Exclude more Unicode whitespace characters (#14)

Author: robinst

CHANGELOG.md

@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 ### Changed
 - Don't autolink if authority is only "end" characters, e.g. like `http://.` or
   `http://"` (#15)
+- Stop URLs at Unicode whitespace characters such as U+00A0 NO-BREAK SPACE,
+  thanks @otopba!
 
 ## [0.6.0] - 2016-11-07
 ### Added

src/main/java/org/nibor/autolink/internal/Scanners.java

@@ -97,12 +97,31 @@ public static int findUrlEnd(CharSequence input, int beginIndex) {
                 case '\u009D':
                 case '\u009E':
                 case '\u009F':
-                case '\u00A0': //non-breaking space
-                    // These can never be part of an URL, so stop now. See RFC 3986 and RFC 3987.
+                    // The above can never be part of an URL, so stop now. See RFC 3986 and RFC 3987.
                     // Some characters are not in the above list, even they are not in "unreserved" or "reserved":
                     //   '"', '\\', '^', '`', '{', '|', '}'
                     // The reason for this is that other link detectors also allow them. Also see below, we require
                     // the quote and the braces to be balanced.
+                case '\u00A0': // no-break space
+                case '\u2000': // en quad
+                case '\u2001': // em quad
+                case '\u2002': // en space
+                case '\u2003': // em space
+                case '\u2004': // three-per-em space
+                case '\u2005': // four-per-em space
+                case '\u2006': // six-per-em space
+                case '\u2007': // figure space
+                case '\u2008': // punctuation space
+                case '\u2009': // thin space
+                case '\u200A': // hair space
+                case '\u2028': // line separator
+                case '\u2029': // paragraph separator
+                case '\u202F': // narrow no-break space
+                case '\u205F': // medium mathematical space
+                case '\u3000': // ideographic space
+                    // While these are allowed by RFC 3987, they are Unicode whitespace characters
+                    // that look like a space, so it would be confusing not to end URLs.
+                    // They are also excluded from IDNs by some browsers.
                     break loop;
                 case '?':
                 case '!':

src/test/java/org/nibor/autolink/AutolinkUrlTest.java

@@ -190,6 +190,33 @@ public void international() {
         assertLinked("http://example.org/\u00A2", "|http://example.org/\u00A2|");
     }
 
+    @Test
+    public void unicodeWhitespace() {
+        char[] whitespace = new char[] {
+            '\u00A0', // no-break space
+            '\u2000', // en quad
+            '\u2001', // em quad
+            '\u2002', // en space
+            '\u2003', // em space
+            '\u2004', // three-per-em space
+            '\u2005', // four-per-em space
+            '\u2006', // six-per-em space
+            '\u2007', // figure space
+            '\u2008', // punctuation space
+            '\u2009', // thin space
+            '\u200A', // hair space
+            '\u2028', // line separator
+            '\u2029', // paragraph separator
+            '\u202F', // narrow no-break space
+            '\u205F', // medium mathematical space
+            '\u3000', // ideographic space
+        };
+
+        for (char c : whitespace) {
+            assertLinked("http://example.org" + c, "|http://example.org|" + c);
+        }
+    }
+
     @Test
     public void replyLevel() {
         assertLinked(">http://example.org/", ">|http://example.org/|");