1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
|
from fontTools.misc.textTools import bytechr, byteord, bytesjoin, tobytes, tostr
from fontTools.misc import eexec
from .psOperators import (
PSOperators,
ps_StandardEncoding,
ps_array,
ps_boolean,
ps_dict,
ps_integer,
ps_literal,
ps_mark,
ps_name,
ps_operator,
ps_procedure,
ps_procmark,
ps_real,
ps_string,
)
import re
from collections.abc import Callable
from string import whitespace
import logging
log = logging.getLogger(__name__)
ps_special = b"()<>[]{}%" # / is one too, but we take care of that one differently
skipwhiteRE = re.compile(bytesjoin([b"[", whitespace, b"]*"]))
endofthingPat = bytesjoin([b"[^][(){}<>/%", whitespace, b"]*"])
endofthingRE = re.compile(endofthingPat)
commentRE = re.compile(b"%[^\n\r]*")
# XXX This not entirely correct as it doesn't allow *nested* embedded parens:
stringPat = rb"""
\(
(
(
[^()]* \ [()]
)
|
(
[^()]* \( [^()]* \)
)
)*
[^()]*
\)
"""
stringPat = b"".join(stringPat.split())
stringRE = re.compile(stringPat)
hexstringRE = re.compile(bytesjoin([b"<[", whitespace, b"0-9A-Fa-f]*>"]))
class PSTokenError(Exception):
pass
class PSError(Exception):
pass
class PSTokenizer(object):
def __init__(self, buf=b"", encoding="ascii"):
# Force self.buf to be a byte string
buf = tobytes(buf)
self.buf = buf
self.len = len(buf)
self.pos = 0
self.closed = False
self.encoding = encoding
def read(self, n=-1):
"""Read at most 'n' bytes from the buffer, or less if the read
hits EOF before obtaining 'n' bytes.
If 'n' is negative or omitted, read all data until EOF is reached.
"""
if self.closed:
raise ValueError("I/O operation on closed file")
if n is None or n < 0:
newpos = self.len
else:
newpos = min(self.pos + n, self.len)
r = self.buf[self.pos : newpos]
self.pos = newpos
return r
def close(self):
if not self.closed:
self.closed = True
del self.buf, self.pos
def getnexttoken(
self,
# localize some stuff, for performance
len=len,
ps_special=ps_special,
stringmatch=stringRE.match,
hexstringmatch=hexstringRE.match,
commentmatch=commentRE.match,
endmatch=endofthingRE.match,
):
self.skipwhite()
if self.pos >= self.len:
return None, None
pos = self.pos
buf = self.buf
char = bytechr(byteord(buf[pos]))
if char in ps_special:
if char in b"{}[]":
tokentype = "do_special"
token = char
elif char == b"%":
tokentype = "do_comment"
_, nextpos = commentmatch(buf, pos).span()
token = buf[pos:nextpos]
elif char == b"(":
tokentype = "do_string"
m = stringmatch(buf, pos)
if m is None:
raise PSTokenError("bad string at character %d" % pos)
_, nextpos = m.span()
token = buf[pos:nextpos]
elif char == b"<":
tokentype = "do_hexstring"
m = hexstringmatch(buf, pos)
if m is None:
raise PSTokenError("bad hexstring at character %d" % pos)
_, nextpos = m.span()
token = buf[pos:nextpos]
else:
raise PSTokenError("bad token at character %d" % pos)
else:
if char == b"/":
tokentype = "do_literal"
m = endmatch(buf, pos + 1)
else:
tokentype = ""
m = endmatch(buf, pos)
if m is None:
raise PSTokenError("bad token at character %d" % pos)
_, nextpos = m.span()
token = buf[pos:nextpos]
self.pos = pos + len(token)
token = tostr(token, encoding=self.encoding)
return tokentype, token
def skipwhite(self, whitematch=skipwhiteRE.match):
_, nextpos = whitematch(self.buf, self.pos).span()
self.pos = nextpos
def starteexec(self):
self.pos = self.pos + 1
self.dirtybuf = self.buf[self.pos :]
self.buf, R = eexec.decrypt(self.dirtybuf, 55665)
self.len = len(self.buf)
self.pos = 4
def stopeexec(self):
if not hasattr(self, "dirtybuf"):
return
self.buf = self.dirtybuf
del self.dirtybuf
class PSInterpreter(PSOperators):
def __init__(self, encoding="ascii"):
systemdict = {}
userdict = {}
self.encoding = encoding
self.dictstack = [systemdict, userdict]
self.stack = []
self.proclevel = 0
self.procmark = ps_procmark()
self.fillsystemdict()
def fillsystemdict(self):
systemdict = self.dictstack[0]
systemdict["["] = systemdict["mark"] = self.mark = ps_mark()
systemdict["]"] = ps_operator("]", self.do_makearray)
systemdict["true"] = ps_boolean(1)
systemdict["false"] = ps_boolean(0)
systemdict["StandardEncoding"] = ps_array(ps_StandardEncoding)
systemdict["FontDirectory"] = ps_dict({})
self.suckoperators(systemdict, self.__class__)
def suckoperators(self, systemdict, klass):
for name in dir(klass):
attr = getattr(self, name)
if isinstance(attr, Callable) and name[:3] == "ps_":
name = name[3:]
systemdict[name] = ps_operator(name, attr)
for baseclass in klass.__bases__:
self.suckoperators(systemdict, baseclass)
def interpret(self, data, getattr=getattr):
tokenizer = self.tokenizer = PSTokenizer(data, self.encoding)
getnexttoken = tokenizer.getnexttoken
do_token = self.do_token
handle_object = self.handle_object
try:
while 1:
tokentype, token = getnexttoken()
if not token:
break
if tokentype:
handler = getattr(self, tokentype)
object = handler(token)
else:
object = do_token(token)
if object is not None:
handle_object(object)
tokenizer.close()
self.tokenizer = None
except:
if self.tokenizer is not None:
log.debug(
"ps error:\n"
"- - - - - - -\n"
"%s\n"
">>>\n"
"%s\n"
"- - - - - - -",
self.tokenizer.buf[self.tokenizer.pos - 50 : self.tokenizer.pos],
self.tokenizer.buf[self.tokenizer.pos : self.tokenizer.pos + 50],
)
raise
def handle_object(self, object):
if not (self.proclevel or object.literal or object.type == "proceduretype"):
if object.type != "operatortype":
object = self.resolve_name(object.value)
if object.literal:
self.push(object)
else:
if object.type == "proceduretype":
self.call_procedure(object)
else:
object.function()
else:
self.push(object)
def call_procedure(self, proc):
handle_object = self.handle_object
for item in proc.value:
handle_object(item)
def resolve_name(self, name):
dictstack = self.dictstack
for i in range(len(dictstack) - 1, -1, -1):
if name in dictstack[i]:
return dictstack[i][name]
raise PSError("name error: " + str(name))
def do_token(
self,
token,
int=int,
float=float,
ps_name=ps_name,
ps_integer=ps_integer,
ps_real=ps_real,
):
try:
num = int(token)
except (ValueError, OverflowError):
try:
num = float(token)
except (ValueError, OverflowError):
if "#" in token:
hashpos = token.find("#")
try:
base = int(token[:hashpos])
num = int(token[hashpos + 1 :], base)
except (ValueError, OverflowError):
return ps_name(token)
else:
return ps_integer(num)
else:
return ps_name(token)
else:
return ps_real(num)
else:
return ps_integer(num)
def do_comment(self, token):
pass
def do_literal(self, token):
return ps_literal(token[1:])
def do_string(self, token):
return ps_string(token[1:-1])
def do_hexstring(self, token):
hexStr = "".join(token[1:-1].split())
if len(hexStr) % 2:
hexStr = hexStr + "0"
cleanstr = []
for i in range(0, len(hexStr), 2):
cleanstr.append(chr(int(hexStr[i : i + 2], 16)))
cleanstr = "".join(cleanstr)
return ps_string(cleanstr)
def do_special(self, token):
if token == "{":
self.proclevel = self.proclevel + 1
return self.procmark
elif token == "}":
proc = []
while 1:
topobject = self.pop()
if topobject == self.procmark:
break
proc.append(topobject)
self.proclevel = self.proclevel - 1
proc.reverse()
return ps_procedure(proc)
elif token == "[":
return self.mark
elif token == "]":
return ps_name("]")
else:
raise PSTokenError("huh?")
def push(self, object):
self.stack.append(object)
def pop(self, *types):
stack = self.stack
if not stack:
raise PSError("stack underflow")
object = stack[-1]
if types:
if object.type not in types:
raise PSError(
"typecheck, expected %s, found %s" % (repr(types), object.type)
)
del stack[-1]
return object
def do_makearray(self):
array = []
while 1:
topobject = self.pop()
if topobject == self.mark:
break
array.append(topobject)
array.reverse()
self.push(ps_array(array))
def close(self):
"""Remove circular references."""
del self.stack
del self.dictstack
def unpack_item(item):
tp = type(item.value)
if tp == dict:
newitem = {}
for key, value in item.value.items():
newitem[key] = unpack_item(value)
elif tp == list:
newitem = [None] * len(item.value)
for i in range(len(item.value)):
newitem[i] = unpack_item(item.value[i])
if item.type == "proceduretype":
newitem = tuple(newitem)
else:
newitem = item.value
return newitem
def suckfont(data, encoding="ascii"):
m = re.search(rb"/FontName\s+/([^ \t\n\r]+)\s+def", data)
if m:
fontName = m.group(1)
fontName = fontName.decode()
else:
fontName = None
interpreter = PSInterpreter(encoding=encoding)
interpreter.interpret(
b"/Helvetica 4 dict dup /Encoding StandardEncoding put definefont pop"
)
interpreter.interpret(data)
fontdir = interpreter.dictstack[0]["FontDirectory"].value
if fontName in fontdir:
rawfont = fontdir[fontName]
else:
# fall back, in case fontName wasn't found
fontNames = list(fontdir.keys())
if len(fontNames) > 1:
fontNames.remove("Helvetica")
fontNames.sort()
rawfont = fontdir[fontNames[0]]
interpreter.close()
return unpack_item(rawfont)
|
