X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/dbe845386fa136ccb8571e50dadb3c882661a59b..5670a10f90a88d52fda0d1f23fef62aa9edc8467:/apps/catalogue/models.py?ds=sidebyside diff --git a/apps/catalogue/models.py b/apps/catalogue/models.py index db194347e..133440b3b 100644 --- a/apps/catalogue/models.py +++ b/apps/catalogue/models.py @@ -6,6 +6,7 @@ from django.contrib.auth.models import User from django.core.files import File from django.template.loader import render_to_string from django.utils.safestring import mark_safe +from django.core.urlresolvers import reverse from newtagging.models import TagBase from newtagging import managers @@ -33,7 +34,7 @@ class TagSubcategoryManager(models.Manager): class Tag(TagBase): - name = models.CharField(_('name'), max_length=50, unique=True, db_index=True) + name = models.CharField(_('name'), max_length=50, db_index=True) slug = models.SlugField(_('slug'), max_length=120, unique=True, db_index=True) sort_key = models.SlugField(_('sort key'), max_length=120, db_index=True) category = models.CharField(_('category'), max_length=50, blank=False, null=False, @@ -69,18 +70,26 @@ class Tag(TagBase): return TagBase.get_tag_list(tags) +def book_upload_path(ext): + def get_dynamic_path(book, filename): + return 'lektura/%s.%s' % (book.slug, ext) + return get_dynamic_path + + class Book(models.Model): title = models.CharField(_('title'), max_length=120) slug = models.SlugField(_('slug'), max_length=120, unique=True, db_index=True) description = models.TextField(_('description'), blank=True) created_at = models.DateTimeField(_('creation date'), auto_now=True) _short_html = models.TextField(_('short HTML'), editable=False) + parent_number = models.IntegerField(_('parent number'), default=0) # Formats - xml_file = models.FileField(_('XML file'), upload_to='books/xml', blank=True) - pdf_file = models.FileField(_('PDF file'), upload_to='books/pdf', blank=True) - odt_file = models.FileField(_('ODT file'), upload_to='books/odt', blank=True) - html_file = models.FileField(_('HTML file'), upload_to='books/html', blank=True) + xml_file = models.FileField(_('XML file'), upload_to=book_upload_path('xml'), blank=True) + html_file = models.FileField(_('HTML file'), upload_to=book_upload_path('html'), blank=True) + pdf_file = models.FileField(_('PDF file'), upload_to=book_upload_path('pdf'), blank=True) + odt_file = models.FileField(_('ODT file'), upload_to=book_upload_path('odt'), blank=True) + txt_file = models.FileField(_('TXT file'), upload_to=book_upload_path('txt'), blank=True) parent = models.ForeignKey('self', blank=True, null=True, related_name='children') @@ -88,6 +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) @@ -97,11 +110,13 @@ class Book(models.Model): formats = [] if self.html_file: - formats.append(u'Czytaj online' % self.html_file.url) + formats.append(u'Czytaj online' % reverse('book_text', kwargs={'slug': self.slug})) if self.pdf_file: 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})) @@ -128,15 +143,24 @@ 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 # Read book metadata book_info = dcparser.parse(xml_file) - book = Book(title=book_info.title, slug=slughifi(book_info.title)) + book_base, book_slug = book_info.url.rsplit('/', 1) + 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 = [] @@ -146,50 +170,63 @@ class Book(models.Model): if category == 'author': tag_sort_key = tag_name.last_name tag_name = ' '.join(tag_name.first_names) + ' ' + tag_name.last_name - tag, created = Tag.objects.get_or_create(name=tag_name, - slug=slughifi(tag_name), sort_key=slughifi(tag_sort_key), category=category) - tag.save() + tag, created = Tag.objects.get_or_create(slug=slughifi(tag_name)) + if created: + tag.name = tag_name + tag.sort_key = slughifi(tag_sort_key) + tag.category = category + tag.save() book_tags.append(tag) book.tags = book_tags if hasattr(book_info, 'parts'): - for part_url in book_info.parts: + for n, part_url in enumerate(book_info.parts): base, slug = part_url.rsplit('/', 1) child_book = Book.objects.get(slug=slug) child_book.parent = book + child_book.parent_number = n child_book.save() # Save XML and HTML files 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}) - theme_names = [s.strip() for s in fragment.themes.split(',')] - themes = [] - for theme_name in theme_names: - tag, created = Tag.objects.get_or_create(name=theme_name, - slug=slughifi(theme_name), sort_key=slughifi(theme_name), 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): @@ -226,7 +263,10 @@ class Fragment(models.Model): {'fragment': self, 'book': self.book, 'book_authors': book_authors})) self.save() return mark_safe(self._short_html) - + + def get_absolute_url(self): + return '%s#m%s' % (reverse('book_text', kwargs={'slug': self.book.slug}), self.anchor) + class Meta: ordering = ('book', 'anchor',) verbose_name = _('fragment')