Convert string to pandoc auto_identifiers default algorithm. Intended as a CopyQ clipboard function.

pandoc_identifier.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# (c) Copyright 2019 by Joseph Reagle
# Licensed under the GPLv3, see <http://www.gnu.org/licenses/gpl-3.0.html>
#
""" Convert string to pandoc auto_identifiers default algorithm. 
    Intended as a CopyQ clipboard function.
"""

import argparse  # http://docs.python.org/dev/library/argparse.html
import doctest
import logging
import re
import sys

critical = logging.critical
error = logging.error
warn = logging.warn
info = logging.info
debug = logging.debug
excpt = logging.exception


def auto_id(s):
    """Convert to pandoc auto_identifer.

    https://pandoc.org/MANUAL.html#headings-and-sections

    >>> auto_id("Heading identifiers in HTML")
    'heading-identifiers-in-html'
    >>> auto_id("Maître d'hôtel")
    'maître-dhôtel'
    >>> auto_id("*Dogs*?--in *my* house?")
    'dogs--in-my-house'
    >>> auto_id("[HTML], [S5], or [RTF]?")
    'html-s5-or-rtf'
    >>> auto_id("3. Applications")
    'applications'
    >>> auto_id("33")
    'section'

    """

    # Remove all formatting, links, etc.
    # Ignored, not in clipboard

    # Remove all footnotes.
    # ignored, not in clipboard

    # Replace all spaces and newlines with hyphens. [jr: moved up]
    s = re.sub(r"\s", r"-", s)
    info(f"{s=} ==============")

    # Remove all non-alphanumeric characters, except underscores, hyphens, and
    # periods.
    s = re.sub(r"[^\w\-\.]", r"", s, flags=re.UNICODE)
    info(f"{s=}")

    # Convert all alphabetic characters to lowercase.
    s = s.lower()
    info(f"{s=}")

    # Remove everything up to the first letter
    # (identifiers may not begin with number or punctuation mark).
    # [jr: first letter *or* underscore]
    s = re.sub(r"^[^a-zA-Z_]+", r"", s)
    info(f"{s=}")

    # If nothing is left after this, use the identifier section.
    if not s:
        s = "section"
    info(f"{s=}")

    return s


def main(argv):
    """Process arguments and execute."""

    arg_parser = argparse.ArgumentParser(
        description="Convert text to pandoc auto_identifiers"
    )
    # positional arguments
    arg_parser.add_argument("text", nargs="*", metavar="TEXT")
    arg_parser.add_argument(
        "-T", "--test", action="store_true", default=False, help="Test"
    )
    arg_parser.add_argument(
        "-L",
        "--log-to-file",
        action="store_true",
        default=False,
        help="log to file %(prog)s.log",
    )
    arg_parser.add_argument(
        "-V",
        "--verbose",
        action="count",
        default=0,
        help="Increase verbosity (specify multiple times for more)",
    )
    arg_parser.add_argument(
        "--version",
        action="version",
        version=f"0.1 using Python {sys.version}",
    )
    args = arg_parser.parse_args()

    log_level = 100  # default
    if args.verbose == 1:
        log_level = logging.CRITICAL  # 50
    elif args.verbose == 2:
        log_level = logging.INFO  # 20
    elif args.verbose >= 3:
        log_level = logging.DEBUG  # 10
    LOG_FORMAT = "%(levelno)s %(funcName).5s: %(message)s"
    if args.log_to_file:
        info("logging to file")
        logging.basicConfig(
            filename="change_case.log",
            filemode="w",
            level=log_level,
            format=LOG_FORMAT,
        )
    else:
        logging.basicConfig(level=log_level, format=LOG_FORMAT)

    if args.test:
        doctest.testmod()
    else:
        text = " ".join(args.text)
        result = auto_id(text)
        info(result)
        print(result)


if "__main__" == __name__:
    main(sys.argv[1:])