From f633ea807ef9a83f84f41767e71fad71656a4439 Mon Sep 17 00:00:00 2001
From: Thibaut Horel <thibaut.horel@gmail.com>
Date: Sat, 17 Aug 2013 18:25:04 +0200
Subject: Take line jumps into accounts when grouping words

---
 compare.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'compare.py')

diff --git a/compare.py b/compare.py
index a458924..7305517 100644
--- a/compare.py
+++ b/compare.py
@@ -7,10 +7,10 @@ import string_utils as su
 # wikibook = "Bloy - Le Sang du pauvre, Stock, 1932.djvu".replace(" ", "_")
 wikibook = "Villiers de L'Isle-Adam - Tribulat Bonhomet, 1908.djvu".replace(" ", "_")
 
-n = 79
+n = 88
 ocrpage = parse_page_sexp(wikibook, n)
-l1 = ocrpage['words']
+l1, c1 = ocrpage['words'], ocrpage["coords"]
 l2 = get_page(wikibook, n)
 l3 = su.simplify(l2)
-C = su.align(l2.split(), l1)
-su.print_alignment(l3.split(), l1, C[1])
+C = su.align(l3.split(), l1, c1)
+su.print_alignment(l2.split(), l1, c1, C[1])
-- 
cgit v1.2.3-70-g09d2