astlan-diff.py

A Python script for finding changes between Astlan EPUB editions:

[code=python]
#!/usr/bin/python3
# -*- coding: utf-8 -*-

import difflib
import epub
from bs4 import BeautifulSoup

def text_paras(book, href):
soup = BeautifulSoup(book.read_item(href), ‘lxml’)
return [x.get_text() for x in soup.find_all(‘p’)]

book1 = epub.open_epub(‘Apostles of Doom Alpha 1 – J. L. Langland.epub’)
book2 = epub.open_epub(‘Apostles of Doom Alpha 2 – J. L. Langland.epub’)

for item in book1.opf.manifest.values():
print(item.href)
if item and item.media_type == ‘application/xhtml+xml’:
paras1 = text_paras(book1, item.href)
paras2 = text_paras(book2, item.href)

s = difflib.SequenceMatcher(None, paras1, paras2)
for opcode in s.get_opcodes():
print(“%6s a[%d:%d] b[%d:%d]” % opcode)

if opcode[0] == ‘insert’:
print(‘B: ‘, paras2[opcode[3]:opcode[4]])

elif opcode[0] == ‘replace’:
print(‘A: ‘, paras1[opcode[1]:opcode[2]])
print(‘B: ‘, paras2[opcode[3]:opcode[4]])

elif opcode[0] == ‘delete’:
print(‘A: ‘, paras1[opcode[1]:opcode[2]])

[/code]

I was also looking at using either NLTK or Google’s Tensor Flow language models to pull out all of the character and place names for spell checking, but that will have to wait until later.