Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-19 00:01:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix truncated urls containing ","

Browse Source 
adressing http://mantis.tokeek.de/view.php?id=58

Exclude comma from percent-encoding in MultiProtocolURL (see  RFC 1738 2.2  and  RFC 3986 2.2)
This commit is contained in:
reger 2014-05-13 01:50:15 +02:00
parent 9112f0a2df
commit 024f8e9b33
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
source/net/yacy/cora/document/id/MultiProtocolURL.java
View File

@ -495,8 +495,9 @@ public class MultiProtocolURL implements Serializable, Comparable<MultiProtocolU
* <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>The unreserved characters & : - _ . ! ~ * ' ( ) ; , remain the same.
* see RFC 1738 2.2 and RFC 3986 2.2
*
* <li>All other ASCII characters are converted into the
* 3-character string "%xy", where xy is
* the two-digit hexadecimal representation of the character
@ -529,7 +530,8 @@ public class MultiProtocolURL implements Serializable, Comparable<MultiProtocolU
|| ch == '.' || ch == '!'
|| ch == '~' || ch == '*'
|| ch == '\'' || ch == '('
|| ch == ')' || ch == ';') {
|| ch == ')' || ch == ';'
|| ch == ',') { // RFC 1738 2.2 special char (may be used unencoded)
sbuf.append((char)ch);
} else if (ch == '/') { // reserved, but may appear in post part where it should not be replaced
sbuf.append((char)ch);