mm_matchs 1.1.4 → 1.1.5
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 +125 -2
- package/html.js +13 -13
- package/htmlformat.js +3 -3
- package/index copy.js +897 -0
- package/index.js +191 -612
- package/package.json +2 -2
- package/regex.js +93 -0
- package/test.js +173 -191
package/README.md
CHANGED
|
@@ -1,2 +1,125 @@
|
|
|
1
|
-
# mm_matchs
|
|
2
|
-
|
|
1
|
+
# mm_matchs
|
|
2
|
+
|
|
3
|
+
这是一个用于匹配复杂字符串结构的Node.js模块,提供了丰富的字符串匹配功能,可以匹配前缀包含、后缀包含、以及时间、地点等多种模式。
|
|
4
|
+
|
|
5
|
+
## 特点
|
|
6
|
+
|
|
7
|
+
- 支持多种匹配模式:前缀匹配、后缀匹配、正则匹配等
|
|
8
|
+
- 内置丰富的匹配规则:时间、日期、地点、网址等
|
|
9
|
+
- 使用简单,支持链式调用
|
|
10
|
+
- 可扩展性强,支持自定义匹配规则
|
|
11
|
+
|
|
12
|
+
## 安装
|
|
13
|
+
|
|
14
|
+
```bash
|
|
15
|
+
npm install mm_matchs
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## 基础用法
|
|
19
|
+
|
|
20
|
+
```javascript
|
|
21
|
+
const Matchs = require('mm_matchs');
|
|
22
|
+
const ms = new Matchs();
|
|
23
|
+
|
|
24
|
+
// 使用String原型扩展方法
|
|
25
|
+
const str = "我叫文武, 手机号码是15817188866";
|
|
26
|
+
|
|
27
|
+
// 前缀匹配
|
|
28
|
+
console.log(str.matchs('手机号码*')); // 15817188866
|
|
29
|
+
|
|
30
|
+
// 后缀匹配
|
|
31
|
+
console.log(str.matchs('*武')); // 文武
|
|
32
|
+
|
|
33
|
+
// 区间匹配
|
|
34
|
+
console.log(str.matchs('如果*就*')); // 匹配两个通配符之间的内容
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
## 内置匹配规则
|
|
38
|
+
|
|
39
|
+
### 时间日期类
|
|
40
|
+
|
|
41
|
+
```javascript
|
|
42
|
+
// 匹配日期时间
|
|
43
|
+
str = "1991-04-01 12:15:36";
|
|
44
|
+
console.log(str.matchs('{日期时间}'));
|
|
45
|
+
|
|
46
|
+
// 匹配年月日
|
|
47
|
+
str = "1991年4月1日";
|
|
48
|
+
console.log(str.matchs('{年月日}'));
|
|
49
|
+
|
|
50
|
+
// 匹配时间
|
|
51
|
+
str = "现在的时间是19:35:59";
|
|
52
|
+
console.log(str.matchs('{时间}'));
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
### 地理位置类
|
|
56
|
+
|
|
57
|
+
```javascript
|
|
58
|
+
// 匹配省份
|
|
59
|
+
str = "广东省深圳市南山区";
|
|
60
|
+
console.log(str.matchs('{省份}'));
|
|
61
|
+
|
|
62
|
+
// 匹配城市
|
|
63
|
+
console.log(str.matchs('{城市}'));
|
|
64
|
+
|
|
65
|
+
// 匹配方位
|
|
66
|
+
console.log(str.matchs('{方位}'));
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
### 网络通信类
|
|
70
|
+
|
|
71
|
+
```javascript
|
|
72
|
+
// 匹配网址
|
|
73
|
+
console.log("http://www.example.com".matchs('{网址}'));
|
|
74
|
+
|
|
75
|
+
// 匹配邮箱
|
|
76
|
+
console.log("test@example.com".matchs('{邮箱}'));
|
|
77
|
+
|
|
78
|
+
// 匹配手机号码
|
|
79
|
+
console.log("13812345678".matchs('{手机号码}'));
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
### 其他常用匹配
|
|
83
|
+
|
|
84
|
+
```javascript
|
|
85
|
+
// 匹配身份证号
|
|
86
|
+
console.log("440123199001011234".matchs('{身份证号}'));
|
|
87
|
+
|
|
88
|
+
// 匹配车牌号
|
|
89
|
+
console.log("粤B12345".matchs('{车牌号}'));
|
|
90
|
+
|
|
91
|
+
// 匹配中英文
|
|
92
|
+
console.log("Hello世界".matchs('{中英文}'));
|
|
93
|
+
```
|
|
94
|
+
|
|
95
|
+
## API文档
|
|
96
|
+
|
|
97
|
+
### 主要方法
|
|
98
|
+
|
|
99
|
+
- `matchs(pattern)`: 字符串匹配方法,支持通配符和预定义规则
|
|
100
|
+
- `tense(str, format)`: 匹配时态
|
|
101
|
+
- `bearing(str, format)`: 匹配方位
|
|
102
|
+
- `province(str, format)`: 匹配省份
|
|
103
|
+
- `city(str, format)`: 匹配城市
|
|
104
|
+
|
|
105
|
+
### 预定义规则
|
|
106
|
+
|
|
107
|
+
模块内置了多种匹配规则,使用花括号`{}`包裹规则名称:
|
|
108
|
+
|
|
109
|
+
- `{日期时间}`: 匹配日期时间格式
|
|
110
|
+
- `{日期}`: 匹配日期
|
|
111
|
+
- `{时间}`: 匹配时间
|
|
112
|
+
- `{网址}`: 匹配URL
|
|
113
|
+
- `{邮箱}`: 匹配电子邮箱
|
|
114
|
+
- `{手机号码}`: 匹配手机号
|
|
115
|
+
- `{身份证号}`: 匹配身份证号码
|
|
116
|
+
- `{车牌号}`: 匹配车牌号
|
|
117
|
+
- `{中英文}`: 匹配中英文混合
|
|
118
|
+
|
|
119
|
+
## 许可证
|
|
120
|
+
|
|
121
|
+
ISC License
|
|
122
|
+
|
|
123
|
+
## 作者
|
|
124
|
+
|
|
125
|
+
qww
|
package/html.js
CHANGED
|
@@ -11,18 +11,21 @@ class Html2Article {
|
|
|
11
11
|
* @param {Object} arg
|
|
12
12
|
*/
|
|
13
13
|
constructor(arg) {
|
|
14
|
+
// 导入正则表达式
|
|
15
|
+
this.regex = require('./regex');
|
|
16
|
+
|
|
14
17
|
// 正则表达式过滤:正则表达式,要替换成的文本
|
|
15
18
|
this.filters = [{
|
|
16
|
-
rx:
|
|
19
|
+
rx: this.regex.script,
|
|
17
20
|
value: ""
|
|
18
21
|
}, {
|
|
19
|
-
rx:
|
|
22
|
+
rx: this.regex.style,
|
|
20
23
|
value: ""
|
|
21
24
|
}, {
|
|
22
|
-
rx:
|
|
25
|
+
rx: this.regex.comment,
|
|
23
26
|
value: ""
|
|
24
27
|
}, {
|
|
25
|
-
rx:
|
|
28
|
+
rx: this.regex.link,
|
|
26
29
|
value: "</a>\n"
|
|
27
30
|
}];
|
|
28
31
|
|
|
@@ -71,19 +74,19 @@ Html2Article.prototype.getArticle = function(html) {
|
|
|
71
74
|
var body = "";
|
|
72
75
|
|
|
73
76
|
if (html.indexOf("<article") !== -1) {
|
|
74
|
-
var mh = html.match(
|
|
77
|
+
var mh = html.match(eval(this.regex.article));
|
|
75
78
|
if (mh) {
|
|
76
79
|
body = mh[0];
|
|
77
80
|
}
|
|
78
81
|
} else {
|
|
79
82
|
if (html.indexOf("<main") !== -1) {
|
|
80
|
-
var mh = html.match(
|
|
83
|
+
var mh = html.match(eval(this.regex.main));
|
|
81
84
|
if (mh) {
|
|
82
85
|
body = mh[0];
|
|
83
86
|
}
|
|
84
87
|
}
|
|
85
88
|
else {
|
|
86
|
-
var mh = html.match(
|
|
89
|
+
var mh = html.match(eval(this.regex.body));
|
|
87
90
|
if (mh) {
|
|
88
91
|
body = mh[0];
|
|
89
92
|
}
|
|
@@ -146,10 +149,8 @@ Html2Article.prototype.getTitle = function(html) {
|
|
|
146
149
|
* @return {String} 返回时间字符串
|
|
147
150
|
*/
|
|
148
151
|
Html2Article.prototype.getPublishDate = function(html) {
|
|
149
|
-
|
|
150
|
-
var
|
|
151
|
-
var rx =
|
|
152
|
-
/((\d{4}(\-|\/|\.)(0[1-9]|1[012]|[1-9])(\-|\/|\.)([12][0-9]|0[1-9]|3[01]|[1-9]))|(([一二三四五六七八九]+年)?[一二三四五六七八九十]+月([一二三四五六七八九十]+(日|号))?)|((\d{4}年)?(0?[1-9]|1[012]|[1-9])月([12][0-9]|0?[1-9]|3[01]|[1-9])(日|号))) ?((([01][0-9]|2[0-3]):([0-4][0-9]|5[0-9])(:([0-4][0-9]|5[0-9]))?)|(([01][0-9]|2[0-3])点([0-4][0-9]|5[0-9])分(([0-4][0-9]|5[0-9])秒)?)|([一二三四五六七八九十]+点[一二三四五六七八九十]+分([一二三四五六七八九十]+秒)?))/;
|
|
152
|
+
var text = html.replace(eval(this.regex.clear_tag), "");
|
|
153
|
+
var rx = eval(this.regex.datetime);
|
|
153
154
|
var mh = text.match(rx);
|
|
154
155
|
var result = "1900-01-01";
|
|
155
156
|
if (mh) {
|
|
@@ -175,8 +176,7 @@ Html2Article.prototype.getContent = function(bodyText) {
|
|
|
175
176
|
// 去除每行的空白字符,剔除标签
|
|
176
177
|
for (var i = 0; i < orgLines.length; i++) {
|
|
177
178
|
var lineInfo = orgLines[i];
|
|
178
|
-
|
|
179
|
-
var str = lineInfo.replace(/<\/p>|<br.*?\/>/gi, "\r\n").replace(/<.*?>/g, "").trim();
|
|
179
|
+
var str = lineInfo.replace(eval(this.regex.line_break), "\r\n").replace(eval(this.regex.clearTag), "").trim();
|
|
180
180
|
if (str) {
|
|
181
181
|
lines.push(str);
|
|
182
182
|
}
|
package/htmlformat.js
CHANGED
|
@@ -75,7 +75,7 @@ function style_html(html_source, indent_size, indent_character, max_char) {
|
|
|
75
75
|
|
|
76
76
|
var char = '';
|
|
77
77
|
var content = [];
|
|
78
|
-
var reg_match =
|
|
78
|
+
var reg_match = this.regex.scriptEndTag;
|
|
79
79
|
reg_match.lastIndex = this.pos;
|
|
80
80
|
var reg_array = reg_match.exec(this.input);
|
|
81
81
|
var end_script = reg_array ? reg_array.index : this.input.length; //absolute end of script
|
|
@@ -193,7 +193,7 @@ function style_html(html_source, indent_size, indent_character, max_char) {
|
|
|
193
193
|
} else if (tag_check.charAt(0) === '!') { //peek for <!-- comment
|
|
194
194
|
if (tag_check.indexOf('[if') != -1) { //peek for <!--[if conditional comment
|
|
195
195
|
if (tag_complete.indexOf('!IE') != -1) { //this type needs a closing --> so...
|
|
196
|
-
var comment = this.get_unformatted(
|
|
196
|
+
var comment = this.get_unformatted(this.regex.commentEnd, tag_complete); //...delegate to get_unformatted
|
|
197
197
|
content.push(comment);
|
|
198
198
|
}
|
|
199
199
|
this.tag_type = 'START';
|
|
@@ -201,7 +201,7 @@ function style_html(html_source, indent_size, indent_character, max_char) {
|
|
|
201
201
|
this.tag_type = 'END';
|
|
202
202
|
this.unindent();
|
|
203
203
|
} else if (tag_check.indexOf('[cdata[') != -1) { //if it's a <[cdata[ comment...
|
|
204
|
-
var comment = this.get_unformatted(
|
|
204
|
+
var comment = this.get_unformatted(this.regex.cdataEnd, tag_complete); //...delegate to get_unformatted function
|
|
205
205
|
content.push(comment);
|
|
206
206
|
this.tag_type = 'SINGLE'; //<![CDATA[ comments are treated like single tags
|
|
207
207
|
} else {
|