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
|
if not modules then modules = { } end modules ['typo-tal'] = {
version = 1.001,
comment = "companion to typo-tal.mkiv",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files"
}
-- I'll make it a bit more efficient and provide named instances too which is needed for
-- nested tables.
--
-- Currently we have two methods: text and number with some downward compatible
-- defaulting.
-- We can speed up by saving the current fontcharacters[font] + lastfont.
local next, type = next, type
local div = math.div
local utfbyte = utf.byte
local splitmethod = utilities.parsers.splitmethod
local nodecodes = nodes.nodecodes
local glyph_code = nodecodes.glyph
local glue_code = nodecodes.glue
local fontcharacters = fonts.hashes.characters
----- unicodes = fonts.hashes.unicodes
local categories = characters.categories -- nd
local variables = interfaces.variables
local v_text = variables.text
local v_number = variables.number
local nuts = nodes.nuts
local tonut = nuts.tonut
local tonode = nuts.tonode
local getnext = nuts.getnext
local getprev = nuts.getprev
local getid = nuts.getid
local getfont = nuts.getfont
local getchar = nuts.getchar
local getfield = nuts.getfield
local setfield = nuts.setfield
local getattr = nuts.getattr
local setattr = nuts.setattr
local insert_node_before = nuts.insert_before
local insert_node_after = nuts.insert_after
local traverse_list_by_id = nuts.traverse_id
local dimensions_of_list = nuts.dimensions
local first_glyph = nuts.first_glyph
local nodepool = nuts.pool
local new_kern = nodepool.kern
local new_gluespec = nodepool.gluespec
local tracers = nodes.tracers
local setcolor = tracers.colors.set
local tracedrule = tracers.pool.nuts.rule
local characteralign = { }
typesetters.characteralign = characteralign
local trace_split = false trackers.register("typesetters.characteralign", function(v) trace_split = true end)
local report = logs.reporter("aligning")
local a_characteralign = attributes.private("characteralign")
local a_character = attributes.private("characters")
local enabled = false
local datasets = false
local comma = 0x002C
local period = 0x002E
local punctuationspace = 0x2008
local validseparators = {
[comma] = true,
[period] = true,
[punctuationspace] = true,
}
local validsigns = {
[0x002B] = 0x002B, -- plus
[0x002D] = 0x2212, -- hyphen
[0x00B1] = 0x00B1, -- plusminus
[0x2212] = 0x2212, -- minus
[0x2213] = 0x2213, -- minusplus
}
local function traced_kern(w)
return tracedrule(w,nil,nil,"darkgray")
end
function characteralign.handler(originalhead,where)
if not datasets then
return originalhead, false
end
local head = tonut(originalhead)
-- local first = first_glyph(head) -- we could do that once
local first
for n in traverse_list_by_id(glyph_code,head) do
first = n
break
end
if not first then
return originalhead, false
end
local a = getattr(first,a_characteralign)
if not a or a == 0 then
return originalhead, false
end
local column = div(a,0xFFFF)
local row = a % 0xFFFF
local dataset = datasets and datasets[column] or setcharacteralign(column)
local separator = dataset.separator
local list = dataset.list
local b_start = nil
local b_stop = nil
local a_start = nil
local a_stop = nil
local c = nil
local current = first
local sign = nil
--
local validseparators = dataset.separators
local validsigns = dataset.signs
local method = dataset.method
-- we can think of constraints
if method == v_number then
while current do
local id = getid(current)
if id == glyph_code then
local char = getchar(current)
local font = getfont(current)
-- local unicode = unicodes[font][char]
local unicode = fontcharacters[font][char].unicode or char -- ignore tables
if not unicode then
-- no unicode so forget about it
elseif unicode == separator then
c = current
if trace_split then
setcolor(current,"darkred")
end
dataset.hasseparator = true
elseif categories[unicode] == "nd" or validseparators[unicode] then
if c then
if not a_start then
a_start = current
end
a_stop = current
if trace_split then
setcolor(current,validseparators[unicode] and "darkcyan" or "darkblue")
end
else
if not b_start then
if sign then
b_start = sign
local new = validsigns[getchar(sign)]
if char == new or not fontcharacters[getfont(sign)][new] then
if trace_split then
setcolor(sign,"darkyellow")
end
else
setfield(sign,"char",new)
if trace_split then
setcolor(sign,"darkmagenta")
end
end
sign = nil
b_stop = current
else
b_start = current
b_stop = current
end
else
b_stop = current
end
if trace_split and current ~= sign then
setcolor(current,validseparators[unicode] and "darkcyan" or "darkblue")
end
end
elseif not b_start then
sign = validsigns[unicode] and current
-- if trace_split then
-- setcolor(current,"darkgreen")
-- end
end
elseif (b_start or a_start) and id == glue_code then
-- maybe only in number mode
-- somewhat inefficient
local next = getnext(current)
local prev = getprev(current)
if next and prev and getid(next) == glyph_code and getid(prev) == glyph_code then -- too much checking
local width = fontcharacters[getfont(b_start)][separator or period].width
-- local spec = getfield(current,"spec")
-- free_spec(spec)
setfield(current,"spec",new_gluespec(width))
setattr(current,a_character,punctuationspace)
if a_start then
a_stop = current
elseif b_start then
b_stop = current
end
end
end
current = getnext(current)
end
else
while current do
local id = getid(current)
if id == glyph_code then
local char = getchar(current)
local font = getfont(current)
-- local unicode = unicodes[font][char]
local unicode = fontcharacters[font][char].unicode or char -- ignore tables
if not unicode then
-- no unicode so forget about it
elseif unicode == separator then
c = current
if trace_split then
setcolor(current,"darkred")
end
dataset.hasseparator = true
else
if c then
if not a_start then
a_start = current
end
a_stop = current
if trace_split then
setcolor(current,"darkgreen")
end
else
if not b_start then
b_start = current
end
b_stop = current
if trace_split then
setcolor(current,"darkblue")
end
end
end
end
current = getnext(current)
end
end
local entry = list[row]
if entry then
if not dataset.collected then
-- print("[maxbefore] [maxafter]")
local maxbefore = 0
local maxafter = 0
for k, v in next, list do
local before = v.before
local after = v.after
if before and before > maxbefore then
maxbefore = before
end
if after and after > maxafter then
maxafter = after
end
end
dataset.maxbefore = maxbefore
dataset.maxafter = maxafter
dataset.collected = true
end
local maxbefore = dataset.maxbefore
local maxafter = dataset.maxafter
local before = entry.before or 0
local after = entry.after or 0
local new_kern = trace_split and traced_kern or new_kern
if b_start then
if before < maxbefore then
head = insert_node_before(head,b_start,new_kern(maxbefore-before))
end
if not c then
-- print("[before]")
if dataset.hasseparator then
local width = fontcharacters[getfont(b_stop)][separator].width
insert_node_after(head,b_stop,new_kern(maxafter+width))
end
elseif a_start then
-- print("[before] [separator] [after]")
if after < maxafter then
insert_node_after(head,a_stop,new_kern(maxafter-after))
end
else
-- print("[before] [separator]")
if maxafter > 0 then
insert_node_after(head,c,new_kern(maxafter))
end
end
elseif a_start then
if c then
-- print("[separator] [after]")
if maxbefore > 0 then
head = insert_node_before(head,c,new_kern(maxbefore))
end
else
-- print("[after]")
local width = fontcharacters[getfont(b_stop)][separator].width
head = insert_node_before(head,a_start,new_kern(maxbefore+width))
end
if after < maxafter then
insert_node_after(head,a_stop,new_kern(maxafter-after))
end
elseif c then
-- print("[separator]")
if maxbefore > 0 then
head = insert_node_before(head,c,new_kern(maxbefore))
end
if maxafter > 0 then
insert_node_after(head,c,new_kern(maxafter))
end
end
else
entry = {
before = b_start and dimensions_of_list(b_start,getnext(b_stop)) or 0,
after = a_start and dimensions_of_list(a_start,getnext(a_stop)) or 0,
}
list[row] = entry
end
return tonode(head), true
end
-- If needed we can have more modes which then also means a faster simple handler
-- for non numbers.
function setcharacteralign(column,separator)
if not enabled then
nodes.tasks.enableaction("processors","typesetters.characteralign.handler")
enabled = true
end
if not datasets then
datasets = { }
end
local dataset = datasets[column] -- we can use a metatable
if not dataset then
local method, token
if separator then
method, token = splitmethod(separator)
if method and token then
separator = utfbyte(token) or comma
else
separator = utfbyte(separator) or comma
method = validseparators[separator] and v_number or v_text
end
else
separator = comma
method = v_number
end
dataset = {
separator = separator,
list = { },
maxafter = 0,
maxbefore = 0,
collected = false,
method = method,
separators = validseparators,
signs = validsigns,
}
datasets[column] = dataset
used = true
end
return dataset
end
local function resetcharacteralign()
datasets = false
end
characteralign.setcharacteralign = setcharacteralign
characteralign.resetcharacteralign = resetcharacteralign
commands.setcharacteralign = setcharacteralign
commands.resetcharacteralign = resetcharacteralign
|