From 1d53df7c99126679d391a1efc96b30aa3848b4d3 Mon Sep 17 00:00:00 2001 From: Guillaume Horel Date: Sat, 17 Aug 2013 19:01:24 -0400 Subject: add function for converting alignment to sexp --- parsedjvutext.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'parsedjvutext.py') diff --git a/parsedjvutext.py b/parsedjvutext.py index 3d4ee96..773a1d4 100644 --- a/parsedjvutext.py +++ b/parsedjvutext.py @@ -33,11 +33,14 @@ def parse_wordline(line): coords = map(int, line[1:5]) return word, coords -def parse_page_sexp(djvubook, pagenumber): +def page_sexp(djvubook, pagenumber): args = ["djvused", "-e", "select {0};print-txt".format(pagenumber), djvubook] - page = [parse_wordline(line) for line in \ - subprocess.check_output(args).split("\n") if "word" in line] + return subprocess.check_output(args).split("\n") + +def parse_page_sexp(djvubook, pagenumber): + page = [parse_wordline(line) for line in page_sexp(djvubook, pagenumber) \ + if "word" in line] return {"words": [a for a, b in page], "coords": [b for a, b in page]} def parse_book_sexp(djvubook): -- cgit v1.2.3-70-g09d2