From: <bra...@us...> - 2009-10-23 00:58:51
|
Revision: 2828 http://archive-access.svn.sourceforge.net/archive-access/?rev=2828&view=rev Author: bradtofel Date: 2009-10-23 00:58:43 +0000 (Fri, 23 Oct 2009) Log Message: ----------- FEATURE: now parses "charset detection mode" flag ("cm#_") to specify different strategies. Modified Paths: -------------- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java =================================================================== --- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java 2009-10-23 00:46:31 UTC (rev 2827) +++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/ArchivalUrlRequestParser.java 2009-10-23 00:58:43 UTC (rev 2828) @@ -46,6 +46,7 @@ public final static String JS_CONTEXT = "js"; public final static String CSS_CONTEXT = "cs"; public final static String IMG_CONTEXT = "im"; + public final static String CHARSET_MODE = "cm"; protected RequestParser[] getRequestParsers() { RequestParser[] theParsers = { Modified: trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java =================================================================== --- trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java 2009-10-23 00:46:31 UTC (rev 2827) +++ trunk/archive-access/projects/wayback/wayback-core/src/main/java/org/archive/wayback/archivalurl/requestparser/ReplayRequestParser.java 2009-10-23 00:58:43 UTC (rev 2828) @@ -46,7 +46,7 @@ * timestamp, flags, & url */ public final static Pattern WB_REQUEST_REGEX = Pattern - .compile("^(\\d{1,14})(([a-z]{2}_)*)/(.*)$"); + .compile("^(\\d{1,14})(([a-z]{2}[0-9]*_)*)/(.*)$"); /** * @param wrapped @@ -124,6 +124,11 @@ wbRequest.setJSContext(true); } else if(flag.equals(ArchivalUrlRequestParser.IMG_CONTEXT)) { wbRequest.setIMGContext(true); + } else if(flag.startsWith(ArchivalUrlRequestParser.CHARSET_MODE)) { + String modeString = flag.substring( + ArchivalUrlRequestParser.CHARSET_MODE.length()); + int mode = Integer.parseInt(modeString); + wbRequest.setCharsetMode(mode); } } } This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |