Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge from trunk

Browse Source
This commit is contained in:
Charles Haley 2011-02-10 21:26:27 +00:00
commit 70636b42c4
20 changed files with 1119 additions and 405 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
format_docs/pdb/apnx.txt Normal file
View File

@ -0,0 +1,69 @@
APNX
----
apnx files are used by the Amazon Kindle (firmware revision 3.1+) to
map pages from a print book to the Kindle version. Integers within
the file are big-endian.
Layout
------
bytes content comments
4 00010001 Format identifier. Value of 65537 little-endian.
4 start of next The offset after ending location of the first header.
Starts a new sequence of header info
4 length Length of first header
N first header String containing content header
Starts next sequence
2 unknown Always 1
2 length Length of second header
2 page count Total number of bytes after second header that
represent pages. This total includes bytes that
are ignored by the pageMap.
2 unknown Always 32
N second header String containing the page mapping header
4*N padding The first number given in the page mapping header indicates the number of 0 bytes.
4*N page list
Content Header
--------------
The content header is a string enclosed in {} containing key, value pairs.
content comments
contentGuid Guid.
asin Amazon identifier for the Kindle version of the book.
cdeType MOBI cdeType. Should always be EBOK for ebooks.
fileRevisionId Revision of this file.
Example:
{"contentGuid":"d8c14b0","asin":"B000JML5VM","cdeType":"EBOK","fileRevisionId":"1296874359405"}
Page Mapping Header
-------------------
The page mapping header is a string enclosed in {} containing key, value pairs.
content comments
asin The ISBN 10 for the paper book the pages correspond to
pageMap Three value tuple. Looks like: "(N,N,N)"
1) Number of bytes after header that starts the page numbering sequence
2) unknown
3) unknown
Example:
{"asin":"1906694184","pageMap":"(4,a,1)"}
Page List
---------
The page list is a sequence of offsets in the uncompressed HTML. Each
value is the beginning of a new page. Each entry is a 4 byte big endian
int. The list is ordered lowest to highest.

104
resources/default_tweaks.py
View File

@ -10,7 +10,7 @@ you know what you are doing. If you delete this file, it will be recreated from
defaults.
'''
#: Auto increment series index
# The algorithm used to assign a new book in an existing series a series number.
# New series numbers assigned using this tweak are always integer values, except
# if a constant non-integer is specified.
@ -29,7 +29,7 @@ defaults.
# series_index_auto_increment = 16.5
series_index_auto_increment = 'next'
#: Add separator after completing an author name
# Should the completion separator be append
# to the end of the completed text to
# automatically begin a new completion operation
@ -38,6 +38,7 @@ series_index_auto_increment = 'next'
authors_completer_append_separator = False
#: Author sort name algorithm
# The algorithm used to copy author to author_sort
# Possible values are:
# invert: use "fn ln" -> "ln, fn" (the default algorithm)
@ -49,6 +50,7 @@ authors_completer_append_separator = False
# selecting 'manage authors', and pressing 'Recalculate all author sort values'.
author_sort_copy_method = 'invert'
#: Use author sort in Tag Browser
# Set which author field to display in the tags pane (the list of authors,
# series, publishers etc on the left hand side). The choices are author and
# author_sort. This tweak affects only what is displayed under the authors
@ -63,6 +65,7 @@ author_sort_copy_method = 'invert'
# categories_use_field_for_author_name = 'author_sort'
categories_use_field_for_author_name = 'author'
#: Control partitioning of Tag Browser
# When partitioning the tags browser, the format of the subcategory label is
# controlled by a template: categories_collapsed_name_template if sorting by
# name, categories_collapsed_rating_template if sorting by average rating, and
@ -74,24 +77,25 @@ categories_use_field_for_author_name = 'author'
# author category will be the name of the author. The sub-values available are:
# name: the printable name of the item
# count: the number of books that references this item
# avg_rating: the averate rating of all the books referencing this item
# avg_rating: the average rating of all the books referencing this item
# sort: the sort value. For authors, this is the author_sort for that author
# category: the category (e.g., authors, series) that the item is in.
# Note that the "r'" in front of the { is necessary if there are backslashes
# (\ characters) in the template. It doesn't hurt anything to leave it there
# even if there aren't any backslashes.
categories_collapsed_name_template = r'{first.sort:shorten(4,'',0)} - {last.sort:shorten(4,'',0)}'
categories_collapsed_name_template = r'{first.sort:shorten(4,"",0)} - {last.sort:shorten(4,"",0)}'
categories_collapsed_rating_template = r'{first.avg_rating:4.2f:ifempty(0)} - {last.avg_rating:4.2f:ifempty(0)}'
categories_collapsed_popularity_template = r'{first.count:d} - {last.count:d}'
#: Set boolean custom columns to be tristate
# Set whether boolean custom columns are two- or three-valued.
# Two-values for true booleans
# three-values for yes/no/unknown
# Set to 'yes' for three-values, 'no' for two-values
bool_custom_columns_are_tristate = 'yes'
#: Specify columns to sort the booklist by on startup
# Provide a set of columns to be sorted on when calibre starts
# The argument is None if saved sort history is to be used
# otherwise it is a list of column,order pairs. Column is the
@ -101,6 +105,7 @@ bool_custom_columns_are_tristate = 'yes'
# title within authors.
sort_columns_at_startup = None
#; Control how dates are displayed
# Format to be used for publication date and the timestamp (date).
# A string controlling how the publication date is displayed in the GUI
# d the day as number without a leading zero (1 to 31)
@ -121,25 +126,30 @@ sort_columns_at_startup = None
gui_pubdate_display_format = 'MMM yyyy'
gui_timestamp_display_format = 'dd MMM yyyy'
# Control title and series sorting in the library view.
# If set to 'library_order', Leading articles such as The and A will be ignored.
# If set to 'strictly_alphabetic', the titles will be sorted without processing
# For example, with library_order, The Client will sort under 'C'. With
# strictly_alphabetic, the book will sort under 'T'.
# This flag affects Calibre's library display. It has no effect on devices. In
# addition, titles for books added before changing the flag will retain their
# order until the title is edited. Double-clicking on a title and hitting return
# without changing anything is sufficient to change the sort.
#: Control how title and series names are formatted when saving to disk/sending
# to device. The behavior depends on the field being processed. If processing
# title, then if set to 'library_order', the title will be replaced with
# title_sort. If set to 'strictly_alphabetic', then the title is left unchanged.
# If processing series, then if set to 'library_order', articles such as 'The'
# and 'An' will be moved to the end. If set to 'strictly_alphabetic', the series
# will be sent without change. For example, with library_order, "The Lord of the
# Rings" will become "Lord of the Rings, The". With strictly_alphabetic, it
# would remain "The Lord of the Rings".
title_series_sorting = 'library_order'
#: Control formatting of title and series when used in templates
# Control how title and series names are formatted when saving to disk/sending
# to device. If set to library_order, leading articles such as The and A will
# be put at the end
# If set to 'strictly_alphabetic', the titles will be sorted without processing
# For example, with library_order, "The Client" will become "Client, The". With
# strictly_alphabetic, it would remain "The Client".
# to device. The behavior depends on the field being processed. If processing
# title, then if set to 'library_order', the title will be replaced with
# title_sort. If set to 'strictly_alphabetic', then the title is left unchanged.
# If processing series, then if set to 'library_order', articles such as 'The'
# and 'An' will be moved to the end. If set to 'strictly_alphabetic', the series
# will be sent without change. For example, with library_order, "The Lord of the
# Rings" will become "Lord of the Rings, The". With strictly_alphabetic, it
# would remain "The Lord of the Rings".
save_template_title_series_sorting = 'library_order'
#: Set the list of words considered to be "articles" for sort strings
# Set the list of words that are to be considered 'articles' when computing the
# title sort strings. The list is a regular expression, with the articles
# separated by 'or' bars. Comparisons are case insensitive, and that cannot be
@ -149,7 +159,7 @@ save_template_title_series_sorting = 'library_order'
# Default: '^(A|The|An)\s+'
title_sort_articles=r'^(A|The|An)\s+'
#: Specify a folder calibre should connect to at startup
# Specify a folder that calibre should connect to at startup using
# connect_to_folder. This must be a full path to the folder. If the folder does
# not exist when calibre starts, it is ignored. If there are '\' characters in
@ -159,7 +169,7 @@ title_sort_articles=r'^(A|The|An)\s+'
# auto_connect_to_folder = '/home/dropbox/My Dropbox/someone/library'
auto_connect_to_folder = ''
#: Specify renaming rules for SONY collections
# Specify renaming rules for sony collections. This tweak is only applicable if
# metadata management is set to automatic. Collections on Sonys are named
# depending upon whether the field is standard or custom. A collection derived
@ -212,7 +222,7 @@ auto_connect_to_folder = ''
sony_collection_renaming_rules={}
sony_collection_name_template='{value}{category:| (|)}'
#: Specify how SONY collections are sorted
# Specify how sony collections are sorted. This tweak is only applicable if
# metadata management is set to automatic. You can indicate which metadata is to
# be used to sort on a collection-by-collection basis. The format of the tweak
@ -231,7 +241,7 @@ sony_collection_name_template='{value}{category:| (|)}'
sony_collection_sorting_rules = []
# Create search terms to apply a query across several built-in search terms.
#: Create search terms to apply a query across several built-in search terms.
# Syntax: {'new term':['existing term 1', 'term 2', ...], 'new':['old'...] ...}
# Example: create the term 'myseries' that when used as myseries:foo would
# search all of the search categories 'series', '#myseries', and '#myseries2':
@ -244,15 +254,17 @@ sony_collection_sorting_rules = []
grouped_search_terms = {}
# Set this to True (not 'True') to ensure that tags in 'Tags to add when adding
#: Control how tags are applied when copying books to another library
# Set this to True to ensure that tags in 'Tags to add when adding
# a book' are added when copying books to another library
add_new_book_tags_when_importing_books = False
# Set the maximum number of tags to show per book in the content server
#: Set the maximum number of tags to show per book in the content server
max_content_server_tags_shown=5
# Set custom metadata fields that the content server will or will not display.
#: Set custom metadata fields that the content server will or will not display.
# content_server_will_display is a list of custom fields to be displayed.
# content_server_wont_display is a list of custom fields not to be displayed.
# wont_display has priority over will_display.
@ -270,13 +282,27 @@ max_content_server_tags_shown=5
content_server_will_display = ['*']
content_server_wont_display = []
# Same as above (content server) but for the book details pane. Same syntax.
#: Set custom metadata fields that the book details panel will or will not display.
# book_details_will_display is a list of custom fields to be displayed.
# book_details_wont_display is a list of custom fields not to be displayed.
# wont_display has priority over will_display.
# The special value '*' means all custom fields. The value [] means no entries.
# Defaults:
# book_details_will_display = ['*']
# book_details_wont_display = []
# Examples:
# To display only the custom fields #mytags and #genre:
# book_details_will_display = ['#mytags', '#genre']
# book_details_wont_display = []
# To display all fields except #mycomments:
# book_details_will_display = ['*']
# book_details_wont_display['#mycomments']
# As above, this tweak affects only display of custom fields. The standard
# fields are not affected
book_details_will_display = ['*']
book_details_wont_display = []
#: Set the maximum number of sort 'levels'
# Set the maximum number of sort 'levels' that calibre will use to resort the
# library after certain operations such as searches or device insertion. Each
# sort level adds a performance penalty. If the database is large (thousands of
@ -284,16 +310,14 @@ book_details_wont_display = []
# level sorts, and if you are seeing a slowdown, reduce the value of this tweak.
maximum_resort_levels = 5
# Absolute path to a TTF font file to use as the font for the title and author
# when generating a default cover. Useful if the default font (Liberation
#: Specify which font to use when generating a default cover
# Absolute path to .ttf font files to use as the fonts for the title, author
# and footer when generating a default cover. Useful if the default font (Liberation
# Serif) does not contain glyphs for the language of the books in your library.
generate_cover_title_font = None
# Absolute path to a TTF font file to use as the font for the footer in the
# default cover
generate_cover_foot_font = None
#: Control behavior of double clicks on the book list
# Behavior of doubleclick on the books list. Choices: open_viewer, do_nothing,
# edit_cell, edit_metadata. Selecting edit_metadata has the side effect of
# disabling editing a field using a single click.
@ -302,7 +326,8 @@ generate_cover_foot_font = None
doubleclick_on_library_view = 'open_viewer'
# Language to use when sorting. Setting this tweak will force sorting to use the
#: Language to use when sorting.
# Setting this tweak will force sorting to use the
# collating order for the specified language. This might be useful if you run
# calibre in English but want sorting to work in the language where you live.
# Set the tweak to the desired ISO 639-1 language code, in lower case.
@ -313,12 +338,13 @@ doubleclick_on_library_view = 'open_viewer'
# Example: locale_for_sorting = 'nb' -- sort using Norwegian rules.
locale_for_sorting = ''
#: Number of columns for custom metadata in the edit metadata dialog
# Set whether to use one or two columns for custom metadata when editing
# metadata one book at a time. If True, then the fields are laid out using two
# columns. If False, one column is used.
metadata_single_use_2_cols_for_custom_fields = True
#: The number of seconds to wait before sending emails
# The number of seconds to wait before sending emails when using a
# public email server like gmail or hotmail. Default is: 5 minutes
# Setting it to lower may cause the server's SPAM controls to kick in,
@ -326,3 +352,9 @@ metadata_single_use_2_cols_for_custom_fields = True
# calibre.
public_smtp_relay_delay = 301
#: Remove the bright yellow lines at the edges of the book list
# Control whether the bright yellow lines at the edges of book list are drawn
# when a section of the user interface is hidden. Changes will take effect
# after a restart of calibre.
draw_hidden_section_indicators = True

67
resources/recipes/jakarta_post.recipe Normal file
View File

@ -0,0 +1,67 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2011, Adrian Gunawan <agunawan at adrnalin.com>'
__author__ = 'Adrian Gunawan'
__version__ = 'v1.0'
__date__ = '02 February 2011'
'''
http://www.thejakartapost.com/
'''
from calibre.web.feeds.news import BasicNewsRecipe
class JakartaPost(BasicNewsRecipe):
title = u'Jakarta Post'
masthead_url = 'http://www.thejakartapost.com/images/jakartapost_logo.jpg'
cover_url = 'http://www.thejakartapost.com/images/jakartapost_logo.jpg'
__author__ = u'Adrian Gunawan'
description = u'Indonesian Newspaper in English from Jakarta Post Online Edition'
category = 'breaking news, national, business, international, Indonesia'
language = 'en_ID'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
no_javascript = True
remove_empty_feeds = True
timefmt = ' [%A, %d %B, %Y]'
encoding = 'utf-8'
keep_only_tags = [dict(name='div', attrs ={'id':'news-main'})]
extra_css = '''
h1{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large;}
.cT-storyDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.articleBody{font-family:Arial,Helvetica,sans-serif; color:black;font-size:small;}
.cT-imageLandscape{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:x-small;}
.source{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:xx-small;}
#content{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
.pageprint{font-family:Arial,Helvetica,sans-serif;font-size:small;}
#bylineDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.featurePic-wide{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
#idfeaturepic{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h2{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h4{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h5{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
'''
remove_tags = [
dict(name='div', attrs ={'class':['text-size']}),
]
feeds = [
(u'Breaking News', u'http://www.thejakartapost.com/breaking/feed'),
(u'National', u'http://www.thejakartapost.com/channel/national/feed'),
(u'Archipelago', u'http://www.thejakartapost.com/channel/archipelago/feed'),
(u'Business', u'http://www.thejakartapost.com/channel/business/feed'),
(u'Jakarta', u'http://www.thejakartapost.com/channel/jakarta/feed'),
(u'World', u'http://www.thejakartapost.com/channel/world/feed'),
(u'Sports', u'http://www.thejakartapost.com/channel/sports/feed'),
]

77
resources/recipes/kompas.recipe Normal file
View File

@ -0,0 +1,77 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2011, Adrian Gunawan <agunawan at adrnalin.com>'
__author__ = 'Adrian Gunawan'
__version__ = 'v1.0'
__date__ = '02 February 2011'
'''
http://www.kompas.com/
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Kompas(BasicNewsRecipe):
title = u'Kompas'
masthead_url = 'http://stat.k.kidsklik.com/data/2k10/kompascom2011/images/logo_kompas.png'
cover_url = 'http://stat.k.kidsklik.com/data/2k10/kompascom2011/images/logo_kompas.png'
__author__ = u'Adrian Gunawan'
description = u'Indonesian News from Kompas Online Edition'
category = 'local news, international, business, Indonesia'
language = 'id'
oldest_article = 5
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
no_javascript = True
remove_empty_feeds = True
timefmt = ' [%A, %d %B, %Y]'
encoding = 'utf-8'
keep_only_tags = [dict(name='div', attrs ={'class':'content_kiri_detail'})]
extra_css = '''
h1{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:large;}
.cT-storyDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.articleBody{font-family:Arial,Helvetica,sans-serif; color:black;font-size:small;}
.cT-imageLandscape{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:x-small;}
.source{font-family:Arial,Helvetica,sans-serif; color:#333333 ;font-size:xx-small;}
#content{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
.pageprint{font-family:Arial,Helvetica,sans-serif;font-size:small;}
#bylineDetails{font-family:Arial,Helvetica,sans-serif; color:#666666;font-size:x-small;}
.featurePic-wide{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
#idfeaturepic{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h2{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h4{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
h5{font-family:Georgia,"Times New Roman",Times,serif; font-size:small;}
body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
'''
remove_tags = [
dict(name='div', attrs ={'class':['c_biru_kompas2011', 'c_abu01_kompas2011', 'c_abu_01_kompas2011', 'right', 'clearit']}),
dict(name='div', attrs ={'id':['comment_list', 'comment_paging', 'share']}),
dict(name='form'),
dict(name='ul'),
]
preprocess_regexps = [
(re.compile(r'<!--TERKAIT -->.*<!--TERKAIT END -->', re.DOTALL|re.IGNORECASE),lambda match: ''),
(re.compile(r'<strong>Sent Using.*</body>', re.DOTALL|re.IGNORECASE),lambda match: ''),
(re.compile(r'<strong>Kirim Komentar Anda</strong>', re.DOTALL|re.IGNORECASE),lambda match: ''),
(re.compile(r'<a[^>]*>Kembali ke Index Topik Pilihan</a>', re.DOTALL|re.IGNORECASE),lambda match: ''),
]
feeds = [
(u'Nasional', u'http://www.kompas.com/getrss/nasional'),
(u'Regional', u'http://www.kompas.com/getrss/regional'),
(u'Internasional', u'http://www.kompas.com/getrss/internasional'),
(u'Megapolitan', u'http://www.kompas.com/getrss/megapolitan'),
(u'Bisnis Keuangan', u'http://www.kompas.com/getrss/bisniskeuangan'),
(u'Kesehatan', u'http://www.kompas.com/getrss/kesehatan'),
(u'Olahraga', u'http://www.kompas.com/getrss/olahraga'),
]

5
src/calibre/customize/builtins.py
View File

@ -497,7 +497,7 @@ from calibre.devices.binatone.driver import README
from calibre.devices.hanvon.driver import N516, EB511, ALEX, AZBOOKA, THEBOOK
from calibre.devices.edge.driver import EDGE
from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS, \
SOVOS, PICO, SUNSTECH_EB700, ARCHOS7O
SOVOS, PICO, SUNSTECH_EB700, ARCHOS7O, STASH
from calibre.devices.sne.driver import SNE
from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, KOGAN, \
GEMEI, VELOCITYMICRO, PDNOVEL_KOBO, Q600, LUMIREAD, ALURATEK_COLOR, \
@ -605,9 +605,8 @@ plugins += [
ELONEX,
TECLAST_K3,
NEWSMY,
PICO, SUNSTECH_EB700, ARCHOS7O,
PICO, SUNSTECH_EB700, ARCHOS7O, SOVOS, STASH,
IPAPYRUS,
SOVOS,
EDGE,
SNE,
ALEX,

2
src/calibre/devices/android/driver.py
View File

@ -83,7 +83,7 @@ class ANDROID(USBMS):
'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID',
'SCH-I500_CARD', 'SPH-D700_CARD', 'MB810', 'GT-P1000', 'DESIRE',
'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT', 'A70H',
'IDEOS_TABLET', 'MYTOUCH_4G']
'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE']
WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
'A70S', 'A101IT']

68
src/calibre/devices/kindle/apnx.py Normal file
View File

@ -0,0 +1,68 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2011, John Schember <john at nachtimwald.com>'
__docformat__ = 'restructuredtext en'
'''
Generates and writes an APNX page mapping file.
'''
import struct
import uuid
from calibre.ebooks.pdb.header import PdbHeaderReader
class APNXBuilder(object):
'''
Currently uses the Adobe 1024 byte count equal one page formula.
'''
def write_apnx(self, mobi_file_path, apnx_path):
with open(mobi_file_path, 'rb') as mf:
phead = PdbHeaderReader(mf)
r0 = phead.section_data(0)
text_length = struct.unpack('>I', r0[4:8])[0]
pages = self.get_pages(text_length)
apnx = self.generate_apnx(pages)
with open(apnx_path, 'wb') as apnxf:
apnxf.write(apnx)
def generate_apnx(self, pages):
apnx = ''
content_vals = {
'guid': str(uuid.uuid4()).replace('-', '')[:8],
'isbn': '',
}
content_header = '{"contentGuid":"%(guid)s","asin":"%(isbn)s","cdeType":"EBOK","fileRevisionId":"1"}' % content_vals
page_header = '{"asin":"%(isbn)s","pageMap":"(1,a,1)"}' % content_vals
apnx += struct.pack('>I', 65537)
apnx += struct.pack('>I', 12 + len(content_header))
apnx += struct.pack('>I', len(content_header))
apnx += content_header
apnx += struct.pack('>H', 1)
apnx += struct.pack('>H', len(page_header))
apnx += struct.pack('>H', len(pages))
apnx += struct.pack('>H', 32)
apnx += page_header
# write page values to apnx
for page in pages:
apnx += struct.pack('>L', page)
return apnx
def get_pages(self, text_length):
pages = []
count = 0
while count < text_length:
pages.append(count)
count += 1024
return pages

315
src/calibre/devices/kindle/bookmark.py Normal file
View File

@ -0,0 +1,315 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__docformat__ = 'restructuredtext en'
import os
from cStringIO import StringIO
from struct import unpack
class Bookmark(): # {{{
'''
A simple class fetching bookmark data
Kindle-specific
'''
def __init__(self, path, id, book_format, bookmark_extension):
self.book_format = book_format
self.bookmark_extension = bookmark_extension
self.book_length = 0
self.id = id
self.last_read = 0
self.last_read_location = 0
self.path = path
self.timestamp = 0
self.user_notes = None
self.get_bookmark_data()
self.get_book_length()
try:
self.percent_read = min(float(100*self.last_read / self.book_length),100)
except:
self.percent_read = 0
def record(self, n):
from calibre.ebooks.metadata.mobi import StreamSlicer
if n >= self.nrecs:
raise ValueError('non-existent record %r' % n)
offoff = 78 + (8 * n)
start, = unpack('>I', self.data[offoff + 0:offoff + 4])
stop = None
if n < (self.nrecs - 1):
stop, = unpack('>I', self.data[offoff + 8:offoff + 12])
return StreamSlicer(self.stream, start, stop)
def get_bookmark_data(self):
''' Return the timestamp and last_read_location '''
from calibre.ebooks.metadata.mobi import StreamSlicer
user_notes = {}
if self.bookmark_extension == 'mbp':
MAGIC_MOBI_CONSTANT = 150
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.timestamp, = unpack('>I', data[0x24:0x28])
bpar_offset, = unpack('>I', data[0x4e:0x52])
lrlo = bpar_offset + 0x0c
self.last_read = int(unpack('>I', data[lrlo:lrlo+4])[0])
self.last_read_location = self.last_read/MAGIC_MOBI_CONSTANT + 1
entries, = unpack('>I', data[0x4a:0x4e])
# Store the annotations/locations
bpl = bpar_offset + 4
bpar_len, = unpack('>I', data[bpl:bpl+4])
bpar_len += 8
#print "bpar_len: 0x%x" % bpar_len
eo = bpar_offset + bpar_len
# Walk bookmark entries
#print " --- %s --- " % self.path
current_entry = 1
sig = data[eo:eo+4]
previous_block = None
while sig == 'DATA':
text = None
entry_type = None
rec_len, = unpack('>I', data[eo+4:eo+8])
if rec_len == 0:
current_block = "empty_data"
elif data[eo+8:eo+12] == "EBAR":
current_block = "data_header"
#entry_type = "data_header"
location, = unpack('>I', data[eo+0x34:eo+0x38])
#print "data_header location: %d" % location
else:
current_block = "text_block"
if previous_block == 'empty_data':
entry_type = 'Note'
elif previous_block == 'data_header':
entry_type = 'Highlight'
text = data[eo+8:eo+8+rec_len].decode('utf-16-be')
if entry_type:
displayed_location = location/MAGIC_MOBI_CONSTANT + 1
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=entry_type,
text=text)
eo += rec_len + 8
current_entry += 1
previous_block = current_block
sig = data[eo:eo+4]
while sig == 'BKMK':
# Fix start location for Highlights using BKMK data
end_loc, = unpack('>I', data[eo+0x10:eo+0x14])
if end_loc in user_notes and \
(user_notes[end_loc]['type'] == 'Highlight' or \
user_notes[end_loc]['type'] == 'Note'):
# Switch location to start (0x08:0x0c)
start, = unpack('>I', data[eo+8:eo+12])
user_notes[start] = user_notes[end_loc]
'''
print " %s: swapping 0x%x (%d) to 0x%x (%d)" % (user_notes[end_loc]['type'],
end_loc,
end_loc/MAGIC_MOBI_CONSTANT + 1,
start,
start//MAGIC_MOBI_CONSTANT + 1)
'''
user_notes[start]['displayed_location'] = start/MAGIC_MOBI_CONSTANT + 1
user_notes.pop(end_loc)
else:
# If a bookmark coincides with a user annotation, the locs could
# be the same - cheat by nudging -1
# Skip bookmark for last_read_location
if end_loc != self.last_read:
# print " adding Bookmark at 0x%x (%d)" % (end_loc, end_loc/MAGIC_MOBI_CONSTANT + 1)
displayed_location = end_loc/MAGIC_MOBI_CONSTANT + 1
user_notes[end_loc - 1] = dict(id=self.id,
displayed_location=displayed_location,
type='Bookmark',
text=None)
rec_len, = unpack('>I', data[eo+4:eo+8])
eo += rec_len + 8
sig = data[eo:eo+4]
elif self.bookmark_extension == 'tan':
from calibre.ebooks.metadata.topaz import get_metadata as get_topaz_metadata
def get_topaz_highlight(displayed_location):
# Parse My Clippings.txt for a matching highlight
# Search looks for book title match, highlight match, and location match
# Author is not matched
# This will find the first instance of a clipping only
book_fs = self.path.replace('.%s' % self.bookmark_extension,'.%s' % self.book_format)
with open(book_fs,'rb') as f2:
stream = StringIO(f2.read())
mi = get_topaz_metadata(stream)
my_clippings = self.path
split = my_clippings.find('documents') + len('documents/')
my_clippings = my_clippings[:split] + "My Clippings.txt"
try:
with open(my_clippings, 'r') as f2:
marker_found = 0
text = ''
search_str1 = '%s' % (mi.title)
search_str2 = '- Highlight Loc. %d' % (displayed_location)
for line in f2:
if marker_found == 0:
if line.startswith(search_str1):
marker_found = 1
elif marker_found == 1:
if line.startswith(search_str2):
marker_found = 2
elif marker_found == 2:
if line.startswith('=========='):
break
text += line.strip()
else:
raise Exception('error')
except:
text = '(Unable to extract highlight text from My Clippings.txt)'
return text
MAGIC_TOPAZ_CONSTANT = 33.33
self.timestamp = os.path.getmtime(self.path)
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.last_read = int(unpack('>I', data[5:9])[0])
self.last_read_location = self.last_read/MAGIC_TOPAZ_CONSTANT + 1
entries, = unpack('>I', data[9:13])
current_entry = 0
e_base = 0x0d
while current_entry < entries:
location, = unpack('>I', data[e_base+2:e_base+6])
text = None
text_len, = unpack('>I', data[e_base+0xA:e_base+0xE])
e_type, = unpack('>B', data[e_base+1])
if e_type == 0:
e_type = 'Bookmark'
elif e_type == 1:
e_type = 'Highlight'
text = get_topaz_highlight(location/MAGIC_TOPAZ_CONSTANT + 1)
elif e_type == 2:
e_type = 'Note'
text = data[e_base+0x10:e_base+0x10+text_len]
else:
e_type = 'Unknown annotation type'
displayed_location = location/MAGIC_TOPAZ_CONSTANT + 1
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
if text_len == 0xFFFFFFFF:
e_base = e_base + 14
else:
e_base = e_base + 14 + 2 + text_len
current_entry += 1
for location in user_notes:
if location == self.last_read:
user_notes.pop(location)
break
elif self.bookmark_extension == 'pdr':
self.timestamp = os.path.getmtime(self.path)
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.last_read = int(unpack('>I', data[5:9])[0])
entries, = unpack('>I', data[9:13])
current_entry = 0
e_base = 0x0d
self.pdf_page_offset = 0
while current_entry < entries:
'''
location, = unpack('>I', data[e_base+2:e_base+6])
text = None
text_len, = unpack('>I', data[e_base+0xA:e_base+0xE])
e_type, = unpack('>B', data[e_base+1])
if e_type == 0:
e_type = 'Bookmark'
elif e_type == 1:
e_type = 'Highlight'
text = get_topaz_highlight(location/MAGIC_TOPAZ_CONSTANT + 1)
elif e_type == 2:
e_type = 'Note'
text = data[e_base+0x10:e_base+0x10+text_len]
else:
e_type = 'Unknown annotation type'
if self.book_format in ['tpz','azw1']:
displayed_location = location/MAGIC_TOPAZ_CONSTANT + 1
elif self.book_format == 'pdf':
# *** This needs implementation
displayed_location = location
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
if text_len == 0xFFFFFFFF:
e_base = e_base + 14
else:
e_base = e_base + 14 + 2 + text_len
current_entry += 1
'''
# Use label as page number
pdf_location, = unpack('>I', data[e_base+1:e_base+5])
label_len, = unpack('>H', data[e_base+5:e_base+7])
location = int(data[e_base+7:e_base+7+label_len])
displayed_location = location
e_type = 'Bookmark'
text = None
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
self.pdf_page_offset = pdf_location - location
e_base += (7 + label_len)
current_entry += 1
self.last_read_location = self.last_read - self.pdf_page_offset
else:
print "unsupported bookmark_extension: %s" % self.bookmark_extension
self.user_notes = user_notes
def get_book_length(self):
from calibre.ebooks.metadata.mobi import StreamSlicer
book_fs = self.path.replace('.%s' % self.bookmark_extension,'.%s' % self.book_format)
self.book_length = 0
if self.bookmark_extension == 'mbp':
# Read the book len from the header
try:
with open(book_fs,'rb') as f:
self.stream = StringIO(f.read())
self.data = StreamSlicer(self.stream)
self.nrecs, = unpack('>H', self.data[76:78])
record0 = self.record(0)
self.book_length = int(unpack('>I', record0[0x04:0x08])[0])
except:
pass
elif self.bookmark_extension == 'tan':
# Read bookLength from metadata
from calibre.ebooks.metadata.topaz import MetadataUpdater
try:
with open(book_fs,'rb') as f:
mu = MetadataUpdater(f)
self.book_length = mu.book_length
except:
pass
elif self.bookmark_extension == 'pdr':
from calibre import plugins
try:
self.book_length = plugins['pdfreflow'][0].get_numpages(open(book_fs).read())
except:
pass
else:
print "unsupported bookmark_extension: %s" % self.bookmark_extension
# }}}

333
src/calibre/devices/kindle/driver.py
View File

@ -7,10 +7,11 @@ __docformat__ = 'restructuredtext en'
'''
Device driver for Amazon's Kindle
'''
import datetime, os, re, sys, json, hashlib
from cStringIO import StringIO
from struct import unpack
import datetime, os, re, sys, json, hashlib
from calibre.devices.kindle.apnx import APNXBuilder
from calibre.devices.kindle.bookmark import Bookmark
from calibre.devices.usbms.driver import USBMS
'''
@ -170,6 +171,8 @@ class KINDLE2(KINDLE):
description = _('Communicate with the Kindle 2/3 eBook reader.')
FORMATS = KINDLE.FORMATS + ['pdf']
DELETE_EXTS = KINDLE.DELETE_EXTS + ['.apnx']
PRODUCT_ID = [0x0002, 0x0004]
BCD = [0x0100]
@ -205,6 +208,23 @@ class KINDLE2(KINDLE):
if h in path_map:
book.device_collections = list(sorted(path_map[h]))
def upload_cover(self, path, filename, metadata, filepath):
'''
Hijacking this function to write the apnx file.
'''
if not filepath.lower().endswith('.mobi'):
return
apnx_path = '%s.apnx' % os.path.join(path, filename)
apnx_builder = APNXBuilder()
try:
apnx_builder.write_apnx(filepath, apnx_path)
except:
print 'Failed to generate APNX'
import traceback
traceback.print_exc()
class KINDLE_DX(KINDLE2):
name = 'Kindle DX Device Interface'
@ -214,310 +234,3 @@ class KINDLE_DX(KINDLE2):
PRODUCT_ID = [0x0003]
BCD = [0x0100]
class Bookmark(): # {{{
'''
A simple class fetching bookmark data
Kindle-specific
'''
def __init__(self, path, id, book_format, bookmark_extension):
self.book_format = book_format
self.bookmark_extension = bookmark_extension
self.book_length = 0
self.id = id
self.last_read = 0
self.last_read_location = 0
self.path = path
self.timestamp = 0
self.user_notes = None
self.get_bookmark_data()
self.get_book_length()
try:
self.percent_read = min(float(100*self.last_read / self.book_length),100)
except:
self.percent_read = 0
def record(self, n):
from calibre.ebooks.metadata.mobi import StreamSlicer
if n >= self.nrecs:
raise ValueError('non-existent record %r' % n)
offoff = 78 + (8 * n)
start, = unpack('>I', self.data[offoff + 0:offoff + 4])
stop = None
if n < (self.nrecs - 1):
stop, = unpack('>I', self.data[offoff + 8:offoff + 12])
return StreamSlicer(self.stream, start, stop)
def get_bookmark_data(self):
''' Return the timestamp and last_read_location '''
from calibre.ebooks.metadata.mobi import StreamSlicer
user_notes = {}
if self.bookmark_extension == 'mbp':
MAGIC_MOBI_CONSTANT = 150
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.timestamp, = unpack('>I', data[0x24:0x28])
bpar_offset, = unpack('>I', data[0x4e:0x52])
lrlo = bpar_offset + 0x0c
self.last_read = int(unpack('>I', data[lrlo:lrlo+4])[0])
self.last_read_location = self.last_read/MAGIC_MOBI_CONSTANT + 1
entries, = unpack('>I', data[0x4a:0x4e])
# Store the annotations/locations
bpl = bpar_offset + 4
bpar_len, = unpack('>I', data[bpl:bpl+4])
bpar_len += 8
#print "bpar_len: 0x%x" % bpar_len
eo = bpar_offset + bpar_len
# Walk bookmark entries
#print " --- %s --- " % self.path
current_entry = 1
sig = data[eo:eo+4]
previous_block = None
while sig == 'DATA':
text = None
entry_type = None
rec_len, = unpack('>I', data[eo+4:eo+8])
if rec_len == 0:
current_block = "empty_data"
elif data[eo+8:eo+12] == "EBAR":
current_block = "data_header"
#entry_type = "data_header"
location, = unpack('>I', data[eo+0x34:eo+0x38])
#print "data_header location: %d" % location
else:
current_block = "text_block"
if previous_block == 'empty_data':
entry_type = 'Note'
elif previous_block == 'data_header':
entry_type = 'Highlight'
text = data[eo+8:eo+8+rec_len].decode('utf-16-be')
if entry_type:
displayed_location = location/MAGIC_MOBI_CONSTANT + 1
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=entry_type,
text=text)
eo += rec_len + 8
current_entry += 1
previous_block = current_block
sig = data[eo:eo+4]
while sig == 'BKMK':
# Fix start location for Highlights using BKMK data
end_loc, = unpack('>I', data[eo+0x10:eo+0x14])
if end_loc in user_notes and \
(user_notes[end_loc]['type'] == 'Highlight' or \
user_notes[end_loc]['type'] == 'Note'):
# Switch location to start (0x08:0x0c)
start, = unpack('>I', data[eo+8:eo+12])
user_notes[start] = user_notes[end_loc]
'''
print " %s: swapping 0x%x (%d) to 0x%x (%d)" % (user_notes[end_loc]['type'],
end_loc,
end_loc/MAGIC_MOBI_CONSTANT + 1,
start,
start//MAGIC_MOBI_CONSTANT + 1)
'''
user_notes[start]['displayed_location'] = start/MAGIC_MOBI_CONSTANT + 1
user_notes.pop(end_loc)
else:
# If a bookmark coincides with a user annotation, the locs could
# be the same - cheat by nudging -1
# Skip bookmark for last_read_location
if end_loc != self.last_read:
# print " adding Bookmark at 0x%x (%d)" % (end_loc, end_loc/MAGIC_MOBI_CONSTANT + 1)
displayed_location = end_loc/MAGIC_MOBI_CONSTANT + 1
user_notes[end_loc - 1] = dict(id=self.id,
displayed_location=displayed_location,
type='Bookmark',
text=None)
rec_len, = unpack('>I', data[eo+4:eo+8])
eo += rec_len + 8
sig = data[eo:eo+4]
elif self.bookmark_extension == 'tan':
from calibre.ebooks.metadata.topaz import get_metadata as get_topaz_metadata
def get_topaz_highlight(displayed_location):
# Parse My Clippings.txt for a matching highlight
# Search looks for book title match, highlight match, and location match
# Author is not matched
# This will find the first instance of a clipping only
book_fs = self.path.replace('.%s' % self.bookmark_extension,'.%s' % self.book_format)
with open(book_fs,'rb') as f2:
stream = StringIO(f2.read())
mi = get_topaz_metadata(stream)
my_clippings = self.path
split = my_clippings.find('documents') + len('documents/')
my_clippings = my_clippings[:split] + "My Clippings.txt"
try:
with open(my_clippings, 'r') as f2:
marker_found = 0
text = ''
search_str1 = '%s' % (mi.title)
search_str2 = '- Highlight Loc. %d' % (displayed_location)
for line in f2:
if marker_found == 0:
if line.startswith(search_str1):
marker_found = 1
elif marker_found == 1:
if line.startswith(search_str2):
marker_found = 2
elif marker_found == 2:
if line.startswith('=========='):
break
text += line.strip()
else:
raise Exception('error')
except:
text = '(Unable to extract highlight text from My Clippings.txt)'
return text
MAGIC_TOPAZ_CONSTANT = 33.33
self.timestamp = os.path.getmtime(self.path)
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.last_read = int(unpack('>I', data[5:9])[0])
self.last_read_location = self.last_read/MAGIC_TOPAZ_CONSTANT + 1
entries, = unpack('>I', data[9:13])
current_entry = 0
e_base = 0x0d
while current_entry < entries:
location, = unpack('>I', data[e_base+2:e_base+6])
text = None
text_len, = unpack('>I', data[e_base+0xA:e_base+0xE])
e_type, = unpack('>B', data[e_base+1])
if e_type == 0:
e_type = 'Bookmark'
elif e_type == 1:
e_type = 'Highlight'
text = get_topaz_highlight(location/MAGIC_TOPAZ_CONSTANT + 1)
elif e_type == 2:
e_type = 'Note'
text = data[e_base+0x10:e_base+0x10+text_len]
else:
e_type = 'Unknown annotation type'
displayed_location = location/MAGIC_TOPAZ_CONSTANT + 1
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
if text_len == 0xFFFFFFFF:
e_base = e_base + 14
else:
e_base = e_base + 14 + 2 + text_len
current_entry += 1
for location in user_notes:
if location == self.last_read:
user_notes.pop(location)
break
elif self.bookmark_extension == 'pdr':
self.timestamp = os.path.getmtime(self.path)
with open(self.path,'rb') as f:
stream = StringIO(f.read())
data = StreamSlicer(stream)
self.last_read = int(unpack('>I', data[5:9])[0])
entries, = unpack('>I', data[9:13])
current_entry = 0
e_base = 0x0d
self.pdf_page_offset = 0
while current_entry < entries:
'''
location, = unpack('>I', data[e_base+2:e_base+6])
text = None
text_len, = unpack('>I', data[e_base+0xA:e_base+0xE])
e_type, = unpack('>B', data[e_base+1])
if e_type == 0:
e_type = 'Bookmark'
elif e_type == 1:
e_type = 'Highlight'
text = get_topaz_highlight(location/MAGIC_TOPAZ_CONSTANT + 1)
elif e_type == 2:
e_type = 'Note'
text = data[e_base+0x10:e_base+0x10+text_len]
else:
e_type = 'Unknown annotation type'
if self.book_format in ['tpz','azw1']:
displayed_location = location/MAGIC_TOPAZ_CONSTANT + 1
elif self.book_format == 'pdf':
# *** This needs implementation
displayed_location = location
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
if text_len == 0xFFFFFFFF:
e_base = e_base + 14
else:
e_base = e_base + 14 + 2 + text_len
current_entry += 1
'''
# Use label as page number
pdf_location, = unpack('>I', data[e_base+1:e_base+5])
label_len, = unpack('>H', data[e_base+5:e_base+7])
location = int(data[e_base+7:e_base+7+label_len])
displayed_location = location
e_type = 'Bookmark'
text = None
user_notes[location] = dict(id=self.id,
displayed_location=displayed_location,
type=e_type,
text=text)
self.pdf_page_offset = pdf_location - location
e_base += (7 + label_len)
current_entry += 1
self.last_read_location = self.last_read - self.pdf_page_offset
else:
print "unsupported bookmark_extension: %s" % self.bookmark_extension
self.user_notes = user_notes
def get_book_length(self):
from calibre.ebooks.metadata.mobi import StreamSlicer
book_fs = self.path.replace('.%s' % self.bookmark_extension,'.%s' % self.book_format)
self.book_length = 0
if self.bookmark_extension == 'mbp':
# Read the book len from the header
try:
with open(book_fs,'rb') as f:
self.stream = StringIO(f.read())
self.data = StreamSlicer(self.stream)
self.nrecs, = unpack('>H', self.data[76:78])
record0 = self.record(0)
self.book_length = int(unpack('>I', record0[0x04:0x08])[0])
except:
pass
elif self.bookmark_extension == 'tan':
# Read bookLength from metadata
from calibre.ebooks.metadata.topaz import MetadataUpdater
try:
with open(book_fs,'rb') as f:
mu = MetadataUpdater(f)
self.book_length = mu.book_length
except:
pass
elif self.bookmark_extension == 'pdr':
from calibre import plugins
try:
self.book_length = plugins['pdfreflow'][0].get_numpages(open(book_fs).read())
except:
pass
else:
print "unsupported bookmark_extension: %s" % self.bookmark_extension
# }}}

12
src/calibre/devices/teclast/driver.py
View File

@ -92,3 +92,15 @@ class SUNSTECH_EB700(TECLAST_K3):
VENDOR_NAME = 'SUNEB700'
WINDOWS_MAIN_MEM = 'USB-MSC'
class STASH(TECLAST_K3):
name = 'Stash device interface'
gui_name = 'Stash'
description = _('Communicate with the Stash W950 reader.')
FORMATS = ['epub', 'fb2', 'lrc', 'pdb', 'html', 'fb2', 'wtxt',
'txt', 'pdf']
VENDOR_NAME = 'STASH'
WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'W950'

6
src/calibre/ebooks/conversion/utils.py
View File

@ -342,11 +342,9 @@ class HeuristicProcessor(object):
return content
def txt_process(self, match):
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
separate_paragraphs_single_line
from calibre.ebooks.txt.processor import convert_basic, separate_paragraphs_single_line
content = match.group('text')
content = separate_paragraphs_single_line(content)
content = preserve_spaces(content)
content = convert_basic(content, epub_split_size_kb=0)
return content
@ -356,6 +354,8 @@ class HeuristicProcessor(object):
self.log.debug("Running Text Processing")
outerhtml = re.compile(r'.*?(?<=<pre>)(?P<text>.*?)</pre>', re.IGNORECASE|re.DOTALL)
html = outerhtml.sub(self.txt_process, html)
from calibre.ebooks.conversion.preprocess import convert_entities
html = re.sub(r'&(\S+?);', convert_entities, html)
else:
# Add markup naively
# TODO - find out if there are cases where there are more than one <pre> tag or

21
src/calibre/ebooks/epub/output.py
View File

@ -216,21 +216,22 @@ class EPUBOutput(OutputFormatPlugin):
encryption = self.encrypt_fonts(encrypted_fonts, tdir, uuid)
from calibre.ebooks.epub import initialize_container
epub = initialize_container(output_path, os.path.basename(opf),
extra_entries=extra_entries)
epub.add_dir(tdir)
if encryption is not None:
epub.writestr('META-INF/encryption.xml', encryption)
if metadata_xml is not None:
epub.writestr('META-INF/metadata.xml',
metadata_xml.encode('utf-8'))
with initialize_container(output_path, os.path.basename(opf),
extra_entries=extra_entries) as epub:
epub.add_dir(tdir)
if encryption is not None:
epub.writestr('META-INF/encryption.xml', encryption)
if metadata_xml is not None:
epub.writestr('META-INF/metadata.xml',
metadata_xml.encode('utf-8'))
if opts.extract_to is not None:
from calibre.utils.zipfile import ZipFile
if os.path.exists(opts.extract_to):
shutil.rmtree(opts.extract_to)
os.mkdir(opts.extract_to)
epub.extractall(path=opts.extract_to)
with ZipFile(output_path) as zf:
zf.extractall(path=opts.extract_to)
self.log.info('EPUB extracted to', opts.extract_to)
epub.close()
def encrypt_fonts(self, uris, tdir, uuid): # {{{
from binascii import unhexlify

3
src/calibre/ebooks/lit/input.py
View File

@ -37,13 +37,12 @@ class LITInput(InputFormatPlugin):
body = body[0]
if len(body) == 1 and body[0].tag == XHTML('pre'):
pre = body[0]
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
from calibre.ebooks.txt.processor import convert_basic, \
separate_paragraphs_single_line
from calibre.ebooks.chardet import xml_to_unicode
from lxml import etree
import copy
html = separate_paragraphs_single_line(pre.text)
html = preserve_spaces(html)
html = convert_basic(html).replace('<html>',
'<html xmlns="%s">'%XHTML_NS)
html = xml_to_unicode(html, strip_encoding_pats=True,

16
src/calibre/gui2/actions/choose_library.py
View File

@ -237,6 +237,7 @@ class ChooseLibraryAction(InterfaceAction):
return
self.stats.rename(location, newloc)
self.build_menus()
self.gui.iactions['Copy To Library'].build_menus()
def delete_requested(self, name, location):
loc = location.replace('/', os.sep)
@ -253,6 +254,7 @@ class ChooseLibraryAction(InterfaceAction):
pass
self.stats.remove(location)
self.build_menus()
self.gui.iactions['Copy To Library'].build_menus()
def backup_status(self, location):
dirty_text = 'no'
@ -329,6 +331,7 @@ class ChooseLibraryAction(InterfaceAction):
' libraries.')%loc, show=True)
self.stats.remove(location)
self.build_menus()
self.gui.iactions['Copy To Library'].build_menus()
return
prefs['library_path'] = loc
@ -371,9 +374,20 @@ class ChooseLibraryAction(InterfaceAction):
if not self.change_library_allowed():
return
from calibre.gui2.dialogs.choose_library import ChooseLibrary
self.gui.library_view.save_state()
db = self.gui.library_view.model().db
c = ChooseLibrary(db, self.gui.library_moved, self.gui)
location = self.stats.canonicalize_path(db.library_path)
self.pre_choose_dialog_location = location
c = ChooseLibrary(db, self.choose_library_callback, self.gui)
c.exec_()
self.choose_dialog_library_renamed = getattr(c, 'library_renamed', False)
def choose_library_callback(self, newloc, copy_structure=False):
self.gui.library_moved(newloc, copy_structure=copy_structure)
if getattr(self, 'choose_dialog_library_renamed', False):
self.stats.rename(self.pre_choose_dialog_location, prefs['library_path'])
self.build_menus()
self.gui.iactions['Copy To Library'].build_menus()
def change_library_allowed(self):
if os.environ.get('CALIBRE_OVERRIDE_DATABASE_PATH', None):

2
src/calibre/gui2/dialogs/choose_library.py
View File

@ -71,6 +71,8 @@ class ChooseLibrary(QDialog, Ui_Dialog):
prefs['library_path'] = loc
self.callback(loc, copy_structure=self.copy_structure.isChecked())
else:
self.db.prefs.disable_setting = True
self.library_renamed = True
move_library(self.db.library_path, loc, self.parent(),
self.callback)

297
src/calibre/gui2/preferences/tweaks.py
View File

@ -5,37 +5,312 @@ __license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import textwrap
from calibre.gui2.preferences import ConfigWidgetBase, test_widget, AbortCommit
from calibre.gui2.preferences.tweaks_ui import Ui_Form
from calibre.gui2 import error_dialog
from calibre.gui2 import error_dialog, NONE
from calibre.utils.config import read_raw_tweaks, write_tweaks
from calibre.gui2.widgets import PythonHighlighter
from calibre import isbytestring
from PyQt4.Qt import QAbstractListModel, Qt, QStyledItemDelegate, QStyle, \
QStyleOptionViewItem, QFont, QDialogButtonBox, QDialog, \
QVBoxLayout, QPlainTextEdit, QLabel
class Delegate(QStyledItemDelegate): # {{{
def __init__(self, view):
QStyledItemDelegate.__init__(self, view)
self.view = view
def paint(self, p, opt, idx):
copy = QStyleOptionViewItem(opt)
copy.showDecorationSelected = True
if self.view.currentIndex() == idx:
copy.state |= QStyle.State_HasFocus
QStyledItemDelegate.paint(self, p, copy, idx)
# }}}
class Tweak(object): # {{{
def __init__(self, name, doc, var_names, defaults, custom):
self.name = name
self.doc = doc.strip()
self.var_names = var_names
self.default_values = {}
for x in var_names:
self.default_values[x] = defaults[x]
self.custom_values = {}
for x in var_names:
if x in custom:
self.custom_values[x] = custom[x]
def __str__(self):
ans = ['#: ' + self.name]
for line in self.doc.splitlines():
if line:
ans.append('# ' + line)
for key, val in self.default_values.iteritems():
val = self.custom_values.get(key, val)
ans.append('%s = %r'%(key, val))
ans = '\n'.join(ans)
if isinstance(ans, unicode):
ans = ans.encode('utf-8')
return ans
def __cmp__(self, other):
return cmp(self.is_customized, getattr(other, 'is_customized', False))
@property
def is_customized(self):
for x, val in self.default_values.iteritems():
if self.custom_values.get(x, val) != val:
return True
return False
@property
def edit_text(self):
ans = ['# %s'%self.name]
for x, val in self.default_values.iteritems():
val = self.custom_values.get(x, val)
ans.append('%s = %r'%(x, val))
return '\n\n'.join(ans)
def restore_to_default(self):
self.custom_values.clear()
def update(self, varmap):
self.custom_values.update(varmap)
# }}}
class Tweaks(QAbstractListModel): # {{{
def __init__(self, parent=None):
QAbstractListModel.__init__(self, parent)
raw_defaults, raw_custom = read_raw_tweaks()
self.parse_tweaks(raw_defaults, raw_custom)
def rowCount(self, *args):
return len(self.tweaks)
def data(self, index, role):
row = index.row()
try:
tweak = self.tweaks[row]
except:
return NONE
if role == Qt.DisplayRole:
return textwrap.fill(tweak.name, 40)
if role == Qt.FontRole and tweak.is_customized:
ans = QFont()
ans.setBold(True)
return ans
if role == Qt.ToolTipRole:
tt = _('This tweak has it default value')
if tweak.is_customized:
tt = _('This tweak has been customized')
return tt
if role == Qt.UserRole:
return tweak
return NONE
def parse_tweaks(self, defaults, custom):
l, g = {}, {}
try:
exec custom in g, l
except:
print 'Failed to load custom tweaks file'
import traceback
traceback.print_exc()
dl, dg = {}, {}
exec defaults in dg, dl
lines = defaults.splitlines()
pos = 0
self.tweaks = []
while pos < len(lines):
line = lines[pos]
if line.startswith('#:'):
pos = self.read_tweak(lines, pos, dl, l)
pos += 1
default_keys = set(dl.iterkeys())
custom_keys = set(l.iterkeys())
self.plugin_tweaks = {}
for key in custom_keys - default_keys:
self.plugin_tweaks[key] = l[key]
def read_tweak(self, lines, pos, defaults, custom):
name = lines[pos][2:].strip()
doc, var_names = [], []
while True:
pos += 1
line = lines[pos]
if not line.startswith('#'):
break
doc.append(line[1:].strip())
doc = '\n'.join(doc)
while True:
line = lines[pos]
if not line.strip():
break
spidx1 = line.find(' ')
spidx2 = line.find('=')
spidx = spidx1 if spidx1 > 0 and (spidx2 == 0 or spidx2 > spidx1) else spidx2
if spidx > 0:
var = line[:spidx]
if var not in defaults:
raise ValueError('%r not in default tweaks dict'%var)
var_names.append(var)
pos += 1
if not var_names:
raise ValueError('Failed to find any variables for %r'%name)
self.tweaks.append(Tweak(name, doc, var_names, defaults, custom))
#print '\n\n', self.tweaks[-1]
return pos
def restore_to_default(self, idx):
tweak = self.data(idx, Qt.UserRole)
if tweak is not NONE:
tweak.restore_to_default()
self.dataChanged.emit(idx, idx)
def restore_to_defaults(self):
for r in range(self.rowCount()):
self.restore_to_default(self.index(r))
def update_tweak(self, idx, varmap):
tweak = self.data(idx, Qt.UserRole)
if tweak is not NONE:
tweak.update(varmap)
self.dataChanged.emit(idx, idx)
def to_string(self):
ans = ['#!/usr/bin/env python',
'# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai', '',
'# This file was automatically generated by calibre, do not'
' edit it unless you know what you are doing.', '',
]
for tweak in self.tweaks:
ans.extend(['', str(tweak), ''])
if self.plugin_tweaks:
ans.extend(['', '',
'# The following are tweaks for installed plugins', ''])
for key, val in self.plugin_tweaks.iteritems():
ans.extend(['%s = %r'%(key, val), '', ''])
return '\n'.join(ans)
@property
def plugin_tweaks_string(self):
ans = []
for key, val in self.plugin_tweaks.iteritems():
ans.extend(['%s = %r'%(key, val), '', ''])
ans = '\n'.join(ans)
if isbytestring(ans):
ans = ans.decode('utf-8')
return ans
def set_plugin_tweaks(self, d):
self.plugin_tweaks = d
# }}}
class PluginTweaks(QDialog): # {{{
def __init__(self, raw, parent=None):
QDialog.__init__(self, parent)
self.edit = QPlainTextEdit(self)
self.highlighter = PythonHighlighter(self.edit.document())
self.l = QVBoxLayout()
self.setLayout(self.l)
self.l.addWidget(QLabel(
_('Add/edit tweaks for any custom plugins you have installed.')))
self.l.addWidget(self.edit)
self.edit.setPlainText(raw)
self.bb = QDialogButtonBox(QDialogButtonBox.Ok|QDialogButtonBox.Cancel,
Qt.Horizontal, self)
self.bb.accepted.connect(self.accept)
self.bb.rejected.connect(self.reject)
self.l.addWidget(self.bb)
self.resize(550, 300)
# }}}
class ConfigWidget(ConfigWidgetBase, Ui_Form):
def genesis(self, gui):
self.gui = gui
self.current_tweaks.textChanged.connect(self.changed)
self.delegate = Delegate(self.tweaks_view)
self.tweaks_view.setItemDelegate(self.delegate)
self.tweaks_view.currentChanged = self.current_changed
self.highlighter = PythonHighlighter(self.edit_tweak.document())
self.restore_default_button.clicked.connect(self.restore_to_default)
self.apply_button.clicked.connect(self.apply_tweak)
self.plugin_tweaks_button.clicked.connect(self.plugin_tweaks)
def plugin_tweaks(self):
raw = self.tweaks.plugin_tweaks_string
d = PluginTweaks(raw, self)
if d.exec_() == d.Accepted:
g, l = {}, {}
try:
exec unicode(d.edit.toPlainText()) in g, l
except:
import traceback
return error_dialog(self, _('Failed'),
_('There was a syntax error in your tweak. Click '
'the show details button for details.'), show=True,
det_msg=traceback.format_exc())
self.tweaks.set_plugin_tweaks(l)
self.changed()
def current_changed(self, current, previous):
tweak = self.tweaks.data(current, Qt.UserRole)
self.help.setPlainText(tweak.doc)
self.edit_tweak.setPlainText(tweak.edit_text)
def changed(self, *args):
self.changed_signal.emit()
def initialize(self):
deft, curt = read_raw_tweaks()
self.current_tweaks.blockSignals(True)
self.current_tweaks.setPlainText(curt.decode('utf-8'))
self.current_tweaks.blockSignals(False)
self.tweaks = Tweaks()
self.tweaks_view.setModel(self.tweaks)
self.default_tweaks.setPlainText(deft.decode('utf-8'))
def restore_to_default(self, *args):
idx = self.tweaks_view.currentIndex()
if idx.isValid():
self.tweaks.restore_to_default(idx)
tweak = self.tweaks.data(idx, Qt.UserRole)
self.edit_tweak.setPlainText(tweak.edit_text)
self.changed()
def restore_defaults(self):
ConfigWidgetBase.restore_defaults(self)
deft, curt = read_raw_tweaks()
self.current_tweaks.setPlainText(deft.decode('utf-8'))
self.tweaks.restore_to_defaults()
self.changed()
def apply_tweak(self):
idx = self.tweaks_view.currentIndex()
if idx.isValid():
l, g = {}, {}
try:
exec unicode(self.edit_tweak.toPlainText()) in g, l
except:
import traceback
error_dialog(self.gui, _('Failed'),
_('There was a syntax error in your tweak. Click '
'the show details button for details.'),
det_msg=traceback.format_exc(), show=True)
return
self.tweaks.update_tweak(idx, l)
self.changed()
def commit(self):
raw = unicode(self.current_tweaks.toPlainText()).encode('utf-8')
raw = self.tweaks.to_string()
try:
exec raw
except:
@ -54,5 +329,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
if __name__ == '__main__':
from PyQt4.Qt import QApplication
app = QApplication([])
#Tweaks()
#test_widget
test_widget('Advanced', 'Tweaks')

112
src/calibre/gui2/preferences/tweaks.ui
View File

@ -7,31 +7,73 @@
<x>0</x>
<y>0</y>
<width>660</width>
<height>351</height>
<height>531</height>
</rect>
</property>
<property name="windowTitle">
<string>Form</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout">
<item>
<widget class="QLabel" name="label_18">
<property name="text">
<string>Values for the tweaks are shown below. Edit them to change the behavior of calibre. Your changes will only take effect after a restart of calibre.</string>
</property>
<property name="wordWrap">
<bool>true</bool>
</property>
</widget>
<layout class="QGridLayout" name="gridLayout_2">
<item row="0" column="0" rowspan="2">
<layout class="QVBoxLayout" name="verticalLayout_2">
<item>
<widget class="QLabel" name="label_18">
<property name="text">
<string>Values for the tweaks are shown below. Edit them to change the behavior of calibre. Your changes will only take effect &lt;b&gt;after a restart&lt;/b&gt; of calibre.</string>
</property>
<property name="wordWrap">
<bool>true</bool>
</property>
</widget>
</item>
<item>
<widget class="QListView" name="tweaks_view">
<property name="sizePolicy">
<sizepolicy hsizetype="Minimum" vsizetype="Expanding">
<horstretch>0</horstretch>
<verstretch>0</verstretch>
</sizepolicy>
</property>
<property name="minimumSize">
<size>
<width>300</width>
<height>0</height>
</size>
</property>
<property name="alternatingRowColors">
<bool>true</bool>
</property>
<property name="spacing">
<number>5</number>
</property>
<property name="uniformItemSizes">
<bool>true</bool>
</property>
</widget>
</item>
<item>
<widget class="QPushButton" name="plugin_tweaks_button">
<property name="toolTip">
<string>Edit tweaks for any custom plugins you have installed</string>
</property>
<property name="text">
<string>&amp;Plugin tweaks</string>
</property>
</widget>
</item>
</layout>
</item>
<item>
<widget class="QGroupBox" name="groupBox_6">
<item row="0" column="1">
<widget class="QGroupBox" name="groupBox">
<property name="title">
<string>All available tweaks</string>
<string>Help</string>
</property>
<layout class="QGridLayout" name="gridLayout_11">
<item row="0" column="0">
<widget class="QPlainTextEdit" name="default_tweaks">
<layout class="QVBoxLayout" name="verticalLayout">
<item>
<widget class="QPlainTextEdit" name="help">
<property name="lineWrapMode">
<enum>QPlainTextEdit::NoWrap</enum>
</property>
<property name="readOnly">
<bool>true</bool>
</property>
@ -40,14 +82,38 @@
</layout>
</widget>
</item>
<item>
<widget class="QGroupBox" name="groupBox_7">
<item row="1" column="1">
<widget class="QGroupBox" name="groupBox_2">
<property name="title">
<string>&amp;Current tweaks</string>
<string>Edit tweak</string>
</property>
<layout class="QGridLayout" name="gridLayout_10">
<item row="0" column="0">
<widget class="QPlainTextEdit" name="current_tweaks"/>
<layout class="QGridLayout" name="gridLayout">
<item row="0" column="0" colspan="2">
<widget class="QPlainTextEdit" name="edit_tweak">
<property name="lineWrapMode">
<enum>QPlainTextEdit::NoWrap</enum>
</property>
</widget>
</item>
<item row="1" column="0">
<widget class="QPushButton" name="restore_default_button">
<property name="toolTip">
<string>Restore this tweak to its default value</string>
</property>
<property name="text">
<string>Restore &amp;default</string>
</property>
</widget>
</item>
<item row="1" column="1">
<widget class="QPushButton" name="apply_button">
<property name="toolTip">
<string>Apply any changes you made to this tweak</string>
</property>
<property name="text">
<string>&amp;Apply</string>
</property>
</widget>
</item>
</layout>
</widget>

4
src/calibre/gui2/widgets.py
View File

@ -20,7 +20,7 @@ from calibre.gui2.filename_pattern_ui import Ui_Form
from calibre import fit_image
from calibre.ebooks import BOOK_EXTENSIONS
from calibre.ebooks.metadata.meta import metadata_from_filename
from calibre.utils.config import prefs, XMLConfig
from calibre.utils.config import prefs, XMLConfig, tweaks
from calibre.gui2.progress_indicator import ProgressIndicator as _ProgressIndicator
history = XMLConfig('history')
@ -932,7 +932,7 @@ class SplitterHandle(QSplitterHandle):
def paintEvent(self, ev):
QSplitterHandle.paintEvent(self, ev)
if self.highlight:
if self.highlight and tweaks['draw_hidden_section_indicators']:
painter = QPainter(self)
painter.setClipRect(ev.rect())
painter.fillRect(self.rect(), Qt.yellow)

10
src/calibre/library/save_to_disk.py
View File

@ -142,11 +142,13 @@ class SafeFormat(TemplateFormatter):
def get_components(template, mi, id, timefmt='%b %Y', length=250,
sanitize_func=ascii_filename, replace_whitespace=False,
to_lowercase=False):
tsfmt = partial(title_sort, order=tweaks['save_template_title_series_sorting'])
tsorder = tweaks['save_template_title_series_sorting']
format_args = FORMAT_ARGS.copy()
format_args.update(mi.all_non_none_fields())
if mi.title:
format_args['title'] = tsfmt(mi.title)
format_args['title'] = mi.title if tsorder == 'strictly_alphabetic' \
else mi.get('title_sort', title_sort(mi.title, order='library_order'))
if mi.authors:
format_args['authors'] = mi.format_authors()
format_args['author'] = format_args['authors']
@ -157,7 +159,7 @@ def get_components(template, mi, id, timefmt='%b %Y', length=250,
else:
format_args['tags'] = ''
if mi.series:
format_args['series'] = tsfmt(mi.series)
format_args['series'] = title_sort(mi.series, order=tsorder)
if mi.series_index is not None:
format_args['series_index'] = mi.format_series_index()
else:
@ -176,7 +178,7 @@ def get_components(template, mi, id, timefmt='%b %Y', length=250,
cm = custom_metadata[key]
## TODO: NEWMETA: should ratings be divided by 2? The standard rating isn't...
if cm['datatype'] == 'series':
format_args[key] = tsfmt(format_args[key])
format_args[key] = title_sort(format_args[key], order=tsorder)
if key+'_index' in format_args:
format_args[key+'_index'] = fmt_sidx(format_args[key+'_index'])
elif cm['datatype'] == 'datetime':

1
src/calibre/utils/localization.py
View File

@ -107,6 +107,7 @@ _extra_lang_codes = {
'en_CZ' : _('English (Czechoslovakia)'),
'en_PK' : _('English (Pakistan)'),
'en_HR' : _('English (Croatia)'),
'en_ID' : _('English (Indonesia)'),
'en_IL' : _('English (Israel)'),
'en_SG' : _('English (Singapore)'),
'en_YE' : _('English (Yemen)'),