Arthur de Jong

Open Source / Free Software developer

summaryrefslogtreecommitdiffstats
path: root/stdnum/util.py
blob: 111f5af8945599d93000bb694bcf1f22c9d82173 (plain)
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
# util.py - common utility functions
# coding: utf-8
#
# Copyright (C) 2012-2016 Arthur de Jong
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library 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
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
# 02110-1301 USA

"""Common utility functions for other stdnum modules.

This module is meant for internal use by stdnum modules and is not
guaranteed to remain stable and as such not part of the public API of
stdnum.

>>> get_cc_module('nl', 'vat').__name__
'stdnum.nl.btw'
>>> get_cc_module('is', 'vat').__name__
'stdnum.is_.vsk'
"""

import pkgutil
import pydoc
import re
import sys
import unicodedata

from stdnum.exceptions import *


_strip_doctest_re = re.compile(r'^>>> .*\Z', re.DOTALL | re.MULTILINE)


def _mk_char_map(mapping):
    """Transform a dictionary with comma separated uniode chracter names
    to tuples with unicode characters as key."""
    for key, value in mapping.items():
        for char in key.split(','):
            try:
                yield (unicodedata.lookup(char), value)
            except KeyError:  # pragma: no cover (does not happen on Python3)
                pass


# build mapping of Unicode characters to equivalent ASCII characters
_char_map = dict(_mk_char_map({
    'HYPHEN-MINUS,ARMENIAN HYPHEN,HEBREW PUNCTUATION MAQAF,HYPHEN,'
    'NON-BREAKING HYPHEN,FIGURE DASH,EN DASH,EM DASH,HORIZONTAL BAR,'
    'SMALL HYPHEN-MINUS,FULLWIDTH HYPHEN-MINUS,MONGOLIAN NIRUGU,OVERLINE,'
    'HYPHEN BULLET,MACRON,MODIFIER LETTER MINUS SIGN,FULLWIDTH MACRON,'
    'OGHAM SPACE MARK,SUPERSCRIPT MINUS,SUBSCRIPT MINUS,MINUS SIGN,'
    'HORIZONTAL LINE EXTENSION,HORIZONTAL SCAN LINE-1,HORIZONTAL SCAN LINE-3,'
    'HORIZONTAL SCAN LINE-7,HORIZONTAL SCAN LINE-9,STRAIGHTNESS':
        '-',
    'ASTERISK,ARABIC FIVE POINTED STAR,SYRIAC HARKLEAN ASTERISCUS,'
    'FLOWER PUNCTUATION MARK,VAI FULL STOP,SMALL ASTERISK,FULLWIDTH ASTERISK,'
    'ASTERISK OPERATOR,STAR OPERATOR,HEAVY ASTERISK,LOW ASTERISK,'
    'OPEN CENTRE ASTERISK,EIGHT SPOKED ASTERISK,SIXTEEN POINTED ASTERISK,'
    'TEARDROP-SPOKED ASTERISK,OPEN CENTRE TEARDROP-SPOKED ASTERISK,'
    'HEAVY TEARDROP-SPOKED ASTERISK,EIGHT TEARDROP-SPOKED PROPELLER ASTERISK,'
    'HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK,'
    'ARABIC FIVE POINTED STAR':
        '*',
    'COMMA,ARABIC COMMA,SINGLE LOW-9 QUOTATION MARK,IDEOGRAPHIC COMMA,'
    'ARABIC DECIMAL SEPARATOR,ARABIC THOUSANDS SEPARATOR,PRIME,RAISED COMMA,'
    'PRESENTATION FORM FOR VERTICAL COMMA,SMALL COMMA,'
    'SMALL IDEOGRAPHIC COMMA,FULLWIDTH COMMA,CEDILLA':
        ',',
    'FULL STOP,MIDDLE DOT,GREEK ANO TELEIA,ARABIC FULL STOP,'
    'IDEOGRAPHIC FULL STOP,SYRIAC SUPRALINEAR FULL STOP,'
    'SYRIAC SUBLINEAR FULL STOP,SAMARITAN PUNCTUATION NEQUDAA,'
    'TIBETAN MARK INTERSYLLABIC TSHEG,TIBETAN MARK DELIMITER TSHEG BSTAR,'
    'RUNIC SINGLE PUNCTUATION,BULLET,ONE DOT LEADER,HYPHENATION POINT,'
    'WORD SEPARATOR MIDDLE DOT,RAISED DOT,KATAKANA MIDDLE DOT,'
    'SMALL FULL STOP,FULLWIDTH FULL STOP,HALFWIDTH KATAKANA MIDDLE DOT,'
    'AEGEAN WORD SEPARATOR DOT,PHOENICIAN WORD SEPARATOR,'
    'KHAROSHTHI PUNCTUATION DOT,DOT ABOVE,ARABIC SYMBOL DOT ABOVE,'
    'ARABIC SYMBOL DOT BELOW,BULLET OPERATOR,DOT OPERATOR':
        '.',
    'SOLIDUS,SAMARITAN PUNCTUATION ARKAANU,FULLWIDTH SOLIDUS,DIVISION SLASH,'
    'MATHEMATICAL RISING DIAGONAL,BIG SOLIDUS,FRACTION SLASH':
        '/',
    'COLON,ETHIOPIC WORDSPACE,RUNIC MULTIPLE PUNCTUATION,MONGOLIAN COLON,'
    'PRESENTATION FORM FOR VERTICAL COLON,FULLWIDTH COLON,'
    'PRESENTATION FORM FOR VERTICAL TWO DOT LEADER,SMALL COLON':
        ':',
    'SPACE,NO-BREAK SPACE,EN QUAD,EM QUAD,EN SPACE,EM SPACE,'
    'THREE-PER-EM SPACE,FOUR-PER-EM SPACE,SIX-PER-EM SPACE,FIGURE SPACE,'
    'PUNCTUATION SPACE,THIN SPACE,HAIR SPACE,NARROW NO-BREAK SPACE,'
    'MEDIUM MATHEMATICAL SPACE,IDEOGRAPHIC SPACE':
        ' ',
}))


def _clean_chars(number):
    """Replace various Unicode characters with their ASCII counterpart."""
    return ''.join(_char_map.get(x, x) for x in number)


def clean(number, deletechars=''):
    """Remove the specified characters from the supplied number.

    >>> clean('123-456:78 9', ' -:')
    '123456789'
    >>> clean('1–2—3―4')
    '1-2-3-4'
    """
    try:
        number = ''.join(x for x in number)
    except Exception:
        raise InvalidFormat()
    if sys.version < '3' and isinstance(number, str):  # pragma: no cover (Python 2/3 specific code)
        try:
            number = _clean_chars(number.decode()).encode()
        except UnicodeError:
            try:
                number = _clean_chars(number.decode('utf-8')).encode('utf-8')
            except UnicodeError:
                pass
    else:  # pragma: no cover (Python 2/3 specific code)
        number = _clean_chars(number)
    return ''.join(x for x in number if x not in deletechars)


def get_number_modules(base='stdnum'):
    """Yield all the module and package names under the specified module."""
    __import__(base)
    module = sys.modules[base]
    for loader, name, is_pkg in pkgutil.walk_packages(
            module.__path__, module.__name__ + '.',
            onerror=lambda x: None):
        __import__(name)
        module = sys.modules[name]
        if hasattr(module, 'validate'):
            yield module


def get_module_name(module):
    """Return the short description of the number."""
    return pydoc.splitdoc(pydoc.getdoc(module))[0].strip('.')


def get_module_description(module):
    """Return a description of the number."""
    doc = pydoc.splitdoc(pydoc.getdoc(module))[1]
    # remove the doctests
    return _strip_doctest_re.sub('', doc).strip()


def get_module_list():
    for module in get_number_modules():
        yield ' * %s: %s' % (
            module.__name__.replace('stdnum.', ''),
            get_module_name(module),
        )


def get_cc_module(cc, name):
    """Find the country-specific named module."""
    cc = cc.lower()
    # add suffix for python reserved words
    if cc in ('in', 'is', 'if'):
        cc += '_'
    try:
        mod = __import__('stdnum.%s' % cc, globals(), locals(), [name])
        return getattr(mod, name, None)
    except ImportError:
        return


def get_soap_client(wsdlurl):  # pragma: no cover (no tests for this function)
    """Get a SOAP client for performing requests."""
    # this function isn't automatically tested because the functions using
    # it are not automatically tested
    try:
        from urllib import getproxies
    except ImportError:
        from urllib.request import getproxies
    # try suds first
    try:
        from suds.client import Client
        return Client(wsdlurl, proxy=getproxies()).service
    except ImportError:
        # fall back to using pysimplesoap
        from pysimplesoap.client import SoapClient
        return SoapClient(wsdl=wsdlurl, proxy=getproxies())