Some search tests and fixes.

[wolnelektury.git] / apps / catalogue / models.py

diff --git a/apps/catalogue/models.py b/apps/catalogue/models.py
index f31dbe6..2097e17 100644 (file)
--- a/apps/catalogue/models.py
+++ b/apps/catalogue/models.py
@@ -1,4 +1,7 @@
 # -*- coding: utf-8 -*-
 # -*- coding: utf-8 -*-

+# This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+#

 from django.db import models
 from django.db.models import permalink, Q
 from django.utils.translation import ugettext_lazy as _
 from django.db import models
 from django.db.models import permalink, Q
 from django.utils.translation import ugettext_lazy as _


@@ -6,12 +9,16 @@ 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.files import File
 from django.template.loader import render_to_string
 from django.utils.safestring import mark_safe

+from django.utils.translation import get_language

 from django.core.urlresolvers import reverse
 from django.core.urlresolvers import reverse

+from datetime import datetime

 
 from newtagging.models import TagBase
 from newtagging import managers
 
 from newtagging.models import TagBase
 from newtagging import managers

+from catalogue.fields import JSONField

 
 from librarian import html, dcparser
 
 from librarian import html, dcparser

+from mutagen import id3

 
 
 TAG_CATEGORIES = (
 
 
 TAG_CATEGORIES = (


@@ -21,6 +28,7 @@ TAG_CATEGORIES = (
     ('genre', _('genre')),
     ('theme', _('theme')),
     ('set', _('set')),
     ('genre', _('genre')),
     ('theme', _('theme')),
     ('set', _('set')),

+    ('book', _('book')),

 )
 
 
 )
 
 


@@ -41,14 +49,29 @@ class Tag(TagBase):
         db_index=True, choices=TAG_CATEGORIES)
     description = models.TextField(_('description'), blank=True)
     main_page = models.BooleanField(_('main page'), default=False, db_index=True, help_text=_('Show tag on main page'))
         db_index=True, choices=TAG_CATEGORIES)
     description = models.TextField(_('description'), blank=True)
     main_page = models.BooleanField(_('main page'), default=False, db_index=True, help_text=_('Show tag on main page'))

-        
+    

     user = models.ForeignKey(User, blank=True, null=True)
     user = models.ForeignKey(User, blank=True, null=True)

+    book_count = models.IntegerField(_('book count'), default=0, blank=False, null=False)
+    death = models.IntegerField(_(u'year of death'), blank=True, null=True)
+    gazeta_link = models.CharField(blank=True,  max_length=240)
+    wiki_link = models.CharField(blank=True,  max_length=240)

     
     def has_description(self):
         return len(self.description) > 0
     has_description.short_description = _('description')
     has_description.boolean = True
 
     
     def has_description(self):
         return len(self.description) > 0
     has_description.short_description = _('description')
     has_description.boolean = True
 

+    def alive(self):
+        return self.death is None
+    
+    def in_pd(self):
+        """ tests whether an author is in public domain """
+        return self.death is not None and self.goes_to_pd() <= datetime.now().year
+    
+    def goes_to_pd(self):
+        """ calculates the year of public domain entry for an author """
+        return self.death + 71 if self.death is not None else None
+

     @permalink
     def get_absolute_url(self):
         return ('catalogue.views.tagged_object_list', [self.slug])
     @permalink
     def get_absolute_url(self):
         return ('catalogue.views.tagged_object_list', [self.slug])


@@ -83,6 +106,10 @@ class Book(models.Model):
     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)
     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)

+    extra_info = JSONField(_('extra information'))
+    gazeta_link = models.CharField(blank=True,  max_length=240)
+    wiki_link = models.CharField(blank=True,  max_length=240)
+

     
     # Formats
     xml_file = models.FileField(_('XML file'), upload_to=book_upload_path('xml'), blank=True)
     
     # Formats
     xml_file = models.FileField(_('XML file'), upload_to=book_upload_path('xml'), blank=True)


@@ -90,6 +117,8 @@ class Book(models.Model):
     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)
     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)

+    mp3_file = models.FileField(_('MP3 file'), upload_to=book_upload_path('mp3'), blank=True)
+    ogg_file = models.FileField(_('OGG file'), upload_to=book_upload_path('ogg'), blank=True)

     
     parent = models.ForeignKey('self', blank=True, null=True, related_name='children')
     
     
     parent = models.ForeignKey('self', blank=True, null=True, related_name='children')
     


@@ -97,26 +126,65 @@ class Book(models.Model):
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)
     
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)
     

+    @property
+    def name(self):
+        return self.title
+    

     def short_html(self):
     def short_html(self):

-        if len(self._short_html):
-            return mark_safe(self._short_html)
+        key = '_short_html_%s' % get_language()
+        short_html = getattr(self, key)
+        
+        if len(short_html):
+            return mark_safe(short_html)

         else:
         else:

-            tags = self.tags.filter(~Q(category__in=('set', 'theme')))
-            tags = [u'<a href="%s">%s</a>' % (tag.get_absolute_url(), tag.name) for tag in tags]
+            tags = self.tags.filter(~Q(category__in=('set', 'theme', 'book')))
+            tags = [mark_safe(u'<a href="%s">%s</a>' % (tag.get_absolute_url(), tag.name)) for tag in tags]

 
             formats = []
             if self.html_file:
 
             formats = []
             if self.html_file:

-                formats.append(u'<a href="%s">Czytaj online</a>' % reverse('book_text', kwargs={'slug': self.slug}))
+                formats.append(u'<a href="%s">%s</a>' % (reverse('book_text', kwargs={'slug': self.slug}), _('Read online')))

             if self.pdf_file:
             if self.pdf_file:

-                formats.append(u'<a href="%s">Plik PDF</a>' % self.pdf_file.url)
+                formats.append(u'<a href="%s">PDF</a>' % self.pdf_file.url)

             if self.odt_file:
             if self.odt_file:

-                formats.append(u'<a href="%s">Plik ODT</a>' % self.odt_file.url)
+                formats.append(u'<a href="%s">ODT</a>' % self.odt_file.url)
+            if self.txt_file:
+                formats.append(u'<a href="%s">TXT</a>' % self.txt_file.url)
+            if self.mp3_file:
+                formats.append(u'<a href="%s">MP3</a>' % self.mp3_file.url)
+            if self.ogg_file:
+                formats.append(u'<a href="%s">OGG</a>' % self.ogg_file.url)

             
             

-            self._short_html = unicode(render_to_string('catalogue/book_short.html',
-                {'book': self, 'tags': tags, 'formats': formats}))
-            self.save()
-            return mark_safe(self._short_html)
+            formats = [mark_safe(format) for format in formats]
+            
+            setattr(self, key, unicode(render_to_string('catalogue/book_short.html',
+                {'book': self, 'tags': tags, 'formats': formats})))
+            self.save(reset_short_html=False)
+            return mark_safe(getattr(self, key))

     
     

+    def save(self, force_insert=False, force_update=False, reset_short_html=True):
+        if reset_short_html:
+            # Reset _short_html during save
+            for key in filter(lambda x: x.startswith('_short_html'), self.__dict__):
+                self.__setattr__(key, '')
+        
+        book = super(Book, self).save(force_insert, force_update)
+        
+        if self.mp3_file:
+            print self.mp3_file, self.mp3_file.path
+            extra_info = self.get_extra_info_value()
+            extra_info.update(self.get_mp3_info())
+            self.set_extra_info_value(extra_info)
+            book = super(Book, self).save(force_insert, force_update)
+        
+        return book
+    
+    def get_mp3_info(self):
+        """Retrieves artist and director names from audio ID3 tags."""
+        audio = id3.ID3(self.mp3_file.path)
+        artist_name = ', '.join(', '.join(tag.text) for tag in audio.getall('TPE1'))
+        director_name = ', '.join(', '.join(tag.text) for tag in audio.getall('TPE3'))
+        return {'artist_name': artist_name, 'director_name': director_name}
+        

     def has_description(self):
         return len(self.description) > 0
     has_description.short_description = _('description')
     def has_description(self):
         return len(self.description) > 0
     has_description.short_description = _('description')


@@ -137,8 +205,11 @@ class Book(models.Model):
     has_html_file.short_description = 'HTML'
     has_html_file.boolean = True
 
     has_html_file.short_description = 'HTML'
     has_html_file.boolean = True
 

+    class AlreadyExists(Exception):
+        pass
+    

     @staticmethod
     @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
         from tempfile import NamedTemporaryFile
         from slughifi import slughifi
         from markupstring import MarkupString


@@ -146,7 +217,19 @@ class Book(models.Model):
         # Read book metadata
         book_info = dcparser.parse(xml_file)
         book_base, book_slug = book_info.url.rsplit('/', 1)
         # 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 created:
+            book_shelves = []
+        else:
+            if not overwrite:
+                raise Book.AlreadyExists(_('Book %s already exists') % book_slug)
+            # Save shelves for this book
+            book_shelves = list(book.tags.filter(category='set'))
+        
+        book.title = book_info.title
+        book.set_extra_info_value(book_info.to_dict())
+        book._short_html = ''

         book.save()
         
         book_tags = []
         book.save()
         
         book_tags = []


@@ -163,53 +246,77 @@ class Book(models.Model):
                 tag.category = category
                 tag.save()
             book_tags.append(tag)
                 tag.category = category
                 tag.save()
             book_tags.append(tag)

+            
+        book_tag, created = Tag.objects.get_or_create(slug=('l-' + book.slug)[:120])
+        if created:
+            book_tag.name = book.title[:50]
+            book_tag.sort_key = ('l-' + book.slug)[:120]
+            book_tag.category = 'book'
+            book_tag.save()
+        book_tags.append(book_tag)
+        

         book.tags = book_tags
         
         if hasattr(book_info, 'parts'):
         book.tags = book_tags
         
         if hasattr(book_info, 'parts'):

-            for part_url, n in enumerate(book_info.parts):
+            for n, part_url in enumerate(book_info.parts):

                 base, slug = part_url.rsplit('/', 1)
                 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()
+                try:
+                    child_book = Book.objects.get(slug=slug)
+                    child_book.parent = book
+                    child_book.parent_number = n
+                    child_book.save()
+                except Book.DoesNotExist, e:
+                    raise Book.DoesNotExist(_('Book with slug = "%s" does not exist.') % slug)

         
         

+        book_descendants = list(book.children.all())
+        while len(book_descendants) > 0:
+            child_book = book_descendants.pop(0)
+            for fragment in child_book.fragments.all():
+                fragment.tags = set(list(fragment.tags) + [book_tag])
+            book_descendants += list(child_book.children.all())
+            

         # Save XML and HTML files
         # Save XML and HTML files

-        book.xml_file.save('%s.xml' % book.slug, File(file(xml_file)), save=False)
+        if not isinstance(xml_file, File):
+            xml_file = File(file(xml_file))
+        book.xml_file.save('%s.xml' % book.slug, xml_file, save=False)

         
         html_file = NamedTemporaryFile()
         
         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)

             
             

-            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
+            # 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 = set(list(book.tags) + themes + [book_tag])
+                book_themes += themes
+            
+            book_themes = set(book_themes)
+            book.tags = list(book.tags) + list(book_themes) + book_shelves

         
         

-        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):
     
     @permalink
     def get_absolute_url(self):


@@ -236,22 +343,51 @@ class Fragment(models.Model):
     tags = managers.TagDescriptor(Tag)
     
     def short_html(self):
     tags = managers.TagDescriptor(Tag)
     
     def short_html(self):

-        if len(self._short_html):
-            return mark_safe(self._short_html)
+        key = '_short_html_%s' % get_language()
+        short_html = getattr(self, key)         
+        if len(short_html):
+            return mark_safe(short_html)

         else:
         else:

-            book_authors = [u'<a href="%s">%s</a>' % (tag.get_absolute_url(), tag.name) 
+            book_authors = [mark_safe(u'<a href="%s">%s</a>' % (tag.get_absolute_url(), tag.name)) 

                 for tag in self.book.tags if tag.category == 'author']
             
                 for tag in self.book.tags if tag.category == 'author']
             

-            self._short_html = unicode(render_to_string('catalogue/fragment_short.html',
-                {'fragment': self, 'book': self.book, 'book_authors': book_authors}))
+            setattr(self, key, unicode(render_to_string('catalogue/fragment_short.html',
+                {'fragment': self, 'book': self.book, 'book_authors': book_authors})))

             self.save()
             self.save()

-            return mark_safe(self._short_html)
+            return mark_safe(getattr(self, key))

     
     def get_absolute_url(self):
     
     def get_absolute_url(self):

-        return '%s#m%s' % (self.book.html_file.url, self.anchor)
+        return '%s#m%s' % (reverse('book_text', kwargs={'slug': self.book.slug}), self.anchor)

     
     class Meta:
         ordering = ('book', 'anchor',)
         verbose_name = _('fragment')
         verbose_name_plural = _('fragments')
 
     
     class Meta:
         ordering = ('book', 'anchor',)
         verbose_name = _('fragment')
         verbose_name_plural = _('fragments')
 

+
+class BookStub(models.Model):
+    title = models.CharField(_('title'), max_length=120)
+    author = models.CharField(_('author'), max_length=120)
+    pd = models.IntegerField(_('goes to public domain'), null=True, blank=True)
+    slug = models.SlugField(_('slug'), max_length=120, unique=True, db_index=True)
+    translator = models.TextField(_('translator'), blank=True)
+    translator_death = models.TextField(_('year of translator\'s death'), blank=True)
+
+    def in_pd(self):
+        return self.pd is not None and self.pd <= datetime.now().year
+
+    @property
+    def name(self):
+        return self.title
+    
+    @permalink
+    def get_absolute_url(self):
+        return ('catalogue.views.book_detail', [self.slug])
+
+    def __unicode__(self):
+        return self.title
+    
+    class Meta:
+        ordering = ('title',)
+        verbose_name = _('book stub')
+        verbose_name_plural = _('book stubs')
\ No newline at end of file