DeDRM_tools/DeDRM_Macintosh_Application/DeDRM.app/Contents/Resources/stylexml2css.py

280 lines
10 KiB
Python
Raw Normal View History

2010-01-17 18:10:35 +06:00
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
2010-03-02 18:46:56 +06:00
# For use with Topaz Scripts Version 2.6
2010-01-17 18:10:35 +06:00
import csv
import sys
import os
import getopt
import re
2010-01-17 18:10:35 +06:00
from struct import pack
from struct import unpack
2012-12-27 05:17:56 +06:00
debug = False
2010-01-17 18:10:35 +06:00
class DocParser(object):
2010-01-20 18:13:31 +06:00
def __init__(self, flatxml, fontsize, ph, pw):
2010-01-17 18:10:35 +06:00
self.flatdoc = flatxml.split('\n')
2010-01-19 18:11:59 +06:00
self.fontsize = int(fontsize)
2010-01-20 18:13:31 +06:00
self.ph = int(ph) * 1.0
self.pw = int(pw) * 1.0
2010-01-17 18:10:35 +06:00
stags = {
'paragraph' : 'p',
'graphic' : '.graphic'
}
attr_val_map = {
2010-01-19 18:11:59 +06:00
'hang' : 'text-indent: ',
'indent' : 'text-indent: ',
'line-space' : 'line-height: ',
'margin-bottom' : 'margin-bottom: ',
'margin-left' : 'margin-left: ',
'margin-right' : 'margin-right: ',
'margin-top' : 'margin-top: ',
'space-after' : 'padding-bottom: ',
2010-01-17 18:10:35 +06:00
}
attr_str_map = {
'align-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
'align-left' : 'text-align: left;',
'align-right' : 'text-align: right;',
'align-justify' : 'text-align: justify;',
'display-inline' : 'display: inline;',
'pos-left' : 'text-align: left;',
'pos-right' : 'text-align: right;',
'pos-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
}
2010-01-17 18:10:35 +06:00
# 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:
2010-01-19 18:11:59 +06:00
(name, argres) = item.split('=',1)
else :
2010-01-17 18:10:35 +06:00
name = item
argres = ''
if name.endswith(tagpath) :
2010-01-17 18:10:35 +06:00
result = argres
foundat = j
break
return foundat, result
# return list of start positions for the tagpath
def posinDoc(self, tagpath):
startpos = []
pos = 0
res = ""
while res != None :
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
if res != None :
startpos.append(foundpos)
pos = foundpos + 1
return startpos
2011-10-28 12:24:15 +06:00
# returns a vector of integers for the tagpath
def getData(self, tagpath, pos, end, clean=False):
if clean:
digits_only = re.compile(r'''([0-9]+)''')
2011-10-28 12:24:15 +06:00
argres=[]
(foundat, argt) = self.findinDoc(tagpath, pos, end)
if (argt != None) and (len(argt) > 0) :
argList = argt.split('|')
for strval in argList:
if clean:
m = re.search(digits_only, strval)
if m != None:
strval = m.group()
argres.append(int(strval))
2011-10-28 12:24:15 +06:00
return argres
2010-01-17 18:10:35 +06:00
def process(self):
2010-01-19 18:11:59 +06:00
classlst = ''
2010-03-02 18:46:56 +06:00
csspage = '.cl-center { text-align: center; margin-left: auto; margin-right: auto; }\n'
csspage += '.cl-right { text-align: right; }\n'
csspage += '.cl-left { text-align: left; }\n'
csspage += '.cl-justify { text-align: justify; }\n'
2010-01-17 18:10:35 +06:00
# generate a list of each <style> starting point in the stylesheet
styleList= self.posinDoc('book.stylesheet.style')
stylecnt = len(styleList)
styleList.append(-1)
# process each style converting what you can
2012-12-27 05:17:56 +06:00
if debug: print ' ', 'Processing styles.'
2010-01-17 18:10:35 +06:00
for j in xrange(stylecnt):
2012-12-27 05:17:56 +06:00
if debug: print ' ', 'Processing style %d' %(j)
2010-01-17 18:10:35 +06:00
start = styleList[j]
end = styleList[j+1]
(pos, tag) = self.findinDoc('style._tag',start,end)
if tag == None :
(pos, tag) = self.findinDoc('style.type',start,end)
2010-01-17 18:10:35 +06:00
# Is this something we know how to convert to css
if tag in self.stags :
# get the style class
(pos, sclass) = self.findinDoc('style.class',start,end)
if sclass != None:
2010-03-02 18:46:56 +06:00
sclass = sclass.replace(' ','-')
2010-01-20 18:13:31 +06:00
sclass = '.cl-' + sclass.lower()
else :
2010-01-17 18:10:35 +06:00
sclass = ''
2012-12-27 05:17:56 +06:00
if debug: print 'sclass', sclass
2010-01-17 18:10:35 +06:00
# check for any "after class" specifiers
(pos, aftclass) = self.findinDoc('style._after_class',start,end)
if aftclass != None:
2010-03-02 18:46:56 +06:00
aftclass = aftclass.replace(' ','-')
2010-01-20 18:13:31 +06:00
aftclass = '.cl-' + aftclass.lower()
else :
2010-01-17 18:10:35 +06:00
aftclass = ''
2012-12-27 05:17:56 +06:00
if debug: print 'aftclass', aftclass
2010-01-17 18:10:35 +06:00
cssargs = {}
while True :
2010-01-20 18:13:31 +06:00
(pos1, attr) = self.findinDoc('style.rule.attr', start, end)
(pos2, val) = self.findinDoc('style.rule.value', start, end)
2010-01-17 18:10:35 +06:00
2012-12-27 05:17:56 +06:00
if debug: print 'attr', attr
if debug: print 'val', val
2010-01-17 18:10:35 +06:00
if attr == None : break
2010-01-17 18:10:35 +06:00
if (attr == 'display') or (attr == 'pos') or (attr == 'align'):
# handle text based attributess
attr = attr + '-' + val
if attr in self.attr_str_map :
cssargs[attr] = (self.attr_str_map[attr], '')
else :
# handle value based attributes
if attr in self.attr_val_map :
2010-01-19 18:11:59 +06:00
name = self.attr_val_map[attr]
2010-01-20 18:13:31 +06:00
if attr in ('margin-bottom', 'margin-top', 'space-after') :
scale = self.ph
elif attr in ('margin-right', 'indent', 'margin-left', 'hang') :
scale = self.pw
elif attr == 'line-space':
scale = self.fontsize * 2.0
2012-12-27 05:17:56 +06:00
2012-09-09 06:45:24 +06:00
if val == "":
val = 0
2010-01-20 18:13:31 +06:00
2010-01-17 18:10:35 +06:00
if not ((attr == 'hang') and (int(val) == 0)) :
2010-01-20 18:13:31 +06:00
pv = float(val)/scale
cssargs[attr] = (self.attr_val_map[attr], pv)
2010-01-17 18:10:35 +06:00
keep = True
2010-01-20 18:13:31 +06:00
start = max(pos1, pos2) + 1
2010-01-17 18:10:35 +06:00
# disable all of the after class tags until I figure out how to handle them
if aftclass != "" : keep = False
if keep :
2012-12-27 05:17:56 +06:00
if debug: print 'keeping style'
# make sure line-space does not go below 100% or above 300% since
2010-01-20 18:13:31 +06:00
# it can be wacky in some styles
2010-01-17 18:10:35 +06:00
if 'line-space' in cssargs:
seg = cssargs['line-space'][0]
val = cssargs['line-space'][1]
if val < 1.0: val = 1.0
2010-01-20 18:13:31 +06:00
if val > 3.0: val = 3.0
2010-01-17 18:10:35 +06:00
del cssargs['line-space']
2010-01-19 18:11:59 +06:00
cssargs['line-space'] = (self.attr_val_map['line-space'], val)
2010-01-17 18:10:35 +06:00
2010-01-17 18:10:35 +06:00
# handle modifications for css style hanging indents
if 'hang' in cssargs:
hseg = cssargs['hang'][0]
hval = cssargs['hang'][1]
del cssargs['hang']
2010-01-19 18:11:59 +06:00
cssargs['hang'] = (self.attr_val_map['hang'], -hval)
2010-01-17 18:10:35 +06:00
mval = 0
mseg = 'margin-left: '
2010-01-20 18:13:31 +06:00
mval = hval
2010-01-17 18:10:35 +06:00
if 'margin-left' in cssargs:
mseg = cssargs['margin-left'][0]
mval = cssargs['margin-left'][1]
2010-01-20 18:13:31 +06:00
if mval < 0: mval = 0
2010-01-17 18:10:35 +06:00
mval = hval + mval
2010-01-20 18:13:31 +06:00
cssargs['margin-left'] = (mseg, mval)
2010-01-17 18:10:35 +06:00
if 'indent' in cssargs:
del cssargs['indent']
cssline = sclass + ' { '
for key in iter(cssargs):
mseg = cssargs[key][0]
mval = cssargs[key][1]
if mval == '':
cssline += mseg + ' '
else :
2010-01-20 18:13:31 +06:00
aseg = mseg + '%.1f%%;' % (mval * 100.0)
2010-01-17 18:10:35 +06:00
cssline += aseg + ' '
cssline += '}'
2010-01-19 18:11:59 +06:00
if sclass != '' :
classlst += sclass + '\n'
2010-01-17 18:10:35 +06:00
# handle special case of paragraph class used inside chapter heading
# and non-chapter headings
if sclass != '' :
ctype = sclass[4:7]
if ctype == 'ch1' :
csspage += 'h1' + cssline + '\n'
if ctype == 'ch2' :
csspage += 'h2' + cssline + '\n'
if ctype == 'ch3' :
csspage += 'h3' + cssline + '\n'
if ctype == 'h1-' :
csspage += 'h4' + cssline + '\n'
if ctype == 'h2-' :
csspage += 'h5' + cssline + '\n'
if ctype == 'h3_' :
csspage += 'h6' + cssline + '\n'
2010-03-02 18:46:56 +06:00
if cssline != ' { }':
csspage += self.stags[tag] + cssline + '\n'
2010-01-19 18:11:59 +06:00
2010-01-19 18:11:59 +06:00
return csspage, classlst
2010-01-17 18:10:35 +06:00
2010-01-20 18:13:31 +06:00
def convert2CSS(flatxml, fontsize, ph, pw):
print ' ', 'Using font size:',fontsize
print ' ', 'Using page height:', ph
print ' ', 'Using page width:', pw
2010-01-17 18:10:35 +06:00
# create a document parser
2010-01-20 18:13:31 +06:00
dp = DocParser(flatxml, fontsize, ph, pw)
2012-12-27 05:17:56 +06:00
if debug: print ' ', 'Created DocParser.'
2010-01-17 18:10:35 +06:00
csspage = dp.process()
2012-12-27 05:17:56 +06:00
if debug: print ' ', 'Processed DocParser.'
2010-01-17 18:10:35 +06:00
return csspage
2011-10-28 12:24:15 +06:00
def getpageIDMap(flatxml):
dp = DocParser(flatxml, 0, 0, 0)
pageidnumbers = dp.getData('info.original.pid', 0, -1, True)
2011-10-28 12:24:15 +06:00
return pageidnumbers