File: util.py

package info (click to toggle)
0ad 0.0.17-1
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 51,248 kB
  • ctags: 46,933
  • sloc: cpp: 223,208; ansic: 31,240; python: 16,343; perl: 4,083; sh: 1,011; makefile: 915; xml: 733; java: 621; ruby: 229; erlang: 53; sql: 40
file content (300 lines) | stat: -rw-r--r-- 9,456 bytes parent folder | download | duplicates (2)
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
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
# -*- coding: utf-8 -*-
#
# Copyright (C) 2007-2011 Edgewall Software
# Copyright (C) 2013 Wildfire Games
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without modification, are permitted provided that the
# following conditions are met:
#
#   Redistributions of source code must retain the above copyright notice, this list of conditions and the following
#   disclaimer.
#   Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following
#   disclaimer in the documentation and/or other materials provided with the distribution.
#   The name of the author may not be used to endorse or promote products derived from this software without specific
#   prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR “AS IS” AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
# AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
# NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# This software consists of voluntary contributions made by many
# individuals. For the exact contribution history, see the revision
# history and logs:
# • http://babel.edgewall.org/log/trunk/babel/messages
# • http://trac.wildfiregames.com/browser/ps/trunk/source/tools/i18n/potter

"""Various utility classes and functions."""

from __future__ import absolute_import, division, print_function, unicode_literals

import codecs
from datetime import timedelta, tzinfo
import os
import re
import textwrap
import time

try:
    from itertools import izip as zip
    from itertools import imap as map
except ImportError:
    pass # Python 3

missing = object()

__all__ = ['distinct', 'pathmatch', 'relpath', 'wraptext', 'UTC',
           'LOCALTZ']
__docformat__ = 'restructuredtext en'


def distinct(iterable):
    """Yield all items in an iterable collection that are distinct.

    Unlike when using sets for a similar effect, the original ordering of the
    items in the collection is preserved by this function.

    >>> print list(distinct([1, 2, 1, 3, 4, 4]))
    [1, 2, 3, 4]
    >>> print list(distinct('foobar'))
    ['f', 'o', 'b', 'a', 'r']

    :param iterable: the iterable collection providing the data
    :return: the distinct items in the collection
    :rtype: ``iterator``
    """
    seen = set()
    for item in iter(iterable):
        if item not in seen:
            yield item
            seen.add(item)

# Regexp to match python magic encoding line
PYTHON_MAGIC_COMMENT_re = re.compile(
    r'[ \t\f]* \# .* coding[=:][ \t]*([-\w.]+)', re.VERBOSE)
def parse_encoding(fp):
    """Deduce the encoding of a source file from magic comment.

    It does this in the same way as the `Python interpreter`__

    .. __: http://docs.python.org/ref/encodings.html

    The ``fp`` argument should be a seekable file object.

    (From Jeff Dairiki)
    """
    pos = fp.tell()
    fp.seek(0)
    try:
        line1 = fp.readline()
        has_bom = line1.startswith(codecs.BOM_UTF8)
        if has_bom:
            line1 = line1[len(codecs.BOM_UTF8):]

        m = PYTHON_MAGIC_COMMENT_re.match(line1)
        if not m:
            try:
                import parser
                parser.suite(line1)
            except (ImportError, SyntaxError):
                # Either it's a real syntax error, in which case the source is
                # not valid python source, or line2 is a continuation of line1,
                # in which case we don't want to scan line2 for a magic
                # comment.
                pass
            else:
                line2 = fp.readline()
                m = PYTHON_MAGIC_COMMENT_re.match(line2)

        if has_bom:
            if m:
                raise SyntaxError(
                    "python refuses to compile code with both a UTF8 "
                    "byte-order-mark and a magic encoding comment")
            return 'utf_8'
        elif m:
            return m.group(1)
        else:
            return None
    finally:
        fp.seek(pos)

def pathmatch(pattern, filename):
    """Extended pathname pattern matching.
    
    This function is similar to what is provided by the ``fnmatch`` module in
    the Python standard library, but:
    
     * can match complete (relative or absolute) path names, and not just file
       names, and
     * also supports a convenience pattern ("**") to match files at any
       directory level.
    
    Examples:
    
    >>> pathmatch('**.py', 'bar.py')
    True
    >>> pathmatch('**.py', 'foo/bar/baz.py')
    True
    >>> pathmatch('**.py', 'templates/index.html')
    False
    
    >>> pathmatch('**/templates/*.html', 'templates/index.html')
    True
    >>> pathmatch('**/templates/*.html', 'templates/foo/bar.html')
    False
    
    :param pattern: the glob pattern
    :param filename: the path name of the file to match against
    :return: `True` if the path name matches the pattern, `False` otherwise
    :rtype: `bool`
    """
    symbols = {
        '?':   '[^/]',
        '?/':  '[^/]/',
        '*':   '[^/]+',
        '*/':  '[^/]+/',
        '**/': '(?:.+/)*?',
        '**':  '(?:.+/)*?[^/]+',
    }
    buf = []
    for idx, part in enumerate(re.split('([?*]+/?)', pattern)):
        if idx % 2:
            buf.append(symbols[part])
        elif part:
            buf.append(re.escape(part))
    match = re.match(''.join(buf) + '$', filename.replace(os.sep, '/'))
    return match is not None


class TextWrapper(textwrap.TextWrapper):
    wordsep_re = re.compile(
        r'(\s+|'                                  # any whitespace
        r'(?<=[\w\!\"\'\&\.\,\?])-{2,}(?=\w))'    # em-dash
    )


def wraptext(text, width=70, initial_indent='', subsequent_indent=''):
    """Simple wrapper around the ``textwrap.wrap`` function in the standard
    library. This version does not wrap lines on hyphens in words.
    
    :param text: the text to wrap
    :param width: the maximum line width
    :param initial_indent: string that will be prepended to the first line of
                           wrapped output
    :param subsequent_indent: string that will be prepended to all lines save
                              the first of wrapped output
    :return: a list of lines
    :rtype: `list`
    """
    wrapper = TextWrapper(width=width, initial_indent=initial_indent,
                          subsequent_indent=subsequent_indent,
                          break_long_words=False)
    return wrapper.wrap(text)


try:
    relpath = os.path.relpath
except AttributeError:
    def relpath(path, start='.'):
        """Compute the relative path to one path from another.
        
        >>> relpath('foo/bar.txt', '').replace(os.sep, '/')
        'foo/bar.txt'
        >>> relpath('foo/bar.txt', 'foo').replace(os.sep, '/')
        'bar.txt'
        >>> relpath('foo/bar.txt', 'baz').replace(os.sep, '/')
        '../foo/bar.txt'
        
        :return: the relative path
        :rtype: `basestring`
        """
        start_list = os.path.abspath(start).split(os.sep)
        path_list = os.path.abspath(path).split(os.sep)

        # Work out how much of the filepath is shared by start and path.
        i = len(os.path.commonprefix([start_list, path_list]))

        rel_list = [os.path.pardir] * (len(start_list) - i) + path_list[i:]
        return os.path.join(*rel_list)

ZERO = timedelta(0)


class FixedOffsetTimezone(tzinfo):
    """Fixed offset in minutes east from UTC."""

    def __init__(self, offset, name=None):
        self._offset = timedelta(minutes=offset)
        if name is None:
            name = 'Etc/GMT+%d' % offset
        self.zone = name

    def __str__(self):
        return self.zone

    def __repr__(self):
        return '<FixedOffset "%s" %s>' % (self.zone, self._offset)

    def utcoffset(self, dt):
        return self._offset

    def tzname(self, dt):
        return self.zone

    def dst(self, dt):
        return ZERO


try:
    from pytz import UTC
except ImportError:
    UTC = FixedOffsetTimezone(0, 'UTC')
    """`tzinfo` object for UTC (Universal Time).
    
    :type: `tzinfo`
    """

STDOFFSET = timedelta(seconds = -time.timezone)
if time.daylight:
    DSTOFFSET = timedelta(seconds = -time.altzone)
else:
    DSTOFFSET = STDOFFSET

DSTDIFF = DSTOFFSET - STDOFFSET


class LocalTimezone(tzinfo):

    def utcoffset(self, dt):
        if self._isdst(dt):
            return DSTOFFSET
        else:
            return STDOFFSET

    def dst(self, dt):
        if self._isdst(dt):
            return DSTDIFF
        else:
            return ZERO

    def tzname(self, dt):
        return time.tzname[self._isdst(dt)]

    def _isdst(self, dt):
        tt = (dt.year, dt.month, dt.day,
              dt.hour, dt.minute, dt.second,
              dt.weekday(), 0, -1)
        stamp = time.mktime(tt)
        tt = time.localtime(stamp)
        return tt.tm_isdst > 0


LOCALTZ = LocalTimezone()
"""`tzinfo` object for local time-zone.

:type: `tzinfo`
"""