md2html: rewrite relative image links to the plain/ blob URL

A README's relative image paths (screenshots/foo.png) are repo blobs that
cgit only serves via its plain command, but a browser resolves a relative
<img src> against the about-page URL, so the image 404s. Rewrite relative
<img src> to an absolute /<repo>/plain/<path>?h=<branch> URL using the
CGIT_REPO_URL / CGIT_REPO_DEFBRANCH environment cgit gives the about-filter.
Absolute so it also works with ui-summary readme rendering.

1 files changed, 28 insertions, 3 deletions

diff --git a/filters/html-converters/md2html b/filters/html-converters/md2html
index 59f43a8..de393c7 100755
--- a/filters/html-converters/md2html
+++ b/filters/html-converters/md2html
@@ -288,10 +288,10 @@ sys.stdout.write(HtmlFormatter(style='pastie').get_style_defs('.highlight'))
 sys.stdout.write('''
 </style>   
 ''')
-sys.stdout.write("<div class='markdown-body'>")
-sys.stdout.flush()
+# Render to a string (not straight to stdout) so we can post-process it.
 # Note: you may want to run this through bleach for sanitization
-markdown.markdownFromFile(
+html = markdown.markdown(
+	sys.stdin.read(),
 	output_format="html5",
 	extensions=[
 		"markdown.extensions.fenced_code",
@@ -301,4 +301,29 @@ markdown.markdownFromFile(
 		TocExtension(anchorlink=True)],
 	extension_configs={
 		"markdown.extensions.codehilite":{"css_class":"highlight"}})
+
+# A README's relative image paths (e.g. screenshots/x.png) are repo blobs, which
+# cgit only serves via its `plain` command; but a browser resolves a relative
+# <img src> against the about-page URL (/<repo>/about/), so the image 404s.
+# Rewrite relative <img src> to an absolute /<repo>/plain/<path>?h=<branch> URL
+# (absolute so it also works where cgit renders the readme on the summary page).
+# cgit exports the repo context to about-filters via these environment vars; if
+# they're absent we leave the src untouched.
+import os, re
+repo = os.environ.get("CGIT_REPO_URL", "").strip("/")
+if repo:
+	branch = os.environ.get("CGIT_REPO_DEFBRANCH", "").strip()
+	plain = "/" + repo + "/plain/"
+	query = ("?h=" + branch) if branch else ""
+	# leave absolute, protocol-relative, root-relative, anchor and data: URLs alone
+	skip = re.compile(r"^(?:[a-z][a-z0-9+.\-]*:|//|/|#)", re.I)
+	def rewrite(m):
+		url = m.group(2)
+		if not url or skip.match(url):
+			return m.group(0)
+		return m.group(1) + plain + re.sub(r"^\./", "", url) + query + m.group(3)
+	html = re.sub(r'(<img\b[^>]*?\bsrc=")([^"]*)(")', rewrite, html, flags=re.I)
+
+sys.stdout.write("<div class='markdown-body'>")
+sys.stdout.write(html)
 sys.stdout.write("</div>")