Merge remote-tracking branch 'gitignore/bookmeta-patch-20170302'

# Conflicts:
#	cps/epub.py
This commit is contained in:
OzzieIsaacs 2017-03-03 19:48:02 +01:00
commit 8c7ba2ccdf
6 changed files with 62 additions and 13 deletions

View File

@ -63,7 +63,9 @@ def default_meta(tmp_file_path, original_file_name, original_file_extension):
description="", description="",
tags="", tags="",
series="", series="",
series_id="") series_id="",
comments="",
languages="")
def pdf_meta(tmp_file_path, original_file_name, original_file_extension): def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
@ -91,7 +93,9 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
description=subject, description=subject,
tags="", tags="",
series="", series="",
series_id="") series_id="",
comments="",
languages="")
def pdf_preview(tmp_file_path, tmp_dir): def pdf_preview(tmp_file_path, tmp_dir):

View File

@ -247,7 +247,7 @@ class Books(Base):
identifiers = relationship('Identifiers', backref='books') identifiers = relationship('Identifiers', backref='books')
def __init__(self, title, sort, author_sort, timestamp, pubdate, series_index, last_modified, path, has_cover, def __init__(self, title, sort, author_sort, timestamp, pubdate, series_index, last_modified, path, has_cover,
authors, tags): authors, tags, languages = None):
self.title = title self.title = title
self.sort = sort self.sort = sort
self.author_sort = author_sort self.author_sort = author_sort

View File

@ -5,7 +5,7 @@ import zipfile
from lxml import etree from lxml import etree
import os import os
import uploader import uploader
from iso639 import languages as isoLanguages
def extractCover(zip, coverFile, coverpath, tmp_file_name): def extractCover(zip, coverFile, coverpath, tmp_file_name):
if coverFile is None: if coverFile is None:
@ -41,12 +41,31 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0] p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
epub_metadata = {} epub_metadata = {}
try:#maybe description isn't present
comments = tree.xpath("//*[local-name() = 'description']/text()")[0]
epub_metadata['comments'] = comments
except:
epub_metadata['comments'] = ""
for s in ['title', 'description', 'creator']: for s in ['title', 'description', 'creator']:
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns) tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
if len(tmp) > 0: if len(tmp) > 0:
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0] epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
else: else:
epub_metadata[s] = "Unknown" epub_metadata[s] = "Unknown"
#detect lang need futher modification in web.py /upload
try:#maybe dc:language isn't present, less possible but possible
lang = p.xpath('dc:language/text()', namespaces=ns)[0]
lang = lang.split('-', 1)[0]
lang.lower()
if len(lang) == 2:
epub_metadata['languages'] = isoLanguages.get(part1=lang).name
elif len(lang) == 3:
epub_metadata['languages'] = isoLanguages.get(part3=lang).name
else:
epub_metadata['languages'] = ""
except:
epub_metadata['languages'] = ""
coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns) coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
coverfile = None coverfile = None
@ -60,16 +79,16 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
markup = zip.read(os.path.join(coverpath,coversection[0])) markup = zip.read(os.path.join(coverpath,coversection[0]))
markupTree = etree.fromstring(markup) markupTree = etree.fromstring(markup)
#no matter xhtml or html with no namespace #no matter xhtml or html with no namespace
imgsrc = markupTree.xpath( "//*[local-name() = 'img']/@src") imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src")
#imgsrc maybe startwith "../"" so fullpath join then relpath to cwd #imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath,coversection[0])),imgsrc[0])) filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0]))
coverfile = extractCover(zip, filename, "", tmp_file_path) coverfile = extractCover(zip, filename, "", tmp_file_path)
else: else:
coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path)
else: else:
meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns) meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns)
if len(meta_cover) > 0: if len(meta_cover) > 0:
meta_cover_content = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href",namespaces=ns) meta_cover_content = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns)
if len(meta_cover_content) > 0: if len(meta_cover_content) > 0:
coverfile = extractCover(zip, meta_cover_content[0], coverpath, tmp_file_path) coverfile = extractCover(zip, meta_cover_content[0], coverpath, tmp_file_path)
@ -87,4 +106,6 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
description=epub_metadata['description'], description=epub_metadata['description'],
tags="", tags="",
series="", series="",
series_id="") series_id="",
comments=epub_metadata['comments'],
languages=epub_metadata['languages'])

View File

@ -59,4 +59,5 @@ def get_fb2_info(tmp_file_path, original_file_extension):
description=description, description=description,
tags="", tags="",
series="", series="",
series_id="") series_id="",
languages="")

View File

@ -7,7 +7,7 @@ import hashlib
from collections import namedtuple from collections import namedtuple
import book_formats import book_formats
BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id') BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id, comments, languages')
""" """
:rtype: BookMeta :rtype: BookMeta

View File

@ -5,7 +5,7 @@ import logging
from logging.handlers import RotatingFileHandler from logging.handlers import RotatingFileHandler
import textwrap import textwrap
from flask import Flask, render_template, request, Response, redirect, url_for, send_from_directory, \ from flask import Flask, render_template, request, Response, redirect, url_for, send_from_directory, \
make_response, g, flash, abort make_response, g, flash, abort, Markup
from flask import __version__ as flaskVersion from flask import __version__ as flaskVersion
import ub import ub
from ub import config from ub import config
@ -2209,16 +2209,39 @@ def upload():
else: else:
db_author = db.Authors(author, helper.get_sorted_author(author), "") db_author = db.Authors(author, helper.get_sorted_author(author), "")
db.session.add(db_author) db.session.add(db_author)
#add language actually one value in list
input_language = meta.languages
db_language = None
if input_language != "":
input_language = isoLanguages.get(name=input_language).part3
hasLanguage = db.session.query(db.Languages).filter(db.Languages.lang_code == input_language).first()
if hasLanguage:
db_language = hasLanguage
else:
db_language = db.Languages(input_language)
db.session.add(db_language)
# combine path and normalize path from windows systems # combine path and normalize path from windows systems
path = os.path.join(author_dir, title_dir).replace('\\','/') path = os.path.join(author_dir, title_dir).replace('\\','/')
db_book = db.Books(title, "", db_author.sort, datetime.datetime.now(), datetime.datetime(101, 01, 01), 1, db_book = db.Books(title, "", db_author.sort, datetime.datetime.now(), datetime.datetime(101, 01, 01), 1,
datetime.datetime.now(), path, has_cover, db_author, []) datetime.datetime.now(), path, has_cover, db_author, [], db_language)
db_book.authors.append(db_author) db_book.authors.append(db_author)
if db_language is not None:
db_book.languages.append(db_language)
db_data = db.Data(db_book, meta.extension.upper()[1:], file_size, data_name) db_data = db.Data(db_book, meta.extension.upper()[1:], file_size, data_name)
db_book.data.append(db_data) db_book.data.append(db_data)
db.session.add(db_book) db.session.add(db_book)
db.session.flush()# flush content get db_book.id avalible
#add comment
upload_comment = Markup(meta.comments).unescape()
db_comment = None
if upload_comment != "":
db_comment = db.Comments(upload_comment, db_book.id)
db.session.add(db_comment)
db.session.commit() db.session.commit()
if db_language is not None: #display Full name instead of iso639.part3
db_book.languages[0].language_name = _(meta.languages)
author_names = [] author_names = []
for author in db_book.authors: for author in db_book.authors:
author_names.append(author.name) author_names.append(author.name)