gigablast/open-source-search-engine
1
0
Fork 0
mirror of https://github.com/gigablast/open-source-search-engine.git synced 2024-10-04 04:07:13 +03:00
Code Issues Projects Releases Wiki Activity

fix bug of losing the hopcount 0 spiderrequest

Browse Source 
because it gets overridden by a link to itself
then it becomes hopcount 1.
This commit is contained in:
Matt 2016-01-05 13:49:54 -07:00
parent 953d636448
commit 5804e28230
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
XmlDoc.cpp
View File

@ -27321,6 +27321,8 @@ char *XmlDoc::addOutlinkSpiderRecsToMetaList ( ) {
if ( ! m_hopCountValid ) { char *xx=NULL;*xx=0; }
//if ( ! m_spideredTimeValid ) { char *xx=NULL;*xx=0; }
int64_t myUh48 = m_firstUrl.getUrlHash48();
// . pre-allocate a buffer to hold the spider recs
// . taken from SpiderRequest::store()
int32_t size = 0;
@ -27781,9 +27783,15 @@ char *XmlDoc::addOutlinkSpiderRecsToMetaList ( ) {
strcpy(ksr.m_url,s);
// this must be valid
if ( ! m_docIdValid ) { char *xx=NULL;*xx=0; }
// set the key, ksr.m_key. isDel = false
ksr.setKey ( firstIp, *d , false );
// we were hopcount 0, so if we link to ourselves we override
// our original hopcount of 0 with this guy that has a
// hopcount of 1. that sux... so don't do it.
if ( ksr.getUrlHash48() == myUh48 ) continue;
// if we've recently added this url to spiderdb in Spider.cpp, skip it
//if ( sc && sc->isInDupCache ( &ksr , false ) )
// continue;