1 file changed, 94 insertions, 0 deletions
diff --git a/tests/extensions/test-syntax-highlight.lua b/tests/extensions/test-syntax-highlight.lua
new file mode 100644
index 0000000..3b0eeb8
--- /dev/null
+++ b/tests/extensions/test-syntax-highlight.lua
@@ -0,0 +1,94 @@
+-- Unit checks for custom/extensions/syntax-highlight.lua, run under a
+-- standalone Lua by t0502-syntax-highlight.sh with the script path as the
+-- first argument. The filter remembers whether the lexers loaded for the
+-- life of the interpreter, so the two sides of that split are two runs of
+-- this file. In highlight mode the shell points CGIT_SCINTILLUA_PATH at the
+-- fake-lexers directory beside this file and every path through a working
+-- lexer is checked, and in nolexers mode it points at an empty directory so
+-- the escaped fallback is what everything renders through.
+
+local test_directory = arg[0]:match("^(.*)/") or "."
+local h = dofile(test_directory .. "/harness.lua")
+
+local script = arg[1]
+local mode = arg[2] or "highlight"
+
+h.load(script)
+
+local function render(filename, text)
+	return h.run({ filename }, { text })
+end
+
+if mode == "nolexers" then
+	local out, ret = render("hello.fake", "if 42")
+	h.equals("without lexers source is served escaped", out, "if 42")
+	h.equals("close answers zero", ret, 0)
+
+	out = render("hello.fake", "a <b> & c")
+	h.equals("the fallback escapes markup", out, "a &lt;b&gt; &amp; c")
+
+	-- Large output leaves in slices, and a byte lost at a boundary would
+	-- put the line numbers beside it out of step, so the whole escaped
+	-- blob has to come back intact across several slices.
+	out = render("big.fake", string.rep("x<y>", 30000))
+	h.equals("slicing loses nothing at the boundaries", out,
+		string.rep("x&lt;y&gt;", 30000))
+
+	h.finish()
+end
+
+local out, ret = render("hello.fake", "if 42 'hi' & zz")
+h.contains("keywords are wrapped in their class", out,
+	"<span class='hl-keyword'>if</span>")
+h.contains("numbers are wrapped in their class", out,
+	"<span class='hl-number'>42</span>")
+h.contains("a dotted tag maps by its first component", out,
+	"<span class='hl-string'>'hi'</span>")
+h.contains("bytes between tokens are escaped", out, " &amp; ")
+h.contains("later tokens still highlight", out,
+	"<span class='hl-keyword'>zz</span>")
+h.equals("close answers zero", ret, 0)
+
+out = h.run({ "split.fake" }, { "i", "f" })
+h.equals("writes are joined before lexing", out,
+	"<span class='hl-keyword'>if</span>")
+
+-- The short lexer tags four bytes and stops, and every byte after it still
+-- has to reach the page.
+out = render("cut.short", "abcd<ef>")
+h.equals("a lexer stopping early leaves an escaped tail", out,
+	"<span class='hl-keyword'>abcd</span>&lt;ef&gt;")
+
+out = render("boom.badlex", "some <code>")
+h.equals("a lexer that raises falls back to escaped text", out,
+	"some &lt;code&gt;")
+
+-- The viadetect lexer name only resolves through detect(), so highlighted
+-- output proves the detection path ran ahead of the extension path.
+out = render("script.viadetect", "if")
+h.equals("filename detection picks the lexer", out,
+	"<span class='hl-keyword'>if</span>")
+
+out = render("tool.py", "import <x>")
+h.equals("an extension with no lexer serves escaped text", out,
+	"import &lt;x&gt;")
+
+out = render("noextension", "words <here>")
+h.equals("a file with no extension serves escaped text", out,
+	"words &lt;here&gt;")
+
+out = render("big.fake", string.rep("a", 512 * 1024 + 1))
+h.excludes("an oversized blob skips the lexing pass", out, "<span")
+h.equals("and still arrives whole", #out, 512 * 1024 + 1)
+
+out, ret = render("empty.fake", "")
+h.equals("an empty blob renders empty", out, "")
+h.equals("an empty blob still answers zero", ret, 0)
+
+-- cgit's C sink stops at the first NUL byte, which the script documents for
+-- binaries that slip past the text detection.
+out = render("blob.bin", "ab\0cd")
+h.contains("bytes before a nul survive", out, "ab")
+h.excludes("bytes after a nul are dropped", out, "cd")
+
+h.finish()