wordsninja 1.0.0 → 1.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +12 -10
- package/example.js +15 -0
- package/index.js +22 -33
- package/package.json +4 -4
- package/words-en.json +126140 -0
- package/words-en.txt +0 -126138
package/README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
|
1
|
-
# WordsNinja
|
|
2
|
-
Split
|
|
1
|
+
# WordsNinja
|
|
2
|
+
Split an English sentence that lacks spaces and accents into separate words.
|
|
3
|
+
|
|
4
|
+
[](https://www.npmjs.com/package/wordsninja)
|
|
3
5
|
|
|
4
6
|
## Install
|
|
5
7
|
```bash
|
|
@@ -27,7 +29,7 @@ WordsNinja.addWords('new word');
|
|
|
27
29
|
```
|
|
28
30
|
Parameters
|
|
29
31
|
|
|
30
|
-
- `word`: The word (string|array)
|
|
32
|
+
- `word`: The word(s) (string|array)
|
|
31
33
|
|
|
32
34
|
|
|
33
35
|
|
|
@@ -39,10 +41,10 @@ let words = WordsNinja.splitSentence(string, {camelCaseSplitter, capitalizeFirst
|
|
|
39
41
|
|
|
40
42
|
Parameters
|
|
41
43
|
- `string`: The string for split
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
44
|
+
- `options`
|
|
45
|
+
- `camelCaseSplitter`: Split by Camel Case, Default is `false` (optional)
|
|
46
|
+
- `capitalizeFirstLetter`: Capitalize First Letter, Default is `false` (optional)
|
|
47
|
+
- `joinWords`: Return join words as sentence, Default is `false` (optional)
|
|
46
48
|
|
|
47
49
|
Example
|
|
48
50
|
|
|
@@ -69,9 +71,9 @@ Result
|
|
|
69
71
|
let string = 'youneedtolearnfromyourmistakes';
|
|
70
72
|
let words = WordsNinja.splitSentence(string,
|
|
71
73
|
{
|
|
72
|
-
camelCaseSplitter: true, //
|
|
74
|
+
camelCaseSplitter: true, // Camel case splitting
|
|
73
75
|
capitalizeFirstLetter: true, // Capitalize first letter of result
|
|
74
|
-
joinWords: true // Join words
|
|
76
|
+
joinWords: true // Join words with spaces
|
|
75
77
|
}
|
|
76
78
|
);
|
|
77
79
|
console.log(words);
|
|
@@ -101,7 +103,7 @@ WordsNinja.addWords('Parsa');
|
|
|
101
103
|
let words = WordsNinja.splitSentence(string,
|
|
102
104
|
{
|
|
103
105
|
capitalizeFirstLetter: true, // Capitalize first letter of result
|
|
104
|
-
joinWords: true // Join words
|
|
106
|
+
joinWords: true // Join words with spaces
|
|
105
107
|
}
|
|
106
108
|
);
|
|
107
109
|
console.log(words);
|
package/example.js
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
const WordsNinjaPack = require("./index.js");
|
|
2
|
+
const WordsNinja = new WordsNinjaPack();
|
|
3
|
+
|
|
4
|
+
(async () => {
|
|
5
|
+
await WordsNinja.loadDictionary();
|
|
6
|
+
|
|
7
|
+
let string = 'youneedtolearnfromyourmistakes';
|
|
8
|
+
let words = WordsNinja.splitSentence(string,
|
|
9
|
+
{
|
|
10
|
+
camelCaseSplitter: false, // Camel case splitting
|
|
11
|
+
capitalizeFirstLetter: false, // Capitalize first letter of result
|
|
12
|
+
joinWords: false // Join words with space
|
|
13
|
+
});
|
|
14
|
+
console.log(words);
|
|
15
|
+
})();
|
package/index.js
CHANGED
|
@@ -1,9 +1,7 @@
|
|
|
1
1
|
'use strict'
|
|
2
2
|
|
|
3
|
-
const
|
|
4
|
-
const path = require('path');
|
|
3
|
+
const jsonWords = require('./words-en.json');
|
|
5
4
|
const splitRegex = new RegExp("[^a-zA-Z0-9']+", "g");
|
|
6
|
-
const FILE_WORDS = path.join(__dirname, 'words-en.txt');
|
|
7
5
|
let maxWordLen = 0;
|
|
8
6
|
let wordCost = {};
|
|
9
7
|
let maxCost = 9e999;
|
|
@@ -19,21 +17,16 @@ class WordsNinja {
|
|
|
19
17
|
*/
|
|
20
18
|
loadDictionary() {
|
|
21
19
|
return new Promise((resolve) => {
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
wordCost[word]
|
|
30
|
-
if (word.length > maxWordLen)
|
|
31
|
-
maxWordLen = word.length;
|
|
32
|
-
if (wordCost[word] < maxCost)
|
|
33
|
-
maxCost = wordCost[word];
|
|
34
|
-
});
|
|
35
|
-
resolve(wordCost);
|
|
20
|
+
let words = jsonWords;
|
|
21
|
+
|
|
22
|
+
words.forEach(function (word, index) {
|
|
23
|
+
wordCost[word] = Math.log((index + 1) * Math.log(words.length));
|
|
24
|
+
if (word.length > maxWordLen)
|
|
25
|
+
maxWordLen = word.length;
|
|
26
|
+
if (wordCost[word] < maxCost)
|
|
27
|
+
maxCost = wordCost[word];
|
|
36
28
|
});
|
|
29
|
+
resolve(wordCost);
|
|
37
30
|
});
|
|
38
31
|
};
|
|
39
32
|
|
|
@@ -45,7 +38,7 @@ class WordsNinja {
|
|
|
45
38
|
* @param {boolean} options.joinWords - Return join words as sentence, Default false (optional)
|
|
46
39
|
* @returns {Array|string} result - Split String
|
|
47
40
|
*/
|
|
48
|
-
splitSentence(string, {
|
|
41
|
+
splitSentence(string, {camelCaseSplitter, capitalizeFirstLetter, joinWords} = {}) {
|
|
49
42
|
let list = [];
|
|
50
43
|
let that = this;
|
|
51
44
|
camelCaseSplitter = camelCaseSplitter || false;
|
|
@@ -60,10 +53,8 @@ class WordsNinja {
|
|
|
60
53
|
list.push(word);
|
|
61
54
|
})
|
|
62
55
|
})
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
else
|
|
66
|
-
return list;
|
|
56
|
+
|
|
57
|
+
return joinWords ? list.join(' ') : list;
|
|
67
58
|
}
|
|
68
59
|
|
|
69
60
|
/**
|
|
@@ -96,14 +87,14 @@ class WordsNinja {
|
|
|
96
87
|
let candidates = cost.slice(Math.max(0, i - maxWordLen), i).reverse();
|
|
97
88
|
let minPair = [Number.MAX_SAFE_INTEGER, 0];
|
|
98
89
|
candidates.forEach(function (c, k) {
|
|
99
|
-
let
|
|
90
|
+
let cCost;
|
|
100
91
|
if (wordCost[s.substring(i - k - 1, i).toLowerCase()]) {
|
|
101
|
-
|
|
92
|
+
cCost = c + wordCost[s.substring(i - k - 1, i).toLowerCase()];
|
|
102
93
|
} else {
|
|
103
|
-
|
|
94
|
+
cCost = Number.MAX_SAFE_INTEGER;
|
|
104
95
|
}
|
|
105
|
-
if (
|
|
106
|
-
minPair = [
|
|
96
|
+
if (cCost < minPair[0]) {
|
|
97
|
+
minPair = [cCost, k + 1];
|
|
107
98
|
}
|
|
108
99
|
})
|
|
109
100
|
return minPair;
|
|
@@ -118,13 +109,11 @@ class WordsNinja {
|
|
|
118
109
|
while (i > 0) {
|
|
119
110
|
let c = best_match(i)[0];
|
|
120
111
|
let k = best_match(i)[1];
|
|
121
|
-
//if (c == cost[i])
|
|
122
|
-
// console.log("Alert: " + c);
|
|
123
112
|
|
|
124
113
|
let newToken = true;
|
|
125
|
-
if (s.slice(i - k, i)
|
|
114
|
+
if (s.slice(i - k, i) !== "'") {
|
|
126
115
|
if (out.length > 0) {
|
|
127
|
-
if (out[-1]
|
|
116
|
+
if (out[-1] === "'s" || (Number.isInteger(s[i - 1]) && Number.isInteger(out[-1][0]))) {
|
|
128
117
|
out[-1] = s.slice(i - k, i) + out[-1];
|
|
129
118
|
newToken = false;
|
|
130
119
|
}
|
|
@@ -145,7 +134,7 @@ class WordsNinja {
|
|
|
145
134
|
* Camel Case Splitter
|
|
146
135
|
* Based on 'split-camelcase-to-words' package, https://www.npmjs.com/package/split-camelcase-to-words
|
|
147
136
|
* @private
|
|
148
|
-
* @param {string} inputString
|
|
137
|
+
* @param {string} inputString
|
|
149
138
|
* @return {string} String
|
|
150
139
|
*/
|
|
151
140
|
camelCaseSplitter(inputString) {
|
|
@@ -155,7 +144,7 @@ class WordsNinja {
|
|
|
155
144
|
|
|
156
145
|
let splitStringsArray = [];
|
|
157
146
|
arrayOfStrings.forEach(tempString => {
|
|
158
|
-
if (tempString
|
|
147
|
+
if (tempString !== '') {
|
|
159
148
|
let splitWords = tempString.split(/(?=[A-Z])/).join(" ");
|
|
160
149
|
splitStringsArray.push(splitWords);
|
|
161
150
|
}
|
package/package.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "wordsninja",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.1.0",
|
|
4
4
|
"description": "Split a English sentence without any spaces nor accents, into words.",
|
|
5
5
|
"main": "index.js",
|
|
6
|
-
"author": "Parsa Kafi <parselearn@gmail.com> (
|
|
6
|
+
"author": "Parsa Kafi <parselearn@gmail.com> (https://parsa.ws)",
|
|
7
7
|
"license": "MIT",
|
|
8
8
|
"scripts": {},
|
|
9
9
|
"keywords": [
|
|
@@ -20,10 +20,10 @@
|
|
|
20
20
|
],
|
|
21
21
|
"repository": {
|
|
22
22
|
"type": "git",
|
|
23
|
-
"url": "https://github.com/parsakafi/wordsninja.git"
|
|
23
|
+
"url": "git+https://github.com/parsakafi/wordsninja.git"
|
|
24
24
|
},
|
|
25
25
|
"bugs": {
|
|
26
26
|
"url": "https://github.com/parsakafi/wordsninja/issues"
|
|
27
27
|
},
|
|
28
|
-
"homepage": "https://
|
|
28
|
+
"homepage": "https://parsa.ws/projects/wordsninja-js-package"
|
|
29
29
|
}
|