File: strformat.py

package info (click to toggle)
linkchecker 10.5.0-1.1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 3,112 kB
  • sloc: python: 13,131; makefile: 134; sh: 71; xml: 36; sql: 20; javascript: 19; php: 2
file content (256 lines) | stat: -rw-r--r-- 7,969 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
# Copyright (C) 2000-2014 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
#
# Some functions have been taken and adjusted from the quodlibet
# source. Quodlibet is (C) 2004-2005 Joe Wreschnig, Michael Urman
# and licensed under the GNU General Public License version 2.
"""
Various string utility functions. Note that these functions are not
necessarily optimised for large strings, so use with care.
"""

import math
import re
import textwrap
import os
import time
import locale
import pydoc

# some handy time constants
SECONDS_PER_MINUTE = 60
SECONDS_PER_HOUR = 60 * SECONDS_PER_MINUTE
SECONDS_PER_DAY = 24 * SECONDS_PER_HOUR


def ascii_safe(s):
    """Get ASCII string without raising encoding errors. Unknown
    characters of the given encoding will be ignored.

    @param s: the string to be encoded
    @type s: string or None
    @return: version of s containing only ASCII characters, or None if s was None
    @rtype: string or None
    """
    if s:
        s = s.encode('ascii', 'ignore').decode('ascii')
    return s


def unquote(s, matching=False):
    """Remove leading and ending single and double quotes.
    The quotes need to match if matching is True. Only one quote from each
    end will be stripped.

    @return: if s evaluates to False, return s as is, else return
        string with stripped quotes
    @rtype: unquoted string, or s unchanged if it is evaluating to False
    """
    if not s:
        return s
    if len(s) < 2:
        return s
    if matching:
        if s[0] in ("\"'") and s[0] == s[-1]:
            s = s[1:-1]
    else:
        if s[0] in ("\"'"):
            s = s[1:]
        if s[-1] in ("\"'"):
            s = s[:-1]
    return s


_para_mac = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\r')
_para_posix = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\n')
_para_win = r"(?:{sep})(?:(?:{sep})\s*)+".format(sep='\r\n')
_para_ro = re.compile(f"{_para_mac}|{_para_posix}|{_para_win}")


def get_paragraphs(text):
    """A new paragraph is considered to start at a line which follows
    one or more blank lines (lines containing nothing or just spaces).
    The first line of the text also starts a paragraph."""
    if not text:
        return []
    return _para_ro.split(text)


def wrap(text, width, **kwargs):
    """Adjust lines of text to be not longer than width. The text will be
    returned unmodified if width <= 0.
    See textwrap.wrap() for a list of supported kwargs.
    Returns text with lines no longer than given width."""
    if width <= 0 or not text:
        return text
    ret = []
    for para in get_paragraphs(text):
        text = " ".join(para.strip().split())
        ret.extend(textwrap.wrap(text, width, **kwargs))
    return os.linesep.join(ret)


def indent(text, indent_string="  "):
    """Indent each line of text with the given indent string."""
    return os.linesep.join(f"{indent_string}{x}" for x in text.splitlines())


def paginate(text):
    """Print text in pages of lines."""
    pydoc.pager(text)


def strsize(b, grouping=True):
    """Return human representation of bytes b. A negative number of bytes
    raises a value error."""
    if b < 0:
        raise ValueError("Invalid negative byte number")
    if b < 1024:
        return "%sB" % locale.format_string("%d", b, grouping)
    if b < 1024 * 10:
        return "%sKB" % locale.format_string("%d", (b // 1024), grouping)
    if b < 1024 * 1024:
        return "%sKB" % locale.format_string("%.2f", (float(b) / 1024), grouping)
    if b < 1024 * 1024 * 10:
        return "%sMB" % locale.format_string(
            "%.2f", (float(b) / (1024 * 1024)), grouping
        )
    if b < 1024 * 1024 * 1024:
        return "%sMB" % locale.format_string(
            "%.1f", (float(b) / (1024 * 1024)), grouping
        )
    if b < 1024 * 1024 * 1024 * 10:
        return "%sGB" % locale.format_string(
            "%.2f", (float(b) / (1024 * 1024 * 1024)), grouping
        )
    return "%sGB" % locale.format_string(
        "%.1f", (float(b) / (1024 * 1024 * 1024)), grouping
    )


def strtime(t, func=time.localtime):
    """Return ISO 8601 formatted time."""
    return time.strftime("%Y-%m-%d %H:%M:%S", func(t)) + strtimezone()


# from quodlibet
def strduration_long(duration, do_translate=True):
    """Turn a time value in seconds into x hours, x minutes, etc."""
    if do_translate:
        # use global translator functions
        global _, _n
    else:
        # do not translate
        def _(x): return x
        def _n(a, b, n): return a if n == 1 else b
    if duration < 0:
        duration = abs(duration)
        prefix = "-"
    else:
        prefix = ""
    if duration < 1:
        return _("%(prefix)s%(duration).02f seconds") % {
            "prefix": prefix,
            "duration": duration,
        }
    # translation dummies
    _n("%d second", "%d seconds", 1)
    _n("%d minute", "%d minutes", 1)
    _n("%d hour", "%d hours", 1)
    _n("%d day", "%d days", 1)
    _n("%d year", "%d years", 1)
    cutoffs = [
        (60, "%d second", "%d seconds"),
        (60, "%d minute", "%d minutes"),
        (24, "%d hour", "%d hours"),
        (365, "%d day", "%d days"),
        (None, "%d year", "%d years"),
    ]
    time_str = []
    for divisor, single, plural in cutoffs:
        if duration < 1:
            break
        if divisor is None:
            duration, unit = 0, duration
        else:
            duration, unit = divmod(duration, divisor)
        if unit:
            time_str.append(_n(single, plural, math.ceil(unit)) % unit)
    time_str.reverse()
    if len(time_str) > 2:
        time_str.pop()
    return "{}{}".format(prefix, ", ".join(time_str))


def strtimezone():
    """Return timezone info, %z on some platforms, but not supported on all.
    """
    if time.daylight:
        zone = time.altzone
    else:
        zone = time.timezone
    return "%+04d" % (-zone // SECONDS_PER_HOUR)


def stripurl(s):
    """Remove any lines from string after the first line.
    Also remove whitespace at start and end from given string."""
    if not s:
        return s
    return s.splitlines()[0].strip()


def limit(s, length=72):
    """If the length of the string exceeds the given limit, it will be cut
    off and three dots will be appended.

    @param s: the string to limit
    @type s: string
    @param length: maximum length
    @type length: non-negative integer
    @return: limited string, at most length+3 characters long
    """
    assert length >= 0, "length limit must be a non-negative integer"
    if not s or len(s) <= length:
        return s
    if length == 0:
        return ""
    return "%s..." % s[:length]


def strline(s):
    """Display string representation on one line."""
    return strip_control_chars("`%s'" % s.replace("\n", "\\n"))


def format_feature_warning(**kwargs):
    """Format warning that a module could not be imported and that it should
    be installed for a certain URL.
    """
    return (
        _(
            "Could not import %(module)s for %(feature)s."
            " Install %(module)s from %(url)s to use this feature."
        )
        % kwargs
    )


def strip_control_chars(text):
    """Remove console control characters from text."""
    if text:
        return re.sub(r"[\x01-\x1F\x7F]", "", text)
    return text