bm_php2py._run_script()

Complexity

Conditions

20

Size

Total Lines	146
Code Lines	95

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

#!/usr/bin/env python
def _run_script():
    global array_seen, nl, sd, tail_text

    if len(sys.argv) > 1:
        bmdir = sys.argv[1].rstrip('/') + '/'
    else:
        bmdir = '../../bmpm/'

    outfilename = '../abydos/phonetic/_beider_morse_data.py'
    outfile = codecs.open(outfilename, 'w', 'utf-8')

    outfile.write(
        '# -*- coding: utf-8 -*-\n\n# Copyright 2014-2018 by \
Christopher C. Little.\n# This file is part of Abydos.\n#\n# This file is \
based on Alexander Beider and Stephen P. Morse\'s implementation\n# of the \
Beider-Morse Phonetic Matching (BMPM) System, available at\n# \
http://stevemorse.org/phonetics/bmpm.htm.\n#\n# Abydos is free software: \
you can redistribute it and/or modify\n# it under the terms of the GNU \
General Public License as published by\n# the Free Software Foundation, \
either version 3 of the License, or\n# (at your option) any later version.\n\
#\n# Abydos is distributed in the hope that it will be useful,\n# but WITHOUT \
ANY WARRANTY; without even the implied warranty of\n# MERCHANTABILITY or \
FITNESS FOR A PARTICULAR PURPOSE. See the\n# GNU General Public License for \
more details.\n#\n# You should have received a copy of the GNU General Public \
License\n# along with Abydos. If not, see <http://www.gnu.org/licenses/>.\n\n\
"""abydos.phonetic._beider_morse_data.\n\nBehind-the-scenes constants, \
rules, etc. for the Beider-Morse Phonentic\nMatching (BMPM) algorithm\n\nDO \
NOT EDIT - This document is automatically generated from the reference\n\
implementation in PHP.\n"""\n\nfrom \
__future__ import (\n    absolute_import,\n    division,\n    print_function,\
    unicode_literals,\n)\n'
    )

    outfile.write('L_NONE = 0\n')
    for i, l in enumerate(lang_tuple):
        outfile.write('L_' + l.upper() + ' = 2**' + str(i) + '\n')
    outfile.write('\n\n')

    tail_text += '\nBMDATA = {}\n'

    subdirs = ('gen', 'sep', 'ash')

    for s in subdirs:
        sd = s
        tail_text += '\nBMDATA[\'' + s + '\'] = {}\n'
        tail_text += 'BMDATA[\'' + s + '\'][\'approx\'] = {}\n'
        tail_text += 'BMDATA[\'' + s + '\'][\'exact\'] = {}\n'
        tail_text += 'BMDATA[\'' + s + '\'][\'rules\'] = {}\n'
        tail_text += 'BMDATA[\'' + s + '\'][\'hebrew\'] = {}\n\n'
        tail_text += (
            'BMDATA[\''
            + s
            + '\'][\'language_rules\'] = _'
            + s.upper()
            + '_LANGUAGE_RULES\n'
        )
        tail_text += (
            'BMDATA[\''
            + s
            + '\'][\'languages\'] = _'
            + s.upper()
            + '_LANGUAGES\n'
        )

        phps = [
            f
            for f in sorted(listdir(bmdir + s + '/'))
            if (isfile(bmdir + s + '/' + f) and f.endswith('.php'))
        ]
        for infilename in phps:
            for pfx in (
                'rules',
                'approx',
                'exact',
                'hebrew',
                'language',
                'lang',
            ):
                if infilename.startswith(pfx):
                    array_seen = False
                    infilepath = bmdir + s + '/' + infilename
                    infileenc = chardet.detect(open(infilepath, 'rb').read())[
                        'encoding'
                    ]
                    print(s + '/' + infilename)  # noqa: T001
                    infile = codecs.open(infilepath, 'r', infileenc)
                    # if infilename.startswith('lang'):
                    #     tuplename = infilename[:-4]
                    # else:
                    #     tuplename = pfx + '_' + infilename[len(pfx) : -4]
                    # indent = len(tuplename) + 21

                    outfile.write('# ' + s + '/' + infilename + '\n')

                    ignore = True
                    for line in infile:
                        if 'function Language' in line:
                            break
                        if not ignore:
                            if re.search(r'\?>', line):
                                ignore = True
                            else:
                                line = pythonize(line, infilename[:-4], s)
                                if line.startswith('BMDATA'):
                                    tail_text += line
                                else:
                                    outfile.write(line)
                        if '*/' in line:
                            ignore = False

                    outfile.write('\n\n')
                    break

    outfile.write(tail_text)

    outfile.close()
    outfilelines = codecs.open(outfilename, 'r', 'utf-8').readlines()
    outfile = codecs.open(outfilename, 'w', 'utf-8')
    nl = False
    fixlanguagesarray = False

    sep_lang = (
        "('any', 'french', 'hebrew', 'italian', 'portuguese', 'spanish')"
    )

    for line in outfilelines:
        line = line.rstrip()
        if line:
            if fixlanguagesarray:
                line = ' ' + line.strip()
                fixlanguagesarray = False
            if len(line) > 79 or sep_lang in line:
                line += '  # noqa: E501'
            outfile.write(line)
            if not line.endswith('='):
                outfile.write('\n')
            else:
                fixlanguagesarray = True
            nl = False
        else:
            if not nl:
                outfile.write('\n')
            nl = True

    outfile.write(
        '\n\nif __name__ == \'__main__\':\n    import doctest\n\n\
    doctest.testmod()\n'