Update to new librarian api for html, txt.

[wolnelektury.git] / src / catalogue / models / book.py

diff --git a/src/catalogue/models/book.py b/src/catalogue/models/book.py
index 3eb6023..7d36662 100644 (file)
--- a/src/catalogue/models/book.py
+++ b/src/catalogue/models/book.py
@@ -1,5 +1,5 @@
-# This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
-# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+# This file is part of Wolne Lektury, licensed under GNU Affero GPLv3 or later.
+# Copyright © Fundacja Wolne Lektury. See NOTICE for more information.

 #
 from collections import OrderedDict
 import json
 #
 from collections import OrderedDict
 import json


@@ -19,7 +19,7 @@ from django.utils.translation import gettext_lazy as _, get_language
 from fnpdjango.storage import BofhFileSystemStorage
 from lxml import html
 from librarian.cover import WLCover
 from fnpdjango.storage import BofhFileSystemStorage
 from lxml import html
 from librarian.cover import WLCover

-from librarian.html import transform_abstrakt
+from librarian.builders.html import AbstraktHtmlBuilder

 from librarian.builders import builders
 from newtagging import managers
 from catalogue import constants
 from librarian.builders import builders
 from newtagging import managers
 from catalogue import constants


@@ -35,29 +35,29 @@ bofh_storage = BofhFileSystemStorage()
 
 class Book(models.Model):
     """Represents a book imported from WL-XML."""
 
 class Book(models.Model):
     """Represents a book imported from WL-XML."""

-    title = models.CharField(_('title'), max_length=32767)
-    sort_key = models.CharField(_('sort key'), max_length=120, db_index=True, editable=False)
+    title = models.CharField('tytuł', max_length=32767)
+    sort_key = models.CharField('klucz sortowania', max_length=120, db_index=True, editable=False)

     sort_key_author = models.CharField(
     sort_key_author = models.CharField(

-        _('sort key by author'), max_length=120, db_index=True, editable=False, default='')
-    slug = models.SlugField(_('slug'), max_length=120, db_index=True, unique=True)
-    common_slug = models.SlugField(_('slug'), max_length=120, db_index=True)
-    language = models.CharField(_('language code'), max_length=3, db_index=True, default=app_settings.DEFAULT_LANGUAGE)
-    description = models.TextField(_('description'), blank=True)
-    abstract = models.TextField(_('abstract'), blank=True)
-    toc = models.TextField(_('toc'), blank=True)
-    created_at = models.DateTimeField(_('creation date'), auto_now_add=True, db_index=True)
-    changed_at = models.DateTimeField(_('change date'), auto_now=True, db_index=True)
-    parent_number = models.IntegerField(_('parent number'), default=0)
-    extra_info = models.TextField(_('extra information'), default='{}')
+        'klucz sortowania wg autora', max_length=120, db_index=True, editable=False, default='')
+    slug = models.SlugField('slug', max_length=120, db_index=True, unique=True)
+    common_slug = models.SlugField('wspólny slug', max_length=120, db_index=True)
+    language = models.CharField('kod języka', max_length=3, db_index=True, default=app_settings.DEFAULT_LANGUAGE)
+    description = models.TextField('opis', blank=True)
+    abstract = models.TextField('abstrakt', blank=True)
+    toc = models.TextField('spis treści', blank=True)
+    created_at = models.DateTimeField('data utworzenia', auto_now_add=True, db_index=True)
+    changed_at = models.DateTimeField('data motyfikacji', auto_now=True, db_index=True)
+    parent_number = models.IntegerField('numer w ramach rodzica', default=0)
+    extra_info = models.TextField('dodatkowe informacje', default='{}')

     gazeta_link = models.CharField(blank=True, max_length=240)
     wiki_link = models.CharField(blank=True, max_length=240)
     gazeta_link = models.CharField(blank=True, max_length=240)
     wiki_link = models.CharField(blank=True, max_length=240)

-    print_on_demand = models.BooleanField(_('print on demand'), default=False)
-    recommended = models.BooleanField(_('recommended'), default=False)
-    audio_length = models.CharField(_('audio length'), blank=True, max_length=8)
-    preview = models.BooleanField(_('preview'), default=False)
-    preview_until = models.DateField(_('preview until'), blank=True, null=True)
+    print_on_demand = models.BooleanField('druk na żądanie', default=False)
+    recommended = models.BooleanField('polecane', default=False)
+    audio_length = models.CharField('długość audio', blank=True, max_length=8)
+    preview = models.BooleanField('prapremiera', default=False)
+    preview_until = models.DateField('prapremiera do', blank=True, null=True)

     preview_key = models.CharField(max_length=32, blank=True, null=True)
     preview_key = models.CharField(max_length=32, blank=True, null=True)

-    findable = models.BooleanField(_('findable'), default=True, db_index=True)
+    findable = models.BooleanField('wyszukiwalna', default=True, db_index=True)

 
     # files generated during publication
     xml_file = fields.XmlField(storage=bofh_storage, with_etag=False)
 
     # files generated during publication
     xml_file = fields.XmlField(storage=bofh_storage, with_etag=False)


@@ -68,15 +68,15 @@ class Book(models.Model):
     mobi_file = fields.MobiField(storage=bofh_storage)
     pdf_file = fields.PdfField(storage=bofh_storage)
 
     mobi_file = fields.MobiField(storage=bofh_storage)
     pdf_file = fields.PdfField(storage=bofh_storage)
 

-    cover = fields.CoverField(_('cover'), storage=bofh_storage)
+    cover = fields.CoverField('okładka', storage=bofh_storage)

     # Cleaner version of cover for thumbs
     # Cleaner version of cover for thumbs

-    cover_clean = fields.CoverCleanField(_('clean cover'))
-    cover_thumb = fields.CoverThumbField(_('cover thumbnail'))
+    cover_clean = fields.CoverCleanField('czysta okładka')
+    cover_thumb = fields.CoverThumbField('miniatura okładki')

     cover_api_thumb = fields.CoverApiThumbField(
     cover_api_thumb = fields.CoverApiThumbField(

-        _('cover thumbnail for mobile app'))
-    simple_cover = fields.SimpleCoverField(_('cover for mobile app'))
+        'mniaturka okładki dla aplikacji')
+    simple_cover = fields.SimpleCoverField('okładka dla aplikacji')

     cover_ebookpoint = fields.CoverEbookpointField(
     cover_ebookpoint = fields.CoverEbookpointField(

-        _('cover for Ebookpoint'))
+        'okładka dla Ebookpoint')

 
     ebook_formats = constants.EBOOK_FORMATS
     formats = ebook_formats + ['html', 'xml']
 
     ebook_formats = constants.EBOOK_FORMATS
     formats = ebook_formats + ['html', 'xml']


@@ -91,6 +91,7 @@ class Book(models.Model):
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)
     tag_relations = GenericRelation(Tag.intermediary_table_model)
     tagged = managers.ModelTaggedItemManager(Tag)
     tags = managers.TagDescriptor(Tag)
     tag_relations = GenericRelation(Tag.intermediary_table_model)

+    translators = models.ManyToManyField(Tag, blank=True)

 
     html_built = django.dispatch.Signal()
     published = django.dispatch.Signal()
 
     html_built = django.dispatch.Signal()
     published = django.dispatch.Signal()


@@ -104,8 +105,8 @@ class Book(models.Model):
 
     class Meta:
         ordering = ('sort_key_author', 'sort_key')
 
     class Meta:
         ordering = ('sort_key_author', 'sort_key')

-        verbose_name = _('book')
-        verbose_name_plural = _('books')
+        verbose_name = 'książka'
+        verbose_name_plural = 'książki'

         app_label = 'catalogue'
 
     def __str__(self):
         app_label = 'catalogue'
 
     def __str__(self):


@@ -154,12 +155,6 @@ class Book(models.Model):
     def genre_unicode(self):
         return self.tag_unicode('genre')
 
     def genre_unicode(self):
         return self.tag_unicode('genre')
 

-    def translators(self):
-        translators = self.get_extra_info_json().get('translators') or []
-        return [
-            '\xa0'.join(reversed(translator.split(', ', 1))) for translator in translators
-        ]
-

     def translator(self):
         translators = self.get_extra_info_json().get('translators')
         if not translators:
     def translator(self):
         translators = self.get_extra_info_json().get('translators')
         if not translators:


@@ -331,6 +326,12 @@ class Book(models.Model):
             total += app_settings.GET_MP3_LENGTH(media.file.path)
         return int(total)
 
             total += app_settings.GET_MP3_LENGTH(media.file.path)
         return int(total)
 

+    def get_time(self):
+        try:
+            return round(self.xml_file.size / 1000 * 40)
+        except ValueError:
+            return 0
+    

     def has_media(self, type_):
         if type_ in Book.formats:
             return bool(getattr(self, "%s_file" % type_))
     def has_media(self, type_):
         if type_ in Book.formats:
             return bool(getattr(self, "%s_file" % type_))


@@ -397,7 +398,7 @@ class Book(models.Model):
 
     def has_description(self):
         return len(self.description) > 0
 
     def has_description(self):
         return len(self.description) > 0

-    has_description.short_description = _('description')
+    has_description.short_description = 'opis'

     has_description.boolean = True
 
     def has_mp3_file(self):
     has_description.boolean = True
 
     def has_mp3_file(self):


@@ -416,7 +417,7 @@ class Book(models.Model):
     has_daisy_file.boolean = True
 
     def has_sync_file(self):
     has_daisy_file.boolean = True
 
     def has_sync_file(self):

-        return self.has_media("sync")
+        return settings.FEATURE_SYNCHRO and self.has_media("sync")

 
     def get_sync(self):
         with self.get_media('sync').first().file.open('r') as f:
 
     def get_sync(self):
         with self.get_media('sync').first().file.open('r') as f:


@@ -556,11 +557,8 @@ class Book(models.Model):
                 urlretrieve('%s/%s' % (remote_gallery_url, ilustr_src), ilustr_path)
 
     def load_abstract(self):
                 urlretrieve('%s/%s' % (remote_gallery_url, ilustr_src), ilustr_path)
 
     def load_abstract(self):

-        abstract = self.wldocument(parse_dublincore=False).edoc.getroot().find('.//abstrakt')
-        if abstract is not None:
-            self.abstract = transform_abstrakt(abstract)
-        else:
-            self.abstract = ''
+        self.abstract = AbstraktHtmlBuilder().build(
+            self.wldocument2()).get_bytes().decode('utf-8')

 
     def load_toc(self):
         self.toc = ''
 
     def load_toc(self):
         self.toc = ''


@@ -594,7 +592,7 @@ class Book(models.Model):
 
     @classmethod
     def from_text_and_meta(cls, raw_file, book_info, overwrite=False, dont_build=None, search_index=True,
 
     @classmethod
     def from_text_and_meta(cls, raw_file, book_info, overwrite=False, dont_build=None, search_index=True,

-                           remote_gallery_url=None, days=0, findable=True):
+                           remote_gallery_url=None, days=0, findable=True, logo=None, logo_mono=None, logo_alt=None):

         from catalogue import tasks
 
         if dont_build is None:
         from catalogue import tasks
 
         if dont_build is None:


@@ -608,7 +606,7 @@ class Book(models.Model):
                 try:
                     children.append(Book.objects.get(slug=part_url.slug))
                 except Book.DoesNotExist:
                 try:
                     children.append(Book.objects.get(slug=part_url.slug))
                 except Book.DoesNotExist:

-                    raise Book.DoesNotExist(_('Book "%s" does not exist.') % part_url.slug)
+                    raise Book.DoesNotExist('Książka "%s" nie istnieje.' % part_url.slug)

 
         # Read book metadata
         book_slug = book_info.url.slug
 
         # Read book metadata
         book_slug = book_info.url.slug


@@ -624,7 +622,7 @@ class Book(models.Model):
                 book.preview_until = date.today() + timedelta(days)
         else:
             if not overwrite:
                 book.preview_until = date.today() + timedelta(days)
         else:
             if not overwrite:

-                raise Book.AlreadyExists(_('Book %s already exists') % book_slug)
+                raise Book.AlreadyExists('Książka %s już istnieje' % book_slug)

             # Save shelves for this book
             book_shelves = list(book.tags.filter(category='set'))
             old_cover = book.cover_info()
             # Save shelves for this book
             book_shelves = list(book.tags.filter(category='set'))
             old_cover = book.cover_info()


@@ -641,21 +639,26 @@ class Book(models.Model):
             book.common_slug = book_info.variant_of.slug
         else:
             book.common_slug = book.slug
             book.common_slug = book_info.variant_of.slug
         else:
             book.common_slug = book.slug

-        book.extra_info = json.dumps(book_info.to_dict())
+        extra = book_info.to_dict()
+        if logo:
+            extra['logo'] = logo
+        if logo_mono:
+            extra['logo_mono'] = logo_mono
+        if logo_alt:
+            extra['logo_alt'] = logo_alt
+        book.extra_info = json.dumps(extra)

         book.load_abstract()
         book.load_toc()
         book.save()
 
         meta_tags = Tag.tags_from_info(book_info)
 
         book.load_abstract()
         book.load_toc()
         book.save()
 
         meta_tags = Tag.tags_from_info(book_info)
 

-        for tag in meta_tags:
-            if not tag.for_books:
-                tag.for_books = True
-                tag.save()
-
-        book.tags = set(meta_tags + book_shelves)
+        just_tags = [t for (t, rel) in meta_tags if not rel]
+        book.tags = set(just_tags + book_shelves)

         book.save()  # update sort_key_author
 
         book.save()  # update sort_key_author
 

+        book.translators.set([t for (t, rel) in meta_tags if rel == 'translator'])
+

         cover_changed = old_cover != book.cover_info()
         obsolete_children = set(b for b in book.children.all()
                                 if b not in children)
         cover_changed = old_cover != book.cover_info()
         obsolete_children = set(b for b in book.children.all()
                                 if b not in children)


@@ -714,13 +717,14 @@ class Book(models.Model):
         cls.published.send(sender=cls, instance=book)
         return book
 
         cls.published.send(sender=cls, instance=book)
         return book
 

+    # TODO TEST

     def update_references(self):
         Entity = apps.get_model('references', 'Entity')
         doc = self.wldocument2()
     def update_references(self):
         Entity = apps.get_model('references', 'Entity')
         doc = self.wldocument2()

-        doc._compat_assign_section_ids()
-        doc._compat_assign_ordered_ids()
+        doc.assign_ids()
+

         refs = {}
         refs = {}

-        for ref_elem in doc.references():
+        for i, ref_elem in enumerate(doc.references()):

             uri = ref_elem.attrib.get('href', '')
             if not uri:
                 continue
             uri = ref_elem.attrib.get('href', '')
             if not uri:
                 continue


@@ -729,16 +733,18 @@ class Book(models.Model):
             else:
                 entity, entity_created = Entity.objects.get_or_create(uri=uri)
                 if entity_created:
             else:
                 entity, entity_created = Entity.objects.get_or_create(uri=uri)
                 if entity_created:

-                    entity.populate()
-                    entity.save()
+                    try:
+                        entity.populate()
+                    except:
+                        pass
+                    else:
+                        entity.save()

                 ref, ref_created = entity.reference_set.get_or_create(book=self)
                 refs[uri] = ref
                 if not ref_created:
                     ref.occurence_set.all().delete()
                 ref, ref_created = entity.reference_set.get_or_create(book=self)
                 refs[uri] = ref
                 if not ref_created:
                     ref.occurence_set.all().delete()

-            sec = ref_elem.get_link()
-            m = re.match(r'sec(\d+)', sec)
-            assert m is not None
-            sec = int(m.group(1))
+            anchor = ref_elem.get_link()
+

             snippet = ref_elem.get_snippet()
             b = builders['html-snippet']()
             for s in snippet:
             snippet = ref_elem.get_snippet()
             b = builders['html-snippet']()
             for s in snippet:


@@ -746,7 +752,8 @@ class Book(models.Model):
             html = b.output().get_bytes().decode('utf-8')
 
             ref.occurence_set.create(
             html = b.output().get_bytes().decode('utf-8')
 
             ref.occurence_set.create(

-                section=sec,
+                section=i,
+                anchor=anchor,

                 html=html
             )
         self.reference_set.exclude(entity__uri__in=refs).delete()
                 html=html
             )
         self.reference_set.exclude(entity__uri__in=refs).delete()


@@ -939,7 +946,7 @@ class Book(models.Model):
     def stage_note(self):
         stage = self.get_extra_info_json().get('stage')
         if stage and stage < '0.4':
     def stage_note(self):
         stage = self.get_extra_info_json().get('stage')
         if stage and stage < '0.4':

-            return (_('This work needs modernisation'),
+            return (_('Ten utwór wymaga uwspółcześnienia'),

                     reverse('infopage', args=['wymagajace-uwspolczesnienia']))
         else:
             return None, None
                     reverse('infopage', args=['wymagajace-uwspolczesnienia']))
         else:
             return None, None