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

fixed must-match filter for smb crawling

Browse Source 
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7222 6c8d7289-2bf4-0310-a012-ef5d649a1542
This commit is contained in:
orbiter 2010-10-05 00:05:08 +00:00
parent 099def2a04
commit c3bf17a3a1
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
htroot/Crawler_p.java
View File

@ -144,7 +144,13 @@ public class Crawler_p {
if (newcrawlingMustMatch.length() < 2) newcrawlingMustMatch = CrawlProfile.MATCH_ALL; // avoid that all urls are filtered out if bad value was submitted if (newcrawlingMustMatch.length() < 2) newcrawlingMustMatch = CrawlProfile.MATCH_ALL; // avoid that all urls are filtered out if bad value was submitted
// special cases: // special cases:
if (crawlingStartURL!= null && fullDomain) { if (crawlingStartURL!= null && fullDomain) {
newcrawlingMustMatch = crawlingStartURL.isFile() ? "file://" + crawlingStartURL.getPath() + ".*" : crawlingStartURL.isSMB() ? "smb://" + crawlingStartURL.getPath() + ".*" : ".*" + crawlingStartURL.getHost() + ".*"; if (crawlingStartURL.isFile()) {
newcrawlingMustMatch = "file://" + crawlingStartURL.getPath() + ".*";
} else if (crawlingStartURL.isSMB()) {
newcrawlingMustMatch = "smb://.*" + crawlingStartURL.getHost() + ".*" + crawlingStartURL.getPath() + ".*";
} else {
newcrawlingMustMatch = ".*" + crawlingStartURL.getHost() + ".*";
}
} }
if (crawlingStart!= null && subPath && (pos = crawlingStart.lastIndexOf('/')) > 0) { if (crawlingStart!= null && subPath && (pos = crawlingStart.lastIndexOf('/')) > 0) {
newcrawlingMustMatch = crawlingStart.substring(0, pos + 1) + ".*"; newcrawlingMustMatch = crawlingStart.substring(0, pos + 1) + ".*";