X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/e3f24620b9a69f1eb0652a9ffec2c2c3d6a10b8e..5670a10f90a88d52fda0d1f23fef62aa9edc8467:/apps/catalogue/models.py diff --git a/apps/catalogue/models.py b/apps/catalogue/models.py index 7f6268fdb..133440b3b 100644 --- a/apps/catalogue/models.py +++ b/apps/catalogue/models.py @@ -97,6 +97,10 @@ class Book(models.Model): tagged = managers.ModelTaggedItemManager(Tag) tags = managers.TagDescriptor(Tag) + @property + def name(self): + return self.title + def short_html(self): if len(self._short_html): return mark_safe(self._short_html) @@ -111,6 +115,8 @@ class Book(models.Model): formats.append(u'Plik PDF' % self.pdf_file.url) if self.odt_file: formats.append(u'Plik ODT' % self.odt_file.url) + if self.txt_file: + formats.append(u'Plik TXT' % self.txt_file.url) self._short_html = unicode(render_to_string('catalogue/book_short.html', {'book': self, 'tags': tags, 'formats': formats})) @@ -137,8 +143,11 @@ class Book(models.Model): has_html_file.short_description = 'HTML' has_html_file.boolean = True + class AlreadyExists(Exception): + pass + @staticmethod - def from_xml_file(xml_file): + def from_xml_file(xml_file, overwrite=False): from tempfile import NamedTemporaryFile from slughifi import slughifi from markupstring import MarkupString @@ -146,7 +155,12 @@ class Book(models.Model): # Read book metadata book_info = dcparser.parse(xml_file) book_base, book_slug = book_info.url.rsplit('/', 1) - book = Book(title=book_info.title, slug=book_slug) + book, created = Book.objects.get_or_create(slug=book_slug) + if not created and not overwrite: + raise Book.AlreadyExists('Book %s already exists' % book_slug) + + book.title = book_info.title + book._short_html = '' book.save() book_tags = [] @@ -177,39 +191,42 @@ class Book(models.Model): book.xml_file.save('%s.xml' % book.slug, File(file(xml_file)), save=False) html_file = NamedTemporaryFile() - html.transform(book.xml_file.path, html_file) - book.html_file.save('%s.html' % book.slug, File(html_file), save=False) - - # Extract fragments - closed_fragments, open_fragments = html.extract_fragments(book.html_file.path) - book_themes = [] - 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 = Fragment(text=text, short_text=short_text, anchor=fragment.id, book=book) + if html.transform(book.xml_file.path, html_file): + book.html_file.save('%s.html' % book.slug, File(html_file), save=False) + + # Extract fragments + closed_fragments, open_fragments = html.extract_fragments(book.html_file.path) + book_themes = [] + 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: + tag, created = Tag.objects.get_or_create(slug=slughifi(theme_name)) + if created: + tag.name = theme_name + tag.sort_key = slughifi(theme_name) + tag.category = 'theme' + tag.save() + themes.append(tag) + new_fragment.save() + new_fragment.tags = list(book.tags) + themes + book_themes += themes - try: - theme_names = [s.strip() for s in fragment.themes.split(',')] - except AttributeError: - continue - themes = [] - for theme_name in theme_names: - tag, created = Tag.objects.get_or_create(slug=slughifi(theme_name)) - if created: - tag.name = theme_name - tag.sort_key = slughifi(theme_name) - tag.category = 'theme' - tag.save() - themes.append(tag) - new_fragment.save() - new_fragment.tags = list(book.tags) + themes - book_themes += themes + book_themes = set(book_themes) + book.tags = list(book.tags) + list(book_themes) - book_themes = set(book_themes) - book.tags = list(book.tags) + list(book_themes) - return book.save() + book.save() + return book @permalink def get_absolute_url(self):