Cut text between characters, never inside one

The index description was cut at a byte count, which could split a
multibyte character and leave an invalid sequence on the page. Commit
subjects already backed up to the start of the character, so html_ntxt
now does that for every caller.

2 files changed, 24 insertions, 0 deletions

diff --git a/tests/t0101-index.sh b/tests/t0101-index.shindex adad6be..e433beb 100755--- a/tests/t0101-index.sh+++ b/tests/t0101-index.sh@@ -53,4 +53,18 @@ test_expect_success 'the feed link encodes the repository and the branch' ' 	grep "title=.Atom feed. href=.http://example.org/foo%2Bbar/atom/?h=1%2B2." tmp ' +# The description limit counts bytes, so a cut has to land between+# characters rather than leave half of one on the page.+test_expect_success 'a cut description keeps whole characters' '+	{+		echo "max-repodesc-length=10" &&+		sed "s/^cache-size=.*/cache-size=0/" cgitrc &&+		echo "repo.url=mb" &&+		echo "repo.path=$PWD/repos/foo/.git" &&+		echo "repo.desc=日本語の説明文です"+	} >descrc &&+	CGIT_CONFIG="$PWD/descrc" QUERY_STRING="url=" cgit >tmp &&+	grep ">日本語\.\.\.</a>" tmp+'+ test_done
diff --git a/tests/t0101-index.sh b/tests/t0101-index.sh
index adad6be..e433beb 100755
--- a/tests/t0101-index.sh
+++ b/tests/t0101-index.sh
@@ -53,4 +53,18 @@ test_expect_success 'the feed link encodes the repository and the branch' '
 	grep "title=.Atom feed. href=.http://example.org/foo%2Bbar/atom/?h=1%2B2." tmp
 '
 
+# The description limit counts bytes, so a cut has to land between
+# characters rather than leave half of one on the page.
+test_expect_success 'a cut description keeps whole characters' '
+	{
+		echo "max-repodesc-length=10" &&
+		sed "s/^cache-size=.*/cache-size=0/" cgitrc &&
+		echo "repo.url=mb" &&
+		echo "repo.path=$PWD/repos/foo/.git" &&
+		echo "repo.desc=日本語の説明文です"
+	} >descrc &&
+	CGIT_CONFIG="$PWD/descrc" QUERY_STRING="url=" cgit >tmp &&
+	grep ">日本語\.\.\.</a>" tmp
+'
+
 test_done
diff --git a/tests/t0103-log.sh b/tests/t0103-log.shindex ed92a76..f9612e6 100755--- a/tests/t0103-log.sh+++ b/tests/t0103-log.sh@@ -91,4 +91,14 @@ test_expect_success 'the pager of a followed log keeps the name followed' ' 	grep "href=./fol/log/b.txt?ofs=6&amp;follow=1.>\[next\]" tmp ' +test_expect_success 'a cut subject keeps whole characters' '+	git -C repos/foo commit --allow-empty -m "日本語の説明文です日本語の説明文です" &&+	{+		echo "max-message-length=20" &&+		sed "s/^cache-size=.*/cache-size=0/" cgitrc+	} >subjectrc &&+	CGIT_CONFIG="$PWD/subjectrc" QUERY_STRING="url=foo/log/" cgit >tmp &&+	grep ">日本語の説\.\.\.</a>" tmp+'+ test_done
diff --git a/tests/t0103-log.sh b/tests/t0103-log.sh
index ed92a76..f9612e6 100755
--- a/tests/t0103-log.sh
+++ b/tests/t0103-log.sh
@@ -91,4 +91,14 @@ test_expect_success 'the pager of a followed log keeps the name followed' '
 	grep "href=./fol/log/b.txt?ofs=6&amp;follow=1.>\[next\]" tmp
 '
 
+test_expect_success 'a cut subject keeps whole characters' '
+	git -C repos/foo commit --allow-empty -m "日本語の説明文です日本語の説明文です" &&
+	{
+		echo "max-message-length=20" &&
+		sed "s/^cache-size=.*/cache-size=0/" cgitrc
+	} >subjectrc &&
+	CGIT_CONFIG="$PWD/subjectrc" QUERY_STRING="url=foo/log/" cgit >tmp &&
+	grep ">日本語の説\.\.\.</a>" tmp
+'
+
 test_done