boxtec
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server
4
1
Fork 0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '3ee9a26ef2'
${ noResults }
yacy_search_server/source/de/anomic/net/URL.java

610 lines
25 KiB
Raw Blame History

// URL.java
// (C) 2006 by Michael Peter Christen; mc@anomic.de, Frankfurt a. M., Germany
// first published 13.07.2006 on http://www.anomic.de
//
// $LastChangedDate: 2006-04-02 22:40:07 +0200 (So, 02 Apr 2006) $
// $LastChangedRevision: 1986 $
// $LastChangedBy: orbiter $
//
// LICENSE
//
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation; either version 2 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
package de.anomic.net;
// this class exsist to provide a system-wide normal form representation of urls,
// and to prevent that java.net.URL usage causes DNS queries which are used in java.net.
import java.io.File;
import java.net.MalformedURLException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class URL {
private String protocol, host, userInfo, path, quest, ref;
private int port;
public URL(String url) throws MalformedURLException {
if (url == null) throw new MalformedURLException("url string is null");
parseURLString(url);
}
public void parseURLString(String url) throws MalformedURLException {
// identify protocol
assert (url != null);
url = url.trim();
int p = url.indexOf(':');
if (p < 0) throw new MalformedURLException("protocol is not given in '" + url + "'");
this.protocol = url.substring(0, p).toLowerCase().trim();
if (url.length() < p + 4) throw new MalformedURLException("URL not parseable: '" + url + "'");
if (url.substring(p + 1, p + 3).equals("//")) {
// identify host, userInfo and file for http and ftp protocol
int q = url.indexOf('/', p + 3);
int r;
if (q < 0) {
if ((r = url.indexOf('@', p + 3)) < 0) {
host = url.substring(p + 3);
userInfo = null;
} else {
host = url.substring(r + 1);
userInfo = url.substring(p + 3, r);
}
path = "/";
} else {
host = url.substring(p + 3, q);
if ((r = host.indexOf('@')) < 0) {
userInfo = null;
} else {
userInfo = host.substring(0, r);
host = host.substring(r + 1);
}
path = url.substring(q);
}
path = resolveBackpath(path);
identPort(url, (protocol.equals("http") ? 80 : ((protocol.equals("https")) ? 443 : ((protocol.equals("ftp")) ? 21 : -1))));
identRef();
identQuest();
escape();
} else {
// this is not a http or ftp url
if (protocol.equals("mailto")) {
// parse email url
int q = url.indexOf('@', p + 3);
if (q < 0) {
throw new MalformedURLException("wrong email address: " + url);
} else {
userInfo = url.substring(p + 1, q);
host = url.substring(q + 1);
path = null;
port = -1;
quest = null;
ref = null;
}
} else {
throw new MalformedURLException("unknown protocol: " + url);
}
}
}
public URL(File file) throws MalformedURLException {
this("file", "", -1, file.getAbsolutePath());
}
public static URL newURL(String baseURL, String relPath) throws MalformedURLException {
if ((baseURL == null) ||
(relPath.startsWith("http://")) ||
(relPath.startsWith("https://")) ||
(relPath.startsWith("ftp://")) ||
(relPath.startsWith("file://")) ||
(relPath.startsWith("smb://"))) {
return new URL(relPath);
} else {
return new URL(new URL(baseURL), relPath);
}
}
public static URL newURL(URL baseURL, String relPath) throws MalformedURLException {
if ((baseURL == null) ||
(relPath.startsWith("http://")) ||
(relPath.startsWith("https://")) ||
(relPath.startsWith("ftp://")) ||
(relPath.startsWith("file://")) ||
(relPath.startsWith("smb://"))) {
return new URL(relPath);
} else {
return new URL(baseURL, relPath);
}
}
private URL(URL baseURL, String relPath) throws MalformedURLException {
if (baseURL == null) throw new MalformedURLException("base URL is null");
if (relPath == null) throw new MalformedURLException("relPath is null");
this.protocol = baseURL.protocol;
this.host = baseURL.host;
this.port = baseURL.port;
this.userInfo = baseURL.userInfo;
if (relPath.toLowerCase().startsWith("javascript:")) {
this.path = baseURL.path;
} else if (
(relPath.startsWith("http://")) ||
(relPath.startsWith("https://")) ||
(relPath.startsWith("ftp://")) ||
(relPath.startsWith("file://")) ||
(relPath.startsWith("smb://"))) {
this.path = baseURL.path;
} else if (relPath.startsWith("/")) {
this.path = relPath;
} else if (baseURL.path.endsWith("/")) {
if (relPath.startsWith("#") || relPath.startsWith("?")) {
throw new MalformedURLException("relative path malformed: " + relPath);
} else {
this.path = baseURL.path + relPath;
}
} else {
if (relPath.startsWith("#") || relPath.startsWith("?")) {
this.path = baseURL.path + relPath;
} else {
int q = baseURL.path.lastIndexOf('/');
if (q < 0) {
this.path = relPath;
} else {
this.path = baseURL.path.substring(0, q + 1) + relPath;
}
}
}
this.quest = baseURL.quest;
this.ref = baseURL.ref;
path = resolveBackpath(path);
identRef();
identQuest();
escape();
}
public URL(String protocol, String host, int port, String path) throws MalformedURLException {
if (protocol == null) throw new MalformedURLException("protocol is null");
this.protocol = protocol;
this.host = host;
this.port = port;
this.path = path;
identRef();
identQuest();
escape();
}
// resolve '..'
String resolveBackpath(String path) /* throws MalformedURLException */ {
/* original version by [MC]
int p;
while ((p = path.indexOf("/..")) >= 0) {
String head = path.substring(0, p);
int q = head.lastIndexOf('/');
if (q < 0) throw new MalformedURLException("backpath cannot be resolved in path = " + path);
path = head.substring(0, q) + path.substring(p + 3);
}*/
/* by [MT] */
if (path.length() == 0 || path.charAt(0) != '/') { path = "/" + path; }
Pattern pathPattern = Pattern.compile("(/[^/]+(?<!/\\.{1,2})/)[.]{2}(?=/|$)|/\\.(?=/)|/(?=/)");
Matcher matcher = pathPattern.matcher(path);
while (matcher.find()) {
path = matcher.replaceAll("");
matcher.reset(path);
}
return path.equals("")?"/":path;
}
/**
* Escapes the following parts of the url, this object already contains:
* <ul>
* <li>path: see {@link #escape(String)}</li>
* <li>ref: same as above</li>
* <li>quest: same as above without the ampersand ("&amp;") and the equals symbol</li>
* </ul>
*/
private void escape() {
if (path != null && path.indexOf('%') == -1) escapePath();
if (quest != null && quest.indexOf('%') == -1) escapeQuest();
if (ref != null && ref.indexOf('%') == -1) escapeRef();
}
private void escapePath() {
String[] pathp = path.split("/", -1);
String ptmp = "";
for (int i = 0; i < pathp.length; i++) {
ptmp += "/" + escape(pathp[i]);
}
path = ptmp.substring((ptmp.length() > 0) ? 1 : 0);
}
private void escapeRef() {
ref = escape(ref);
}
private void escapeQuest() {
String[] questp = quest.split("&", -1);
String qtmp = "";
for (int i = 0; i < questp.length; i++) {
if (questp[i].indexOf('=') != -1) {
qtmp += "&" + escape(questp[i].substring(0, questp[i].indexOf('=')));
qtmp += "=" + escape(questp[i].substring(questp[i].indexOf('=') + 1));
} else {
qtmp += "&" + escape(questp[i]);
}
}
quest = qtmp.substring((qtmp.length() > 0) ? 1 : 0);
}
private final static String[] hex = {
"%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
"%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F",
"%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17",
"%18", "%19", "%1A", "%1B", "%1C", "%1D", "%1E", "%1F",
"%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
"%28", "%29", "%2A", "%2B", "%2C", "%2D", "%2E", "%2F",
"%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37",
"%38", "%39", "%3A", "%3B", "%3C", "%3D", "%3E", "%3F",
"%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47",
"%48", "%49", "%4A", "%4B", "%4C", "%4D", "%4E", "%4F",
"%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57",
"%58", "%59", "%5A", "%5B", "%5C", "%5D", "%5E", "%5F",
"%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67",
"%68", "%69", "%6A", "%6B", "%6C", "%6D", "%6E", "%6F",
"%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77",
"%78", "%79", "%7A", "%7B", "%7C", "%7D", "%7E", "%7F",
"%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87",
"%88", "%89", "%8A", "%8B", "%8C", "%8D", "%8E", "%8F",
"%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97",
"%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
"%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7",
"%A8", "%A9", "%AA", "%AB", "%AC", "%AD", "%AE", "%AF",
"%B0", "%B1", "%B2", "%B3", "%B4", "%B5", "%B6", "%B7",
"%B8", "%B9", "%BA", "%BB", "%BC", "%BD", "%BE", "%BF",
"%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
"%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF",
"%D0", "%D1", "%D2", "%D3", "%D4", "%D5", "%D6", "%D7",
"%D8", "%D9", "%DA", "%DB", "%DC", "%DD", "%DE", "%DF",
"%E0", "%E1", "%E2", "%E3", "%E4", "%E5", "%E6", "%E7",
"%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
"%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7",
"%F8", "%F9", "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
};
/**
* Encode a string to the "x-www-form-urlencoded" form, enhanced
* with the UTF-8-in-URL proposal. This is what happens:
*
* <ul>
* <li>The ASCII characters 'a' through 'z', 'A' through 'Z',
* and '0' through '9' remain the same.
*
* <li>The unreserved characters - _ . ! ~ * ' ( ) remain the same.
*
* <li>All other ASCII characters are converted into the
* 3-character string "%xy", where xy is
* the two-digit hexadecimal representation of the character
* code
*
* <li>All non-ASCII characters are encoded in two steps: first
* to a sequence of 2 or 3 bytes, using the UTF-8 algorithm;
* secondly each of these bytes is encoded as "%xx".
* </ul>
*
* @param s The string to be encoded
* @return The encoded string
*/
// from: http://www.w3.org/International/URLUTF8Encoder.java
public static String escape(String s)
{
StringBuffer sbuf = new StringBuffer();
int len = s.length();
for (int i = 0; i < len; i++) {
int ch = s.charAt(i);
if ('A' <= ch && ch <= 'Z') { // 'A'..'Z'
sbuf.append((char)ch);
} else if ('a' <= ch && ch <= 'z') { // 'a'..'z'
sbuf.append((char)ch);
} else if ('0' <= ch && ch <= '9') { // '0'..'9'
sbuf.append((char)ch);
} else if (ch == ' ') { // space
sbuf.append("%20");
} else if (ch == '&' || ch == ':' // unreserved
|| ch == '-' || ch == '_'
|| ch == '.' || ch == '!'
|| ch == '~' || ch == '*'
|| ch == '\'' || ch == '('
|| ch == ')' || ch == ';') {
sbuf.append((char)ch);
} else if (ch <= 0x007f) { // other ASCII
sbuf.append(hex[ch]);
} else if (ch <= 0x07FF) { // non-ASCII <= 0x7FF
sbuf.append(hex[0xc0 | (ch >> 6)]);
sbuf.append(hex[0x80 | (ch & 0x3F)]);
} else { // 0x7FF < ch <= 0xFFFF
sbuf.append(hex[0xe0 | (ch >> 12)]);
sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]);
sbuf.append(hex[0x80 | (ch & 0x3F)]);
}
}
return sbuf.toString();
}
// from: http://www.w3.org/International/unescape.java
public static String unescape(String s) {
StringBuffer sbuf = new StringBuffer();
int l = s.length();
int ch = -1;
int b, sumb = 0;
for (int i = 0, more = -1; i < l; i++) {
/* Get next byte b from URL segment s */
switch (ch = s.charAt(i)) {
case '%':
ch = s.charAt(++i) ;
int hb = (Character.isDigit ((char) ch) ? ch - '0' : 10 + Character.toLowerCase((char) ch) - 'a') & 0xF;
ch = s.charAt(++i) ;
int lb = (Character.isDigit ((char) ch) ? ch - '0' : 10 + Character.toLowerCase ((char) ch) - 'a') & 0xF;
b = (hb << 4) | lb;
break;
case '+':
b = ' ';
break;
default:
b = ch;
}
/* Decode byte b as UTF-8, sumb collects incomplete chars */
if ((b & 0xc0) == 0x80) { // 10xxxxxx (continuation byte)
sumb = (sumb << 6) | (b & 0x3f) ; // Add 6 bits to sumb
if (--more == 0) sbuf.append((char) sumb) ; // Add char to sbuf
} else if ((b & 0x80) == 0x00) { // 0xxxxxxx (yields 7 bits)
sbuf.append((char) b) ; // Store in sbuf
} else if ((b & 0xe0) == 0xc0) { // 110xxxxx (yields 5 bits)
sumb = b & 0x1f;
more = 1; // Expect 1 more byte
} else if ((b & 0xf0) == 0xe0) { // 1110xxxx (yields 4 bits)
sumb = b & 0x0f;
more = 2; // Expect 2 more bytes
} else if ((b & 0xf8) == 0xf0) { // 11110xxx (yields 3 bits)
sumb = b & 0x07;
more = 3; // Expect 3 more bytes
} else if ((b & 0xfc) == 0xf8) { // 111110xx (yields 2 bits)
sumb = b & 0x03;
more = 4; // Expect 4 more bytes
} else /*if ((b & 0xfe) == 0xfc)*/ { // 1111110x (yields 1 bit)
sumb = b & 0x01;
more = 5; // Expect 5 more bytes
}
/* We don't test if the UTF-8 encoding is well-formed */
}
return sbuf.toString();
}
private void identPort(String inputURL, int dflt) throws MalformedURLException {
// identify ref in file
int r = this.host.indexOf(':');
if (r < 0) {
this.port = dflt;
} else {
try {
String portStr = this.host.substring(r + 1);
if (portStr.trim().length() > 0) this.port = Integer.parseInt(portStr);
else this.port = -1;
this.host = this.host.substring(0, r);
} catch (NumberFormatException e) {
throw new MalformedURLException("wrong port in host fragment '" + this.host + "' of input url '" + inputURL + "'");
}
}
}
private void identRef() {
// identify ref in file
int r = path.indexOf('#');
if (r < 0) {
this.ref = null;
} else {
this.ref = path.substring(r + 1);
this.path = path.substring(0, r);
}
}
private void identQuest() {
// identify quest in file
int r = path.indexOf('?');
if (r < 0) {
this.quest = null;
} else {
this.quest = path.substring(r + 1);
this.path = path.substring(0, r);
}
}
public String getFile() {
return getFile(true);
}
public String getFile(boolean includeReference) {
// this is the path plus quest plus ref
// if there is no quest and no ref the result is identical to getPath
// this is defined according to http://java.sun.com/j2se/1.4.2/docs/api/java/net/URL.html#getFile()
if (quest != null) return ((includeReference) && (ref != null)) ? path + "?" + quest + "#" + ref : path + "?" + quest;
return ((includeReference) && (ref != null)) ? path + "#" + ref : path;
}
public String getFileName() {
// this is a method not defined in any sun api
// it returns the last portion of a path without any reference
int p = path.lastIndexOf('/');
if (p < 0) return path;
if (p == path.length() - 1) return ""; // no file name, this is a path to a directory
return path.substring(p + 1); // the 'real' file name
}
public String getPath() {
return path;
}
public String getAuthority() {
return ((port >= 0) && (host != null)) ? host + ":" + port : ((host != null) ? host : "");
}
public String getHost() {
return host;
}
public int getPort() {
return port;
}
public String getProtocol() {
return protocol;
}
public String getRef() {
return ref;
}
public String getUserInfo() {
return userInfo;
}
public String getQuery() {
return quest;
}
public String toString() {
return toNormalform(false, true);
}
public String toNormalform(boolean stripReference, boolean stripAmp) {
if (stripAmp)
return toNormalform(!stripReference).replaceAll("&amp;", "&");
else
return toNormalform(!stripReference);
}
private String toNormalform(boolean includeReference) {
// generates a normal form of the URL
boolean defaultPort = false;
if (this.protocol.equals("mailto")) {
return this.protocol + ":" + this.userInfo + "@" + this.host;
} else if (this.protocol.equals("http")) {
if (this.port < 0 || this.port == 80) { defaultPort = true; }
} else if (this.protocol.equals("ftp")) {
if (this.port < 0 || this.port == 21) { defaultPort = true; }
} else if (this.protocol.equals("https")) {
if (this.port < 0 || this.port == 443) { defaultPort = true; }
}
String path = resolveBackpath(this.getFile(includeReference));
if (defaultPort) {
return this.protocol + "://" +
((this.userInfo != null) ? (this.userInfo + "@") : ("")) +
this.getHost().toLowerCase() + path;
}
return this.protocol + "://" +
((this.userInfo != null) ? (this.userInfo + "@") : ("")) +
this.getHost().toLowerCase() + ((defaultPort) ? ("") : (":" + this.port)) + path;
}
public boolean equals(URL other) {
return (((this.protocol == other.protocol) || (this.protocol.equals(other.protocol))) &&
((this.host == other.host ) || (this.host.equals(other.host))) &&
((this.userInfo == other.userInfo) || (this.userInfo.equals(other.userInfo))) &&
((this.path == other.path ) || (this.path.equals(other.path))) &&
((this.quest == other.quest ) || (this.quest.equals(other.quest))) &&
((this.ref == other.ref ) || (this.ref.equals(other.ref))) &&
((this.port == other.port )));
}
public int hashCode() {
return this.toString().hashCode();
}
public int compareTo(Object h) {
assert (h instanceof URL);
return this.toString().compareTo(((URL) h).toString());
}
public static void main(String[] args) {
String[][] test = new String[][]{
new String[]{null, "http://www.anomic.de/home/test?x=1#home"},
new String[]{null, "http://www.anomic.de/home/test?x=1"},
new String[]{null, "http://www.anomic.de/home/test#home"},
new String[]{null, "ftp://ftp.anomic.de/home/test#home"},
new String[]{null, "http://www.anomic.de/home/../abc/"},
new String[]{null, "mailto:abcdefg@nomailnomail.com"},
new String[]{"http://www.anomic.de/home", "test"},
new String[]{"http://www.anomic.de/home", "test/"},
new String[]{"http://www.anomic.de/home/", "test"},
new String[]{"http://www.anomic.de/home/", "test/"},
new String[]{"http://www.anomic.de/home/index.html", "test.htm"},
new String[]{"http://www.anomic.de/home/index.html", "http://www.yacy.net/test"},
new String[]{"http://www.anomic.de/home/index.html", "ftp://ftp.yacy.net/test"},
new String[]{"http://www.anomic.de/home/index.html", "../test"},
new String[]{"http://www.anomic.de/home/index.html", "mailto:abcdefg@nomailnomail.com"},
new String[]{null, "news:de.test"},
new String[]{"http://www.anomic.de/home", "news:de.test"},
new String[]{"http://www.anomic.de/home", "ftp://ftp.anomic.de/src"},
new String[]{null, "ftp://ftp.delegate.org/"},
new String[]{"http://www.anomic.de/home", "ftp://ftp.delegate.org/"},
new String[]{"http://www.anomic.de","mailto:yacy@weltherrschaft.org"},
new String[]{"http://www.anomic.de","javascipt:temp"},
new String[]{null,"http://yacy-websuche.de/wiki/index.php?title=De:IntroInformationFreedom&action=history"},
new String[]{null, "http://diskusjion.no/index.php?s=5bad5f431a106d9a8355429b81bb0ca5&showuser=23585"},
new String[]{null, "http://diskusjion.no/index.php?s=5bad5f431a106d9a8355429b81bb0ca5&amp;showuser=23585"}
};
String environment, url;
de.anomic.net.URL aURL, aURL1;
java.net.URL jURL;
for (int i = 0; i < test.length; i++) {
environment = test[i][0];
url = test[i][1];
try {aURL = de.anomic.net.URL.newURL(environment, url);} catch (MalformedURLException e) {aURL = null;}
if (environment == null) {
try {jURL = new java.net.URL(url);} catch (MalformedURLException e) {jURL = null;}
} else {
try {jURL = new java.net.URL(new java.net.URL(environment), url);} catch (MalformedURLException e) {jURL = null;}
}
// check equality to java.net.URL
if (((aURL == null) && (jURL != null)) ||
((aURL != null) && (jURL == null)) ||
((aURL != null) && (jURL != null) && (!(jURL.toString().equals(aURL.toString()))))) {
System.out.println("Difference for environment=" + environment + ", url=" + url + ":");
System.out.println((jURL == null) ? "jURL rejected input" : "jURL=" + jURL.toString());
System.out.println((aURL == null) ? "aURL rejected input" : "aURL=" + aURL.toString());
}
// check stability: the normalform of the normalform must be equal to the normalform
if (aURL != null) try {
aURL1 = new de.anomic.net.URL(aURL.toNormalform(false, true));
if (!(aURL1.toNormalform(false, true).equals(aURL.toNormalform(false, true)))) {
System.out.println("no stability for url:");
System.out.println("aURL0=" + aURL.toString());
System.out.println("aURL1=" + aURL1.toString());
}
} catch (MalformedURLException e) {
System.out.println("no stability for url:");
System.out.println("aURL0=" + aURL.toString());
System.out.println("aURL1 cannot be computed:" + e.getMessage());
}
}
}
}
Reference in new issue View Git Blame Copy Permalink