mirror of
https://github.com/janeczku/calibre-web
synced 2024-11-16 06:12:58 +00:00
backup metadata first step
This commit is contained in:
Ozzieisaacs
parent
110d283a50
commit
ca0ee5d391
22
cps/db.py
22
cps/db.py
@ -322,6 +322,15 @@ class Data(Base):
|
||||
return u"<Data('{0},{1}{2}{3}')>".format(self.book, self.format, self.uncompressed_size, self.name)
|
||||
|
||||
|
||||
class Metadata_Dirtied(Base):
|
||||
__tablename__ = 'metadata_dirtied'
|
||||
id = Column(Integer, primary_key=True, autoincrement=True)
|
||||
book = Column(Integer, ForeignKey('books.id'), nullable=False, unique=True)
|
||||
|
||||
def __init__(self, book):
|
||||
self.book = book
|
||||
|
||||
|
||||
class Books(Base):
|
||||
__tablename__ = 'books'
|
||||
|
||||
@ -390,6 +399,9 @@ class CustomColumns(Base):
|
||||
display_dict = json.loads(self.display)
|
||||
return display_dict
|
||||
|
||||
def to_json(self):
|
||||
pass
|
||||
|
||||
|
||||
class AlchemyEncoder(json.JSONEncoder):
|
||||
|
||||
@ -642,6 +654,16 @@ class CalibreDB:
|
||||
|
||||
def get_book_format(self, book_id, file_format):
|
||||
return self.session.query(Data).filter(Data.book == book_id).filter(Data.format == file_format).first()
|
||||
def set_metadata_dirty(self, book_id):
|
||||
if not self.session.query(Metadata_Dirtied).filter(Metadata_Dirtied.book==book_id).one_or_none():
|
||||
self.session.add(Metadata_Dirtied(book_id))
|
||||
def delete_dirty_metadata(self, book_id):
|
||||
try:
|
||||
self.session.query(Metadata_Dirtied).filter(Metadata_Dirtied.book==book_id).delete()
|
||||
self.session.commit()
|
||||
except (OperationalError) as e:
|
||||
self.session.rollback()
|
||||
log.error("Database error: {}".format(e))
|
||||
|
||||
# Language and content filters for displaying in the UI
|
||||
def common_filters(self, allow_show_archived=False, return_all_languages=False):
|
||||
|
||||
@ -203,6 +203,7 @@ def edit_book(book_id):
|
||||
if modify_date:
|
||||
book.last_modified = datetime.utcnow()
|
||||
kobo_sync_status.remove_synced_book(edited_books_id, all=True)
|
||||
calibre_db.set_metadata_dirty(book.id)
|
||||
|
||||
calibre_db.session.merge(book)
|
||||
calibre_db.session.commit()
|
||||
@ -277,6 +278,8 @@ def upload():
|
||||
|
||||
move_coverfile(meta, db_book)
|
||||
|
||||
if modify_date:
|
||||
calibre_db.set_metadata_dirty(book_id)
|
||||
# save data to database, reread data
|
||||
calibre_db.session.commit()
|
||||
|
||||
@ -555,6 +558,7 @@ def table_xchange_author_title():
|
||||
renamed_author=renamed)
|
||||
if modify_date:
|
||||
book.last_modified = datetime.utcnow()
|
||||
calibre_db.set_metadata_dirty(book.id)
|
||||
try:
|
||||
calibre_db.session.commit()
|
||||
except (OperationalError, IntegrityError, StaleDataError) as e:
|
||||
|
||||
@ -578,6 +578,7 @@ def deleteDatabaseEntry(ID):
|
||||
|
||||
|
||||
# Gets cover file from gdrive
|
||||
# ToDo: Check is this right everyone get read permissions on cover files?
|
||||
def get_cover_via_gdrive(cover_path):
|
||||
df = getFileFromEbooksFolder(cover_path, 'cover.jpg')
|
||||
if df:
|
||||
@ -600,6 +601,29 @@ def get_cover_via_gdrive(cover_path):
|
||||
else:
|
||||
return None
|
||||
|
||||
# Gets cover file from gdrive
|
||||
def get_metadata_backup_via_gdrive(metadata_path):
|
||||
df = getFileFromEbooksFolder(metadata_path, 'metadata.opf')
|
||||
if df:
|
||||
if not session.query(PermissionAdded).filter(PermissionAdded.gdrive_id == df['id']).first():
|
||||
df.GetPermissions()
|
||||
df.InsertPermission({
|
||||
'type': 'anyone',
|
||||
'value': 'anyone',
|
||||
'role': 'writer', # ToDo needs write access
|
||||
'withLink': True})
|
||||
permissionAdded = PermissionAdded()
|
||||
permissionAdded.gdrive_id = df['id']
|
||||
session.add(permissionAdded)
|
||||
try:
|
||||
session.commit()
|
||||
except OperationalError as ex:
|
||||
log.error_or_exception('Database error: {}'.format(ex))
|
||||
session.rollback()
|
||||
return df.metadata.get('webContentLink')
|
||||
else:
|
||||
return None
|
||||
|
||||
# Creates chunks for downloading big files
|
||||
def partial(total_byte_len, part_size_limit):
|
||||
s = []
|
||||
|
||||
@ -19,7 +19,6 @@
|
||||
|
||||
import os
|
||||
import io
|
||||
import sys
|
||||
import mimetypes
|
||||
import re
|
||||
import shutil
|
||||
@ -685,7 +684,8 @@ def update_dir_structure(book_id,
|
||||
|
||||
def delete_book(book, calibrepath, book_format):
|
||||
if not book_format:
|
||||
clear_cover_thumbnail_cache(book.id) ## here it breaks
|
||||
clear_cover_thumbnail_cache(book.id) ## here it breaks
|
||||
calibre_db.delete_dirty_metadata(book.id)
|
||||
if config.config_use_google_drive:
|
||||
return delete_book_gdrive(book, book_format)
|
||||
else:
|
||||
|
||||
@ -23,7 +23,7 @@ from .services.background_scheduler import BackgroundScheduler, use_APScheduler
|
||||
from .tasks.database import TaskReconnectDatabase
|
||||
from .tasks.thumbnail import TaskGenerateCoverThumbnails, TaskGenerateSeriesThumbnails, TaskClearCoverThumbnailCache
|
||||
from .services.worker import WorkerThread
|
||||
|
||||
from .tasks.metadata_backup import TaskBackupMetadata
|
||||
|
||||
def get_scheduled_tasks(reconnect=True):
|
||||
tasks = list()
|
||||
@ -32,6 +32,10 @@ def get_scheduled_tasks(reconnect=True):
|
||||
if reconnect:
|
||||
tasks.append([lambda: TaskReconnectDatabase(), 'reconnect', False])
|
||||
|
||||
# ToDo make configurable. Generate metadata.opf file for each changed book
|
||||
if True:
|
||||
tasks.append([lambda: TaskBackupMetadata(), 'backup metadata', False])
|
||||
|
||||
# Generate all missing book cover thumbnails
|
||||
if config.schedule_generate_book_covers:
|
||||
tasks.append([lambda: TaskClearCoverThumbnailCache(0), 'delete superfluous book covers', True])
|
||||
@ -91,6 +95,7 @@ def should_task_be_running(start, duration):
|
||||
end_time = start_time + datetime.timedelta(hours=duration // 60, minutes=duration % 60)
|
||||
return start_time < now < end_time
|
||||
|
||||
|
||||
def calclulate_end_time(start, duration):
|
||||
start_time = datetime.datetime.now().replace(hour=start, minute=0)
|
||||
return start_time + datetime.timedelta(hours=duration // 60, minutes=duration % 60)
|
||||
|
||||
174
cps/tasks/metadata_backup.py
Normal file
174
cps/tasks/metadata_backup.py
Normal file
@ -0,0 +1,174 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# This file is part of the Calibre-Web (https://github.com/janeczku/calibre-web)
|
||||
# Copyright (C) 2020 monkey
|
||||
#
|
||||
# This program is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# This program is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
import datetime
|
||||
import os
|
||||
import json
|
||||
from urllib.request import urlopen
|
||||
from lxml import etree
|
||||
from html import escape
|
||||
|
||||
from cps import config, db, fs, gdriveutils, logger, ub
|
||||
from cps.services.worker import CalibreTask, STAT_CANCELLED, STAT_ENDED
|
||||
from flask_babel import lazy_gettext as N_
|
||||
|
||||
OPF_NAMESPACE = "http://www.idpf.org/2007/opf"
|
||||
PURL_NAMESPACE = "http://purl.org/dc/elements/1.1/"
|
||||
|
||||
OPF = "{%s}" % OPF_NAMESPACE
|
||||
PURL = "{%s}" % PURL_NAMESPACE
|
||||
|
||||
etree.register_namespace("opf", OPF_NAMESPACE)
|
||||
etree.register_namespace("dc", PURL_NAMESPACE)
|
||||
|
||||
OPF_NS = {None: OPF_NAMESPACE} # the default namespace (no prefix)
|
||||
NSMAP = {'dc': PURL_NAMESPACE, 'opf': OPF_NAMESPACE}
|
||||
|
||||
|
||||
class TaskBackupMetadata(CalibreTask):
|
||||
|
||||
def __init__(self, task_message=N_('Backing up Metadata')):
|
||||
super(TaskBackupMetadata, self).__init__(task_message)
|
||||
self.log = logger.create()
|
||||
self.db_session = db.CalibreDB(expire_on_commit=False, init=True).session
|
||||
|
||||
def run(self, worker_thread):
|
||||
try:
|
||||
metadata_backup = self.db_session.query(db.Metadata_Dirtied).all()
|
||||
custom_columns = self.db_session.query(db.CustomColumns).all()
|
||||
for backup in metadata_backup:
|
||||
book = self.db_session.query(db.Books).filter(db.Books.id == backup.book).one_or_none()
|
||||
# self.db_session.query(db.Metadata_Dirtied).filter(db.Metadata_Dirtied == backup.id).delete()
|
||||
# self.db_session.commit()
|
||||
if book:
|
||||
metadata_file = self.open_metadata(book, custom_columns)
|
||||
self._handleSuccess()
|
||||
self.db_session.remove()
|
||||
else:
|
||||
self.log.error("Book {} not found in database".format(backup.book))
|
||||
self._handleError("Book {} not found in database".format(backup.book))
|
||||
self.db_session.remove()
|
||||
|
||||
except Exception as ex:
|
||||
self.log.debug('Error creating metadata backup: ' + str(ex))
|
||||
self._handleError('Error creating metadata backup: ' + str(ex))
|
||||
self.db_session.rollback()
|
||||
self.db_session.remove()
|
||||
|
||||
def open_metadata(self, book, custom_columns):
|
||||
if config.config_use_google_drive:
|
||||
if not gdriveutils.is_gdrive_ready():
|
||||
raise Exception('Google Drive is configured but not ready')
|
||||
|
||||
web_content_link = gdriveutils.get_metadata_backup_via_gdrive(book.path)
|
||||
if not web_content_link:
|
||||
raise Exception('Google Drive cover url not found')
|
||||
|
||||
stream = None
|
||||
try:
|
||||
stream = urlopen(web_content_link)
|
||||
except Exception as ex:
|
||||
# Bubble exception to calling function
|
||||
self.log.debug('Error reading metadata.opf: ' + str(ex)) # ToDo Chek whats going on
|
||||
raise ex
|
||||
finally:
|
||||
if stream is not None:
|
||||
stream.close()
|
||||
else:
|
||||
book_metadata_filepath = os.path.join(config.config_calibre_dir, book.path, 'metadata.opf')
|
||||
if not os.path.isfile(book_metadata_filepath):
|
||||
self.create_new_metadata_backup(book, custom_columns, book_metadata_filepath)
|
||||
# ToDo What to do
|
||||
return open(book_metadata_filepath, "w")
|
||||
else:
|
||||
etree.parse(book_metadata_filepath)
|
||||
# backup not found has to be created
|
||||
#raise Exception('Book cover file not found')
|
||||
|
||||
def create_new_metadata_backup(self, book, custom_columns, book_metadata_filepath):
|
||||
# generate root package element
|
||||
package = etree.Element(OPF + "package", nsmap=OPF_NS)
|
||||
package.set("unique-identifier", "uuid_id")
|
||||
package.set("version", "2.0")
|
||||
|
||||
# generate metadata element and all subelements of it
|
||||
metadata = etree.SubElement(package, "metadata", nsmap=NSMAP)
|
||||
identifier = etree.SubElement(metadata, PURL + "identifier", id="calibre_id", nsmap=NSMAP)
|
||||
identifier.set(OPF + "scheme", "calibre")
|
||||
identifier.text = str(book.id)
|
||||
identifier2 = etree.SubElement(metadata, PURL + "identifier", id="uuid_id", nsmap=NSMAP)
|
||||
identifier2.set(OPF + "scheme", "uuid")
|
||||
identifier2.text = book.uuid
|
||||
title = etree.SubElement(metadata, PURL + "title", nsmap=NSMAP)
|
||||
title.text = book.title
|
||||
for author in book.authors:
|
||||
creator = etree.SubElement(metadata, PURL + "creator", nsmap=NSMAP)
|
||||
creator.text = str(author)
|
||||
creator.set(OPF + "file-as", book.author_sort) # ToDo Check
|
||||
creator.set(OPF + "role", "aut")
|
||||
contributor = etree.SubElement(metadata, PURL + "contributor", nsmap=NSMAP)
|
||||
contributor.text = "calibre (5.7.2) [https://calibre-ebook.com]"
|
||||
contributor.set(OPF + "file-as", "calibre") # ToDo Check
|
||||
contributor.set(OPF + "role", "bpk")
|
||||
date = etree.SubElement(metadata, PURL + "date", nsmap=NSMAP)
|
||||
date.text = datetime.datetime.strftime(book.pubdate, "%Y-%m-%dT%H:%M:%S+00:00")
|
||||
language = etree.SubElement(metadata, PURL + "language", nsmap=NSMAP)
|
||||
if book.languages:
|
||||
language.text = str(book.languages)
|
||||
else:
|
||||
language.text = "" # ToDo: insert locale (2 letter code)
|
||||
if book.tags:
|
||||
subject = etree.SubElement(metadata, PURL + "subject", nsmap=NSMAP)
|
||||
subject.text = str(book.tags)
|
||||
etree.SubElement(metadata, "meta", name="calibre:author_link_map",
|
||||
content="{" + escape(",".join(['"' + str(a) + '":""' for a in book.authors])) + "}",
|
||||
nsmap=NSMAP)
|
||||
etree.SubElement(metadata, "meta", name="calibre:series",
|
||||
content=str(book.series),
|
||||
nsmap=NSMAP)
|
||||
etree.SubElement(metadata, "meta", name="calibre:series_index",
|
||||
content=str(book.series_index),
|
||||
nsmap=NSMAP)
|
||||
etree.SubElement(metadata, "meta", name="calibre:timestamp",
|
||||
content=datetime.datetime.strftime(book.timestamp, "%Y-%m-%dT%H:%M:%S+00:00"),
|
||||
nsmap=NSMAP)
|
||||
etree.SubElement(metadata, "meta", name="calibre:title_sort",
|
||||
content=book.sort,
|
||||
nsmap=NSMAP)
|
||||
for cc in custom_columns:
|
||||
etree.SubElement(metadata, "meta", name="calibre:user_metadata:#{}".format(cc.label),
|
||||
content=escape(cc.get_display_dict()),
|
||||
nsmap=NSMAP)
|
||||
|
||||
pass
|
||||
|
||||
# generate guide element and all sub elements of it
|
||||
guide = etree.SubElement(package, "guide")
|
||||
etree.SubElement(guide, "reference", type="cover", title="Titelbild", href="cover.jpg")
|
||||
|
||||
# prepare finalize everything and output
|
||||
doc = etree.ElementTree(package)
|
||||
with open(book_metadata_filepath, 'wb') as f:
|
||||
doc.write(f, xml_declaration=True, encoding='utf-8', pretty_print=True)
|
||||
|
||||
@property
|
||||
def name(self):
|
||||
return "Backing up Metadata"
|
||||
|
||||
@property
|
||||
def is_cancellable(self):
|
||||
return True
|
||||
Loading…
Reference in New Issue
Block a user