[PATCH] highlight: Only pygmentize for HTML mimetypes

[Rocco Rutte]

Hi,

* Dirkjan Ochtman wrote:
> Rocco Rutte <pdmef <at> gmx.net> writes:
> > - test against "text/html", not just for "html"
> > - use stringify() to render template to string

> Actually, I'm not sure about these.

> For the first, "html" would also match "application/xhtml+xml", which is nice
> (and I don't think there's any downside). Maybe change this back and add a
> comment about why this is a good thing?

The XHTML mimetype was why I first tested for "html" only. Later I
thought this might clash with a file's content-type by accident for
sending out raw revisions... turns out hgweb optimizes this case using
rawfile(). So I added a lengthy comment mentioning both.

> For the second, in crew, templates should always return an iterator over
> strings, so I'd prefer just using ''.join() (should be faster, too).

That wasn't obvious for me, sorry, fixed.

Regards, Rocco

# HG changeset patch
# User Rocco Rutte <pdmef at gmx.net>
# Date 1220521459 -7200
# Node ID 98170e45ca39639f4fa2e6ca8c9a0b061f0772de
# Parent  6c4a08270222569ba906f4f1c7860783eec19225
highlight: Only pygmentize for HTML mimetypes

For non-html mimetypes it doesn't make much sense. This also fixes the
issue that highlight unconditionally adds a <link/> tag for its CSS to
the template's header (which is pointless in text/plain output).

diff --git a/hgext/highlight/__init__.py b/hgext/highlight/__init__.py
--- a/hgext/highlight/__init__.py
+++ b/hgext/highlight/__init__.py
@@ -25,14 +25,25 @@ web_annotate = webcommands.annotate
 web_annotate = webcommands.annotate
 
 def filerevision_highlight(web, tmpl, fctx):
-    style = web.config('web', 'pygments_style', 'colorful')
-    highlight.pygmentize('fileline', fctx, style, tmpl)
+    mt = ''.join(tmpl('mimetype', encoding=web.encoding))
+    # only pygmentize for mimetype containing 'html' so we both match
+    # 'text/html' and possibly 'application/xhtml+xml' in the future
+    # so that we don't have to touch the extension when the mimetype
+    # for a template changes; also hgweb optimizes the case that a
+    # raw file is sent using rawfile() and doesn't call us, so we
+    # can't clash with the file's content-type here in case we
+    # pygmentize a html file
+    if 'html' in mt:
+        style = web.config('web', 'pygments_style', 'colorful')
+        highlight.pygmentize('fileline', fctx, style, tmpl)
     return web_filerevision(web, tmpl, fctx)
 
 def annotate_highlight(web, req, tmpl):
-    fctx = webutil.filectx(web.repo, req)
-    style = web.config('web', 'pygments_style', 'colorful')
-    highlight.pygmentize('annotateline', fctx, style, tmpl)
+    mt = ''.join(tmpl('mimetype', encoding=web.encoding))
+    if 'html' in mt:
+        fctx = webutil.filectx(web.repo, req)
+        style = web.config('web', 'pygments_style', 'colorful')
+        highlight.pygmentize('annotateline', fctx, style, tmpl)
     return web_annotate(web, req, tmpl)
 
 def generate_css(web, req, tmpl):
diff --git a/tests/test-highlight b/tests/test-highlight
--- a/tests/test-highlight
+++ b/tests/test-highlight
@@ -18,14 +18,47 @@ hg serve -p $HGPORT -d -n test --pid-fil
 hg serve -p $HGPORT -d -n test --pid-file=hg.pid -A access.log -E errors.log
 cat hg.pid >> $DAEMON_PIDS
 
-echo % hgweb filerevision
+echo % hgweb filerevision, html
 ("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/file/tip/get-with-headers.py') \
     | sed "s/[0-9]* years ago/long ago/g"
 
-echo % hgweb fileannotate
+echo % hgweb fileannotate, html
 ("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/annotate/tip/get-with-headers.py') \
     | sed "s/[0-9]* years ago/long ago/g"
 
+echo % hgweb fileannotate, raw
+("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/annotate/tip/get-with-headers.py?style=raw') \
+    | sed "s/^test at 0:/0:/" > a
+
+echo "200 Script output follows" > b
+echo "" >> b
+echo "" >> b
+hg annotate "get-with-headers.py" >> b
+echo "" >> b
+echo "" >> b
+echo "" >> b
+echo "" >> b
+
+S1=`"$TESTDIR/md5sum.py" a | sed 's/a$//'`
+S2=`"$TESTDIR/md5sum.py" b | sed 's/b$//'`
+
+test "$S1" = "$S2" && echo "annotate ok" || echo "annotate fail"
+
+echo
+echo % hgweb filerevision, raw
+("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/file/tip/get-with-headers.py?style=raw') \
+    > a
+
+echo "200 Script output follows" > b
+echo "" >> b
+hg cat get-with-headers.py >> b
+
+S1=`"$TESTDIR/md5sum.py" a | sed 's/a$//'`
+S2=`"$TESTDIR/md5sum.py" b | sed 's/b$//'`
+
+test "$S1" = "$S2" && echo "cat ok" || echo "cat fail"
+
+echo
 echo % hgweb highlightcss friendly
 "$TESTDIR/get-with-headers.py" localhost:$HGPORT '/highlightcss' > out
 head -n 4 out
diff --git a/tests/test-highlight.out b/tests/test-highlight.out
--- a/tests/test-highlight.out
+++ b/tests/test-highlight.out
@@ -1,6 +1,6 @@ adding get-with-headers.py
 adding get-with-headers.py
 % hg serve
-% hgweb filerevision
+% hgweb filerevision, html
 200 Script output follows
 
 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
@@ -63,7 +63,7 @@ 200 Script output follows
 </body>
 </html>
 
-% hgweb fileannotate
+% hgweb fileannotate, html
 200 Script output follows
 
 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
@@ -130,6 +130,12 @@ 200 Script output follows
 </body>
 </html>
 
+% hgweb fileannotate, raw
+annotate ok
+
+% hgweb filerevision, raw
+cat ok
+
 % hgweb highlightcss friendly
 200 Script output follows