1# isil.py - functions for handling identifiers for libraries and related
2#           organizations
3#
4# Copyright (C) 2011-2017 Arthur de Jong
5#
6# This library is free software; you can redistribute it and/or
7# modify it under the terms of the GNU Lesser General Public
8# License as published by the Free Software Foundation; either
9# version 2.1 of the License, or (at your option) any later version.
10#
11# This library is distributed in the hope that it will be useful,
12# but WITHOUT ANY WARRANTY; without even the implied warranty of
13# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14# Lesser General Public License for more details.
15#
16# You should have received a copy of the GNU Lesser General Public
17# License along with this library; if not, write to the Free Software
18# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
19# 02110-1301 USA
20
21"""ISIL (International Standard Identifier for Libraries).
22
23The ISIL is the International Standard Identifier for Libraries and Related
24Organizations (ISO 15511) used to uniquely identify libraries, archives,
25museums, and similar organisations.
26
27The identifier can be up to 15 characters that may use digits,
28letters (case insensitive) hyphens, colons and slashes. The non-alphanumeric
29characters are part of the identifier and are not just for readability.
30
31The identifier consists of two parts separated by a hyphen. The first part is
32either a two-letter ISO 3166 country code or a (not two-letter) non-national
33prefix that identifies the agency that issued the ISIL. The second part is
34the is the identifier issued by that agency.
35
36Only the first part can be validated since it is registered globally. There
37may be some validation possible with the second parts (some agencies provide
38web services for validation) but there is no common format to these services.
39
40More information:
41
42* https://en.wikipedia.org/wiki/ISBT_128
43* http://biblstandard.dk/isil/
44* https://www.iso.org/standard/57332.html
45
46>>> validate('IT-RM0267')
47'IT-RM0267'
48>>> validate('OCLC-DLC')
49'OCLC-DLC'
50>>> validate('WW-RM0267')  # unregistered country code
51Traceback (most recent call last):
52    ...
53InvalidComponent: ...
54>>> format('it-RM0267')
55'IT-RM0267'
56"""
57
58from stdnum.exceptions import *
59from stdnum.util import clean
60
61
62# the valid characters in an ISIL
63_alphabet = set(
64    '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz-:/')
65
66
67def compact(number):
68    """Convert the ISIL to the minimal representation. This strips
69    surrounding whitespace."""
70    return clean(number, '').strip()
71
72
73def _is_known_agency(agency):
74    """Check whether the specified agency is valid."""
75    # look it up in the db
76    from stdnum import numdb
77    results = numdb.get('isil').info(agency.upper() + '$')
78    # there should be only one part and it should have properties
79    return len(results) == 1 and bool(results[0][1])
80
81
82def validate(number):
83    """Check if the number provided is a valid ISIL."""
84    number = compact(number)
85    if not all(x in _alphabet for x in number):
86        raise InvalidFormat()
87    if len(number) > 15:
88        raise InvalidLength()
89    if not _is_known_agency(number.split('-')[0]):
90        raise InvalidComponent()
91    return number
92
93
94def is_valid(number):
95    """Check if the number provided is a valid ISIL."""
96    try:
97        return bool(validate(number))
98    except ValidationError:
99        return False
100
101
102def format(number):
103    """Reformat the number to the standard presentation format."""
104    number = compact(number)
105    parts = number.split('-')
106    if len(parts) > 1 and _is_known_agency(parts[0]):
107        parts[0] = parts[0].upper()
108    return '-'.join(parts)
109