# Extract fragments
closed_fragments, open_fragments = html.extract_fragments(book.html_file.path)
for fragment in closed_fragments.values():
- text = fragment.to_string()
- short_text = ''
- if (len(MarkupString(text)) > 240):
- short_text = unicode(MarkupString(text)[:160])
- new_fragment, created = Fragment.objects.get_or_create(anchor=fragment.id, book=book,
- defaults={'text': text, 'short_text': short_text})
-
try:
theme_names = [s.strip() for s in fragment.themes.split(',')]
except AttributeError:
continue
themes = []
for theme_name in theme_names:
+ if not theme_name:
+ continue
tag, created = Tag.objects.get_or_create(slug=slughifi(theme_name), category='theme')
if created:
tag.name = theme_name
tag.sort_key = slughifi(theme_name)
tag.save()
themes.append(tag)
+ if not themes:
+ continue
+
+ text = fragment.to_string()
+ short_text = ''
+ if (len(MarkupString(text)) > 240):
+ short_text = unicode(MarkupString(text)[:160])
+ new_fragment, created = Fragment.objects.get_or_create(anchor=fragment.id, book=book,
+ defaults={'text': text, 'short_text': short_text})
+
new_fragment.save()
new_fragment.tags = set(book_tags + themes + [book_tag])
self.assert_(('theme', 'love') in [ (tag.category, tag.slug) for tag in book.fragments.all()[0].tags ])
+ def test_book_with_empty_theme(self):
+ """ empty themes should be ignored """
+
+ BOOK_TEXT = """<utwor>
+ <opowiadanie>
+ <akap><begin id="m01" /><motyw id="m01"> , Love , , </motyw>Ala ma kota<end id="m01" /></akap>
+ </opowiadanie></utwor>
+ """
+
+ book = models.Book.from_text_and_meta(ContentFile(BOOK_TEXT), self.book_info)
+ self.assert_([('theme', 'love')],
+ [ (tag.category, tag.slug) for tag in book.fragments.all()[0].tags.filter(category='theme') ])
+
+ def test_book_with_no_theme(self):
+ """ fragments with no themes shouldn't be created at all """
+
+ BOOK_TEXT = """<utwor>
+ <opowiadanie>
+ <akap><begin id="m01" /><motyw id="m01"></motyw>Ala ma kota<end id="m01" /></akap>
+ </opowiadanie></utwor>
+ """
+
+ book = models.Book.from_text_and_meta(ContentFile(BOOK_TEXT), self.book_info)
+ self.assertEqual(book.fragments.count(), 0)
+ self.assertEqual(book.tags.filter(category='theme').count(), 0)
+
def test_book_replace_title(self):
BOOK_TEXT = """<utwor />"""
book = models.Book.from_text_and_meta(ContentFile(BOOK_TEXT), self.book_info)