Attachment 10749 Details for Bug 21547 – icu-collation-test.py

icu-collation-test.py

icu-collation-test.py (text/plain), 3.01 KB, created by Mike FABIAN on 2018-01-15 14:36:24 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Mike FABIAN

Created: 2018-01-15 14:36:24 UTC

Size: 3.01 KB

patch

obsolete

>#!/usr/bin/env python3
>
>import sys
>import icu
>import argparse
>
>_ARGS = None
>
>def parse_args():
>    '''
>    Parse the command line arguments.
>    '''
>    parser = argparse.ArgumentParser(
>        description='A simple tool to test ICU/CLDR style collation rules.')
>    parser.add_argument(
>        '-r', '--rules',
>        nargs='?',
>        type=str,
>        action='store',
>        default=None,
>        help=('File to read the collation rules from. '
>              + 'default: %(default)s.'))
>    parser.add_argument(
>        '-u', '--unicode_rules',
>        nargs='?',
>        type=str,
>        action='store',
>        default=None,
>        help=('File to write the rules to using <U....> Unicode code points '
>              + 'for everything which is not ASCII. This is useful if one '
>              + 'wants to write equivalent rules for a glibc locale. '
>              + 'default: %(default)s.'))
>    parser.add_argument(
>        '-i', '--input',
>        nargs='?',
>        type=str,
>        action='store',
>        default=None,
>        help=('Test file containing the lines which should be sorted. '
>              + 'default: %(default)s.'))
>    parser.add_argument(
>        '-o', '--output',
>        nargs='?',
>        type=str,
>        action='store',
>        default=None,
>        help=('Test file containing the sorted lines. '
>              + 'default: %(default)s.'))
>    return parser.parse_args()
>
>def is_ascii(text):
>    '''Checks whether all characters in text are ASCII characters
>
>    Returns âTrueâ if the text is all ASCII, âFalseâ if not.
>
>    :param text: The text to check
>    :type text: string
>    :rtype: bool
>
>    Examples:
>
>    >>> is_ascii('Abc')
>    True
>
>    >>> is_ascii('NaÃ¯ve')
>    False
>    '''
>    try:
>        text.encode('ascii')
>    except UnicodeEncodeError:
>        return False
>    else:
>        return True
>
>if __name__ == '__main__':
>    _ARGS = parse_args()
>    rules = ''
>    if _ARGS.rules:
>        with open(_ARGS.rules, 'r') as rulesfile:
>            rules = rulesfile.read()
>
>    if _ARGS.unicode_rules and rules:
>        code_point_rules = ''
>        for char in rules:
>            if is_ascii(char):
>                code_point_rules += char
>            else:
>                code_point_rules += '{}[{:04X}]'.format(char, ord(char))
>        if code_point_rules:
>            with open(_ARGS.unicode_rules, 'w') as unicode_rules_file:
>                unicode_rules_file.write(code_point_rules)
>
>    icucollator = icu.RuleBasedCollator(rules)
>
>    input_list = []
>    if _ARGS.input:
>        with open(_ARGS.input, 'r') as inputfile:
>            input_list = inputfile.readlines()
>    else:
>        input_list = sys.stdin.readlines()
>
>    input_list = [line.rstrip('\n') for line in input_list]
>
>    output_list = sorted(input_list, key=icucollator.getSortKey)
>
>    if _ARGS.output:
>        with open (_ARGS.output, 'w') as outputfile:
>            for line in output_list:
>                outputfile.write('%s\n' %line)
>    else:
>        for line in output_list:
>            sys.stdout.write('%s\n' %line)
>
>    exit(0)

Actions: View

Attachments on bug 21547: 10696 | 10749 | 10755 | 10756