我正在寻找最终的邮政编码和邮政编码正则表达式。我正在寻找一种能覆盖世界大部分地区(希望是所有地区)的东西。
当前回答
我知道这是一个老问题，但我无意中遇到了同样的问题。 我有来自100多个国家的发票，并试图得到正确的债权人在zip(如果每其他检查失败)。 所以我所做的就是写一个简短的Python脚本，从一个字符串创建一个模式:
class RegexPatternBuilder:
"""
Builds a regex pattern out of a given string(i.e. --> HM452 AX2155 : [A-Z]{2}\d{3}\s{1}[A-Z]{2}\d{4})
"""
__is_alpha_count = 0
__is_numeric_count = 0
__is_whitespace_count = 0
__pattern = ""
# Count: wich character of the string we're locking at right now
__count = 0
# Countrys like Andora starts theire ZIP with the country abbreviation :AD500
# So check at first if the ZIP starts with the abbreviation and if so, add it to the pattern and increase the count.
def __init__(self, zip_string, country):
self.__zip_string = zip_string
self.__country = country
if self.__zip_string.startswith(country):
self.__pattern = f'({self.__country})'
self.__count += len(self.__country)
def build_regex(self):
# Last step ;
# Add the current alpha_numeric pattern with count
if len(self.__zip_string) == self.__count:
if self.__is_alpha_count:
self.__pattern += f"[A-Z]{{{self.__is_alpha_count}}}"
if self.__is_numeric_count:
self.__pattern += f"\d{{{self.__is_numeric_count}}}"
return f'{self.__pattern}\\b'
# Case: Whitespace
# Check if there is a crossing from numeric / alphanumeric to whitespace,
# if so --> add the alpha_numeric regex to the whole pattern with the
# count as the number of viable appeaerances.
# Since there is max 1 whitespace in a ZIP, add the whitespace regex immediately.
# Every other case is similar to that.
if self.__zip_string[self.__count].isspace():
if self.__is_numeric_count:
self.__pattern += f"\d{{{self.__is_numeric_count}}}"
if self.__is_alpha_count:
self.__pattern += f"[A-Z]{{{self.__is_alpha_count}}}"
self.__pattern += "\s{1}"
self.__is_whitespace_count += 1
self.__is_alpha_count = 0
self.__is_numeric_count = 0
# Case: Is Alphanumeric
if self.__zip_string[self.__count].isalpha():
if self.__is_numeric_count:
self.__pattern += f"[0-9]{{{self.__is_numeric_count}}}"
self.__is_whitespace_count = 0
self.__is_alpha_count += 1
self.__is_numeric_count = 0
# Case: Is Numeric
if self.__zip_string[self.__count].isnumeric():
if self.__is_alpha_count:
self.__pattern += f"[A-Z]{{{self.__is_alpha_count}}}"
self.__is_whitespace_count = 0
self.__is_alpha_count = 0
self.__is_numeric_count += 1
# Case: Special Character (i.e. - )
# No escaping or count for this so far, because it shouldn't be needed for our zip purposes
if not self.__zip_string[self.__count].isalpha() \
and not self.__zip_string[self.__count].isnumeric() \
and not self.__zip_string[self.__count].isspace():
self.__pattern += f'{self.__zip_string[self.__count]}{{1}}'
self.__count += 1
return self.build_regex()
有了这个，我创建了所有不同的可能的正则表达式的所有拉链(按国家)，我们历史上写回一个db表(即这样的东西在最后: 国家:RE PATTERN:(\d{5})\b[这可能是什么国家;d])
也许它能帮助别人。
其他回答
没有。
世界各地的邮政/邮政编码并不遵循一个共同的模式。在一些国家，它们由数字组成，在其他国家，它们可以是数字和字母的组合，有些可以包含空格，有些可以包含点，字符的数量从2个到至少6个不等……
你能做的(理论上)是为世界上每个国家创建一个单独的正则表达式，我不推荐。但是您仍然会忽略验证部分:邮政编码12345可能存在，但12346不存在，也许12344也不存在。你如何用正则表达式检查它?
你不能。
你为什么要这么做，你为什么这么在乎?正如Tom Ritter所指出的，你是否有一个ZIP/邮政编码并不重要，更不用说它是否有效了，除非你真的要把东西发送到那个地址。即使你希望有一天你会给他们寄东西，这并不意味着你今天就需要邮政编码。
unicode CLDR包含每个国家的邮政编码正则表达式。(总共158个正则表达式!)
从http://unicode.org/Public/cldr/26.0.1/下载core.zip 解压缩core.zip 从解压缩的内容(直接内容:common/ supplementary /postalCodeData.xml)中查看common/ supplementary /postalCodeData.xml
谷歌还有一个web服务，提供每个国家的地址格式信息，包括邮政编码，网址是http://i18napis.appspot.com/address (我通过http://unicode.org/review/pri180/找到了这个链接)
编辑
这里是postalCodeData.xml正则表达式的副本:
"GB", "GIR[ ]?0AA|((AB|AL|B|BA|BB|BD|BH|BL|BN|BR|BS|BT|CA|CB|CF|CH|CM|CO|CR|CT|CV|CW|DA|DD|DE|DG|DH|DL|DN|DT|DY|E|EC|EH|EN|EX|FK|FY|G|GL|GY|GU|HA|HD|HG|HP|HR|HS|HU|HX|IG|IM|IP|IV|JE|KA|KT|KW|KY|L|LA|LD|LE|LL|LN|LS|LU|M|ME|MK|ML|N|NE|NG|NN|NP|NR|NW|OL|OX|PA|PE|PH|PL|PO|PR|RG|RH|RM|S|SA|SE|SG|SK|SL|SM|SN|SO|SP|SR|SS|ST|SW|SY|TA|TD|TF|TN|TQ|TR|TS|TW|UB|W|WA|WC|WD|WF|WN|WR|WS|WV|YO|ZE)(\d[\dA-Z]?[ ]?\d[ABD-HJLN-UW-Z]{2}))|BFPO[ ]?\d{1,4}"
"JE", "JE\d[\dA-Z]?[ ]?\d[ABD-HJLN-UW-Z]{2}"
"GG", "GY\d[\dA-Z]?[ ]?\d[ABD-HJLN-UW-Z]{2}"
"IM", "IM\d[\dA-Z]?[ ]?\d[ABD-HJLN-UW-Z]{2}"
"US", "\d{5}([ \-]\d{4})?"
"CA", "[ABCEGHJKLMNPRSTVXY]\d[ABCEGHJ-NPRSTV-Z][ ]?\d[ABCEGHJ-NPRSTV-Z]\d"
"DE", "\d{5}"
"JP", "\d{3}-\d{4}"
"FR", "\d{2}[ ]?\d{3}"
"AU", "\d{4}"
"IT", "\d{5}"
"CH", "\d{4}"
"AT", "\d{4}"
"ES", "\d{5}"
"NL", "\d{4}[ ]?[A-Z]{2}"
"BE", "\d{4}"
"DK", "\d{4}"
"SE", "\d{3}[ ]?\d{2}"
"NO", "\d{4}"
"BR", "\d{5}[\-]?\d{3}"
"PT", "\d{4}([\-]\d{3})?"
"FI", "\d{5}"
"AX", "22\d{3}"
"KR", "\d{3}[\-]\d{3}"
"CN", "\d{6}"
"TW", "\d{3}(\d{2})?"
"SG", "\d{6}"
"DZ", "\d{5}"
"AD", "AD\d{3}"
"AR", "([A-HJ-NP-Z])?\d{4}([A-Z]{3})?"
"AM", "(37)?\d{4}"
"AZ", "\d{4}"
"BH", "((1[0-2]|[2-9])\d{2})?"
"BD", "\d{4}"
"BB", "(BB\d{5})?"
"BY", "\d{6}"
"BM", "[A-Z]{2}[ ]?[A-Z0-9]{2}"
"BA", "\d{5}"
"IO", "BBND 1ZZ"
"BN", "[A-Z]{2}[ ]?\d{4}"
"BG", "\d{4}"
"KH", "\d{5}"
"CV", "\d{4}"
"CL", "\d{7}"
"CR", "\d{4,5}|\d{3}-\d{4}"
"HR", "\d{5}"
"CY", "\d{4}"
"CZ", "\d{3}[ ]?\d{2}"
"DO", "\d{5}"
"EC", "([A-Z]\d{4}[A-Z]|(?:[A-Z]{2})?\d{6})?"
"EG", "\d{5}"
"EE", "\d{5}"
"FO", "\d{3}"
"GE", "\d{4}"
"GR", "\d{3}[ ]?\d{2}"
"GL", "39\d{2}"
"GT", "\d{5}"
"HT", "\d{4}"
"HN", "(?:\d{5})?"
"HU", "\d{4}"
"IS", "\d{3}"
"IN", "\d{6}"
"ID", "\d{5}"
"IL", "\d{5}"
"JO", "\d{5}"
"KZ", "\d{6}"
"KE", "\d{5}"
"KW", "\d{5}"
"LA", "\d{5}"
"LV", "\d{4}"
"LB", "(\d{4}([ ]?\d{4})?)?"
"LI", "(948[5-9])|(949[0-7])"
"LT", "\d{5}"
"LU", "\d{4}"
"MK", "\d{4}"
"MY", "\d{5}"
"MV", "\d{5}"
"MT", "[A-Z]{3}[ ]?\d{2,4}"
"MU", "(\d{3}[A-Z]{2}\d{3})?"
"MX", "\d{5}"
"MD", "\d{4}"
"MC", "980\d{2}"
"MA", "\d{5}"
"NP", "\d{5}"
"NZ", "\d{4}"
"NI", "((\d{4}-)?\d{3}-\d{3}(-\d{1})?)?"
"NG", "(\d{6})?"
"OM", "(PC )?\d{3}"
"PK", "\d{5}"
"PY", "\d{4}"
"PH", "\d{4}"
"PL", "\d{2}-\d{3}"
"PR", "00[679]\d{2}([ \-]\d{4})?"
"RO", "\d{6}"
"RU", "\d{6}"
"SM", "4789\d"
"SA", "\d{5}"
"SN", "\d{5}"
"SK", "\d{3}[ ]?\d{2}"
"SI", "\d{4}"
"ZA", "\d{4}"
"LK", "\d{5}"
"TJ", "\d{6}"
"TH", "\d{5}"
"TN", "\d{4}"
"TR", "\d{5}"
"TM", "\d{6}"
"UA", "\d{5}"
"UY", "\d{5}"
"UZ", "\d{6}"
"VA", "00120"
"VE", "\d{4}"
"ZM", "\d{5}"
"AS", "96799"
"CC", "6799"
"CK", "\d{4}"
"RS", "\d{6}"
"ME", "8\d{4}"
"CS", "\d{5}"
"YU", "\d{5}"
"CX", "6798"
"ET", "\d{4}"
"FK", "FIQQ 1ZZ"
"NF", "2899"
"FM", "(9694[1-4])([ \-]\d{4})?"
"GF", "9[78]3\d{2}"
"GN", "\d{3}"
"GP", "9[78][01]\d{2}"
"GS", "SIQQ 1ZZ"
"GU", "969[123]\d([ \-]\d{4})?"
"GW", "\d{4}"
"HM", "\d{4}"
"IQ", "\d{5}"
"KG", "\d{6}"
"LR", "\d{4}"
"LS", "\d{3}"
"MG", "\d{3}"
"MH", "969[67]\d([ \-]\d{4})?"
"MN", "\d{6}"
"MP", "9695[012]([ \-]\d{4})?"
"MQ", "9[78]2\d{2}"
"NC", "988\d{2}"
"NE", "\d{4}"
"VI", "008(([0-4]\d)|(5[01]))([ \-]\d{4})?"
"PF", "987\d{2}"
"PG", "\d{3}"
"PM", "9[78]5\d{2}"
"PN", "PCRN 1ZZ"
"PW", "96940"
"RE", "9[78]4\d{2}"
"SH", "(ASCN|STHL) 1ZZ"
"SJ", "\d{4}"
"SO", "\d{5}"
"SZ", "[HLMS]\d{3}"
"TC", "TKCA 1ZZ"
"WF", "986\d{2}"
"XK", "\d{5}"
"YT", "976\d{2}"
每个邮政编码系统只使用A-Z和/或0-9，有时还使用空格/破折号 并不是每个国家都使用邮政编码(例如都柏林以外的爱尔兰)，但我们在这里忽略它。 最短的邮政编码格式是塞拉利昂NN 最长的是美属萨摩亚，有NNNNN-NNNNNN 你应该留出一个空格或破折号。 不应该以空格或破折号开始或结束
这应包括上述内容:
(?i)^[a-z0-9][a-z0-9\- ]{0,10}[a-z0-9]$
试图用一个正则表达式覆盖整个世界是不完全可能的，当然也不可行，也不推荐。
不是自吹自擂，但我已经写了一些非常全面的正则表达式，你可能会觉得有用。
Canadian postal codes Basic validation: ^[ABCEGHJ-NPRSTVXY]{1}[0-9]{1}[ABCEGHJ-NPRSTV-Z]{1}[ ]?[0-9]{1}[ABCEGHJ-NPRSTV-Z]{1}[0-9]{1}$ Extended validation: ^(A(0[ABCEGHJ-NPR]|1[ABCEGHK-NSV-Y]|2[ABHNV]|5[A]|8[A])|B(0[CEHJ-NPRSTVW]|1[ABCEGHJ-NPRSTV-Y]|2[ABCEGHJNRSTV-Z]|3[ABEGHJ-NPRSTVZ]|4[ABCEGHNPRV]|5[A]|6[L]|9[A])|C(0[AB]|1[ABCEN])|E(1[ABCEGHJNVWX]|2[AEGHJ-NPRSV]|3[ABCELNVYZ]|4[ABCEGHJ-NPRSTV-Z]|5[ABCEGHJ-NPRSTV]|6[ABCEGHJKL]|7[ABCEGHJ-NP]|8[ABCEGJ-NPRST]|9[ABCEGH])|G(0[ACEGHJ-NPRSTV-Z]|1[ABCEGHJ-NPRSTV-Y]|2[ABCEGJ-N]|3[ABCEGHJ-NZ]|4[ARSTVWXZ]|5[ABCHJLMNRTVXYZ]|6[ABCEGHJKLPRSTVWXZ]|7[ABGHJKNPSTXYZ]|8[ABCEGHJ-NPTVWYZ]|9[ABCHNPRTX])|H(0[HM]|1[ABCEGHJ-NPRSTV-Z]|2[ABCEGHJ-NPRSTV-Z]|3[ABCEGHJ-NPRSTV-Z]|4[ABCEGHJ-NPRSTV-Z]|5[AB]|7[ABCEGHJ-NPRSTV-Y]|8[NPRSTYZ]|9[ABCEGHJKPRSWX])|J(0[ABCEGHJ-NPRSTV-Z]|1[ACEGHJ-NRSTXZ]|2[ABCEGHJ-NRSTWXY]|3[ABEGHLMNPRTVXYZ]|4[BGHJ-NPRSTV-Z]|5[ABCJ-MRTV-Z]|6[AEJKNRSTVWYXZ]|7[ABCEGHJ-NPRTV-Z]|8[ABCEGHLMNPRTVXYZ]|9[ABEHJLNTVXYZ])|K(0[ABCEGHJ-M]|1[ABCEGHJ-NPRSTV-Z]|2[ABCEGHJ-MPRSTVW]|4[ABCKMPR]|6[AHJKTV]|7[ACGHK-NPRSV]|8[ABHNPRV]|9[AHJKLV])|L(0[[ABCEGHJ-NPRS]]|1[ABCEGHJ-NPRSTV-Z]|2[AEGHJMNPRSTVW]|3[BCKMPRSTVXYZ]|4[ABCEGHJ-NPRSTV-Z]|5[ABCEGHJ-NPRSTVW]|6[ABCEGHJ-MPRSTV-Z]|7[ABCEGJ-NPRST]|8[EGHJ-NPRSTVW]|9[ABCGHK-NPRSTVWYZ])|M(1[BCEGHJ-NPRSTVWX]|2[HJ-NPR]|3[ABCHJ-N]|4[ABCEGHJ-NPRSTV-Y]|5[ABCEGHJ-NPRSTVWX]|6[ABCEGHJ-NPRS]|7[AY]|8[V-Z]|9[ABCLMNPRVW])|N(0[ABCEGHJ-NPR]|1[ACEGHKLMPRST]|2[ABCEGHJ-NPRTVZ]|3[ABCEHLPRSTVWY]|4[BGKLNSTVWXZ]|5[ACHLPRV-Z]|6[ABCEGHJ-NP]|7[AGLMSTVWX]|8[AHMNPRSTV-Y]|9[ABCEGHJKVY])|P(0[ABCEGHJ-NPRSTV-Y]|1[ABCHLP]|2[ABN]|3[ABCEGLNPY]|4[NPR]|5[AEN]|6[ABC]|7[ABCEGJKL]|8[NT]|9[AN])|R(0[ABCEGHJ-M]|1[ABN]|2[CEGHJ-NPRV-Y]|3[ABCEGHJ-NPRSTV-Y]|4[AHJKL]|5[AGH]|6[MW]|7[ABCN]|8[AN]|9[A])|S(0[ACEGHJ-NP]|2[V]|3[N]|4[AHLNPRSTV-Z]|6[HJKVWX]|7[HJ-NPRSTVW]|9[AHVX])|T(0[ABCEGHJ-MPV]|1[ABCGHJ-MPRSV-Y]|2[ABCEGHJ-NPRSTV-Z]|3[ABCEGHJ-NPRZ]|4[ABCEGHJLNPRSTVX]|5[ABCEGHJ-NPRSTV-Z]|6[ABCEGHJ-NPRSTVWX]|7[AENPSVXYZ]|8[ABCEGHLNRSVWX]|9[ACEGHJKMNSVWX])|V(0[ABCEGHJ-NPRSTVWX]|1[ABCEGHJ-NPRSTV-Z]|2[ABCEGHJ-NPRSTV-Z]|3[ABCEGHJ-NRSTV-Y]|4[ABCEGK-NPRSTVWXZ]|5[ABCEGHJ-NPRSTV-Z]|6[ABCEGHJ-NPRSTV-Z]|7[ABCEGHJ-NPRSTV-Y]|8[ABCGJ-NPRSTV-Z]|9[ABCEGHJ-NPRSTV-Z])|X(0[ABCGX]|1[A])|Y(0[AB]|1[A]))[ ]?[0-9]{1}[ABCEGHJ-NPRSTV-Z]{1}[0-9]{1}$ US ZIP codes ^[0-9]{5}(-[0-9]{4})?$ UK post codes ^([A-PR-UWYZ]([0-9]{1,2}|([A-HK-Y][0-9]|[A-HK-Y][0-9]([0-9]|[ABEHMNPRV-Y]))|[0-9][A-HJKS-UW])\ [0-9][ABD-HJLNP-UW-Z]{2}|(GIR\ 0AA)|(SAN\ TA1)|(BFPO\ (C\/O\ )?[0-9]{1,4})|((ASCN|BBND|[BFS]IQQ|PCRN|STHL|TDCU|TKCA)\ 1ZZ))$
如果不把东西邮寄到某个地址，并让那个人在收到时告诉你，就不可能保证准确性，但我们可以通过排除我们知道是不好的情况来缩小范围。
推荐文章
- 如何从JavaScript中使用正则表达式的字符串中剥离所有标点符号?
- 正则表达式中的单词边界是什么?
- 如何将一个标题转换为jQuery的URL段塞?
- Javascript和regex:分割字符串并保留分隔符
- (grep)正则表达式匹配非ascii字符?
- 如何在保持原始字符串的同时对字符串执行Perl替换?
- 创建正则表达式匹配数组
- *的区别是什么?和。*正则表达式?
- 如何将“camelCase”转换为“Camel Case”?
- 在Java中使用正则表达式提取值
- Java中的正则表达式命名组
- 使用正则表达式搜索和替换Visual Studio代码
- 使用split("|")按管道符号拆分Java字符串
- 替换字符串中第一次出现的模式
- “\d”在正则表达式中是数字吗?
