Added extraction of wiki_url from DublinCore.

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

diff --git a/apps/catalogue/models.py b/apps/catalogue/models.py
index f31dbe6..81965ce 100644 (file)
--- a/apps/catalogue/models.py
+++ b/apps/catalogue/models.py
@@ -10,6 +10,7 @@ from django.core.urlresolvers import reverse
 
 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
 


@@ -41,8 +42,9 @@ 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)

     
     def has_description(self):
         return len(self.description) > 0
     
     def has_description(self):
         return len(self.description) > 0


@@ -83,6 +85,7 @@ 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'))

     
     # 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)


@@ -96,6 +99,11 @@ class Book(models.Model):
     objects = models.Manager()
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)
     objects = models.Manager()
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)

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

     
     def short_html(self):
         if len(self._short_html):
     
     def short_html(self):
         if len(self._short_html):


@@ -111,6 +119,8 @@ class Book(models.Model):
                 formats.append(u'<a href="%s">Plik PDF</a>' % self.pdf_file.url)
             if self.odt_file:
                 formats.append(u'<a href="%s">Plik ODT</a>' % self.odt_file.url)
                 formats.append(u'<a href="%s">Plik PDF</a>' % self.pdf_file.url)
             if self.odt_file:
                 formats.append(u'<a href="%s">Plik ODT</a>' % self.odt_file.url)

+            if self.txt_file:
+                formats.append(u'<a href="%s">Plik TXT</a>' % self.txt_file.url)

             
             self._short_html = unicode(render_to_string('catalogue/book_short.html',
                 {'book': self, 'tags': tags, 'formats': formats}))
             
             self._short_html = unicode(render_to_string('catalogue/book_short.html',
                 {'book': self, 'tags': tags, 'formats': formats}))


@@ -137,8 +147,11 @@ 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 +159,19 @@ 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.extra_info = book_info.to_dict()
+        book._short_html = ''

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


@@ -166,7 +191,7 @@ class Book(models.Model):
         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)
                 child_book = Book.objects.get(slug=slug)
                 child_book.parent = book
                 base, slug = part_url.rsplit('/', 1)
                 child_book = Book.objects.get(slug=slug)
                 child_book.parent = book


@@ -177,39 +202,42 @@ class Book(models.Model):
         book.xml_file.save('%s.xml' % book.slug, File(file(xml_file)), save=False)
         
         html_file = NamedTemporaryFile()
         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_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):


@@ -248,7 +276,7 @@ class Fragment(models.Model):
             return mark_safe(self._short_html)
     
     def get_absolute_url(self):
             return mark_safe(self._short_html)
     
     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',)
     
     class Meta:
         ordering = ('book', 'anchor',)