Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2026-04-29 17:23:04 +02:00
Code Issues Projects Releases Wiki Activity

Editing of metadata in DRMed MOBI. Catalog tweaks.

Browse source
This commit is contained in:
Kovid Goyal 2010-02-18 10:30:41 -07:00
commit cff2089581
5 changed files with 91 additions and 53 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
src/calibre/customize/__init__.py
View file

@ -248,6 +248,7 @@ class CatalogPlugin(Plugin):
#: dest = 'catalog_title',
#: help = (_('Title of generated catalog. \nDefault:') + " '" +
#: '%default' + "'"))]
#: cli_options parsed in library.cli:catalog_option_parser()
cli_options = []
@ -274,9 +275,10 @@ def search_sort_db(self, db, opts):
def get_output_fields(self, opts):
# Return a list of requested fields, with opts.sort_by first
all_fields = set(
['author_sort','authors','comments','cover','formats', 'id','isbn','pubdate','publisher','rating',
'series_index','series','size','tags','timestamp',
'title','uuid'])
['author_sort','authors','comments','cover','formats',
'id','isbn','pubdate','publisher','rating',
'series_index','series','size','tags','timestamp',
'title','uuid'])
fields = all_fields
if opts.fields != 'all':

40
src/calibre/ebooks/metadata/mobi.py
View file

@ -12,6 +12,7 @@
from struct import pack, unpack
from cStringIO import StringIO
from calibre import prints
from calibre.ebooks.mobi import MobiError
from calibre.ebooks.mobi.writer import rescale_image, MAX_THUMB_DIMEN
from calibre.ebooks.mobi.langcodes import iana2mobi
@ -85,6 +86,8 @@ def truncate(self, value):
self._stream.truncate(value)
class MetadataUpdater(object):
DRM_KEY_SIZE = 48
def __init__(self, stream):
self.stream = stream
data = self.data = StreamSlicer(stream)
@ -105,6 +108,13 @@ def __init__(self, stream):
self.timestamp = None
self.pdbrecords = self.get_pdbrecords()
self.drm_block = None
if self.encryption_type != 0:
if self.have_exth:
self.drm_block = self.fetchDRMdata()
else:
raise MobiError('Unable to set metadata on DRM file without EXTH header')
self.original_exth_records = {}
if not have_exth:
self.create_exth()
@ -112,6 +122,16 @@ def __init__(self, stream):
# Fetch timestamp, cover_record, thumbnail_record
self.fetchEXTHFields()
def fetchDRMdata(self):
''' Fetch the DRM keys '''
drm_offset = int(unpack('>I', self.record0[0xa8:0xac])[0])
self.drm_key_count = int(unpack('>I', self.record0[0xac:0xb0])[0])
drm_keys = ''
for x in range(self.drm_key_count):
base_addr = drm_offset + (x * self.DRM_KEY_SIZE)
drm_keys += self.record0[base_addr:base_addr + self.DRM_KEY_SIZE]
return drm_keys
def fetchEXTHFields(self):
stream = self.stream
record0 = self.record0
@ -186,7 +206,6 @@ def patchSection(self, section, new):
def create_exth(self, new_title=None, exth=None):
# Add an EXTH block to record 0, rewrite the stream
# self.hexdump(self.record0)
if isinstance(new_title, unicode):
new_title = new_title.encode(self.codec, 'replace')
@ -212,8 +231,14 @@ def create_exth(self, new_title=None, exth=None):
exth = ['EXTH', pack('>II', 12, 0), pad]
exth = ''.join(exth)
# Update title_offset, title_len if new_title
self.record0[0x54:0x58] = pack('>L', 0x10 + mobi_header_length + len(exth))
# Update drm_offset(0xa8), title_offset(0x54)
if self.encryption_type != 0:
self.record0[0xa8:0xac] = pack('>L', 0x10 + mobi_header_length + len(exth))
self.record0[0xb0:0xb4] = pack('>L', len(self.drm_block))
self.record0[0x54:0x58] = pack('>L', 0x10 + mobi_header_length + len(exth) + len(self.drm_block))
else:
self.record0[0x54:0x58] = pack('>L', 0x10 + mobi_header_length + len(exth))
if new_title:
self.record0[0x58:0x5c] = pack('>L', len(new_title))
@ -221,6 +246,8 @@ def create_exth(self, new_title=None, exth=None):
new_record0 = StringIO()
new_record0.write(self.record0[:0x10 + mobi_header_length])
new_record0.write(exth)
if self.encryption_type != 0:
new_record0.write(self.drm_block)
new_record0.write(new_title if new_title else title_in_file)
# Pad to a 4-byte boundary
@ -228,8 +255,6 @@ def create_exth(self, new_title=None, exth=None):
pad = '\0' * (4 - trail) # Always pad w/ at least 1 byte
new_record0.write(pad)
#self.hexdump(new_record0.getvalue())
# Rebuild the stream, update the pdbrecords pointers
self.patchSection(0,new_record0.getvalue())
@ -339,10 +364,7 @@ def pop_exth_record(exth_id):
recs.append((202, pack('>I', self.thumbnail_rindex)))
pop_exth_record(202)
if getattr(self, 'encryption_type', -1) != 0:
raise MobiError('Setting metadata in DRMed MOBI files is not supported.')
# Restore any original EXTH fields that weren't modified/updated
# Restore any original EXTH fields that weren't updated
for id in sorted(self.original_exth_records):
recs.append((id, self.original_exth_records[id]))
recs = sorted(recs, key=lambda x:(x[0],x[0]))

77
src/calibre/library/catalog.py
View file

@ -11,7 +11,7 @@
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Tag, NavigableString
from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.utils.logging import Log
from calibre.utils.date import isoformat
from calibre.utils.date import isoformat, now as nowf
FIELDS = ['all', 'author_sort', 'authors', 'comments',
'cover', 'formats', 'id', 'isbn', 'pubdate', 'publisher', 'rating',
@ -21,7 +21,7 @@
class CSV_XML(CatalogPlugin):
'CSV/XML catalog generator'
Option = namedtuple('Option', 'option, default, dest, help')
Option = namedtuple('Option', 'option, default, dest, action, help')
name = 'Catalog_CSV_XML'
description = 'CSV/XML catalog generator'
@ -34,6 +34,7 @@ class CSV_XML(CatalogPlugin):
Option('--fields',
default = 'all',
dest = 'fields',
action = None,
help = _('The fields to output when cataloging books in the '
'database. Should be a comma-separated list of fields.\n'
'Available fields: %s.\n'
@ -43,6 +44,7 @@ class CSV_XML(CatalogPlugin):
Option('--sort-by',
default = 'id',
dest = 'sort_by',
action = None,
help = _('Output field to sort on.\n'
'Available fields: author_sort, id, rating, size, timestamp, title.\n'
"Default: '%default'\n"
@ -241,7 +243,7 @@ def run(self, path_to_output, opts, db, notification=DummyReporter()):
class EPUB_MOBI(CatalogPlugin):
'ePub catalog generator'
Option = namedtuple('Option', 'option, default, dest, help')
Option = namedtuple('Option', 'option, default, dest, action, help')
name = 'Catalog_EPUB_MOBI'
description = 'EPUB/MOBI catalog generator'
@ -254,12 +256,14 @@ class EPUB_MOBI(CatalogPlugin):
cli_options = [Option('--catalog-title',
default = 'My Books',
dest = 'catalog_title',
action = None,
help = _('Title of generated catalog used as title in metadata.\n'
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--debug-pipeline',
default=None,
dest='debug_pipeline',
action = None,
help=_("Save the output from different stages of the conversion "
"pipeline to the specified "
"directory. Useful if you are unsure at which stage "
@ -269,48 +273,56 @@ class EPUB_MOBI(CatalogPlugin):
Option('--exclude-genre',
default='\[[\w ]*\]',
dest='exclude_genre',
action = None,
help=_("Regex describing tags to exclude as genres.\n" "Default: '%default' excludes bracketed tags, e.g. '[<tag>]'\n"
"Applies to: ePub, MOBI output formats")),
Option('--exclude-tags',
default=('~,'+_('Catalog')),
dest='exclude_tags',
action = None,
help=_("Comma-separated list of tag words indicating book should be excluded from output. Case-insensitive.\n"
"--exclude-tags=skip will match 'skip this book' and 'Skip will like this'.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--generate-titles',
default=True,
default=False,
dest='generate_titles',
action = 'store_true',
help=_("Include 'Titles' section in catalog.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--generate-recently-added',
default=True,
default=False,
dest='generate_recently_added',
action = 'store_true',
help=_("Include 'Recently Added' section in catalog.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--note-tag',
default='*',
dest='note_tag',
action = None,
help=_("Tag prefix for user notes, e.g. '*Jeff might enjoy reading this'.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--numbers-as-text',
default=False,
dest='numbers_as_text',
action = None,
help=_("Sort titles with leading numbers as text, e.g.,\n'2001: A Space Odyssey' sorts as \n'Two Thousand One: A Space Odyssey'.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--output-profile',
default=None,
dest='output_profile',
action = None,
help=_("Specifies the output profile. In some cases, an output profile is required to optimize the catalog for the device. For example, 'kindle' or 'kindle_dx' creates a structured Table of Contents with Sections and Articles.\n"
"Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
Option('--read-tag',
default='+',
dest='read_tag',
action = None,
help=_("Tag indicating book has been read.\n" "Default: '%default'\n"
"Applies to: ePub, MOBI output formats")),
]
@ -1749,9 +1761,8 @@ def add_books_to_HTML_by_date_range(date_range_list, date_range, dtc):
book['title_sort'] = self.generateSortTitle(book['title'])
self.booksByDateRange = sorted(nspt, key=lambda x:(x['timestamp'], x['timestamp']),reverse=True)
today = datetime.datetime.now()
date_range_list = []
today_time = datetime.datetime(today.year, today.month, today.day)
today_time = nowf().replace(hour=23, minute=59, second=59)
books_added_in_date_range = False
for (i, date) in enumerate(self.DATE_RANGE):
date_range_limit = self.DATE_RANGE[i]
@ -1759,14 +1770,16 @@ def add_books_to_HTML_by_date_range(date_range_list, date_range, dtc):
date_range = '%d to %d days ago' % (self.DATE_RANGE[i-1], self.DATE_RANGE[i])
else:
date_range = 'Last %d days' % (self.DATE_RANGE[i])
for book in self.booksByDateRange:
book_time = datetime.datetime(book['timestamp'].year, book['timestamp'].month, book['timestamp'].day)
if (today_time-book_time).days <= date_range_limit:
#print "generateHTMLByDateAdded: %s added %d days ago" % (book['title'], (today_time-book_time).days)
book_time = book['timestamp']
delta = today_time-book_time
if delta.days <= date_range_limit:
date_range_list.append(book)
books_added_in_date_range = True
else:
break
dtc = add_books_to_HTML_by_date_range(date_range_list, date_range, dtc)
date_range_list = [book]
@ -3412,13 +3425,12 @@ def logerror(self):
def run(self, path_to_output, opts, db, notification=DummyReporter()):
opts.log = log = Log()
opts.fmt = self.fmt = path_to_output.rpartition('.')[2]
self.opts = opts
# Add local options
opts.creator = "calibre"
# Finalize output_profile
op = self.opts.output_profile
op = opts.output_profile
if op is None:
op = 'default'
if opts.connected_device['name'] and 'kindle' in opts.connected_device['name'].lower():
@ -3428,13 +3440,30 @@ def run(self, path_to_output, opts, db, notification=DummyReporter()):
op = "kindle"
opts.descriptionClip = 380 if op.endswith('dx') or 'kindle' not in op else 100
opts.authorClip = 100 if op.endswith('dx') or 'kindle' not in op else 60
self.opts.output_profile = op
opts.output_profile = op
opts.basename = "Catalog"
opts.cli_environment = not hasattr(opts,'sync')
# GwR *** hardwired to sort by author, could be an option if passed in opts
opts.sort_descriptions_by_author = True
# If exclude_genre is blank, assume user wants all genre tags included
if opts.exclude_genre.strip() == '':
opts.exclude_genre = '\[^.\]'
log(" converting empty exclude_genre to '\[^.\]'")
if opts.connected_device['name']:
if opts.connected_device['serial']:
log(" connected_device: '%s' #%s%s " % \
(opts.connected_device['name'],
opts.connected_device['serial'][0:4],
'x' * (len(opts.connected_device['serial']) - 4)))
else:
log(" connected_device: '%s'" % opts.connected_device['name'])
for storage in opts.connected_device['storage']:
if storage:
log(" mount point: %s" % storage)
if opts.verbose:
opts_dict = vars(opts)
log(u"%s(): Generating %s %sin %s environment" %
@ -3452,26 +3481,6 @@ def run(self, path_to_output, opts, db, notification=DummyReporter()):
sections_list.append('Genres')
log(u"Creating Sections for %s" % ', '.join(sections_list))
# If exclude_genre is blank, assume user wants all genre tags included
if opts.exclude_genre.strip() == '':
opts.exclude_genre = '\[^.\]'
log(" converting empty exclude_genre to '\[^.\]'")
if opts.connected_device['name']:
if opts.connected_device['serial']:
log(" connected_device: '%s' #%s%s " % \
(opts.connected_device['name'],
opts.connected_device['serial'][0:4],
'x' * (len(opts.connected_device['serial']) - 4)))
else:
log(" connected_device: '%s'" % opts.connected_device['name'])
for storage in opts.connected_device['storage']:
if storage:
log(" mount point: %s" % storage)
# for book in opts.connected_device['books']:
# log("%s: %s" % (book.title, book.path))
# Display opts
keys = opts_dict.keys()
keys.sort()
@ -3482,6 +3491,8 @@ def run(self, path_to_output, opts, db, notification=DummyReporter()):
'search_text','sort_by','sort_descriptions_by_author','sync']:
log(" %s: %s" % (key, opts_dict[key]))
self.opts = opts
# Launch the Catalog builder
catalog = self.CatalogBuilder(db, opts, self, report_progress=notification)
if opts.verbose:

18
src/calibre/library/cli.py
View file

@ -587,9 +587,6 @@ def command_export(args, dbpath):
do_export(get_db(dbpath, opts), ids, dir, opts)
return 0
# GR additions
def catalog_option_parser(args):
from calibre.customize.ui import available_catalog_formats, plugin_for_catalog_format
from calibre.utils.logging import Log
@ -599,10 +596,17 @@ def add_plugin_parser_options(fmt, parser, log):
# Fetch the extension-specific CLI options from the plugin
plugin = plugin_for_catalog_format(fmt)
for option in plugin.cli_options:
parser.add_option(option.option,
default=option.default,
dest=option.dest,
help=option.help)
if option.action:
parser.add_option(option.option,
default=option.default,
dest=option.dest,
action=option.action,
help=option.help)
else:
parser.add_option(option.option,
default=option.default,
dest=option.dest,
help=option.help)
return plugin

1
src/calibre/library/database2.py
View file

@ -1467,7 +1467,6 @@ def add_catalog(self, path, title):
db_id, existing = None, False
if matches:
db_id = list(matches)[0]
existing = True
if db_id is None:
obj = self.conn.execute('INSERT INTO books(title, author_sort) VALUES (?, ?)',
(title, 'calibre'))