userdiff: support regexec(3) with multi-byte support

Since 1819ad327b (grep: fix multibyte regex handling under macOS,
2022-08-26) we use the system library for all regular expression
matching on macOS, not just for git grep.  It supports multi-byte
strings and rejects invalid multi-byte characters.

This broke all built-in userdiff word regexes in UTF-8 locales because
they all include such invalid bytes in expressions that are intended to
match multi-byte characters without explicit support for that from the
regex engine.

"|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+" is added to all built-in word
regexes to match a single non-space or multi-byte character.  The \xNN
characters are invalid if interpreted as UTF-8 because they have their
high bit set, which indicates they are part of a multi-byte character,
but they are surrounded by single-byte characters.

Replace that expression with "|[^[:space:]]" if the regex engine
supports multi-byte matching, as there is no need to have an explicit
range for multi-byte characters then.  Check for that capability at
runtime, because it depends on the locale and thus on environment
variables.  Construct the full replacement expression at build time
and just switch it in if necessary to avoid string manipulation and
allocations at runtime.

Additionally the word regex for tex contains the expression
"[a-zA-Z0-9\x80-\xff]+" with a similarly invalid range.  The best
replacement with only valid characters that I can come up with is
"([a-zA-Z0-9]|[^\x01-\x7f])+".  Unlike the original it matches NUL
characters, though.  Assuming that tex files usually don't contain NUL
this should be acceptable.

Reported-by: D. Ben Knoble <ben.knoble@gmail.com>
Reported-by: Eric Sunshine <sunshine@sunshineco.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: René Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 34 insertions, 2 deletions

diff --git a/t/t4034-diff-words.sh b/t/t4034-diff-words.sh
index 15764ee9ac..74586f3813 100755
--- a/t/t4034-diff-words.sh
+++ b/t/t4034-diff-words.sh
@@ -69,6 +69,10 @@ test_language_driver () {
 		echo "* diff='"$lang"'" >.gitattributes &&
 		word_diff --color-words
 	'
+	test_expect_success "diff driver '$lang' in Islandic" '
+		LANG=is_IS.UTF-8 LANGUAGE=is LC_ALL="$is_IS_locale" \
+		word_diff --color-words
+	'
 }
 
 test_expect_success setup '
diff --git a/userdiff.c b/userdiff.c
index e25356a061..8bb7b7a4ba 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -15,6 +15,7 @@ static int drivers_alloc;
 		.cflags = REG_EXTENDED, \
 	}, \
 	.word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \
+	.word_regex_multi_byte = wrx "|[^[:space:]]", \
 }
 #define IPATTERN(lang, rx, wrx) { \
 	.name = lang, \
@@ -24,6 +25,7 @@ static int drivers_alloc;
 		.cflags = REG_EXTENDED | REG_ICASE, \
 	}, \
 	.word_regex = wrx "|[^[:space:]]|[\xc0-\xff][\x80-\xbf]+", \
+	.word_regex_multi_byte = wrx "|[^[:space:]]", \
 }
 
 /*
@@ -292,7 +294,7 @@ PATTERNS("scheme",
 	 /* All other words should be delimited by spaces or parentheses */
 	 "|([^][)(}{[ \t])+"),
 PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
-	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
+	 "\\\\[a-zA-Z@]+|\\\\.|([a-zA-Z0-9]|[^\x01-\x7f])+"),
 { "default", NULL, -1, { NULL, 0 } },
 };
 #undef PATTERNS
@@ -328,6 +330,25 @@ static int userdiff_find_by_namelen_cb(struct userdiff_driver *driver,
 	return 0;
 }
 
+static int regexec_supports_multi_byte_chars(void)
+{
+	static const char not_space[] = "[^[:space:]]";
+	static const char utf8_multi_byte_char[] = "\xc2\xa3";
+	regex_t re;
+	regmatch_t match;
+	static int result = -1;
+
+	if (result != -1)
+		return result;
+	if (regcomp(&re, not_space, REG_EXTENDED))
+		BUG("invalid regular expression: %s", not_space);
+	result = !regexec(&re, utf8_multi_byte_char, 1, &match, 0) &&
+		match.rm_so == 0 &&
+		match.rm_eo == strlen(utf8_multi_byte_char);
+	regfree(&re);
+	return result;
+}
+
 static struct userdiff_driver *userdiff_find_by_namelen(const char *name, size_t len)
 {
 	struct find_by_namelen_data udcbdata = {
@@ -401,7 +422,13 @@ int userdiff_config(const char *k, const char *v)
 struct userdiff_driver *userdiff_find_by_name(const char *name)
 {
 	int len = strlen(name);
-	return userdiff_find_by_namelen(name, len);
+	struct userdiff_driver *driver = userdiff_find_by_namelen(name, len);
+	if (driver && driver->word_regex_multi_byte) {
+		if (regexec_supports_multi_byte_chars())
+			driver->word_regex = driver->word_regex_multi_byte;
+		driver->word_regex_multi_byte = NULL;
+	}
+	return driver;
 }
 
 struct userdiff_driver *userdiff_find_by_path(struct index_state *istate,
diff --git a/userdiff.h b/userdiff.h
index aee91bc77e..b09974f6b2 100644
--- a/userdiff.h
+++ b/userdiff.h
@@ -17,6 +17,7 @@ struct userdiff_driver {
 	int binary;
 	struct userdiff_funcname funcname;
 	const char *word_regex;
+	const char *word_regex_multi_byte;
 	const char *textconv;
 	struct notes_cache *textconv_cache;
 	int textconv_want_cache;