blob: 003460ed4ad3e70ae5389d6305200ffdfceab331 (
plain)
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
|
package parse
import (
"strings"
)
// TokenizeText function use the given raw text and parses by a Rule object and
// retrieves the parsed text in a Text struct object.
func TokenizeText(rawText string, rule Rule) Text {
return findSentences(rawText, rule)
}
func findSentences(rawText string, rule Rule) Text {
text := Text{}
var sentence string
var i int
slen := len(rawText)
for j, chr := range rawText {
j += len(string(chr))
//when separator or the last
if rule.IsSentenceSeparator(chr) || j == slen {
sentence = rawText[i:j]
if len(sentence) > 0 {
text.Append(sentence, findWords(sentence, rule))
}
sentence = ""
i = j
}
}
return text
}
func findWords(rawSentence string, rule Rule) (words []string) {
words = []string{}
var word string
var i int
slen := len(rawSentence)
for j, chr := range rawSentence {
chrlen := len(string(chr))
j += chrlen
//when separator or the last
if sep := rule.IsWordSeparator(chr); sep || j == slen {
if sep {
word = rawSentence[i : j-chrlen]
} else {
word = rawSentence[i:j]
}
if len(word) > 0 {
words = append(words, strings.ToLower(word))
}
word = ""
i = j
}
}
return
}
|
