def __init__(self, filter=None):
self._formatter = NullFormatter()
self._lexer = Python3Lexer(ensurenl=False, stripnl=False)
self._lexer.add_filter("tokenmerge")
if filter is None:
filter = ConverterFilter()
self._lexer.add_filter(filter)
def get_api_from_file(filename):
"""
@filename - source file to parse and extract API symbols
@return - string - API definition
Extract API symbols from a source file.
"""
lex = None
# start language definitions - sorted by lang name
if filename.lower().endswith('.java'):
lex = lexers.JavaLexer()
lex.add_filter(filters.JavaAPIFilter())
elif filename.lower().endswith('.php'):
lex = lexers.PhpLexer(startinline=True)
lex.add_filter(filters.PHPAPIFilter())
elif filename.lower().endswith('.py'):
lex = lexers.PythonLexer()
lex.add_filter(filters.PythonAPIFilter())
# end language definitions
if lex:
code = open(filename, 'r').read()
return highlight(code, lex, NullFormatter())+"\n"
else:
return None
def redent(s):
"""
Shamelessly stolen from infobob(#python bot) code
https://code.launchpad.net/~pound-python/infobat/infobob
"""
lexer = PythonLexer()
lexer.add_filter(_RedentFilter())
return highlight(s, lexer, NullFormatter())
def paste_raw_all(id):
data = query_db("select * from pastes where id = ?", [id], one=True)
try:
Lexer = get_lexer_by_name(data["syntaxhighlight"].lower())
except:
Lexer = get_lexer_by_name("python")
return Response(highlight(data["text"], Lexer, NullFormatter()),
mimetype="text/plain")
def test_correct_output():
hfmt = HtmlFormatter(nowrap=True)
houtfile = StringIO()
hfmt.format(tokensource, houtfile)
nfmt = NullFormatter()
noutfile = StringIO()
nfmt.format(tokensource, noutfile)
stripped_html = re.sub('<.*?>', '', houtfile.getvalue())
escaped_text = escape_html(noutfile.getvalue())
assert stripped_html == escaped_text
def test_correct_output(self):
hfmt = CodeHtmlFormatter(instance_class=type, nowrap=True)
houtfile = StringIO()
hfmt.format(tokensource, houtfile)
nfmt = NullFormatter()
noutfile = StringIO()
nfmt.format(tokensource, noutfile)
stripped_html = re.sub('<.*?>', '', houtfile.getvalue())
escaped_text = escape_html(noutfile.getvalue())
self.assertEqual(stripped_html, escaped_text)
if (closing_char) and def_started:
def_started = False
# for cases such as array(); - value is ();
if len(svalue) > 1:
yield token.Text, svalue[:-1]
yield token.Text, "\n"
if def_started:
yield ttype, value
if __name__ == "__main__":
import os
from pygments import highlight
from pygments.lexers import PhpLexer
from pygments.formatters import NullFormatter
lex = PhpLexer(startinline=True)
lex.add_filter(PHPAPIFilter())
for (path, dirs, files) in os.walk('~/repos/git/symfony/src'):
for fname in files:
f = os.path.join(path, fname)
if f.endswith(".php"):
code = open(f, 'r').read()
print "---------- start %s ----------" % f
print highlight(code, lex, NullFormatter())
print "---------- end %s ----------" % f
for filename in os.listdir(INPUT_DIR):
if filename.startswith('.'):
continue
with open(os.path.join(INPUT_DIR, filename), encoding='utf-8') as f:
code = f.read()
if filename.endswith('.ansi'):
lexer = ANSILexer()
else:
lexer = get_lexer_for_filename(filename)
lexer.add_filter(Sublette.filter())
highlighted = highlight(code, lexer, formatter)
# Detect size by output instead of input.
text = highlight(code, lexer, NullFormatter())
lines = text.split('\n')
columns = max(len(line.rstrip()) for line in lines)
rows = len(lines)
html = weasyprint.HTML(string=TEMPLATE % {
'css': formatter.get_style_defs('body'),
'html': highlighted,
'width': (columns+4) * 15,
'height': (rows+2) * 30,
})
output_path = OUTPUT_PATTERN % filename
with open(output_path, 'wb') as f:
html.write_png(f, font_config=font_config)
print(os.path.relpath(output_path, os.path.curdir))
def redent(s):
lexer = PythonLexer()
lexer.add_filter(_RedentFilter())
return highlight(s, lexer, NullFormatter())