Sync to trunk.

This commit is contained in:
John Schember 2011-09-27 06:45:18 -04:00
commit 18d3044147
15 changed files with 141 additions and 39 deletions

View File

@ -0,0 +1,21 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1316944753(BasicNewsRecipe):
title = u'Den of Geek'
__author__ = 'Jaded'
language = 'en'
description = 'From science fiction enthusiasts through to gaming fanatics, Den of Geek has become the one-stop UK website for people genuinely passionate about their entertainment media. Den of Geek covers popular culture but always with an edgy, UK centric slant that sets it apart from the crowd.'
category = 'Movies, TV, Games, Comics, Cult, News, Reviews'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
no_stylesheets = True
use_embedded_content = True
publication_type = 'newsportal'
masthead_url ='http://www.denofgeek.com/siteimage/scale/0/0/logo.gif'
cover_url ='http://a5.sphotos.ak.fbcdn.net/hphotos-ak-snc6/166479_180131695357862_139191826118516_354818_4993703_n.jpg'
feeds = [(u'Movies', u'http://www.denofgeek.com/movies/rss/'), (u'TV', u'http://www.denofgeek.com/television/rss/'), (u'Comics & Books', u'http://www.denofgeek.com/comics/rss/'), (u'Games', u'http://www.denofgeek.com/games/rss/'), (u'DVD/Blu-ray', u'http://www.denofgeek.com/Reviews/rss/')]

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.0 KiB

View File

@ -7,6 +7,7 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
SPOOL_SIZE = 30*1024*1024
'''
Rewrite of the calibre database backend.

View File

@ -8,7 +8,7 @@ __copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
# Imports {{{
import os, shutil, uuid, json, glob, time, tempfile
import os, shutil, uuid, json, glob, time
from functools import partial
import apsw
@ -16,7 +16,8 @@ import apsw
from calibre import isbytestring, force_unicode, prints
from calibre.constants import (iswindows, filesystem_encoding,
preferred_encoding)
from calibre.ptempfile import PersistentTemporaryFile
from calibre.ptempfile import PersistentTemporaryFile, SpooledTemporaryFile
from calibre.db import SPOOL_SIZE
from calibre.db.schema_upgrades import SchemaUpgrade
from calibre.library.field_metadata import FieldMetadata
from calibre.ebooks.metadata import title_sort, author_to_author_sort
@ -38,7 +39,7 @@ Differences in semantics from pysqlite:
'''
SPOOL_SIZE = 30*1024*1024
class DynamicFilter(object): # {{{
@ -805,7 +806,7 @@ class DB(object):
shutil.copyfileobj(f, pt)
return pt.name
if as_file:
ret = tempfile.SpooledTemporaryFile(SPOOL_SIZE)
ret = SpooledTemporaryFile(SPOOL_SIZE)
shutil.copyfileobj(f, ret)
ret.seek(0)
else:

View File

@ -51,11 +51,11 @@ class KOBO(USBMS):
EXTRA_CUSTOMIZATION_MESSAGE = [
_('The Kobo supports several collections including ')+\
'Read, Closed, Im_Reading ' +\
'Read, Closed, Im_Reading. ' +\
_('Create tags for automatic management'),
]
EXTRA_CUSTOMIZATION_DEFAULT = ', '.join(['tags'])
EXTRA_CUSTOMIZATION_DEFAULT = [', '.join(['tags'])]
OPT_COLLECTIONS = 0

View File

@ -73,6 +73,20 @@ class Worker(Thread): # Get details {{{
8: ['août'],
9: ['sept'],
12: ['déc'],
},
'es': {
1: ['enero'],
2: ['febrero'],
3: ['marzo'],
4: ['abril'],
5: ['mayo'],
6: ['junio'],
7: ['julio'],
8: ['agosto'],
9: ['septiembre', 'setiembre'],
10: ['octubre'],
11: ['noviembre'],
12: ['diciembre'],
},
'jp': {
1: [u'1月'],
@ -101,13 +115,16 @@ class Worker(Thread): # Get details {{{
text()="Dettagli prodotto" or \
text()="Product details" or \
text()="Détails sur le produit" or \
text()="Detalles del producto" or \
text()="登録情報"]/../div[@class="content"]
'''
# Editor: is for Spanish
self.publisher_xpath = '''
descendant::*[starts-with(text(), "Publisher:") or \
starts-with(text(), "Verlag:") or \
starts-with(text(), "Editore:") or \
starts-with(text(), "Editeur") or \
starts-with(text(), "Editor:") or \
starts-with(text(), "出版社:")]
'''
self.language_xpath = '''
@ -116,12 +133,14 @@ class Worker(Thread): # Get details {{{
or text() = "Language" \
or text() = "Sprache:" \
or text() = "Lingua:" \
or text() = "Idioma:" \
or starts-with(text(), "Langue") \
or starts-with(text(), "言語") \
]
'''
self.ratings_pat = re.compile(
r'([0-9.]+) ?(out of|von|su|étoiles sur|つ星のうち) ([\d\.]+)( (stars|Sternen|stelle)){0,1}')
r'([0-9.]+) ?(out of|von|su|étoiles sur|つ星のうち|de un máximo de) ([\d\.]+)( (stars|Sternen|stelle|estrellas)){0,1}')
lm = {
'eng': ('English', 'Englisch'),
@ -143,6 +162,7 @@ class Worker(Thread): # Get details {{{
for i, vals in self.months.iteritems():
for x in vals:
ans = ans.replace(x, self.english_months[i])
ans = ans.replace(' de ', ' ')
return ans
def run(self):
@ -422,6 +442,7 @@ class Amazon(Source):
'uk' : _('UK'),
'it' : _('Italy'),
'jp' : _('Japan'),
'es' : _('Spain'),
}
options = (
@ -789,6 +810,16 @@ if __name__ == '__main__': # tests {{{
),
] # }}}
es_tests = [ # {{{
(
{'identifiers':{'isbn': '8483460831'}},
[title_test('Tiempos Interesantes',
exact=True), authors_test(['Terry Pratchett'])
]
),
] # }}}
jp_tests = [ # {{{
( # isbn -> title, authors
{'identifiers':{'isbn': '9784101302720' }},
@ -804,6 +835,6 @@ if __name__ == '__main__': # tests {{{
] # }}}
test_identify_plugin(Amazon.name, com_tests)
#test_identify_plugin(Amazon.name, jp_tests)
#test_identify_plugin(Amazon.name, es_tests)
# }}}

View File

@ -249,6 +249,7 @@ class SaveWorker(Thread):
recs[pref.name] = getattr(self.opts, pref.name)
plugboards = self.db.prefs.get('plugboards', {})
template_functions = self.db.prefs.get('user_template_functions', [])
for i, task in enumerate(tasks):
tids = [x[-1] for x in task]
@ -260,7 +261,7 @@ class SaveWorker(Thread):
job = ParallelJob('save_book',
'Save books (%d of %d)'%(i, len(tasks)),
lambda x,y:x,
args=[tids, dpath, plugboards, self.path, recs])
args=[tids, dpath, plugboards, template_functions, self.path, recs])
jobs.add(job)
server.add_job(job)
@ -312,9 +313,12 @@ class SaveWorker(Thread):
break
def save_book(ids, dpath, plugboards, path, recs, notification=lambda x,y:x):
def save_book(ids, dpath, plugboards, template_functions, path, recs,
notification=lambda x,y:x):
from calibre.library.save_to_disk import config, save_serialized_to_disk
from calibre.customize.ui import apply_null_metadata
from calibre.utils.formatter_functions import load_user_template_functions
load_user_template_functions(template_functions)
opts = config().parse()
for name in recs:
setattr(opts, name, recs[name])

View File

@ -126,7 +126,7 @@ void XMLImages::add(GfxState *state, Object *ref, Stream *str,
if (img->type == jpeg) {
int c;
str = ((DCTStream *)str)->getRawStream();
str = str->getNextStream();
str->reset();
// copy the stream

View File

@ -625,7 +625,12 @@ static string get_link_dest(LinkAction *link, PDFDoc *doc) {
return oss.str();
}
#if (POPPLER_MAJOR_VERSION == 0) && (POPPLER_MINOR_VERSION < 17)
void XMLOutputDev::process_link(Link* link){
#else
void XMLOutputDev::process_link(AnnotLink* link){
#endif
double _x1, _y1, _x2, _y2;
int x1, y1, x2, y2;

View File

@ -244,6 +244,11 @@ class XMLOutputDev : public OutputDev {
XMLImages *images;
PDFDoc *doc;
#if (POPPLER_MAJOR_VERSION == 0) && (POPPLER_MINOR_VERSION < 17)
void process_link(Link* link);
#else
void process_link(AnnotLink* link);
#endif
};
}

View File

@ -7,7 +7,7 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import textwrap, re, os, errno
import textwrap, re, os, errno, shutil
from PyQt4.Qt import (Qt, QDateEdit, QDate, pyqtSignal, QMessageBox,
QIcon, QToolButton, QWidget, QLabel, QGridLayout, QApplication,
@ -33,8 +33,9 @@ from calibre.gui2.comments_editor import Editor
from calibre.library.comments import comments_to_html
from calibre.gui2.dialogs.tag_editor import TagEditor
from calibre.utils.icu import strcmp
from calibre.ptempfile import PersistentTemporaryFile
from calibre.ptempfile import PersistentTemporaryFile, SpooledTemporaryFile
from calibre.gui2.languages import LanguagesEdit as LE
from calibre.db import SPOOL_SIZE
def save_dialog(parent, title, msg, det_msg=''):
d = QMessageBox(parent)
@ -43,8 +44,6 @@ def save_dialog(parent, title, msg, det_msg=''):
d.setStandardButtons(QMessageBox.Yes | QMessageBox.No | QMessageBox.Cancel)
return d.exec_()
'''
The interface common to all widgets used to set basic metadata
class BasicMetadataWidget(object):
@ -731,7 +730,11 @@ class FormatsManager(QWidget):
else:
old_extensions.add(ext)
for ext in new_extensions:
db.add_format(id_, ext, open(paths[ext], 'rb'), notify=False,
with SpooledTemporaryFile(SPOOL_SIZE) as spool:
with open(paths[ext], 'rb') as f:
shutil.copyfileobj(f, spool)
spool.seek(0)
db.add_format(id_, ext, spool, notify=False,
index_is_id=True)
dbfmts = db.formats(id_, index_is_id=True)
db_extensions = set([f.lower() for f in (dbfmts.split(',') if dbfmts

View File

@ -7,7 +7,7 @@ __docformat__ = 'restructuredtext en'
The database used to store ebook metadata
'''
import os, sys, shutil, cStringIO, glob, time, functools, traceback, re, \
json, uuid, tempfile, hashlib, copy
json, uuid, hashlib, copy
from collections import defaultdict
import threading, random
from itertools import repeat
@ -26,7 +26,8 @@ from calibre.library.sqlite import connect, IntegrityError
from calibre.library.prefs import DBPrefs
from calibre.ebooks.metadata.book.base import Metadata
from calibre.constants import preferred_encoding, iswindows, filesystem_encoding
from calibre.ptempfile import PersistentTemporaryFile, base_dir
from calibre.ptempfile import (PersistentTemporaryFile,
base_dir, SpooledTemporaryFile)
from calibre.customize.ui import run_plugins_on_import
from calibre import isbytestring
from calibre.utils.filenames import ascii_filename
@ -610,7 +611,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
with lopen(os.path.join(tpath, 'cover.jpg'), 'wb') as f:
f.write(cdata)
for format in formats:
with tempfile.SpooledTemporaryFile(max_size=SPOOL_SIZE) as stream:
with SpooledTemporaryFile(SPOOL_SIZE) as stream:
try:
self.copy_format_to(id, format, stream, index_is_id=True)
stream.seek(0)
@ -694,7 +695,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
shutil.copyfileobj(f, pt)
return pt.name
if as_file:
ret = tempfile.SpooledTemporaryFile(SPOOL_SIZE)
ret = SpooledTemporaryFile(SPOOL_SIZE)
shutil.copyfileobj(f, ret)
ret.seek(0)
else:
@ -1282,7 +1283,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
shutil.copyfileobj(f, pt)
ret = pt.name
elif as_file:
ret = tempfile.SpooledTemporaryFile(max_size=SPOOL_SIZE)
ret = SpooledTemporaryFile(SPOOL_SIZE)
shutil.copyfileobj(f, ret)
ret.seek(0)
# Various bits of code try to use the name as the default

View File

@ -181,4 +181,17 @@ class TemporaryFile(object):
class SpooledTemporaryFile(tempfile.SpooledTemporaryFile):
def __init__(self, max_size=0, suffix="", prefix="", dir=None, mode='w+b',
bufsize=-1):
if prefix == None:
prefix = ''
if suffix is None:
suffix = ''
if dir is None:
dir = base_dir()
tempfile.SpooledTemporaryFile.__init__(self, max_size=max_size, suffix=suffix,
prefix=prefix, dir=dir, mode=mode, bufsize=bufsize)

View File

@ -170,32 +170,40 @@ def format_date(dt, format, assume_utc=False, as_utc=False):
if format == 'iso':
return isoformat(dt, assume_utc=assume_utc, as_utc=as_utc)
if dt == UNDEFINED_DATE:
return ''
strf = partial(strftime, t=dt.timetuple())
def format_day(mo):
l = len(mo.group(0))
def format_day(dy):
l = len(dy)
if l == 1: return '%d'%dt.day
if l == 2: return '%02d'%dt.day
if l == 3: return strf('%a')
return strf('%A')
def format_month(mo):
l = len(mo.group(0))
l = len(mo)
if l == 1: return '%d'%dt.month
if l == 2: return '%02d'%dt.month
if l == 3: return strf('%b')
return strf('%B')
def format_year(mo):
if len(mo.group(0)) == 2: return '%02d'%(dt.year % 100)
def format_year(yr):
if len(yr) == 2: return '%02d'%(dt.year % 100)
return '%04d'%dt.year
if dt == UNDEFINED_DATE:
def repl_func(mo):
s = mo.group(0)
if s is None:
return ''
if s[0] == 'd':
return format_day(s)
if s[0] == 'M':
return format_month(s)
return format_year(s)
format = re.sub('d{1,4}', format_day, format)
format = re.sub('M{1,4}', format_month, format)
return re.sub('yyyy|yy', format_year, format)
return re.sub('(d{1,4}|M{1,4}|(?:yyyy|yy))', repl_func, format)
def replace_months(datestr, clang):
# Replace months by english equivalent for parse_date

View File

@ -13,7 +13,7 @@ from functools import partial
from contextlib import nested, closing
from calibre import (browser, __appname__, iswindows,
from calibre import (browser, __appname__, iswindows, force_unicode,
strftime, preferred_encoding, as_unicode)
from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString, CData, Tag
from calibre.ebooks.metadata.opf2 import OPFCreator
@ -49,7 +49,7 @@ class BasicNewsRecipe(Recipe):
#: A couple of lines that describe the content this recipe downloads.
#: This will be used primarily in a GUI that presents a list of recipes.
description = ''
description = u''
#: The author of this recipe
__author__ = __appname__
@ -112,8 +112,6 @@ class BasicNewsRecipe(Recipe):
#: If set to "optional" the use of a username and password becomes optional
needs_subscription = False
#:
#: If True the navigation bar is center aligned, otherwise it is left aligned
center_navbar = True
@ -1205,12 +1203,22 @@ class BasicNewsRecipe(Recipe):
mi.author_sort = __appname__
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
mi.timestamp = nowf()
article_titles, aseen = [], set()
for f in feeds:
for a in f:
if a.title and a.title not in aseen:
aseen.add(a.title)
article_titles.append(force_unicode(a.title, 'utf-8'))
mi.comments = self.description
if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace')
mi.comments += ('\n\n' + _('Articles in this issue: ') + '\n' +
'\n\n'.join(article_titles))
language = canonicalize_lang(self.language)
if language is not None:
mi.language = language
if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace')
mi.pubdate = nowf()
opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx')
@ -1256,6 +1264,7 @@ class BasicNewsRecipe(Recipe):
self.play_order_counter = 0
self.play_order_map = {}
def feed_index(num, parent):
f = feeds[num]
for j, a in enumerate(f):