From b5a00a5e914da988dcd81c6d276f7bb22a46aa20 Mon Sep 17 00:00:00 2001 From: Thibaut Horel Date: Sat, 17 Aug 2013 14:59:36 +0200 Subject: Some tweaks --- compare.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'compare.py') diff --git a/compare.py b/compare.py index c37cde9..a458924 100644 --- a/compare.py +++ b/compare.py @@ -4,12 +4,13 @@ from wikisource import get_page from parsedjvutext import parse_page_sexp 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(" ", "_") +# wikibook = "Bloy - Le Sang du pauvre, Stock, 1932.djvu".replace(" ", "_") +wikibook = "Villiers de L'Isle-Adam - Tribulat Bonhomet, 1908.djvu".replace(" ", "_") n = 79 ocrpage = parse_page_sexp(wikibook, n) l1 = ocrpage['words'] -l2 = get_page(wikibook, n).replace(u"’", u"'").split() -C = su.align(l2, l1) -su.print_alignment(l2, l1, C[1]) +l2 = get_page(wikibook, n) +l3 = su.simplify(l2) +C = su.align(l2.split(), l1) +su.print_alignment(l3.split(), l1, C[1]) -- cgit v1.2.3-70-g09d2