/
opentype.py
1077 lines (966 loc) · 36.4 KB
/
opentype.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
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import time
from fontTools.pens.boundsPen import ControlBoundsPen
from fontTools.pens.hashPointPen import HashPointPen
from fontTools.ttLib import TTFont, TTLibError
from fontTools.ttLib.tables._g_l_y_f import (
OVERLAP_COMPOUND,
ROUND_XY_TO_GRID,
USE_MY_METRICS,
)
from fontTools.ttLib.tables._h_e_a_d import mac_epoch_diff
from extractor.exceptions import ExtractorError
from extractor.stream import InstructionStream
from extractor.tools import RelaxedInfo, copyAttr
TRUETYPE_INSTRUCTIONS_KEY = "public.truetype.instructions"
TRUETYPE_ROUND_KEY = "public.truetype.roundOffsetToGrid"
TRUETYPE_METRICS_KEY = "public.truetype.useMyMetrics"
TRUETYPE_OVERLAP_KEY = "public.truetype.overlap"
OBJECT_LIBS_KEY = "public.objectLibs"
# ----------------
# Public Functions
# ----------------
def isOpenType(pathOrFile):
try:
font = TTFont(pathOrFile)
del font
except TTLibError:
return False
return True
def extractFontFromOpenType(
pathOrFile,
destination,
doGlyphOrder=True,
doGlyphs=True,
doInfo=True,
doKerning=True,
doFeatures=True,
customFunctions=[],
doInstructions=True,
):
source = TTFont(pathOrFile)
if doInfo:
extractOpenTypeInfo(source, destination)
if doGlyphs:
extractOpenTypeGlyphs(source, destination)
extractUnicodeVariationSequences(source, destination)
if doGlyphOrder:
extractGlyphOrder(source, destination)
if doKerning:
kerning, groups = extractOpenTypeKerning(source, destination)
destination.groups.update(groups)
destination.kerning.clear()
destination.kerning.update(kerning)
if doFeatures:
features = extractOpenTypeFeatures(source)
destination.features.text = features
for function in customFunctions:
function(source, destination)
if doInstructions:
extractInstructions(source, destination)
source.close()
def extractGlyphOrder(source, destination):
glyphOrder = source.getGlyphOrder()
if len(glyphOrder):
destination.lib["public.glyphOrder"] = glyphOrder
# ---------------------------
# Unicode Variation Sequences
# ---------------------------
def extractUnicodeVariationSequences(source, destination):
"""
Extract the Unicode Variation Sequences
"""
cmap = source.get("cmap")
mapping = cmap.getBestCmap()
for subtable in cmap.tables:
if subtable.format == 14:
destination.lib["public.unicodeVariationSequences"] = {
"%04X" % variationSelector: {
"%04X" % charValue: glyphName if glyphName else mapping.get(charValue)
for (charValue, glyphName) in uvsList
}
for variationSelector, uvsList in subtable.uvsDict.items()
}
# ------------
# Instructions
# ------------
def extractInstructions(source, destination):
if "glyf" not in source:
return
lib = destination.lib[TRUETYPE_INSTRUCTIONS_KEY] = {
"formatVersion": "1",
"maxFunctionDefs": 0,
"maxInstructionDefs": 0,
"maxStackElements": 0,
"maxStorage": 0,
"maxTwilightPoints": 0,
"maxZones": 0,
}
extractControlValues(source, lib)
extractFontProgram(source, lib)
extractGlyphPrograms(source, destination)
extractMaxpValues(source, lib)
extractPreProgram(source, lib)
def extractControlValues(source, lib):
"""
Extract the TrueType control values table to the font lib.
"""
if "cvt " not in source:
return
cvt = source["cvt "]
lib["controlValue"] = {str(i): val for i, val in enumerate(cvt.values)}
def extractFontProgram(source, lib):
"""
Extract the TrueType font program to the font lib.
"""
if "fpgm" not in source:
return
fpgm = source["fpgm"].program
lib["fontProgram"] = _byteCodeToTtxAssembly(fpgm)
def extractGlyphPrograms(source, destination):
"""
Extract the TrueType pre-program to the font lib.
"""
if "glyf" not in source:
return
glyph_table = source["glyf"]
for name in glyph_table.keys():
glyph = glyph_table[name]
dest_glyph = destination[name]
if glyph.isComposite():
# Extract composite flags
_extractCompositeFlags(glyph, dest_glyph)
if not hasattr(glyph, "program"):
continue
hash_pen = HashPointPen(dest_glyph.width, destination)
dest_glyph.drawPoints(hash_pen)
lib = dest_glyph.lib[TRUETYPE_INSTRUCTIONS_KEY] = {
"formatVersion": "1",
"id": hash_pen.hash,
}
lib["assembly"] = _byteCodeToTtxAssembly(glyph.program)
def extractMaxpValues(source, lib):
"""
Extract the TrueType maximum profile values to the font lib.
"""
if "maxp" not in source:
return
maxp = source["maxp"]
lib.update(
{
"maxFunctionDefs": maxp.maxFunctionDefs,
"maxInstructionDefs": maxp.maxInstructionDefs,
"maxStackElements": maxp.maxStackElements,
"maxStorage": maxp.maxStorage,
"maxTwilightPoints": maxp.maxTwilightPoints,
"maxZones": maxp.maxZones,
}
)
def extractPreProgram(source, lib):
"""
Extract the TrueType pre-program to the font lib.
"""
if "prep" not in source:
return
prep = source["prep"].program
lib["controlValueProgram"] = _byteCodeToTtxAssembly(prep)
def _byteCodeToTtxAssembly(program):
stream = InstructionStream(program_bytes=program.getBytecode())
return "\n%s\n" % str(stream)
def _extractCompositeFlags(glyph, dest_glyph):
# Find the lib key or add it
if OBJECT_LIBS_KEY not in dest_glyph.lib:
dest_glyph.lib[OBJECT_LIBS_KEY] = {}
object_libs = dest_glyph.lib[OBJECT_LIBS_KEY]
for ci, c in enumerate(glyph.components):
flags = {}
flags[TRUETYPE_ROUND_KEY] = bool(c.flags & ROUND_XY_TO_GRID)
flags[TRUETYPE_METRICS_KEY] = bool(c.flags & USE_MY_METRICS)
if flags:
identifier = f"component{ci}"
dest_glyph.components[ci].identifier = identifier
object_libs[identifier] = flags
# Overlap is stored directly in the glyph lib
dest_glyph.lib["public.truetype.overlap"] = bool(
c.flags & OVERLAP_COMPOUND
)
# ----
# Info
# ----
def extractOpenTypeInfo(source, destination):
info = RelaxedInfo(destination.info)
_extractInfoHead(source, info)
_extractInfoName(source, info)
_extracInfoOS2(source, info)
_extractInfoHhea(source, info)
_extractInfoVhea(source, info)
_extractInfoPost(source, info)
_extractInfoCFF(source, info)
_extractInfoGasp(source, info)
def _extractInfoHead(source, info):
head = source["head"]
# version
version = str(round(head.fontRevision, 3))
versionMajor, versionMinor = version.split(".")
info.versionMajor = int(versionMajor)
info.versionMinor = int(versionMinor)
# upm
info.unitsPerEm = head.unitsPerEm
# created
format = "%Y/%m/%d %H:%M:%S"
created = head.created
created = time.gmtime(max(0, created + mac_epoch_diff))
info.openTypeHeadCreated = time.strftime(format, created)
# lowestRecPPEM
info.openTypeHeadLowestRecPPEM = head.lowestRecPPEM
# flags
info.openTypeHeadFlags = binaryToIntList(head.flags)
# styleMapStyleName
macStyle = binaryToIntList(head.macStyle)
styleMapStyleName = "regular"
if 0 in macStyle and 1 in macStyle:
styleMapStyleName = "bold italic"
elif 0 in macStyle:
styleMapStyleName = "bold"
elif 1 in macStyle:
styleMapStyleName = "italic"
info.styleMapStyleName = styleMapStyleName
def _extractInfoName(source, info):
records = []
nameIDs = {}
for record in source["name"].names:
nameID = record.nameID
platformID = record.platformID
encodingID = record.platEncID
languageID = record.langID
string = record.toUnicode()
nameIDs[nameID, platformID, encodingID, languageID] = string
records.append(
(
nameID,
platformID,
encodingID,
languageID,
dict(
nameID=nameID,
platformID=platformID,
encodingID=encodingID,
languageID=languageID,
string=string,
),
)
)
attributes = dict(
familyName=_priorityOrder(16) + _priorityOrder(1),
styleName=_priorityOrder(17) + _priorityOrder(2),
styleMapFamilyName=_priorityOrder(1),
# styleMapStyleName will be handled in head extraction
copyright=_priorityOrder(0),
trademark=_priorityOrder(7),
openTypeNameDesigner=_priorityOrder(9),
openTypeNameDesignerURL=_priorityOrder(12),
openTypeNameManufacturer=_priorityOrder(8),
openTypeNameManufacturerURL=_priorityOrder(11),
openTypeNameLicense=_priorityOrder(13),
openTypeNameLicenseURL=_priorityOrder(14),
openTypeNameVersion=_priorityOrder(5),
openTypeNameUniqueID=_priorityOrder(3),
openTypeNameDescription=_priorityOrder(10),
openTypeNamePreferredFamilyName=_priorityOrder(16),
openTypeNamePreferredSubfamilyName=_priorityOrder(17),
openTypeNameCompatibleFullName=_priorityOrder(18),
openTypeNameSampleText=_priorityOrder(20),
openTypeNameWWSFamilyName=_priorityOrder(21),
openTypeNameWWSSubfamilyName=_priorityOrder(22),
)
for attr, priority in attributes.items():
value = _skimNameIDs(nameIDs, priority)
if value is not None:
setattr(info, attr, value)
info.openTypeNameRecords = [record[-1] for record in sorted(records)]
def _priorityOrder(nameID):
priority = [
(nameID, 1, 0, 0),
(nameID, 1, None, None),
(nameID, None, None, None),
]
return priority
def _skimNameIDs(nameIDs, priority):
for (nameID, platformID, platEncID, langID) in priority:
for (nID, pID, pEID, lID), text in nameIDs.items():
if nID != nameID:
continue
if pID != platformID and platformID is not None:
continue
if pEID != platEncID and platEncID is not None:
continue
if lID != langID and langID is not None:
continue
return text
def _extracInfoOS2(source, info):
os2 = source["OS/2"]
# openTypeOS2WidthClass
copyAttr(os2, "usWidthClass", info, "openTypeOS2WidthClass")
# openTypeOS2WeightClass
copyAttr(os2, "usWeightClass", info, "openTypeOS2WeightClass")
# openTypeOS2Selection
if hasattr(os2, "fsSelection"):
fsSelection = binaryToIntList(os2.fsSelection)
fsSelection = [i for i in fsSelection if i in (1, 2, 3, 4)]
info.openTypeOS2Selection = fsSelection
# openTypeOS2VendorID
copyAttr(os2, "achVendID", info, "openTypeOS2VendorID")
## the string could be padded with null bytes. strip those.
if info.openTypeOS2VendorID.endswith("\x00"):
r = []
for c in reversed(info.openTypeOS2VendorID):
if r or c != "\x00":
r.insert(0, c)
info.openTypeOS2VendorID = "".join(r)
# openTypeOS2Panose
if hasattr(os2, "panose"):
info.openTypeOS2Panose = [
os2.panose.bFamilyType,
os2.panose.bSerifStyle,
os2.panose.bWeight,
os2.panose.bProportion,
os2.panose.bContrast,
os2.panose.bStrokeVariation,
os2.panose.bArmStyle,
os2.panose.bLetterForm,
os2.panose.bMidline,
os2.panose.bXHeight,
]
# openTypeOS2FamilyClass
# XXX info.openTypeOS2FamilyClass
if hasattr(os2, "ulUnicodeRange1"):
info.openTypeOS2UnicodeRanges = (
binaryToIntList(os2.ulUnicodeRange1)
+ binaryToIntList(os2.ulUnicodeRange2, 32)
+ binaryToIntList(os2.ulUnicodeRange3, 64)
+ binaryToIntList(os2.ulUnicodeRange4, 96)
)
if hasattr(os2, "ulCodePageRange1"):
info.openTypeOS2CodePageRanges = binaryToIntList(
os2.ulCodePageRange1
) + binaryToIntList(os2.ulCodePageRange2, 32)
copyAttr(os2, "sxHeight", info, "xHeight")
copyAttr(os2, "sCapHeight", info, "capHeight")
copyAttr(os2, "sTypoAscender", info, "ascender")
copyAttr(os2, "sTypoDescender", info, "descender")
copyAttr(os2, "sTypoAscender", info, "openTypeOS2TypoAscender")
copyAttr(os2, "sTypoDescender", info, "openTypeOS2TypoDescender")
copyAttr(os2, "sTypoLineGap", info, "openTypeOS2TypoLineGap")
copyAttr(os2, "usWinAscent", info, "openTypeOS2WinAscent")
copyAttr(os2, "usWinDescent", info, "openTypeOS2WinDescent")
if hasattr(os2, "fsType"):
info.openTypeOS2Type = binaryToIntList(os2.fsType)
copyAttr(os2, "ySubscriptXSize", info, "openTypeOS2SubscriptXSize")
copyAttr(os2, "ySubscriptYSize", info, "openTypeOS2SubscriptYSize")
copyAttr(os2, "ySubscriptXOffset", info, "openTypeOS2SubscriptXOffset")
copyAttr(os2, "ySubscriptYOffset", info, "openTypeOS2SubscriptYOffset")
copyAttr(os2, "ySuperscriptXSize", info, "openTypeOS2SuperscriptXSize")
copyAttr(os2, "ySuperscriptYSize", info, "openTypeOS2SuperscriptYSize")
copyAttr(os2, "ySuperscriptXOffset", info, "openTypeOS2SuperscriptXOffset")
copyAttr(os2, "ySuperscriptYOffset", info, "openTypeOS2SuperscriptYOffset")
copyAttr(os2, "yStrikeoutSize", info, "openTypeOS2StrikeoutSize")
copyAttr(os2, "yStrikeoutPosition", info, "openTypeOS2StrikeoutPosition")
def _extractInfoHhea(source, info):
if "hhea" not in source:
return
hhea = source["hhea"]
info.openTypeHheaAscender = hhea.ascent
info.openTypeHheaDescender = hhea.descent
info.openTypeHheaLineGap = hhea.lineGap
info.openTypeHheaCaretSlopeRise = hhea.caretSlopeRise
info.openTypeHheaCaretSlopeRun = hhea.caretSlopeRun
info.openTypeHheaCaretOffset = hhea.caretOffset
def _extractInfoVhea(source, info):
if "vhea" not in source:
return
vhea = source["vhea"]
info.openTypeVheaVertTypoAscender = vhea.ascent
info.openTypeVheaVertTypoDescender = vhea.descent
info.openTypeVheaVertTypoLineGap = vhea.lineGap
info.openTypeVheaCaretSlopeRise = vhea.caretSlopeRise
info.openTypeVheaCaretSlopeRun = vhea.caretSlopeRun
if hasattr(vhea, "caretOffset"):
info.openTypeVheaCaretOffset = vhea.caretOffset
def _extractInfoPost(source, info):
post = source["post"]
info.italicAngle = post.italicAngle
info.postscriptUnderlineThickness = post.underlineThickness
info.postscriptUnderlinePosition = post.underlinePosition
info.postscriptIsFixedPitch = bool(post.isFixedPitch)
def _extractInfoCFF(source, info):
if "CFF " not in source:
return
cff = source["CFF "].cff
info.postscriptFontName = cff.fontNames[0]
# TopDict
topDict = cff.topDictIndex[0]
info.postscriptFullName = topDict.rawDict.get("FullName", None)
info.postscriptWeightName = topDict.rawDict.get("Weight", None)
# Private
# CID doesn't have this, so safely extract.
if hasattr(topDict, "Private"):
private = topDict.Private
info.postscriptBlueValues = private.rawDict.get("BlueValues", [])
info.postscriptOtherBlues = private.rawDict.get("OtherBlues", [])
info.postscriptFamilyBlues = private.rawDict.get("FamilyBlues", [])
info.postscriptFamilyOtherBlues = private.rawDict.get(
"FamilyOtherBlues", []
)
info.postscriptStemSnapH = private.rawDict.get("StemSnapH", [])
info.postscriptStemSnapV = private.rawDict.get("StemSnapV", [])
info.postscriptBlueFuzz = private.rawDict.get("BlueFuzz", None)
info.postscriptBlueShift = private.rawDict.get("BlueShift", None)
info.postscriptBlueScale = private.rawDict.get("BlueScale", None)
info.postscriptForceBold = bool(private.rawDict.get("ForceBold", None))
info.postscriptNominalWidthX = private.rawDict.get(
"nominalWidthX", None
)
info.postscriptDefaultWidthX = private.rawDict.get(
"defaultWidthX", None
)
# XXX postscriptSlantAngle
# XXX postscriptUniqueID
def _extractInfoGasp(source, info):
if "gasp" not in source:
return
gasp = source["gasp"]
records = []
for size, bits in sorted(gasp.gaspRange.items()):
behavior = []
if bits & 0x0001:
behavior.append(0)
if bits & 0x0002:
behavior.append(1)
if bits & 0x0004:
behavior.append(2)
if bits & 0x0008:
behavior.append(3)
record = dict(rangeMaxPPEM=size, rangeGaspBehavior=behavior)
records.append(record)
info.openTypeGaspRangeRecords = records
# Tools
def binaryToIntList(value, start=0):
intList = []
counter = start
while value:
if value & 1:
intList.append(counter)
value >>= 1
counter += 1
return intList
# --------
# Outlines
# --------
def extractOpenTypeGlyphs(source, destination):
# grab the cmap
vmtx = source.get("vmtx")
vorg = source.get("VORG")
is_ttf = "glyf" in source
reversedMapping = source.get("cmap").buildReversed()
# grab the glyphs
glyphSet = source.getGlyphSet()
for glyphName in glyphSet.keys():
sourceGlyph = glyphSet[glyphName]
# make the new glyph
destination.newGlyph(glyphName)
destinationGlyph = destination[glyphName]
# outlines
if is_ttf:
pen = destinationGlyph.getPointPen()
sourceGlyph.drawPoints(pen)
else:
pen = destinationGlyph.getPen()
sourceGlyph.draw(pen)
# width
destinationGlyph.width = sourceGlyph.width
# unicodes
destinationGlyph.unicodes = list(reversedMapping.get(glyphName, []))
# height and vertical origin
if vmtx is not None and glyphName in vmtx.metrics:
destinationGlyph.height = vmtx[glyphName][0]
if vorg is not None:
if glyphName in vorg.VOriginRecords:
destinationGlyph.verticalOrigin = vorg[glyphName]
else:
destinationGlyph.verticalOrigin = vorg.defaultVertOriginY
else:
tsb = vmtx[glyphName][1]
bounds_pen = ControlBoundsPen(glyphSet)
sourceGlyph.draw(bounds_pen)
if bounds_pen.bounds is None:
continue
xMin, yMin, xMax, yMax = bounds_pen.bounds
destinationGlyph.verticalOrigin = tsb + yMax
# -------
# Kerning
# -------
def extractOpenTypeKerning(source, destination):
kerning = {}
groups = {}
if "GPOS" in source:
kerning, groups = _extractOpenTypeKerningFromGPOS(source)
elif "kern" in source:
kerning = _extractOpenTypeKerningFromKern(source)
groups = {}
for name, group in groups.items():
groups[name] = list(sorted(group))
return kerning, groups
def _extractOpenTypeKerningFromGPOS(source):
gpos = source["GPOS"].table
# get an ordered list of scripts
scriptOrder = _makeScriptOrder(gpos)
# extract kerning and classes from each applicable lookup
(
kerningDictionaries,
leftClassDictionaries,
rightClassDictionaries,
) = _gatherDataFromLookups(gpos, scriptOrder)
# merge all kerning pairs
kerning = _mergeKerningDictionaries(kerningDictionaries)
# get rid of groups that have only one member
leftSingleMemberGroups = _findSingleMemberGroups(leftClassDictionaries)
rightSingleMemberGroups = _findSingleMemberGroups(rightClassDictionaries)
# filter out the single glyph groups from the kerning
kerning = _removeSingleMemberGroupReferences(
kerning, leftSingleMemberGroups, rightSingleMemberGroups
)
# merge groups that have the exact same member list
leftClasses, leftClassRename = _mergeClasses(leftClassDictionaries)
rightClasses, rightClassRename = _mergeClasses(rightClassDictionaries)
# search for overlapping groups and raise an error if any were found
_validateClasses(leftClasses)
_validateClasses(rightClasses)
# populate the class marging into the kerning
kerning = _replaceRenamedPairMembers(
kerning, leftClassRename, rightClassRename
)
# rename the groups to final names
leftClassRename = _renameClasses(leftClasses, "public.kern1.")
rightClassRename = _renameClasses(rightClasses, "public.kern2.")
# populate the final group names
kerning = _replaceRenamedPairMembers(
kerning, leftClassRename, rightClassRename
)
leftGroups = _setGroupNames(leftClasses, leftClassRename)
rightGroups = _setGroupNames(rightClasses, rightClassRename)
# combine the side groups
groups = {}
groups.update(leftGroups)
groups.update(rightGroups)
# done.
return kerning, groups
def _makeScriptOrder(gpos):
"""
Run therough GPOS and make an alphabetically
ordered list of scripts. If DFLT is in the list,
move it to the front.
"""
scripts = []
for scriptRecord in gpos.ScriptList.ScriptRecord:
scripts.append(scriptRecord.ScriptTag)
if "DFLT" in scripts:
scripts.remove("DFLT")
scripts.insert(0, "DFLT")
return sorted(scripts)
def _gatherDataFromLookups(gpos, scriptOrder):
"""
Gather kerning and classes from the applicable lookups
and return them in script order.
"""
lookupIndexes = _gatherLookupIndexes(gpos)
seenLookups = set()
kerningDictionaries = []
leftClassDictionaries = []
rightClassDictionaries = []
for script in scriptOrder:
kerning = []
leftClasses = []
rightClasses = []
for lookupIndex in lookupIndexes[script]:
if lookupIndex in seenLookups:
continue
seenLookups.add(lookupIndex)
result = _gatherKerningForLookup(gpos, lookupIndex)
if result is None:
continue
k, lG, rG = result
kerning.append(k)
leftClasses.append(lG)
rightClasses.append(rG)
if kerning:
kerningDictionaries.append(kerning)
leftClassDictionaries.append(leftClasses)
rightClassDictionaries.append(rightClasses)
return kerningDictionaries, leftClassDictionaries, rightClassDictionaries
def _gatherLookupIndexes(gpos):
"""
Gather a mapping of script to lookup indexes
referenced by the kern feature for each script.
Returns a dictionary of this structure:
{
"latn" : [0],
"DFLT" : [0]
}
"""
# gather the indexes of the kern features
kernFeatureIndexes = [
index
for index, featureRecord in enumerate(gpos.FeatureList.FeatureRecord)
if featureRecord.FeatureTag == "kern"
]
# find scripts and languages that have kern features
scriptKernFeatureIndexes = {}
for scriptRecord in gpos.ScriptList.ScriptRecord:
script = scriptRecord.ScriptTag
thisScriptKernFeatureIndexes = []
defaultLangSysRecord = scriptRecord.Script.DefaultLangSys
if defaultLangSysRecord is not None:
f = []
for featureIndex in defaultLangSysRecord.FeatureIndex:
if featureIndex not in kernFeatureIndexes:
continue
f.append(featureIndex)
if f:
thisScriptKernFeatureIndexes.append((None, f))
if scriptRecord.Script.LangSysRecord is not None:
for langSysRecord in scriptRecord.Script.LangSysRecord:
langSys = langSysRecord.LangSysTag
f = []
for featureIndex in langSysRecord.LangSys.FeatureIndex:
if featureIndex not in kernFeatureIndexes:
continue
f.append(featureIndex)
if f:
thisScriptKernFeatureIndexes.append((langSys, f))
scriptKernFeatureIndexes[script] = thisScriptKernFeatureIndexes
# convert the feature indexes to lookup indexes
scriptLookupIndexes = {}
for script, featureDefinitions in scriptKernFeatureIndexes.items():
lookupIndexes = scriptLookupIndexes[script] = []
for language, featureIndexes in featureDefinitions:
for featureIndex in featureIndexes:
featureRecord = gpos.FeatureList.FeatureRecord[featureIndex]
for lookupIndex in featureRecord.Feature.LookupListIndex:
if lookupIndex not in lookupIndexes:
lookupIndexes.append(lookupIndex)
# done
return scriptLookupIndexes
def _gatherKerningForLookup(gpos, lookupIndex):
"""
Gather the kerning and class data for a particular lookup.
Returns kerning, left clases, right classes.
The kerning dictionary is of this structure:
{
("a", "a") : 10,
((1, 1, 3), "a") : -20
}
The class dictionaries have this structure:
{
(1, 1, 3) : ["x", "y", "z"]
}
Where the tuple means this:
(lookup index, subtable index, class index)
"""
allKerning = {}
allLeftClasses = {}
allRightClasses = {}
lookup = gpos.LookupList.Lookup[lookupIndex]
# only handle pair positioning and extension
if lookup.LookupType not in (2, 9):
return
for subtableIndex, subtable in enumerate(lookup.SubTable):
if lookup.LookupType == 2:
format = subtable.Format
lookupType = subtable.LookupType
if (lookupType, format) == (2, 1):
kerning = _handleLookupType2Format1(subtable)
allKerning.update(kerning)
elif (lookupType, format) == (2, 2):
kerning, leftClasses, rightClasses = _handleLookupType2Format2(
subtable, lookupIndex, subtableIndex
)
allKerning.update(kerning)
allLeftClasses.update(leftClasses)
allRightClasses.update(rightClasses)
elif lookup.LookupType == 9:
extSubtable = subtable.ExtSubTable
format = extSubtable.Format
lookupType = extSubtable.LookupType
if (lookupType, format) == (2, 1):
kerning = _handleLookupType2Format1(extSubtable)
allKerning.update(kerning)
elif (lookupType, format) == (2, 2):
kerning, leftClasses, rightClasses = _handleLookupType2Format2(
extSubtable, lookupIndex, subtableIndex
)
allKerning.update(kerning)
allLeftClasses.update(leftClasses)
allRightClasses.update(rightClasses)
# done
return allKerning, allLeftClasses, allRightClasses
def _handleLookupType2Format1(subtable):
"""
Extract a kerning dictionary from a Lookup Type 2 Format 1.
"""
kerning = {}
coverage = subtable.Coverage.glyphs
valueFormat1 = subtable.ValueFormat1
pairSets = subtable.PairSet
for index, leftGlyphName in enumerate(coverage):
pairSet = pairSets[index]
for pairValueRecord in pairSet.PairValueRecord:
rightGlyphName = pairValueRecord.SecondGlyph
if valueFormat1:
value = pairValueRecord.Value1
else:
value = pairValueRecord.Value2
if hasattr(value, "XAdvance"):
value = value.XAdvance
kerning[leftGlyphName, rightGlyphName] = value
return kerning
def _handleLookupType2Format2(subtable, lookupIndex, subtableIndex):
"""
Extract kerning, left class and right class dictionaries from a Lookup Type 2 Format 2.
"""
# extract the classes
leftClasses = _extractFeatureClasses(
lookupIndex=lookupIndex,
subtableIndex=subtableIndex,
classDefs=subtable.ClassDef1.classDefs,
coverage=subtable.Coverage.glyphs,
)
rightClasses = _extractFeatureClasses(
lookupIndex=lookupIndex,
subtableIndex=subtableIndex,
classDefs=subtable.ClassDef2.classDefs,
)
# extract the pairs
kerning = {}
for class1RecordIndex, class1Record in enumerate(subtable.Class1Record):
for class2RecordIndex, class2Record in enumerate(
class1Record.Class2Record
):
leftClass = (lookupIndex, subtableIndex, class1RecordIndex)
rightClass = (lookupIndex, subtableIndex, class2RecordIndex)
valueFormat1 = subtable.ValueFormat1
if valueFormat1:
value = class2Record.Value1
else:
value = class2Record.Value2
if hasattr(value, "XAdvance") and value.XAdvance != 0:
value = value.XAdvance
kerning[leftClass, rightClass] = value
return kerning, leftClasses, rightClasses
def _mergeKerningDictionaries(kerningDictionaries):
"""
Merge all of the kerning dictionaries found into
one flat dictionary.
"""
# work through the dictionaries backwards since
# this uses an update to load the kerning. this
# will ensure that the script order is honored.
kerning = {}
for dictionaryGroup in reversed(kerningDictionaries):
for dictionary in dictionaryGroup:
kerning.update(dictionary)
# done.
return kerning
def _findSingleMemberGroups(classDictionaries):
"""
Find all classes that have only one member.
"""
toRemove = {}
for classDictionaryGroup in classDictionaries:
for classDictionary in classDictionaryGroup:
for name, members in list(classDictionary.items()):
if len(members) == 1:
toRemove[name] = list(members)[0]
del classDictionary[name]
return toRemove
def _removeSingleMemberGroupReferences(kerning, leftGroups, rightGroups):
"""
Translate group names into glyph names in pairs
if the group only contains one glyph.
"""
new = {}
for (left, right), value in kerning.items():
left = leftGroups.get(left, left)
right = rightGroups.get(right, right)
new[left, right] = value
return new
def _mergeClasses(classDictionaries):
"""
Look for classes that have the exact same list
of members and flag them for removal.
This returns left classes, left rename map,
right classes and right rename map.
The classes have the standard class structure.
The rename maps have this structure:
{
(1, 1, 3) : (2, 3, 4),
old name : new name
}
Where the key is the class that should be
preserved and the value is a list of classes
that should be removed.
"""
# build a mapping of members to names
memberTree = {}
for classDictionaryGroup in classDictionaries:
for classDictionary in classDictionaryGroup:
for name, members in classDictionary.items():
if members not in memberTree:
memberTree[members] = set()
memberTree[members].add(name)
# find members that have more than one name
classes = {}
rename = {}
for members, names in memberTree.items():
name = names.pop()
if len(names) > 0:
for otherName in names:
rename[otherName] = name
classes[name] = members
return classes, rename
def _setGroupNames(classes, classRename):
"""
Set the final names into the groups.
"""
groups = {}
for groupName, glyphList in classes.items():
groupName = classRename.get(groupName, groupName)
# if the glyph list has only one member,
# the glyph name will be used in the pairs.
# no group is needed.
if len(glyphList) == 1:
continue
groups[groupName] = glyphList
return groups
def _validateClasses(classes):
"""
Check to make sure that a glyph is not part of more than
one class. If this is found, an ExtractorError is raised.
"""
glyphToClass = {}
for className, glyphList in classes.items():
for glyphName in glyphList:
if glyphName not in glyphToClass:
glyphToClass[glyphName] = set()
glyphToClass[glyphName].add(className)
for glyphName, groupList in glyphToClass.items():
if len(groupList) > 1:
raise ExtractorError(
"Kerning classes are in an conflicting state."
)
def _replaceRenamedPairMembers(kerning, leftRename, rightRename):
"""
Populate the renamed pair members into the kerning.
"""
renamedKerning = {}
for (left, right), value in kerning.items():
left = leftRename.get(left, left)
right = rightRename.get(right, right)
renamedKerning[left, right] = value
return renamedKerning
def _renameClasses(classes, prefix):
"""
Replace class IDs with nice strings.
"""
renameMap = {}
for classID, glyphList in classes.items():
if len(glyphList) == 0:
groupName = "%s_empty_lu.%d_st.%d_cl.%d" % (
prefix,
classID[0],
classID[1],
classID[2],
)
elif len(glyphList) == 1:
groupName = list(glyphList)[0]
else:
glyphList = list(sorted(glyphList))
groupName = prefix + glyphList[0]
if groupName in renameMap.values():
print(" Dropping duplicate group rename target:")
print(f" {classID} -> {groupName}")
print(f" Glyphs: {glyphList}")
else:
renameMap[classID] = groupName
if len(list(renameMap.values())) != len(set(renameMap.values())):
print("Rename list for classes contains duplicates:")
values = list(renameMap.values())
for v in values:
if values.count(v) > 1:
print(f" {v}")