Android/frameworks_base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge "Support for new gTLDs"

Browse Source
This commit is contained in:
Selim Gurun
2014-03-28 23:35:09 +00:00
committed by Android (Google) Code Review
parent c0469c00bf b080c3c54a
commit b4f27c95bc
2 changed files with 33 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
core/java/android/util/Patterns.java
View File

@@ -28,7 +28,12 @@ public class Patterns {
* 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
*
* @deprecated Due to the recent profileration of gTLDs, this API is
* expected to become out-of-date very quickly. Therefore it is now
* deprecated.
*/
@Deprecated
public static final String TOP_LEVEL_DOMAIN_STR =
"((aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
+ "|(biz|b[abdefghijmnorstvwyz])"
@@ -59,7 +64,9 @@ public class Patterns {
/**
* Regular expression pattern to match all IANA top-level domains.
* @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}.
*/
@Deprecated
public static final Pattern TOP_LEVEL_DOMAIN =
Pattern.compile(TOP_LEVEL_DOMAIN_STR);
@@ -68,7 +75,10 @@ public class Patterns {
* 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
*
* @deprecated This API is deprecated. See {@link #TOP_LEVEL_DOMAIN_STR}.
*/
@Deprecated
public static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL =
"(?:"
+ "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
@@ -107,6 +117,24 @@ public class Patterns {
public static final String GOOD_IRI_CHAR =
"a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF";
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]))");
/**
* RFC 1035 Section 2.3.4 limits the labels to a maximum 63 octets.
*/
private static final String IRI
= "[" + GOOD_IRI_CHAR + "]([" + GOOD_IRI_CHAR + "\\-]{0,61}[" + GOOD_IRI_CHAR + "]){0,1}";
private static final String HOST_NAME = IRI + "(?:\\." + IRI + ")+";
public static final Pattern DOMAIN_NAME
= Pattern.compile("(" + HOST_NAME + "|" + IP_ADDRESS + ")");
/**
* Regular expression pattern to match most part of RFC 3987
* Internationalized URLs, aka IRIs. Commonly used Unicode characters are
@@ -116,13 +144,7 @@ public class Patterns {
"((?:(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])))"
+ "(?:" + DOMAIN_NAME + ")"
+ "(?:\\:\\d{1,5})?)" // plus option port number
+ "(\\/(?:(?:[" + GOOD_IRI_CHAR + "\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params
+ "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?"
@@ -130,19 +152,6 @@ public class Patterns {
// input. This is to stop foo.sure from
// matching as foo.su
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]))");
public static final Pattern DOMAIN_NAME
= Pattern.compile(
"(((([" + GOOD_IRI_CHAR + "][" + GOOD_IRI_CHAR + "\\-]*)*[" + GOOD_IRI_CHAR + "]\\.)+"
+ TOP_LEVEL_DOMAIN + ")|"
+ IP_ADDRESS + ")");
public static final Pattern EMAIL_ADDRESS
= Pattern.compile(
"[a-zA-Z0-9\\+\\.\\_\\%\\-\\+]{1,256}" +
@@ -159,7 +168,7 @@ public class Patterns {
* 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