mirror/v
1
0
Fork 0
mirror of https://github.com/vlang/v.git synced 2023-08-10 21:13:21 +03:00
Code Issues Projects Releases Wiki Activity

builtin: deprecate string.split_by_whitespace in favor of fields()

Browse Source
This commit is contained in:
Alexander Medvednikov 2021-03-16 08:29:14 +03:00
parent 138da8e130
commit 93df560cf9
2 changed files with 133 additions and 118 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
vlib/builtin/string.v
View File

@ -1616,8 +1616,32 @@ pub fn (s string) repeat(count int) string {
// fields returns a string array of the string split by `\t` and ` `
// Example: assert '\t\tv = v'.fields() == ['', '', 'v', '=', 'v']
pub fn (s string) fields() []string {
// TODO do this in a better way
return s.replace('\t', ' ').split(' ')
mut res := []string{}
mut word_start := 0
mut word_end := 0
mut is_in_word := false
mut is_space := false
for i, c in s {
is_space = c in [` `, `\t`, `\n`]
if !is_in_word && !is_space {
word_start = i
is_in_word = true
continue
}
if is_space && is_in_word {
word_end = i
res << s[word_start..word_end]
is_in_word = false
word_end = 0
word_start = 0
continue
}
}
if is_in_word && word_start > 0 {
// collect the remainder word at the end
res << s[word_start..s.len]
}
return res
}
// strip_margin allows multi-line strings to be formatted in a way that removes white-space
@ -1684,31 +1708,8 @@ pub fn (s string) strip_margin_custom(del byte) string {
// split_by_whitespace - extract only the non whitespace tokens/words from the given string `s`.
// example: ' sss ssss'.split_by_whitespace() => ['sss', 'ssss']
[deprecated: 'use string.fields() instead']
pub fn (s string) split_by_whitespace() []string {
mut res := []string{}
mut word_start := 0
mut word_end := 0
mut is_in_word := false
mut is_space := false
for i, c in s {
is_space = c in [` `, `\t`, `\n`]
if !is_in_word && !is_space {
word_start = i
is_in_word = true
continue
}
if is_space && is_in_word {
word_end = i
res << s[word_start..word_end]
is_in_word = false
word_end = 0
word_start = 0
continue
}
}
if is_in_word && word_start > 0 {
// collect the remainder word at the end
res << s[word_start..s.len]
}
return res
return s.fields()
}

144
vlib/builtin/string_test.v
View File

@ -1,3 +1,5 @@
import strings
// Copyright (c) 2019-2021 Alexander Medvednikov. All rights reserved.
// Use of this source code is governed by an MIT license
// that can be found in the LICENSE file.
@ -88,7 +90,10 @@ fn test_compare_strings() {
fn test_sort() {
mut vals := [
'arr', 'an', 'a', 'any'
'arr',
'an',
'a',
'any',
]
len := vals.len
vals.sort()
@ -101,7 +106,10 @@ fn test_sort() {
fn test_sort_reverse() {
mut vals := [
'arr', 'an', 'a', 'any'
'arr',
'an',
'a',
'any',
]
len := vals.len
vals.sort(b > a)
@ -113,35 +121,35 @@ fn test_sort_reverse() {
}
fn test_split_nth() {
a := "1,2,3"
assert (a.split(',').len == 3)
assert (a.split_nth(',', -1).len == 3)
assert (a.split_nth(',', 0).len == 3)
assert (a.split_nth(',', 1).len == 1)
assert (a.split_nth(',', 2).len == 2)
assert (a.split_nth(',', 10).len == 3)
b := "1::2::3"
assert (b.split('::').len == 3)
assert (b.split_nth('::', -1).len == 3)
assert (b.split_nth('::', 0).len == 3)
assert (b.split_nth('::', 1).len == 1)
assert (b.split_nth('::', 2).len == 2)
assert (b.split_nth('::', 10).len == 3)
c := "ABCDEF"
a := '1,2,3'
assert a.split(',').len == 3
assert a.split_nth(',', -1).len == 3
assert a.split_nth(',', 0).len == 3
assert a.split_nth(',', 1).len == 1
assert a.split_nth(',', 2).len == 2
assert a.split_nth(',', 10).len == 3
b := '1::2::3'
assert b.split('::').len == 3
assert b.split_nth('::', -1).len == 3
assert b.split_nth('::', 0).len == 3
assert b.split_nth('::', 1).len == 1
assert b.split_nth('::', 2).len == 2
assert b.split_nth('::', 10).len == 3
c := 'ABCDEF'
println(c.split('').len)
assert (c.split('').len == 6)
assert (c.split_nth('', 3).len == 3)
assert (c.split_nth('BC', -1).len == 2)
d := ","
assert (d.split(',').len == 2)
assert (d.split_nth('', 3).len == 1)
assert (d.split_nth(',', -1).len == 2)
assert (d.split_nth(',', 3).len == 2)
e := ",,,0,,,,,a,,b,"
assert (e.split(',,').len == 5)
assert (e.split_nth(',,', 3).len == 3)
assert (e.split_nth(',', -1).len == 12)
assert (e.split_nth(',', 3).len == 3)
assert c.split('').len == 6
assert c.split_nth('', 3).len == 3
assert c.split_nth('BC', -1).len == 2
d := ','
assert d.split(',').len == 2
assert d.split_nth('', 3).len == 1
assert d.split_nth(',', -1).len == 2
assert d.split_nth(',', 3).len == 2
e := ',,,0,,,,,a,,b,'
assert e.split(',,').len == 5
assert e.split_nth(',,', 3).len == 3
assert e.split_nth(',', -1).len == 12
assert e.split_nth(',', 3).len == 3
}
fn test_split_nth_values() {
@ -241,10 +249,12 @@ fn test_join() {
mut strings := ['a', 'b', 'c']
mut s := strings.join(' ')
assert s == 'a b c'
strings = ['one
strings = [
'one
two ',
'three!
four!']
four!',
]
s = strings.join(' ')
assert s.contains('one') && s.contains('two ') && s.contains('four')
empty := []string{len: 0}
@ -284,31 +294,39 @@ fn test_replace() {
assert c.replace('', '-') == c
v := 'a b c d'
assert v.replace(' ', ' ') == 'a b c d'
}
fn test_replace_each() {
s := 'hello man man :)'
q := s.replace_each([
'man', 'dude',
'hello', 'hey'
'man',
'dude',
'hello',
'hey',
])
assert q == 'hey dude dude :)'
bb := '[b]bold[/b] [code]code[/code]'
assert bb.replace_each([
'[b]', '<b>',
'[/b]', '</b>',
'[code]', '<code>',
'[/code]', '</code>'
'[b]',
'<b>',
'[/b]',
'</b>',
'[code]',
'<code>',
'[/code]',
'</code>',
]) == '<b>bold</b> <code>code</code>'
bb2 := '[b]cool[/b]'
assert bb2.replace_each([
'[b]', '<b>',
'[/b]', '</b>',
'[b]',
'<b>',
'[/b]',
'</b>',
]) == '<b>cool</b>'
t := 'aaaaaaaa'
y := t.replace_each([
'aa', 'b'
'aa',
'b',
])
assert y == 'bbbb'
}
@ -425,7 +443,7 @@ fn test_to_num() {
fn test_inter_format_string() {
float_num := 1.52345
float_num_string := '-${float_num:.03f}-'
float_num_string := '-${float_num:.3f}-'
assert float_num_string == '-1.523-'
int_num := 7
int_num_string := '-${int_num:03d}-'
@ -645,14 +663,13 @@ fn test_for_loop_two() {
}
fn test_quote() {
a := `'`
println("testing double quotes")
b := "hi"
a := `\'`
println('testing double quotes')
b := 'hi'
assert b == 'hi'
assert a.str() == '\''
assert a.str() == "'"
}
fn test_ustring_comparisons() {
/*
QTODO
@ -773,8 +790,8 @@ fn test_raw_with_quotes() {
fn test_escape() {
a := 10
println("\"$a")
assert "\"$a" == "\"10"
println('\"$a')
assert '\"$a' == '"10'
}
fn test_atoi() {
@ -815,9 +832,9 @@ fn test_inter_before_comp_if() {
fn test_double_quote_inter() {
a := 1
b := 2
println("${a} ${b}")
assert "${a} ${b}" == "1 2"
assert '${a} ${b}' == "1 2"
println('$a $b')
assert '$a $b' == '1 2'
assert '$a $b' == '1 2'
}
fn foo(b byte) byte {
@ -830,7 +847,7 @@ fn filter(b byte) bool {
fn test_split_into_lines() {
line_content := 'Line'
text_crlf := '${line_content}\r\n${line_content}\r\n${line_content}'
text_crlf := '$line_content\r\n$line_content\r\n$line_content'
lines_crlf := text_crlf.split_into_lines()
assert lines_crlf.len == 3
@ -838,7 +855,7 @@ fn test_split_into_lines() {
assert line == line_content
}
text_lf := '${line_content}\n${line_content}\n${line_content}'
text_lf := '$line_content\n$line_content\n$line_content'
lines_lf := text_lf.split_into_lines()
assert lines_lf.len == 3
@ -848,13 +865,10 @@ fn test_split_into_lines() {
}
fn test_string_literal_with_backslash() {
a := 'Hello\
World'
a := 'HelloWorld'
assert a == 'HelloWorld'
b := 'One\
Two\
Three'
b := 'OneTwoThree'
assert b == 'OneTwoThree'
}
@ -887,7 +901,7 @@ fn test_sorter() {
Ka{
s: 'ccc'
i: 102
}
},
]
cmp := fn (a &Ka, b &Ka) int {
return compare_strings(a.s, b.s)
@ -902,10 +916,10 @@ fn test_sorter() {
}
fn test_split_by_whitespace() {
assert 'a bcde'.split_by_whitespace() == ['a', 'bcde']
assert ' sss \t ssss '.split_by_whitespace() == ['sss', 'ssss']
assert '\n xyz \t abc def'.split_by_whitespace() == ['xyz', 'abc', 'def']
assert ''.split_by_whitespace() == []
assert 'a bcde'.fields() == ['a', 'bcde']
assert ' sss \t ssss '.fields() == ['sss', 'ssss']
assert '\n xyz \t abc def'.fields() == ['xyz', 'abc', 'def']
assert ''.fields() == []
}
fn test_interpolation_after_quoted_variable_still_works() {