Show characters a browser breaks at as escapes

The HTML parser turns a carriage return with no line feed after it into
a line feed, and WebKit starts a new line at U+2028 and U+2029, while
git and the line numbers count line feeds alone, so each one set every
later line of the tree and blame pages a line below its number. CSS
Text makes vertical tab, form feed and next line forced breaks as well,
though no engine honours that yet. The escapes follow gitweb, which
shows control characters the same way.

2 files changed, 62 insertions, 4 deletions

diff --git a/tests/t0005-markup.sh b/tests/t0005-markup.shindex e3cb08d..829c839 100755--- a/tests/t0005-markup.sh+++ b/tests/t0005-markup.sh@@ -96,15 +96,17 @@ test_expect_success 'the stylesheet and the script name only the current hooks' 	grep "window.cgit.highlightLines" "$TEST_OUTPUT_DIRECTORY/../assets/cgit.js" ' -# The rest of the hooks need a tag, a symlink, a submodule, a trailer, clone-# urls, an empty repository and a second page of repositories, so they get a-# commit and a config of their own after the checks above have read the first-# ones.+# The rest of the hooks need a tag, a symlink, a submodule, a trailer, a lone+# carriage return, clone urls, an empty repository and a second page of+# repositories, so they get a commit and a config of their own after the checks+# above have read the first ones. test_expect_success 'set up the remaining kinds of entry' ' 	( 		cd repos/hooks && 		git tag -a -m "first release" v1 && 		test_ln_s_add file-1 link &&+		printf "a\\rb\\n" >cr.txt &&+		git add cr.txt && 		git update-index --add --cacheinfo "160000,$(git rev-parse HEAD),sub" && 		git commit -m "more kinds of entry" -m "Fixes: $(git rev-parse --short HEAD)" 	) &&@@ -139,6 +141,11 @@ test_expect_success 'the refs, summary and tree name every section and row' ' 	grep "<tr class=.mod.>" tmp ' +test_expect_success 'a character the browser would break a line at is an escape' '+	more "hooks/tree/cr.txt" >tmp &&+	grep "a<span class=.escape.>" tmp+'+ test_expect_success 'the commit page has its trailer table and diffstat' ' 	more "hooks/commit/" >tmp && 	grep "<table class=.commit-trailers.>" tmp &&
diff --git a/tests/t0005-markup.sh b/tests/t0005-markup.sh
index e3cb08d..829c839 100755
--- a/tests/t0005-markup.sh
+++ b/tests/t0005-markup.sh
@@ -96,15 +96,17 @@ test_expect_success 'the stylesheet and the script name only the current hooks'
 	grep "window.cgit.highlightLines" "$TEST_OUTPUT_DIRECTORY/../assets/cgit.js"
 '
 
-# The rest of the hooks need a tag, a symlink, a submodule, a trailer, clone
-# urls, an empty repository and a second page of repositories, so they get a
-# commit and a config of their own after the checks above have read the first
-# ones.
+# The rest of the hooks need a tag, a symlink, a submodule, a trailer, a lone
+# carriage return, clone urls, an empty repository and a second page of
+# repositories, so they get a commit and a config of their own after the checks
+# above have read the first ones.
 test_expect_success 'set up the remaining kinds of entry' '
 	(
 		cd repos/hooks &&
 		git tag -a -m "first release" v1 &&
 		test_ln_s_add file-1 link &&
+		printf "a\\rb\\n" >cr.txt &&
+		git add cr.txt &&
 		git update-index --add --cacheinfo "160000,$(git rev-parse HEAD),sub" &&
 		git commit -m "more kinds of entry" -m "Fixes: $(git rev-parse --short HEAD)"
 	) &&
@@ -139,6 +141,11 @@ test_expect_success 'the refs, summary and tree name every section and row' '
 	grep "<tr class=.mod.>" tmp
 '
 
+test_expect_success 'a character the browser would break a line at is an escape' '
+	more "hooks/tree/cr.txt" >tmp &&
+	grep "a<span class=.escape.>" tmp
+'
+
 test_expect_success 'the commit page has its trailer table and diffstat' '
 	more "hooks/commit/" >tmp &&
 	grep "<table class=.commit-trailers.>" tmp &&
diff --git a/tests/t0104-tree.sh b/tests/t0104-tree.shindex fefff4a..d464f8c 100755--- a/tests/t0104-tree.sh+++ b/tests/t0104-tree.sh@@ -31,6 +31,57 @@ test_expect_success 'the code is set in the font of its line numbers' ' 	grep "^  font: inherit;$" rule ' +# A browser starts a new line at more characters than git ends one at, and+# each would push the rest of the code a line below its numbers.+test_expect_success 'set up a file holding the characters a browser breaks at' '+	test_create_repo repos/breaks &&+	(+		cd repos/breaks &&+		printf "a\\rb\\vc\\fd\\302\\205e\\342\\200\\250f\\342\\200\\251g\\nh\\r\\ni\\r" >breaks.txt &&+		git add breaks.txt &&+		git commit -m breaks+	) &&+	{+		echo "virtual-root=/" &&+		echo "cache-size=0" &&+		echo "enable-blame=1" &&+		echo "repo.url=breaks" &&+		echo "repo.path=$PWD/repos/breaks/.git"+	} >breaksrc+'++test_expect_success 'each of them is shown as an escape in the tree' '+	CGIT_CONFIG="$PWD/breaksrc" QUERY_STRING="url=breaks/tree/breaks.txt" cgit >tmp &&+	grep "<code>a<span class=.escape.>\\\\r</span>b<span class=.escape.>\\\\v</span>c" tmp &&+	grep "c<span class=.escape.>\\\\f</span>d<span class=.escape.>\\\\u0085</span>e" tmp &&+	grep "e<span class=.escape.>\\\\u2028</span>f<span class=.escape.>\\\\u2029</span>g$" tmp+'++test_expect_success 'only a carriage return before a line feed is left as it is' '+	printf "h\\r\\n" >expect &&+	grep "^h" tmp >actual &&+	test_cmp expect actual &&+	grep "^i<span class=.escape.>\\\\r</span></code>" tmp+'++test_expect_success 'the numbers count only the lines git counts' '+	grep "<a id=.n3. href=.#n3.>3</a>" tmp &&+	! grep "<a id=.n4. href=.#n4.>4</a>" tmp+'++test_expect_success 'the blame page escapes them the same way' '+	CGIT_CONFIG="$PWD/breaksrc" QUERY_STRING="url=breaks/blame/breaks.txt" cgit >tmp &&+	grep "<code>a<span class=.escape.>\\\\r</span>b<span class=.escape.>\\\\v</span>c" tmp &&+	grep "e<span class=.escape.>\\\\u2028</span>f<span class=.escape.>\\\\u2029</span>g$" tmp &&+	grep "^i<span class=.escape.>\\\\r</span></code>" tmp+'++# The striped background is padded with spaces to the widest line, which is+# 31 columns once its six escapes are written out, though it is 18 bytes.+test_expect_success 'the blame stripes are as wide as the escaped line' '+	grep "^ \\{31\\}</pre></div>" tmp+'+ test_expect_success 'generate foo+bar/tree' 'cgit_url "foo%2bbar/tree" >tmp'  test_expect_success 'verify a+b link' '
diff --git a/tests/t0104-tree.sh b/tests/t0104-tree.sh
index fefff4a..d464f8c 100755
--- a/tests/t0104-tree.sh
+++ b/tests/t0104-tree.sh
@@ -31,6 +31,57 @@ test_expect_success 'the code is set in the font of its line numbers' '
 	grep "^  font: inherit;$" rule
 '
 
+# A browser starts a new line at more characters than git ends one at, and
+# each would push the rest of the code a line below its numbers.
+test_expect_success 'set up a file holding the characters a browser breaks at' '
+	test_create_repo repos/breaks &&
+	(
+		cd repos/breaks &&
+		printf "a\\rb\\vc\\fd\\302\\205e\\342\\200\\250f\\342\\200\\251g\\nh\\r\\ni\\r" >breaks.txt &&
+		git add breaks.txt &&
+		git commit -m breaks
+	) &&
+	{
+		echo "virtual-root=/" &&
+		echo "cache-size=0" &&
+		echo "enable-blame=1" &&
+		echo "repo.url=breaks" &&
+		echo "repo.path=$PWD/repos/breaks/.git"
+	} >breaksrc
+'
+
+test_expect_success 'each of them is shown as an escape in the tree' '
+	CGIT_CONFIG="$PWD/breaksrc" QUERY_STRING="url=breaks/tree/breaks.txt" cgit >tmp &&
+	grep "<code>a<span class=.escape.>\\\\r</span>b<span class=.escape.>\\\\v</span>c" tmp &&
+	grep "c<span class=.escape.>\\\\f</span>d<span class=.escape.>\\\\u0085</span>e" tmp &&
+	grep "e<span class=.escape.>\\\\u2028</span>f<span class=.escape.>\\\\u2029</span>g$" tmp
+'
+
+test_expect_success 'only a carriage return before a line feed is left as it is' '
+	printf "h\\r\\n" >expect &&
+	grep "^h" tmp >actual &&
+	test_cmp expect actual &&
+	grep "^i<span class=.escape.>\\\\r</span></code>" tmp
+'
+
+test_expect_success 'the numbers count only the lines git counts' '
+	grep "<a id=.n3. href=.#n3.>3</a>" tmp &&
+	! grep "<a id=.n4. href=.#n4.>4</a>" tmp
+'
+
+test_expect_success 'the blame page escapes them the same way' '
+	CGIT_CONFIG="$PWD/breaksrc" QUERY_STRING="url=breaks/blame/breaks.txt" cgit >tmp &&
+	grep "<code>a<span class=.escape.>\\\\r</span>b<span class=.escape.>\\\\v</span>c" tmp &&
+	grep "e<span class=.escape.>\\\\u2028</span>f<span class=.escape.>\\\\u2029</span>g$" tmp &&
+	grep "^i<span class=.escape.>\\\\r</span></code>" tmp
+'
+
+# The striped background is padded with spaces to the widest line, which is
+# 31 columns once its six escapes are written out, though it is 18 bytes.
+test_expect_success 'the blame stripes are as wide as the escaped line' '
+	grep "^ \\{31\\}</pre></div>" tmp
+'
+
 test_expect_success 'generate foo+bar/tree' 'cgit_url "foo%2bbar/tree" >tmp'
 
 test_expect_success 'verify a+b link' '