Archives/Athou_commafeed
1
0
Fork 1
mirror of https://github.com/Athou/commafeed.git synced 2026-03-21 21:37:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

commons-lang upgrade to v3

Browse Source
This commit is contained in:
Athou
2014-10-28 16:36:09 +01:00
parent 3cccf741d6
commit 24bd1121af
34 changed files with 69 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/main/java/edu/uci/ics/crawler4j/url/URLCanonicalizer.java
View File

@@ -28,11 +28,11 @@ import java.util.Map;
import java.util.SortedMap;
import java.util.TreeMap;
import org.apache.commons.lang.StringUtils;
import org.apache.commons.lang3.StringUtils;
/**
* See http://en.wikipedia.org/wiki/URL_normalization for a reference Note: some
* parts of the code are adapted from: http://stackoverflow.com/a/4057470/405418
* See http://en.wikipedia.org/wiki/URL_normalization for a reference Note: some parts of the code are adapted from:
* http://stackoverflow.com/a/4057470/405418
*
* @author Yasser Ganjisaffar <lastname at gmail dot com>
*/
@@ -46,7 +46,7 @@ public class URLCanonicalizer {
try {
URL canonicalURL = new URL(UrlResolver.resolveUrl(context == null ? "" : context, href));
String host = canonicalURL.getHost().toLowerCase();
if (StringUtils.isBlank(host)) {
// This is an invalid Url.
@@ -113,7 +113,7 @@ public class URLCanonicalizer {
URL result = new URL(protocol, host, port, pathAndQueryString);
return result.toExternalForm();
} catch (MalformedURLException ex) {
return null;
} catch (URISyntaxException ex) {
@@ -122,8 +122,7 @@ public class URLCanonicalizer {
}
/**
* Takes a query string, separates the constituent name-value pairs, and
* stores them in a SortedMap ordered by lexicographical order.
* Takes a query string, separates the constituent name-value pairs, and stores them in a SortedMap ordered by lexicographical order.
*
* @return Null if there is no query string.
*/
@@ -149,7 +148,7 @@ public class URLCanonicalizer {
params.put(tokens[0], "");
}
break;
case 2:
case 2:
params.put(tokens[0], tokens[1]);
break;
}
@@ -188,8 +187,7 @@ public class URLCanonicalizer {
}
/**
* Percent-encode values according the RFC 3986. The built-in Java
* URLEncoder does not encode according to the RFC, so we make the extra
* Percent-encode values according the RFC 3986. The built-in Java URLEncoder does not encode according to the RFC, so we make the extra
* replacements.
*
* @param string