[PATCH v3 1/2] filters: Improved syntax-highlighting.py

[Stefan Tatschner]

- Switched back to python2 according to a problem in pygments with python3.
  With the next release of pygments this problem should be fixed.
  Issue see here:
  https://bitbucket.org/birkenfeld/pygments-main/issue/901/problems-with-python3
- Just read the stdin, decode it to utf-8 and ignore unknown signs. This ensures
  that even destroyed files do not cause any errors in the filter.
- Improved language guessing:
  -> At first use guess_lexer_for_filename for a better detection of the used
     programming languages (even mixed cases will be detected, e.g. php + html).
  -> If nothing was found look if there is a shebang and use guess_lexer.
  -> As default/fallback choose TextLexer.

Signed-off-by: Stefan Tatschner <stefan at sevenbyte.org>
---
 filters/syntax-highlighting.py | 52 +++++++++++++++++++++++++++---------------
 1 file changed, 33 insertions(+), 19 deletions(-)

diff --git a/filters/syntax-highlighting.py b/filters/syntax-highlighting.py
index 72d9097..53081a4 100755
--- a/filters/syntax-highlighting.py
+++ b/filters/syntax-highlighting.py
@@ -1,13 +1,16 @@
-#!/usr/bin/env python3
+#!/usr/bin/env python2
 
-# This script uses Pygments and Python3. You must have both installed for this to work.
+# This script uses Pygments and Python2. You must have both installed
+# for this to work.
+#
 # http://pygments.org/
 # http://python.org/
 #
-# It may be used with the source-filter or repo.source-filter settings in cgitrc.
+# It may be used with the source-filter or repo.source-filter settings
+# in cgitrc.
 #
-# The following environment variables can be used to retrieve the configuration
-# of the repository for which this script is called:
+# The following environment variables can be used to retrieve the
+# configuration of the repository for which this script is called:
 # CGIT_REPO_URL        ( = repo.url       setting )
 # CGIT_REPO_NAME       ( = repo.name      setting )
 # CGIT_REPO_PATH       ( = repo.path      setting )
@@ -18,22 +21,33 @@
 
 
 import sys
-import cgi
-import codecs
-from pygments.lexers import get_lexer_for_filename
 from pygments import highlight
+from pygments.util import ClassNotFound
+from pygments.lexers import TextLexer
+from pygments.lexers import guess_lexer
+from pygments.lexers import guess_lexer_for_filename
 from pygments.formatters import HtmlFormatter
 
-sys.stdin = codecs.getreader("utf-8")(sys.stdin.detach())
-sys.stdout = codecs.getwriter("utf-8")(sys.stdout.detach())
-doc = sys.stdin.read()
+
+# read stdin and decode to utf-8. ignore any unkown signs.
+data = sys.stdin.read().decode(encoding='utf-8', errors='ignore')
+filename = sys.argv[1]
+formatter = HtmlFormatter(encoding='utf-8', style='pastie')
+
 try:
-	lexer = get_lexer_for_filename(sys.argv[1])
-	formatter = HtmlFormatter(style='pastie')
-	sys.stdout.write("<style>")
-	sys.stdout.write(formatter.get_style_defs('.highlight'))
-	sys.stdout.write("</style>")
+    lexer = guess_lexer_for_filename(filename, data, encoding='utf-8')
+except ClassNotFound:
+    # check if there is any shebang
+    if data[0:2] == '#!':
+        lexer = guess_lexer(data, encoding='utf-8')
+    else:
+        lexer = TextLexer(encoding='utf-8')
+except TypeError:
+    lexer = TextLexer(encoding='utf-8')
 
-	highlight(doc, lexer, formatter, sys.stdout)
-except:
-	sys.stdout.write(str(cgi.escape(doc).encode("ascii", "xmlcharrefreplace"), "ascii"))
+# highlight! :-)
+# printout pygments' css definitions as well
+sys.stdout.write('<style>')
+sys.stdout.write(formatter.get_style_defs('.highlight'))
+sys.stdout.write('</style>')
+highlight(data, lexer, formatter, outfile=sys.stdout)
-- 
1.8.5.2