find

oml/__main__.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import os
 import sys

oml/app.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 from flask import Flask
 from flask.ext.script import Manager

oml/changelog.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import json
 from datetime import datetime

oml/commands.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 from flask.ext.script import Command
 
@@ -10,7 +11,10 @@ class Setup(Command):
         """
         def run(self):
             import setup
+            import settings
             setup.create_default_lists()
+            settings.db.session.connection().execute("PRAGMA journal_mode=WAL")
+            settings.db.session.commit()
 
 class UpdateStatic(Command):
         """
@@ -28,8 +32,8 @@ class UpdateStatic(Command):
             oxjs = os.path.join(settings.static_path, 'oxjs')
             if not os.path.exists(oxjs):
                 r('git', 'clone', 'https://git.0x2620.org/oxjs.git', oxjs)
-            r('python', os.path.join(oxjs, 'tools', 'build', 'build.py'))
-            r('python', os.path.join(settings.static_path, 'py', 'build.py'))
+            r('python2', os.path.join(oxjs, 'tools', 'build', 'build.py'))
+            r('python2', os.path.join(settings.static_path, 'py', 'build.py'))
 
 class Release(Command):
         """

oml/directory.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 # DHT placeholder
 

oml/ed25519_utils.py

@@ -1,3 +1,7 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
+
 import ed25519
 ENCODING='base64'
 

oml/item/add.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import base64
 import models

oml/item/api.py

@@ -1,5 +1,7 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
+
 from datetime import datetime
 
 from flask import json

oml/item/covers.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import sqlite3
 import Image

oml/item/migrate.py

@@ -1,3 +1,7 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
+
 import models
 from copy import deepcopy
 

oml/item/models.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import os
 import re
@@ -198,6 +199,8 @@ class Item(db.Model):
                         if value:
                             value = unicode(value)
                             value = ox.sort_string(value).lower()
+                elif isinstance(value, list): #empty list
+                    value = ''
                 setattr(self, 'sort_%s' % key['id'], value)
 
     def update_find(self):
@@ -295,11 +298,14 @@ class Item(db.Model):
 
     def update_cover(self):
         cover = None
-        if 'cover' in self.meta:
+        if 'cover' in self.meta and self.meta['cover']:
             cover = ox.cache.read_url(self.meta['cover'])
             #covers[self.id] = requests.get(self.meta['cover']).content
             if cover:
                 covers[self.id] = cover
+        else:
+            if covers[self.id]:
+                del covers[self.id]
         path = self.get_path()
         if not cover and path:
             cover = self.extract_cover()

oml/item/person.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import unicodedata
 

oml/item/query.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import settings
 import models

oml/item/views.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import os
 from datetime import datetime
@@ -77,7 +78,7 @@ def cover(id, size=None):
     if not 'coverRatio' in item.meta:
         #img = Image.open(StringIO(str(covers[id])))
         img = Image.open(StringIO(data))
-        item.meta['coverRatio'] = float(img.size[0])/img.size[1]
+        item.meta['coverRatio'] = img.size[0]/img.size[1]
         db.session.add(item)
         db.session.commit()
     resp = make_response(data)

oml/localnodes.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
 
 import socket
 import thread

oml/meta/__init__.py

@@ -7,6 +7,7 @@ import loc
 import lookupbyisbn
 import openlibrary
 import worldcat
+import google
 
 providers = [
     ('openlibrary', 'olid'),
@@ -17,9 +18,12 @@ providers = [
 ]
 
 def find(title, author=None, publisher=None, date=None):
+    results = google.find(title=title, author=author, publisher=publisher, date=date)
+    '''
     results = openlibrary.find(title=title, author=author, publisher=publisher, date=date)
     for r in results:
         r['mainid'] = 'olid'
+    '''
     return results
 
 def lookup(key, value):

oml/meta/google.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=4:sts=4:ts=4
+from __future__ import division
+
+import ox.web.google
+import stdnum.isbn
+
+from .utils import find_isbns
+
+
+def find(title, author=None, publisher=None, date=None):
+    print 'google.find', title, author, publisher, date
+    query = title
+    if author:
+        if isinstance(author, list):
+            author = ' '.join(author)
+        query += ' ' + author
+    query += ' isbn'
+    isbns = []
+    for r in ox.web.google.find(query):
+        isbns += find_isbns(' '.join(r))
+
+    results = []
+    done = set()
+    for isbn in isbns:
+        if isbn not in done:
+            key = 'isbn%d'%len(isbn)
+            #r = lookup(key, isbn)
+            #r['mainid'] = key
+            r = {
+                key: isbn,
+                'mainid': key
+            }
+            results.append(r)
+            done.add(isbn)
+            if len(isbn) == 10:
+                done.add(stdnum.isbn.to_isbn13(isbn))
+    return results

oml/meta/loc.py

@@ -33,7 +33,10 @@ def lookup(id):
     info = {
         'lccn': id
     }
-    info['title'] = ''.join([e.text for e in mods.findall(ns + 'titleInfo')[0]])
+    title = mods.findall(ns + 'titleInfo')
+    if not title:
+        return {}
+    info['title'] = ''.join([e.text for e in title[0]])
     origin = mods.findall(ns + 'originInfo')
     if origin:
         info['place'] = []

oml/meta/lookupbyisbn.py

@@ -14,6 +14,8 @@ def get_ids(key, value):
         if m:
             asin = m[0].split('/')[-3]
             ids.append(('asin', asin))
+    if key == 'isbn10':
+        ids.append(('isbn13', stdnum.isbn.to_isbn13(value)))
     if key == 'asin':
         if stdnum.isbn.is_valid(value):
             ids.append(('isbn10', value))
@@ -47,14 +49,16 @@ def lookup(id):
             r[key] = int(r[key])
     desc = find_re(data, '<h2>Description:<\/h2>(.*?)<div ')
     desc = desc.replace('<br /><br />', ' ').replace('<br /> ', ' ').replace('<br />', ' ')
-    r['description'] = desc
-    if r['description'] == u'Description of this item is not available at this time.':
-        r['description'] = ''
+    r['description'] = decode_html(strip_tags(desc))
     r['cover'] = find_re(data, '<img src="(.*?)" alt="Book cover').replace('._SL160_', '')
     for key in r:
         if isinstance(r[key], basestring):
             r[key] = decode_html(strip_tags(r[key])).strip()
-    if 'author' in r and isinstance(r['author'], basestring):
+    if 'author' in r and isinstance(r['author'], basestring) and r['author']:
         r['author'] = [r['author']]
+    else:
+        r['author'] = []
+    if r['description'].lower() == u'Description of this item is not available at this time.'.lower():
+        r['description'] = ''
     return r
 

oml/meta/utils.py

@@ -1,5 +1,16 @@
-
+import re
+import stdnum.isbn
 
 def normalize_isbn(value):
     return ''.join([s for s in value if s.isdigit() or s == 'X'])
 
+def find_isbns(text):
+    matches = re.compile('\d[\d\-X\ ]+').findall(text)
+    matches = [normalize_isbn(value) for value in matches]
+    return [isbn for isbn in matches if stdnum.isbn.is_valid(isbn)
+        and len(isbn) in (10, 13)
+        and isbn not in (
+        '0' * 10,
+        '0' * 13,
+    )]
+

oml/utils.py

@@ -8,7 +8,7 @@ import stdnum.isbn
 
 import ox
 
-from meta.utils import normalize_isbn
+from meta.utils import normalize_isbn, find_isbns
 
 def valid_olid(id):
     return id.startswith('OL') and id.endswith('M')
@@ -76,16 +76,6 @@ def sort_title(title):
     title = re.sub(u'[\'!¿¡,\.;\-"\:\*\[\]]', '', title)
     return title.strip()
 
-def find_isbns(text):
-    matches = re.compile('\d[\d\-X\ ]+').findall(text)
-    matches = [normalize_isbn(value) for value in matches]
-    return [isbn for isbn in matches if stdnum.isbn.is_valid(isbn)
-        and len(isbn) in (10, 13)
-        and isbn not in (
-        '0' * 10,
-        '0' * 13,
-    )]
-
 def get_position_by_id(list, key):
     for i in range(0, len(list)):
         if list[i]['id'] == key: