Merge from trunk

This commit is contained in:
Charles Haley 2011-06-13 09:51:46 +01:00
commit 69f06412fa
11 changed files with 87 additions and 33 deletions

View File

@ -6,7 +6,7 @@ class HBR(BasicNewsRecipe):
title = 'Harvard Business Review Blogs' title = 'Harvard Business Review Blogs'
description = 'To subscribe go to http://hbr.harvardbusiness.org' description = 'To subscribe go to http://hbr.harvardbusiness.org'
needs_subscription = True needs_subscription = True
__author__ = 'Kovid Goyal and Sujata Raman, enhanced by BrianG' __author__ = 'Kovid Goyal, enhanced by BrianG'
language = 'en' language = 'en'
no_stylesheets = True no_stylesheets = True

View File

@ -348,7 +348,6 @@ class MobiReader(object):
self.processed_html = self.remove_random_bytes(self.processed_html) self.processed_html = self.remove_random_bytes(self.processed_html)
root = soupparser.fromstring(self.processed_html) root = soupparser.fromstring(self.processed_html)
if root.tag != 'html': if root.tag != 'html':
self.log.warn('File does not have opening <html> tag') self.log.warn('File does not have opening <html> tag')
nroot = html.fromstring('<html><head></head><body></body></html>') nroot = html.fromstring('<html><head></head><body></body></html>')

View File

@ -38,6 +38,10 @@ class DeviceJob(BaseJob): # {{{
BaseJob.__init__(self, description) BaseJob.__init__(self, description)
self.func = func self.func = func
self.callback_on_done = done self.callback_on_done = done
if not isinstance(self.callback_on_done, (Dispatcher,
FunctionDispatcher)):
self.callback_on_done = FunctionDispatcher(self.callback_on_done)
self.args, self.kwargs = args, kwargs self.args, self.kwargs = args, kwargs
self.exception = None self.exception = None
self.job_manager = job_manager self.job_manager = job_manager
@ -259,7 +263,8 @@ class DeviceManager(Thread): # {{{
job = self.next() job = self.next()
if job is not None: if job is not None:
self.current_job = job self.current_job = job
self.device.set_progress_reporter(job.report_progress) if self.device is not None:
self.device.set_progress_reporter(job.report_progress)
self.current_job.run() self.current_job.run()
self.current_job = None self.current_job = None
else: else:
@ -592,7 +597,7 @@ class DeviceMenu(QMenu): # {{{
# }}} # }}}
class DeviceSignals(QObject): class DeviceSignals(QObject): # {{{
#: This signal is emitted once, after metadata is downloaded from the #: This signal is emitted once, after metadata is downloaded from the
#: connected device. #: connected device.
#: The sequence: gui.device_manager.is_device_connected will become True, #: The sequence: gui.device_manager.is_device_connected will become True,
@ -609,6 +614,7 @@ class DeviceSignals(QObject):
device_connection_changed = pyqtSignal(object) device_connection_changed = pyqtSignal(object)
device_signals = DeviceSignals() device_signals = DeviceSignals()
# }}}
class DeviceMixin(object): # {{{ class DeviceMixin(object): # {{{

View File

@ -9,6 +9,7 @@ __docformat__ = 'restructuredtext en'
import os, socket, time import os, socket, time
from binascii import unhexlify from binascii import unhexlify
from functools import partial from functools import partial
from threading import Thread
from itertools import repeat from itertools import repeat
from calibre.utils.smtp import (compose_mail, sendmail, extract_email_address, from calibre.utils.smtp import (compose_mail, sendmail, extract_email_address,
@ -22,9 +23,30 @@ from calibre.library.save_to_disk import get_components
from calibre.utils.config import tweaks from calibre.utils.config import tweaks
from calibre.gui2.threaded_jobs import ThreadedJob from calibre.gui2.threaded_jobs import ThreadedJob
class Worker(Thread):
def __init__(self, func, args):
Thread.__init__(self)
self.daemon = True
self.exception = self.tb = None
self.func, self.args = func, args
def run(self):
#time.sleep(1000)
try:
self.func(*self.args)
except Exception as e:
import traceback
self.exception = e
self.tb = traceback.format_exc()
finally:
self.func = self.args = None
class Sendmail(object): class Sendmail(object):
MAX_RETRIES = 1 MAX_RETRIES = 1
TIMEOUT = 15 * 60 # seconds
def __init__(self): def __init__(self):
self.calculate_rate_limit() self.calculate_rate_limit()
@ -42,22 +64,32 @@ class Sendmail(object):
abort=None, notifications=None): abort=None, notifications=None):
try_count = 0 try_count = 0
while try_count <= self.MAX_RETRIES: while True:
if try_count > 0: if try_count > 0:
log('\nRetrying in %d seconds...\n' % log('\nRetrying in %d seconds...\n' %
self.rate_limit) self.rate_limit)
try: worker = Worker(self.sendmail,
self.sendmail(attachment, aname, to, subject, text, log) (attachment, aname, to, subject, text, log))
try_count = self.MAX_RETRIES worker.start()
log('Email successfully sent') start_time = time.time()
except: while worker.is_alive():
worker.join(0.2)
if abort.is_set(): if abort.is_set():
log('Sending aborted by user')
return return
if try_count == self.MAX_RETRIES: if time.time() - start_time > self.TIMEOUT:
raise log('Sending timed out')
log.exception('\nSending failed...\n') raise Exception(
'Sending email %r to %r timed out, aborting'% (subject,
to))
if worker.exception is None:
log('Email successfully sent')
return
log.error('\nSending failed...\n')
log.debug(worker.tb)
try_count += 1 try_count += 1
if try_count > self.MAX_RETRIES:
raise worker.exception
def sendmail(self, attachment, aname, to, subject, text, log): def sendmail(self, attachment, aname, to, subject, text, log):
while time.time() - self.last_send_time <= self.rate_limit: while time.time() - self.last_send_time <= self.rate_limit:
@ -90,7 +122,7 @@ def send_mails(jobnames, callback, attachments, to_s, subjects,
attachments, to_s, subjects, texts, attachment_names): attachments, to_s, subjects, texts, attachment_names):
description = _('Email %s to %s') % (name, to) description = _('Email %s to %s') % (name, to)
job = ThreadedJob('email', description, gui_sendmail, (attachment, aname, to, job = ThreadedJob('email', description, gui_sendmail, (attachment, aname, to,
subject, text), {}, callback, killable=False) subject, text), {}, callback)
job_manager.run_threaded_job(job) job_manager.run_threaded_job(job)

View File

@ -457,7 +457,7 @@ class JobsDialog(QDialog, Ui_JobsDialog):
def kill_job(self, *args): def kill_job(self, *args):
if question_dialog(self, _('Are you sure?'), _('Do you really want to stop the selected job?')): if question_dialog(self, _('Are you sure?'), _('Do you really want to stop the selected job?')):
for index in self.jobs_view.selectedIndexes(): for index in self.jobs_view.selectionModel().selectedRows():
row = index.row() row = index.row()
self.model.kill_job(row, self) self.model.kill_job(row, self)

View File

@ -462,11 +462,11 @@ class EditRules(QWidget): # {{{
self.l = l = QGridLayout(self) self.l = l = QGridLayout(self)
self.setLayout(l) self.setLayout(l)
self.l1 = l1 = QLabel(_( self.l1 = l1 = QLabel('<p>'+_(
'You can control the color of columns in the' 'You can control the color of columns in the'
' book list by creating "rules" that tell calibre' ' book list by creating "rules" that tell calibre'
' what color to use. Click the Add Rule button below' ' what color to use. Click the Add Rule button below'
' to get started. You can change an existing rule by double' ' to get started.<p>You can <b>change an existing rule</b> by double'
' clicking it.')) ' clicking it.'))
l1.setWordWrap(True) l1.setWordWrap(True)
l.addWidget(l1, 0, 0, 1, 2) l.addWidget(l1, 0, 0, 1, 2)

View File

@ -139,14 +139,26 @@ class AmazonKindleStore(StorePlugin):
cover_xpath = './/div[@class="productTitle"]//img/@src' cover_xpath = './/div[@class="productTitle"]//img/@src'
title_xpath = './/div[@class="productTitle"]/a//text()' title_xpath = './/div[@class="productTitle"]/a//text()'
price_xpath = './/div[@class="newPrice"]/span/text()' price_xpath = './/div[@class="newPrice"]/span/text()'
# Vertical list of books. Search "martin" # Vertical list of books.
else: else:
data_xpath = '//div[contains(@class, "results")]//div[contains(@class, "result")]' # New style list. Search "Paolo Bacigalupi"
format_xpath = './/span[@class="binding"]//text()' if doc.xpath('boolean(//div[@class="image"])'):
asin_xpath = './/div[@class="image"]/a[1]' data_xpath = '//div[contains(@class, "results")]//div[contains(@class, "result")]'
cover_xpath = './/img[@class="productImage"]/@src' format_xpath = './/span[@class="binding"]//text()'
title_xpath = './/a[@class="title"]/text()' asin_xpath = './/div[@class="image"]/a[1]'
price_xpath = './/span[@class="price"]/text()' cover_xpath = './/img[@class="productImage"]/@src'
title_xpath = './/a[@class="title"]/text()'
price_xpath = './/span[@class="price"]/text()'
# Old style list. Search "martin"
else:
data_xpath = '//div[contains(@class, "result")]'
format_xpath = './/span[@class="format"]//text()'
asin_xpath = './/div[@class="productImage"]/a[1]'
cover_xpath = './/div[@class="productImage"]//img/@src'
title_xpath = './/div[@class="productTitle"]/a/text()'
price_xpath = './/div[@class="newPrice"]//span//text()'
for data in doc.xpath(data_xpath): for data in doc.xpath(data_xpath):
if counter <= 0: if counter <= 0:

View File

@ -26,7 +26,7 @@ from calibre.library.custom_columns import CustomColumns
from calibre.library.sqlite import connect, IntegrityError from calibre.library.sqlite import connect, IntegrityError
from calibre.library.prefs import DBPrefs from calibre.library.prefs import DBPrefs
from calibre.ebooks.metadata.book.base import Metadata from calibre.ebooks.metadata.book.base import Metadata
from calibre.constants import preferred_encoding, iswindows, isosx, filesystem_encoding from calibre.constants import preferred_encoding, iswindows, filesystem_encoding
from calibre.ptempfile import PersistentTemporaryFile from calibre.ptempfile import PersistentTemporaryFile
from calibre.customize.ui import run_plugins_on_import from calibre.customize.ui import run_plugins_on_import
from calibre import isbytestring from calibre import isbytestring
@ -188,8 +188,9 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
apply_default_prefs = not os.path.exists(self.dbpath) apply_default_prefs = not os.path.exists(self.dbpath)
self.connect() self.connect()
self.is_case_sensitive = not iswindows and not isosx and \ self.is_case_sensitive = (not iswindows and
not os.path.exists(self.dbpath.replace('metadata.db', 'MeTAdAtA.dB')) not os.path.exists(self.dbpath.replace('metadata.db',
'MeTAdAtA.dB')))
SchemaUpgrade.__init__(self) SchemaUpgrade.__init__(self)
# Guarantee that the library_id is set # Guarantee that the library_id is set
self.library_id self.library_id
@ -606,7 +607,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
f = self.format(id, format, index_is_id=True, as_file=True) f = self.format(id, format, index_is_id=True, as_file=True)
if f is None: if f is None:
continue continue
with tempfile.SpooledTemporaryFile(max_size=100*(1024**2)) as stream: with tempfile.SpooledTemporaryFile(max_size=30*(1024**2)) as stream:
with f: with f:
shutil.copyfileobj(f, stream) shutil.copyfileobj(f, stream)
stream.seek(0) stream.seek(0)

View File

@ -189,7 +189,7 @@ Extra CSS
This option allows you to specify arbitrary CSS that will be applied to all HTML files in the This option allows you to specify arbitrary CSS that will be applied to all HTML files in the
input. This CSS is applied with very high priority and so should override most CSS present in input. This CSS is applied with very high priority and so should override most CSS present in
the input document itself. You can use this setting to fine tune the presentation/layout of your the **input document** itself. You can use this setting to fine tune the presentation/layout of your
document. For example, if you want all paragraphs of class `endnote` to be right aligned, just document. For example, if you want all paragraphs of class `endnote` to be right aligned, just
add:: add::
@ -200,7 +200,8 @@ or if you want to change the indentation of all paragraphs::
p { text-indent: 5mm; } p { text-indent: 5mm; }
:guilabel:`Extra CSS` is a very powerful option, but you do need an understanding of how CSS works :guilabel:`Extra CSS` is a very powerful option, but you do need an understanding of how CSS works
to use it to its full potential. to use it to its full potential. You can use the debug pipeline option described above to see what
CSS is present in your input document.
Miscellaneous Miscellaneous
~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~

View File

@ -317,6 +317,9 @@ def feed_from_xml(raw_xml, title=None, oldest_article=7,
max_articles_per_feed=100, max_articles_per_feed=100,
get_article_url=lambda item: item.get('link', None), get_article_url=lambda item: item.get('link', None),
log=default_log): log=default_log):
# Handle unclosed escaped entities. They trip up feedparser and HBR for one
# generates them
raw_xml = re.sub(r'(&amp;#\d+)([^0-9;])', r'\1;\2', raw_xml)
feed = parse(raw_xml) feed = parse(raw_xml)
pfeed = Feed(get_article_url=get_article_url, log=log) pfeed = Feed(get_article_url=get_article_url, log=log)
pfeed.populate_from_feed(feed, title=title, pfeed.populate_from_feed(feed, title=title,

View File

@ -13,8 +13,8 @@ from functools import partial
from contextlib import nested, closing from contextlib import nested, closing
from calibre import browser, __appname__, iswindows, \ from calibre import (browser, __appname__, iswindows,
strftime, preferred_encoding, as_unicode strftime, preferred_encoding, as_unicode)
from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString, CData, Tag from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString, CData, Tag
from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre import entity_to_unicode from calibre import entity_to_unicode