test_isbn.doctest - more detailed doctests for stdnum.isbn module

Copyright (C) 2010 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


This file contains more detailed doctests for the stdnum.isbn module. It
tries to test more corner cases and detailed functionality that is not
really useful as module documentation.

>>> from stdnum import isbn


These are normal variations that should just work.

>>> isbn.is_valid('978-9024538270')
True
>>> isbn.is_valid(u'1857982185')
True
>>> isbn.is_valid('85152-629-2') # 9-digit SBN (silently converted to ISBN10)
True


These are tests to check what happes when a wrong type is passed.

>>> isbn.is_valid(1857982185) # integer, not string
False
>>> isbn.is_valid(None)
False
>>> isbn.is_valid('')
False


Tests for mangling and incorect check digits.

>>> isbn.is_valid('08515x-629-2') # added X in the middle
False
>>> isbn.is_valid('85152-629-1') # incorrect check digit
False
>>> isbn.is_valid('978-902453827X') # ISBN with X check digit
False


See if ISBN10 to 13 conversion works.

>>> isbn.to_isbn13('978-9024538270') # ISBN13 should stay ISBN13
'978-9024538270'
>>> isbn.to_isbn13('1 85798218 5')
'978 1 85798218 3'
>>> isbn.to_isbn13('1857982185')
'9781857982183'
>>> isbn.to_isbn13('1-85798-218-5')
'978-1-85798-218-3'
>>> isbn.is_valid(isbn.to_isbn13('1 85798218 5'))
True


Regrouping tests.

>>> isbn.split('9024538270') # normal ISBN10
('', '90', '245', '3827', '0')
>>> isbn.split('9999678270') # ISBN10, unknown publisher in group
('', '99996', '', '7827', '0')
>>> isbn.split('979-20-1234567-8')
('979', '', '', '201234567', '8')


Some tests for the ranges module. This is more an internal module so
tests here are not very critical.

>>> from stdnum.isbn import ranges
>>> list(ranges._wrap(2 * 'abc def ghijklmn opqr stuvwx yz', 40))[0]
'abc def ghijklmn opqr stuvwx yzabc def'


Test output function. Bit of a limited test but we see if the serialised
form of the prefix/ranges list contains at least the same prefixes as the
current _prefixes list.

>>> import StringIO
>>> output = StringIO.StringIO()
>>> ranges.output(output)
>>> k = set( x.split(' ')[0] for x in StringIO.StringIO(output.getvalue()).readlines() )
>>> k == set(ranges._prefixes.keys())
True


Make an XML file with somre prefix definitions and load that into the
ranges module.

First save the current ranges so we can restore later.

>>> save_prefixes = ranges._prefixes

Write the XML to a file.

>>> import tempfile
>>> xmlfile = tempfile.NamedTemporaryFile(delete=False)
>>> xmlfile.write("""<?xml version='1.0' encoding='utf-8'?>
... <ISBNRangeMessage>
... <MessageSerialNumber>0aad2b046ddd9b30e080cb2b24afc868</MessageSerialNumber>
... <MessageDate>Thu, 20 May 2010 18:36:55 GMT</MessageDate>
...  <EAN.UCCPrefixes><EAN.UCC>
...   <Prefix>978</Prefix>
...   <Rules>
...    <Rule><Range>0000000-5999999</Range><Length>1</Length></Rule>
...    <Rule><Range>6000000-6499999</Range><Length>3</Length></Rule>
...    <Rule><Range>6500000-6999999</Range><Length>0</Length></Rule>
...   </Rules>
...  </EAN.UCC></EAN.UCCPrefixes>
...  <RegistrationGroups>
...   <Group>
...    <Prefix>978-0</Prefix>
...    <Rules>
...     <Rule><Range>0000000-1999999</Range><Length>2</Length></Rule>
...     <Rule><Range>2000000-6999999</Range><Length>3</Length></Rule>
...    </Rules>
...   </Group>
...  </RegistrationGroups>
... </ISBNRangeMessage>
... """)
>>> xmlfile.close()

Load the XML file by URL and output it to another string. Check if the
content of the XML has been

>>> import urllib
>>> ranges.download('file://' + urllib.pathname2url(xmlfile.name))
>>> import sys
>>> ranges.output()
# generated from RangeMessage.xml, downloaded from
# http://www.isbn-international.org/agency?rmxml=1
# serial 0aad2b046ddd9b30e080cb2b24afc868
# date Thu, 20 May 2010 18:36:55 GMT
_prefixes = """
978 0-5 600-649
978-0 00-19 200-699
"""

Restore the original ranges and clean up.

>>> ranges._prefixes = save_prefixes
>>> import os
>>> os.unlink(xmlfile.name)