plainify.py

import os
import re
import shutil
import sys

TITLE_RE = re.compile(r"^\s*#\+TITLE:\s*([^\n]+)\n")
PROPERTIES_RE = re.compile(r"^\n?[ \t]*:PROPERTIES:[ \t]*\n", re.MULTILINE)
END_RE = re.compile(r"^[ \t]*:END:[ \t]*\n\n", re.MULTILINE)
PROPERTY_RE = re.compile(r"^[ \t]*:[\w\-]+:[^\n]*\n", re.MULTILINE)
ITALICS_RE = re.compile(r"^/([^\n]+)/", re.MULTILINE)
HASH_RE = re.compile(r"^#[^\n]+\n", re.MULTILINE)
VERSE_RE = re.compile(r"^#\+(?:BEGIN|END)_VERSE[ \t]*\n", re.MULTILINE)
INDEX_RE = re.compile(r"[\n]+\* Index\s+")


def plainify_dir(directory):
    destDir = os.path.join(os.path.dirname(directory), os.path.basename(directory) + " plain")

    if os.path.exists(destDir):
        shutil.rmtree(destDir)

    for root, dirs, files in os.walk(directory):
        newDir = os.path.join(destDir, root[len(directory) + 1:])

        if not os.path.isdir(newDir):
            os.makedirs(newDir)

        for file in files:
            if file.endswith(".txt"):
                plainify(os.path.join(root, file), os.path.join(newDir, file))


def plainify(source, dest):
    print(source)

    with open(source, "r", encoding="utf-8") as f:
        text = f.read()

    match = TITLE_RE.match(text)

    if match:
        title = match.group(1) + "\n\n\n"
    else:
        title = ""

    newText = PROPERTIES_RE.sub("", text)
    newText = END_RE.sub("", newText)
    newText = PROPERTY_RE.sub("", newText)
    newText = ITALICS_RE.sub(r"\1", newText)
    newText = VERSE_RE.sub("", newText)
    newText = HASH_RE.sub("", newText)
    newText = INDEX_RE.sub("", newText)

    with open(dest, "w", encoding="utf-8") as f:
        f.write(title + newText)


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("usage: plainify.py library-dir")
        sys.exit(1)
    else:
        directory = sys.argv[1]

        if not os.path.isdir(directory):
            print("ERROR: No such directory '{0}'".format(directory))
            sys.exit(1)
        else:
            plainify_dir(directory)