mirror of
https://github.com/gryf/ebook-converter.git
synced 2026-04-20 13:11:27 +02:00
Added docx writer related modules
This commit is contained in:
@@ -0,0 +1,10 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
|
||||
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,182 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
|
||||
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
|
||||
# cff_standard_strings {{{
|
||||
# The 391 Standard Strings as used in the CFF format.
|
||||
# from Adobe Technical None #5176, version 1.0, 18 March 1998
|
||||
|
||||
cff_standard_strings = [
|
||||
'.notdef', 'space', 'exclam', 'quotedbl', 'numbersign', 'dollar', 'percent',
|
||||
'ampersand', 'quoteright', 'parenleft', 'parenright', 'asterisk', 'plus',
|
||||
'comma', 'hyphen', 'period', 'slash', 'zero', 'one', 'two', 'three', 'four',
|
||||
'five', 'six', 'seven', 'eight', 'nine', 'colon', 'semicolon', 'less', 'equal',
|
||||
'greater', 'question', 'at', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
|
||||
'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
|
||||
'bracketleft', 'backslash', 'bracketright', 'asciicircum', 'underscore',
|
||||
'quoteleft', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
|
||||
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'braceleft',
|
||||
'bar', 'braceright', 'asciitilde', 'exclamdown', 'cent', 'sterling',
|
||||
'fraction', 'yen', 'florin', 'section', 'currency', 'quotesingle',
|
||||
'quotedblleft', 'guillemotleft', 'guilsinglleft', 'guilsinglright', 'fi', 'fl',
|
||||
'endash', 'dagger', 'daggerdbl', 'periodcentered', 'paragraph', 'bullet',
|
||||
'quotesinglbase', 'quotedblbase', 'quotedblright', 'guillemotright',
|
||||
'ellipsis', 'perthousand', 'questiondown', 'grave', 'acute', 'circumflex',
|
||||
'tilde', 'macron', 'breve', 'dotaccent', 'dieresis', 'ring', 'cedilla',
|
||||
'hungarumlaut', 'ogonek', 'caron', 'emdash', 'AE', 'ordfeminine', 'Lslash',
|
||||
'Oslash', 'OE', 'ordmasculine', 'ae', 'dotlessi', 'lslash', 'oslash', 'oe',
|
||||
'germandbls', 'onesuperior', 'logicalnot', 'mu', 'trademark', 'Eth', 'onehalf',
|
||||
'plusminus', 'Thorn', 'onequarter', 'divide', 'brokenbar', 'degree', 'thorn',
|
||||
'threequarters', 'twosuperior', 'registered', 'minus', 'eth', 'multiply',
|
||||
'threesuperior', 'copyright', 'Aacute', 'Acircumflex', 'Adieresis', 'Agrave',
|
||||
'Aring', 'Atilde', 'Ccedilla', 'Eacute', 'Ecircumflex', 'Edieresis', 'Egrave',
|
||||
'Iacute', 'Icircumflex', 'Idieresis', 'Igrave', 'Ntilde', 'Oacute',
|
||||
'Ocircumflex', 'Odieresis', 'Ograve', 'Otilde', 'Scaron', 'Uacute',
|
||||
'Ucircumflex', 'Udieresis', 'Ugrave', 'Yacute', 'Ydieresis', 'Zcaron',
|
||||
'aacute', 'acircumflex', 'adieresis', 'agrave', 'aring', 'atilde', 'ccedilla',
|
||||
'eacute', 'ecircumflex', 'edieresis', 'egrave', 'iacute', 'icircumflex',
|
||||
'idieresis', 'igrave', 'ntilde', 'oacute', 'ocircumflex', 'odieresis',
|
||||
'ograve', 'otilde', 'scaron', 'uacute', 'ucircumflex', 'udieresis', 'ugrave',
|
||||
'yacute', 'ydieresis', 'zcaron', 'exclamsmall', 'Hungarumlautsmall',
|
||||
'dollaroldstyle', 'dollarsuperior', 'ampersandsmall', 'Acutesmall',
|
||||
'parenleftsuperior', 'parenrightsuperior', 'twodotenleader', 'onedotenleader',
|
||||
'zerooldstyle', 'oneoldstyle', 'twooldstyle', 'threeoldstyle', 'fouroldstyle',
|
||||
'fiveoldstyle', 'sixoldstyle', 'sevenoldstyle', 'eightoldstyle',
|
||||
'nineoldstyle', 'commasuperior', 'threequartersemdash', 'periodsuperior',
|
||||
'questionsmall', 'asuperior', 'bsuperior', 'centsuperior', 'dsuperior',
|
||||
'esuperior', 'isuperior', 'lsuperior', 'msuperior', 'nsuperior', 'osuperior',
|
||||
'rsuperior', 'ssuperior', 'tsuperior', 'ff', 'ffi', 'ffl', 'parenleftinferior',
|
||||
'parenrightinferior', 'Circumflexsmall', 'hyphensuperior', 'Gravesmall',
|
||||
'Asmall', 'Bsmall', 'Csmall', 'Dsmall', 'Esmall', 'Fsmall', 'Gsmall', 'Hsmall',
|
||||
'Ismall', 'Jsmall', 'Ksmall', 'Lsmall', 'Msmall', 'Nsmall', 'Osmall', 'Psmall',
|
||||
'Qsmall', 'Rsmall', 'Ssmall', 'Tsmall', 'Usmall', 'Vsmall', 'Wsmall', 'Xsmall',
|
||||
'Ysmall', 'Zsmall', 'colonmonetary', 'onefitted', 'rupiah', 'Tildesmall',
|
||||
'exclamdownsmall', 'centoldstyle', 'Lslashsmall', 'Scaronsmall', 'Zcaronsmall',
|
||||
'Dieresissmall', 'Brevesmall', 'Caronsmall', 'Dotaccentsmall', 'Macronsmall',
|
||||
'figuredash', 'hypheninferior', 'Ogoneksmall', 'Ringsmall', 'Cedillasmall',
|
||||
'questiondownsmall', 'oneeighth', 'threeeighths', 'fiveeighths',
|
||||
'seveneighths', 'onethird', 'twothirds', 'zerosuperior', 'foursuperior',
|
||||
'fivesuperior', 'sixsuperior', 'sevensuperior', 'eightsuperior',
|
||||
'ninesuperior', 'zeroinferior', 'oneinferior', 'twoinferior', 'threeinferior',
|
||||
'fourinferior', 'fiveinferior', 'sixinferior', 'seveninferior',
|
||||
'eightinferior', 'nineinferior', 'centinferior', 'dollarinferior',
|
||||
'periodinferior', 'commainferior', 'Agravesmall', 'Aacutesmall',
|
||||
'Acircumflexsmall', 'Atildesmall', 'Adieresissmall', 'Aringsmall', 'AEsmall',
|
||||
'Ccedillasmall', 'Egravesmall', 'Eacutesmall', 'Ecircumflexsmall',
|
||||
'Edieresissmall', 'Igravesmall', 'Iacutesmall', 'Icircumflexsmall',
|
||||
'Idieresissmall', 'Ethsmall', 'Ntildesmall', 'Ogravesmall', 'Oacutesmall',
|
||||
'Ocircumflexsmall', 'Otildesmall', 'Odieresissmall', 'OEsmall', 'Oslashsmall',
|
||||
'Ugravesmall', 'Uacutesmall', 'Ucircumflexsmall', 'Udieresissmall',
|
||||
'Yacutesmall', 'Thornsmall', 'Ydieresissmall', '001.000', '001.001', '001.002',
|
||||
'001.003', 'Black', 'Bold', 'Book', 'Light', 'Medium', 'Regular', 'Roman',
|
||||
'Semibold'
|
||||
]
|
||||
# }}}
|
||||
|
||||
|
||||
STANDARD_CHARSETS = [ # {{{
|
||||
# ISOAdobe
|
||||
(".notdef", "space", "exclam", "quotedbl", "numbersign", "dollar",
|
||||
"percent", "ampersand", "quoteright", "parenleft", "parenright",
|
||||
"asterisk", "plus", "comma", "hyphen", "period", "slash", "zero",
|
||||
"one", "two", "three", "four", "five", "six", "seven", "eight", "nine",
|
||||
"colon", "semicolon", "less", "equal", "greater", "question", "at",
|
||||
"A", "B", "C", "D", "E", "F", "G", "H", "I", "J", "K", "L", "M", "N",
|
||||
"O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z",
|
||||
"bracketleft", "backslash", "bracketright", "asciicircum",
|
||||
"underscore", "quoteleft", "a", "b", "c", "d", "e", "f", "g", "h", "i",
|
||||
"j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w",
|
||||
"x", "y", "z", "braceleft", "bar", "braceright", "asciitilde",
|
||||
"exclamdown", "cent", "sterling", "fraction", "yen", "florin",
|
||||
"section", "currency", "quotesingle", "quotedblleft", "guillemotleft",
|
||||
"guilsinglleft", "guilsinglright", "fi", "fl", "endash", "dagger",
|
||||
"daggerdbl", "periodcentered", "paragraph", "bullet", "quotesinglbase",
|
||||
"quotedblbase", "quotedblright", "guillemotright", "ellipsis",
|
||||
"perthousand", "questiondown", "grave", "acute", "circumflex", "tilde",
|
||||
"macron", "breve", "dotaccent", "dieresis", "ring", "cedilla",
|
||||
"hungarumlaut", "ogonek", "caron", "emdash", "AE", "ordfeminine",
|
||||
"Lslash", "Oslash", "OE", "ordmasculine", "ae", "dotlessi", "lslash",
|
||||
"oslash", "oe", "germandbls", "onesuperior", "logicalnot", "mu",
|
||||
"trademark", "Eth", "onehalf", "plusminus", "Thorn", "onequarter",
|
||||
"divide", "brokenbar", "degree", "thorn", "threequarters",
|
||||
"twosuperior", "registered", "minus", "eth", "multiply",
|
||||
"threesuperior", "copyright", "Aacute", "Acircumflex", "Adieresis",
|
||||
"Agrave", "Aring", "Atilde", "Ccedilla", "Eacute", "Ecircumflex",
|
||||
"Edieresis", "Egrave", "Iacute", "Icircumflex", "Idieresis", "Igrave",
|
||||
"Ntilde", "Oacute", "Ocircumflex", "Odieresis", "Ograve", "Otilde",
|
||||
"Scaron", "Uacute", "Ucircumflex", "Udieresis", "Ugrave", "Yacute",
|
||||
"Ydieresis", "Zcaron", "aacute", "acircumflex", "adieresis", "agrave",
|
||||
"aring", "atilde", "ccedilla", "eacute", "ecircumflex", "edieresis",
|
||||
"egrave", "iacute", "icircumflex", "idieresis", "igrave", "ntilde",
|
||||
"oacute", "ocircumflex", "odieresis", "ograve", "otilde", "scaron",
|
||||
"uacute", "ucircumflex", "udieresis", "ugrave", "yacute", "ydieresis",
|
||||
"zcaron"),
|
||||
|
||||
# Expert
|
||||
("notdef", "space", "exclamsmall", "Hungarumlautsmall", "dollaroldstyle",
|
||||
"dollarsuperior", "ampersandsmall", "Acutesmall", "parenleftsuperior",
|
||||
"parenrightsuperior", "twodotenleader", "onedotenleader", "comma",
|
||||
"hyphen", "period", "fraction", "zerooldstyle", "oneoldstyle",
|
||||
"twooldstyle", "threeoldstyle", "fouroldstyle", "fiveoldstyle",
|
||||
"sixoldstyle", "sevenoldstyle", "eightoldstyle", "nineoldstyle",
|
||||
"colon", "semicolon", "commasuperior", "threequartersemdash",
|
||||
"periodsuperior", "questionsmall", "asuperior", "bsuperior",
|
||||
"centsuperior", "dsuperior", "esuperior", "isuperior", "lsuperior",
|
||||
"msuperior", "nsuperior", "osuperior", "rsuperior", "ssuperior",
|
||||
"tsuperior", "ff", "fi", "fl", "ffi", "ffl", "parenleftinferior",
|
||||
"parenrightinferior", "Circumflexsmall", "hyphensuperior",
|
||||
"Gravesmall", "Asmall", "Bsmall", "Csmall", "Dsmall", "Esmall",
|
||||
"Fsmall", "Gsmall", "Hsmall", "Ismall", "Jsmall", "Ksmall", "Lsmall",
|
||||
"Msmall", "Nsmall", "Osmall", "Psmall", "Qsmall", "Rsmall", "Ssmall",
|
||||
"Tsmall", "Usmall", "Vsmall", "Wsmall", "Xsmall", "Ysmall", "Zsmall",
|
||||
"colonmonetary", "onefitted", "rupiah", "Tildesmall",
|
||||
"exclamdownsmall", "centoldstyle", "Lslashsmall", "Scaronsmall",
|
||||
"Zcaronsmall", "Dieresissmall", "Brevesmall", "Caronsmall",
|
||||
"Dotaccentsmall", "Macronsmall", "figuredash", "hypheninferior",
|
||||
"Ogoneksmall", "Ringsmall", "Cedillasmall", "onequarter", "onehalf",
|
||||
"threequarters", "questiondownsmall", "oneeighth", "threeeighths",
|
||||
"fiveeighths", "seveneighths", "onethird", "twothirds", "zerosuperior",
|
||||
"onesuperior", "twosuperior", "threesuperior", "foursuperior",
|
||||
"fivesuperior", "sixsuperior", "sevensuperior", "eightsuperior",
|
||||
"ninesuperior", "zeroinferior", "oneinferior", "twoinferior",
|
||||
"threeinferior", "fourinferior", "fiveinferior", "sixinferior",
|
||||
"seveninferior", "eightinferior", "nineinferior", "centinferior",
|
||||
"dollarinferior", "periodinferior", "commainferior", "Agravesmall",
|
||||
"Aacutesmall", "Acircumflexsmall", "Atildesmall", "Adieresissmall",
|
||||
"Aringsmall", "AEsmall", "Ccedillasmall", "Egravesmall", "Eacutesmall",
|
||||
"Ecircumflexsmall", "Edieresissmall", "Igravesmall", "Iacutesmall",
|
||||
"Icircumflexsmall", "Idieresissmall", "Ethsmall", "Ntildesmall",
|
||||
"Ogravesmall", "Oacutesmall", "Ocircumflexsmall", "Otildesmall",
|
||||
"Odieresissmall", "OEsmall", "Oslashsmall", "Ugravesmall",
|
||||
"Uacutesmall", "Ucircumflexsmall", "Udieresissmall", "Yacutesmall",
|
||||
"Thornsmall", "Ydieresissmall"),
|
||||
|
||||
# Expert Subset
|
||||
(".notdef", "space", "dollaroldstyle", "dollarsuperior",
|
||||
"parenleftsuperior", "parenrightsuperior", "twodotenleader",
|
||||
"onedotenleader", "comma", "hyphen", "period", "fraction",
|
||||
"zerooldstyle", "oneoldstyle", "twooldstyle", "threeoldstyle",
|
||||
"fouroldstyle", "fiveoldstyle", "sixoldstyle", "sevenoldstyle",
|
||||
"eightoldstyle", "nineoldstyle", "colon", "semicolon",
|
||||
"commasuperior", "threequartersemdash", "periodsuperior",
|
||||
"asuperior", "bsuperior", "centsuperior", "dsuperior", "esuperior",
|
||||
"isuperior", "lsuperior", "msuperior", "nsuperior", "osuperior",
|
||||
"rsuperior", "ssuperior", "tsuperior", "ff", "fi", "fl", "ffi",
|
||||
"ffl", "parenleftinferior", "parenrightinferior", "hyphensuperior",
|
||||
"colonmonetary", "onefitted", "rupiah", "centoldstyle",
|
||||
"figuredash", "hypheninferior", "onequarter", "onehalf",
|
||||
"threequarters", "oneeighth", "threeeighths", "fiveeighths",
|
||||
"seveneighths", "onethird", "twothirds", "zerosuperior",
|
||||
"onesuperior", "twosuperior", "threesuperior", "foursuperior",
|
||||
"fivesuperior", "sixsuperior", "sevensuperior", "eightsuperior",
|
||||
"ninesuperior", "zeroinferior", "oneinferior", "twoinferior",
|
||||
"threeinferior", "fourinferior", "fiveinferior", "sixinferior",
|
||||
"seveninferior", "eightinferior", "nineinferior", "centinferior",
|
||||
"dollarinferior", "periodinferior", "commainferior"),
|
||||
] # }}}
|
||||
|
||||
@@ -0,0 +1,311 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
|
||||
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
from struct import pack, unpack_from
|
||||
from polyglot.builtins import range, unicode_type
|
||||
|
||||
t1_operand_encoding = [None] * 256
|
||||
t1_operand_encoding[0:32] = (32) * ["do_operator"]
|
||||
t1_operand_encoding[32:247] = (247 - 32) * ["read_byte"]
|
||||
t1_operand_encoding[247:251] = (251 - 247) * ["read_small_int1"]
|
||||
t1_operand_encoding[251:255] = (255 - 251) * ["read_small_int2"]
|
||||
t1_operand_encoding[255] = "read_long_int"
|
||||
|
||||
t2_operand_encoding = t1_operand_encoding[:]
|
||||
t2_operand_encoding[28] = "read_short_int"
|
||||
t2_operand_encoding[255] = "read_fixed_1616"
|
||||
|
||||
cff_dict_operand_encoding = t2_operand_encoding[:]
|
||||
cff_dict_operand_encoding[29] = "read_long_int"
|
||||
cff_dict_operand_encoding[30] = "read_real_number"
|
||||
cff_dict_operand_encoding[255] = "reserved"
|
||||
|
||||
real_nibbles = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
|
||||
'.', 'E', 'E-', None, '-']
|
||||
real_nibbles_map = {x:i for i, x in enumerate(real_nibbles)}
|
||||
|
||||
|
||||
class ByteCode(dict):
|
||||
|
||||
def read_byte(self, b0, data, index):
|
||||
return b0 - 139, index
|
||||
|
||||
def read_small_int1(self, b0, data, index):
|
||||
b1 = ord(data[index:index+1])
|
||||
return (b0-247)*256 + b1 + 108, index+1
|
||||
|
||||
def read_small_int2(self, b0, data, index):
|
||||
b1 = ord(data[index:index+1])
|
||||
return -(b0-251)*256 - b1 - 108, index+1
|
||||
|
||||
def read_short_int(self, b0, data, index):
|
||||
value, = unpack_from(b">h", data, index)
|
||||
return value, index+2
|
||||
|
||||
def read_long_int(self, b0, data, index):
|
||||
value, = unpack_from(b">l", data, index)
|
||||
return value, index+4
|
||||
|
||||
def read_fixed_1616(self, b0, data, index):
|
||||
value, = unpack_from(b">l", data, index)
|
||||
return value / 65536.0, index+4
|
||||
|
||||
def read_real_number(self, b0, data, index):
|
||||
number = ''
|
||||
while True:
|
||||
b = ord(data[index:index+1])
|
||||
index = index + 1
|
||||
nibble0 = (b & 0xf0) >> 4
|
||||
nibble1 = b & 0x0f
|
||||
if nibble0 == 0xf:
|
||||
break
|
||||
number = number + real_nibbles[nibble0]
|
||||
if nibble1 == 0xf:
|
||||
break
|
||||
number = number + real_nibbles[nibble1]
|
||||
return float(number), index
|
||||
|
||||
def write_float(self, f, encoding='ignored'):
|
||||
s = unicode_type(f).upper()
|
||||
if s[:2] == "0.":
|
||||
s = s[1:]
|
||||
elif s[:3] == "-0.":
|
||||
s = "-" + s[2:]
|
||||
nibbles = []
|
||||
while s:
|
||||
c = s[0]
|
||||
s = s[1:]
|
||||
if c == "E" and s[:1] == "-":
|
||||
s = s[1:]
|
||||
c = "E-"
|
||||
nibbles.append(real_nibbles_map[c])
|
||||
nibbles.append(0xf)
|
||||
if len(nibbles) % 2:
|
||||
nibbles.append(0xf)
|
||||
d = bytearray([30])
|
||||
for i in range(0, len(nibbles), 2):
|
||||
d.append(nibbles[i] << 4 | nibbles[i+1])
|
||||
return bytes(d)
|
||||
|
||||
def write_int(self, value, encoding="cff"):
|
||||
four_byte_op = {'cff':29, 't1':255}.get(encoding, None)
|
||||
|
||||
if -107 <= value <= 107:
|
||||
code = bytes(bytearray([value + 139]))
|
||||
elif 108 <= value <= 1131:
|
||||
value = value - 108
|
||||
code = bytes(bytearray([(value >> 8) + 247, (value & 0xFF)]))
|
||||
elif -1131 <= value <= -108:
|
||||
value = -value - 108
|
||||
code = bytes(bytearray([(value >> 8) + 251, (value & 0xFF)]))
|
||||
elif four_byte_op is None:
|
||||
# T2 only supports 2 byte ints
|
||||
code = bytes(bytearray([28])) + pack(b">h", value)
|
||||
else:
|
||||
code = bytes(bytearray([four_byte_op])) + pack(b">l", value)
|
||||
return code
|
||||
|
||||
def write_offset(self, value):
|
||||
return bytes(bytearray([29])) + pack(b">l", value)
|
||||
|
||||
def write_number(self, value, encoding="cff"):
|
||||
f = self.write_float if isinstance(value, float) else self.write_int
|
||||
return f(value, encoding)
|
||||
|
||||
|
||||
class Dict(ByteCode):
|
||||
|
||||
operand_encoding = cff_dict_operand_encoding
|
||||
TABLE = ()
|
||||
FILTERED = frozenset()
|
||||
OFFSETS = frozenset()
|
||||
|
||||
def __init__(self):
|
||||
ByteCode.__init__(self)
|
||||
|
||||
self.operators = {op:(name, arg) for op, name, arg, default in
|
||||
self.TABLE}
|
||||
self.defaults = {name:default for op, name, arg, default in self.TABLE}
|
||||
|
||||
def safe_get(self, name):
|
||||
return self.get(name, self.defaults[name])
|
||||
|
||||
def decompile(self, strings, global_subrs, data):
|
||||
self.strings = strings
|
||||
self.global_subrs = global_subrs
|
||||
self.stack = []
|
||||
index = 0
|
||||
while index < len(data):
|
||||
b0 = ord(data[index:index+1])
|
||||
index += 1
|
||||
handler = getattr(self, self.operand_encoding[b0])
|
||||
value, index = handler(b0, data, index)
|
||||
if value is not None:
|
||||
self.stack.append(value)
|
||||
|
||||
def do_operator(self, b0, data, index):
|
||||
if b0 == 12:
|
||||
op = (b0, ord(data[index:index+1]))
|
||||
index += 1
|
||||
else:
|
||||
op = b0
|
||||
operator, arg_type = self.operators[op]
|
||||
self.handle_operator(operator, arg_type)
|
||||
return None, index
|
||||
|
||||
def handle_operator(self, operator, arg_type):
|
||||
if isinstance(arg_type, tuple):
|
||||
value = ()
|
||||
for i in range(len(arg_type)-1, -1, -1):
|
||||
arg = arg_type[i]
|
||||
arghandler = getattr(self, 'arg_' + arg)
|
||||
value = (arghandler(operator),) + value
|
||||
else:
|
||||
arghandler = getattr(self, 'arg_' + arg_type)
|
||||
value = arghandler(operator)
|
||||
self[operator] = value
|
||||
|
||||
def arg_number(self, name):
|
||||
return self.stack.pop()
|
||||
|
||||
def arg_SID(self, name):
|
||||
return self.strings[self.stack.pop()]
|
||||
|
||||
def arg_array(self, name):
|
||||
ans = self.stack[:]
|
||||
del self.stack[:]
|
||||
return ans
|
||||
|
||||
def arg_delta(self, name):
|
||||
out = []
|
||||
current = 0
|
||||
for v in self.stack:
|
||||
current = current + v
|
||||
out.append(current)
|
||||
del self.stack[:]
|
||||
return out
|
||||
|
||||
def compile(self, strings):
|
||||
data = []
|
||||
for op, name, arg, default in self.TABLE:
|
||||
if name in self.FILTERED:
|
||||
continue
|
||||
val = self.safe_get(name)
|
||||
opcode = bytes(bytearray(op if isinstance(op, tuple) else [op]))
|
||||
if val != self.defaults[name]:
|
||||
self.encoding_offset = name in self.OFFSETS
|
||||
if isinstance(arg, tuple):
|
||||
if len(val) != len(arg):
|
||||
raise ValueError('Invalid argument %s for operator: %s'
|
||||
%(val, op))
|
||||
for typ, v in zip(arg, val):
|
||||
if typ == 'SID':
|
||||
val = strings(val)
|
||||
data.append(getattr(self, 'encode_'+typ)(v))
|
||||
else:
|
||||
if arg == 'SID':
|
||||
val = strings(val)
|
||||
data.append(getattr(self, 'encode_'+arg)(val))
|
||||
data.append(opcode)
|
||||
self.raw = b''.join(data)
|
||||
return self.raw
|
||||
|
||||
def encode_number(self, val):
|
||||
if self.encoding_offset:
|
||||
return self.write_offset(val)
|
||||
return self.write_number(val)
|
||||
|
||||
def encode_SID(self, val):
|
||||
return self.write_int(val)
|
||||
|
||||
def encode_array(self, val):
|
||||
return b''.join(map(self.encode_number, val))
|
||||
|
||||
def encode_delta(self, value):
|
||||
out = []
|
||||
last = 0
|
||||
for v in value:
|
||||
out.append(v - last)
|
||||
last = v
|
||||
return self.encode_array(out)
|
||||
|
||||
|
||||
class TopDict(Dict):
|
||||
|
||||
TABLE = (
|
||||
# opcode name argument type default
|
||||
((12, 30), 'ROS', ('SID','SID','number'), None,),
|
||||
((12, 20), 'SyntheticBase', 'number', None,),
|
||||
(0, 'version', 'SID', None,),
|
||||
(1, 'Notice', 'SID', None,),
|
||||
((12, 0), 'Copyright', 'SID', None,),
|
||||
(2, 'FullName', 'SID', None,),
|
||||
((12, 38), 'FontName', 'SID', None,),
|
||||
(3, 'FamilyName', 'SID', None,),
|
||||
(4, 'Weight', 'SID', None,),
|
||||
((12, 1), 'isFixedPitch', 'number', 0,),
|
||||
((12, 2), 'ItalicAngle', 'number', 0,),
|
||||
((12, 3), 'UnderlinePosition', 'number', None,),
|
||||
((12, 4), 'UnderlineThickness', 'number', 50,),
|
||||
((12, 5), 'PaintType', 'number', 0,),
|
||||
((12, 6), 'CharstringType', 'number', 2,),
|
||||
((12, 7), 'FontMatrix', 'array', [0.001,0,0,0.001,0,0],),
|
||||
(13, 'UniqueID', 'number', None,),
|
||||
(5, 'FontBBox', 'array', [0,0,0,0],),
|
||||
((12, 8), 'StrokeWidth', 'number', 0,),
|
||||
(14, 'XUID', 'array', None,),
|
||||
((12, 21), 'PostScript', 'SID', None,),
|
||||
((12, 22), 'BaseFontName', 'SID', None,),
|
||||
((12, 23), 'BaseFontBlend', 'delta', None,),
|
||||
((12, 31), 'CIDFontVersion', 'number', 0,),
|
||||
((12, 32), 'CIDFontRevision', 'number', 0,),
|
||||
((12, 33), 'CIDFontType', 'number', 0,),
|
||||
((12, 34), 'CIDCount', 'number', 8720,),
|
||||
(15, 'charset', 'number', 0,),
|
||||
((12, 35), 'UIDBase', 'number', None,),
|
||||
(16, 'Encoding', 'number', 0,),
|
||||
(18, 'Private', ('number','number'), None,),
|
||||
((12, 37), 'FDSelect', 'number', None,),
|
||||
((12, 36), 'FDArray', 'number', None,),
|
||||
(17, 'CharStrings', 'number', None,),
|
||||
)
|
||||
|
||||
# We will not write these operators out
|
||||
FILTERED = {'ROS', 'SyntheticBase', 'UniqueID', 'XUID',
|
||||
'CIDFontVersion', 'CIDFontRevision', 'CIDFontType', 'CIDCount',
|
||||
'UIDBase', 'Encoding', 'FDSelect', 'FDArray'}
|
||||
OFFSETS = {'charset', 'Encoding', 'CharStrings', 'Private'}
|
||||
|
||||
|
||||
class PrivateDict(Dict):
|
||||
|
||||
TABLE = (
|
||||
# opcode name argument type default
|
||||
(6, 'BlueValues', 'delta', None,),
|
||||
(7, 'OtherBlues', 'delta', None,),
|
||||
(8, 'FamilyBlues', 'delta', None,),
|
||||
(9, 'FamilyOtherBlues', 'delta', None,),
|
||||
((12, 9), 'BlueScale', 'number', 0.039625,),
|
||||
((12, 10), 'BlueShift', 'number', 7,),
|
||||
((12, 11), 'BlueFuzz', 'number', 1,),
|
||||
(10, 'StdHW', 'number', None,),
|
||||
(11, 'StdVW', 'number', None,),
|
||||
((12, 12), 'StemSnapH', 'delta', None,),
|
||||
((12, 13), 'StemSnapV', 'delta', None,),
|
||||
((12, 14), 'ForceBold', 'number', 0,),
|
||||
((12, 15), 'ForceBoldThreshold', 'number', None,), # deprecated
|
||||
((12, 16), 'lenIV', 'number', None,), # deprecated
|
||||
((12, 17), 'LanguageGroup', 'number', 0,),
|
||||
((12, 18), 'ExpansionFactor', 'number', 0.06,),
|
||||
((12, 19), 'initialRandomSeed', 'number', 0,),
|
||||
(20, 'defaultWidthX', 'number', 0,),
|
||||
(21, 'nominalWidthX', 'number', 0,),
|
||||
(19, 'Subrs', 'number', None,),
|
||||
)
|
||||
|
||||
OFFSETS = {'Subrs'}
|
||||
@@ -0,0 +1,221 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
|
||||
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
from struct import unpack_from, unpack, calcsize
|
||||
from functools import partial
|
||||
|
||||
from calibre.utils.fonts.sfnt import UnknownTable
|
||||
from calibre.utils.fonts.sfnt.errors import UnsupportedFont, NoGlyphs
|
||||
from calibre.utils.fonts.sfnt.cff.dict_data import TopDict, PrivateDict
|
||||
from calibre.utils.fonts.sfnt.cff.constants import (cff_standard_strings,
|
||||
STANDARD_CHARSETS)
|
||||
from polyglot.builtins import iteritems, itervalues, range
|
||||
|
||||
# Useful links
|
||||
# http://www.adobe.com/content/dam/Adobe/en/devnet/font/pdfs/5176.CFF.pdf
|
||||
# http://www.adobe.com/content/dam/Adobe/en/devnet/font/pdfs/5177.Type2.pdf
|
||||
|
||||
|
||||
class CFF(object):
|
||||
|
||||
def __init__(self, raw):
|
||||
(self.major_version, self.minor_version, self.header_size,
|
||||
self.offset_size) = unpack_from(b'>4B', raw)
|
||||
if (self.major_version, self.minor_version) != (1, 0):
|
||||
raise UnsupportedFont('The CFF table has unknown version: '
|
||||
'(%d, %d)'%(self.major_version, self.minor_version))
|
||||
offset = self.header_size
|
||||
|
||||
# Read Names Index
|
||||
self.font_names = Index(raw, offset)
|
||||
offset = self.font_names.pos
|
||||
if len(self.font_names) > 1:
|
||||
raise UnsupportedFont('CFF table has more than one font.')
|
||||
|
||||
# Read Top Dict
|
||||
self.top_index = Index(raw, offset)
|
||||
self.top_dict = TopDict()
|
||||
offset = self.top_index.pos
|
||||
|
||||
# Read strings
|
||||
self.strings = Strings(raw, offset)
|
||||
offset = self.strings.pos
|
||||
|
||||
# Read global subroutines
|
||||
self.global_subrs = Subrs(raw, offset)
|
||||
offset = self.global_subrs.pos
|
||||
|
||||
# Decompile Top Dict
|
||||
self.top_dict.decompile(self.strings, self.global_subrs, self.top_index[0])
|
||||
self.is_CID = 'ROS' in self.top_dict
|
||||
if self.is_CID:
|
||||
raise UnsupportedFont('Subsetting of CID keyed fonts is not supported')
|
||||
|
||||
# Read CharStrings (Glyph definitions)
|
||||
try:
|
||||
offset = self.top_dict['CharStrings']
|
||||
except KeyError:
|
||||
raise ValueError('This font has no CharStrings')
|
||||
cs_type = self.top_dict.safe_get('CharstringType')
|
||||
if cs_type != 2:
|
||||
raise UnsupportedFont('This font has unsupported CharstringType: '
|
||||
'%s'%cs_type)
|
||||
self.char_strings = CharStringsIndex(raw, offset)
|
||||
self.num_glyphs = len(self.char_strings)
|
||||
|
||||
# Read Private Dict
|
||||
self.private_dict = self.private_subrs = None
|
||||
pd = self.top_dict.safe_get('Private')
|
||||
if pd:
|
||||
size, offset = pd
|
||||
self.private_dict = PrivateDict()
|
||||
self.private_dict.decompile(self.strings, self.global_subrs,
|
||||
raw[offset:offset+size])
|
||||
if 'Subrs' in self.private_dict:
|
||||
self.private_subrs = Subrs(raw, offset +
|
||||
self.private_dict['Subrs'])
|
||||
|
||||
# Read charset (Glyph names)
|
||||
self.charset = Charset(raw, self.top_dict.safe_get('charset'),
|
||||
self.strings, self.num_glyphs, self.is_CID)
|
||||
|
||||
# import pprint
|
||||
# pprint.pprint(self.top_dict)
|
||||
# pprint.pprint(self.private_dict)
|
||||
|
||||
|
||||
class Index(list):
|
||||
|
||||
def __init__(self, raw, offset, prepend=()):
|
||||
list.__init__(self)
|
||||
self.extend(prepend)
|
||||
|
||||
count = unpack_from(b'>H', raw, offset)[0]
|
||||
offset += 2
|
||||
self.pos = offset
|
||||
|
||||
if count > 0:
|
||||
self.offset_size = unpack_from(b'>B', raw, offset)[0]
|
||||
offset += 1
|
||||
if self.offset_size == 3:
|
||||
offsets = [unpack(b'>L', b'\0' + raw[i:i+3])[0]
|
||||
for i in range(offset, offset+3*(count+1), 3)]
|
||||
else:
|
||||
fmt = {1:'B', 2:'H', 4:'L'}[self.offset_size]
|
||||
fmt = ('>%d%s'%(count+1, fmt)).encode('ascii')
|
||||
offsets = unpack_from(fmt, raw, offset)
|
||||
offset += self.offset_size * (count+1) - 1
|
||||
|
||||
for i in range(len(offsets)-1):
|
||||
off, noff = offsets[i:i+2]
|
||||
obj = raw[offset+off:offset+noff]
|
||||
self.append(obj)
|
||||
|
||||
try:
|
||||
self.pos = offset + offsets[-1]
|
||||
except IndexError:
|
||||
self.pos = offset
|
||||
|
||||
|
||||
class Strings(Index):
|
||||
|
||||
def __init__(self, raw, offset):
|
||||
super(Strings, self).__init__(raw, offset, prepend=[x.encode('ascii')
|
||||
for x in cff_standard_strings])
|
||||
|
||||
|
||||
class Charset(list):
|
||||
|
||||
def __init__(self, raw, offset, strings, num_glyphs, is_CID):
|
||||
super(Charset, self).__init__()
|
||||
self.standard_charset = offset if offset in {0, 1, 2} else None
|
||||
if is_CID and self.standard_charset is not None:
|
||||
raise ValueError("CID font must not use a standard charset")
|
||||
if self.standard_charset is None:
|
||||
self.append(b'.notdef')
|
||||
fmt = unpack_from(b'>B', raw, offset)[0]
|
||||
offset += 1
|
||||
f = {0:self.parse_fmt0, 1:self.parse_fmt1,
|
||||
2:partial(self.parse_fmt1, is_two_byte=True)}.get(fmt, None)
|
||||
if f is None:
|
||||
raise UnsupportedFont('This font uses unsupported charset '
|
||||
'table format: %d'%fmt)
|
||||
f(raw, offset, strings, num_glyphs, is_CID)
|
||||
|
||||
def parse_fmt0(self, raw, offset, strings, num_glyphs, is_CID):
|
||||
fmt = ('>%dH'%(num_glyphs-1)).encode('ascii')
|
||||
ids = unpack_from(fmt, raw, offset)
|
||||
if is_CID:
|
||||
ids = ('cid%05d'%x for x in ids)
|
||||
else:
|
||||
ids = (strings[x] for x in ids)
|
||||
self.extend(ids)
|
||||
|
||||
def parse_fmt1(self, raw, offset, strings, num_glyphs, is_CID,
|
||||
is_two_byte=False):
|
||||
fmt = b'>2H' if is_two_byte else b'>HB'
|
||||
sz = calcsize(fmt)
|
||||
count = 1
|
||||
while count < num_glyphs:
|
||||
first, nleft = unpack_from(fmt, raw, offset)
|
||||
offset += sz
|
||||
count += nleft + 1
|
||||
self.extend('cid%05d'%x if is_CID else strings[x] for x in
|
||||
range(first, first + nleft+1))
|
||||
|
||||
def lookup(self, glyph_id):
|
||||
if self.standard_charset is None:
|
||||
return self[glyph_id]
|
||||
return STANDARD_CHARSETS[self.standard_charset][glyph_id].encode('ascii')
|
||||
|
||||
def safe_lookup(self, glyph_id):
|
||||
try:
|
||||
return self.lookup(glyph_id)
|
||||
except (KeyError, IndexError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
class Subrs(Index):
|
||||
pass
|
||||
|
||||
|
||||
class CharStringsIndex(Index):
|
||||
pass
|
||||
|
||||
|
||||
class CFFTable(UnknownTable):
|
||||
|
||||
def decompile(self):
|
||||
self.cff = CFF(self.raw)
|
||||
|
||||
def subset(self, character_map, extra_glyphs):
|
||||
from calibre.utils.fonts.sfnt.cff.writer import Subset
|
||||
# Map codes from the cmap table to glyph names, this will be used to
|
||||
# reconstruct character_map for the subset font
|
||||
charset_map = {code:self.cff.charset.safe_lookup(glyph_id) for code,
|
||||
glyph_id in iteritems(character_map)}
|
||||
charset = set(itervalues(charset_map))
|
||||
charset.discard(None)
|
||||
if not charset and character_map:
|
||||
raise NoGlyphs('This font has no glyphs for the specified characters')
|
||||
charset |= {
|
||||
self.cff.charset.safe_lookup(glyph_id) for glyph_id in extra_glyphs}
|
||||
charset.discard(None)
|
||||
s = Subset(self.cff, charset)
|
||||
|
||||
# Rebuild character_map with the glyph ids from the subset font
|
||||
character_map.clear()
|
||||
for code, charname in iteritems(charset_map):
|
||||
glyph_id = s.charname_map.get(charname, None)
|
||||
if glyph_id:
|
||||
character_map[code] = glyph_id
|
||||
|
||||
# Check that raw is parseable
|
||||
CFF(s.raw)
|
||||
|
||||
self.raw = s.raw
|
||||
Reference in New Issue
Block a user