Start work on a generic link extractor.

At the moment this just implements the first step of the Styliser's
link detection. It doesn't apply any of the "intelligent" corrections.

src/com/dmdirc/util/text/Link.java

@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2006-2014 DMDirc Developers
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+package com.dmdirc.util.text;
+
+import java.util.Objects;
+
+/**
+* Describes a single link found within some text.
+*/
+public class Link {
+
+    private final int start;
+    private final int end;
+    private final String content;
+
+    public Link(final int start, final int end, final String content) {
+        this.start = start;
+        this.end = end;
+        this.content = content;
+    }
+
+    /**
+     * Gets the character offset that the link was found at.
+     *
+     * @return The position the link was found at
+     */
+    public int getStart() {
+        return start;
+    }
+
+    /**
+     * Gets the character offset of the end of the link.
+     *
+     * @return The position immediately after the last character of the link.
+     */
+    public int getEnd() {
+        return end;
+    }
+
+    /**
+     * Gets the content of the link.
+     *
+     * @return The link's content
+     */
+    public String getContent() {
+        return content;
+    }
+
+    @Override
+    public boolean equals(final Object o) {
+        if (this == o) {
+            return true;
+        }
+
+        if (o == null || getClass() != o.getClass()) {
+            return false;
+        }
+
+        final Link link = (Link) o;
+        return end == link.getEnd() && start == link.getStart()
+                && Objects.equals(content, link.getContent());
+    }
+
+    @Override
+    public int hashCode() {
+        return Objects.hash(start, end, content);
+    }
+
+    @Override
+    public String toString() {
+        return "Link{start=" + start + ", end=" + end + ", content='" + content + "'}";
+    }
+}

src/com/dmdirc/util/text/LinkExtractor.java

@@ -0,0 +1,69 @@
+/*
+ * Copyright (c) 2006-2014 DMDirc Developers
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+package com.dmdirc.util.text;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+/**
+ * Finds links within a body of text.
+ */
+public class LinkExtractor {
+
+    /** Defines all characters treated as trailing punctuation that are illegal in URLs. */
+    private static final String URL_PUNCT_ILLEGAL = "\"";
+    /** Defines all characters treated as trailing punctuation that're legal in URLs. */
+    private static final String URL_PUNCT_LEGAL = "';:!,\\.\\?";
+    /** Defines all trailing punctuation. */
+    private static final String URL_PUNCT = URL_PUNCT_ILLEGAL + URL_PUNCT_LEGAL;
+    /** Defines all characters allowed in URLs that aren't treated as trailing punct. */
+    private static final String URL_NOPUNCT = "a-z0-9$\\-_@&\\+\\*\\(\\)=/#%~\\|";
+    /** Defines all characters allowed in URLs per W3C specs. */
+    private static final String URL_CHARS = '[' + URL_PUNCT_LEGAL + URL_NOPUNCT
+            + "]*[" + URL_NOPUNCT + "]+[" + URL_PUNCT_LEGAL + URL_NOPUNCT + "]*";
+    /** The regular expression to use for marking up URLs. */
+    private static final String URL_REGEXP = "(?i)((?>(?<!" + "[a-f0-9]{5})[a-f]|[g-z+])+://" +
+            URL_CHARS + "|(?<![a-z0-9:/])www\\." + URL_CHARS + ')';
+    /** The pattern to use to match URLs. */
+    private static final Pattern URL_PATTERN = Pattern.compile(URL_REGEXP);
+
+    /**
+     * Finds all available links within the given text.
+     *
+     * @param text The text to search for links.
+     * @return A list of found links, ordered according to their position in the text.
+     */
+    public List<Link> findLinks(final CharSequence text) {
+        final List<Link> res = new ArrayList<>();
+        final Matcher matcher = URL_PATTERN.matcher(text);
+
+        while (matcher.find()) {
+            res.add(new Link(matcher.start(), matcher.end(), matcher.group()));
+        }
+
+        return res;
+    }
+
+}

test/com/dmdirc/util/text/LinkExtractorTest.java

@@ -0,0 +1,143 @@
+/*
+ * Copyright (c) 2006-2014 DMDirc Developers
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+package com.dmdirc.util.text;
+
+import java.util.Arrays;
+import java.util.List;
+
+import org.junit.Before;
+import org.junit.Ignore;
+import org.junit.Test;
+
+import static org.junit.Assert.assertEquals;
+
+public class LinkExtractorTest {
+
+    private LinkExtractor extractor;
+
+    @Before
+    public void setup() {
+        extractor = new LinkExtractor();
+    }
+
+    private void testLinks(final CharSequence input, final Link ... expected) {
+        final List<Link> result = extractor.findLinks(input);
+        assertEquals(Arrays.asList(expected), result);
+    }
+
+    @Test
+    public void testEmptyString() {
+        testLinks("");
+    }
+
+    @Test
+    public void testNoLinks() {
+        testLinks("no links here!");
+    }
+
+    @Test
+    public void testPlainWwwLink() {
+        testLinks("www.google.com", new Link(0, 14, "www.google.com"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testPlainWwwLinkInSentence() {
+        testLinks("word www.google.com word", new Link(5, 19, "www.google.com"));
+        testLinks("word www.google.com, word", new Link(5, 19, "www.google.com"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testPlainWwwLinkWithPunctuation() {
+        testLinks("www.google.com.", new Link(0, 14, "www.google.com"));
+        testLinks("www.google.com!", new Link(0, 14, "www.google.com"));
+        testLinks("www.google.com?", new Link(0, 14, "www.google.com"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testPlainWwwLinkWithBrackets() {
+        testLinks("(www.google.com)", new Link(1, 15, "www.google.com"));
+        testLinks("[www.google.com]", new Link(1, 15, "www.google.com"));
+        testLinks("<www.google.com>", new Link(1, 15, "www.google.com"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testPlainWwwLinkWithComplicatedBrackets() {
+        testLinks("(foo: www.google.com)", new Link(6, 21, "www.google.com"));
+        testLinks("[foo: www.google.com]", new Link(6, 21, "www.google.com"));
+        testLinks("<foo: www.google.com>", new Link(6, 21, "www.google.com"));
+
+        testLinks("(foo: 'www.google.com')", new Link(7, 22, "www.google.com"));
+        testLinks("('www.google.com')", new Link(2, 17, "www.google.com"));
+        testLinks("[\"www.google.com\"]", new Link(2, 17, "www.google.com"));
+
+        testLinks("www.example.com/blah(foobar)", new Link(0, 28, "www.example.com/blah(foobar)"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testPlainWwwLinkWithQuotes() {
+        testLinks("\"www.google.com\"", new Link(1, 15, "www.google.com"));
+        testLinks("'www.google.com'", new Link(1, 15, "www.google.com"));
+    }
+
+    @Test
+    public void testPrefixedLinks() {
+        testLinks("http://www.google.com", new Link(0, 21, "http://www.google.com"));
+        testLinks("http://www.google.com:80/test#flub",
+                new Link(0, 34, "http://www.google.com:80/test#flub"));
+
+        testLinks("svn+ssh://foo:bar", new Link(0, 17, "svn+ssh://foo:bar"));
+    }
+
+    @Test
+    @Ignore("Not implemented yet")
+    public void testMultipleLinks() {
+        testLinks("www.foo.com www.bar.com",
+                new Link(0, 11, "www.foo.com"),
+                new Link(12, 23, "www.bar.com"));
+
+        testLinks("(www.foo.com www.bar.com)",
+                new Link(1, 12, "www.foo.com"),
+                new Link(13, 24, "www.bar.com"));
+
+        testLinks("('www.foo.com')->x(\"www.bar.com\")",
+                new Link(2, 13, "www.foo.com"),
+                new Link(20, 31, "www.bar.com"));
+
+        testLinks("\"foo\" www.foo.com \"www.bar.com\"",
+                new Link(6, 17, "www.foo.com"),
+                new Link(19, 30, "www.bar.com"));
+    }
+
+    @Test
+    public void testIncompleteLinks() {
+        testLinks("www...");
+        testLinks("http://...");
+        testLinks("/var/web/www.google.com/blah");
+    }
+
+}