migration to remove empty html files, librarian upgrade

diff --git a/apps/catalogue/migrations/0007_remove_empty_html.py b/apps/catalogue/migrations/0007_remove_empty_html.py
new file mode 100644 (file)
index 0000000..ec882b9
--- /dev/null
+++ b/apps/catalogue/migrations/0007_remove_empty_html.py
@@ -0,0 +1,146 @@
+# encoding: utf-8
+import datetime
+from south.db import db
+from south.v2 import DataMigration
+from django.db import models
+
+class Migration(DataMigration):
+    
+    def forwards(self, orm):
+        """ Look for HTML files without any real content and delete them """
+        from lxml import etree
+        from librarian import html_has_content
+        
+        for book in orm.Book.objects.exclude(html_file=''):
+            if not html_has_content(etree.parse(book.html_file)):
+                book.html_file.delete()
+                # must do it by hand, we don't see real Book.save
+                for key in filter(lambda x: x.startswith('_short_html'), book.__dict__):
+                    book.__setattr__(key, '')
+                book.save()
+    
+    def backwards(self, orm):
+        """ Do nothing. We don't want empty HTML files anyway. """
+        pass
+    
+    models = {
+        'auth.group': {
+            'Meta': {'object_name': 'Group'},
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'name': ('django.db.models.fields.CharField', [], {'unique': 'True', 'max_length': '80'}),
+            'permissions': ('django.db.models.fields.related.ManyToManyField', [], {'to': "orm['auth.Permission']", 'blank': 'True'})
+        },
+        'auth.permission': {
+            'Meta': {'unique_together': "(('content_type', 'codename'),)", 'object_name': 'Permission'},
+            'codename': ('django.db.models.fields.CharField', [], {'max_length': '100'}),
+            'content_type': ('django.db.models.fields.related.ForeignKey', [], {'to': "orm['contenttypes.ContentType']"}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'name': ('django.db.models.fields.CharField', [], {'max_length': '50'})
+        },
+        'auth.user': {
+            'Meta': {'object_name': 'User'},
+            'date_joined': ('django.db.models.fields.DateTimeField', [], {'default': 'datetime.datetime.now'}),
+            'email': ('django.db.models.fields.EmailField', [], {'max_length': '75', 'blank': 'True'}),
+            'first_name': ('django.db.models.fields.CharField', [], {'max_length': '30', 'blank': 'True'}),
+            'groups': ('django.db.models.fields.related.ManyToManyField', [], {'to': "orm['auth.Group']", 'blank': 'True'}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'is_active': ('django.db.models.fields.BooleanField', [], {'default': 'True', 'blank': 'True'}),
+            'is_staff': ('django.db.models.fields.BooleanField', [], {'default': 'False', 'blank': 'True'}),
+            'is_superuser': ('django.db.models.fields.BooleanField', [], {'default': 'False', 'blank': 'True'}),
+            'last_login': ('django.db.models.fields.DateTimeField', [], {'default': 'datetime.datetime.now'}),
+            'last_name': ('django.db.models.fields.CharField', [], {'max_length': '30', 'blank': 'True'}),
+            'password': ('django.db.models.fields.CharField', [], {'max_length': '128'}),
+            'user_permissions': ('django.db.models.fields.related.ManyToManyField', [], {'to': "orm['auth.Permission']", 'blank': 'True'}),
+            'username': ('django.db.models.fields.CharField', [], {'unique': 'True', 'max_length': '30'})
+        },
+        'catalogue.book': {
+            'Meta': {'object_name': 'Book'},
+            '_short_html': ('django.db.models.fields.TextField', [], {}),
+            '_short_html_de': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_en': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_es': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_fr': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_lt': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_pl': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_ru': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_uk': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_tag_counter': ('catalogue.fields.JSONField', [], {'default': "''"}),
+            '_theme_counter': ('catalogue.fields.JSONField', [], {'default': "''"}),
+            'created_at': ('django.db.models.fields.DateTimeField', [], {'auto_now': 'True', 'blank': 'True'}),
+            'description': ('django.db.models.fields.TextField', [], {'blank': 'True'}),
+            'epub_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'extra_info': ('catalogue.fields.JSONField', [], {}),
+            'gazeta_link': ('django.db.models.fields.CharField', [], {'max_length': '240', 'blank': 'True'}),
+            'html_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'mp3_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'odt_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'ogg_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'parent': ('django.db.models.fields.related.ForeignKey', [], {'blank': 'True', 'related_name': "'children'", 'null': 'True', 'to': "orm['catalogue.Book']"}),
+            'parent_number': ('django.db.models.fields.IntegerField', [], {'default': '0'}),
+            'pdf_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'slug': ('django.db.models.fields.SlugField', [], {'unique': 'True', 'max_length': '120', 'db_index': 'True'}),
+            'title': ('django.db.models.fields.CharField', [], {'max_length': '120'}),
+            'txt_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'}),
+            'wiki_link': ('django.db.models.fields.CharField', [], {'max_length': '240', 'blank': 'True'}),
+            'xml_file': ('django.db.models.fields.files.FileField', [], {'max_length': '100', 'blank': 'True'})
+        },
+        'catalogue.bookstub': {
+            'Meta': {'object_name': 'BookStub'},
+            'author': ('django.db.models.fields.CharField', [], {'max_length': '120'}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'pd': ('django.db.models.fields.IntegerField', [], {'null': 'True', 'blank': 'True'}),
+            'slug': ('django.db.models.fields.SlugField', [], {'unique': 'True', 'max_length': '120', 'db_index': 'True'}),
+            'title': ('django.db.models.fields.CharField', [], {'max_length': '120'}),
+            'translator': ('django.db.models.fields.TextField', [], {'blank': 'True'}),
+            'translator_death': ('django.db.models.fields.TextField', [], {'blank': 'True'})
+        },
+        'catalogue.fragment': {
+            'Meta': {'object_name': 'Fragment'},
+            '_short_html': ('django.db.models.fields.TextField', [], {}),
+            '_short_html_de': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_en': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_es': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_fr': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_lt': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_pl': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_ru': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            '_short_html_uk': ('django.db.models.fields.TextField', [], {'null': True, 'blank': True}),
+            'anchor': ('django.db.models.fields.CharField', [], {'max_length': '120'}),
+            'book': ('django.db.models.fields.related.ForeignKey', [], {'related_name': "'fragments'", 'to': "orm['catalogue.Book']"}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'short_text': ('django.db.models.fields.TextField', [], {}),
+            'text': ('django.db.models.fields.TextField', [], {})
+        },
+        'catalogue.tag': {
+            'Meta': {'object_name': 'Tag'},
+            'book_count': ('django.db.models.fields.IntegerField', [], {'default': '0'}),
+            'category': ('django.db.models.fields.CharField', [], {'max_length': '50', 'db_index': 'True'}),
+            'death': ('django.db.models.fields.IntegerField', [], {'null': 'True', 'blank': 'True'}),
+            'description': ('django.db.models.fields.TextField', [], {'blank': 'True'}),
+            'gazeta_link': ('django.db.models.fields.CharField', [], {'max_length': '240', 'blank': 'True'}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'main_page': ('django.db.models.fields.BooleanField', [], {'default': 'False', 'db_index': 'True', 'blank': 'True'}),
+            'name': ('django.db.models.fields.CharField', [], {'max_length': '50', 'db_index': 'True'}),
+            'slug': ('django.db.models.fields.SlugField', [], {'unique': 'True', 'max_length': '120', 'db_index': 'True'}),
+            'sort_key': ('django.db.models.fields.SlugField', [], {'max_length': '120', 'db_index': 'True'}),
+            'user': ('django.db.models.fields.related.ForeignKey', [], {'to': "orm['auth.User']", 'null': 'True', 'blank': 'True'}),
+            'wiki_link': ('django.db.models.fields.CharField', [], {'max_length': '240', 'blank': 'True'})
+        },
+        'catalogue.tagrelation': {
+            'Meta': {'unique_together': "(('tag', 'content_type', 'object_id'),)", 'object_name': 'TagRelation', 'db_table': "'catalogue_tag_relation'"},
+            'content_type': ('django.db.models.fields.related.ForeignKey', [], {'to': "orm['contenttypes.ContentType']"}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'object_id': ('django.db.models.fields.PositiveIntegerField', [], {'db_index': 'True'}),
+            'tag': ('django.db.models.fields.related.ForeignKey', [], {'related_name': "'items'", 'to': "orm['catalogue.Tag']"})
+        },
+        'contenttypes.contenttype': {
+            'Meta': {'unique_together': "(('app_label', 'model'),)", 'object_name': 'ContentType', 'db_table': "'django_content_type'"},
+            'app_label': ('django.db.models.fields.CharField', [], {'max_length': '100'}),
+            'id': ('django.db.models.fields.AutoField', [], {'primary_key': 'True'}),
+            'model': ('django.db.models.fields.CharField', [], {'max_length': '100'}),
+            'name': ('django.db.models.fields.CharField', [], {'max_length': '100'})
+        }
+    }
+    
+    complete_apps = ['catalogue']

diff --git a/requirements.txt b/requirements.txt
index afecb8f..a577d71 100644 (file)
--- a/requirements.txt
+++ b/requirements.txt
@@ -17,6 +17,6 @@ sorl-thumbnail>=3.2
 
 # home-brewed & dependencies
 lxml>=2.2.2
-git+git://github.com/fnp/librarian.git
+-e git+git://github.com/fnp/librarian.git@d43d87400dcc19851442#egg=librarian
 
 # MySQL-python>=1.2,<2.0