Stop URLs at " (#21)

Author: robinst

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## Unreleased
+### Changed
+- Stop URLs when encountering an `"`. This is consistent with RFC 3986,
+  and it seems unlikely that a user would have an unescaped `"` in a URL
+  anyway, as browsers escape it when you copy an URL that contains one.
+
 ## [0.8.0] - 2018-01-10
 ### Changed
 - Add `Automatic-Module-Name` manifest entry so that library can be used

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

@@ -62,6 +62,7 @@ public static int findUrlEnd(CharSequence input, int beginIndex) {
                 case '\u001E':
                 case '\u001F':
                 case ' ':
+                case '\"':
                 case '<':
                 case '>':
                 case '\u007F':
@@ -99,9 +100,9 @@ public static int findUrlEnd(CharSequence input, int beginIndex) {
                 case '\u009F':
                     // 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.
+                    // the braces to be balanced.
                 case '\u00A0': // no-break space
                 case '\u2000': // en quad
                 case '\u2001': // em quad
@@ -175,12 +176,6 @@ public static int findUrlEnd(CharSequence input, int beginIndex) {
                         break loop;
                     }
                     break;
-                case '"':
-                    doubleQuote = !doubleQuote;
-                    if (!doubleQuote) {
-                        last = i;
-                    }
-                    break;
                 case '\'':
                     singleQuote = !singleQuote;
                     if (!singleQuote) {

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

@@ -119,7 +119,6 @@ public void matchingPunctuation() {
         assertLinked("http://example.org/a(b)", "|http://example.org/a(b)|");
         assertLinked("http://example.org/a[b]", "|http://example.org/a[b]|");
         assertLinked("http://example.org/a{b}", "|http://example.org/a{b}|");
-        assertLinked("http://example.org/a\"b\"", "|http://example.org/a\"b\"|");
         assertLinked("http://example.org/a'b'", "|http://example.org/a'b'|");
         assertLinked("(http://example.org/)", "(|http://example.org/|)");
         assertLinked("[http://example.org/]", "[|http://example.org/|]");
@@ -145,13 +144,15 @@ public void matchingPunctuationTricky() {
 
     @Test
     public void quotes() {
-        assertLinked("http://example.org/\"_(foo)", "|http://example.org/\"_(foo)|");
-        assertLinked("http://example.org/\"_(foo)\"", "|http://example.org/\"_(foo)\"|");
-        assertLinked("http://example.org/\"\"", "|http://example.org/\"\"|");
-        assertLinked("http://example.org/\"\"\"", "|http://example.org/\"\"|\"");
-        assertLinked("http://example.org/\".", "|http://example.org/|\".");
-        assertLinked("http://example.org/\"a", "|http://example.org/\"a|");
+        assertLinked("http://example.org/\'_(foo)", "|http://example.org/\'_(foo)|");
+        assertLinked("http://example.org/\'_(foo)\'", "|http://example.org/\'_(foo)\'|");
+        assertLinked("http://example.org/\'\'", "|http://example.org/\'\'|");
+        assertLinked("http://example.org/\'\'\'", "|http://example.org/\'\'|\'");
+        assertLinked("http://example.org/\'.", "|http://example.org/|\'.");
         assertLinked("http://example.org/it's", "|http://example.org/it's|");
+        // " not allowed in URLs
+        assertLinked("http://example.org/\"a", "|http://example.org/|\"a");
+        assertLinked("http://example.org/\"a\"", "|http://example.org/|\"a\"");
     }
 
     @Test