diff --git a/lib/PyFontify.py b/lib/PyFontify.py
index 1b956416..104ce2f6 100644
--- a/lib/PyFontify.py
+++ b/lib/PyFontify.py
@@ -1,152 +1,173 @@
"""Module to analyze Python source code; for syntax coloring tools.
Interface:
- tags = fontify(pytext, searchfrom, searchto)
-The 'pytext' argument is a string containing Python source code.
-The (optional) arguments 'searchfrom' and 'searchto' may contain a slice in pytext.
+ tags = fontify(pytext, searchfrom, searchto)
+
+The PYTEXT argument is a string containing Python source code. The
+(optional) arguments SEARCHFROM and SEARCHTO may contain a slice in
+PYTEXT.
+
The returned value is a list of tuples, formatted like this:
- [('keyword', 0, 6, None), ('keyword', 11, 17, None), ('comment', 23, 53, None), etc. ]
+
+ [('keyword', 0, 6, None),
+ ('keyword', 11, 17, None),
+ ('comment', 23, 53, None),
+ ...
+ ]
+
The tuple contents are always like this:
- (tag, startindex, endindex, sublist)
-tag is one of 'keyword', 'string', 'comment' or 'identifier'
-sublist is not used, hence always None.
+
+ (tag, startindex, endindex, sublist)
+
+TAG is one of 'keyword', 'string', 'comment' or 'identifier'
+SUBLIST is not used, hence always None.
"""
# Based on FontText.py by Mitchell S. Chapman,
# which was modified by Zachary Roadhouse,
# then un-Tk'd by Just van Rossum.
# Many thanks for regular expression debugging & authoring are due to:
-# Tim (the-incredib-ly y'rs) Peters and Cristian Tismer
+# Tim (the-incredib-ly y'rs) Peters and Cristian Tismer
# So, who owns the copyright? ;-) How about this:
# Copyright 1996-1997:
-# Mitchell S. Chapman,
-# Zachary Roadhouse,
-# Tim Peters,
-# Just van Rossum
+# Mitchell S. Chapman,
+# Zachary Roadhouse,
+# Tim Peters,
+# Just van Rossum
__version__ = "0.3.1"
import string, re
-# First a little helper, since I don't like to repeat things. (Tismer speaking)
-def replace(where, what, with):
- return string.join(string.split(where, what), with)
# This list of keywords is taken from ref/node13.html of the
# Python 1.3 HTML documentation. ("access" is intentionally omitted.)
-keywordsList = [
- "del", "from", "lambda", "return",
- "and", "elif", "global", "not", "try",
- "break", "else", "if", "or", "while",
- "class", "except", "import", "pass",
- "continue", "finally", "in", "print",
- "def", "for", "is", "raise"]
-# Build up a regular expression which will match anything
-# interesting, including multi-line triple-quoted strings.
+keywordsList = ["and", "assert", "break", "class", "continue", "def",
+ "del", "elif", "else", "except", "exec", "finally",
+ "for", "from", "global", "if", "import", "in", "is",
+ "lambda", "not", "or", "pass", "print", "raise",
+ "return", "try", "while",
+ ]
+
+# First a little helper, since I don't like to repeat things. (Tismer speaking)
+def replace(where, what, with):
+ return string.join(string.split(where, what), with)
+
+# A regexp for matching Python comments.
commentPat = "#.*"
-pat = "q[^\q\n]*\(\\\\[\000-\377][^\q\n]*\)*q"
-quotePat = replace(pat, "q", "'") + "\|" + replace(pat, 'q', '"')
+# A regexp for matching simple quoted strings.
+pat = "q[^q\\n]*(\\[\000-\377][^q\\n]*)*q"
+quotePat = replace(pat, "q", "'") + "|" + replace(pat, 'q', '"')
-# Way to go, Tim!
+# A regexp for matching multi-line tripled-quoted strings. (Way to go, Tim!)
pat = """
- qqq
- [^\\q]*
- \(
- \( \\\\[\000-\377]
- \| q
- \( \\\\[\000-\377]
- \| [^\\q]
- \| q
- \( \\\\[\000-\377]
- \| [^\\q]
- \)
- \)
- \)
- [^\\q]*
- \)*
- qqq
+ qqq
+ [^q]*
+ (
+ ( \\[\000-\377]
+ | q
+ ( \\[\000-\377]
+ | [^q]
+ | q
+ ( \\[\000-\377]
+ | [^q]
+ )
+ )
+ )
+ [^q]*
+ )*
+ qqq
"""
-pat = string.join(string.split(pat), '') # get rid of whitespace
-tripleQuotePat = replace(pat, "q", "'") + "\|" + replace(pat, 'q', '"')
+pat = string.join(string.split(pat), '') # get rid of whitespace
+tripleQuotePat = replace(pat, "q", "'") + "|" + replace(pat, 'q', '"')
-# Build up a regular expression which matches all and only
-# Python keywords. This will let us skip the uninteresting
-# identifier references.
-# nonKeyPat identifies characters which may legally precede
-# a keyword pattern.
-nonKeyPat = "\(^\|[^a-zA-Z0-9_.\"']\)"
+# A regexp which matches all and only Python keywords. This will let
+# us skip the uninteresting identifier references.
+nonKeyPat = "(^|[^a-zA-Z0-9_.\"'])" # legal keyword-preceding characters
+keyPat = nonKeyPat + "(" + string.join(keywordsList, "|") + ")" + nonKeyPat
-keyPat = nonKeyPat + "\("
-for keyword in keywordsList:
- keyPat = keyPat + keyword + "\|"
-keyPat = keyPat[:-2] + "\)" + nonKeyPat
+# Our final syntax-matching regexp is the concatation of the regexp's we
+# constructed above.
+syntaxPat = keyPat + \
+ "|" + commentPat + \
+ "|" + tripleQuotePat + \
+ "|" + quotePat
+syntaxRE = re.compile(syntaxPat)
-matchPat = keyPat + "\|" + commentPat + "\|" + tripleQuotePat + "\|" + quotePat
-matchRE = re.compile(matchPat)
-
-idKeyPat = "[ \t]*[A-Za-z_][A-Za-z_0-9.]*" # Ident w. leading whitespace.
+# Finally, we construct a regexp for matching indentifiers (with
+# optional leading whitespace).
+idKeyPat = "[ \t]*[A-Za-z_][A-Za-z_0-9.]*"
idRE = re.compile(idKeyPat)
-def fontify(pytext, searchfrom = 0, searchto = None):
- if searchto is None:
- searchto = len(pytext)
- # Cache a few attributes for quicker reference.
- search = matchRE.search
- group = matchRE.group
- idSearch = idRE.search
- idGroup = idRE.group
-
- tags = []
- tags_append = tags.append
- commentTag = 'comment'
- stringTag = 'string'
- keywordTag = 'keyword'
- identifierTag = 'identifier'
-
- start = 0
- end = searchfrom
- while 1:
- start = search(pytext, end)
- if start < 0 or start >= searchto:
- break # EXIT LOOP
- match = group(0)
- end = start + len(match)
- c = match[0]
- if c not in "#'\"":
- # Must have matched a keyword.
- if start <> searchfrom:
- # there's still a redundant char before and after it, strip!
- match = match[1:-1]
- start = start + 1
- else:
- # this is the first keyword in the text.
- # Only a space at the end.
- match = match[:-1]
- end = end - 1
- tags_append((keywordTag, start, end, None))
- # If this was a defining keyword, look ahead to the
- # following identifier.
- if match in ["def", "class"]:
- start = idSearch(pytext, end)
- if start == end:
- match = idGroup(0)
- end = start + len(match)
- tags_append((identifierTag, start, end, None))
- elif c == "#":
- tags_append((commentTag, start, end, None))
- else:
- tags_append((stringTag, start, end, None))
- return tags
+def fontify(pytext, searchfrom=0, searchto=None):
+ if searchto is None:
+ searchto = len(pytext)
+ tags = []
+ commentTag = 'comment'
+ stringTag = 'string'
+ keywordTag = 'keyword'
+ identifierTag = 'identifier'
+
+ start = 0
+ end = searchfrom
+ while 1:
+ # Look for some syntax token we're interested in. If find
+ # nothing, we're done.
+ matchobj = syntaxRE.search(pytext, end)
+ if not matchobj:
+ break
+
+ # If we found something outside our search area, it doesn't
+ # count (and we're done).
+ start = matchobj.start()
+ if start >= searchto:
+ break
+
+ match = matchobj.group(0)
+ end = start + len(match)
+ c = match[0]
+ if c == '#':
+ # We matched a comment.
+ tags.append((commentTag, start, end, None))
+ elif c == '"' or c == '\'':
+ # We matched a string.
+ tags.append((stringTag, start, end, None))
+ else:
+ # We matched a keyword.
+ if start != searchfrom:
+ # there's still a redundant char before and after it, strip!
+ match = match[1:-1]
+ start = start + 1
+ else:
+ # This is the first keyword in the text.
+ # Only a space at the end.
+ match = match[:-1]
+ end = end - 1
+ tags.append((keywordTag, start, end, None))
+ # If this was a defining keyword, look ahead to the
+ # following identifier.
+ if match in ["def", "class"]:
+ matchobj = idRE.search(pytext, end)
+ if matchobj:
+ start = matchobj.start()
+ if start == end and start < searchto:
+ end = start + len(matchobj.group(0))
+ tags.append((identifierTag, start, end, None))
+ return tags
def test(path):
- f = open(path)
- text = f.read()
- f.close()
- tags = fontify(text)
- for tag, start, end, sublist in tags:
- print tag, `text[start:end]`
+ f = open(path)
+ text = f.read()
+ f.close()
+ tags = fontify(text)
+ for tag, start, end, sublist in tags:
+ print tag, `text[start:end]`
+
+if __name__ == "__main__":
+ import sys
+ test(sys.argv[0])
diff --git a/lib/py2html.py b/lib/py2html.py
index f86d780e..3c8c9912 100755
--- a/lib/py2html.py
+++ b/lib/py2html.py
@@ -1,6 +1,6 @@
-#!/usr/local/bin/python -u
+#!/usr/bin/python -u
-""" Python Highlighter for HTML Version: 0.5
+""" Python Highlighter Version: 0.8
py2html.py [options] files...
@@ -10,8 +10,8 @@
-stdout read from files, write to stdout
-files read from files, write to filename+'.html' (default)
-format:
- html output HTML page (default)
- rawhtml output pure HTML (without headers, titles, etc.)
+ html output XHTML page (default)
+ rawhtml output pure XHTML (without headers, titles, etc.)
-mode:
color output in color (default)
mono output b/w (for printing)
@@ -21,11 +21,11 @@
-footer:file use contents of file as footer
-URL replace all occurances of 'URL: link' with
'link'; this is always enabled
- in CGI mode
+ in CGI mode
-v verbose
Takes the input, assuming it is Python code and formats it into
- colored HTML. When called without parameters the script tries to
+ colored XHTML. When called without parameters the script tries to
work in CGI mode. It looks for a field 'script=URL' and tries to
use that URL as input file. If it can't find this field, the path
info (the part of the URL following the CGI script name) is
@@ -34,47 +34,43 @@
* Uses Just van Rossum's PyFontify version 0.3 to tag Python scripts.
You can get it via his homepage on starship:
- URL: http://starship.skyport.net/crew/just
+ URL: http://starship.python.net/crew/just
"""
__comments__ = """
The following snippet is a small shell script I use for viewing
- Python scripts per less on Unix:
+ Python scripts via less on Unix:
+
+pyless:
#!/bin/sh
# Browse pretty printed Python code using ANSI codes for highlighting
-py2html -stdout -format:ansi -mode:mono $* | less -r
+py2html -stdout -format:ansi -mode:color $* | less -r
History:
-
+
+ 0.8: Added patch by Patrick Lynch to have py2html.py use style
+ sheets for markup
+ 0.7: Added patch by Ville Skyttä to make py2html.py output
+ valid XHTML.
+ 0.6: Fixed a bug in .escape_html(); thanks to Vespe Savikko for
+ finding this one.
0.5: Added a few suggestions by Kevin Ng to make the CGI version
a little more robust.
"""
-__copyright__ = """
------------------------------------------------------------------------------
-(c) Copyright by Marc-Andre Lemburg, 1998 (mailto:mal@lemburg.com)
-
- Permission to use, copy, modify, and distribute this software and its
- documentation for any purpose and without fee or royalty is hereby granted,
- provided that the above copyright notice appear in all copies and that
- both that copyright notice and this permission notice appear in
- supporting documentation or portions thereof, including modifications,
- that you make.
-
- THE AUTHOR MARC-ANDRE LEMBURG DISCLAIMS ALL WARRANTIES WITH REGARD TO
- THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
- FITNESS, IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL,
- INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING
- FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
- NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION
- WITH THE USE OR PERFORMANCE OF THIS SOFTWARE !
+__copyright__ = """\
+ Copyright (c) 1998-2000, Marc-Andre Lemburg; mailto:mal@lemburg.com
+ Copyright (c) 2000-2002, eGenix.com Software GmbH; mailto:info@egenix.com
+ Distributed under the terms and conditions of the eGenix.com Public
+ License. See http://www.egenix.com/files/python/mxLicense.html for
+ details, or contact the author. All Rights Reserved.\
"""
-__version__ = '0.5'
+__version__ = '0.8'
__cgifooter__ = ('\n# code highlighted using py2html.py '
- 'version %s
\n' % __version__)
+ '"http://www.lemburg.com/files/python/">py2html.py '
+ 'version %s\n' % __version__)
import sys,string,re
@@ -86,21 +82,25 @@ sys.path.append('.')
# URL of the input form the user is redirected to in case no script=xxx
# form field is given. The URL *must* be absolute. Leave blank to
# have the script issue an error instead.
-INPUT_FORM = 'http://starship.skyport.net/~lemburg/SoftwareDescriptions.html#py2html.py'
+INPUT_FORM = 'http://www.lemburg.com/files/python/SoftwareDescriptions.html#py2html.py'
+
+# HTML DOCTYPE and XML namespace
+HTML_DOCTYPE = ''
+HTML_XMLNS = ' xmlns="http://www.w3.org/1999/xhtml"'
### Helpers
def fileio(file, mode='rb', data=None, close=0):
if type(file) == type(''):
- f = open(file,mode)
- close = 1
+ f = open(file,mode)
+ close = 1
else:
- f = file
+ f = file
if data:
- f.write(data)
+ f.write(data)
else:
- data = f.read()
+ data = f.read()
if close: f.close()
return data
@@ -112,35 +112,36 @@ class PrettyPrint:
* supports tagging Python scripts in the following ways:
- # format/mode | color mono
- # --------------------------
- # rawhtml | x x (HTML without headers, etc.)
- # html | x x (a HTML page with HEAD&BODY:)
- # ansi | x (with Ansi-escape sequences)
+ # format/mode | color mono
+ # --------------------------
+ # rawhtml | x x (HTML without headers, etc.)
+ # html | x x (a HTML page with HEAD&BODY:)
+ # ansi | x x (with Ansi-escape sequences)
- * interfaces:
+ * interfaces:
- file_filter -- takes two files: input & output (may be stdin/stdout)
- filter -- takes a string and returns the highlighted version
-
- * to create an instance use:
+ file_filter -- takes two files: input & output (may be stdin/stdout)
+ filter -- takes a string and returns the highlighted version
- c = PrettyPrint(tagfct,format,mode)
+ * to create an instance use:
- where format and mode must be strings according to the
- above table if you plan to use PyFontify.fontify as
- tagfct
+ c = PrettyPrint(tagfct,format,mode)
+
+ where format and mode must be strings according to the
+ above table if you plan to use PyFontify.fontify as
+ tagfct
* the tagfct has to take one argument, text, and return a taglist
- (format: [(id,left,right,sublist),...], where id is the
- "name" given to the slice left:right in text and sublist is a
- taglist for tags inside the slice or None)
+ (format: [(id,left,right,sublist),...], where id is the
+ "name" given to the slice left:right in text and sublist is a
+ taglist for tags inside the slice or None)
"""
# misc settings
title = ''
bgcolor = '#FFFFFF'
+ css = ''
header = ''
footer = ''
replace_URLs = 0
@@ -149,19 +150,19 @@ class PrettyPrint:
def __init__(self,tagfct=None,format='html',mode='color'):
- self.tag = tagfct
- self.set_mode = getattr(self,'set_mode_'+format+'_'+mode)
- self.filter = getattr(self,'filter_'+format)
- self.set_mode()
+ self.tag = tagfct
+ self.set_mode = getattr(self,'set_mode_%s_%s' % (format, mode))
+ self.filter = getattr(self,'filter_%s' % format)
def file_filter(self,infile,outfile):
- text = fileio(infile,'r')
- if type(infile) == type('') and self.title == '':
- self.title = infile
- fileio(outfile,'w',self.filter(text))
+ self.set_mode()
+ text = fileio(infile,'r')
+ if type(infile) == type('') and self.title == '':
+ self.title = infile
+ fileio(outfile,'w',self.filter(text))
- ### set pre- and postfixes for formats & modes
+ ### Set pre- and postfixes for formats & modes
#
# These methods must set self.formats to a dictionary having
# an entry for every tag returned by the tagging function.
@@ -175,134 +176,185 @@ class PrettyPrint:
def set_mode_html_color(self):
- self.formats = {
- 'all':('','
'),
- 'comment':('',''),
- 'keyword':('',''),
- 'parameter':('' % (strip(x)),
- ''),
- 'string':('','')
- }
+ self.css = """
+ """ % self.bgcolor
+
+ self.formats = {
+ 'all':('','
'),
+ 'comment':(''),
+ 'keyword':('',''),
+ 'parameter':('',''),
+ 'identifier':( lambda x,strip=string.strip:
+ '' % (strip(x)),
+ ''),
+ 'string':('','')
+ }
set_mode_rawhtml_color = set_mode_html_color
def set_mode_html_mono(self):
- self.formats = {
- 'all':('','
'),
- 'comment':('',''),
- 'keyword':( '',''),
- 'parameter':('',''),
- 'identifier':( lambda x,strip=string.strip:
- '' % (strip(x)),
- ''),
- 'string':('','')
- }
+ self.css = """
+ """ % self.bgcolor
+
+ self.formats = {
+ 'all':('','
'),
+ 'comment':(''),
+ 'keyword':( '',''),
+ 'parameter':('',''),
+ 'identifier':( lambda x,strip=string.strip:
+ '' % (strip(x)),
+ ''),
+ 'string':('','')
+ }
set_mode_rawhtml_mono = set_mode_html_mono
def set_mode_ansi_mono(self):
- self.formats = {
- 'all':('',''),
- 'comment':('\033[2m','\033[m'),
- 'keyword':('\033[4m','\033[m'),
- 'parameter':('',''),
- 'identifier':('\033[1m','\033[m'),
- 'string':('','')
- }
+ self.formats = {
+ 'all':('',''),
+ 'comment':('\033[2m','\033[m'),
+ 'keyword':('\033[4m','\033[m'),
+ 'parameter':('',''),
+ 'identifier':('\033[1m','\033[m'),
+ 'string':('','')
+ }
- ### filter for Python scripts given as string
+ def set_mode_ansi_color(self):
+
+ self.formats = {
+ 'all':('',''),
+ 'comment':('\033[34;2m','\033[m'),
+ 'keyword':('\033[1;34m','\033[m'),
+ 'parameter':('',''),
+ 'identifier':('\033[1;31m','\033[m'),
+ 'string':('\033[32;2m','\033[m')
+ }
+
+ ### Filters for Python scripts given as string
def escape_html(self,text):
- t = (('<','<'),('>','>'))
- for x,y in t:
- text = string.join(string.split(text,x),y)
- return text
+ t = (('&','&'),('<','<'),('>','>'))
+ for x,y in t:
+ text = string.join(string.split(text,x),y)
+ return text
def filter_html(self,text):
- output = self.fontify(self.escape_html(text))
- if self.replace_URLs:
- output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
- 'URL:\\1\\2',output)
- html = """%s
-
- %s
- %s
- %s
- \n"""%(self.title,self.bgcolor,self.header,output,self.footer)
- return html
+ output = self.fontify(self.escape_html(text))
+ if self.replace_URLs:
+ output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
+ 'URL:\\1\\2',output)
+ html = """%s
+
+ %s
+
+ %s
+
+
+
+ %s
+
+ %s
+
+ %s
+ \n"""%(HTML_DOCTYPE,
+ HTML_XMLNS,
+ self.title,
+ self.css,
+ self.header,
+ output,
+ self.footer)
+ return html
def filter_rawhtml(self,text):
- output = self.fontify(self.escape_html(text))
- if self.replace_URLs:
- output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
- 'URL:\\1\\2',output)
- return self.header+output+self.footer
+ output = self.fontify(self.escape_html(text))
+ if self.replace_URLs:
+ output = re.sub('URL:([ \t]+)([^ \n\r<]+)',
+ 'URL:\\1\\2',output)
+ return self.header + output + self.footer
def filter_ansi(self,text):
- output = self.fontify(text)
- return self.header+output+self.footer
+ output = self.fontify(text)
+ return self.header + output + self.footer
- ### fontify engine
+ ### Fontify engine
def fontify(self,pytext):
- # parse
- taglist = self.tag(pytext)
+ # parse
+ taglist = self.tag(pytext)
- # prepend special 'all' tag:
- taglist[:0] = [('all',0,len(pytext),None)]
+ # prepend special 'all' tag:
+ taglist[:0] = [('all',0,len(pytext),None)]
- # prepare splitting
- splits = []
- addsplits(splits,pytext,self.formats,taglist)
+ # prepare splitting
+ splits = []
+ addsplits(splits,pytext,self.formats,taglist)
- # do splitting & inserting
- splits.sort()
- l = []
- li = 0
- for ri,dummy,insert in splits:
- if ri > li: l.append(pytext[li:ri])
- l.append(insert)
- li = ri
- if li < len(pytext): l.append(pytext[li:])
-
- return string.join(l,'')
+ # do splitting & inserting
+ splits.sort()
+ l = []
+ li = 0
+ for ri,dummy,insert in splits:
+ if ri > li: l.append(pytext[li:ri])
+ l.append(insert)
+ li = ri
+ if li < len(pytext): l.append(pytext[li:])
+
+ return string.join(l,'')
def addsplits(splits,text,formats,taglist):
- # helper for fontify()
+
+ """ Helper for .fontify()
+ """
for id,left,right,sublist in taglist:
- try:
- pre,post = formats[id]
- except KeyError:
- # sys.stderr.write('Warning: no format for %s specified\n'%repr(id))
- pre,post = '',''
- if type(pre) != type(''):
- pre = pre(text[left:right])
- if type(post) != type(''):
- post = post(text[left:right])
- # len(splits) is a dummy used to make sorting stable
- splits.append((left,len(splits),pre))
- if sublist:
- addsplits(splits,text,formats,sublist)
- splits.append((right,len(splits),post))
+ try:
+ pre,post = formats[id]
+ except KeyError:
+ # sys.stderr.write('Warning: no format for %s specified\n'%repr(id))
+ pre,post = '',''
+ if type(pre) != type(''):
+ pre = pre(text[left:right])
+ if type(post) != type(''):
+ post = post(text[left:right])
+ # len(splits) is a dummy used to make sorting stable
+ splits.append((left,len(splits),pre))
+ if sublist:
+ addsplits(splits,text,formats,sublist)
+ splits.append((right,len(splits),post))
def write_html_error(titel,text):
print """\
-html>%s
+%s%s
%s
%s