Data update

This commit is contained in:
Ingy döt Net 2025-08-11 18:05:26 -07:00
parent 4d5544505c
commit 4924dd0264
3073 changed files with 55820 additions and 4408 deletions

View file

@ -0,0 +1 @@
(print (len "åéèàâêç"))

View file

@ -0,0 +1,2 @@
select s, length(s), strlen(s) as '# bytes' from
(select unnest(['J̲o̲s̲é̲', '𝔘𝔫𝔦𝔠𝔬𝔡𝔢']) as s);

View file

@ -0,0 +1,17 @@
CFStringRef s
s = @"møøse"
printf @"\"%@\"",s
print @"character length:",len(s)
print @"unicode length:",,len(s,_kLenUnicode)
print @"byte length UTF8:",len(s,_kLenBytesUTF8)
print @"byte length UTF16:",len(s,_kLenBytesUTF16)
print
s = @"𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
printf @"\"%@\"",s
print @"character length:",len(s)
print @"unicode length:",,len(s,_kLenUnicode)
print @"byte length UTF8:",len(s,_kLenBytesUTF8)
print @"byte length UTF16:",len(s,_kLenBytesUTF16)

View file

@ -0,0 +1,12 @@
require "gchar"
local fmt = require "fmt"
local moose = "møøse"
local unicode = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
local jose = "J\u{332}o\u{332}s\u{332}e\u{301}\u{332}"
local f = "%5s %7s %5s"
fmt.print("Strings : " .. f, moose, unicode, jose)
fmt.print("\nBytes : " .. f, #moose, #unicode, #jose)
fmt.print("\nCodepoints: " .. f, utf8.len(moose), utf8.len(unicode), utf8.len(jose))
fmt.print("\nGraphemes : " .. f, gchar.of(moose):len(), gchar.of(unicode):len(), gchar.of(jose):len())

View file

@ -0,0 +1,6 @@
s =: "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
print (quote s), s.Count, s.Bytes
s =: "José&e10;"
print (quote s), s.Count, s.Bytes
s =: "J̲o̲s̲é̲"
print (quote s), s.Count, s.Bytes

View file

@ -1,3 +1,4 @@
System.print("møøse".bytes.count)
System.print("𝔘𝔫𝔦𝔠𝔬𝔡𝔢".bytes.count)
System.print("J̲o̲s̲é̲".bytes.count)
var jose = "J\u0332o\u0332s\u0332e\u0301\u0332"
System.print(jose.bytes.count)

View file

@ -1,3 +1,4 @@
System.print("møøse".count)
System.print("𝔘𝔫𝔦𝔠𝔬𝔡𝔢".count)
System.print("J̲o̲s̲é̲".count)
var jose = "J\u0332o\u0332s\u0332e\u0301\u0332"
System.print(jose.count)

View file

@ -2,4 +2,5 @@ import "./upc" for Graphemes
System.print(Graphemes.clusterCount("møøse"))
System.print(Graphemes.clusterCount("𝔘𝔫𝔦𝔠𝔬𝔡𝔢"))
System.print(Graphemes.clusterCount("J̲o̲s̲é̲"))
var jose = "J\u0332o\u0332s\u0332e\u0301\u0332"
System.print(Graphemes.clusterCount(jose))