| 1 |
""" |
|---|
| 2 |
Original code from active state recipe |
|---|
| 3 |
'Colorize Python source using the built-in tokenizer' |
|---|
| 4 |
|
|---|
| 5 |
---------------------------------------------------------------------------- |
|---|
| 6 |
MoinMoin - Python Source Parser |
|---|
| 7 |
|
|---|
| 8 |
This code is part of MoinMoin (http://moin.sourceforge.net/) and converts |
|---|
| 9 |
Python source code to HTML markup, rendering comments, keywords, operators, |
|---|
| 10 |
numeric and string literals in different colors. |
|---|
| 11 |
|
|---|
| 12 |
It shows how to use the built-in keyword, token and tokenize modules |
|---|
| 13 |
to scan Python source code and re-emit it with no changes to its |
|---|
| 14 |
original formatting (which is the hard part). |
|---|
| 15 |
""" |
|---|
| 16 |
__revision__ = '$Id$' |
|---|
| 17 |
|
|---|
| 18 |
import string |
|---|
| 19 |
import keyword, token, tokenize |
|---|
| 20 |
from cStringIO import StringIO |
|---|
| 21 |
|
|---|
| 22 |
from Products.PortalTransforms.interfaces import itransform |
|---|
| 23 |
|
|---|
| 24 |
|
|---|
| 25 |
## Python Source Parser ##################################################### |
|---|
| 26 |
|
|---|
| 27 |
_KEYWORD = token.NT_OFFSET + 1 |
|---|
| 28 |
_TEXT = token.NT_OFFSET + 2 |
|---|
| 29 |
|
|---|
| 30 |
class Parser: |
|---|
| 31 |
""" Send colored python source. |
|---|
| 32 |
""" |
|---|
| 33 |
|
|---|
| 34 |
def __init__(self, raw, tags, out): |
|---|
| 35 |
""" Store the source text. |
|---|
| 36 |
""" |
|---|
| 37 |
self.raw = string.strip(string.expandtabs(raw)) |
|---|
| 38 |
self.out = out |
|---|
| 39 |
self.tags = tags |
|---|
| 40 |
|
|---|
| 41 |
def format(self): |
|---|
| 42 |
""" Parse and send the colored source. |
|---|
| 43 |
""" |
|---|
| 44 |
# store line offsets in self.lines |
|---|
| 45 |
self.lines = [0, 0] |
|---|
| 46 |
pos = 0 |
|---|
| 47 |
while 1: |
|---|
| 48 |
pos = string.find(self.raw, '\n', pos) + 1 |
|---|
| 49 |
if not pos: break |
|---|
| 50 |
self.lines.append(pos) |
|---|
| 51 |
self.lines.append(len(self.raw)) |
|---|
| 52 |
|
|---|
| 53 |
# parse the source and write it |
|---|
| 54 |
self.pos = 0 |
|---|
| 55 |
text = StringIO(self.raw) |
|---|
| 56 |
self.out.write('<pre class="python">\n') |
|---|
| 57 |
try: |
|---|
| 58 |
tokenize.tokenize(text.readline, self) |
|---|
| 59 |
except tokenize.TokenError, ex: |
|---|
| 60 |
msg = ex[0] |
|---|
| 61 |
line = ex[1][0] |
|---|
| 62 |
self.out.write("<h5 class='error>'ERROR: %s%s</h5>" % ( |
|---|
| 63 |
msg, self.raw[self.lines[line]:])) |
|---|
| 64 |
self.out.write('\n</pre>\n') |
|---|
| 65 |
|
|---|
| 66 |
def __call__(self, toktype, toktext, (srow,scol), (erow,ecol), line): |
|---|
| 67 |
""" Token handler. |
|---|
| 68 |
""" |
|---|
| 69 |
#print "type", toktype, token.tok_name[toktype], "text", toktext, |
|---|
| 70 |
#print "start", srow,scol, "end", erow,ecol, "<br>" |
|---|
| 71 |
|
|---|
| 72 |
## calculate new positions |
|---|
| 73 |
oldpos = self.pos |
|---|
| 74 |
newpos = self.lines[srow] + scol |
|---|
| 75 |
self.pos = newpos + len(toktext) |
|---|
| 76 |
|
|---|
| 77 |
## handle newlines |
|---|
| 78 |
if toktype in [token.NEWLINE, tokenize.NL]: |
|---|
| 79 |
self.out.write('\n') |
|---|
| 80 |
return |
|---|
| 81 |
|
|---|
| 82 |
## send the original whitespace, if needed |
|---|
| 83 |
if newpos > oldpos: |
|---|
| 84 |
self.out.write(self.raw[oldpos:newpos]) |
|---|
| 85 |
|
|---|
| 86 |
## skip indenting tokens |
|---|
| 87 |
if toktype in [token.INDENT, token.DEDENT]: |
|---|
| 88 |
self.pos = newpos |
|---|
| 89 |
return |
|---|
| 90 |
|
|---|
| 91 |
## map token type to a group |
|---|
| 92 |
if token.LPAR <= toktype and toktype <= token.OP: |
|---|
| 93 |
toktype = 'OP' |
|---|
| 94 |
elif toktype == token.NAME and keyword.iskeyword(toktext): |
|---|
| 95 |
toktype = 'KEYWORD' |
|---|
| 96 |
else: |
|---|
| 97 |
toktype = tokenize.tok_name[toktype] |
|---|
| 98 |
|
|---|
| 99 |
open_tag = self.tags.get('OPEN_'+toktype, self.tags['OPEN_TEXT']) |
|---|
| 100 |
close_tag = self.tags.get('CLOSE_'+toktype, self.tags['CLOSE_TEXT']) |
|---|
| 101 |
|
|---|
| 102 |
## send text |
|---|
| 103 |
self.out.write(open_tag) |
|---|
| 104 |
self.out.write(toktext) |
|---|
| 105 |
self.out.write(close_tag) |
|---|
| 106 |
|
|---|
| 107 |
|
|---|
| 108 |
|
|---|
| 109 |
class PythonTransform: |
|---|
| 110 |
"""Colorize Python source files |
|---|
| 111 |
""" |
|---|
| 112 |
__implements__ = itransform |
|---|
| 113 |
|
|---|
| 114 |
__name__ = "python_to_html" |
|---|
| 115 |
inputs = ("text/x-python",) |
|---|
| 116 |
output = "text/html" |
|---|
| 117 |
|
|---|
| 118 |
config = { |
|---|
| 119 |
'OPEN_NUMBER': '<font color="#0080C0">', |
|---|
| 120 |
'CLOSE_NUMBER': '</font>', |
|---|
| 121 |
'OPEN_OP': '<font color="#0000C0">', |
|---|
| 122 |
'CLOSE_OP': '</font>', |
|---|
| 123 |
'OPEN_STRING': '<font color="#004080">', |
|---|
| 124 |
'CLOSE_STRING': '</font>', |
|---|
| 125 |
'OPEN_COMMENT': '<font color="#008000">', |
|---|
| 126 |
'CLOSE_COMMENT': '</font>', |
|---|
| 127 |
'OPEN_NAME': '<font color="#000000">', |
|---|
| 128 |
'CLOSE_NAME': '</font>', |
|---|
| 129 |
'OPEN_ERRORTOKEN': '<font color="#FF8080">', |
|---|
| 130 |
'CLOSE_ERRORTOKEN': '</font>', |
|---|
| 131 |
'OPEN_KEYWORD': '<font color="#C00000">', |
|---|
| 132 |
'CLOSE_KEYWORD': '</font>', |
|---|
| 133 |
'OPEN_TEXT': '', |
|---|
| 134 |
'CLOSE_TEXT': '', |
|---|
| 135 |
} |
|---|
| 136 |
|
|---|
| 137 |
def name(self): |
|---|
| 138 |
return self.__name__ |
|---|
| 139 |
|
|---|
| 140 |
def convert(self, orig, data, **kwargs): |
|---|
| 141 |
dest = StringIO() |
|---|
| 142 |
Parser(orig, self.config, dest).format() |
|---|
| 143 |
data.setData(dest.getvalue()) |
|---|
| 144 |
return data |
|---|
| 145 |
|
|---|
| 146 |
|
|---|
| 147 |
def register(): |
|---|
| 148 |
return PythonTransform() |
|---|