vieter-v
/
v
2
0
Fork 0
Code Issues Pull Requests Releases Activity

encoding.utf8: remove const unicode_con_table_up_to_low table (#9672)

pull/9676/head
penguindark 2021-04-11 09:28:19 +02:00 committed by GitHub
parent acb58d4923
commit cca06fce90
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 957 additions and 1542 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
cmd/tools/vtest-cleancode.v
View File

@ -43,6 +43,7 @@ const (
'vlib/builtin/',
'vlib/cli/',
'vlib/dl/',
'vlib/encoding/utf8/',
'vlib/flag/',
'vlib/gg/',
'vlib/math/bits/bits.v',

2
vlib/encoding/utf8/east_asian/east_asian_width.v
View File

@ -37,7 +37,7 @@ pub fn east_asian_width_property_at(s string, index int) EastAsianWidthProperty
mut left, mut right := 0, east_asian.east_asian_width_data.len - 1
for left <= right {
middle := left + ((right - left) / 2)
entry := east_asian_width_data[middle]
entry := east_asian.east_asian_width_data[middle]
if codepoint < entry.point {
right = middle - 1
continue

2
vlib/encoding/utf8/utf8.v
View File

@ -11,7 +11,7 @@ pub fn validate_str(str string) bool {
return validate(str.str, str.len)
}
pub fn validate(data byteptr, len int) bool {
pub fn validate(data &byte, len int) bool {
mut state := Utf8State{}
for i := 0; i < len; i++ {
s := unsafe { data[i] }

2279
vlib/encoding/utf8/utf8_util.v
View File

File diff suppressed because it is too large Load Diff

15
vlib/encoding/utf8/utf8_util_test.v
View File

@ -1,11 +1,10 @@
import encoding.utf8
fn test_utf8_util() {
// string test
src:="ăĂ ôÔ testo 怔"//_\u1E5A\u1E5B<=>\u1F49\u1F41<=>\u0128\u012a\u012c" // len 29 runes, raw 49 bytes
src_upper:="ĂĂ ÔÔ TESTO Æ€”"//_\u1E5A\u1E5A<=>\u1F49\u1F49<=>\u0128\u012A\u012C"
src_lower:="ăă ôô testo 怔"//_\u1E5B\u1E5B<=>\u1F41\u1F41<=>\u0129\u012B\u012D"
src := 'ăĂ ôÔ testo 怔' //_\u1E5A\u1E5B<=>\u1F49\u1F41<=>\u0128\u012a\u012c" // len 29 runes, raw 49 bytes
src_upper := 'ĂĂ ÔÔ TESTO Æ€”' //_\u1E5A\u1E5A<=>\u1F49\u1F49<=>\u0128\u012A\u012C"
src_lower := 'ăă ôô testo 怔' //_\u1E5B\u1E5B<=>\u1F41\u1F41<=>\u0129\u012B\u012D"
upper := utf8.to_upper(src)
lower := utf8.to_lower(src)
assert upper == src_upper
@ -22,12 +21,12 @@ fn test_utf8_util() {
assert lower1 == (src_lower.ustring())
// test len function
assert utf8.len("pippo")==5
assert utf8.len('pippo') == 5
assert utf8.len(src) == 15 // 29
assert src.len == 24 // 49
// test u_len function
assert utf8.u_len(src1) == 15 // 29
assert utf8.u_len("pippo".ustring())==5
assert utf8.u_len('pippo'.ustring()) == 5
// western punctuation
a := '.abc?abcòàè.'
@ -37,7 +36,7 @@ fn test_utf8_util() {
assert utf8.is_punct(a, 4) == true // ?
assert utf8.is_punct(a, 14) == true // last .
assert utf8.is_punct(a, 12) == false // è
println("OK western")
println('OK western')
// global punctuation
b := '.ĂĂa. ÔÔ TESTO Æ€'
@ -52,7 +51,7 @@ fn test_utf8_util() {
}
fn test_raw_indexing() {
a := "我是V Lang!"
a := '我是V Lang!'
// test non ascii characters
assert utf8.raw_index(a, 0) == '我'