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

py2exe functionality added for standalone windows executables. Initial implementation of HTML->LRF conversion

Browse Source
This commit is contained in:
Kovid Goyal 2007-04-17 07:16:25 +00:00
parent e294564d29
commit 65b430b23a
14 changed files with 2536 additions and 166 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

282
LICENSE Normal file
View File

@ -0,0 +1,282 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Lesser General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS

BIN
icons/library.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 82 KiB

24
installer.nsi Normal file
View File

@ -0,0 +1,24 @@
;------------------------------------------------------------------------------------------------------
;Include Modern UI
!include "MUI.nsh"
;------------------------------------------------------------------------------------------------------
;General
;Name and file
Name "libprs500"
OutFile "Basic.exe"
;Default installation folder
InstallDir "$PROGRAMFILES\libprs500"
;Get installation folder from registry if available
InstallDirRegKey HKCU "Software\libprs500" ""
;------------------------------------------------------------------------------------------------------
;Interface Settings
!define MUI_ABORTWARNING
;------------------------------------------------------------------------------------------------------

19
setup.py
View File

@ -17,6 +17,17 @@ import sys
import ez_setup
ez_setup.use_setuptools()
try:
import py2exe
console = [{'script' : 'src/libprs500/cli/main.py', 'dest_base':'prs500'}]
windows = [{'script' : 'src/libprs500/gui/main.py', 'dest_base':'prs500-gui',
'icon_resources':[(1,'icons/library.ico')]}]
options = { 'py2exe' : {'includes': ['sip', 'pkg_resources'], 'dist_dir':'c:\libprs500',
'packages' : ['PIL']}}
except ImportError:
console, windows, options = [], [], {}
finally:
library = 'libprs500_lib.zip'
# Try to install the Python imaging library as the package name (PIL) doesn't
# match the distribution file name, thus declaring itas a dependency is useless
@ -66,11 +77,17 @@ setup(
'prs500 = libprs500.cli.main:main', \
'lrf-meta = libprs500.lrf.meta:main', \
'rtf-meta = libprs500.metadata.rtf:main', \
'makelrf = libprs500.lrf.makelrf:main'\
'makelrf = libprs500.lrf.makelrf:main', \
'txt2lrf = libprs500.lrf.makelrf:txt', \
'html2lrf = libprs500.lrf.makelrf:html',\
],
'gui_scripts' : [ 'prs500-gui = libprs500.gui.main:main']
},
zip_safe = True,
console = console,
windows = windows,
options = options,
library = library,
description =
"""
Library to interface with the Sony Portable Reader 500

2
src/libprs500/cli/main.py
View File

@ -23,7 +23,7 @@ from optparse import OptionParser
from libprs500 import __version__ as VERSION
from libprs500.prs500 import PRS500
from terminfo import TerminalController
from libprs500.cli.terminfo import TerminalController
from libprs500.errors import ArgumentError, DeviceError, DeviceLocked

4
src/libprs500/gui/main.py
View File

@ -33,8 +33,8 @@ from libprs500.gui import installErrorHandler, Error, _Warning, \
from libprs500.gui.widgets import LibraryBooksModel, DeviceBooksModel, \
DeviceModel
from libprs500.gui.main_ui import Ui_MainWindow
from database import LibraryDatabase
from editbook import EditBookDialog
from libprs500.gui.database import LibraryDatabase
from libprs500.gui.editbook import EditBookDialog
DEFAULT_BOOK_COVER = None

3
src/libprs500/lrf/__init__.py
View File

@ -19,3 +19,6 @@ At the time fo writing, this package only supports reading and writing LRF meat
__docformat__ = "epytext"
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
class ConversionError(Exception):
pass

1767
src/libprs500/lrf/html/BeautifulSoup.py Normal file
View File

File diff suppressed because it is too large Load Diff

20
src/libprs500/lrf/html/__init__.py Normal file
View File

@ -0,0 +1,20 @@
## Copyright (C) 2006 Kovid Goyal kovid@kovidgoyal.net
## 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.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
This package contains code to convert HTML ebooks to LRF ebooks.
"""
__docformat__ = "epytext"
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>"

334
src/libprs500/lrf/html/convert.py Normal file
View File

@ -0,0 +1,334 @@
## Copyright (C) 2006 Kovid Goyal kovid@kovidgoyal.net
## This work is based on htmlbbeb created by esperanc.
##
## 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.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Code to convert HTML ebooks into LRF ebooks.
"""
import os, re, sys
from htmlentitydefs import name2codepoint
from libprs500.lrf.html.BeautifulSoup import BeautifulSoup, Comment, Tag, NavigableString
from libprs500.lrf.pylrs.pylrs import Book, Page, Paragraph, TextBlock, CR
from libprs500.lrf.pylrs.pylrs import Span as _Span
from libprs500.lrf import ConversionError
class Span(_Span):
replaced_entities = [ 'amp', 'lt', 'gt' , 'ldquo', 'rdquo', 'lsquo', 'rsquo' ]
patterns = [ re.compile('&'+i+';') for i in replaced_entities ]
targets = [ unichr(name2codepoint[i]) for i in replaced_entities ]
rules = zip(patterns, targets)
@staticmethod
def unit_convert(val, ref=80):
"""
Tries to convert html units stored in C{val} to pixels. C{ref} contains
the reference value for relative units. Returns the number of pixels
(an int) if successful. Otherwise, returns None.
Assumes: 1 pixel is 1/4 mm. One em is 10pts
"""
m = re.match("\s*([0-9]*\.?[0-9]*)\s*(%|em|px|mm|cm|in|pt|pc)", val)
if m is not None:
unit = float(m.group(1))
if m.group(2) == '%':
result = int(unit/100.0*ref)
elif m.group(2) == 'px':
result = int(unit)
elif m.group(2) == 'in':
result = int(unit * 25.4 * 4)
elif m.group(2) == 'pt':
result = int(unit * 25.4 * 4 / 72)
elif m.group(2)== 'em':
result = int(unit * 25.4 * 4 / 72 * 10)
elif m.group(2)== 'pc':
result = int(unit * 25.4 * 4 / 72 * 12)
elif m.group(2)== 'mm':
result = int(unit * 4)
elif m.group(2)== 'cm':
result = int(unit * 10 * 4)
else:
try:
result = int(val)
except ValueError:
return None
return result
@staticmethod
def translate_attrs(d):
"""
Receives a dictionary of html attributes and styles and returns
approximate Xylog equivalents in a new dictionary
"""
t = dict()
for key in d.keys():
try:
val = d[key].lower()
except IndexError:
val = None
if key == "font-family":
if max(val.find("courier"), val.find("mono"), val.find("fixed"), val.find("typewriter"))>=0:
t["fontfacename"] = "Courier10 BT Roman"
elif max(val.find("arial"), val.find("helvetica"), val.find("verdana"),
val.find("trebuchet"), val.find("sans")) >= 0:
t["fontfacename"] = "Swis721 BT Roman"
else:
t["fontfacename"] = "Dutch801 Rm BT Roman"
elif key == "font-size":
unit = Span.unit_convert(val, 14)
if unit is not None:
# Assume a 10 pt font (14 pixels) has fontsize 100
t["fontsize"] = str(int (unit / 14.0 * 100))
else:
if val.find("xx-small") >= 0:
t["fontsize"] = "40"
elif val.find("x-small") >= 0:
t["fontsize"] = "60"
elif val.find("small") >= 0:
t["fontsize"] = "80"
elif val.find("xx-large") >= 0:
t["fontsize"] = "180"
elif val.find("x-large") >= 0:
t["fontsize"] = "140"
elif val.find("large") >= 0:
t["fontsize"] = "120"
else:
t["fontsize"] = "100"
elif key == "font-weight":
m = re.match ("\s*([0-9]+)", val)
if m is not None:
#report (m.group(1))
t["fontweight"] = str(int(int(m.group(1))))
else:
if val.find("bold") >= 0 or val.find("strong") >= 0:
t["fontweight"] = "1000"
else:
t["fontweight"] = "400"
elif key.startswith("margin"):
if key == "margin":
u = []
for x in val.split(" "):
u.append(Span.unit_convert (x,200)*2)
if len(u)==1:
u = [u[0], u[0], u[0], u[0]]
elif len(u)==2:
u = [u[0], u[1], u[0], u[1]]
elif len(u)==3:
u = [u[0], u[1], u[2], u[1]]
elif key == "margin-top":
u = [Span.unit_convert(val, 200)*2, None, None, None]
elif key == "margin-right":
u = [None, Span.unit_convert(val, 200)*2, None, None]
elif key == "margin-bottom":
u = [None, None, Span.unit_convert(val, 200)*2, None]
else:
u = [None, None, None, Span.unit_convert(val, 200)*2]
if u[2] is not None:
t["parskip"] = str(u[2])
t["footskip"] = str(u[2])
if u[0] is not None:
t["topskip"] = str(u[0])
if u[1] is not None:
t["sidemargin"] = str(u[1])
elif key == "text-align" or key == "align":
if val in ["right", "foot"]:
t["align"] = "foot"
elif val == "center":
t["align"] = "center"
else:
t["align"] = "head"
else:
t[key] = d[key]
return t
def __init__(self, ns, css):
src = ns.string
src = re.sub('[\n\r]+', '', src)
for pat, repl in Span.rules:
src = pat.sub(repl, src)
if not src:
raise ConversionError('No point in adding an empty string')
attrs = Span.translate_attrs(css)
_Span.__init__(self, text=src, **attrs)
class HTMLConvertor(object):
selector_pat = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}")
# Defaults for various formatting tags
css = dict(
h1 = {"font-size":"xx-large", "font-weight":"bold"},
h2 = {"font-size":"x-large", "font-weight":"bold"},
h3 = {"font-size":"large", "font-weight":"bold"},
h4 = {"font-size":"large"},
h5 = {"font-weight":"bold"},
b = {"font-weight":"bold"},
strong = {"font-weight":"bold"},
i = {"font-style":"italic"},
em = {"font-style":"italic"},
)
def __init__(self, book, soup, verbose=False):
self.book = book #: The Book object representing a BBeB book
self.soup = soup #: Parsed HTML soup
self.verbose = verbose
self.current_page = None
self.current_para = None
self.current_style = {}
self.parse_file(self.soup.html)
def parse_css(self, style):
"""
Parse the contents of a <style> tag or .css file.
@param style: C{str(style)} should be the CSS to parse.
@return: A dictionary with one entry per selector where the key is the
selector name and the value is a dictionary of properties
"""
sdict = dict()
for sel in re.findall(HTMLConvertor.selector_pat, style):
for key in sel[0].split(','):
key = key.strip().lower()
val = self.parse_style_properties(sel[1])
if key in sdict:
sdict[key].update(val)
else:
sdict[key] = val
return sdict
def parse_style_properties(self, props):
"""
Parses a style attribute. The code within a CSS selector block or in
the style attribute of an HTML element.
@return: A dictionary with one entry for each property where the key
is the property name and the value is the property value.
"""
prop = dict()
for s in props.split(';'):
l = s.split(':',1)
if len(l)==2:
key = str(l[0].strip()).lower()
val = l[1].strip()
prop [key] = val
return prop
def tag_css(self, tag, parent_css={}):
"""
Return a dictionary of style properties applicable to Tag tag.
"""
prop = dict()
if tag.has_key("align"):
prop["text-align"] = tag["align"]
if self.css.has_key(tag.name):
prop.update(self.css[tag.name])
if tag.has_key("class"):
cls = tag["class"].lower()
for classname in ["."+cls, tag.name+"."+cls]:
if self.css.has_key(classname):
prop.update(self.css[classname])
if parent_css:
prop.update(parent_css)
if tag.has_key("style"):
prop.update(self.parse_style_properties(tag["style"]))
return prop
def parse_file(self, html):
if self.current_page:
self.book.append(self.current_page)
self.current_page = Page()
self.current_block = TextBlock()
self.current_para = Paragraph()
self.parse_tag(html, {})
if self.current_para:
self.current_block.append(self.current_para)
if self.current_block:
self.current_page.append(self.current_block)
if self.current_page:
self.book.append(self.current_page)
def parse_tag(self, tag, parent_css):
def add_text(tag, css):
try:
self.current_para.append(Span(tag, css))
except ConversionError, err:
if self.verbose:
print >>sys.stderr, err
def process_text_tag(tag, pcss):
for c in tag.contents:
if isinstance(tag, NavigableString):
add_text(tag, pcss)
else:
self.parse_tag(c, pcss)
try:
tagname = tag.name.lower()
except AttributeError:
add_text(tag, parent_css)
return
if tagname in ["title", "script", "meta"]:
pass
elif tagname == 'p':
css = self.tag_css(tag, parent_css=parent_css)
self.current_block.append(self.current_para)
self.current_para = Paragraph()
process_text_tag(tag, css)
elif tagname in ['b', 'strong', 'i', 'em', 'span']:
css = self.tag_css(tag, parent_css=parent_css)
process_text_tag(tag, css)
elif tagname == 'font':
pass
elif tagname == 'link':
pass
elif tagname == 'style':
pass
elif tagname == 'br':
self.current_para.append(CR())
elif tagname == 'hr':
self.current_page.append(self.current_para)
self.current_block.append(self.current_page)
self.current_para = Paragraph()
self.current_page = Page()
else:
for c in tag.contents:
if isinstance(c, Comment):
continue
elif isinstance(c, Tag):
self.parse_tag(c)
elif isinstance(c, NavigableString):
add_text(c, parent_css)
def writeto(self, path):
if path.lower().endswith('lrs'):
self.book.renderLrs(path)
else:
self.book.renderLrf(path)
def process_file(path, options):
cwd = os.getcwd()
try:
path = os.path.abspath(path)
os.chdir(os.path.dirname(path))
soup = BeautifulSoup(open(path, 'r').read(), \
convertEntities=BeautifulSoup.HTML_ENTITIES)
book = Book(title=options.title, author=options.author, \
sourceencoding='utf8')
conv = HTMLConvertor(book, soup)
name = os.path.splitext(os.path.basename(path))[0]+'.lrs'
os.chdir(cwd)
conv.writeto(name)
finally:
os.chdir(cwd)

68
src/libprs500/lrf/lrfcreator.py
View File

@ -1,68 +0,0 @@
## Copyright (C) 2006 Kovid Goyal kovid@kovidgoyal.net
## 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.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
from cStringIO import StringIO
from zlib import compress
from xml.dom import minidom as dom
from libprs500.lrf.meta import LRFMetaFile, LRFException
GIF_PIXEL = 'GIF89a\x01\x00\x01\x00\xf0\x00\x00Mhh\x00\x00\x00!\xf9\x04\x00\x00'\
'\x00\x00\x00,\x00\x00\x00\x00\x01\x00\x01\x00\x00\x02\x02D\x01\x00;'
def create_lrf_file():
buff = StringIO()
buff.write(LRFMetaFile.LRF_HEADER)
buff.write("".join(['\0' for i in range(0x56 - 6)]))
lrf = LRFMetaFile(buff)
lrf.version = 999 # No reason
lrf.xor_key = 0x30 # No reason
lrf.root_object_id = 0x32 # No reason
lrf.binding = 0x01 # front to back 0x10 for back to front
lrf.dpi = 1600 # TODO: Play with this
lrf.width = 600 # TODO: Play with this
lrf.height = 800 # TODO: Play with this
lrf.color_depth = 24 # Seems like a good idea
lrf.toc_object_id = 0x42 # No reason
lrf.thumbnail_type = 0x14 # GIF
lrf.thumbnail_size = len(GIF_PIXEL)
doc = dom.getDOMImplementation().createDocument(None, None, None)
info = doc.createElement('Info')
info.setAttribute('version', '1.0')
book_info = doc.createElement('BookInfo')
doc_info = doc.createElement('DocInfo')
info.appendChild(book_info)
info.appendChild(doc_info)
info = doc.toxml(encoding='utf-16')
stream = compress(info)
lrf.compressed_info_size = 4 + len(stream)
lrf.uncompressed_info_size = len(info)
buff.write(stream + GIF_PIXEL)
pos = buff.tell()
if pos%16 != 0:
buff.write("".join(['\0' for i in range(16 - pos%16)]))
buff.seek(0)
return lrf
class LRFCreator(object):
pass
if __name__ == "__main__":
open('test.lrf', 'wb').write(create_lrf_file()._file.read())

93
src/libprs500/lrf/lrftypes.py
View File

@ -1,93 +0,0 @@
## Copyright (C) 2006 Kovid Goyal kovid@kovidgoyal.net
## 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.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
import struct
from libprs500.prstypes import field
from libprs500.lrf.meta import WORD, DWORD
class LRFTag(list):
"""
Base class for all LRF tags.
An LRFTag is simply a sequence of bytes. The first two bytes are the tag id.
Tag ids are always of the form (encoded little endian) # f5 where # is a byte.
Thus there can be atmost 256 distinct tags.
"""
id = field(fmt=WORD, start=0)
def __init__(self, _id, size):
"""
@param _id: The tag id should be an integer
@param _size: The initial size of this tag
"""
list.__init__(self, ['\0' for i in range(size+4)])
self.id = _id
def pack(self, val, fmt=DWORD, start=0):
"""
Encode C{val} and write it to buffer.
@param fmt: See U{struct<http://docs.python.org/lib/module-struct.html>}
@param start: Position in buffer at which to write encoded data
"""
self[start:start+struct.calcsize(fmt)] = struct.pack(fmt, val)
def unpack(self, fmt=DWORD, start=0):
"""
Return decoded data from buffer.
@param fmt: See U{struct<http://docs.python.org/lib/module-struct.html>}
@param start: Position in buffer from which to decode
"""
end = start + struct.calcsize(fmt)
return struct.unpack(fmt, "".join(list.__getslice__(self, start, end)))
class ObjectStart(LRFTag):
""" Tag that marks the start of an LRFObject """
ID = 0xf500
# Stored in 4 bytes. Thus there can be only 1024*1024*1024 objects in an LRF file
object_id = field(fmt=DWORD, start=0)
# Stored in 2 bytes. Thus there can be at most 256**2 distinct object types.
object_type = field(fmt=WORD, start=4)
def __init__(self, _id, _type):
LRFTag.__init__(self, ObjectStart.ID, 6)
self.object_id = _id
self.object_type = _type
class ObjectEnd(LRFTag):
""" Tag that marks the end of an LRFObject """
ID = 0xf501
def __init__(self):
LRFTag.__init__(self, ObjectEnd.ID, 0)
class LRFObject(list):
"""
Base class for all LRF objects. An LRF object is simply a sequence of
L{LRFTag}s. It must start with an L{ObjectStart} tag and end with
an L{ObjectEnd} tag.
"""
def __str__(self):
return "".join(self)
class BookAttr(LRFObject):
"""
Global properties for an LRF ebook. Root element of the LRF element
structure.
"""

85
src/libprs500/lrf/makelrf.py
View File

@ -24,6 +24,7 @@ from tempfile import mkdtemp
from optparse import OptionParser
import xml.dom.minidom as dom
from libprs500.lrf import ConversionError
from libprs500.lrf.meta import LRFException, LRFMetaFile
from libprs500.ptempfile import PersistentTemporaryFile
@ -149,6 +150,90 @@ def makelrf(author=None, title=None, \
if dirpath:
shutil.rmtree(dirpath, True)
def txt():
""" CLI for txt -> lrf conversions """
parser = OptionParser(usage=\
"""usage: %prog [options] mybook.txt
%prog converts mybook.txt to mybook.lrf
"""\
)
parser.add_option("-t", "--title", action="store", type="string", \
dest="title", help="Set the title")
parser.add_option("-a", "--author", action="store", type="string", \
dest="author", help="Set the author", default='Unknown')
defenc = 'cp1252'
enchelp = 'Set the encoding used to decode ' + \
'the text in mybook.txt. Default encoding is ' + defenc
parser.add_option('-e', '--encoding', action='store', type='string', \
dest='encoding', help=enchelp, default=defenc)
options, args = parser.parse_args()
if len(args) != 1:
parser.print_help()
sys.exit(1)
src = args[0]
if options.title == None:
options.title = os.path.splitext(os.path.basename(src))[0]
try:
convert_txt(src, options)
except ConversionError, err:
print >>sys.stderr, err
sys.exit(1)
def convert_txt(path, options):
"""
Convert the text file at C{path} into an lrf file.
@param options: Object with the following attributes:
C{author}, C{title}, C{encoding} (the assumed encoding of
the text in C{path}.)
"""
import fileinput
from libprs500.lrf.pylrs.pylrs import Book
book = Book(title=options.title, author=options.author, \
sourceencoding=options.encoding)
buffer = ''
block = book.Page().TextBlock()
for line in fileinput.input(path):
line = line.strip()
if line:
buffer += line
else:
block.Paragraph(buffer)
buffer = ''
basename = os.path.basename(path)
name = os.path.splitext(basename)[0]+'.lrf'
try:
book.renderLrf(name)
except UnicodeDecodeError:
raise ConversionError(path + ' is not encoded in ' + \
options.encoding +'. Specify the '+ \
'correct encoding with the -e option.')
return os.path.abspath(name)
def html():
""" CLI for html -> lrf conversions """
parser = OptionParser(usage=\
"""usage: %prog [options] mybook.txt
%prog converts mybook.txt to mybook.lrf
"""\
)
parser.add_option("-t", "--title", action="store", type="string", \
dest="title", help="Set the title")
parser.add_option("-a", "--author", action="store", type="string", \
dest="author", help="Set the author", default='Unknown')
options, args = parser.parse_args()
if len(args) != 1:
parser.print_help()
sys.exit(1)
src = args[0]
if options.title == None:
options.title = os.path.splitext(os.path.basename(src))[0]
from libprs500.lrf.html.convert import process_file
process_file(src, options)
def main(cargs=None):
parser = OptionParser(usage=\
"""usage: %prog [options] mybook.[html|pdf|rar]

1
src/libprs500/lrf/pylrs/pylrs.py
View File

@ -5,7 +5,6 @@
import os
import re
import codecs
import sys
from datetime import date
try:
from elementtree.ElementTree import (Element, SubElement)