title: 正则表达式极简教程
date: 2016-10-10 11:45:26
categories:
  - DevOps
  - 工具
  - 其他
tags:
  - null
permalink: /pages/0ba465/

checkMatches("abc", "abc");

// 测试正则表达式字符：|
Assert.assertTrue(checkMatches("yes|no", "yes"));
Assert.assertTrue(checkMatches("yes|no", "no"));
Assert.assertFalse(checkMatches("yes|no", "right"));

yes	matches： yes|no
no	matches： yes|no
right	not matches： yes|no

Assert.assertTrue(checkMatches("(play|end)(ing|ed)", "ended"));
Assert.assertTrue(checkMatches("(play|end)(ing|ed)", "ending"));
Assert.assertTrue(checkMatches("(play|end)(ing|ed)", "playing"));
Assert.assertTrue(checkMatches("(play|end)(ing|ed)", "played"));

ended	matches： (play|end)(ing|ed)
ending	matches： (play|end)(ing|ed)
playing	matches： (play|end)(ing|ed)
played	matches： (play|end)(ing|ed)

// 测试正则表达式字符：[]
Assert.assertTrue(checkMatches("[abc]", "b"));  // 字符只能是a、b、c
Assert.assertTrue(checkMatches("[a-z]", "m")); // 字符只能是a - z
Assert.assertTrue(checkMatches("[A-Z]", "O")); // 字符只能是A - Z
Assert.assertTrue(checkMatches("[a-zA-Z]", "K")); // 字符只能是a - z和A - Z
Assert.assertTrue(checkMatches("[a-zA-Z]", "k"));
Assert.assertTrue(checkMatches("[0-9]", "5")); // 字符只能是0 - 9

b	matches： [abc]
m	matches： [a-z]
O	matches： [A-Z]
K	matches： [a-zA-Z]
k	matches： [a-zA-Z]
5	matches： [0-9]

// 测试正则表达式字符：[^]
Assert.assertFalse(checkMatches("[^abc]", "b")); // 字符不能是a、b、c
Assert.assertFalse(checkMatches("[^a-z]", "m")); // 字符不能是a - z
Assert.assertFalse(checkMatches("[^A-Z]", "O")); // 字符不能是A - Z
Assert.assertFalse(checkMatches("[^a-zA-Z]", "K")); // 字符不能是a - z和A - Z
Assert.assertFalse(checkMatches("[^a-zA-Z]", "k"));
Assert.assertFalse(checkMatches("[^0-9]", "5")); // 字符不能是0 - 9

b	not matches： [^abc]
m	not matches： [^a-z]
O	not matches： [^A-Z]
K	not matches： [^a-zA-Z]
k	not matches： [^a-zA-Z]
5	not matches： [^0-9]

// {n}: n 是一个非负整数。匹配确定的 n 次。
checkMatches("ap{1}", "a");
checkMatches("ap{1}", "ap");
checkMatches("ap{1}", "app");
checkMatches("ap{1}", "apppppppppp");

// {n,}: n 是一个非负整数。至少匹配 n 次。
checkMatches("ap{1,}", "a");
checkMatches("ap{1,}", "ap");
checkMatches("ap{1,}", "app");
checkMatches("ap{1,}", "apppppppppp");

// {n,m}: m 和 n 均为非负整数，其中 n <= m。最少匹配 n 次且最多匹配 m 次。
checkMatches("ap{2,5}", "a");
checkMatches("ap{2,5}", "ap");
checkMatches("ap{2,5}", "app");
checkMatches("ap{2,5}", "apppppppppp");

a	not matches： ap{1}
ap	matches： ap{1}
app	not matches： ap{1}
apppppppppp	not matches： ap{1}
a	not matches： ap{1,}
ap	matches： ap{1,}
app	matches： ap{1,}
apppppppppp	matches： ap{1,}
a	not matches： ap{2,5}
ap	not matches： ap{2,5}
app	matches： ap{2,5}
apppppppppp	not matches： ap{2,5}

* 的转义字符：\*
+ 的转义字符：\+
? 的转义字符：\?
^ 的转义字符：\^
$ 的转义字符：\$
. 的转义字符：\.

Assert.assertTrue(checkMatches("^app[a-z]{0,}", "apple")); // 字符串必须以app开头
Assert.assertFalse(checkMatches("^app[a-z]{0,}", "aplause"));

apple	matches： ^app[a-z]{0,}
aplause	not matches： ^app[a-z]{0,}

Assert.assertTrue(checkMatches("[a-z]{0,}ing$", "playing")); // 字符串必须以ing结尾
Assert.assertFalse(checkMatches("[a-z]{0,}ing$", "long"));

playing	matches： [a-z]{0,}ing$
long	not matches： [a-z]{0,}ing$

// 匹配除“\n”之外的任何单个字符
Assert.assertTrue(checkMatches(".{1,}", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_"));
Assert.assertTrue(checkMatches(".{1,}", "~!@#$%^&*()+`-=[]{};:<>,./?|\\"));
Assert.assertFalse(checkMatches(".", "\n"));
Assert.assertFalse(checkMatches("[^\n]", "\n"));

// 匹配一个数字字符。等价于[0-9]
Assert.assertTrue(checkMatches("\\d{1,}", "0123456789"));
// 匹配一个非数字字符。等价于[^0-9]
Assert.assertFalse(checkMatches("\\D{1,}", "0123456789"));

// 匹配包括下划线的任何单词字符。类似但不等价于“[A-Za-z0-9_]”，这里的单词字符指的是Unicode字符集
Assert.assertTrue(checkMatches("\\w{1,}", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_"));
Assert.assertFalse(checkMatches("\\w{1,}", "~!@#$%^&*()+`-=[]{};:<>,./?|\\"));
// 匹配任何非单词字符
Assert.assertFalse(checkMatches("\\W{1,}", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_"));
Assert.assertTrue(checkMatches("\\W{1,}", "~!@#$%^&*()+`-=[]{};:<>,./?|\\"));

// 匹配任何不可见字符，包括空格、制表符、换页符等等。等价于[ \f\n\r\t\v]
Assert.assertTrue(checkMatches("\\s{1,}", " \f\r\n\t"));
// 匹配任何可见字符。等价于[^ \f\n\r\t\v]
Assert.assertFalse(checkMatches("\\S{1,}", " \f\r\n\t"));

ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_	matches： .{1,}
~!@#$%^&*()+`-=[]{};:<>,./?|\\	matches： .{1,}
\n	not matches： .
\n	not matches： [^\n]
0123456789	matches： \\d{1,}
0123456789	not matches： \\D{1,}
ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_	matches： \\w{1,}
~!@#$%^&*()+`-=[]{};:<>,./?|\\	not matches： \\w{1,}
ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_	not matches： \\W{1,}
~!@#$%^&*()+`-=[]{};:<>,./?|\\	matches： \\W{1,}
 \f\r\n\t	matches： \\s{1,}
 \f\r\n\t	not matches： \\S{1,}

// *: 匹配前面的子表达式零次或多次。* 等价于{0,}。
checkMatches("ap*", "a");
checkMatches("ap*", "ap");
checkMatches("ap*", "app");
checkMatches("ap*", "apppppppppp");

// +: 匹配前面的子表达式一次或多次。+ 等价于 {1,}。
checkMatches("ap+", "a");
checkMatches("ap+", "ap");
checkMatches("ap+", "app");
checkMatches("ap+", "apppppppppp");

// ?: 匹配前面的子表达式零次或一次。? 等价于 {0,1}。
checkMatches("ap?", "a");
checkMatches("ap?", "ap");
checkMatches("ap?", "app");
checkMatches("ap?", "apppppppppp");

a	matches： ap*
ap	matches： ap*
app	matches： ap*
apppppppppp	matches： ap*
a	not matches： ap+
ap	matches： ap+
app	matches： ap+
apppppppppp	matches： ap+
a	matches： ap?
ap	matches： ap?
app	not matches： ap?
apppppppppp	not matches： ap?

// (\w+)\s\1\W(\w+) 匹配重复的单词和紧随每个重复的单词的单词
Assert.assertTrue(findAll("(\\w+)\\s\\1\\W(\\w+)",
		"He said that that was the the correct answer.") > 0);

regex = (\w+)\s\1\W(\w+), content: He said that that was the the correct answer.
[1th] start: 8, end: 21, group: that that was
[2th] start: 22, end: 37, group: the the correct

// (?<duplicateWord>\w+)\s\k<duplicateWord>\W(?<nextWord>\w+) 匹配重复的单词和紧随每个重复的单词的单词
Assert.assertTrue(findAll("(?<duplicateWord>\\w+)\\s\\k<duplicateWord>\\W(?<nextWord>\\w+)",
		"He said that that was the the correct answer.") > 0);

regex = (?<duplicateWord>\w+)\s\k<duplicateWord>\W(?<nextWord>\w+), content: He said that that was the the correct answer.
[1th] start: 8, end: 21, group: that that was
[2th] start: 22, end: 37, group: the the correct

// 匹配由句号终止的语句。
Assert.assertTrue(findAll("(?:\\b(?:\\w+)\\W*)+\\.", "This is a short sentence. Never end") > 0);

regex = (?:\b(?:\w+)\W*)+\., content: This is a short sentence. Never end
[1th] start: 0, end: 25, group: This is a short sentence.

// \b\w+(?=\sis\b) 表示要捕获is之前的单词
Assert.assertTrue(findAll("\\b\\w+(?=\\sis\\b)", "The dog is a Malamute.") > 0);
Assert.assertFalse(findAll("\\b\\w+(?=\\sis\\b)", "The island has beautiful birds.") > 0);
Assert.assertFalse(findAll("\\b\\w+(?=\\sis\\b)", "The pitch missed home plate.") > 0);
Assert.assertTrue(findAll("\\b\\w+(?=\\sis\\b)", "Sunday is a weekend day.") > 0);

regex = \b\w+(?=\sis\b), content: The dog is a Malamute.
[1th] start: 4, end: 7, group: dog
regex = \b\w+(?=\sis\b), content: The island has beautiful birds.
not found
regex = \b\w+(?=\sis\b), content: The pitch missed home plate.
not found
regex = \b\w+(?=\sis\b), content: Sunday is a weekend day.
[1th] start: 0, end: 6, group: Sunday

// (?<=\b20)\d{2}\b 表示要捕获以20开头的数字的后面部分
Assert.assertTrue(findAll("(?<=\\b20)\\d{2}\\b", "2010 1999 1861 2140 2009") > 0);

regex = (?<=\b20)\d{2}\b, content: 2010 1999 1861 2140 2009
[1th] start: 2, end: 4, group: 10
[2th] start: 22, end: 24, group: 09

// \b(?!un)\w+\b 表示要捕获未以“un”开头的单词
Assert.assertTrue(findAll("\\b(?!un)\\w+\\b", "unite one unethical ethics use untie ultimate") > 0);

regex = \b(?!un)\w+\b, content: unite one unethical ethics use untie ultimate
[1th] start: 6, end: 9, group: one
[2th] start: 20, end: 26, group: ethics
[3th] start: 27, end: 30, group: use
[4th] start: 37, end: 45, group: ultimate

// (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b 表示要捕获任意工作日（即周一到周五）
Assert.assertTrue(findAll("(?<!(Saturday|Sunday) )\\b\\w+ \\d{1,2}, \\d{4}\\b", "Monday February 1, 2010") > 0);
Assert.assertTrue(findAll("(?<!(Saturday|Sunday) )\\b\\w+ \\d{1,2}, \\d{4}\\b", "Wednesday February 3, 2010") > 0);
Assert.assertFalse(findAll("(?<!(Saturday|Sunday) )\\b\\w+ \\d{1,2}, \\d{4}\\b", "Saturday February 6, 2010") > 0);
Assert.assertFalse(findAll("(?<!(Saturday|Sunday) )\\b\\w+ \\d{1,2}, \\d{4}\\b", "Sunday February 7, 2010") > 0);
Assert.assertTrue(findAll("(?<!(Saturday|Sunday) )\\b\\w+ \\d{1,2}, \\d{4}\\b", "Monday, February 8, 2010") > 0);

regex = (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b, content: Monday February 1, 2010
[1th] start: 7, end: 23, group: February 1, 2010
regex = (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b, content: Wednesday February 3, 2010
[1th] start: 10, end: 26, group: February 3, 2010
regex = (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b, content: Saturday February 6, 2010
not found
regex = (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b, content: Sunday February 7, 2010
not found
regex = (?<!(Saturday|Sunday) )\b\w+ \d{1,2}, \d{4}\b, content: Monday, February 8, 2010
[1th] start: 8, end: 24, group: February 8, 2010

// 贪婪匹配
Assert.assertTrue(findAll("a\\w*b", "abaabaaabaaaab") > 0);

// 懒惰匹配
Assert.assertTrue(findAll("a\\w*?b", "abaabaaabaaaab") > 0);
Assert.assertTrue(findAll("a\\w+?b", "abaabaaabaaaab") > 0);
Assert.assertTrue(findAll("a\\w??b", "abaabaaabaaaab") > 0);
Assert.assertTrue(findAll("a\\w{0,4}?b", "abaabaaabaaaab") > 0);
Assert.assertTrue(findAll("a\\w{3,}?b", "abaabaaabaaaab") > 0);

regex = a\w*b, content: abaabaaabaaaab
[1th] start: 0, end: 14, group: abaabaaabaaaab
regex = a\w*?b, content: abaabaaabaaaab
[1th] start: 0, end: 2, group: ab
[2th] start: 2, end: 5, group: aab
[3th] start: 5, end: 9, group: aaab
[4th] start: 9, end: 14, group: aaaab
regex = a\w+?b, content: abaabaaabaaaab
[1th] start: 0, end: 5, group: abaab
[2th] start: 5, end: 9, group: aaab
[3th] start: 9, end: 14, group: aaaab
regex = a\w??b, content: abaabaaabaaaab
[1th] start: 0, end: 2, group: ab
[2th] start: 2, end: 5, group: aab
[3th] start: 6, end: 9, group: aab
[4th] start: 11, end: 14, group: aab
regex = a\w{0,4}?b, content: abaabaaabaaaab
[1th] start: 0, end: 2, group: ab
[2th] start: 2, end: 5, group: aab
[3th] start: 5, end: 9, group: aaab
[4th] start: 9, end: 14, group: aaaab
regex = a\w{3,}?b, content: abaabaaabaaaab
[1th] start: 0, end: 5, group: abaab
[2th] start: 5, end: 14, group: aaabaaaab

^[\u4e00-\u9fa5]+$

(1[1-5]|2[1-3]|3[1-7]|4[1-3]|5[0-4]|6[1-5])\d{4}

((\d{4}((0[13578]|1[02])(0[1-9]|[12]\d|3[01])|(0[13456789]|1[012])(0[1-9]|[12]\d|30)|02(0[1-9]|1\d|2[0-8])))|([02468][048]|[13579][26])0229)

^((1[1-5]|2[1-3]|3[1-7]|4[1-3]|5[0-4]|6[1-5])\d{4})((\d{2}((0[13578]|1[02])(0[1-9]|[12]\d|3[01])|(0[13456789]|1[012])(0[1-9]|[12]\d|30)|02(0[1-9]|1\d|2[0-8])))|([02468][048]|[13579][26])0229)(\d{3})$

^((1[1-5]|2[1-3]|3[1-7]|4[1-3]|5[0-4]|6[1-5])\d{4})((\d{4}((0[13578]|1[02])(0[1-9]|[12]\d|3[01])|(0[13456789]|1[012])(0[1-9]|[12]\d|30)|02(0[1-9]|1\d|2[0-8])))|([02468][048]|[13579][26])0229)(\d{3}(\d|X))$

^[a-zA-Z]\w{5,17}$

^[A-Za-z0-9](([_\.\-]?[a-zA-Z0-9]+)*)@([A-Za-z0-9]+)(([\.\-]?[a-zA-Z0-9]+)*)\.([A-Za-z]{2,})$

^(ht|f)(tp|tps)\://[a-zA-Z0-9\-\.]+\.([a-zA-Z]{2,3})?(/\S*)?$

^([0-1][0-9]|[2][0-3]):([0-5][0-9])$

^(?:(?!0000)[0-9]{4}([-/.]?)(?:(?:0?[1-9]|1[0-2])\1(?:0?[1-9]|1[0-9]|2[0-8])|(?:0?[13-9]|1[0-2])\1(?:29|30)|(?:0?[13578]|1[02])\1(?:31))|(?:[0-9]{2}(?:0[48]|[2468][048]|[13579][26])|(?:0[48]|[2468][048]|[13579][26])00)([-/.]?)0?2\2(?:29))$

^((\+)?86\s*)?((13[0-9])|(15([0-3]|[5-9]))|(18[0,2,5-9]))\d{8}$

^(010|02[0-9])(\s|-)\d{8}|(0[3-9]\d{2})(\s|-)\d{7}$

^([01]?\d\d?|2[0-4]\d|25[0-5])\.([01]?\d\d?|2[0-4]\d|25[0-5])\.([01]?\d\d?|2[0-4]\d|25[0-5])\.([01]?\d\d?|2[0-4]\d|25[0-5])$

(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))