git/lancet
1
0
Fork 0
mirror of https://github.com/duke-git/lancet.git synced 2026-03-01 00:35:28 +08:00
Code Issues Projects Releases Wiki Activity

doc: add doc for SplitWords and WordCount

Browse Source
This commit is contained in:
dudaodong
2023-02-23 10:23:38 +08:00
parent c02654559a
commit 15c1537bf0
5 changed files with 647 additions and 333 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
docs/strutil.md
View File

@@ -42,6 +42,8 @@ import (
- [Wrap](#Wrap) - [Wrap](#Wrap)
- [Unwrap](#Unwrap) - [Unwrap](#Unwrap)
- [SplitEx](#SplitEx) - [SplitEx](#SplitEx)
- [SplitWords](#SplitWords)
- [WordCount](#WordCount)
<div STYLE="page-break-after: always;"></div> <div STYLE="page-break-after: always;"></div>
@@ -735,3 +737,89 @@ func main() {
fmt.Println(arr5) //[]string{" a", "b", "c"} fmt.Println(arr5) //[]string{" a", "b", "c"}
} }
``` ```
### <span id="SplitWords">SplitWords</span>
<p>Splits a string into words, word only contains alphabetic characters.</p>
<b>Signature:</b>
```go
func SplitWords(s string) []string
```
<b>Example:</b>
```go
import (
"fmt"
"github.com/duke-git/lancet/strutil"
)
func main() {
result1 := strutil.SplitWords("a word")
result2 := strutil.SplitWords("I'am a programmer")
result3 := strutil.SplitWords("Bonjour, je suis programmeur")
result4 := strutil.SplitWords("a -b-c' 'd'e")
result5 := strutil.SplitWords("你好，我是一名码农")
result6 := strutil.SplitWords("こんにちは，私はプログラマーです")
fmt.Println(result1)
fmt.Println(result2)
fmt.Println(result3)
fmt.Println(result4)
fmt.Println(result5)
fmt.Println(result6)
// Output:
// [a word]
// [I'am a programmer]
// [Bonjour je suis programmeur]
// [a b-c' d'e]
// []
// []
}
```
### <span id="WordCount">WordCount</span>
<p>Return the number of meaningful word, word only contains alphabetic characters.</p>
<b>Signature:</b>
```go
func WordCount(s string) int
```
<b>Example:</b>
```go
import (
"fmt"
"github.com/duke-git/lancet/strutil"
)
func main() {
result1 := strutil.WordCount("a word")
result2 := strutil.WordCount("I'am a programmer")
result3 := strutil.WordCount("Bonjour, je suis programmeur")
result4 := strutil.WordCount("a -b-c' 'd'e")
result5 := strutil.WordCount("你好，我是一名码农")
result6 := strutil.WordCount("こんにちは，私はプログラマーです")
fmt.Println(result1)
fmt.Println(result2)
fmt.Println(result3)
fmt.Println(result4)
fmt.Println(result5)
fmt.Println(result6)
// Output:
// 2
// 3
// 4
// 3
// 0
// 0
}
```

94
docs/strutil_zh-CN.md
View File

@@ -42,6 +42,8 @@ import (
- [Wrap](#Wrap) - [Wrap](#Wrap)
- [Unwrap](#Unwrap) - [Unwrap](#Unwrap)
- [SplitEx](#SplitEx) - [SplitEx](#SplitEx)
- [SplitWords](#SplitWords)
- [WordCount](#WordCount)
<div STYLE="page-break-after: always;"></div> <div STYLE="page-break-after: always;"></div>
@@ -408,7 +410,7 @@ func Pad(source string, size int, padStr string) string
```go ```go
import ( import (
"fmt" "fmt"
"github.com/duke-git/lancet/v2/strutil" "github.com/duke-git/lancet/strutil"
) )
func main() { func main() {
@@ -453,7 +455,7 @@ func PadEnd(source string, size int, padStr string) string
```go ```go
import ( import (
"fmt" "fmt"
"github.com/duke-git/lancet/v2/strutil" "github.com/duke-git/lancet/strutil"
) )
func main() { func main() {
@@ -499,7 +501,7 @@ func PadStart(source string, size int, padStr string) string
```go ```go
import ( import (
"fmt" "fmt"
"github.com/duke-git/lancet/v2/strutil" "github.com/duke-git/lancet/strutil"
) )
func main() { func main() {
@@ -736,3 +738,89 @@ func main() {
fmt.Println(arr5) //[]string{" a", "b", "c"} fmt.Println(arr5) //[]string{" a", "b", "c"}
} }
``` ```
### <span id="SplitWords">SplitWords</span>
<p>将字符串拆分为单词，只支持字母字符单词。</p>
<b>函数签名:</b>
```go
func SplitWords(s string) []string
```
<b>示例:</b>
```go
import (
"fmt"
"github.com/duke-git/lancet/strutil"
)
func main() {
result1 := strutil.SplitWords("a word")
result2 := strutil.SplitWords("I'am a programmer")
result3 := strutil.SplitWords("Bonjour, je suis programmeur")
result4 := strutil.SplitWords("a -b-c' 'd'e")
result5 := strutil.SplitWords("你好，我是一名码农")
result6 := strutil.SplitWords("こんにちは，私はプログラマーです")
fmt.Println(result1)
fmt.Println(result2)
fmt.Println(result3)
fmt.Println(result4)
fmt.Println(result5)
fmt.Println(result6)
// Output:
// [a word]
// [I'am a programmer]
// [Bonjour je suis programmeur]
// [a b-c' d'e]
// []
// []
}
```
### <span id="WordCount">WordCount</span>
<p>返回有意义单词的数量，只支持字母字符单词。</p>
<b>函数签名:</b>
```go
func WordCount(s string) int
```
<b>示例:</b>
```go
import (
"fmt"
"github.com/duke-git/lancet/strutil"
)
func main() {
result1 := strutil.WordCount("a word")
result2 := strutil.WordCount("I'am a programmer")
result3 := strutil.WordCount("Bonjour, je suis programmeur")
result4 := strutil.WordCount("a -b-c' 'd'e")
result5 := strutil.WordCount("你好，我是一名码农")
result6 := strutil.WordCount("こんにちは，私はプログラマーです")
fmt.Println(result1)
fmt.Println(result2)
fmt.Println(result3)
fmt.Println(result4)
fmt.Println(result5)
fmt.Println(result6)
// Output:
// 2
// 3
// 4
// 3
// 0
// 0
}
```

71
strutil/string.go
View File

@@ -253,3 +253,74 @@ func SplitEx(s, sep string, removeEmptyString bool) []string {
return ret return ret
} }
// SplitWords splits a string into words, word only contains alphabetic characters.
func SplitWords(s string) []string {
var word string
var words []string
var r rune
var size, pos int
isWord := false
for len(s) > 0 {
r, size = utf8.DecodeRuneInString(s)
switch {
case isLetter(r):
if !isWord {
isWord = true
word = s
pos = 0
}
case isWord && (r == '\'' || r == '-'):
// is word
default:
if isWord {
isWord = false
words = append(words, word[:pos])
}
}
pos += size
s = s[size:]
}
if isWord {
words = append(words, word[:pos])
}
return words
}
// WordCount return the number of meaningful word, word only contains alphabetic characters.
func WordCount(s string) int {
var r rune
var size, count int
isWord := false
for len(s) > 0 {
r, size = utf8.DecodeRuneInString(s)
switch {
case isLetter(r):
if !isWord {
isWord = true
count++
}
case isWord && (r == '\'' || r == '-'):
// is word
default:
isWord = false
}
s = s[size:]
}
return count
}

33
strutil/string_internal.go
View File

@@ -132,3 +132,36 @@ func padAtPosition(str string, length int, padStr string, position int) string {
return leftPad + str + rightPad return leftPad + str + rightPad
} }
// isLetter checks r is a letter but not CJK character.
func isLetter(r rune) bool {
if !unicode.IsLetter(r) {
return false
}
switch {
// cjk char: /[\u3040-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\uff66-\uff9f]/
// hiragana and katakana (Japanese only)
case r >= '\u3034' && r < '\u30ff':
return false
// CJK unified ideographs extension A (Chinese, Japanese, and Korean)
case r >= '\u3400' && r < '\u4dbf':
return false
// CJK unified ideographs (Chinese, Japanese, and Korean)
case r >= '\u4e00' && r < '\u9fff':
return false
// CJK compatibility ideographs (Chinese, Japanese, and Korean)
case r >= '\uf900' && r < '\ufaff':
return false
// half-width katakana (Japanese only)
case r >= '\uff66' && r < '\uff9f':
return false
}
return true
}

34
strutil/string_test.go
View File

@@ -295,3 +295,37 @@ func TestSplitEx(t *testing.T) {
assert.Equal([]string{" a", "b", "c", ""}, SplitEx(" a = b = c = ", " = ", false)) assert.Equal([]string{" a", "b", "c", ""}, SplitEx(" a = b = c = ", " = ", false))
assert.Equal([]string{" a", "b", "c"}, SplitEx(" a = b = c = ", " = ", true)) assert.Equal([]string{" a", "b", "c"}, SplitEx(" a = b = c = ", " = ", true))
} }
func TestSplitWords(t *testing.T) {
assert := internal.NewAssert(t, "TestSplitWords")
cases := map[string][]string{
"a word": {"a", "word"},
"I'am a programmer": {"I'am", "a", "programmer"},
"Bonjour, je suis programmeur": {"Bonjour", "je", "suis", "programmeur"},
"a -b-c' 'd'e": {"a", "b-c'", "d'e"},
"你好，我是一名码农": nil,
"こんにちは，私はプログラマーです": nil,
}
for k, v := range cases {
assert.Equal(v, SplitWords(k))
}
}
func TestWordCount(t *testing.T) {
assert := internal.NewAssert(t, "TestSplitWords")
cases := map[string]int{
"a word": 2, // {"a", "word"},
"I'am a programmer": 3, // {"I'am", "a", "programmer"},
"Bonjour, je suis programmeur": 4, // {"Bonjour", "je", "suis", "programmeur"},
"a -b-c' 'd'e": 3, // {"a", "b-c'", "d'e"},
"你好，我是一名码农": 0, // nil,
"こんにちは，私はプログラマーです": 0, // nil,
}
for k, v := range cases {
assert.Equal(v, WordCount(k))
}
}