Sync to trunk.

This commit is contained in:
John Schember 2010-01-06 19:58:21 -05:00
commit e27fa828f4
13 changed files with 658 additions and 182 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 5.3 KiB

View File

@ -15,12 +15,13 @@ class ElPais(BasicNewsRecipe):
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_tags = [dict(name='div', attrs={'class':'zona_superior'}), dict(name='div', attrs={'class':'limpiar'}), dict(name='div', attrs={'id':'pie'})]
extra_css = 'h1 {font: sans-serif large;} \n h2 {font: sans-serif medium;} \n h3 {font: sans-serif small;} \n h4 {font: sans-serif bold small;} \n p{ font:10pt serif}'
feeds = [(u'Internacional', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporint'), (u'Espana', u'http://www.elpais.es/rss/rss_section.html?anchor=elppornac'), (u'Deportes', u'http://www.elpais.es/rss/rss_section.html?anchor=elppordep'), (u'Economia', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporeco'), (u'Tecnologia', u'http://www.elpais.es/rss/rss_section.html?anchor=elpportec'), (u'Cultura', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporcul'), (u'Gente', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporgen'), (u'Sociedad', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporsoc'), (u'Opinion', u'http://www.elpais.es/rss/rss_section.html?anchor=elpporopi')]
def print_version(self, url):
url = url+'?print=1'
return url
def print_version(self, url):
url = url+'?print=1'
return url

View File

@ -31,6 +31,7 @@ class IncMagazineRecipe(BasicNewsRecipe):
def parse_index(self):
soup = self.index_to_soup(self.INDEX)
self.browser.open(self.INDEX)
url = self.browser.geturl()
date = url.rpartition('/')[0].rpartition('/')[2]

View File

@ -1,93 +1,93 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class PeopleMag(BasicNewsRecipe):
title = 'People/US Magazine Mashup'
__author__ = 'BrianG'
language = 'en'
description = 'Headlines from People and US Magazine'
no_stylesheets = True
use_embedded_content = False
oldest_article = 2
max_articles_per_feed = 50
extra_css = '''
h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.byline {font-size: small; color: #666666; font-style:italic; }
.lastline {font-size: small; color: #666666; font-style:italic;}
.contact {font-size: small; color: #666666;}
.contact p {font-size: small; color: #666666;}
.photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
.photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
.article_timestamp{font-size:x-small; color:#666666;}
a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class': 'panel_news_article_main'}),
dict(name='div', attrs={'class':'article_content'}),
dict(name='div', attrs={'class': 'headline'}),
dict(name='div', attrs={'class': 'post'}),
dict(name='div', attrs={'class': 'packageheadlines'}),
dict(name='div', attrs={'class': 'snap_preview'}),
dict(name='div', attrs={'id': 'articlebody'})
]
remove_tags = [
dict(name='div', attrs={'class':'share_comments'}),
dict(name='p', attrs={'class':'twitter_facebook'}),
dict(name='div', attrs={'class':'share_comments_bottom'}),
dict(name='h2', attrs={'id':'related_content'}),
dict(name='div', attrs={'class':'next_article'}),
dict(name='div', attrs={'class':'prev_article'}),
dict(name='ul', attrs={'id':'sharebar'}),
dict(name='div', attrs={'class':'sharelinkcont'}),
dict(name='div', attrs={'class':'categories'}),
dict(name='ul', attrs={'class':'categories'}),
dict(name='div', attrs={'id':'promo'}),
dict(name='div', attrs={'class':'linksWrapper'}),
dict(name='p', attrs={'class':'tag tvnews'}),
dict(name='p', attrs={'class':'tag movienews'}),
dict(name='p', attrs={'class':'tag musicnews'}),
dict(name='p', attrs={'class':'tag couples'}),
dict(name='p', attrs={'class':'tag gooddeeds'}),
dict(name='p', attrs={'class':'tag weddings'}),
dict(name='p', attrs={'class':'tag health'})
]
feeds = [
('PEOPLE Headlines', 'http://feeds.people.com/people/headlines'),
('US Headlines', 'http://www.usmagazine.com/celebrity_news/rss')
]
def get_article_url(self, article):
ans = article.link
try:
self.log('Looking for full story link in', ans)
soup = self.index_to_soup(ans)
x = soup.find(text="View All")
if x is not None:
ans = ans + '?viewAll=y'
self.log('Found full story link', ans)
except:
pass
return ans
def postprocess_html(self, soup,first):
for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
tag.extract()
for tag in soup.findAll(name='br'):
tag.extract()
return soup
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class PeopleMag(BasicNewsRecipe):
title = 'People/US Magazine Mashup'
__author__ = 'BrianG'
language = 'en'
description = 'Headlines from People and US Magazine'
no_stylesheets = True
use_embedded_content = False
oldest_article = 2
max_articles_per_feed = 50
extra_css = '''
h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
.byline {font-size: small; color: #666666; font-style:italic; }
.lastline {font-size: small; color: #666666; font-style:italic;}
.contact {font-size: small; color: #666666;}
.contact p {font-size: small; color: #666666;}
.photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
.photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
.article_timestamp{font-size:x-small; color:#666666;}
a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
'''
keep_only_tags = [
dict(name='div', attrs={'class': 'panel_news_article_main'}),
dict(name='div', attrs={'class':'article_content'}),
dict(name='div', attrs={'class': 'headline'}),
dict(name='div', attrs={'class': 'post'}),
dict(name='div', attrs={'class': 'packageheadlines'}),
dict(name='div', attrs={'class': 'snap_preview'}),
dict(name='div', attrs={'id': 'articlebody'})
]
remove_tags = [
dict(name='div', attrs={'class':'share_comments'}),
dict(name='p', attrs={'class':'twitter_facebook'}),
dict(name='div', attrs={'class':'share_comments_bottom'}),
dict(name='h2', attrs={'id':'related_content'}),
dict(name='div', attrs={'class':'next_article'}),
dict(name='div', attrs={'class':'prev_article'}),
dict(name='ul', attrs={'id':'sharebar'}),
dict(name='div', attrs={'class':'sharelinkcont'}),
dict(name='div', attrs={'class':'categories'}),
dict(name='ul', attrs={'class':'categories'}),
dict(name='div', attrs={'id':'promo'}),
dict(name='div', attrs={'class':'linksWrapper'}),
dict(name='p', attrs={'class':'tag tvnews'}),
dict(name='p', attrs={'class':'tag movienews'}),
dict(name='p', attrs={'class':'tag musicnews'}),
dict(name='p', attrs={'class':'tag couples'}),
dict(name='p', attrs={'class':'tag gooddeeds'}),
dict(name='p', attrs={'class':'tag weddings'}),
dict(name='p', attrs={'class':'tag health'})
]
feeds = [
('PEOPLE Headlines', 'http://feeds.people.com/people/headlines'),
('US Headlines', 'http://www.usmagazine.com/celebrity_news/rss')
]
def get_article_url(self, article):
ans = article.link
try:
self.log('Looking for full story link in', ans)
soup = self.index_to_soup(ans)
x = soup.find(text="View All")
if x is not None:
ans = ans + '?viewAll=y'
self.log('Found full story link', ans)
except:
pass
return ans
def postprocess_html(self, soup,first):
for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
tag.extract()
for tag in soup.findAll(name='br'):
tag.extract()
return soup

View File

@ -185,7 +185,7 @@ class Develop(Command):
script = template.format(
module=mod, func=func,
path=self.libdir, resources=self.sharedir,
executables=self.staging_bindir,
executables=self.bindir,
extensions=self.j(self.libdir, 'calibre', 'plugins'))
path = self.j(self.staging_bindir, name)
if not os.path.exists(self.staging_bindir):

View File

@ -245,7 +245,7 @@ class MobiMLizer(object):
bgcolor=istate.bgcolor)
if istate.fgcolor != 'black':
inline = etree.SubElement(inline, XHTML('font'),
color=istate.fgcolor)
color=unicode(istate.fgcolor))
if istate.strikethrough:
inline = etree.SubElement(inline, XHTML('s'))
bstate.inline = inline

View File

@ -605,7 +605,6 @@ def build_forms(srcdir, info=None):
if form.endswith('viewer%smain.ui'%os.sep):
info('\t\tPromoting WebView')
dat = dat.replace('self.view = QtWebKit.QWebView(', 'self.view = DocumentView(')
dat = dat.replace('from PyQt4 import QtWebKit', '')
if iswindows:
dat = dat.replace('self.view = QWebView(', 'self.view = DocumentView(')
dat = dat.replace('from QtWebKit.QWebView import QWebView', '')

View File

@ -0,0 +1,69 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from PyQt4.Qt import QThread
from calibre.utils.dictclient import Connection
class Lookup(QThread):
TEMPLATE = u'''<html>
<body>
<div>
{0}
</div>
</body>
</html>
'''
def __init__(self, word, parent=None):
QThread.__init__(self, parent)
self.word = word.encode('utf-8') if isinstance(word, unicode) else word
self.result = self.traceback = self.exception = None
def define(self):
conn = Connection('dict.org')
self.result = conn.define('!', self.word)
if self.result:
self.result = self.result[0].defstr
def run(self):
try:
self.define()
except Exception, e:
import traceback
self.exception = e
self.traceback = traceback.format_exc()
def format_exception(self):
lines = ['<b>Failed to connect to dict.org</b>', '']
lines += self.traceback.splitlines()
ans = '<br>'.join(lines)
if not isinstance(ans, unicode):
ans = ans.decode('utf-8')
return self.TEMPLATE.format(ans)
def no_results(self):
ans = _('No results found for:') + ' ' + self.word.decode('utf-8')
return self.TEMPLATE.format(ans)
@property
def html_result(self):
if self.exception is not None:
return self.format_exception()
if not self.result:
return self.no_results()
lines = self.result.splitlines()
lines[0] = '<b>'+lines[0]+'</b>'
ans = '<br>'.join(lines)
if not isinstance(ans, unicode):
ans = ans.decode('utf-8')
return self.TEMPLATE.format(ans)

View File

@ -9,8 +9,8 @@ import os, math, re, glob
from base64 import b64encode
from PyQt4.Qt import QSize, QSizePolicy, QUrl, SIGNAL, Qt, QTimer, \
QPainter, QPalette, QBrush, QFontDatabase, QDialog, \
QColor, QPoint, QImage, QRegion, QVariant, \
QFont, QObject, QApplication, pyqtSignature
QColor, QPoint, QImage, QRegion, QVariant, QIcon, \
QFont, QObject, QApplication, pyqtSignature, QAction
from PyQt4.QtWebKit import QWebPage, QWebView, QWebSettings
from calibre.utils.config import Config, StringConfig
@ -394,10 +394,20 @@ class DocumentView(QWebView):
self.connect(self.document, SIGNAL('selectionChanged()'), self.selection_changed)
self.connect(self.document, SIGNAL('animated_scroll_done()'),
self.animated_scroll_done, Qt.QueuedConnection)
copy_action = self.pageAction(self.document.Copy)
copy_action.setIcon(QIcon(I('convert.svg')))
d = self.document
self.unimplemented_actions = list(map(self.pageAction,
[d.DownloadImageToDisk, d.OpenLinkInNewWindow, d.DownloadLinkToDisk,
d.OpenImageInNewWindow, d.OpenLink]))
self.dictionary_action = QAction(QIcon(I('dictionary.png')),
_('&Lookup in dictionary'), self)
self.dictionary_action.setShortcut(Qt.CTRL+Qt.Key_L)
self.dictionary_action.triggered.connect(self.lookup)
@property
def copy_action(self):
return self.document.action(QWebPage.Copy)
return self.pageAction(self.document.Copy)
def animated_scroll_done(self):
if self.manager is not None:
@ -426,6 +436,21 @@ class DocumentView(QWebView):
if self.manager is not None:
self.manager.selection_changed(unicode(self.document.selectedText()))
def contextMenuEvent(self, ev):
menu = self.document.createStandardContextMenu()
for action in self.unimplemented_actions:
menu.removeAction(action)
text = unicode(self.selectedText())
if text:
menu.insertAction(list(menu.actions())[0], self.dictionary_action)
menu.exec_(ev.globalPos())
def lookup(self, *args):
if self.manager is not None:
t = unicode(self.selectedText()).strip()
if t:
self.manager.lookup(t.split()[0])
def set_manager(self, manager):
self.manager = manager
self.scrollbar = manager.horizontal_scrollbar

View File

@ -25,6 +25,7 @@ from calibre.utils.config import Config, StringConfig, dynamic
from calibre.gui2.search_box import SearchBox2
from calibre.ebooks.metadata import MetaInformation
from calibre.customize.ui import available_input_formats
from calibre.gui2.viewer.dictionary import Lookup
class TOCItem(QStandardItem):
@ -171,6 +172,9 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
self.pending_bookmark = None
self.selected_text = None
self.read_settings()
self.dictionary_box.hide()
self.close_dictionary_view.clicked.connect(lambda
x:self.dictionary_box.hide())
self.history = History(self.action_back, self.action_forward)
self.metadata = Metadata(self)
self.pos = DoubleSpinBox()
@ -239,6 +243,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
self.action_bookmark.setMenu(self.bookmarks_menu)
self.set_bookmarks([])
if pathtoebook is not None:
f = functools.partial(self.load_ebook, pathtoebook)
QTimer.singleShot(50, f)
@ -261,6 +266,19 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
ca.setShortcut(QKeySequence.Copy)
self.addAction(ca)
def lookup(self, word):
self.dictionary_view.setHtml('<html><body><p>'+ \
_('Connecting to dict.org to lookup: <b>%s</b>&hellip;')%word + \
'</p></body></html>')
self.dictionary_box.show()
self._lookup = Lookup(word, parent=self)
self._lookup.finished.connect(self.looked_up)
self._lookup.start()
def looked_up(self, *args):
html = self._lookup.html_result
self._lookup = None
self.dictionary_view.setHtml(html)
def set_max_width(self):
from calibre.gui2.viewer.documentview import config

View File

@ -50,6 +50,47 @@
</property>
</widget>
</item>
<item row="2" column="0" colspan="2">
<widget class="QFrame" name="dictionary_box">
<property name="frameShape">
<enum>QFrame::StyledPanel</enum>
</property>
<property name="frameShadow">
<enum>QFrame::Raised</enum>
</property>
<layout class="QHBoxLayout" name="horizontalLayout">
<item>
<widget class="QWebView" name="dictionary_view">
<property name="minimumSize">
<size>
<width>0</width>
<height>150</height>
</size>
</property>
<property name="url">
<url>
<string>about:blank</string>
</url>
</property>
</widget>
</item>
<item>
<widget class="QToolButton" name="close_dictionary_view">
<property name="toolTip">
<string>Close dictionary</string>
</property>
<property name="text">
<string>...</string>
</property>
<property name="icon">
<iconset resource="../../../../resources/images.qrc">
<normaloff>:/images/window-close.svg</normaloff>:/images/window-close.svg</iconset>
</property>
</widget>
</item>
</layout>
</widget>
</item>
</layout>
</widget>
</widget>

View File

@ -0,0 +1,317 @@
# Client for the DICT protocol (RFC2229)
#
# Copyright (C) 2002 John Goerzen
#
# 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 2 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, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import socket, re
version = '1.0'
def dequote(str):
"""Will remove single or double quotes from the start and end of a string
and return the result."""
quotechars = "'\""
while len(str) and str[0] in quotechars:
str = str[1:]
while len(str) and str[-1] in quotechars:
str = str[0:-1]
return str
def enquote(str):
"""This function will put a string in double quotes, properly
escaping any existing double quotes with a backslash. It will
return the result."""
return '"' + str.replace('"', "\\\"") + '"'
class Connection:
"""This class is used to establish a connection to a database server.
You will usually use this as the first call into the dictclient library.
Instantiating it takes two optional arguments: a hostname (a string)
and a port (an int). The hostname defaults to localhost
and the port to 2628, the port specified in RFC."""
def __init__(self, hostname = 'localhost', port = 2628):
self.sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
self.sock.connect((hostname, port))
self.rfile = self.sock.makefile("rt")
self.wfile = self.sock.makefile("wt", 0)
self.saveconnectioninfo()
def getresultcode(self):
"""Generic function to get a result code. It will return a list
consisting of two items: the integer result code and the text
following. You will not usually use this function directly."""
line = self.rfile.readline().strip()
code, text = line.split(' ', 1)
return [int(code), text]
def get200result(self):
"""Used when expecting a single line of text -- a 200-class
result. Returns [intcode, remaindertext]"""
code, text = self.getresultcode()
if code < 200 or code >= 300:
raise Exception, "Got '%s' when 200-class response expected" % \
text
return [code, text]
def get100block(self):
"""Used when expecting multiple lines of text -- gets the block
part only. Does not get any codes or anything! Returns a string."""
data = []
while 1:
line = self.rfile.readline().strip()
if line == '.':
break
data.append(line)
return "\n".join(data)
def get100result(self):
"""Used when expecting multiple lines of text, terminated by a period
and a 200 code. Returns: [initialcode, [bodytext_1lineperentry],
finalcode]"""
code, text = self.getresultcode()
if code < 100 or code >= 200:
raise Exception, "Got '%s' when 100-class response expected" % \
code
bodylines = self.get100block().split("\n")
code2 = self.get200result()[0]
return [code, bodylines, code2]
def get100dict(self):
"""Used when expecting a dictionary of results. Will read from
the initial 100 code, to a period and the 200 code."""
dict = {}
for line in self.get100result()[1]:
key, val = line.split(' ', 1)
dict[key] = dequote(val)
return dict
def saveconnectioninfo(self):
"""Called by __init__ to handle the initial connection. Will
save off the capabilities and messageid."""
code, string = self.get200result()
assert code == 220
capstr, msgid = re.search('<(.*)> (<.*>)$', string).groups()
self.capabilities = capstr.split('.')
self.messageid = msgid
def getcapabilities(self):
"""Returns a list of the capabilities advertised by the server."""
return self.capabilities
def getmessageid(self):
"""Returns the message id, including angle brackets."""
return self.messageid
def getdbdescs(self):
"""Gets a dict of available databases. The key is the db name
and the value is the db description. This command may generate
network traffic!"""
if hasattr(self, 'dbdescs'):
return self.dbdescs
self.sendcommand("SHOW DB")
self.dbdescs = self.get100dict()
return self.dbdescs
def getstratdescs(self):
"""Gets a dict of available strategies. The key is the strat
name and the value is the strat description. This call may
generate network traffic!"""
if hasattr(self, 'stratdescs'):
return self.stratdescs
self.sendcommand("SHOW STRAT")
self.stratdescs = self.get100dict()
return self.stratdescs
def getdbobj(self, dbname):
"""Gets a Database object corresponding to the database name passed
in. This function explicitly will *not* generate network traffic.
If you have not yet run getdbdescs(), it will fail."""
if not hasattr(self, 'dbobjs'):
self.dbobjs = {}
if self.dbobjs.has_key(dbname):
return self.dbobjs[dbname]
# We use self.dbdescs explicitly since we don't want to
# generate net traffic with this request!
if dbname != '*' and dbname != '!' and \
not dbname in self.dbdescs.keys():
raise Exception, "Invalid database name '%s'" % dbname
self.dbobjs[dbname] = Database(self, dbname)
return self.dbobjs[dbname]
def sendcommand(self, command):
"""Takes a command, without a newline character, and sends it to
the server."""
self.wfile.write(command + "\n")
def define(self, database, word):
"""Returns a list of Definition objects for each matching
definition. Parameters are the database name and the word
to look up. This is one of the main functions you will use
to interact with the server. Returns a list of Definition
objects. If there are no matches, an empty list is returned.
Note: database may be '*' which means to search all databases,
or '!' which means to return matches from the first database that
has a match."""
self.getdbdescs() # Prime the cache
if database != '*' and database != '!' and \
not database in self.getdbdescs():
raise Exception, "Invalid database '%s' specified" % database
self.sendcommand("DEFINE " + enquote(database) + " " + enquote(word))
code = self.getresultcode()[0]
retval = []
if code == 552:
# No definitions.
return []
if code != 150:
raise Exception, "Unknown code %d" % code
while 1:
code, text = self.getresultcode()
if code != 151:
break
resultword, resultdb = re.search('^"(.+)" (\S+)', text).groups()
defstr = self.get100block()
retval.append(Definition(self, self.getdbobj(resultdb),
resultword, defstr))
return retval
def match(self, database, strategy, word):
"""Gets matches for a query. Arguments are database name,
the strategy (see available ones in getstratdescs()), and the
pattern/word to look for. Returns a list of Definition objects.
If there is no match, an empty list is returned.
Note: database may be '*' which means to search all databases,
or '!' which means to return matches from the first database that
has a match."""
self.getstratdescs() # Prime the cache
self.getdbdescs() # Prime the cache
if not strategy in self.getstratdescs().keys():
raise Exception, "Invalid strategy '%s'" % strategy
if database != '*' and database != '!' and \
not database in self.getdbdescs().keys():
raise Exception, "Invalid database name '%s'" % database
self.sendcommand("MATCH %s %s %s" % (enquote(database),
enquote(strategy),
enquote(word)))
code = self.getresultcode()[0]
if code == 552:
# No Matches
return []
if code != 152:
raise Exception, "Unexpected code %d" % code
retval = []
for matchline in self.get100block().split("\n"):
matchdict, matchword = matchline.split(" ", 1)
retval.append(Definition(self, self.getdbobj(matchdict),
dequote(matchword)))
if self.getresultcode()[0] != 250:
raise Exception, "Unexpected end-of-list code %d" % code
return retval
class Database:
"""An object corresponding to a particular database in a server."""
def __init__(self, dictconn, dbname):
"""Initialize the object -- requires a Connection object and
a database name."""
self.conn = dictconn
self.name = dbname
def getname(self):
"""Returns the short name for this database."""
return self.name
def getdescription(self):
if hasattr(self, 'description'):
return self.description
if self.getname() == '*':
self.description = 'All Databases'
elif self.getname() == '!':
self.description = 'First matching database'
else:
self.description = self.conn.getdbdescs()[self.getname()]
return self.description
def getinfo(self):
"""Returns a string of info describing this database."""
if hasattr(self, 'info'):
return self.info
if self.getname() == '*':
self.info = "This special database will search all databases on the system."
elif self.getname() == '!':
self.info = "This special database will return matches from the first matching database."
else:
self.conn.sendcommand("SHOW INFO " + self.name)
self.info = "\n".join(self.conn.get100result()[1])
return self.info
def define(self, word):
"""Get a definition from within this database.
The argument, word, is the word to look up. The return value is the
same as from Connection.define()."""
return self.conn.define(self.getname(), word)
def match(self, strategy, word):
"""Get a match from within this database.
The argument, word, is the word to look up. The return value is
the same as from Connection.define()."""
return self.conn.match(self.getname(), strategy, word)
class Definition:
"""An object corresponding to a single definition."""
def __init__(self, dictconn, db, word, defstr = None):
"""Instantiate the object. Requires: a Connection object,
a Database object (NOT corresponding to '*' or '!' databases),
a word. Optional: a definition string. If not supplied,
it will be fetched if/when it is requested."""
self.conn = dictconn
self.db = db
self.word = word
self.defstr = defstr
def getdb(self):
"""Get the Database object corresponding to this definition."""
return self.db
def getdefstr(self):
"""Get the definition string (the actual content) of this
definition."""
if not self.defstr:
self.defstr = self.conn.define(self.getdb().getname(), self.word)[0].getdefstr()
return self.defstr
def getword(self):
"""Get the word this object describes."""
return self.word

View File

@ -1,9 +1,10 @@
"""
Read and write ZIP files. Modified by Kovid Goyal to support replacing files in
Read and write ZIP files. Modified by Kovid Goyal to support replacing files in
a zip archive.
"""
from __future__ import with_statement
from calibre.ptempfile import TemporaryDirectory
from calibre import sanitize_file_name
import struct, os, time, sys, shutil
import binascii, cStringIO
@ -789,80 +790,80 @@ class ZipFile:
if self.debug > 2:
print "total", total
def _calculate_file_offsets(self):
for zip_info in self.filelist:
self.fp.seek(zip_info.header_offset, 0)
fheader = self.fp.read(30)
if fheader[0:4] != stringFileHeader:
raise BadZipfile, "Bad magic number for file header"
fheader = struct.unpack(structFileHeader, fheader)
# file_offset is computed here, since the extra field for
# the central directory and for the local file header
# refer to different fields, and they can have different
# lengths
file_offset = (zip_info.header_offset + 30
+ fheader[_FH_FILENAME_LENGTH]
+ fheader[_FH_EXTRA_FIELD_LENGTH])
fname = self.fp.read(fheader[_FH_FILENAME_LENGTH])
if fname != zip_info.orig_filename:
raise RuntimeError(
'File name in directory "%s" and header "%s" differ.' % (
zip_info.orig_filename, fname))
zip_info.file_offset = file_offset
def replace(self, filename, arcname=None, compress_type=None):
"""Delete arcname, and put the bytes from filename into the
archive under the name arcname."""
deleteName = arcname
if deleteName is None:
deleteName = filename
self.delete(deleteName)
self.write(filename, arcname, compress_type)
def replacestr(self, zinfo, bytes):
"""Delete zinfo.filename, and write a new file into the archive. The
contents is the string 'bytes'."""
self.delete(zinfo.filename)
self.writestr(zinfo, bytes)
def delete(self, name):
"""Delete the file from the archive. If it appears multiple
times only the first instance will be deleted."""
for i in range (0, len(self.filelist)):
if self.filelist[i].filename == name:
if self.debug:
print "Removing", name
deleted_offset = self.filelist[i].header_offset
def _calculate_file_offsets(self):
for zip_info in self.filelist:
self.fp.seek(zip_info.header_offset, 0)
fheader = self.fp.read(30)
if fheader[0:4] != stringFileHeader:
raise BadZipfile, "Bad magic number for file header"
fheader = struct.unpack(structFileHeader, fheader)
# file_offset is computed here, since the extra field for
# the central directory and for the local file header
# refer to different fields, and they can have different
# lengths
file_offset = (zip_info.header_offset + 30
+ fheader[_FH_FILENAME_LENGTH]
+ fheader[_FH_EXTRA_FIELD_LENGTH])
fname = self.fp.read(fheader[_FH_FILENAME_LENGTH])
if fname != zip_info.orig_filename:
raise RuntimeError(
'File name in directory "%s" and header "%s" differ.' % (
zip_info.orig_filename, fname))
zip_info.file_offset = file_offset
def replace(self, filename, arcname=None, compress_type=None):
"""Delete arcname, and put the bytes from filename into the
archive under the name arcname."""
deleteName = arcname
if deleteName is None:
deleteName = filename
self.delete(deleteName)
self.write(filename, arcname, compress_type)
def replacestr(self, zinfo, bytes):
"""Delete zinfo.filename, and write a new file into the archive. The
contents is the string 'bytes'."""
self.delete(zinfo.filename)
self.writestr(zinfo, bytes)
def delete(self, name):
"""Delete the file from the archive. If it appears multiple
times only the first instance will be deleted."""
for i in range (0, len(self.filelist)):
if self.filelist[i].filename == name:
if self.debug:
print "Removing", name
deleted_offset = self.filelist[i].header_offset
deleted_size = (self.filelist[i].file_offset - self.filelist[i].header_offset) + self.filelist[i].compress_size
zinfo_size = struct.calcsize(structCentralDir) + len(self.filelist[i].filename) + len(self.filelist[i].extra)
# Remove the file's data from the archive.
current_offset = self.fp.tell()
self.fp.seek(0, 2)
archive_size = self.fp.tell()
self.fp.seek(deleted_offset + deleted_size)
buf = self.fp.read()
self.fp.seek(deleted_offset)
self.fp.write(buf)
self.fp.truncate(archive_size - deleted_size - zinfo_size)
if current_offset > deleted_offset + deleted_size:
current_offset -= deleted_size
elif current_offset > deleted_offset:
current_offset = deleted_offset
self.fp.seek(current_offset, 0)
# Remove file from central directory.
del self.filelist[i]
# Adjust the remaining offsets in the central directory.
for j in range (i, len(self.filelist)):
if self.filelist[j].header_offset > deleted_offset:
self.filelist[j].header_offset -= deleted_size
if self.filelist[j].file_offset > deleted_offset:
zinfo_size = struct.calcsize(structCentralDir) + len(self.filelist[i].filename) + len(self.filelist[i].extra)
# Remove the file's data from the archive.
current_offset = self.fp.tell()
self.fp.seek(0, 2)
archive_size = self.fp.tell()
self.fp.seek(deleted_offset + deleted_size)
buf = self.fp.read()
self.fp.seek(deleted_offset)
self.fp.write(buf)
self.fp.truncate(archive_size - deleted_size - zinfo_size)
if current_offset > deleted_offset + deleted_size:
current_offset -= deleted_size
elif current_offset > deleted_offset:
current_offset = deleted_offset
self.fp.seek(current_offset, 0)
# Remove file from central directory.
del self.filelist[i]
# Adjust the remaining offsets in the central directory.
for j in range (i, len(self.filelist)):
if self.filelist[j].header_offset > deleted_offset:
self.filelist[j].header_offset -= deleted_size
if self.filelist[j].file_offset > deleted_offset:
self.filelist[j].file_offset -= deleted_size
self._didModify = True
return
if self.debug:
print name, "not in archive"
self._didModify = True
return
if self.debug:
print name, "not in archive"
def namelist(self):
"""Return a list of file names in the archive."""
@ -1035,10 +1036,14 @@ class ZipFile:
os.unlink(upperdirs)
if upperdirs and not os.path.exists(upperdirs):
os.makedirs(upperdirs)
source = self.open(member, pwd=pwd)
if not os.path.exists(targetpath): # Could be a previously automatically created directory
target = open(targetpath, "wb")
try:
target = open(targetpath, "wb")
except IOError:
targetpath = sanitize_file_name(targetpath)
target = open(targetpath, "wb")
shutil.copyfileobj(source, target)
source.close()
target.close()
@ -1179,7 +1184,7 @@ class ZipFile:
zinfo.file_size))
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo
def add_dir(self, path, prefix=''):
'''
Add a directory recursively to the zip file with an optional prefix.
@ -1195,10 +1200,10 @@ class ZipFile:
if os.path.isdir(f):
self.add_dir(f, prefix=arcname)
else:
self.write(f, arcname)
self.write(f, arcname)
finally:
os.chdir(cwd)
def __del__(self):
"""Call the "close()" method in case the user forgot."""
@ -1294,7 +1299,7 @@ class ZipFile:
if self.debug > 0:
msg = 'Archive comment is too long; truncating to %d bytes' \
% ZIP_MAX_COMMENT
print msg
print msg
self.comment = self.comment[:ZIP_MAX_COMMENT]
endrec = struct.pack(structEndArchive, stringEndArchive,
@ -1314,7 +1319,7 @@ def safe_replace(zipstream, name, datastream):
Replace a file in a zip file in a safe manner. This proceeds by extracting
and re-creating the zipfile. This is neccessary because :method:`ZipFile.replace`
sometimes created corrupted zip files.
:param zipstream: Stream from a zip file
:param name: The name of the file to replace
:param datastream: The data to replace the file with.