get_data_as_dict()

src/calibre/db/__init__.py

@@ -54,6 +54,70 @@ def _get_series_values(val):
             pass
     return (val, None)
 
+def get_data_as_dict(self, prefix=None, authors_as_string=False, ids=None):
+    '''
+    Return all metadata stored in the database as a dict. Includes paths to
+    the cover and each format.
+
+    :param prefix: The prefix for all paths. By default, the prefix is the absolute path
+    to the library folder.
+    :param ids: Set of ids to return the data for. If None return data for
+    all entries in database.
+    '''
+    import os
+    from calibre.ebooks.metadata import authors_to_string
+    backend = getattr(self, 'backend', self)  # Works with both old and legacy interfaces
+    if prefix is None:
+        prefix = backend.library_path
+    fdata = backend.custom_column_num_map
+
+    FIELDS = set(['title', 'sort', 'authors', 'author_sort', 'publisher',
+        'rating', 'timestamp', 'size', 'tags', 'comments', 'series',
+        'series_index', 'uuid', 'pubdate', 'last_modified', 'identifiers',
+        'languages']).union(set(fdata))
+    for x, data in fdata.iteritems():
+        if data['datatype'] == 'series':
+            FIELDS.add('%d_index'%x)
+    data = []
+    for record in self.data:
+        if record is None:
+            continue
+        db_id = record[self.FIELD_MAP['id']]
+        if ids is not None and db_id not in ids:
+            continue
+        x = {}
+        for field in FIELDS:
+            x[field] = record[self.FIELD_MAP[field]]
+        data.append(x)
+        x['id'] = db_id
+        x['formats'] = []
+        isbn = self.isbn(db_id, index_is_id=True)
+        x['isbn'] = isbn if isbn else ''
+        if not x['authors']:
+            x['authors'] = _('Unknown')
+        x['authors'] = [i.replace('|', ',') for i in x['authors'].split(',')]
+        if authors_as_string:
+            x['authors'] = authors_to_string(x['authors'])
+        x['tags'] = [i.replace('|', ',').strip() for i in x['tags'].split(',')] if x['tags'] else []
+        path = os.path.join(prefix, self.path(record[self.FIELD_MAP['id']], index_is_id=True))
+        x['cover'] = os.path.join(path, 'cover.jpg')
+        if not record[self.FIELD_MAP['cover']]:
+            x['cover'] = None
+        formats = self.formats(record[self.FIELD_MAP['id']], index_is_id=True)
+        if formats:
+            for fmt in formats.split(','):
+                path = self.format_abspath(x['id'], fmt, index_is_id=True)
+                if path is None:
+                    continue
+                if prefix != self.library_path:
+                    path = os.path.relpath(path, self.library_path)
+                    path = os.path.join(prefix, path)
+                x['formats'].append(path)
+                x['fmt_'+fmt.lower()] = path
+            x['available_formats'] = [i.upper() for i in formats.split(',')]
+
+    return data
+
 '''
 Rewrite of the calibre database backend.
 

src/calibre/db/legacy.py

@@ -11,7 +11,7 @@ from future_builtins import zip
 
 from calibre import force_unicode, isbytestring
 from calibre.constants import preferred_encoding
-from calibre.db import _get_next_series_num_for_list, _get_series_values
+from calibre.db import _get_next_series_num_for_list, _get_series_values, get_data_as_dict
 from calibre.db.adding import (
     find_books_in_directory, import_book_directory_multiple,
     import_book_directory, recursive_import, add_catalog, add_news)
@@ -35,7 +35,6 @@ def cleanup_tags(tags):
             ans.append(tag)
     return ans
 
-
 class LibraryDatabase(object):
 
     ''' Emulate the old LibraryDatabase2 interface '''
@@ -746,6 +745,7 @@ LibraryDatabase.isbn = MT(
     lambda self, index, index_is_id=False: self.get_identifiers(index, index_is_id=index_is_id).get('isbn', None))
 LibraryDatabase.get_books_for_category = MT(
     lambda self, category, id_:self.new_api.get_books_for_category(category, id_))
+LibraryDatabase.get_data_as_dict = MT(get_data_as_dict)
 # }}}
 
 # Legacy setter API {{{
@@ -890,3 +890,4 @@ del MT
 
 
 
+

src/calibre/db/tests/legacy.py

@@ -246,6 +246,12 @@ class LegacyTest(BaseTest):
         db.copy_format_to(1, 'FMT1', d1, True)
         ndb.copy_format_to(1, 'FMT1', d2, True)
         self.assertTrue(d1.getvalue() == d2.getvalue())
+        old = db.get_data_as_dict(prefix='test-prefix')
+        new = ndb.get_data_as_dict(prefix='test-prefix')
+        for o, n in zip(old, new):
+            o = {type('')(k) if isinstance(k, bytes) else k:set(v) if isinstance(v, list) else v for k, v in o.iteritems()}
+            n = {k:set(v) if isinstance(v, list) else v for k, v in n.iteritems()}
+            self.assertEqual(o, n)
         db.close()
         # }}}
 

src/calibre/library/database2.py

@@ -7,14 +7,14 @@ __docformat__ = 'restructuredtext en'
 The database used to store ebook metadata
 '''
 import os, sys, shutil, cStringIO, glob, time, functools, traceback, re, \
-        json, uuid, hashlib, copy
+        json, uuid, hashlib, copy, types
 from collections import defaultdict
 import threading, random
 from itertools import repeat
 
 from calibre import prints, force_unicode
 from calibre.ebooks.metadata import (title_sort, author_to_author_sort,
-        string_to_authors, authors_to_string, get_title_sort_pat)
+        string_to_authors, get_title_sort_pat)
 from calibre.ebooks.metadata.opf2 import metadata_to_opf
 from calibre.library.database import LibraryDatabase
 from calibre.library.field_metadata import FieldMetadata, TagsIcons
@@ -41,7 +41,7 @@ from calibre.ebooks import check_ebook_format
 from calibre.utils.magick.draw import save_cover_data_to
 from calibre.utils.recycle_bin import delete_file, delete_tree
 from calibre.utils.formatter_functions import load_user_template_functions
-from calibre.db import _get_next_series_num_for_list, _get_series_values
+from calibre.db import _get_next_series_num_for_list, _get_series_values, get_data_as_dict
 from calibre.db.adding import find_books_in_directory, import_book_directory_multiple, import_book_directory, recursive_import
 from calibre.db.errors import NoSuchFormat
 from calibre.db.lazy import FormatMetadata, FormatsList
@@ -135,6 +135,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             read_only=False, is_second_db=False, progress_callback=None,
             restore_all_prefs=False):
         self.is_second_db = is_second_db
+        self.get_data_as_dict = types.MethodType(get_data_as_dict, self, LibraryDatabase2)
         try:
             if isbytestring(library_path):
                 library_path = library_path.decode(filesystem_encoding)
@@ -3619,67 +3620,6 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         for i in iter(self):
             yield i[x]
 
-    def get_data_as_dict(self, prefix=None, authors_as_string=False, ids=None):
-        '''
-        Return all metadata stored in the database as a dict. Includes paths to
-        the cover and each format.
-
-        :param prefix: The prefix for all paths. By default, the prefix is the absolute path
-        to the library folder.
-        :param ids: Set of ids to return the data for. If None return data for
-        all entries in database.
-        '''
-        if prefix is None:
-            prefix = self.library_path
-        fdata = self.custom_column_num_map
-
-        FIELDS = set(['title', 'sort', 'authors', 'author_sort', 'publisher',
-            'rating', 'timestamp', 'size', 'tags', 'comments', 'series',
-            'series_index', 'uuid', 'pubdate', 'last_modified', 'identifiers',
-            'languages']).union(set(fdata))
-        for x, data in fdata.iteritems():
-            if data['datatype'] == 'series':
-                FIELDS.add('%d_index'%x)
-        data = []
-        for record in self.data:
-            if record is None:
-                continue
-            db_id = record[self.FIELD_MAP['id']]
-            if ids is not None and db_id not in ids:
-                continue
-            x = {}
-            for field in FIELDS:
-                x[field] = record[self.FIELD_MAP[field]]
-            data.append(x)
-            x['id'] = db_id
-            x['formats'] = []
-            isbn = self.isbn(db_id, index_is_id=True)
-            x['isbn'] = isbn if isbn else ''
-            if not x['authors']:
-                x['authors'] = _('Unknown')
-            x['authors'] = [i.replace('|', ',') for i in x['authors'].split(',')]
-            if authors_as_string:
-                x['authors'] = authors_to_string(x['authors'])
-            x['tags'] = [i.replace('|', ',').strip() for i in x['tags'].split(',')] if x['tags'] else []
-            path = os.path.join(prefix, self.path(record[self.FIELD_MAP['id']], index_is_id=True))
-            x['cover'] = os.path.join(path, 'cover.jpg')
-            if not record[self.FIELD_MAP['cover']]:
-                x['cover'] = None
-            formats = self.formats(record[self.FIELD_MAP['id']], index_is_id=True)
-            if formats:
-                for fmt in formats.split(','):
-                    path = self.format_abspath(x['id'], fmt, index_is_id=True)
-                    if path is None:
-                        continue
-                    if prefix != self.library_path:
-                        path = os.path.relpath(path, self.library_path)
-                        path = os.path.join(prefix, path)
-                    x['formats'].append(path)
-                    x['fmt_'+fmt.lower()] = path
-                x['available_formats'] = [i.upper() for i in formats.split(',')]
-
-        return data
-
     def migrate_old(self, db, progress):
         from PyQt4.QtCore import QCoreApplication
         header = _(u'<p>Migrating old database to ebook library in %s<br><center>')%self.library_path