1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
|
# -*- coding: utf-8 -*-
#
# Copyright (C) 2006-2009 Edgewall Software
# All rights reserved.
#
# This software is licensed as described in the file COPYING, which
# you should have received as part of this distribution. The terms
# are also available at http://genshi.edgewall.org/wiki/License.
#
# This software consists of voluntary contributions made by many
# individuals. For the exact contribution history, see the revision
# history and logs, available at http://genshi.edgewall.org/log/.
"""Various utility classes and functions."""
import htmlentitydefs as entities
import re
__docformat__ = 'restructuredtext en'
class LRUCache(dict):
"""A dictionary-like object that stores only a certain number of items, and
discards its least recently used item when full.
>>> cache = LRUCache(3)
>>> cache['A'] = 0
>>> cache['B'] = 1
>>> cache['C'] = 2
>>> len(cache)
3
>>> cache['A']
0
Adding new items to the cache does not increase its size. Instead, the least
recently used item is dropped:
>>> cache['D'] = 3
>>> len(cache)
3
>>> 'B' in cache
False
Iterating over the cache returns the keys, starting with the most recently
used:
>>> for key in cache:
... print(key)
D
A
C
This code is based on the LRUCache class from ``myghtyutils.util``, written
by Mike Bayer and released under the MIT license. See:
http://svn.myghty.org/myghtyutils/trunk/lib/myghtyutils/util.py
"""
class _Item(object):
def __init__(self, key, value):
self.prv = self.nxt = None
self.key = key
self.value = value
def __repr__(self):
return repr(self.value)
def __init__(self, capacity):
self._dict = dict()
self.capacity = capacity
self.head = None
self.tail = None
def __contains__(self, key):
return key in self._dict
def __iter__(self):
cur = self.head
while cur:
yield cur.key
cur = cur.nxt
def __len__(self):
return len(self._dict)
def __getitem__(self, key):
item = self._dict[key]
self._update_item(item)
return item.value
def __setitem__(self, key, value):
item = self._dict.get(key)
if item is None:
item = self._Item(key, value)
self._dict[key] = item
self._insert_item(item)
else:
item.value = value
self._update_item(item)
self._manage_size()
def __repr__(self):
return repr(self._dict)
def _insert_item(self, item):
item.prv = None
item.nxt = self.head
if self.head is not None:
self.head.prv = item
else:
self.tail = item
self.head = item
self._manage_size()
def _manage_size(self):
while len(self._dict) > self.capacity:
olditem = self._dict[self.tail.key]
del self._dict[self.tail.key]
if self.tail != self.head:
self.tail = self.tail.prv
self.tail.nxt = None
else:
self.head = self.tail = None
def _update_item(self, item):
if self.head == item:
return
prv = item.prv
prv.nxt = item.nxt
if item.nxt is not None:
item.nxt.prv = prv
else:
self.tail = prv
item.prv = None
item.nxt = self.head
self.head.prv = self.head = item
def flatten(items):
"""Flattens a potentially nested sequence into a flat list.
:param items: the sequence to flatten
>>> flatten((1, 2))
[1, 2]
>>> flatten([1, (2, 3), 4])
[1, 2, 3, 4]
>>> flatten([1, (2, [3, 4]), 5])
[1, 2, 3, 4, 5]
"""
retval = []
for item in items:
if isinstance(item, (frozenset, list, set, tuple)):
retval += flatten(item)
else:
retval.append(item)
return retval
def plaintext(text, keeplinebreaks=True):
"""Return the text with all entities and tags removed.
>>> plaintext('<b>1 < 2</b>')
u'1 < 2'
The `keeplinebreaks` parameter can be set to ``False`` to replace any line
breaks by simple spaces:
>>> plaintext('''<b>1
... <
... 2</b>''', keeplinebreaks=False)
u'1 < 2'
:param text: the text to convert to plain text
:param keeplinebreaks: whether line breaks in the text should be kept intact
:return: the text with tags and entities removed
"""
text = stripentities(striptags(text))
if not keeplinebreaks:
text = text.replace('\n', ' ')
return text
_STRIPENTITIES_RE = re.compile(r'&(?:#((?:\d+)|(?:[xX][0-9a-fA-F]+));?|(\w+);)')
def stripentities(text, keepxmlentities=False):
"""Return a copy of the given text with any character or numeric entities
replaced by the equivalent UTF-8 characters.
>>> stripentities('1 < 2')
u'1 < 2'
>>> stripentities('more …')
u'more \u2026'
>>> stripentities('…')
u'\u2026'
>>> stripentities('…')
u'\u2026'
If the `keepxmlentities` parameter is provided and is a truth value, the
core XML entities (&, ', >, < and ") are left intact.
>>> stripentities('1 < 2 …', keepxmlentities=True)
u'1 < 2 \u2026'
"""
def _replace_entity(match):
if match.group(1): # numeric entity
ref = match.group(1)
if ref.startswith('x'):
ref = int(ref[1:], 16)
else:
ref = int(ref, 10)
return unichr(ref)
else: # character entity
ref = match.group(2)
if keepxmlentities and ref in ('amp', 'apos', 'gt', 'lt', 'quot'):
return '&%s;' % ref
try:
return unichr(entities.name2codepoint[ref])
except KeyError:
if keepxmlentities:
return '&%s;' % ref
else:
return ref
return _STRIPENTITIES_RE.sub(_replace_entity, text)
_STRIPTAGS_RE = re.compile(r'(<!--.*?-->|<[^>]*>)')
def striptags(text):
"""Return a copy of the text with any XML/HTML tags removed.
>>> striptags('<span>Foo</span> bar')
'Foo bar'
>>> striptags('<span class="bar">Foo</span>')
'Foo'
>>> striptags('Foo<br />')
'Foo'
HTML/XML comments are stripped, too:
>>> striptags('<!-- <blub>hehe</blah> -->test')
'test'
:param text: the string to remove tags from
:return: the text with tags removed
"""
return _STRIPTAGS_RE.sub('', text)
def stringrepr(string):
ascii = string.encode('ascii', 'backslashreplace')
quoted = "'" + ascii.replace("'", "\\'") + "'"
if len(ascii) > len(string):
return 'u' + quoted
return quoted
# Compatibility fallback implementations for older Python versions
try:
all = all
any = any
except NameError:
def any(S):
for x in S:
if x:
return True
return False
def all(S):
for x in S:
if not x:
return False
return True
|