filters: Improved syntax-highlighting.py

- 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@sevenbyte.org>
This commit is contained in:
Stefan Tatschner 2014-01-13 22:10:45 +01:00 committed by Jason A. Donenfeld
parent a52aaa90da
commit ceffeb5d52

View File

@ -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://pygments.org/
# http://python.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 # The following environment variables can be used to retrieve the
# of the repository for which this script is called: # configuration of the repository for which this script is called:
# CGIT_REPO_URL ( = repo.url setting ) # CGIT_REPO_URL ( = repo.url setting )
# CGIT_REPO_NAME ( = repo.name setting ) # CGIT_REPO_NAME ( = repo.name setting )
# CGIT_REPO_PATH ( = repo.path setting ) # CGIT_REPO_PATH ( = repo.path setting )
@ -18,22 +21,33 @@
import sys import sys
import cgi
import codecs
from pygments.lexers import get_lexer_for_filename
from pygments import highlight 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 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()
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>")
highlight(doc, lexer, formatter, sys.stdout) # read stdin and decode to utf-8. ignore any unkown signs.
except: data = sys.stdin.read().decode(encoding='utf-8', errors='ignore')
sys.stdout.write(str(cgi.escape(doc).encode("ascii", "xmlcharrefreplace"), "ascii")) filename = sys.argv[1]
formatter = HtmlFormatter(encoding='utf-8', style='pastie')
try:
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! :-)
# 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)