/
afm.py
562 lines (471 loc) · 15.9 KB
/
afm.py
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
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
"""
This is a python interface to Adobe Font Metrics Files. Although a
number of other python implementations exist (and may be more complete
than mine) I decided not to go with them because either they were
either
1) copyrighted or used a non-BSD compatible license
2) had too many dependencies and I wanted a free standing lib
3) Did more than I needed and it was easier to write my own than
figure out how to just get what I needed from theirs
It is pretty easy to use, and requires only built-in python libs::
>>> from afm import AFM
>>> fh = open('ptmr8a.afm')
>>> afm = AFM(fh)
>>> afm.string_width_height('What the heck?')
(6220.0, 683)
>>> afm.get_fontname()
'Times-Roman'
>>> afm.get_kern_dist('A', 'f')
0
>>> afm.get_kern_dist('A', 'y')
-92.0
>>> afm.get_bbox_char('!')
[130, -9, 238, 676]
>>> afm.get_bbox_font()
[-168, -218, 1000, 898]
AUTHOR:
John D. Hunter <jdh2358@gmail.com>
"""
from __future__ import print_function
import sys
import os
import re
from _mathtext_data import uni2type1
#Convert string the a python type
# some afm files have floats where we are expecting ints -- there is
# probably a better way to handle this (support floats, round rather
# than truncate). But I don't know what the best approach is now and
# this change to _to_int should at least prevent mpl from crashing on
# these JDH (2009-11-06)
def _to_int(x):
return int(float(x))
_to_float = float
if sys.version_info[0] >= 3:
def _to_str(x):
return x.decode('utf8')
else:
_to_str = str
def _to_list_of_ints(s):
s = s.replace(b',', b' ')
return [_to_int(val) for val in s.split()]
def _to_list_of_floats(s):
return [_to_float(val) for val in s.split()]
def _to_bool(s):
if s.lower().strip() in (b'false', b'0', b'no'):
return False
else:
return True
def _sanity_check(fh):
"""
Check if the file at least looks like AFM.
If not, raise :exc:`RuntimeError`.
"""
# Remember the file position in case the caller wants to
# do something else with the file.
pos = fh.tell()
try:
line = fh.readline()
finally:
fh.seek(pos, 0)
# AFM spec, Section 4: The StartFontMetrics keyword [followed by a
# version number] must be the first line in the file, and the
# EndFontMetrics keyword must be the last non-empty line in the
# file. We just check the first line.
if not line.startswith(b'StartFontMetrics'):
raise RuntimeError('Not an AFM file')
def _parse_header(fh):
"""
Reads the font metrics header (up to the char metrics) and returns
a dictionary mapping *key* to *val*. *val* will be converted to the
appropriate python type as necessary; e.g.:
* 'False'->False
* '0'->0
* '-168 -218 1000 898'-> [-168, -218, 1000, 898]
Dictionary keys are
StartFontMetrics, FontName, FullName, FamilyName, Weight,
ItalicAngle, IsFixedPitch, FontBBox, UnderlinePosition,
UnderlineThickness, Version, Notice, EncodingScheme, CapHeight,
XHeight, Ascender, Descender, StartCharMetrics
"""
headerConverters = {
b'StartFontMetrics': _to_float,
b'FontName': _to_str,
b'FullName': _to_str,
b'FamilyName': _to_str,
b'Weight': _to_str,
b'ItalicAngle': _to_float,
b'IsFixedPitch': _to_bool,
b'FontBBox': _to_list_of_ints,
b'UnderlinePosition': _to_int,
b'UnderlineThickness': _to_int,
b'Version': _to_str,
b'Notice': _to_str,
b'EncodingScheme': _to_str,
b'CapHeight': _to_float, # Is the second version a mistake, or
b'Capheight': _to_float, # do some AFM files contain 'Capheight'? -JKS
b'XHeight': _to_float,
b'Ascender': _to_float,
b'Descender': _to_float,
b'StdHW': _to_float,
b'StdVW': _to_float,
b'StartCharMetrics': _to_int,
b'CharacterSet': _to_str,
b'Characters': _to_int,
}
d = {}
while 1:
line = fh.readline()
if not line:
break
line = line.rstrip()
if line.startswith(b'Comment'):
continue
lst = line.split(b' ', 1)
#print '%-s\t%-d line :: %-s' % ( fh.name, len(lst), line )
key = lst[0]
if len(lst) == 2:
val = lst[1]
else:
val = b''
#key, val = line.split(' ', 1)
try:
d[key] = headerConverters[key](val)
except ValueError:
print('Value error parsing header in AFM:',
key, val, file=sys.stderr)
continue
except KeyError:
print('Found an unknown keyword in AFM header (was %s)' % key,
file=sys.stderr)
continue
if key == b'StartCharMetrics':
return d
raise RuntimeError('Bad parse')
def _parse_char_metrics(fh):
"""
Return a character metric dictionary. Keys are the ASCII num of
the character, values are a (*wx*, *name*, *bbox*) tuple, where
*wx* is the character width, *name* is the postscript language
name, and *bbox* is a (*llx*, *lly*, *urx*, *ury*) tuple.
This function is incomplete per the standard, but thus far parses
all the sample afm files tried.
"""
ascii_d = {}
name_d = {}
while 1:
line = fh.readline()
if not line:
break
line = line.rstrip()
if line.startswith(b'EndCharMetrics'):
return ascii_d, name_d
vals = line.split(b';')[:4]
if len(vals) != 4:
raise RuntimeError('Bad char metrics line: %s' % line)
num = _to_int(vals[0].split()[1])
wx = _to_float(vals[1].split()[1])
name = vals[2].split()[1]
name = name.decode('ascii')
bbox = _to_list_of_floats(vals[3][2:])
bbox = map(int, bbox)
# Workaround: If the character name is 'Euro', give it the
# corresponding character code, according to WinAnsiEncoding (see PDF
# Reference).
if name == 'Euro':
num = 128
if num != -1:
ascii_d[num] = (wx, name, bbox)
name_d[name] = (wx, bbox)
raise RuntimeError('Bad parse')
def _parse_kern_pairs(fh):
"""
Return a kern pairs dictionary; keys are (*char1*, *char2*) tuples and
values are the kern pair value. For example, a kern pairs line like
``KPX A y -50``
will be represented as::
d[ ('A', 'y') ] = -50
"""
line = fh.readline()
if not line.startswith(b'StartKernPairs'):
raise RuntimeError('Bad start of kern pairs data: %s' % line)
d = {}
while 1:
line = fh.readline()
if not line:
break
line = line.rstrip()
if len(line) == 0:
continue
if line.startswith(b'EndKernPairs'):
fh.readline() # EndKernData
return d
vals = line.split()
if len(vals) != 4 or vals[0] != b'KPX':
raise RuntimeError('Bad kern pairs line: %s' % line)
c1, c2, val = _to_str(vals[1]), _to_str(vals[2]), _to_float(vals[3])
d[(c1, c2)] = val
raise RuntimeError('Bad kern pairs parse')
def _parse_composites(fh):
"""
Return a composites dictionary. Keys are the names of the
composites. Values are a num parts list of composite information,
with each element being a (*name*, *dx*, *dy*) tuple. Thus a
composites line reading:
CC Aacute 2 ; PCC A 0 0 ; PCC acute 160 170 ;
will be represented as::
d['Aacute'] = [ ('A', 0, 0), ('acute', 160, 170) ]
"""
d = {}
while 1:
line = fh.readline()
if not line:
break
line = line.rstrip()
if len(line) == 0:
continue
if line.startswith(b'EndComposites'):
return d
vals = line.split(b';')
cc = vals[0].split()
name, numParts = cc[1], _to_int(cc[2])
pccParts = []
for s in vals[1:-1]:
pcc = s.split()
name, dx, dy = pcc[1], _to_float(pcc[2]), _to_float(pcc[3])
pccParts.append((name, dx, dy))
d[name] = pccParts
raise RuntimeError('Bad composites parse')
def _parse_optional(fh):
"""
Parse the optional fields for kern pair data and composites
return value is a (*kernDict*, *compositeDict*) which are the
return values from :func:`_parse_kern_pairs`, and
:func:`_parse_composites` if the data exists, or empty dicts
otherwise
"""
optional = {
b'StartKernData': _parse_kern_pairs,
b'StartComposites': _parse_composites,
}
d = {b'StartKernData': {}, b'StartComposites': {}}
while 1:
line = fh.readline()
if not line:
break
line = line.rstrip()
if len(line) == 0:
continue
key = line.split()[0]
if key in optional:
d[key] = optional[key](fh)
l = (d[b'StartKernData'], d[b'StartComposites'])
return l
def parse_afm(fh):
"""
Parse the Adobe Font Metics file in file handle *fh*. Return value
is a (*dhead*, *dcmetrics*, *dkernpairs*, *dcomposite*) tuple where
*dhead* is a :func:`_parse_header` dict, *dcmetrics* is a
:func:`_parse_composites` dict, *dkernpairs* is a
:func:`_parse_kern_pairs` dict (possibly {}), and *dcomposite* is a
:func:`_parse_composites` dict (possibly {})
"""
_sanity_check(fh)
dhead = _parse_header(fh)
dcmetrics_ascii, dcmetrics_name = _parse_char_metrics(fh)
doptional = _parse_optional(fh)
return dhead, dcmetrics_ascii, dcmetrics_name, doptional[0], doptional[1]
class AFM(object):
def __init__(self, fh):
"""
Parse the AFM file in file object *fh*
"""
(dhead, dcmetrics_ascii, dcmetrics_name, dkernpairs, dcomposite) = \
parse_afm(fh)
self._header = dhead
self._kern = dkernpairs
self._metrics = dcmetrics_ascii
self._metrics_by_name = dcmetrics_name
self._composite = dcomposite
def get_bbox_char(self, c, isord=False):
if not isord:
c = ord(c)
wx, name, bbox = self._metrics[c]
return bbox
def string_width_height(self, s):
"""
Return the string width (including kerning) and string height
as a (*w*, *h*) tuple.
"""
if not len(s):
return 0, 0
totalw = 0
namelast = None
miny = 1e9
maxy = 0
for c in s:
if c == '\n':
continue
wx, name, bbox = self._metrics[ord(c)]
l, b, w, h = bbox
# find the width with kerning
try:
kp = self._kern[(namelast, name)]
except KeyError:
kp = 0
totalw += wx + kp
# find the max y
thismax = b + h
if thismax > maxy:
maxy = thismax
# find the min y
thismin = b
if thismin < miny:
miny = thismin
namelast = name
return totalw, maxy - miny
def get_str_bbox_and_descent(self, s):
"""
Return the string bounding box
"""
if not len(s):
return 0, 0, 0, 0
totalw = 0
namelast = None
miny = 1e9
maxy = 0
left = 0
if not isinstance(s, unicode):
s = s.decode('ascii')
for c in s:
if c == '\n':
continue
name = uni2type1.get(ord(c), 'question')
try:
wx, bbox = self._metrics_by_name[name]
except KeyError:
name = 'question'
wx, bbox = self._metrics_by_name[name]
l, b, w, h = bbox
if l < left:
left = l
# find the width with kerning
try:
kp = self._kern[(namelast, name)]
except KeyError:
kp = 0
totalw += wx + kp
# find the max y
thismax = b + h
if thismax > maxy:
maxy = thismax
# find the min y
thismin = b
if thismin < miny:
miny = thismin
namelast = name
return left, miny, totalw, maxy - miny, -miny
def get_str_bbox(self, s):
"""
Return the string bounding box
"""
return self.get_str_bbox_and_descent(s)[:4]
def get_name_char(self, c, isord=False):
"""
Get the name of the character, ie, ';' is 'semicolon'
"""
if not isord:
c = ord(c)
wx, name, bbox = self._metrics[c]
return name
def get_width_char(self, c, isord=False):
"""
Get the width of the character from the character metric WX
field
"""
if not isord:
c = ord(c)
wx, name, bbox = self._metrics[c]
return wx
def get_width_from_char_name(self, name):
"""
Get the width of the character from a type1 character name
"""
wx, bbox = self._metrics_by_name[name]
return wx
def get_height_char(self, c, isord=False):
"""
Get the height of character *c* from the bounding box. This
is the ink height (space is 0)
"""
if not isord:
c = ord(c)
wx, name, bbox = self._metrics[c]
return bbox[-1]
def get_kern_dist(self, c1, c2):
"""
Return the kerning pair distance (possibly 0) for chars *c1*
and *c2*
"""
name1, name2 = self.get_name_char(c1), self.get_name_char(c2)
return self.get_kern_dist_from_name(name1, name2)
def get_kern_dist_from_name(self, name1, name2):
"""
Return the kerning pair distance (possibly 0) for chars
*name1* and *name2*
"""
try:
return self._kern[(name1, name2)]
except:
return 0
def get_fontname(self):
"Return the font name, e.g., 'Times-Roman'"
return self._header[b'FontName']
def get_fullname(self):
"Return the font full name, e.g., 'Times-Roman'"
name = self._header.get(b'FullName')
if name is None: # use FontName as a substitute
name = self._header[b'FontName']
return name
def get_familyname(self):
"Return the font family name, e.g., 'Times'"
name = self._header.get(b'FamilyName')
if name is not None:
return name
# FamilyName not specified so we'll make a guess
name = self.get_fullname()
extras = br'(?i)([ -](regular|plain|italic|oblique|bold|semibold|light|ultralight|extra|condensed))+$'
return re.sub(extras, '', name)
def get_weight(self):
"Return the font weight, e.g., 'Bold' or 'Roman'"
return self._header[b'Weight']
def get_angle(self):
"Return the fontangle as float"
return self._header[b'ItalicAngle']
def get_capheight(self):
"Return the cap height as float"
return self._header[b'CapHeight']
def get_xheight(self):
"Return the xheight as float"
return self._header[b'XHeight']
def get_underline_thickness(self):
"Return the underline thickness as float"
return self._header[b'UnderlineThickness']
def get_horizontal_stem_width(self):
"""
Return the standard horizontal stem width as float, or *None* if
not specified in AFM file.
"""
return self._header.get(b'StdHW', None)
def get_vertical_stem_width(self):
"""
Return the standard vertical stem width as float, or *None* if
not specified in AFM file.
"""
return self._header.get(b'StdVW', None)
if __name__ == '__main__':
#pathname = '/usr/local/lib/R/afm/'
pathname = '/usr/local/share/fonts/afms/adobe'
for fname in os.listdir(pathname):
with open(os.path.join(pathname, fname)) as fh:
afm = AFM(fh)
w, h = afm.string_width_height('John Hunter is the Man!')