floraachy/pytest2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[svn r37594] Fixed unicode issues in apigen/htmlgen.py and apigen/source, moved some methods

Browse Source 
out of HTMLDocument and added support for finding out the encoding of a Python
file in order to accomplish that (both in source/html.py), fixed some minor
issues (items with a name starting with _ are now hidden from nav, fixed
indentation issue in nav) in htmlgen.py.

--HG--
branch : trunk
This commit is contained in:
guido
2007-01-30 14:24:27 +01:00
parent c2e1510f86
commit 45868fe506
5 changed files with 149 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
py/apigen/source/html.py
View File

@@ -2,14 +2,13 @@
""" html - generating ad-hoc html out of source browser
"""
import py
from py.xml import html, raw
from compiler import ast
import time
from py.__.apigen.source.color import Tokenizer, PythonSchema
class HtmlEnchanter(object):
reserved_words = ['if', 'for', 'return', 'yield']
def __init__(self, mod):
self.mod = mod
self.create_caches()
@@ -37,8 +36,30 @@ class HtmlEnchanter(object):
except KeyError:
return [row] # no more info
def prepare_line(text, tokenizer, encoding):
""" adds html formatting to text items (list)
only processes items if they're of a string type (or unicode)
"""
ret = []
for item in text:
if type(item) in [str, unicode]:
tokens = tokenizer.tokenize(item)
for t in tokens:
data = unicode(t.data, encoding)
if t.type in ['keyword', 'alt_keyword', 'number',
'string', 'comment']:
ret.append(html.span(data, class_=t.type))
else:
ret.append(data)
else:
ret.append(item)
return ret
class HTMLDocument(object):
def __init__(self, tokenizer=None):
def __init__(self, encoding, tokenizer=None):
self.encoding = encoding
self.html = root = html.html()
self.head = head = self.create_head()
root.append(head)
@@ -119,30 +140,11 @@ class HTMLDocument(object):
table.append(tbody)
return table, tbody
def prepare_line(self, text):
""" adds html formatting to text items (list)
only processes items if they're of a string type (or unicode)
"""
ret = []
for item in text:
if type(item) in [str, unicode]:
tokens = self.tokenizer.tokenize(item)
for t in tokens:
if t.type in ['keyword', 'alt_keyword', 'number',
'string', 'comment']:
ret.append(html.span(t.data, class_=t.type))
else:
ret.append(t.data)
else:
ret.append(item)
return ret
def add_row(self, lineno, text):
if text == ['']:
text = [raw(' ')]
else:
text = self.prepare_line(text)
text = prepare_line(text, self.tokenizer, self.encoding)
self.tbody.append(html.tr(html.td(str(lineno), class_='lineno'),
html.td(class_='code', *text)))
@@ -157,7 +159,8 @@ def create_html(mod):
lines = mod.path.open().readlines()
enchanter = HtmlEnchanter(mod)
doc = HTMLDocument()
enc = get_module_encoding(mod.path)
doc = HTMLDocument(enc)
for i, row in enumerate(lines):
row = enchanter.enchant_row(i + 1, row)
doc.add_row(i + 1, row)
@@ -248,3 +251,16 @@ def create_unknown_html(path):
)
return h.unicode()
_reg_enc = py.std.re.compile(r'coding[:=]\s*([-\w.]+)')
def get_module_encoding(path):
if hasattr(path, 'strpath'):
path = path.strpath
if path[-1] in ['c', 'o']:
path = path[:-1]
fpath = py.path.local(path)
code = fpath.read()
match = _reg_enc.search(code)
if match:
return match.group(1)
return 'ISO-8859-1'