Keep a readme whole past a NUL byte

cgit takes filter output through a C string sink that stops at the
first NUL, so a readme holding one lost everything after it. Each NUL
now shows as U+FFFD, as a browser would show it.

2 files changed, 25 insertions, 8 deletions

diff --git a/custom/extensions/about-render.lua b/custom/extensions/about-render.luaindex 1e59716..d7753a3 100644--- a/custom/extensions/about-render.lua+++ b/custom/extensions/about-render.lua@@ -820,9 +820,27 @@ function filter_write(str) end  -- cgit takes filter output through a C string sink that stops at the first--- NUL byte, so a write holding one loses everything from the NUL on.+-- NUL byte, so each one becomes U+FFFD, as a browser would show it, and the+-- text past it survives. A plain find works on Lua 5.1, where a NUL cannot+-- sit in a pattern.+local function replace_nul(text)+	if not text:find("\0", 1, true) then+		return text+	end+	local parts, start = {}, 1+	while true do+		local at = text:find("\0", start, true)+		if not at then+			parts[#parts + 1] = text:sub(start)+			return table.concat(parts, "\239\191\189")+		end+		parts[#parts + 1] = text:sub(start, at - 1)+		start = at + 1+	end+end+ function filter_close()-	local text = table.concat(chunks)+	local text = replace_nul(table.concat(chunks)) 	chunks = {} 	local ext = (filename:match("%.([^.]+)$") or ""):lower() 	local render = handlers[ext] or render_plaintext
diff --git a/custom/extensions/about-render.lua b/custom/extensions/about-render.lua
index 1e59716..d7753a3 100644
--- a/custom/extensions/about-render.lua
+++ b/custom/extensions/about-render.lua
@@ -820,9 +820,27 @@ function filter_write(str)
 end
 
 -- cgit takes filter output through a C string sink that stops at the first
--- NUL byte, so a write holding one loses everything from the NUL on.
+-- NUL byte, so each one becomes U+FFFD, as a browser would show it, and the
+-- text past it survives. A plain find works on Lua 5.1, where a NUL cannot
+-- sit in a pattern.
+local function replace_nul(text)
+	if not text:find("\0", 1, true) then
+		return text
+	end
+	local parts, start = {}, 1
+	while true do
+		local at = text:find("\0", start, true)
+		if not at then
+			parts[#parts + 1] = text:sub(start)
+			return table.concat(parts, "\239\191\189")
+		end
+		parts[#parts + 1] = text:sub(start, at - 1)
+		start = at + 1
+	end
+end
+
 function filter_close()
-	local text = table.concat(chunks)
+	local text = replace_nul(table.concat(chunks))
 	chunks = {}
 	local ext = (filename:match("%.([^.]+)$") or ""):lower()
 	local render = handlers[ext] or render_plaintext
diff --git a/tests/extensions/test-about-render.lua b/tests/extensions/test-about-render.luaindex 4d92882..c4b16a8 100644--- a/tests/extensions/test-about-render.lua+++ b/tests/extensions/test-about-render.lua@@ -48,12 +48,11 @@ out = render(nil, "no name at all") h.contains("a missing filename renders as plain text", out, 	"<pre class='plaintext'>no name at all</pre>") --- cgit's C sink stops at the first NUL byte, which the script documents, so--- the text past one is lost while the wrapper written separately survives.-out = render("README", "before\0after")-h.contains("text before a nul byte survives", out, "before")-h.excludes("text after a nul byte is dropped", out, "after")-h.contains("the wrapper written after the text survives", out, "</pre>")+-- cgit's C sink stops at the first NUL byte, so the script replaces each one+-- before anything is written, and the text past it survives.+out = render("README", "before\0after\0")+h.contains("a nul byte shows as a replacement character", out,+	"<pre class='plaintext'>before\239\191\189after\239\191\189</pre>")  out = h.run({ "README" }, { "two ", "writes" }) h.contains("writes are joined before rendering", out, "two writes")
diff --git a/tests/extensions/test-about-render.lua b/tests/extensions/test-about-render.lua
index 4d92882..c4b16a8 100644
--- a/tests/extensions/test-about-render.lua
+++ b/tests/extensions/test-about-render.lua
@@ -48,12 +48,11 @@ out = render(nil, "no name at all")
 h.contains("a missing filename renders as plain text", out,
 	"<pre class='plaintext'>no name at all</pre>")
 
--- cgit's C sink stops at the first NUL byte, which the script documents, so
--- the text past one is lost while the wrapper written separately survives.
-out = render("README", "before\0after")
-h.contains("text before a nul byte survives", out, "before")
-h.excludes("text after a nul byte is dropped", out, "after")
-h.contains("the wrapper written after the text survives", out, "</pre>")
+-- cgit's C sink stops at the first NUL byte, so the script replaces each one
+-- before anything is written, and the text past it survives.
+out = render("README", "before\0after\0")
+h.contains("a nul byte shows as a replacement character", out,
+	"<pre class='plaintext'>before\239\191\189after\239\191\189</pre>")
 
 out = h.run({ "README" }, { "two ", "writes" })
 h.contains("writes are joined before rendering", out, "two writes")