-
-
Notifications
You must be signed in to change notification settings - Fork 21
/
uni.go
1145 lines (1001 loc) · 32.7 KB
/
uni.go
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
//go:generate go run gen.go
// Command uni prints Unicode information about characters.
package main
import (
"errors"
"fmt"
"os"
"regexp"
"slices"
"sort"
"strconv"
"strings"
"unicode/utf8"
"zgo.at/uni/v2/unidata"
"zgo.at/zli"
"zgo.at/zstd/zmap"
"zgo.at/zstd/zstring"
)
var (
errNoMatches = errors.New("no matches")
version = "git"
)
var usageShort = zli.Usage(zli.UsageHeaders|zli.UsageProgram|zli.UsageTrim, `
Usage: %(prog) [command] [flags]
uni queries the unicode database. https://github.com/arp242/uni
Flags:
-f, -format Output format.
-a, -as How to print the results: list (default), json, or table.
-c, -compact More compact output.
-r, -raw Don't use graphical variants or add combining characters.
-p, -pager Output to $PAGER.
-o, -or Use "or" when searching instead of "and".
Commands:
list List Unicode data such as blocks, categories, etc.
identify Identify all the characters in the given strings.
search Search description for any of the words.
print Print characters by codepoint, category, or block.
emoji Search emojis.
Use "%(prog) help" or "%(prog) -h" for a more detailed help.
`)
var usage = zli.Usage(zli.UsageHeaders|zli.UsageProgram|zli.UsageTrim, `
Usage: %(prog) [command] [flags]
uni queries the unicode database. https://github.com/arp242/uni
Flags:
Flags can appear anywhere; "uni search euro -c" and "uni -c search euro"
are identical. Use "uni search -- -c" if you want to search for "-c".
-f, -format Columns to print and their formatting; see Format section
below for details.
-a, -as How to print the results: list (default), json, or table.
json The columns listed in -format are included,
ignoring formatting flags. Use "-format all" to
include all columns.
table Output as table; instead of listing the codepoints
on every line. This ignores the -format flag.
-c, -compact More compact output; don't print header, "no matches", etc.
For json output it uses minified output, and for table it
has less padding.
-r, -raw Don't use graphical variants for control characters and
don't add ◌ (U+25CC) before combining characters.
-p, -pager Output to $PAGER.
-o, -or Use "or" when searching: match if at least one parameter
matches, instead of only when all parameters match.
-q, -quiet Backwards-compatible alias for -c/-compact.
-j, -json Backwards-compatible alias for -as json
Commands:
list [query] Show an overview of blocks, categories, scripts,
properties, planes, or unicode versions. Every name can be
abbreviated (i.e. "b" for "block"). Use "all" to show
everything.
identify [text] Identify all the characters in the given arguments.
search [query] Search description for any of the words.
print [query] Print characters. The query can be any of the following:
Codepoint Specific codepoint, in number formats:
hexadecimal U+20, U20, 0x20, x20, 20
decimal 0d32
octal 0o40, o40
binary 0b100000
Range Range of codepoints, as "start-end" or
"start..end", using the same notation as
Codepoints. These are all identical:
U+2042..U+2050
U+2042-U+2050
2042..2050
'0o20102 - 0d8272'
UTF-8 UTF-8 byte sequence, optionally separated by
any combination of '0x', '-', '_', or spaces.
For example these are all U+20AC (€):
utf8:e282ac
utf8:0xe20x820xac
'utf8:e2 82 ac'
utf8:0xe2-0x82_0xac
Category Prefix with "category:", "cat:", or "c:".
Both the long as short name can be used.
Block Prefix with "block:" or "b:".
Property Prefix with "property:", "prop:", or "p:".
all All codepoints we know about.
The category, block, and property can be abbreviated, and
non-letter characters can be omitted. These are identical:
block:'Block Drawing' block:box
As are these:
cat:Dash_Punctuation cat:dashpunctuation
If nothing of the above matches it will try to find by
block, category, or property, giving an error if more than
one matches.
emoji [query] Search emojis. The query is matched on the emoji name and
CLDR data.
The CLDR data is a list of keywords. For example 🙏
(folded hands) contains "ask, high 5, high five, please,
pray, thanks", which represents the various scenarios in
which it's used.
You can use <prefix>:query to search in specific fields:
group: g: Group and subgroup
name: n: Emoji name
cldr: c: CLDR data
The query parameters are AND'd together, so this:
uni emoji smiling g:cat-face
Will match everything in the cat-face group with smiling
in the name. Use the -or flag to change this to "cat-face
group OR smiling in the name".
Use "all" to show all emojis.
Modifier flags, both accept a comma-separated list:
-g, -gender Set the gender:
p, person, people
m, man, men, male
f, female, w, woman, women
-t, -tone Set the skin tone modifier:
n, none
l, light
ml, mediumlight, medium-light
m, medium
md, mediumdark, medium-dark
d, dark
Use "all" to include all combinations; the default is to
include no skin tones and the "person" gender.
Note: emojis may not be accurately copied by select & copy
in terminals. It's recommended to copy to the clipboard
directly by piping to e.g. xclip.
Format:
You can use the -format or -f flag to control what to print; placeholders
are in the form of %(name) or %(name flags), where "name" is a column name
and "flags" are some flags to control how it's printed.
%name is a shortcut for %(name l:auto).
If the format string starts with "+" it will prepend the format string with
the character, codepoint, and name. This is an easy way to quickly list
properties yo're interested in. For example, "-f +%unicode to quickly get
the Unicode version it was introduced. Otherwise it works exactly as below.
The special value "all" includes all columns; this is useful especially
with json if you want to get all information uni knows about a codepoint
or emoji.
Flags:
%(name l:5) Left-align and pad with 5 spaces
%(name l:auto) Left-align and pad to the longest value
%(name r:5) Right-align and pad with 5 spaces (also supports auto)
%(name q) Quote with single quotes, excluding any padding
%(name q:") Quote with "
%(name q:[:],) Quote with [ at the start, and ], at the end
%(name Q) Quote like q, but omit the quotes if the value is empty
%(name Q:[:])
%(name t) Trim this column if it's longer than the screen width
%(name f:C) Fill this column with character C instead of space when
aligning; useful for numbers: %(bin r:auto f:0)
%(name h) Don't include in header.
Placeholders that work for all commands:
%(tab) A literal tab when outputting to a terminal, or four
spaces if not; this helps with aligning emojis in
terminals, but some tools like dmenu don't work well
with tabs.
Placeholders for identify, search, and print:
Placeholder Description Example
----------- ----------- -------
%(char) The literal character ✓
(also see -raw flag)
%(cpoint) As codepoint U+2713
%(hex) As hex 2713
%(oct) As octal 23423
%(bin) As binary (little-endian) 10011100010011
%(dec) As decimal 10003
%(utf8) As UTF-8 e2 9c 93
%(utf16le) As UTF-16 LE (Windows) 13 27
%(utf16be) As UTF-16 BE 27 13
%(html) HTML entity (name or hex) ✓
%(xml) XML entity ✓
%(json) JSON escape \u2713
%(keysym) X11 keysym; can be blank checkmark
%(digraph) Vim Digraph; can be blank OK
%(name) Code point name CHECK MARK
%(cat) Category name Other_Symbol
%(block) Block name Dingbats
%(props) Properties, separated by , Pattern Syntax
%(plane) Plane name Basic Multilingual Plane
%(width) Character width Narrow
%(cells) Number of cells it display 1
as, 0, 1, or 2
%(unicode) First assigned in Unicode 1.1
%(wide_padding) Blank for wide characters,
space otherwise; for alignment
%(aliases) Alias names factorial, bang
%(refs) Reference other codepoints, U+221A, U+1F5F8, U+1FBB1
usually similar/alternatives
The default is:
`+defaultFormat+`
Placeholders for emoji:
%(emoji) The emoji itself 🧑🚒
%(name) Emoji name firefighter
%(group) Emoji group People & Body
%(subgroup) Emoji subgroup person-role
%(cpoint) Codepoints U+1F9D1 U+200D U+1F692
%(cldr) CLDR data, w/o emoji name firetruck
%(cldr_full) Full CLDR data firefighter, firetruck
The default is:
`+defaultEmojiFormat+`
`)
const (
defaultFormat = "%(char q h l:3)%(wide_padding) %(cpoint h l:7) %(dec l:6) %(utf8 l:11) %(html l:10) %(name t) %(aliases t h Q:[:])"
defaultCompact = "%(char q h l:3)%(wide_padding) %(cpoint h l:7) %(name t l:auto)"
allFormat = "%(char q h l:3)%(wide_padding) %(cpoint h l:auto) %width %cells %dec %hex %oct %bin" +
" %utf8 %utf16le %utf16be %html %xml %json %keysym %digraph %name %plane %cat %block" +
" %script %props %unicode %aliases %refs"
defaultEmojiFormat = "%(emoji h)%(tab)%name %(cldr t Q:[:])"
defaultEmojiCompact = "%(emoji h)%(tab)%name"
allEmojiFormat = "%(emoji h)%(tab)%name %group %subgroup %cpoint %cldr %(cldr_full)"
)
func main() {
flag := zli.NewFlags(os.Args)
var (
compact = flag.Bool(false, "c", "compact", "q", "quiet")
help = flag.Bool(false, "h", "help")
versionF = flag.Bool(false, "v", "version")
rawF = flag.Bool(false, "r", "raw")
pager = flag.Bool(false, "p", "pager")
or = flag.Bool(false, "o", "or")
formatF = flag.String(defaultFormat, "format", "f")
tone = flag.String("", "t", "tone", "tones")
gender = flag.String("person", "g", "gender", "genders")
asF = flag.String("list", "a", "as")
jsonF = flag.Bool(false, "json", "j")
)
zli.F(flag.Parse())
if versionF.Set() {
fmt.Println(version)
return
}
if pager.Set() {
defer zli.PagerStdout()()
}
if help.Set() {
fmt.Fprint(zli.Stdout, usage)
return
}
cmd, err := flag.ShiftCommand("list", "ls", "identify", "print", "search", "emoji", "help", "version")
if cmd == "ls" { // Alias because I keep typing "ls"
cmd = "list"
}
switch cmd {
case "":
if errors.As(err, &zli.ErrCommandNoneGiven{}) {
fmt.Fprint(zli.Stdout, usageShort)
return
}
zli.F(err)
// These commands don't read from stdin.
case "help":
fmt.Fprint(zli.Stdout, usage)
return
case "version":
u := unidata.Unicodes[unidata.UnicodeLatest]
fmt.Printf("%s; Unicode %s (%s)\n", version, u.Name, u.Released)
return
}
var (
as = parseAsFlags(compact, asF, jsonF)
quiet = compact.Set()
raw = rawF.Set()
args = flag.Args
)
if cmd == "print" {
args, err = zli.InputOrArgs(args, " \t\n", quiet)
zli.F(err)
} else if cmd != "list" {
args, err = zli.InputOrArgs(args, "", quiet)
zli.F(err)
}
format := formatF.String()
if !formatF.Set() && cmd == "emoji" {
format = defaultEmojiFormat
}
if formatF.String() == "all" {
format = allFormat
if cmd == "emoji" {
format = allEmojiFormat
}
}
if strings.HasPrefix(formatF.String(), "+") {
format = defaultCompact
if cmd == "emoji" {
format = defaultEmojiCompact
}
format += " " + formatF.String()[1:]
}
// Replace %name shortcut with %(name l:auto)
format = regexp.MustCompile(`%[a-z0-9-]+`).ReplaceAllStringFunc(format, func(s string) string {
return "%(" + s[1:] + " l:auto)"
})
switch cmd {
case "list":
err = list(args, as)
case "identify":
err = identify(args, format, raw, as)
case "search":
err = search(args, format, raw, as, or.Bool())
case "print":
err = print(args, format, raw, as)
case "emoji":
err = emoji(args, format, raw, as, or.Bool(),
parseToneFlag(tone.String()), parseGenderFlag(gender.String()))
}
if err != nil {
if !(err == errNoMatches && quiet) {
zli.Fatalf(err)
}
zli.Exit(1)
}
}
type fb interface {
Set() bool
Bool() bool
}
type fs interface {
Set() bool
String() string
}
func parseAsFlags(compact fb, asF fs, jsonF fb) printAs {
if jsonF.Set() {
if compact.Set() {
return printAsJSONCompact
}
return printAsJSON
}
var as printAs
switch asF.String() {
default:
zli.Fatalf("unknown value for -as: %q", asF.String())
case "l", "list":
as = printAsList
case "j", "json":
as = printAsJSON
case "t", "tbl", "table":
as = printAsTable
}
if compact.Set() {
as++
}
return as
}
func parseToneFlag(tone string) unidata.EmojiModifier {
if tone == "" {
return 0
}
if tone == "all" {
tone = "none,light,mediumlight,medium,mediumdark,dark"
}
var m unidata.EmojiModifier
for _, t := range zstring.Fields(tone, ",") {
switch t {
case "none", "n":
m |= unidata.ModNone
case "l", "light":
m |= unidata.ModLight
case "ml", "mediumlight", "medium-light", "medium_light":
m |= unidata.ModMediumLight
case "m", "medium":
m |= unidata.ModMedium
case "md", "mediumdark", "medium-dark", "medium_dark":
m |= unidata.ModMediumDark
case "d", "dark":
m |= unidata.ModDark
default:
zli.Fatalf("invalid skin tone: %q", tone)
}
}
return m
}
func parseGenderFlag(gender string) unidata.EmojiModifier {
if gender == "" {
return 0
}
if gender == "all" {
gender = "person,man,woman"
}
var m unidata.EmojiModifier
for _, g := range zstring.Fields(gender, ",") {
switch g {
case "person", "p", "people":
m |= unidata.ModPerson
case "man", "men", "m", "male":
m |= unidata.ModMale
case "woman", "women", "w", "female", "f":
m |= unidata.ModFemale
default:
zli.Fatalf("invalid gender: %q", gender)
}
}
return m
}
// TODO: move to zli or zstd; this is a copy of ShiftCommand() basically.
//
// Actually, f.StringMatch(...) might make sense, since this is a string value.
func match(input string, cmds ...string) (string, error) {
input = strings.ToLower(input)
if len(cmds) == 0 {
return input, nil
}
var found []string
for _, c := range cmds {
if c == input {
return input, nil
}
if strings.HasPrefix(c, input) {
if i := strings.IndexRune(c, '='); i > -1 { // Alias
c = c[i+1:]
}
found = append(found, c)
}
}
switch len(found) {
case 0:
return "", zli.ErrCommandUnknown(input)
case 1:
return found[0], nil
default:
return "", zli.ErrCommandAmbiguous{Cmd: input, Opts: found}
}
}
// TODO: this is essentially the same code repeated 3 times; this sucks.
//
// TODO: add -order flag; grouping by start codepoint isn't neccisarily all that
// useful. Allow by name, too, and assigned, and maybe also grouping logically
// (alphabets, symbols, CJK, control, etc.)
func list(ls []string, as printAs) error {
if as == printAsTable || as == printAsTableCompact {
zli.Fatalf("can't use -as table with the list command")
}
if len(ls) == 0 {
return errors.New("need at least property to list: blocks, categories, scripts, properties, planes, unicode, or all")
}
if slices.Contains(ls, "all") {
ls = []string{"blocks", "categories", "scripts", "properties", "planes", "unicode"}
}
for i, l := range ls {
cmd, err := match(l, "blocks", "categories", "scripts", "properties", "unicode", "planes")
if cmd != "" && len(ls) > 0 && as == printAsList {
if i > 0 {
fmt.Fprintln(zli.Stdout)
}
if len(ls) > 1 {
fmt.Fprintf(zli.Stdout, "%s:\n", zstring.UpperFirst(cmd))
}
}
switch cmd {
case "":
zli.Fatalf("list: %s", err)
case "unicode":
for _, k := range zmap.KeysOrdered(unidata.Unicodes)[1:] {
u := unidata.Unicodes[k]
fmt.Fprintf(zli.Stdout, "%-6s %s\n", u.Name, u.Released)
}
case "planes":
for _, k := range zmap.KeysOrdered(unidata.Planes) {
p := unidata.Planes[k]
s, e := fmt.Sprintf("U+%04X", p.Range[0]), fmt.Sprintf("U+%04X", p.Range[1])
fmt.Fprintf(zli.Stdout, "%-7s - %-8s %s\n", s, e, p.Name)
}
case "blocks":
order := make([]struct {
Range [2]rune
Name string
}, 0, len(unidata.Blocks))
for _, b := range unidata.Blocks {
order = append(order, b)
}
sort.Slice(order, func(i, j int) bool { return order[i].Range[0] < order[j].Range[0] })
assign := make(map[string]int)
for k := range unidata.Codepoints {
for _, b := range order {
if k >= b.Range[0] && k <= b.Range[1] {
assign[b.Name]++
}
}
}
f, err := NewFormat("%(from r:auto) %(to r:auto) %(assigned l:auto) %(name l:auto)",
as, "from", "to", "assigned", "name")
zli.F(err)
fmtCp := map[bool]string{true: "%X", false: "% 7X"}[f.json()]
for _, b := range order {
f.Line(map[string]string{
"from": fmt.Sprintf(fmtCp, b.Range[0]),
"to": fmt.Sprintf(fmtCp, b.Range[1]),
"assigned": strconv.Itoa(assign[b.Name]),
"name": b.Name,
})
}
f.Print(zli.Stdout)
case "scripts":
f, err := NewFormat("%(name l:auto) %(assigned r:auto)",
as, "name", "assigned")
zli.F(err)
assign := make(map[unidata.Script]int)
order := make([]struct {
Name string
Const unidata.Script
}, 0, len(unidata.Scripts))
for k, s := range unidata.Scripts {
if k == unidata.ScriptUnknown {
continue
}
order = append(order, struct {
Name string
Const unidata.Script
}{s.Name, k})
for _, rng := range s.Ranges {
assign[k] += int(rng[1] - rng[0])
}
}
sort.Slice(order, func(i, j int) bool { return order[i].Const < order[j].Const })
for _, s := range order {
f.Line(map[string]string{
"name": s.Name,
"assigned": strconv.Itoa(assign[s.Const]),
})
}
f.Print(zli.Stdout)
case "categories":
order := make([]struct {
ShortName, Name string
Include []unidata.Category
Const unidata.Category
}, 0, len(unidata.Categories))
for k, c := range unidata.Categories {
order = append(order, struct {
ShortName, Name string
Include []unidata.Category
Const unidata.Category
}{c.ShortName, c.Name, c.Include, k})
}
sort.Slice(order, func(i, j int) bool { return order[i].Const < order[j].Const })
assign := make(map[unidata.Category]int)
for _, cp := range unidata.Codepoints {
for _, c := range order {
if cp.Category() == c.Const {
assign[c.Const]++
}
for _, i := range c.Include {
if cp.Category() == i {
assign[c.Const]++
}
}
}
}
f, err := NewFormat("%(short l:auto) %(name l:auto) %(assigned r:auto) %(composed-of l:auto)",
as, "short", "name", "assigned", "composed-of")
zli.F(err)
for _, b := range order {
comp := ""
if len(b.Include) > 0 {
var in []string
for _, i := range b.Include {
in = append(in, unidata.Categories[i].ShortName)
}
comp = strings.Join(in, " | ")
}
f.Line(map[string]string{
"short": b.ShortName,
"name": b.Name,
"assigned": strconv.Itoa(assign[b.Const]),
"composed-of": comp,
})
}
f.Print(zli.Stdout)
case "properties":
order := make([]struct {
Name string
Ranges [][2]rune
}, 0, len(unidata.Properties))
for _, p := range unidata.Properties {
order = append(order, p)
}
sort.Slice(order, func(i, j int) bool { return order[i].Name < order[j].Name })
assign := make(map[string]int)
for _, cp := range unidata.Codepoints {
for _, p := range cp.Properties() {
for _, c := range order {
if p.String() == c.Name {
assign[c.Name]++
}
}
}
}
f, err := NewFormat("%(name l:auto) %(assigned r:auto)",
as, "name", "assigned")
zli.F(err)
for _, b := range order {
f.Line(map[string]string{
"assigned": strconv.Itoa(assign[b.Name]),
"name": b.Name,
})
}
f.Print(zli.Stdout)
}
}
return nil
}
func identify(ins []string, format string, raw bool, as printAs) error {
in := strings.Join(ins, "")
if !utf8.ValidString(in) {
fmt.Fprintf(zli.Stderr, "uni: WARNING: input string is not valid UTF-8\n")
}
f, err := NewFormat(format, as, knownColumns...)
if err != nil {
return err
}
for _, c := range in {
info, ok := unidata.Find(c)
if !ok {
return fmt.Errorf("unknown codepoint: U+%.4X", c) // Should never happen.
}
f.Line(f.toLine(info, raw))
}
f.Print(zli.Stdout)
return nil
}
func search(args []string, format string, raw bool, as printAs, or bool) error {
args = slices.DeleteFunc(args, func(s string) bool { return s == "" })
if len(args) == 0 {
return errors.New("search: need search term")
}
for i := range args {
args[i] = strings.ToUpper(args[i])
}
found := false
f, err := NewFormat(format, as, knownColumns...)
if err != nil {
return err
}
for _, info := range unidata.Codepoints {
hasAlias := func(upperS string) bool {
for _, a := range info.Aliases() {
if strings.Contains(strings.ToUpper(a), upperS) {
return true
}
}
return false
}
m := 0
for _, a := range args {
if strings.Contains(info.Name(), a) || hasAlias(a) {
if or {
found = true
f.Line(f.toLine(info, raw))
break
}
m++
}
}
if !or && m == len(args) {
found = true
f.Line(f.toLine(info, raw))
}
}
if !found {
return errNoMatches
}
f.SortNum("dec")
f.Print(zli.Stdout)
return nil
}
var utfClean = strings.NewReplacer("0x", "", " ", "", "_", "", "-", "")
func nbools(bools ...bool) int {
n := 0
for _, b := range bools {
if b {
n++
}
}
return n
}
func print(args []string, format string, raw bool, as printAs) error {
f, err := NewFormat(format, as, knownColumns...)
if err != nil {
return err
}
for _, a := range args {
a = strings.Trim(strings.ToLower(a), ",/")
if a == "" {
continue
}
// UTF-8
if strings.HasPrefix(a, "utf8:") {
a = a[5:]
seq := utfClean.Replace(a)
if len(seq)%2 == 1 {
seq = "0" + seq
}
byt := make([]byte, 0, len(seq)/2)
for i := 0; len(seq) > i; i += 2 {
b, err := strconv.ParseUint(seq[i:i+2], 16, 8)
if err != nil {
return fmt.Errorf("invalid UTF-8 sequence %q: %q is not a hex number",
a, seq[i:i+2])
}
byt = append(byt, byte(b))
}
r, s := utf8.DecodeRune(byt)
if r == utf8.RuneError && s == 1 {
return fmt.Errorf("invalid UTF-8 sequence: %q", a)
}
if s != len(byt) {
return fmt.Errorf("multiple characters in sequence %q", a)
}
f.Line(f.toLine(unidata.Codepoints[r], raw))
continue
}
// Print everything.
if strings.ToLower(a) == "all" {
for _, info := range unidata.Codepoints {
f.Line(f.toLine(info, raw))
}
continue
}
// Find by block, category, or property.
var (
catOk, blOk, pOk, scOk bool
cat unidata.Category
bl unidata.Block
p unidata.Property
sc unidata.Script
)
switch {
case zstring.HasPrefixes(a, "block:", "b:"):
a = a[strings.IndexByte(a, ':')+1:]
bl, blOk = unidata.FindBlock(a)
if !blOk {
zli.Fatalf("unknown or ambiguous block: %q", a)
}
case zstring.HasPrefixes(a, "script:", "s:"):
a = a[strings.IndexByte(a, ':')+1:]
sc, scOk = unidata.FindScript(a)
if !scOk {
zli.Fatalf("unknown or ambiguous script: %q", a)
}
case zstring.HasPrefixes(a, "category:", "cat:"):
a = a[strings.IndexByte(a, ':')+1:]
cat, catOk = unidata.FindCategory(a)
if !catOk {
zli.Fatalf("unknown or ambiguous category: %q", a)
}
case zstring.HasPrefixes(a, "property:", "prop:", "p:"):
a = a[strings.IndexByte(a, ':')+1:]
p, pOk = unidata.FindProperty(a)
if !pOk {
zli.Fatalf("unknown or ambiguous property: %q", a)
}
default:
cat, catOk = unidata.FindCategory(a)
bl, blOk = unidata.FindBlock(a)
p, pOk = unidata.FindProperty(a)
if nbools(catOk, blOk, pOk) > 1 {
opt := make([]string, 0, 3)
if catOk {
opt = append(opt, fmt.Sprintf("Category(%q)", cat))
}
if blOk {
opt = append(opt, fmt.Sprintf("Block(%q)", bl))
}
if pOk {
opt = append(opt, fmt.Sprintf("Property(%q)", p))
}
zli.Fatalf("%q matched multiple options:\n\t%s\nPrefix with 'block:', 'category:', or 'property:'",
a, strings.Join(opt, ", "))
}
}
// Category name.
if catOk {
cc := unidata.Categories[cat]
if as == printAsList || as == printAsTable {
fmt.Fprintf(zli.Stdout, "Showing category %s (%s)\n", cc.ShortName, cc.Name)
}
for _, info := range unidata.Codepoints {
if info.Category() == cat {
f.Line(f.toLine(info, raw))
}
for _, incl := range cc.Include {
if info.Category() == incl {
f.Line(f.toLine(info, raw))
}
}
}
continue
}
// Script.
if scOk {
cc := unidata.Scripts[sc]
if as == printAsList || as == printAsTable {
fmt.Fprintf(zli.Stdout, "Showing script %s\n", cc.Name)
}
for _, pp := range cc.Ranges {
for cp := pp[0]; cp <= pp[1]; cp++ {
s, ok := unidata.Codepoints[cp]
if ok {
f.Line(f.toLine(s, raw))
}
}
}
continue
}
// Block.
if blOk {
if as == printAsList || as == printAsTable {
fmt.Fprintf(zli.Stdout, "Showing block %s\n", bl)
}
for cp := unidata.Blocks[bl].Range[0]; cp <= unidata.Blocks[bl].Range[1]; cp++ {
s, ok := unidata.Codepoints[cp]
if ok {
f.Line(f.toLine(s, raw))
}
}
continue
}
// Properties
if pOk {
if as == printAsList || as == printAsTable {
fmt.Fprintf(zli.Stdout, "Showing property %s\n", p)
}
for _, pp := range unidata.Properties[p].Ranges {
for cp := pp[0]; cp <= pp[1]; cp++ {
s, ok := unidata.Codepoints[cp]
if ok {
f.Line(f.toLine(s, raw))
}
}
}
continue
}
// U2042, U+2042, U+2042..U+2050, 2042..2050, 2042-2050, 0x2041, etc.
var s []string
switch {
case strings.Contains(a, ".."):
s = strings.SplitN(a, "..", 2)
case strings.Contains(a, "-"):
s = strings.SplitN(a, "-", 2)
default:
s = []string{a, a}
}
s[0], s[1] = strings.TrimSpace(s[0]), strings.TrimSpace(s[1])
start, err := unidata.FromString(s[0])
if err != nil {
return fmt.Errorf("invalid codepoint: %s", errors.Unwrap(err))
}
end, err := unidata.FromString(s[1])
if err != nil {
return fmt.Errorf("invalid codepoint: %s", errors.Unwrap(err))
}
if start.Codepoint > end.Codepoint {
zli.Fatalf("end of range %q is lower than start %q", s[1], s[0])
}
for i := start.Codepoint; i <= end.Codepoint; i++ {