Permalink
Browse files

Alter the domain regex to handle the new hyphenization rules

  • Loading branch information...
1 parent f4814a6 commit e7ff21bfe7f6529ab6bb7b4c7852f7f58d91d8a4 Matt Sanford committed Apr 19, 2010
Binary file not shown.
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
All Classes (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
All Classes (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:41 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Autolink (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Extractor (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Regex (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Uses of Class com.twitter.Autolink (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Uses of Class com.twitter.Extractor (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Uses of Class com.twitter.Regex (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter Class Hierarchy (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Uses of Package com.twitter (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Spaces (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Uses of Class com.twitter.regex.Spaces (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter.regex (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter.regex (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
com.twitter.regex Class Hierarchy (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Uses of Package com.twitter.regex (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Constant Field Values (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Deprecated List (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
View
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
API Help (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
View
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Index (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="./stylesheet.css" TITLE="Style">
View
@@ -2,7 +2,7 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc on Thu Mar 11 09:55:42 PST 2010-->
+<!-- Generated by javadoc on Mon Apr 19 15:24:45 PDT 2010-->
<TITLE>
Twitter Text API
</TITLE>
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:44 PDT 2010 -->
<TITLE>
Overview List (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Overview (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -2,12 +2,12 @@
<!--NewPage-->
<HTML>
<HEAD>
-<!-- Generated by javadoc (build 1.6.0_17) on Thu Mar 11 09:55:42 PST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_17) on Mon Apr 19 15:24:45 PDT 2010 -->
<TITLE>
Class Hierarchy (Twitter Text API)
</TITLE>
-<META NAME="date" CONTENT="2010-03-11">
+<META NAME="date" CONTENT="2010-04-19">
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
@@ -14,7 +14,7 @@
/* URL related hash regex collection */
private static final String URL_VALID_PRECEEDING_CHARS = "(?:[^/\"':!=]|^|\\:)";
- private static final String URL_VALID_DOMAIN = "(?:[^\\p{Punct}\\s]+[\\.-][^\\p{Punct}\\s]+|[^\\p{Punct}\\s])+\\.[a-z]{2,}(?::[0-9]+)?";
+ private static final String URL_VALID_DOMAIN = "(?:[^\\p{Punct}\\s][\\.-](?=[^\\p{Punct}\\s])|[^\\p{Punct}\\s])+\\.[a-z]{2,}(?::[0-9]+)?";
private static final String URL_VALID_URL_PATH_CHARS = "(?:[\\.,]?[a-z0-9!\\*'\\(\\);:=\\+\\$/%#\\[\\]\\-_,~@])";
// Valid end-of-path chracters (so /foo. does not gobble the period).
// 1. Allow ) for Wikipedia URLs.

0 comments on commit e7ff21b

Please sign in to comment.