convert sqlite3 format bible to zefania format

bible-convert-from-sqlite3-to-zefania.py

#!/usr/bin/env python

import os
import re
import sys
import sqlite3
import zhconv


book_name_map = {
    "創世記": "Genesis",
    "出埃及記": "Exodus",
    "利未記": "Leviticus",
    "民數記": "Numbers",
    "申命記": "Deuteronomy",
    "約書亞記": "Joshua",
    "士師記": "Judges",
    "路得記": "Ruth",
    "撒母耳記上": "1 Samuel",
    "撒母耳記下": "2 Samuel",
    "列王紀上": "1 Kings",
    "列王紀下": "2 Kings",
    "歷代志上": "1 Chronicles",
    "歷代志下": "2 Chronicles",
    "以斯拉記": "Ezra",
    "尼希米記": "Nehemiah",
    "以斯帖記": "Esther",
    "約伯記": "Job",
    "詩篇": "Psalm",
    "箴言": "Proverbs",
    "傳道書": "Ecclesiastes",
    "雅歌": "Song of Solomon",
    "以賽亞書": "Isaiah",
    "耶利米書": "Jeremiah",
    "耶利米哀歌": "Lamentations",
    "以西結書": "Ezekiel",
    "但以理書": "Daniel",
    "何西阿書": "Hosea",
    "約珥書": "Joel",
    "阿摩司書": "Amos",
    "俄巴底亞書": "Obadiah",
    "約拿書": "Jonah",
    "彌迦書": "Micah",
    "那鴻書": "Nahum",
    "哈巴谷書": "Habakkuk",
    "西番雅書": "Zephaniah",
    "哈該書": "Haggai",
    "撒迦利亞書": "Zechariah",
    "瑪拉基書": "Malachi",
    "馬太福音": "Matthew",
    "馬可福音": "Mark",
    "路加福音": "Luke",
    "約翰福音": "John",
    "使徒行傳": "Acts",
    "羅馬書": "Romans",
    "哥林多前書": "1 Corinthians",
    "哥林多後書": "2 Corinthians",
    "加拉太書": "Galatians",
    "以弗所書": "Ephesians",
    "腓立比書": "Philippians",
    "歌羅西書": "Colossians",
    "帖撒羅尼迦前書": "1 Thessalonians",
    "帖撒羅尼迦後書": "2 Thessalonians",
    "提摩太前書": "1 Timothy",
    "提摩太後書": "2 Timothy",
    "彼得前書": "1 Peter",
    "彼得後書": "2 Peter",
    "約翰壹書": "1 John",
    "約翰貳書": "2 John",
    "約翰參書": "3 John",
    "猶大書": "Jude",
    "雅各書": "James",
    "提多書": "Titus",
    "腓利門書": "Philemon",
    "希伯來書": "Hebrews",
    "啟示錄": "Revelation"
}


ZEFANIA_HEADER='''<?xml version="1.0"?>
<XMLBIBLE biblename="Chinese Contemporary Bible, 2012">
'''


ZEFANIA_FOOTER='''</XMLBIBLE>'''


BOOK_INDENT = ' ' * 4
CHAP_INDENT = ' ' * 8
VERSE_INDENT = ' ' * 12


def usage():
    print("usage: %s <source sqlite3 file> <output xml filename>" % sys.argv[0])
    sys.exit(-1)


if __name__ == '__main__':

    if len(sys.argv) != 3:
        usage

    sqlite_file = sys.argv[1]
    if not os.path.exists(sqlite_file):
        print('source sqlite3 file: %s do NOT exists.' % sqlite_file)
        usage

    output_xml = sys.argv[2]
    try:
        db = sqlite3.connect(sqlite_file)
        db.execute('select count(*) from books')
        db.execute('select count(*) from verses')
    except Exception as e:
        print(e)
        sys.exit(-1)

    regex = re.compile('</*.*?>')
    with open(output_xml, 'w') as f:
        f.write(ZEFANIA_HEADER)

        books = set()
        for book in db.cursor().execute('select book_number from books'):
            books.add(book[0])
        for idx, book_id in enumerate(sorted(books)):
            book_info = db.cursor().execute("select long_name, short_name from books where book_number='%s'" % book_id).fetchone()
            long_name = zhconv.convert(book_info[0], 'zh-hans')
            short_name = zhconv.convert(book_info[1], 'zh-hans')
            #book_name = book_name_map[long_name]
            f.write(BOOK_INDENT + '<BIBLEBOOK bnumber="%d" bname="%s" bsname="%s">\n' % (idx+1, long_name, short_name))

            chapters = set()
            for chap in db.cursor().execute("select chapter from verses where book_number='%s'" % book_id):
                chapters.add(chap[0])

            for chap_id in sorted(chapters):
                f.write(CHAP_INDENT + '<CHAPTER cnumber="%s">\n' % chap_id)
                verses = db.cursor().execute("select * from verses where book_number='%d' and chapter='%d'" % (book_id, chap_id)).fetchall()
                verse_ids = set()
                verses_map = {}
                for verse in verses:
                    verse_ids.add(verse[2])
                    verses_map[verse[2]] = verse

                for verse_id in sorted(verse_ids):
                    f.write(VERSE_INDENT + '<VERS vnumber="%s">' % (verse_id))
                    verse_text = verses_map[verse_id][3]
                    #import pdb; pdb.set_trace()
                    if verse_text is not None:
                        strip_text = regex.sub('', verse_text)
                        f.write(zhconv.convert(strip_text, 'zh-hans'))
                    f.write("</VERS>\n")
                f.write(CHAP_INDENT + '</CHAPTER>\n')
            f.write(BOOK_INDENT + '</BIBLEBOOK>\n')
        f.write(ZEFANIA_FOOTER)
    db.close()