEFAULT;
 	else if (num_threads < 0)
 		die(_("invalid number of threads specified (%d)"), num_threads);
+	if (num_threads == 1)
+		num_threads = 0;
 #else
 	if (num_threads)
 		warning(_("no threads support, ignoring --threads"));
 	num_threads = 0;
 #endif
 
+	if (!num_threads)
+		/*
+		 * The compiled patterns on the main path are only
+		 * used when not using threading. Otherwise
+		 * start_threads() below calls compile_grep_patterns()
+		 * for each thread.
+		 */
+		compile_grep_patterns(&opt);
+
 #ifndef NO_PTHREADS
 	if (num_threads) {
 		if (!(opt.name_only || opt.unmatch_name_only || opt.count)

config.mak.uname

@@ -555,6 +555,7 @@ else
 		NO_GETTEXT =
 		USE_GETTEXT_SCHEME = fallthrough
 		USE_LIBPCRE= YesPlease
+		NO_LIBPCRE1_JIT = UnfortunatelyYes
 		NO_CURL =
 		USE_NED_ALLOCATOR = YesPlease
 	else

configure.ac

@@ -255,21 +255,61 @@ GIT_PARSE_WITH([openssl]))
 # Perl-compatible regular expressions instead of standard or extended
 # POSIX regular expressions.
 #
-# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
+# Currently USE_LIBPCRE is a synonym for USE_LIBPCRE1, define
+# USE_LIBPCRE2 instead if you'd like to use version 2 of the PCRE
+# library. The USE_LIBPCRE flag will likely be changed to mean v2 by
+# default in future releases.
+#
+# Define LIBPCREDIR=/foo/bar if your PCRE header and library files are in
 # /foo/bar/include and /foo/bar/lib directories.
 #
 AC_ARG_WITH(libpcre,
-AS_HELP_STRING([--with-libpcre],[support Perl-compatible regexes (default is NO)])
+AS_HELP_STRING([--with-libpcre],[synonym for --with-libpcre1]),
+    if test "$withval" = "no"; then
+	USE_LIBPCRE1=
+    elif test "$withval" = "yes"; then
+	USE_LIBPCRE1=YesPlease
+    else
+	USE_LIBPCRE1=YesPlease
+	LIBPCREDIR=$withval
+	AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR])
+        dnl USE_LIBPCRE1 can still be modified below, so don't substitute
+        dnl it yet.
+	GIT_CONF_SUBST([LIBPCREDIR])
+    fi)
+
+AC_ARG_WITH(libpcre1,
+AS_HELP_STRING([--with-libpcre1],[support Perl-compatible regexes via libpcre1 (default is NO)])
+AS_HELP_STRING([],           [ARG can be also prefix for libpcre library and headers]),
+    if test "$withval" = "no"; then
+	USE_LIBPCRE1=
+    elif test "$withval" = "yes"; then
+	USE_LIBPCRE1=YesPlease
+    else
+	USE_LIBPCRE1=YesPlease
+	LIBPCREDIR=$withval
+	AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR])
+        dnl USE_LIBPCRE1 can still be modified below, so don't substitute
+        dnl it yet.
+	GIT_CONF_SUBST([LIBPCREDIR])
+    fi)
+
+AC_ARG_WITH(libpcre2,
+AS_HELP_STRING([--with-libpcre2],[support Perl-compatible regexes via libpcre2 (default is NO)])
 AS_HELP_STRING([],           [ARG can be also prefix for libpcre library and headers]),
+    if test -n "$USE_LIBPCRE1"; then
+        AC_MSG_ERROR([Only supply one of --with-libpcre1 or --with-libpcre2!])
+    fi
+
     if test "$withval" = "no"; then
-	USE_LIBPCRE=
+	USE_LIBPCRE2=
     elif test "$withval" = "yes"; then
-	USE_LIBPCRE=YesPlease
+	USE_LIBPCRE2=YesPlease
     else
-	USE_LIBPCRE=YesPlease
+	USE_LIBPCRE2=YesPlease
 	LIBPCREDIR=$withval
 	AC_MSG_NOTICE([Setting LIBPCREDIR to $LIBPCREDIR])
-        dnl USE_LIBPCRE can still be modified below, so don't substitute
+        dnl USE_LIBPCRE2 can still be modified below, so don't substitute
         dnl it yet.
 	GIT_CONF_SUBST([LIBPCREDIR])
     fi)
@@ -501,13 +541,11 @@ GIT_CONF_SUBST([NEEDS_SSL_WITH_CRYPTO])
 GIT_CONF_SUBST([NO_OPENSSL])
 
 #
-# Define USE_LIBPCRE if you have and want to use libpcre. Various
-# commands such as log and grep offer runtime options to use
-# Perl-compatible regular expressions instead of standard or extended
-# POSIX regular expressions.
+# Handle the USE_LIBPCRE1 and USE_LIBPCRE2 options potentially set
+# above.
 #
 
-if test -n "$USE_LIBPCRE"; then
+if test -n "$USE_LIBPCRE1"; then
 
 GIT_STASH_FLAGS($LIBPCREDIR)
 
@@ -517,7 +555,22 @@ AC_CHECK_LIB([pcre], [pcre_version],
 
 GIT_UNSTASH_FLAGS($LIBPCREDIR)
 
-GIT_CONF_SUBST([USE_LIBPCRE])
+GIT_CONF_SUBST([USE_LIBPCRE1])
+
+fi
+
+
+if test -n "$USE_LIBPCRE2"; then
+
+GIT_STASH_FLAGS($LIBPCREDIR)
+
+AC_CHECK_LIB([pcre2-8], [pcre2_config_8],
+[USE_LIBPCRE2=YesPlease],
+[USE_LIBPCRE2=])
+
+GIT_UNSTASH_FLAGS($LIBPCREDIR)
+
+GIT_CONF_SUBST([USE_LIBPCRE2])
 
 fi