X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/9c31d87a67dca4861c1e609001a6807eba9b6967..3199cbfa76c763b4082b5a8d8f971d74f67e27c0:/catalogue/models.py
diff --git a/catalogue/models.py b/catalogue/models.py
index 483741be8..f3f6bc2d5 100644
--- a/catalogue/models.py
+++ b/catalogue/models.py
@@ -1,12 +1,17 @@
# -*- coding: utf-8 -*-
from django.db import models
-from django.db.models import permalink
+from django.db.models import permalink, Q
from django.utils.translation import ugettext_lazy as _
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 newtagging.models import TagBase
from newtagging import managers
+from librarian import html, dcparser
+
TAG_CATEGORIES = (
('author', _('author')),
@@ -39,12 +44,12 @@ class Tag(TagBase):
def has_description(self):
return len(self.description) > 0
- has_description.short_description = _('Has description')
+ has_description.short_description = _('description')
has_description.boolean = True
@permalink
def get_absolute_url(self):
- return ('catalogue.views.tagged_book_list', [self.slug])
+ return ('catalogue.views.tagged_object_list', [self.slug])
class Meta:
ordering = ('sort_key',)
@@ -68,18 +73,43 @@ class Book(models.Model):
slug = models.SlugField(_('slug'), 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)
# 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)
- objects = managers.ModelTaggedItemManager(Tag)
+ parent = models.ForeignKey('self', blank=True, null=True, related_name='children')
+
+ objects = models.Manager()
+ tagged = managers.ModelTaggedItemManager(Tag)
tags = managers.TagDescriptor(Tag)
+ def short_html(self):
+ if len(self._short_html):
+ return mark_safe(self._short_html)
+ else:
+ tags = self.tags.filter(~Q(category__in=('set', 'theme')))
+ tags = [u'%s' % (tag.get_absolute_url(), tag.name) for tag in tags]
+
+ formats = []
+ if self.html_file:
+ formats.append(u'Czytaj online' % self.html_file.url)
+ 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)
+
+ self._short_html = render_to_string('catalogue/book_short.html',
+ {'book': self, 'tags': tags, 'formats': formats})
+ self.save()
+ return mark_safe(self._short_html)
+
def has_description(self):
return len(self.description) > 0
- has_description.short_description = _('Has description')
+ has_description.short_description = _('description')
has_description.boolean = True
def has_pdf_file(self):
@@ -96,6 +126,69 @@ class Book(models.Model):
return bool(self.html_file)
has_html_file.short_description = 'HTML'
has_html_file.boolean = True
+
+ @staticmethod
+ def from_xml_file(xml_file):
+ 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.save()
+
+ book_tags = []
+ for category in ('kind', 'genre', 'author', 'epoch'):
+ tag_name = getattr(book_info, category)
+ tag_sort_key = tag_name
+ 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()
+ book_tags.append(tag)
+ book.tags = book_tags
+
+ if hasattr(book_info, 'parts'):
+ for part_url in book_info.parts:
+ base, slug = part_url.rsplit('/', 1)
+ child_book = Book.objects.get(slug=slug)
+ child_book.parent = book
+ 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 = MarkupString(text)[:160]
+ new_fragment = Fragment(text=text, short_text=short_text, anchor=fragment.id, book=book)
+
+ 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
+
+ book_themes = set(book_themes)
+ book.tags = list(book.tags) + list(book_themes)
+ return book.save()
@permalink
def get_absolute_url(self):
@@ -110,27 +203,31 @@ class Book(models.Model):
return self.title
-# class Fragment(models.Model):
-# id = models.IntegerField(primary_key=True)
-# text = models.TextField(blank=True)
-# start_paragraph = models.IntegerField(null=True, blank=True)
-# book_id = models.IntegerField(null=True, blank=True)
-# class Meta:
-# db_table = u'fragment'
-
-
-# class Inflections(models.Model):
-# word = models.CharField(max_length=120, primary_key=True)
-# cases = models.TextField() # This field type is a guess.
-# class Meta:
-# db_table = u'inflections'
-
+class Fragment(models.Model):
+ text = models.TextField()
+ short_text = models.TextField(editable=False)
+ _short_html = models.TextField(editable=False)
+ anchor = models.IntegerField()
+ book = models.ForeignKey(Book, related_name='fragments')
-# class Paragraph(models.Model):
-# id = models.IntegerField(primary_key=True)
-# number = models.IntegerField(null=True, blank=True)
-# text = models.TextField(blank=True)
-# book_id = models.IntegerField(null=True, blank=True)
-# class Meta:
-# db_table = u'paragraph'
+ objects = models.Manager()
+ tagged = managers.ModelTaggedItemManager(Tag)
+ tags = managers.TagDescriptor(Tag)
+
+ def short_html(self):
+ if len(self._short_html):
+ return mark_safe(self._short_html)
+ else:
+ book_authors = [u'%s' % (tag.get_absolute_url(), tag.name)
+ for tag in self.book.tags if tag.category == 'author']
+
+ self._short_html = render_to_string('catalogue/fragment_short.html',
+ {'fragment': self, 'book': self.book, 'book_authors': book_authors})
+ self.save()
+ return mark_safe(self._short_html)
+
+ class Meta:
+ ordering = ('book', 'anchor',)
+ verbose_name = _('fragment')
+ verbose_name_plural = _('fragments')