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
|
// Package camelcase is a micro package to split the words of a camelcase type
// string into a slice of words.
package camelcase
import (
"unicode"
"unicode/utf8"
)
// Split splits the camelcase word and returns a list of words. It also
// supports digits. Both lower camel case and upper camel case are supported.
// For more info please check: https://en.wikipedia.org/wiki/CamelCase
//
// Examples
//
// "" => [""]
// "lowercase" => ["lowercase"]
// "Class" => ["Class"]
// "MyClass" => ["My", "Class"]
// "MyC" => ["My", "C"]
// "HTML" => ["HTML"]
// "PDFLoader" => ["PDF", "Loader"]
// "AString" => ["A", "String"]
// "SimpleXMLParser" => ["Simple", "XML", "Parser"]
// "vimRPCPlugin" => ["vim", "RPC", "Plugin"]
// "GL11Version" => ["GL", "11", "Version"]
// "99Bottles" => ["99", "Bottles"]
// "May5" => ["May", "5"]
// "BFG9000" => ["BFG", "9000"]
// "BöseÜberraschung" => ["Böse", "Überraschung"]
// "Two spaces" => ["Two", " ", "spaces"]
// "BadUTF8\xe2\xe2\xa1" => ["BadUTF8\xe2\xe2\xa1"]
//
// Splitting rules
//
// 1) If string is not valid UTF-8, return it without splitting as
// single item array.
// 2) Assign all unicode characters into one of 4 sets: lower case
// letters, upper case letters, numbers, and all other characters.
// 3) Iterate through characters of string, introducing splits
// between adjacent characters that belong to different sets.
// 4) Iterate through array of split strings, and if a given string
// is upper case:
// if subsequent string is lower case:
// move last character of upper case string to beginning of
// lower case string
func Split(src string) (entries []string) {
// don't split invalid utf8
if !utf8.ValidString(src) {
return []string{src}
}
entries = []string{}
var runes [][]rune
lastClass := 0
class := 0
// split into fields based on class of unicode character
for _, r := range src {
switch {
case unicode.IsLower(r):
class = 1
case unicode.IsUpper(r):
class = 2
case unicode.IsDigit(r):
class = 3
default:
class = 4
}
if class == lastClass {
runes[len(runes)-1] = append(runes[len(runes)-1], r)
} else {
runes = append(runes, []rune{r})
}
lastClass = class
}
// handle upper case -> lower case sequences, e.g.
// "PDFL", "oader" -> "PDF", "Loader"
for i := 0; i < len(runes)-1; i++ {
if unicode.IsUpper(runes[i][0]) && unicode.IsLower(runes[i+1][0]) {
runes[i+1] = append([]rune{runes[i][len(runes[i])-1]}, runes[i+1]...)
runes[i] = runes[i][:len(runes[i])-1]
}
}
// construct []string from results
for _, s := range runes {
if len(s) > 0 {
entries = append(entries, string(s))
}
}
return entries
}
|
