Menu
▾
▴
archive-access-cvs
|
From: <bra...@us...> - 2008-09-04 21:35:59
|
Revision: 2590
http://archive-access.svn.sourceforge.net/archive-access/?rev=2590&view=rev
Author: bradtofel
Date: 2008-09-04 21:36:09 +0000 (Thu, 04 Sep 2008)
Log Message:
-----------
BUGFIX(ACC-31): now escapes URLs as they are resolved in UrlOperations.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2008-09-02 23:26:08 UTC (rev 2589)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2008-09-04 21:36:09 UTC (rev 2590)
@@ -83,7 +83,14 @@
public static String resolveUrl(String baseUrl, String url) {
// TODO: this only works for http://
if(url.startsWith("http://")) {
- return url;
+ try {
+ return UURIFactory.getInstance(url).getEscapedURI();
+ } catch (URIException e) {
+ e.printStackTrace();
+ // can't let a space exist... send back close to whatever came
+ // in...
+ return url.replace(" ", "%20");
+ }
}
UURI absBaseURI;
UURI resolvedURI = null;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2009-10-15 22:51:36
|
Revision: 2809
http://archive-access.svn.sourceforge.net/archive-access/?rev=2809&view=rev
Author: bradtofel
Date: 2009-10-15 22:51:23 +0000 (Thu, 15 Oct 2009)
Log Message:
-----------
REFACTOR: moved parsing of path from a URL String here... it should be further refactored into URL, or UURI...
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2009-10-15 22:44:10 UTC (rev 2808)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2009-10-15 22:51:23 UTC (rev 2809)
@@ -22,6 +22,9 @@
public final static String FTP_SCHEME = "ftp://";
public final static String MMS_SCHEME = "mms://";
public final static String RTSP_SCHEME = "rtsp://";
+
+ public final static String DEFAULT_SCHEME = HTTP_SCHEME;
+
// go brewster
public final static String WAIS_SCHEME = "wais://";
@@ -132,6 +135,25 @@
}
return -1;
}
+
+ public static String getURLPath(String url) {
+ int portIdx = url.indexOf(UrlOperations.PORT_SEPARATOR);
+ int pathIdx = url.indexOf(UrlOperations.PATH_START);
+ if(portIdx == -1 && pathIdx == -1) {
+ return "";
+ }
+ if(portIdx == -1) {
+ return url.substring(pathIdx);
+ }
+ if(pathIdx == -1) {
+ return url.substring(portIdx);
+ }
+ if(pathIdx > portIdx) {
+ return url.substring(portIdx);
+ } else {
+ return url.substring(pathIdx);
+ }
+ }
public static String urlToHost(String url) {
if(url.startsWith("dns:")) {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-03-20 01:05:45
|
Revision: 2988
http://archive-access.svn.sourceforge.net/archive-access/?rev=2988&view=rev
Author: bradtofel
Date: 2010-03-20 01:05:39 +0000 (Sat, 20 Mar 2010)
Log Message:
-----------
BUGFIX(unreported): replaced URL to host processing with REGEX, to better handle URLs with freakish illegal characters before the port/path start.
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2010-03-20 01:02:49 UTC (rev 2987)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2010-03-20 01:05:39 UTC (rev 2988)
@@ -92,6 +92,9 @@
Pattern.compile("(([0-9a-z_.-]+)\\.(" + ALL_TLD_PATTERN + "))|" +
"(" + IP_PATTERN + ")");
+ private static final Pattern AUTHORITY_REGEX_SIMPLE =
+ Pattern.compile("([0-9a-z_.-]++)");
+
/**
* @param urlPart
* @return boolean indicating whether urlPart might be an Authority.
@@ -186,22 +189,11 @@
for(String scheme : ALL_SCHEMES) {
if(url.startsWith(scheme)) {
int hostIdx = scheme.length();
- int portIdx = url.indexOf(PORT_SEPARATOR, hostIdx + 1);
- int pathIdx = url.indexOf(PATH_START, hostIdx + 1);
- if(portIdx == -1 && pathIdx == -1) {
- return url.substring(hostIdx);
+
+ Matcher m = AUTHORITY_REGEX_SIMPLE.matcher(url.substring(hostIdx));
+ if(m.find()) {
+ return m.group(0);
}
- if(portIdx == -1) {
- return url.substring(hostIdx,pathIdx);
- }
- if(pathIdx == -1) {
- return url.substring(hostIdx,portIdx);
- }
- if(pathIdx > portIdx) {
- return url.substring(hostIdx,portIdx);
- } else {
- return url.substring(hostIdx,pathIdx);
- }
}
}
return url;
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
|
From: <bra...@us...> - 2010-04-27 20:52:26
|
Revision: 3068
http://archive-access.svn.sourceforge.net/archive-access/?rev=3068&view=rev
Author: bradtofel
Date: 2010-04-27 20:52:20 +0000 (Tue, 27 Apr 2010)
Log Message:
-----------
JAVADOC
Modified Paths:
--------------
trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java
===================================================================
--- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2010-04-27 20:51:27 UTC (rev 3067)
+++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/util/url/UrlOperations.java 2010-04-27 20:52:20 UTC (rev 3068)
@@ -24,8 +24,6 @@
*/
package org.archive.wayback.util.url;
-import java.net.MalformedURLException;
-import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
@@ -45,18 +43,44 @@
private static final Logger LOGGER = Logger.getLogger(
UrlOperations.class.getName());
+ /**
+ * ARC/WARC specific DNS resolution record.
+ */
public final static String DNS_SCHEME = "dns:";
+ /**
+ * HTTP
+ */
public final static String HTTP_SCHEME = "http://";
+ /**
+ * HTTPS
+ */
public final static String HTTPS_SCHEME = "https://";
+ /**
+ * FTP
+ */
public final static String FTP_SCHEME = "ftp://";
+ /**
+ * MMS
+ */
public final static String MMS_SCHEME = "mms://";
+ /**
+ * RTSP
+ */
public final static String RTSP_SCHEME = "rtsp://";
+ /**
+ * Default scheme to assume if unspecified. No context implied...
+ */
public final static String DEFAULT_SCHEME = HTTP_SCHEME;
- // go brewster
+ /**
+ * go brewster
+ */
public final static String WAIS_SCHEME = "wais://";
+ /**
+ * array of static Strings for all "known" schemes
+ */
public final static String ALL_SCHEMES[] = {
HTTP_SCHEME,
HTTPS_SCHEME,
@@ -67,7 +91,14 @@
};
+ /**
+ * character separating host from port within a URL authority
+ */
public final static char PORT_SEPARATOR = ':';
+ /**
+ * character which delimits the path from the authority in a... in some
+ * URLs.
+ */
public final static char PATH_START = '/';
@@ -97,27 +128,35 @@
Pattern.compile("(([0-9a-z_.-]+)\\.(" + ALL_TLD_PATTERN + "))|" +
"(" + IP_PATTERN + ")");
- private static final Pattern AUTHORITY_REGEX_SIMPLE =
- Pattern.compile("([0-9a-z_.-]++)");
+// private static final Pattern AUTHORITY_REGEX_SIMPLE =
+// Pattern.compile("([0-9a-z_.-]++)");
private static final Pattern HOST_REGEX_SIMPLE =
Pattern.compile("(?:[0-9a-z_.:-]+@)?([0-9a-z_.-]++)");
private static final Pattern USERINFO_REGEX_SIMPLE =
Pattern.compile("([0-9a-z_.:-]+)(?:@[0-9a-z_.-]++)");
/**
- * @param urlPart
+ * Tests if the String argument looks like it could be a legitimate
+ * authority fragment of a URL, that is, is it an IP address, or, are the
+ * characters legal in an authority, and does the string end with a legal
+ * TLD.
+ *
+ * @param authString String representation of a fragment of a URL
* @return boolean indicating whether urlPart might be an Authority.
*/
- public static boolean isAuthority(String urlPart) {
- Matcher m = AUTHORITY_REGEX.matcher(urlPart);
+ public static boolean isAuthority(String authString) {
+ Matcher m = AUTHORITY_REGEX.matcher(authString);
return (m != null) && m.matches();
}
/**
- * @param baseUrl
- * @param url
- * @return url resolved against baseUrl, unless it is absolute already
+ * Resolve a possibly relative url argument against a base URL.
+ * @param baseUrl the base URL against which the url should be resolved
+ * @param url the URL, possibly relative, to make absolute.
+ * @return url resolved against baseUrl, unless it is absolute already, and
+ * further transformed by whatever escaping normally takes place with a
+ * UURI.
*/
public static String resolveUrl(String baseUrl, String url) {
for(final String scheme : ALL_SCHEMES) {
@@ -144,6 +183,11 @@
return resolvedURI.getEscapedURI();
}
+ /**
+ * Attempt to find the scheme (http://, https://, etc) from a given URL.
+ * @param url URL String to parse for a scheme.
+ * @return the scheme, including trailing "://" if known, null otherwise.
+ */
public static String urlToScheme(final String url) {
for(final String scheme : ALL_SCHEMES) {
if(url.startsWith(scheme)) {
@@ -153,6 +197,11 @@
return null;
}
+ /**
+ * Return the default port for the scheme String argument, if known.
+ * @param scheme String scheme, including '://', as in, "http://", "ftp://"
+ * @return the default port for the scheme, or -1 if the scheme isn't known.
+ */
public static int schemeToDefaultPort(final String scheme) {
if(scheme.equals(HTTP_SCHEME)) {
return 80;
@@ -172,6 +221,11 @@
return -1;
}
+ /**
+ * Attempt to extract the path component of a url String argument.
+ * @param url the URL which may contain a path, sans scheme.
+ * @return the path component of the URL, or "" if it contains no path.
+ */
public static String getURLPath(String url) {
int portIdx = url.indexOf(UrlOperations.PORT_SEPARATOR);
int pathIdx = url.indexOf(UrlOperations.PATH_START);
@@ -191,6 +245,12 @@
}
}
+ /**
+ * Attempt to extract the hostname component of an absolute URL argument.
+ * @param url the url String from which to extract the hostname
+ * @return the hostname within the URL, or the url argument if the host
+ * cannot be found.
+ */
public static String urlToHost(String url) {
String lcUrl = url.toLowerCase();
if(lcUrl.startsWith("dns:")) {
@@ -210,6 +270,13 @@
return url;
}
+ /**
+ * Extract userinfo from the absolute URL argument, that is, "username@", or
+ * "username:password@" if present.
+ * @param url the URL from which to extract the userinfo
+ * @return the userinfo found, not including the "@", or null if no userinfo
+ * is found
+ */
public static String urlToUserInfo(String url) {
String lcUrl = url.toLowerCase();
if(lcUrl.startsWith("dns:")) {
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X