Android Browser学习十二 传入的Url的处理
Browser会接收和输入很多url, 有时候用户会输入错误这些url, 于是使用了UrlUtil进行了一些字符串造成, 来做即将输入的浏览器的url的字符串进行处理. 这里用来很多的正则表达式
纠正一些http网址的错误:
/**
* 修复一下url的错误
* @param inUrl
* @return
*/
/* package */ static String fixUrl(String inUrl) {
// FIXME: Converting the url to lower case
// duplicates functionality in smartUrlFilter().
// However, changing all current callers of fixUrl to
// call smartUrlFilter in addition may have unwanted
// consequences, and is deferred for now.
int colon = inUrl.indexOf(':');
boolean allLower = true;
for (int index = 0; index < colon; index++) {
char ch = inUrl.charAt(index);
if (!Character.isLetter(ch)) {
break;
}
allLower &= Character.isLowerCase(ch);
if (index == colon - 1 && !allLower) {
inUrl = inUrl.substring(0, colon).toLowerCase()//前缀变小写
+ inUrl.substring(colon);
}
}
if (inUrl.startsWith("http://") || inUrl.startsWith("https://"))
return inUrl;
if (inUrl.startsWith("http:") ||
inUrl.startsWith("https:")) {
if (inUrl.startsWith("http:/") || inUrl.startsWith("https:/")) {
inUrl = inUrl.replaceFirst("/", "//");//纠正http:/baidu这样的错误
} else inUrl = inUrl.replaceFirst(":", "://");//纠正http:baidu这样的错误
}
return inUrl;
}
尝试判断用户在titlebar中输入的是url还是字符串
/**
* Attempts to determine whether user input is a URL or search
* terms. Anything with a space is passed to search if canBeSearch is true.
*
* Converts to lowercase any mistakenly uppercased schema (i.e.,
* "Http://" converts to "http://"
* 尝试判断用户输入的是一个url还是一个关键词搜索
*
* @param canBeSearch If true, will return a search url if it isn't a valid
* URL. If false, invalid URLs will return null
* @return Original or modified URL
*
*/
public static String smartUrlFilter(String url, boolean canBeSearch) {
String inUrl = url.trim();
boolean hasSpace = inUrl.indexOf(' ') != -1;
Matcher matcher = ACCEPTED_URI_SCHEMA.matcher(inUrl);//匹配可以识别的uri的正则
if (matcher.matches()) {
// force scheme to lowercase 网址的前缀http://等强制小写
String scheme = matcher.group(1);
String lcScheme = scheme.toLowerCase();
if (!lcScheme.equals(scheme)) {
inUrl = lcScheme + matcher.group(2);
}
if (hasSpace && Patterns.WEB_URL.matcher(inUrl).matches()) {
inUrl = inUrl.replace(" ", "%20");//处理空格url为 %20
}
return inUrl;
}
if (!hasSpace) {
if (Patterns.WEB_URL.matcher(inUrl).matches()) { //patterns中自带了weburl的正则
return URLUtil.guessUrl(inUrl);//这是webkit提供的猜测 url的方法
}
}
if (canBeSearch) {//看来不是网址了. 开始使用谷歌进行搜索
return URLUtil.composeSearchUrl(inUrl,
QUICKSEARCH_G, QUERY_PLACE_HOLDER);
}
return null;
}
static final Pattern ACCEPTED_URI_SCHEMA = Pattern.compile(//是否是schema前缀
"(?i)" + // switch on case insensitive matching
"(" + // begin group for schema
"(?:http|https|file):\\/\\/" +
"|(?:inline|data|about|javascript):" +
")" +
"(.*)" );
/**
* Regular expression pattern to match most part of RFC 3987
* Internationalized URLs, aka IRIs. Commonly used Unicode characters are
* added.是否是网址的正则
*/
public static final Pattern WEB_URL = Pattern.compile(
"((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)"
+ "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_"
+ "\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?"
+ "((?:(?:[" + GOOD_IRI_CHAR + "][" + GOOD_IRI_CHAR + "\\-]{0,64}\\.)+" // named host
+ TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL
+ "|(?:(?:25[0-5]|2[0-4]" // or ip address
+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]"
+ "|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]"
+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"
+ "|[1-9][0-9]|[0-9])))"
+ "(?:\\:\\d{1,5})?)" // plus option port number
+ "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params
+ "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?"
+ "(?:\\b|$)"); // and finally, a word boundary or end of
// input. This is to stop foo.sure from
// matching as foo.su
其拼接关键词比较有意思, 为什么不用String.format呢??
public static String composeSearchUrl(String inQuery, String template,
String queryPlaceHolder) {
int placeHolderIndex = template.indexOf(queryPlaceHolder);
if (placeHolderIndex < 0) {
return null;
}
String query;
StringBuilder buffer = new StringBuilder();
buffer.append(template.substring(0, placeHolderIndex));
try {
query = java.net.URLEncoder.encode(inQuery, "utf-8");
buffer.append(query);
} catch (UnsupportedEncodingException ex) {
return null;
}
buffer.append(template.substring(
placeHolderIndex + queryPlaceHolder.length()));//防止 %s在 中间出现的情况
return buffer.toString();
}
去除http://
/**
* 去除 url中的http://等等
* @param url
* @return
*/
public static String stripUrl(String url) {
if (url == null) return null;
Matcher m = STRIP_URL_PATTERN.matcher(url);
if (m.matches()) {
return m.group(1); //group0 就是那个匹配的http://
} else {
return url;
}
}
// Regular expression to strip http:// and optionally
// the trailing slash
private static final Pattern STRIP_URL_PATTERN =
Pattern.compile("^http://(.*?)/?$");
Android自带了很多正则的匹配, 我们不需要自己去找
/**
* Commonly used regular expression patterns.
*/
public class Patterns {
/**
* Regular expression to match all IANA top-level domains.
* List accurate as of 2011/07/18. List taken from:
* http://data.iana.org/TLD/tlds-alpha-by-domain.txt
* This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py
*/顶级域名
public static final String TOP_LEVEL_DOMAIN_STR =
"((aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
+ "|(biz|b[abdefghijmnorstvwyz])"
+ "|(cat|com|coop|c[acdfghiklmnoruvxyz])"
+ "|d[ejkmoz]"
+ "|(edu|e[cegrstu])"
+ "|f[ijkmor]"
+ "|(gov|g[abdefghilmnpqrstuwy])"
+ "|h[kmnrtu]"
+ "|(info|int|i[delmnoqrst])"
+ "|(jobs|j[emop])"
+ "|k[eghimnprwyz]"
+ "|l[abcikrstuvy]"
+ "|(mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])"
+ "|(name|net|n[acefgilopruz])"
+ "|(org|om)"
+ "|(pro|p[aefghklmnrstwy])"
+ "|qa"
+ "|r[eosuw]"
+ "|s[abcdeghijklmnortuvyz]"
+ "|(tel|travel|t[cdfghjklmnoprtvwz])"
+ "|u[agksyz]"
+ "|v[aceginu]"
+ "|w[fs]"
+ "|(\u03b4\u03bf\u03ba\u03b9\u03bc\u03ae|\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435|\u0440\u0444|\u0441\u0440\u0431|\u05d8\u05e2\u05e1\u05d8|\u0622\u0632\u0645\u0627\u06cc\u0634\u06cc|\u0625\u062e\u062a\u0628\u0627\u0631|\u0627\u0644\u0627\u0631\u062f\u0646|\u0627\u0644\u062c\u0632\u0627\u0626\u0631|\u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629|\u0627\u0644\u0645\u063a\u0631\u0628|\u0627\u0645\u0627\u0631\u0627\u062a|\u0628\u06be\u0627\u0631\u062a|\u062a\u0648\u0646\u0633|\u0633\u0648\u0631\u064a\u0629|\u0641\u0644\u0633\u0637\u064a\u0646|\u0642\u0637\u0631|\u0645\u0635\u0631|\u092a\u0930\u0940\u0915\u094d\u0937\u093e|\u092d\u093e\u0930\u0924|\u09ad\u09be\u09b0\u09a4|\u0a2d\u0a3e\u0a30\u0a24|\u0aad\u0abe\u0ab0\u0aa4|\u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0bbe|\u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8|\u0b9a\u0bbf\u0b99\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0bc2\u0bb0\u0bcd|\u0baa\u0bb0\u0bbf\u0b9f\u0bcd\u0b9a\u0bc8|\u0c2d\u0c3e\u0c30\u0c24\u0c4d|\u0dbd\u0d82\u0d9a\u0dcf|\u0e44\u0e17\u0e22|\u30c6\u30b9\u30c8|\u4e2d\u56fd|\u4e2d\u570b|\u53f0\u6e7e|\u53f0\u7063|\u65b0\u52a0\u5761|\u6d4b\u8bd5|\u6e2c\u8a66|\u9999\u6e2f|\ud14c\uc2a4\ud2b8|\ud55c\uad6d|xn\\-\\-0zwm56d|xn\\-\\-11b5bs3a9aj6g|xn\\-\\-3e0b707e|xn\\-\\-45brj9c|xn\\-\\-80akhbyknj4f|xn\\-\\-90a3ac|xn\\-\\-9t4b11yi5a|xn\\-\\-clchc0ea0b2g2a9gcd|xn\\-\\-deba0ad|xn\\-\\-fiqs8s|xn\\-\\-fiqz9s|xn\\-\\-fpcrj9c3d|xn\\-\\-fzc2c9e2c|xn\\-\\-g6w251d|xn\\-\\-gecrj9c|xn\\-\\-h2brj9c|xn\\-\\-hgbk6aj7f53bba|xn\\-\\-hlcj6aya9esc7a|xn\\-\\-j6w193g|xn\\-\\-jxalpdlp|xn\\-\\-kgbechtv|xn\\-\\-kprw13d|xn\\-\\-kpry57d|xn\\-\\-lgbbat1ad8j|xn\\-\\-mgbaam7a8h|xn\\-\\-mgbayh7gpa|xn\\-\\-mgbbh1a71e|xn\\-\\-mgbc0a9azcg|xn\\-\\-mgberp4a5d4ar|xn\\-\\-o3cw4h|xn\\-\\-ogbpf8fl|xn\\-\\-p1ai|xn\\-\\-pgbs0dh|xn\\-\\-s9brj9c|xn\\-\\-wgbh1c|xn\\-\\-wgbl6a|xn\\-\\-xkc2al3hye2a|xn\\-\\-xkc2dl3a5ee0h|xn\\-\\-yfro4i67o|xn\\-\\-ygbi2ammx|xn\\-\\-zckzah|xxx)"
+ "|y[et]"
+ "|z[amw])";
/**
* Regular expression pattern to match all IANA top-level domains.
*/
public static final Pattern TOP_LEVEL_DOMAIN =
Pattern.compile(TOP_LEVEL_DOMAIN_STR);
/**
* Regular expression to match all IANA top-level domains for WEB_URL.
* List accurate as of 2011/07/18. List taken from:
* http://data.iana.org/TLD/tlds-alpha-by-domain.txt
* This pattern is auto-generated by frameworks/ex/common/tools/make-iana-tld-pattern.py
*/
public static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL =
"(?:"
+ "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
+ "|(?:biz|b[abdefghijmnorstvwyz])"
+ "|(?:cat|com|coop|c[acdfghiklmnoruvxyz])"
+ "|d[ejkmoz]"
+ "|(?:edu|e[cegrstu])"
+ "|f[ijkmor]"
+ "|(?:gov|g[abdefghilmnpqrstuwy])"
+ "|h[kmnrtu]"
+ "|(?:info|int|i[delmnoqrst])"
+ "|(?:jobs|j[emop])"
+ "|k[eghimnprwyz]"
+ "|l[abcikrstuvy]"
+ "|(?:mil|mobi|museum|m[acdeghklmnopqrstuvwxyz])"
+ "|(?:name|net|n[acefgilopruz])"
+ "|(?:org|om)"
+ "|(?:pro|p[aefghklmnrstwy])"
+ "|qa"
+ "|r[eosuw]"
+ "|s[abcdeghijklmnortuvyz]"
+ "|(?:tel|travel|t[cdfghjklmnoprtvwz])"
+ "|u[agksyz]"
+ "|v[aceginu]"
+ "|w[fs]"
+ "|(?:\u03b4\u03bf\u03ba\u03b9\u03bc\u03ae|\u0438\u0441\u043f\u044b\u0442\u0430\u043d\u0438\u0435|\u0440\u0444|\u0441\u0440\u0431|\u05d8\u05e2\u05e1\u05d8|\u0622\u0632\u0645\u0627\u06cc\u0634\u06cc|\u0625\u062e\u062a\u0628\u0627\u0631|\u0627\u0644\u0627\u0631\u062f\u0646|\u0627\u0644\u062c\u0632\u0627\u0626\u0631|\u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629|\u0627\u0644\u0645\u063a\u0631\u0628|\u0627\u0645\u0627\u0631\u0627\u062a|\u0628\u06be\u0627\u0631\u062a|\u062a\u0648\u0646\u0633|\u0633\u0648\u0631\u064a\u0629|\u0641\u0644\u0633\u0637\u064a\u0646|\u0642\u0637\u0631|\u0645\u0635\u0631|\u092a\u0930\u0940\u0915\u094d\u0937\u093e|\u092d\u093e\u0930\u0924|\u09ad\u09be\u09b0\u09a4|\u0a2d\u0a3e\u0a30\u0a24|\u0aad\u0abe\u0ab0\u0aa4|\u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0bbe|\u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8|\u0b9a\u0bbf\u0b99\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0bc2\u0bb0\u0bcd|\u0baa\u0bb0\u0bbf\u0b9f\u0bcd\u0b9a\u0bc8|\u0c2d\u0c3e\u0c30\u0c24\u0c4d|\u0dbd\u0d82\u0d9a\u0dcf|\u0e44\u0e17\u0e22|\u30c6\u30b9\u30c8|\u4e2d\u56fd|\u4e2d\u570b|\u53f0\u6e7e|\u53f0\u7063|\u65b0\u52a0\u5761|\u6d4b\u8bd5|\u6e2c\u8a66|\u9999\u6e2f|\ud14c\uc2a4\ud2b8|\ud55c\uad6d|xn\\-\\-0zwm56d|xn\\-\\-11b5bs3a9aj6g|xn\\-\\-3e0b707e|xn\\-\\-45brj9c|xn\\-\\-80akhbyknj4f|xn\\-\\-90a3ac|xn\\-\\-9t4b11yi5a|xn\\-\\-clchc0ea0b2g2a9gcd|xn\\-\\-deba0ad|xn\\-\\-fiqs8s|xn\\-\\-fiqz9s|xn\\-\\-fpcrj9c3d|xn\\-\\-fzc2c9e2c|xn\\-\\-g6w251d|xn\\-\\-gecrj9c|xn\\-\\-h2brj9c|xn\\-\\-hgbk6aj7f53bba|xn\\-\\-hlcj6aya9esc7a|xn\\-\\-j6w193g|xn\\-\\-jxalpdlp|xn\\-\\-kgbechtv|xn\\-\\-kprw13d|xn\\-\\-kpry57d|xn\\-\\-lgbbat1ad8j|xn\\-\\-mgbaam7a8h|xn\\-\\-mgbayh7gpa|xn\\-\\-mgbbh1a71e|xn\\-\\-mgbc0a9azcg|xn\\-\\-mgberp4a5d4ar|xn\\-\\-o3cw4h|xn\\-\\-ogbpf8fl|xn\\-\\-p1ai|xn\\-\\-pgbs0dh|xn\\-\\-s9brj9c|xn\\-\\-wgbh1c|xn\\-\\-wgbl6a|xn\\-\\-xkc2al3hye2a|xn\\-\\-xkc2dl3a5ee0h|xn\\-\\-yfro4i67o|xn\\-\\-ygbi2ammx|xn\\-\\-zckzah|xxx)"
+ "|y[et]"
+ "|z[amw]))";
/**
* Good characters for Internationalized Resource Identifiers (IRI).
* This comprises most common used Unicode characters allowed in IRI
* as detailed in RFC 3987.
* Specifically, those two byte Unicode characters are not included.
*/
public static final String GOOD_IRI_CHAR =
"a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF";
/**
* Regular expression pattern to match most part of RFC 3987
* Internationalized URLs, aka IRIs. Commonly used Unicode characters are
* added. 网址 web url 正则
*/
public static final Pattern WEB_URL = Pattern.compile(
"((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)"
+ "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_"
+ "\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?"
+ "((?:(?:[" + GOOD_IRI_CHAR + "][" + GOOD_IRI_CHAR + "\\-]{0,64}\\.)+" // named host
+ TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL
+ "|(?:(?:25[0-5]|2[0-4]" // or ip address
+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]"
+ "|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]"
+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"
+ "|[1-9][0-9]|[0-9])))"
+ "(?:\\:\\d{1,5})?)" // plus option port number
+ "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params
+ "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?"
+ "(?:\\b|$)"); // and finally, a word boundary or end of
// input. This is to stop foo.sure from
// matching as foo.su
//IP地址
public static final Pattern IP_ADDRESS
= Pattern.compile(
"((25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(25[0-5]|2[0-4]"
+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1]"
+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"
+ "|[1-9][0-9]|[0-9]))");
//域名
public static final Pattern DOMAIN_NAME
= Pattern.compile(
"(((([" + GOOD_IRI_CHAR + "][" + GOOD_IRI_CHAR + "\\-]*)*[" + GOOD_IRI_CHAR + "]\\.)+"
+ TOP_LEVEL_DOMAIN + ")|"
+ IP_ADDRESS + ")");
//邮件
public static final Pattern EMAIL_ADDRESS
= Pattern.compile(
"[a-zA-Z0-9\\+\\.\\_\\%\\-\\+]{1,256}" +
"\\@" +
"[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}" +
"(" +
"\\." +
"[a-zA-Z0-9][a-zA-Z0-9\\-]{0,25}" +
")+"
);
/**
* This pattern is intended for searching for things that look like they
* might be phone numbers in arbitrary text, not for validating whether
* something is in fact a phone number. It will miss many things that
* are legitimate phone numbers.
*
* <p> The pattern matches the following:
* <ul>
* <li>Optionally, a + sign followed immediately by one or more digits. Spaces, dots, or dashes
* may follow.
* <li>Optionally, sets of digits in parentheses, separated by spaces, dots, or dashes.
* <li>A string starting and ending with a digit, containing digits, spaces, dots, and/or dashes.
* </ul>
*/电话
public static final Pattern PHONE
= Pattern.compile( // sdd = space, dot, or dash
"(\\+[0-9]+[\\- \\.]*)?" // +<digits><sdd>*
+ "(\\([0-9]+\\)[\\- \\.]*)?" // (<digits>)<sdd>*
+ "([0-9][0-9\\- \\.][0-9\\- \\.]+[0-9])"); // <digit><digit|sdd>+<digit>
/**
* Convenience method to take all of the non-null matching groups in a
* regex Matcher and return them as a concatenated string.
*
* @param matcher The Matcher object from which grouped text will
* be extracted
*
* @return A String comprising all of the non-null matched
* groups concatenated together
*/去除指定字符
public static final String concatGroups(Matcher matcher) {
StringBuilder b = new StringBuilder();
final int numGroups = matcher.groupCount();
for (int i = 1; i <= numGroups; i++) {
String s = matcher.group(i);
System.err.println("Group(" + i + ") : " + s);
if (s != null) {
b.append(s);
}
}
return b.toString();
}
/** 保留 数字和 加号
* Convenience method to return only the digits and plus signs
* in the matching string.
*
* @param matcher The Matcher object from which digits and plus will
* be extracted
*
* @return A String comprising all of the digits and plus in
* the match
*/
public static final String digitsAndPlusOnly(Matcher matcher) {
StringBuilder buffer = new StringBuilder();
String matchingRegion = matcher.group();
for (int i = 0, size = matchingRegion.length(); i < size; i++) {
char character = matchingRegion.charAt(i);
if (character == '+' || Character.isDigit(character)) {
buffer.append(character);
}
}
return buffer.toString();
}
/**
* Do not create this static utility class.
*/
private Patterns() {}
}