From 8b9977bc8cbf4b0c2bc90eb32ec3c78c91c5395c Mon Sep 17 00:00:00 2001
From: Guillaume Horel <guillaume.horel@gmail.com>
Date: Sat, 3 Aug 2013 17:31:08 -0400
Subject: preliminary version of compare

---
 compare.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 compare.py

(limited to 'compare.py')

diff --git a/compare.py b/compare.py
new file mode 100644
index 0000000..4fcacd0
--- /dev/null
+++ b/compare.py
@@ -0,0 +1,15 @@
+import pdb
+from wikisource import get_page
+from parsedjvutext import parse_book
+import lcs
+
+wikibook = "Villiers de L'Isle-Adam - Tribulat Bonhomet, 1908.djvu"
+ocrbook = "Tribulat Bonhomet.xml"
+
+ocrbook = parse_book(ocrbook)
+
+n = 14
+l1 = ocrbook['words'][n]
+l2 = get_page(wikibook, n+1).split()
+C = lcs.LCS(l1, l2)
+lcs.printDiff(C, l1, l2, len(l1), len(l2))
-- 
cgit v1.2.3-70-g09d2