2013-10-02 18:59:40 +00:00
|
|
|
#! /usr/bin/python
|
|
|
|
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
2012-11-20 13:28:12 +00:00
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
from __future__ import print_function
|
2020-01-20 13:29:03 +00:00
|
|
|
from .convert2xml import encodeNumber
|
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
class Unbuffered:
|
2012-11-20 13:28:12 +00:00
|
|
|
def __init__(self, stream):
|
|
|
|
self.stream = stream
|
|
|
|
def write(self, data):
|
|
|
|
self.stream.write(data)
|
|
|
|
self.stream.flush()
|
|
|
|
def __getattr__(self, attr):
|
|
|
|
return getattr(self.stream, attr)
|
2012-05-16 16:15:43 +00:00
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
import sys
|
|
|
|
sys.stdout=Unbuffered(sys.stdout)
|
2012-11-20 13:28:12 +00:00
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
import csv
|
|
|
|
import os
|
|
|
|
import getopt
|
|
|
|
from struct import pack
|
|
|
|
from struct import unpack
|
2012-05-16 16:15:43 +00:00
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
class TpzDRMError(Exception):
|
2012-11-20 13:28:12 +00:00
|
|
|
pass
|
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
# local support routines
|
|
|
|
if 'calibre' in sys.modules:
|
|
|
|
inCalibre = True
|
|
|
|
else:
|
|
|
|
inCalibre = False
|
|
|
|
|
|
|
|
if inCalibre :
|
|
|
|
from calibre_plugins.dedrm import convert2xml
|
|
|
|
from calibre_plugins.dedrm import flatxml2html
|
|
|
|
from calibre_plugins.dedrm import flatxml2svg
|
|
|
|
from calibre_plugins.dedrm import stylexml2css
|
|
|
|
else :
|
|
|
|
import convert2xml
|
|
|
|
import flatxml2html
|
|
|
|
import flatxml2svg
|
|
|
|
import stylexml2css
|
|
|
|
|
|
|
|
# global switch
|
|
|
|
buildXML = False
|
|
|
|
|
|
|
|
# Get a 7 bit encoded number from a file
|
|
|
|
def readEncodedNumber(file):
|
|
|
|
flag = False
|
|
|
|
c = file.read(1)
|
|
|
|
if (len(c) == 0):
|
|
|
|
return None
|
|
|
|
data = ord(c)
|
|
|
|
if data == 0xFF:
|
|
|
|
flag = True
|
|
|
|
c = file.read(1)
|
|
|
|
if (len(c) == 0):
|
|
|
|
return None
|
|
|
|
data = ord(c)
|
|
|
|
if data >= 0x80:
|
|
|
|
datax = (data & 0x7F)
|
|
|
|
while data >= 0x80 :
|
|
|
|
c = file.read(1)
|
|
|
|
if (len(c) == 0):
|
|
|
|
return None
|
|
|
|
data = ord(c)
|
|
|
|
datax = (datax <<7) + (data & 0x7F)
|
|
|
|
data = datax
|
|
|
|
if flag:
|
|
|
|
data = -data
|
|
|
|
return data
|
|
|
|
|
|
|
|
# Get a length prefixed string from the file
|
|
|
|
def lengthPrefixString(data):
|
|
|
|
return encodeNumber(len(data))+data
|
|
|
|
|
|
|
|
def readString(file):
|
|
|
|
stringLength = readEncodedNumber(file)
|
|
|
|
if (stringLength == None):
|
|
|
|
return None
|
|
|
|
sv = file.read(stringLength)
|
|
|
|
if (len(sv) != stringLength):
|
|
|
|
return ""
|
|
|
|
return unpack(str(stringLength)+"s",sv)[0]
|
|
|
|
|
|
|
|
def getMetaArray(metaFile):
|
|
|
|
# parse the meta file
|
|
|
|
result = {}
|
|
|
|
fo = file(metaFile,'rb')
|
|
|
|
size = readEncodedNumber(fo)
|
|
|
|
for i in xrange(size):
|
|
|
|
tag = readString(fo)
|
|
|
|
value = readString(fo)
|
|
|
|
result[tag] = value
|
|
|
|
# print tag, value
|
|
|
|
fo.close()
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
|
|
# dictionary of all text strings by index value
|
|
|
|
class Dictionary(object):
|
|
|
|
def __init__(self, dictFile):
|
|
|
|
self.filename = dictFile
|
|
|
|
self.size = 0
|
|
|
|
self.fo = file(dictFile,'rb')
|
|
|
|
self.stable = []
|
|
|
|
self.size = readEncodedNumber(self.fo)
|
|
|
|
for i in xrange(self.size):
|
|
|
|
self.stable.append(self.escapestr(readString(self.fo)))
|
|
|
|
self.pos = 0
|
|
|
|
def escapestr(self, str):
|
|
|
|
str = str.replace('&','&')
|
|
|
|
str = str.replace('<','<')
|
|
|
|
str = str.replace('>','>')
|
|
|
|
str = str.replace('=','=')
|
|
|
|
return str
|
|
|
|
def lookup(self,val):
|
|
|
|
if ((val >= 0) and (val < self.size)) :
|
|
|
|
self.pos = val
|
|
|
|
return self.stable[self.pos]
|
|
|
|
else:
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Error: %d outside of string table limits" % val)
|
2013-10-02 18:59:40 +00:00
|
|
|
raise TpzDRMError('outside or string table limits')
|
|
|
|
# sys.exit(-1)
|
|
|
|
def getSize(self):
|
|
|
|
return self.size
|
|
|
|
def getPos(self):
|
|
|
|
return self.pos
|
|
|
|
|
|
|
|
|
|
|
|
class PageDimParser(object):
|
|
|
|
def __init__(self, flatxml):
|
|
|
|
self.flatdoc = flatxml.split('\n')
|
|
|
|
# find tag if within pos to end inclusive
|
|
|
|
def findinDoc(self, tagpath, pos, end) :
|
|
|
|
result = None
|
|
|
|
docList = self.flatdoc
|
|
|
|
cnt = len(docList)
|
|
|
|
if end == -1 :
|
|
|
|
end = cnt
|
|
|
|
else:
|
|
|
|
end = min(cnt,end)
|
|
|
|
foundat = -1
|
|
|
|
for j in xrange(pos, end):
|
|
|
|
item = docList[j]
|
|
|
|
if item.find('=') >= 0:
|
|
|
|
(name, argres) = item.split('=')
|
|
|
|
else :
|
|
|
|
name = item
|
|
|
|
argres = ''
|
|
|
|
if name.endswith(tagpath) :
|
|
|
|
result = argres
|
|
|
|
foundat = j
|
|
|
|
break
|
|
|
|
return foundat, result
|
|
|
|
def process(self):
|
|
|
|
(pos, sph) = self.findinDoc('page.h',0,-1)
|
|
|
|
(pos, spw) = self.findinDoc('page.w',0,-1)
|
|
|
|
if (sph == None): sph = '-1'
|
|
|
|
if (spw == None): spw = '-1'
|
|
|
|
return sph, spw
|
|
|
|
|
|
|
|
def getPageDim(flatxml):
|
|
|
|
# create a document parser
|
|
|
|
dp = PageDimParser(flatxml)
|
|
|
|
(ph, pw) = dp.process()
|
|
|
|
return ph, pw
|
|
|
|
|
|
|
|
class GParser(object):
|
|
|
|
def __init__(self, flatxml):
|
|
|
|
self.flatdoc = flatxml.split('\n')
|
|
|
|
self.dpi = 1440
|
|
|
|
self.gh = self.getData('info.glyph.h')
|
|
|
|
self.gw = self.getData('info.glyph.w')
|
|
|
|
self.guse = self.getData('info.glyph.use')
|
|
|
|
if self.guse :
|
|
|
|
self.count = len(self.guse)
|
|
|
|
else :
|
|
|
|
self.count = 0
|
|
|
|
self.gvtx = self.getData('info.glyph.vtx')
|
|
|
|
self.glen = self.getData('info.glyph.len')
|
|
|
|
self.gdpi = self.getData('info.glyph.dpi')
|
|
|
|
self.vx = self.getData('info.vtx.x')
|
|
|
|
self.vy = self.getData('info.vtx.y')
|
|
|
|
self.vlen = self.getData('info.len.n')
|
|
|
|
if self.vlen :
|
|
|
|
self.glen.append(len(self.vlen))
|
|
|
|
elif self.glen:
|
|
|
|
self.glen.append(0)
|
|
|
|
if self.vx :
|
|
|
|
self.gvtx.append(len(self.vx))
|
|
|
|
elif self.gvtx :
|
|
|
|
self.gvtx.append(0)
|
|
|
|
def getData(self, path):
|
|
|
|
result = None
|
|
|
|
cnt = len(self.flatdoc)
|
|
|
|
for j in xrange(cnt):
|
|
|
|
item = self.flatdoc[j]
|
|
|
|
if item.find('=') >= 0:
|
|
|
|
(name, argt) = item.split('=')
|
|
|
|
argres = argt.split('|')
|
|
|
|
else:
|
|
|
|
name = item
|
|
|
|
argres = []
|
|
|
|
if (name == path):
|
|
|
|
result = argres
|
|
|
|
break
|
|
|
|
if (len(argres) > 0) :
|
|
|
|
for j in xrange(0,len(argres)):
|
|
|
|
argres[j] = int(argres[j])
|
|
|
|
return result
|
|
|
|
def getGlyphDim(self, gly):
|
|
|
|
if self.gdpi[gly] == 0:
|
|
|
|
return 0, 0
|
|
|
|
maxh = (self.gh[gly] * self.dpi) / self.gdpi[gly]
|
|
|
|
maxw = (self.gw[gly] * self.dpi) / self.gdpi[gly]
|
|
|
|
return maxh, maxw
|
|
|
|
def getPath(self, gly):
|
|
|
|
path = ''
|
|
|
|
if (gly < 0) or (gly >= self.count):
|
|
|
|
return path
|
|
|
|
tx = self.vx[self.gvtx[gly]:self.gvtx[gly+1]]
|
|
|
|
ty = self.vy[self.gvtx[gly]:self.gvtx[gly+1]]
|
|
|
|
p = 0
|
|
|
|
for k in xrange(self.glen[gly], self.glen[gly+1]):
|
|
|
|
if (p == 0):
|
|
|
|
zx = tx[0:self.vlen[k]+1]
|
|
|
|
zy = ty[0:self.vlen[k]+1]
|
|
|
|
else:
|
|
|
|
zx = tx[self.vlen[k-1]+1:self.vlen[k]+1]
|
|
|
|
zy = ty[self.vlen[k-1]+1:self.vlen[k]+1]
|
|
|
|
p += 1
|
|
|
|
j = 0
|
|
|
|
while ( j < len(zx) ):
|
|
|
|
if (j == 0):
|
|
|
|
# Start Position.
|
|
|
|
path += 'M %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly])
|
|
|
|
elif (j <= len(zx)-3):
|
|
|
|
# Cubic Bezier Curve
|
|
|
|
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[j+2] * self.dpi / self.gdpi[gly], zy[j+2] * self.dpi / self.gdpi[gly])
|
|
|
|
j += 2
|
|
|
|
elif (j == len(zx)-2):
|
|
|
|
# Cubic Bezier Curve to Start Position
|
|
|
|
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
|
|
|
j += 1
|
|
|
|
elif (j == len(zx)-1):
|
|
|
|
# Quadratic Bezier Curve to Start Position
|
|
|
|
path += 'Q %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
|
|
|
|
|
|
|
j += 1
|
|
|
|
path += 'z'
|
|
|
|
return path
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# dictionary of all text strings by index value
|
|
|
|
class GlyphDict(object):
|
|
|
|
def __init__(self):
|
|
|
|
self.gdict = {}
|
|
|
|
def lookup(self, id):
|
|
|
|
# id='id="gl%d"' % val
|
|
|
|
if id in self.gdict:
|
|
|
|
return self.gdict[id]
|
|
|
|
return None
|
|
|
|
def addGlyph(self, val, path):
|
|
|
|
id='id="gl%d"' % val
|
|
|
|
self.gdict[id] = path
|
|
|
|
|
|
|
|
|
|
|
|
def generateBook(bookDir, raw, fixedimage):
|
|
|
|
# sanity check Topaz file extraction
|
|
|
|
if not os.path.exists(bookDir) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find directory with unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
|
|
|
dictFile = os.path.join(bookDir,'dict0000.dat')
|
|
|
|
if not os.path.exists(dictFile) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find dict0000.dat file")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
|
|
|
pageDir = os.path.join(bookDir,'page')
|
|
|
|
if not os.path.exists(pageDir) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find page directory in unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
|
|
|
imgDir = os.path.join(bookDir,'img')
|
|
|
|
if not os.path.exists(imgDir) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find image directory in unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
2012-11-20 13:28:12 +00:00
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
glyphsDir = os.path.join(bookDir,'glyphs')
|
|
|
|
if not os.path.exists(glyphsDir) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find glyphs directory in unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
|
|
|
metaFile = os.path.join(bookDir,'metadata0000.dat')
|
|
|
|
if not os.path.exists(metaFile) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find metadata0000.dat in unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
|
|
|
svgDir = os.path.join(bookDir,'svg')
|
|
|
|
if not os.path.exists(svgDir) :
|
|
|
|
os.makedirs(svgDir)
|
|
|
|
|
|
|
|
if buildXML:
|
|
|
|
xmlDir = os.path.join(bookDir,'xml')
|
|
|
|
if not os.path.exists(xmlDir) :
|
|
|
|
os.makedirs(xmlDir)
|
|
|
|
|
|
|
|
otherFile = os.path.join(bookDir,'other0000.dat')
|
|
|
|
if not os.path.exists(otherFile) :
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Can not find other0000.dat in unencrypted book")
|
2013-10-02 18:59:40 +00:00
|
|
|
return 1
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Updating to color images if available")
|
2013-10-02 18:59:40 +00:00
|
|
|
spath = os.path.join(bookDir,'color_img')
|
|
|
|
dpath = os.path.join(bookDir,'img')
|
|
|
|
filenames = os.listdir(spath)
|
|
|
|
filenames = sorted(filenames)
|
|
|
|
for filename in filenames:
|
|
|
|
imgname = filename.replace('color','img')
|
|
|
|
sfile = os.path.join(spath,filename)
|
|
|
|
dfile = os.path.join(dpath,imgname)
|
|
|
|
imgdata = file(sfile,'rb').read()
|
|
|
|
file(dfile,'wb').write(imgdata)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Creating cover.jpg")
|
2013-10-02 18:59:40 +00:00
|
|
|
isCover = False
|
|
|
|
cpath = os.path.join(bookDir,'img')
|
|
|
|
cpath = os.path.join(cpath,'img0000.jpg')
|
|
|
|
if os.path.isfile(cpath):
|
|
|
|
cover = file(cpath, 'rb').read()
|
|
|
|
cpath = os.path.join(bookDir,'cover.jpg')
|
|
|
|
file(cpath, 'wb').write(cover)
|
|
|
|
isCover = True
|
|
|
|
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing Dictionary')
|
2013-10-02 18:59:40 +00:00
|
|
|
dict = Dictionary(dictFile)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing Meta Data and creating OPF')
|
2013-10-02 18:59:40 +00:00
|
|
|
meta_array = getMetaArray(metaFile)
|
|
|
|
|
|
|
|
# replace special chars in title and authors like & < >
|
|
|
|
title = meta_array.get('Title','No Title Provided')
|
|
|
|
title = title.replace('&','&')
|
|
|
|
title = title.replace('<','<')
|
|
|
|
title = title.replace('>','>')
|
|
|
|
meta_array['Title'] = title
|
|
|
|
authors = meta_array.get('Authors','No Authors Provided')
|
|
|
|
authors = authors.replace('&','&')
|
|
|
|
authors = authors.replace('<','<')
|
|
|
|
authors = authors.replace('>','>')
|
|
|
|
meta_array['Authors'] = authors
|
|
|
|
|
|
|
|
if buildXML:
|
|
|
|
xname = os.path.join(xmlDir, 'metadata.xml')
|
|
|
|
mlst = []
|
|
|
|
for key in meta_array:
|
|
|
|
mlst.append('<meta name="' + key + '" content="' + meta_array[key] + '" />\n')
|
|
|
|
metastr = "".join(mlst)
|
|
|
|
mlst = None
|
|
|
|
file(xname, 'wb').write(metastr)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing StyleSheet')
|
2013-10-02 18:59:40 +00:00
|
|
|
|
|
|
|
# get some scaling info from metadata to use while processing styles
|
|
|
|
# and first page info
|
|
|
|
|
|
|
|
fontsize = '135'
|
|
|
|
if 'fontSize' in meta_array:
|
|
|
|
fontsize = meta_array['fontSize']
|
|
|
|
|
|
|
|
# also get the size of a normal text page
|
|
|
|
# get the total number of pages unpacked as a safety check
|
|
|
|
filenames = os.listdir(pageDir)
|
|
|
|
numfiles = len(filenames)
|
|
|
|
|
|
|
|
spage = '1'
|
|
|
|
if 'firstTextPage' in meta_array:
|
|
|
|
spage = meta_array['firstTextPage']
|
|
|
|
pnum = int(spage)
|
|
|
|
if pnum >= numfiles or pnum < 0:
|
|
|
|
# metadata is wrong so just select a page near the front
|
|
|
|
# 10% of the book to get a normal text page
|
|
|
|
pnum = int(0.10 * numfiles)
|
|
|
|
# print "first normal text page is", spage
|
|
|
|
|
|
|
|
# get page height and width from first text page for use in stylesheet scaling
|
2016-04-14 16:35:48 +00:00
|
|
|
pname = 'page%04d.dat' % (pnum - 1)
|
2013-10-02 18:59:40 +00:00
|
|
|
fname = os.path.join(pageDir,pname)
|
|
|
|
flat_xml = convert2xml.fromData(dict, fname)
|
|
|
|
|
|
|
|
(ph, pw) = getPageDim(flat_xml)
|
|
|
|
if (ph == '-1') or (ph == '0') : ph = '11000'
|
|
|
|
if (pw == '-1') or (pw == '0') : pw = '8500'
|
|
|
|
meta_array['pageHeight'] = ph
|
|
|
|
meta_array['pageWidth'] = pw
|
|
|
|
if 'fontSize' not in meta_array.keys():
|
|
|
|
meta_array['fontSize'] = fontsize
|
|
|
|
|
|
|
|
# process other.dat for css info and for map of page files to svg images
|
|
|
|
# this map is needed because some pages actually are made up of multiple
|
|
|
|
# pageXXXX.xml files
|
|
|
|
xname = os.path.join(bookDir, 'style.css')
|
|
|
|
flat_xml = convert2xml.fromData(dict, otherFile)
|
|
|
|
|
|
|
|
# extract info.original.pid to get original page information
|
|
|
|
pageIDMap = {}
|
|
|
|
pageidnums = stylexml2css.getpageIDMap(flat_xml)
|
|
|
|
if len(pageidnums) == 0:
|
|
|
|
filenames = os.listdir(pageDir)
|
|
|
|
numfiles = len(filenames)
|
|
|
|
for k in range(numfiles):
|
|
|
|
pageidnums.append(k)
|
|
|
|
# create a map from page ids to list of page file nums to process for that page
|
|
|
|
for i in range(len(pageidnums)):
|
|
|
|
id = pageidnums[i]
|
|
|
|
if id in pageIDMap.keys():
|
|
|
|
pageIDMap[id].append(i)
|
|
|
|
else:
|
|
|
|
pageIDMap[id] = [i]
|
|
|
|
|
|
|
|
# now get the css info
|
|
|
|
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
|
|
|
|
file(xname, 'wb').write(cssstr)
|
|
|
|
if buildXML:
|
|
|
|
xname = os.path.join(xmlDir, 'other0000.xml')
|
|
|
|
file(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing Glyphs')
|
2013-10-02 18:59:40 +00:00
|
|
|
gd = GlyphDict()
|
|
|
|
filenames = os.listdir(glyphsDir)
|
|
|
|
filenames = sorted(filenames)
|
|
|
|
glyfname = os.path.join(svgDir,'glyphs.svg')
|
|
|
|
glyfile = open(glyfname, 'w')
|
|
|
|
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
|
|
|
|
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
|
|
|
|
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
|
|
|
|
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
|
|
|
|
glyfile.write('<defs>\n')
|
|
|
|
counter = 0
|
|
|
|
for filename in filenames:
|
|
|
|
# print ' ', filename
|
2019-06-24 16:49:38 +00:00
|
|
|
print('.', end=' ')
|
2013-10-02 18:59:40 +00:00
|
|
|
fname = os.path.join(glyphsDir,filename)
|
|
|
|
flat_xml = convert2xml.fromData(dict, fname)
|
|
|
|
|
|
|
|
if buildXML:
|
|
|
|
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
|
|
|
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
|
|
|
|
|
|
|
gp = GParser(flat_xml)
|
|
|
|
for i in xrange(0, gp.count):
|
|
|
|
path = gp.getPath(i)
|
|
|
|
maxh, maxw = gp.getGlyphDim(i)
|
|
|
|
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
|
|
|
|
glyfile.write(fullpath)
|
|
|
|
gd.addGlyph(counter * 256 + i, fullpath)
|
|
|
|
counter += 1
|
|
|
|
glyfile.write('</defs>\n')
|
|
|
|
glyfile.write('</svg>\n')
|
|
|
|
glyfile.close()
|
2019-06-24 16:49:38 +00:00
|
|
|
print(" ")
|
2013-10-02 18:59:40 +00:00
|
|
|
|
|
|
|
|
|
|
|
# start up the html
|
|
|
|
# also build up tocentries while processing html
|
|
|
|
htmlFileName = "book.html"
|
|
|
|
hlst = []
|
|
|
|
hlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
|
|
|
|
hlst.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n')
|
|
|
|
hlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n')
|
|
|
|
hlst.append('<head>\n')
|
|
|
|
hlst.append('<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n')
|
|
|
|
hlst.append('<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n')
|
|
|
|
hlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
|
|
|
|
hlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
|
|
|
|
if 'ASIN' in meta_array:
|
|
|
|
hlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
|
|
|
|
if 'GUID' in meta_array:
|
|
|
|
hlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
|
|
|
|
hlst.append('<link href="style.css" rel="stylesheet" type="text/css" />\n')
|
|
|
|
hlst.append('</head>\n<body>\n')
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing Pages')
|
2013-10-02 18:59:40 +00:00
|
|
|
# Books are at 1440 DPI. This is rendering at twice that size for
|
|
|
|
# readability when rendering to the screen.
|
|
|
|
scaledpi = 1440.0
|
|
|
|
|
|
|
|
filenames = os.listdir(pageDir)
|
|
|
|
filenames = sorted(filenames)
|
|
|
|
numfiles = len(filenames)
|
|
|
|
|
|
|
|
xmllst = []
|
|
|
|
elst = []
|
|
|
|
|
|
|
|
for filename in filenames:
|
|
|
|
# print ' ', filename
|
2019-06-24 16:49:38 +00:00
|
|
|
print(".", end=' ')
|
2013-10-02 18:59:40 +00:00
|
|
|
fname = os.path.join(pageDir,filename)
|
|
|
|
flat_xml = convert2xml.fromData(dict, fname)
|
|
|
|
|
|
|
|
# keep flat_xml for later svg processing
|
|
|
|
xmllst.append(flat_xml)
|
|
|
|
|
|
|
|
if buildXML:
|
|
|
|
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
|
|
|
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
|
|
|
|
|
|
|
# first get the html
|
|
|
|
pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
|
|
|
|
elst.append(tocinfo)
|
|
|
|
hlst.append(pagehtml)
|
|
|
|
|
|
|
|
# finish up the html string and output it
|
|
|
|
hlst.append('</body>\n</html>\n')
|
|
|
|
htmlstr = "".join(hlst)
|
|
|
|
hlst = None
|
|
|
|
file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print(" ")
|
|
|
|
print('Extracting Table of Contents from Amazon OCR')
|
2013-10-02 18:59:40 +00:00
|
|
|
|
|
|
|
# first create a table of contents file for the svg images
|
|
|
|
tlst = []
|
|
|
|
tlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
|
|
|
|
tlst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
|
|
|
|
tlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
|
|
|
|
tlst.append('<head>\n')
|
|
|
|
tlst.append('<title>' + meta_array['Title'] + '</title>\n')
|
|
|
|
tlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
|
|
|
|
tlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
|
|
|
|
if 'ASIN' in meta_array:
|
|
|
|
tlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
|
|
|
|
if 'GUID' in meta_array:
|
|
|
|
tlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
|
|
|
|
tlst.append('</head>\n')
|
|
|
|
tlst.append('<body>\n')
|
|
|
|
|
|
|
|
tlst.append('<h2>Table of Contents</h2>\n')
|
|
|
|
start = pageidnums[0]
|
|
|
|
if (raw):
|
|
|
|
startname = 'page%04d.svg' % start
|
2012-11-20 13:28:12 +00:00
|
|
|
else:
|
2013-10-02 18:59:40 +00:00
|
|
|
startname = 'page%04d.xhtml' % start
|
|
|
|
|
|
|
|
tlst.append('<h3><a href="' + startname + '">Start of Book</a></h3>\n')
|
|
|
|
# build up a table of contents for the svg xhtml output
|
|
|
|
tocentries = "".join(elst)
|
|
|
|
elst = None
|
|
|
|
toclst = tocentries.split('\n')
|
|
|
|
toclst.pop()
|
|
|
|
for entry in toclst:
|
2019-06-24 16:49:38 +00:00
|
|
|
print(entry)
|
2013-10-02 18:59:40 +00:00
|
|
|
title, pagenum = entry.split('|')
|
|
|
|
id = pageidnums[int(pagenum)]
|
|
|
|
if (raw):
|
|
|
|
fname = 'page%04d.svg' % id
|
|
|
|
else:
|
|
|
|
fname = 'page%04d.xhtml' % id
|
|
|
|
tlst.append('<h3><a href="'+ fname + '">' + title + '</a></h3>\n')
|
|
|
|
tlst.append('</body>\n')
|
|
|
|
tlst.append('</html>\n')
|
|
|
|
tochtml = "".join(tlst)
|
|
|
|
file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
|
|
|
|
|
|
|
|
|
|
|
|
# now create index_svg.xhtml that points to all required files
|
|
|
|
slst = []
|
|
|
|
slst.append('<?xml version="1.0" encoding="utf-8"?>\n')
|
|
|
|
slst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
|
|
|
|
slst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
|
|
|
|
slst.append('<head>\n')
|
|
|
|
slst.append('<title>' + meta_array['Title'] + '</title>\n')
|
|
|
|
slst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
|
|
|
|
slst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
|
|
|
|
if 'ASIN' in meta_array:
|
|
|
|
slst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
|
|
|
|
if 'GUID' in meta_array:
|
|
|
|
slst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
|
|
|
|
slst.append('</head>\n')
|
|
|
|
slst.append('<body>\n')
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print("Building svg images of each book page")
|
2013-10-02 18:59:40 +00:00
|
|
|
slst.append('<h2>List of Pages</h2>\n')
|
|
|
|
slst.append('<div>\n')
|
|
|
|
idlst = sorted(pageIDMap.keys())
|
|
|
|
numids = len(idlst)
|
|
|
|
cnt = len(idlst)
|
|
|
|
previd = None
|
|
|
|
for j in range(cnt):
|
|
|
|
pageid = idlst[j]
|
|
|
|
if j < cnt - 1:
|
|
|
|
nextid = idlst[j+1]
|
|
|
|
else:
|
|
|
|
nextid = None
|
2019-06-24 16:49:38 +00:00
|
|
|
print('.', end=' ')
|
2013-10-02 18:59:40 +00:00
|
|
|
pagelst = pageIDMap[pageid]
|
|
|
|
flst = []
|
|
|
|
for page in pagelst:
|
|
|
|
flst.append(xmllst[page])
|
|
|
|
flat_svg = "".join(flst)
|
|
|
|
flst=None
|
|
|
|
svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
|
|
|
|
if (raw) :
|
|
|
|
pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
|
|
|
|
slst.append('<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid))
|
|
|
|
else :
|
|
|
|
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
|
|
|
|
slst.append('<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid))
|
|
|
|
previd = pageid
|
|
|
|
pfile.write(svgxml)
|
|
|
|
pfile.close()
|
|
|
|
counter += 1
|
|
|
|
slst.append('</div>\n')
|
|
|
|
slst.append('<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n')
|
|
|
|
slst.append('</body>\n</html>\n')
|
|
|
|
svgindex = "".join(slst)
|
|
|
|
slst = None
|
|
|
|
file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print(" ")
|
2013-10-02 18:59:40 +00:00
|
|
|
|
|
|
|
# build the opf file
|
|
|
|
opfname = os.path.join(bookDir, 'book.opf')
|
|
|
|
olst = []
|
|
|
|
olst.append('<?xml version="1.0" encoding="utf-8"?>\n')
|
|
|
|
olst.append('<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n')
|
|
|
|
# adding metadata
|
|
|
|
olst.append(' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n')
|
|
|
|
if 'GUID' in meta_array:
|
|
|
|
olst.append(' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n')
|
|
|
|
if 'ASIN' in meta_array:
|
|
|
|
olst.append(' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n')
|
|
|
|
if 'oASIN' in meta_array:
|
|
|
|
olst.append(' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n')
|
|
|
|
olst.append(' <dc:title>' + meta_array['Title'] + '</dc:title>\n')
|
|
|
|
olst.append(' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n')
|
|
|
|
olst.append(' <dc:language>en</dc:language>\n')
|
|
|
|
olst.append(' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n')
|
|
|
|
if isCover:
|
|
|
|
olst.append(' <meta name="cover" content="bookcover"/>\n')
|
|
|
|
olst.append(' </metadata>\n')
|
|
|
|
olst.append('<manifest>\n')
|
|
|
|
olst.append(' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n')
|
|
|
|
olst.append(' <item id="stylesheet" href="style.css" media-type="text/css"/>\n')
|
|
|
|
# adding image files to manifest
|
|
|
|
filenames = os.listdir(imgDir)
|
|
|
|
filenames = sorted(filenames)
|
|
|
|
for filename in filenames:
|
|
|
|
imgname, imgext = os.path.splitext(filename)
|
|
|
|
if imgext == '.jpg':
|
|
|
|
imgext = 'jpeg'
|
|
|
|
if imgext == '.svg':
|
|
|
|
imgext = 'svg+xml'
|
|
|
|
olst.append(' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n')
|
|
|
|
if isCover:
|
|
|
|
olst.append(' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n')
|
|
|
|
olst.append('</manifest>\n')
|
|
|
|
# adding spine
|
|
|
|
olst.append('<spine>\n <itemref idref="book" />\n</spine>\n')
|
|
|
|
if isCover:
|
|
|
|
olst.append(' <guide>\n')
|
|
|
|
olst.append(' <reference href="cover.jpg" type="cover" title="Cover"/>\n')
|
|
|
|
olst.append(' </guide>\n')
|
|
|
|
olst.append('</package>\n')
|
|
|
|
opfstr = "".join(olst)
|
|
|
|
olst = None
|
|
|
|
file(opfname, 'wb').write(opfstr)
|
|
|
|
|
2019-06-24 16:49:38 +00:00
|
|
|
print('Processing Complete')
|
2013-10-02 18:59:40 +00:00
|
|
|
|
2012-11-20 13:28:12 +00:00
|
|
|
return 0
|
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
def usage():
|
2019-06-24 16:49:38 +00:00
|
|
|
print("genbook.py generates a book from the extract Topaz Files")
|
|
|
|
print("Usage:")
|
|
|
|
print(" genbook.py [-r] [-h [--fixed-image] <bookDir> ")
|
|
|
|
print(" ")
|
|
|
|
print("Options:")
|
|
|
|
print(" -h : help - print this usage message")
|
|
|
|
print(" -r : generate raw svg files (not wrapped in xhtml)")
|
|
|
|
print(" --fixed-image : genearate any Fixed Area as an svg image in the html")
|
|
|
|
print(" ")
|
2012-11-20 13:28:12 +00:00
|
|
|
|
|
|
|
|
2013-10-02 18:59:40 +00:00
|
|
|
def main(argv):
|
|
|
|
bookDir = ''
|
|
|
|
if len(argv) == 0:
|
|
|
|
argv = sys.argv
|
|
|
|
|
2013-04-05 16:44:48 +00:00
|
|
|
try:
|
2013-10-02 18:59:40 +00:00
|
|
|
opts, args = getopt.getopt(argv[1:], "rh:",["fixed-image"])
|
|
|
|
|
|
|
|
except getopt.GetoptError, err:
|
2019-06-24 16:49:38 +00:00
|
|
|
print(str(err))
|
2013-10-02 18:59:40 +00:00
|
|
|
usage()
|
|
|
|
return 1
|
|
|
|
|
|
|
|
if len(opts) == 0 and len(args) == 0 :
|
|
|
|
usage()
|
|
|
|
return 1
|
|
|
|
|
|
|
|
raw = 0
|
|
|
|
fixedimage = True
|
|
|
|
for o, a in opts:
|
|
|
|
if o =="-h":
|
|
|
|
usage()
|
|
|
|
return 0
|
|
|
|
if o =="-r":
|
|
|
|
raw = 1
|
|
|
|
if o =="--fixed-image":
|
|
|
|
fixedimage = True
|
|
|
|
|
|
|
|
bookDir = args[0]
|
|
|
|
|
|
|
|
rv = generateBook(bookDir, raw, fixedimage)
|
|
|
|
return rv
|
|
|
|
|
2012-11-20 13:28:12 +00:00
|
|
|
|
|
|
|
if __name__ == '__main__':
|
2013-10-02 18:59:40 +00:00
|
|
|
sys.exit(main(''))
|