diff options
| author | Guillaume Horel <guillaume.horel@serenitascapital.com> | 2014-02-28 17:31:19 -0500 |
|---|---|---|
| committer | Guillaume Horel <guillaume.horel@serenitascapital.com> | 2014-02-28 17:31:54 -0500 |
| commit | 6e694d555e1004da58ec3425d33043b2f1b5f715 (patch) | |
| tree | 01fc9f907401f50cf6c869c7e1c057287b2dc405 /parsedjvutext.py | |
| parent | aaa42a8efcd53576ced9bf2311e84d8ff2a5c8cf (diff) | |
| download | ocr-layer-curation-6e694d555e1004da58ec3425d33043b2f1b5f715.tar.gz | |
update with the new functions
Diffstat (limited to 'parsedjvutext.py')
| -rw-r--r-- | parsedjvutext.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/parsedjvutext.py b/parsedjvutext.py index ad98d1d..6bd9950 100644 --- a/parsedjvutext.py +++ b/parsedjvutext.py @@ -21,7 +21,7 @@ def parse_page(page, html=False): else: coords = [s[i].value for i in xrange(1, 5)] word = s[5].value - yield (word, coords) + yield (word.decode("utf-8"), coords) else: for c in chain.from_iterable(aux(child, html) for child in s[5:]): yield c |