fnp
/
wolnelektury.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
check for empty source in dc
[wolnelektury.git]
/
apps
/
lesmianator
/
models.py
diff --git
a/apps/lesmianator/models.py
b/apps/lesmianator/models.py
index
5103ebb
..
1b53efd
100644
(file)
--- a/
apps/lesmianator/models.py
+++ b/
apps/lesmianator/models.py
@@
-18,7
+18,6
@@
from django.contrib.contenttypes.models import ContentType
from django.contrib.contenttypes import generic
from django.conf import settings
from django.contrib.contenttypes import generic
from django.conf import settings
-from librarian import text
from catalogue.fields import JSONField
from catalogue.models import Book, Tag
from catalogue.fields import JSONField
from catalogue.models import Book, Tag
@@
-126,12
+125,13
@@
class Continuations(models.Model):
def for_book(cls, book, length=3):
# count from this book only
output = StringIO()
def for_book(cls, book, length=3):
# count from this book only
output = StringIO()
- f = open(book.xml_file.path)
- text.transform(f, output, False, ('raw-text',))
- f.close()
+ wldoc = book.wldocument(parse_dublincore=False)
+ output = wldoc.as_text(('raw-text',)).get_string()
+ del wldoc
+
conts = {}
last_word = ''
conts = {}
last_word = ''
- for letter in output.
getvalue().
decode('utf-8').strip().lower():
+ for letter in output.decode('utf-8').strip().lower():
mydict = conts.setdefault(last_word, {})
mydict.setdefault(letter, 0)
mydict[letter] += 1
mydict = conts.setdefault(last_word, {})
mydict.setdefault(letter, 0)
mydict[letter] += 1