Пример #1
0
def main():

    import argparse
    import sys

    sys.path.append("../../helpers")
    import sourcefile

    parser = argparse.ArgumentParser(description='Footnotes checker PGDP PP.')
    parser.add_argument('filename',
                        metavar='FILENAME',
                        type=str,
                        help='input text file')
    args = parser.parse_args()

    myfile = sourcefile.SourceFile()

    myfile.load_text(args.filename)

    if myfile.text is None:
        print("Cannot read file", f)
        return

    x = FootNotes()
    x.check_footnotes(myfile)

    print(x.anchor_ranges)
    print(x.fn_found)
    print(x.anchor_not_found)
Пример #2
0
    def index_source(self,
                     source_directory: str = "",
                     specific_pages: [str] = []) -> None:
        """
        Indexes source directory.

        Defaults to self.directory; specific filenames can be provided as string list
        """
        source_path = os.path.join(self.directory, source_directory)

        source_filenames = [
            file for file in os.listdir(source_path)
            if os.path.isfile(os.path.join(source_path, file))
        ]

        for filename in source_filenames:

            if len(specific_pages) > 0:
                if filename not in specific_pages:
                    continue

            self.source_files.append(
                sourcefile.SourceFile(self.directory,
                                      os.path.join(source_directory,
                                                   filename)))
Пример #3
0
def main():

    import argparse
    import sys

    sys.path.append("../helpers")
    import sourcefile

    parser = argparse.ArgumentParser(description='Quotes checker PGDP PP.')

    parser.add_argument('--encoding',
                        dest='encoding',
                        help='force document encoding (latin1, utf-8, ...)',
                        default=None)
    parser.add_argument('filename',
                        metavar='FILENAME',
                        type=str,
                        help='input text file')

    help_string = 'Type of quotes to check:'
    for i, q in enumerate(quotes, start=1):
        help_string += "  " + str(i) + " = " + q['open'] + " ... " + q['close']

    parser.add_argument('type', type=int, help=help_string, default=0)

    args = parser.parse_args()

    myfile = sourcefile.SourceFile()

    myfile.load_text(args.filename)

    if myfile.text is None:
        print("Cannot read file", f)
        return

    x = check()

    if args.type == 0:
        for q in quotes:
            x.check_quotes(myfile, q)

    else:
        x.check_quotes(myfile, quotes[args.type - 1])

    for qkey, errors in x.unbalanced.items():
        print(qkey)
        for err in errors:
            print(err[0], err[1], err[2])
Пример #4
0
def test_kpoints():

    import argparse
    import os
    import sys
    import sourcefile

    myfile = sourcefile.SourceFile()
    myfile.load_xhtml("data/testfiles/kpoints.html")

    assert (myfile.tree)

    kp = KPoints()
    kp.check_points(myfile)

    # There should be 2 strings to check
    assert ("centimes. traduct" in kp.point_matches)
    assert ("dot. or" in kp.point_matches)
    assert (len(kp.point_matches) == 2)
Пример #5
0
        self.point_matches = sorted(set(self.point_matches))


if __name__ == '__main__':

    import argparse
    import os

    import sourcefile

    parser = argparse.ArgumentParser(
        description='Diff text document for PGDP PP.')

    parser.add_argument('filename',
                        metavar='FILENAME',
                        type=str,
                        help='input text file')

    args = parser.parse_args()

    kp = KPoints()

    myfile = sourcefile.SourceFile()
    myfile.load_xhtml(args.filename)

    kp.check_points(myfile)

    for x in sorted(kp.point_matches):
        print(x)