Merge branch 'tr/maint-word-diff-regex-sticky' into maint

The regexp configured with diff.wordregex was incorrectly reused
across files.

By Thomas Rast (2) and Johannes Sixt (1)
* tr/maint-word-diff-regex-sticky:
  diff: tweak a _copy_ of diff_options with word-diff
  diff: refactor the word-diff setup from builtin_diff_cmd
  t4034: diff.*.wordregex should not be "sticky" in --word-diff

2 files changed, 102 insertions, 56 deletions

diff --git a/diff.c b/diff.c
index 377ec1ea4c..7ebc7394e1 100644
--- a/diff.c
+++ b/diff.c
@@ -989,10 +989,74 @@ static void diff_words_flush(struct emit_callback *ecbdata)
 		diff_words_show(ecbdata->diff_words);
 }
 
+static void diff_filespec_load_driver(struct diff_filespec *one)
+{
+	/* Use already-loaded driver */
+	if (one->driver)
+		return;
+
+	if (S_ISREG(one->mode))
+		one->driver = userdiff_find_by_path(one->path);
+
+	/* Fallback to default settings */
+	if (!one->driver)
+		one->driver = userdiff_find_by_name("default");
+}
+
+static const char *userdiff_word_regex(struct diff_filespec *one)
+{
+	diff_filespec_load_driver(one);
+	return one->driver->word_regex;
+}
+
+static void init_diff_words_data(struct emit_callback *ecbdata,
+				 struct diff_options *orig_opts,
+				 struct diff_filespec *one,
+				 struct diff_filespec *two)
+{
+	int i;
+	struct diff_options *o = xmalloc(sizeof(struct diff_options));
+	memcpy(o, orig_opts, sizeof(struct diff_options));
+
+	ecbdata->diff_words =
+		xcalloc(1, sizeof(struct diff_words_data));
+	ecbdata->diff_words->type = o->word_diff;
+	ecbdata->diff_words->opt = o;
+	if (!o->word_regex)
+		o->word_regex = userdiff_word_regex(one);
+	if (!o->word_regex)
+		o->word_regex = userdiff_word_regex(two);
+	if (!o->word_regex)
+		o->word_regex = diff_word_regex_cfg;
+	if (o->word_regex) {
+		ecbdata->diff_words->word_regex = (regex_t *)
+			xmalloc(sizeof(regex_t));
+		if (regcomp(ecbdata->diff_words->word_regex,
+			    o->word_regex,
+			    REG_EXTENDED | REG_NEWLINE))
+			die ("Invalid regular expression: %s",
+			     o->word_regex);
+	}
+	for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
+		if (o->word_diff == diff_words_styles[i].type) {
+			ecbdata->diff_words->style =
+				&diff_words_styles[i];
+			break;
+		}
+	}
+	if (want_color(o->use_color)) {
+		struct diff_words_style *st = ecbdata->diff_words->style;
+		st->old.color = diff_get_color_opt(o, DIFF_FILE_OLD);
+		st->new.color = diff_get_color_opt(o, DIFF_FILE_NEW);
+		st->ctx.color = diff_get_color_opt(o, DIFF_PLAIN);
+	}
+}
+
 static void free_diff_words_data(struct emit_callback *ecbdata)
 {
 	if (ecbdata->diff_words) {
 		diff_words_flush(ecbdata);
+		free (ecbdata->diff_words->opt);
 		free (ecbdata->diff_words->minus.text.ptr);
 		free (ecbdata->diff_words->minus.orig);
 		free (ecbdata->diff_words->plus.text.ptr);
@@ -2061,20 +2125,6 @@ static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, char *pre
 	emit_binary_diff_body(file, two, one, prefix);
 }
 
-static void diff_filespec_load_driver(struct diff_filespec *one)
-{
-	/* Use already-loaded driver */
-	if (one->driver)
-		return;
-
-	if (S_ISREG(one->mode))
-		one->driver = userdiff_find_by_path(one->path);
-
-	/* Fallback to default settings */
-	if (!one->driver)
-		one->driver = userdiff_find_by_name("default");
-}
-
 int diff_filespec_is_binary(struct diff_filespec *one)
 {
 	if (one->is_binary == -1) {
@@ -2100,12 +2150,6 @@ static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespe
 	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
 }
 
-static const char *userdiff_word_regex(struct diff_filespec *one)
-{
-	diff_filespec_load_driver(one);
-	return one->driver->word_regex;
-}
-
 void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
 {
 	if (!options->a_prefix)
@@ -2292,42 +2336,8 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(diffopts + 10, NULL, 10);
 		else if (!prefixcmp(diffopts, "-u"))
 			xecfg.ctxlen = strtoul(diffopts + 2, NULL, 10);
-		if (o->word_diff) {
-			int i;
-
-			ecbdata.diff_words =
-				xcalloc(1, sizeof(struct diff_words_data));
-			ecbdata.diff_words->type = o->word_diff;
-			ecbdata.diff_words->opt = o;
-			if (!o->word_regex)
-				o->word_regex = userdiff_word_regex(one);
-			if (!o->word_regex)
-				o->word_regex = userdiff_word_regex(two);
-			if (!o->word_regex)
-				o->word_regex = diff_word_regex_cfg;
-			if (o->word_regex) {
-				ecbdata.diff_words->word_regex = (regex_t *)
-					xmalloc(sizeof(regex_t));
-				if (regcomp(ecbdata.diff_words->word_regex,
-						o->word_regex,
-						REG_EXTENDED | REG_NEWLINE))
-					die ("Invalid regular expression: %s",
-							o->word_regex);
-			}
-			for (i = 0; i < ARRAY_SIZE(diff_words_styles); i++) {
-				if (o->word_diff == diff_words_styles[i].type) {
-					ecbdata.diff_words->style =
-						&diff_words_styles[i];
-					break;
-				}
-			}
-			if (want_color(o->use_color)) {
-				struct diff_words_style *st = ecbdata.diff_words->style;
-				st->old.color = diff_get_color_opt(o, DIFF_FILE_OLD);
-				st->new.color = diff_get_color_opt(o, DIFF_FILE_NEW);
-				st->ctx.color = diff_get_color_opt(o, DIFF_PLAIN);
-			}
-		}
+		if (o->word_diff)
+			init_diff_words_data(&ecbdata, o, one, two);
 		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 			      &xpp, &xecfg);
 		if (o->word_diff)
diff --git a/t/t4034-diff-words.sh b/t/t4034-diff-words.sh
index 5c2012111c..30d42cb3bf 100755
--- a/t/t4034-diff-words.sh
+++ b/t/t4034-diff-words.sh
@@ -3,6 +3,7 @@
 test_description='word diff colors'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY"/diff-lib.sh
 
 cat >pre.simple <<-\EOF
 	h(4)
@@ -293,6 +294,10 @@ test_expect_success '--word-diff=none' '
 	word_diff --word-diff=plain --word-diff=none
 '
 
+test_expect_success 'unset default driver' '
+	test_unconfig diff.wordregex
+'
+
 test_language_driver bibtex
 test_language_driver cpp
 test_language_driver csharp
@@ -348,4 +353,35 @@ test_expect_success 'word-diff with no newline at EOF' '
 	word_diff --word-diff=plain
 '
 
+test_expect_success 'setup history with two files' '
+	echo "a b; c" >a.tex &&
+	echo "a b; c" >z.txt &&
+	git add a.tex z.txt &&
+	git commit -minitial &&
+
+	# modify both
+	echo "a bx; c" >a.tex &&
+	echo "a bx; c" >z.txt &&
+	git commit -mmodified -a
+'
+
+test_expect_success 'wordRegex for the first file does not apply to the second' '
+	echo "*.tex diff=tex" >.gitattributes &&
+	git config diff.tex.wordRegex "[a-z]+|." &&
+	cat >expect <<-\EOF &&
+		diff --git a/a.tex b/a.tex
+		--- a/a.tex
+		+++ b/a.tex
+		@@ -1 +1 @@
+		a [-b-]{+bx+}; c
+		diff --git a/z.txt b/z.txt
+		--- a/z.txt
+		+++ b/z.txt
+		@@ -1 +1 @@
+		a [-b;-]{+bx;+} c
+	EOF
+	git diff --word-diff HEAD~ >actual &&
+	compare_diff_patch expect actual
+'
+
 test_done