esv/convert.py

177 lines
2.8 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
import json
import pandas
import re
import os
titles = [
"Genesis",
"Exodus",
"Leviticus",
"Numbers",
"Deuteronomy",
"Joshua",
"Judges",
"Ruth",
"1 Samuel",
"2 Samuel",
"1 Kings",
"2 Kings",
"1 Chronicles",
"2 Chronicles",
"Ezra",
"Nehemiah",
"Esther",
"Job",
"Psalms",
"Proverbs",
"Ecclesiastes",
"Song of Solomon",
"Isaiah",
"Jeremiah",
"Lamentations",
"Ezekiel",
"Daniel",
"Hosea",
"Joel",
"Amos",
"Obadiah",
"Jonah",
"Micah",
"Nahum",
"Habakkuk",
"Zephaniah",
"Haggai",
"Zechariah",
"Malachi",
"Matthew",
"Mark",
"Luke",
"John",
"The Acts",
"Romans",
"1 Corinthians",
"2 Corinthians",
"Galatians",
"Ephesians",
"Philippians",
"Colossians",
"1 Thessalonians",
"2 Thessalonians",
"1 Timothy",
"2 Timothy",
"Titus",
"Philemon",
"Hebrews",
"James",
"1 Peter",
"2 Peter",
"1 John",
"2 John",
"3 John",
"Jude",
"Revelation"
]
abbreviations = [
"Ge",
"Exo",
"Lev",
"Num",
"Deu",
"Josh",
"Jdgs",
"Ruth",
"1Sm",
"2Sm",
"1Ki",
"2Ki",
"1Chr",
"2Chr",
"Ezra",
"Neh",
"Est",
"Job",
"Psa",
"Prv",
"Eccl",
"SSol",
"Isa",
"Jer",
"Lam",
"Eze",
"Dan",
"Hos",
"Joel",
"Amos",
"Obad",
"Jonah",
"Mic",
"Nahum",
"Hab",
"Zep",
"Hag",
"Zec",
"Mal",
"Mat",
"Mark",
"Luke",
"John",
"Acts",
"Rom",
"1Cor",
"2Cor",
"Gal",
"Eph",
"Phi",
"Col",
"1Th",
"2Th",
"1Tim",
"2Tim",
"Titus",
"Phmn",
"Heb",
"Jas",
"1Pet",
"2Pet",
"1Jn",
"2Jn",
"3Jn",
"Jude",
"Rev"
]
f = open('ESV.json')
json_list = json.load(f)
# The keys we need to extract from the json data
key_list = ['book', 'chapter', 'verse', 'text']
json_list = [{k:d[k] for k in key_list} for d in json_list]
df = pandas.json_normalize(json_list)
# Function to get book name
def get_name(row):
index = int(row["book"]) - 1
return abbreviations[index], titles[index]
df.insert(0, "name", '')
df.insert(0, "abbrev", '')
df[["name", "abbrev"]] = df.apply(get_name, axis=1, result_type='expand')
export_csv = df.to_csv('esv.tsv',
sep='\t',
encoding='utf-8',
header=False,
index=None)
# Sanity check the size of the file.
file_stats = os.stat("esv.tsv")
if file_stats.st_size != 4616589:
print("Warning: File appears different from recorded value")
print("Recorded value: 4616589")
print("Found value: ", file_stats.st_size)
else:
print("Convertion successful!")