Merge branch 'cb/grep-pcre-ucp'

"grep -P" learned to use Unicode Character Property to grok
character classes when processing \b and \w etc.

* cb/grep-pcre-ucp:
  grep: correctly identify utf-8 characters with \{b,w} in -P

2 files changed, 43 insertions, 1 deletions

diff --git a/grep.c b/grep.c
index 06eed69493..1687f65b64 100644
--- a/grep.c
+++ b/grep.c
@@ -293,7 +293,7 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 		options |= PCRE2_CASELESS;
 	}
 	if (!opt->ignore_locale && is_utf8_locale() && !literal)
-		options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
+		options |= (PCRE2_UTF | PCRE2_UCP | PCRE2_MATCH_INVALID_UTF);
 
 #ifndef GIT_PCRE2_VERSION_10_36_OR_HIGHER
 	/* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */
diff --git a/t/perf/p7822-grep-perl-character.sh b/t/perf/p7822-grep-perl-character.sh
new file mode 100755
index 0000000000..87009c60df
--- /dev/null
+++ b/t/perf/p7822-grep-perl-character.sh
@@ -0,0 +1,42 @@
+#!/bin/sh
+
+test_description="git-grep's perl regex
+
+If GIT_PERF_GREP_THREADS is set to a list of threads (e.g. '1 4 8'
+etc.) we will test the patterns under those numbers of threads.
+"
+
+. ./perf-lib.sh
+
+test_perf_large_repo
+test_checkout_worktree
+
+if test -n "$GIT_PERF_GREP_THREADS"
+then
+	test_set_prereq PERF_GREP_ENGINES_THREADS
+fi
+
+for pattern in \
+	'\\bhow' \
+	'\\bÆvar' \
+	'\\d+ \\bÆvar' \
+	'\\bBelón\\b' \
+	'\\w{12}\\b'
+do
+	echo '$pattern' >pat
+	if ! test_have_prereq PERF_GREP_ENGINES_THREADS
+	then
+		test_perf "grep -P '$pattern'" --prereq PCRE "
+			git -P grep -f pat || :
+		"
+	else
+		for threads in $GIT_PERF_GREP_THREADS
+		do
+			test_perf "grep -P '$pattern' with $threads threads" --prereq PTHREADS,PCRE "
+				git -c grep.threads=$threads -P grep -f pat || :
+			"
+		done
+	fi
+done
+
+test_done