gigablast/open-source-search-engine
1
0
Fork 0
mirror of https://github.com/gigablast/open-source-search-engine.git synced 2024-10-04 12:17:35 +03:00
Code Issues Projects Releases Wiki Activity

expose "urlip" injection parm to provide ip of url

Browse Source 
being injected to save gigablast from an ip lookup
if you want.
This commit is contained in:
Matt 2015-09-16 09:43:15 -06:00
parent f9c4f8fc9a
commit bcdecc63c6
3 changed files with 31 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
PageInject.cpp
View File

@ -75,6 +75,13 @@ void setInjectionRequestFromParms ( TcpSocket *sock ,
int32_t def = atoll(m->m_def);
*ii = (char)hr->getLong(m->m_cgi,def);
}
else if ( m->m_type == TYPE_IP ) {
char *ii = (char *)((char *)ir + m->m_off);
char *is = hr->getString(m->m_cgi,NULL);
*(int32_t *)ii = 0; // default ip to 0
// otherwise, set the ip
if ( is ) *(int32_t *)ii = atoip(is);
}
// if unsupported let developer know
else { char *xx=NULL;*xx=0; }
}

19
Parms.cpp
View File

@ -15107,6 +15107,19 @@ void Parms::init ( ) {
m->m_off = (char *)&ir.m_hopCount - (char *)&ir;
m++;
m->m_title = "url IP";
m->m_desc = "Use this IP when injecting the document. Do not use or "
"set to 0.0.0.0, if unknown. If provided, it will save an IP "
"lookup.";
m->m_cgi = "urlip";
m->m_obj = OBJ_IR;
m->m_type = TYPE_IP;
m->m_def = "0.0.0.0";
m->m_flags = PF_API;
m->m_page = PAGE_INJECT;
m->m_off = (char *)&ir.m_injectDocIp - (char *)&ir;
m++;
m->m_title = "last spider time";
m->m_desc = "Override last time spidered";
m->m_cgi = "lastspidered";
@ -15213,7 +15226,10 @@ void Parms::init ( ) {
"Separate MIME from actual content with two returns. "
"At least put a single space in here if you want to "
"inject empty content, otherwise the content will "
"be downloaded from the url.";
"be downloaded from the url. This is because the "
"page injection form always submits the content text area "
"even if it is empty, which should signify that the "
"content should be downloaded.";
m->m_cgi = "content";
m->m_obj = OBJ_IR;
m->m_type = TYPE_CHARPTR;
@ -22490,6 +22506,7 @@ bool Parm::printVal ( SafeBuf *sb , collnum_t collnum , int32_t occNum ) {
return sb->safePrintf("CMD");
if ( m_type == TYPE_IP )
// may print 0.0.0.0
return sb->safePrintf("%s",iptoa(*(int32_t *)val) );
log("parms: missing parm type!!");

11
XmlDoc.cpp
View File

@ -1258,6 +1258,12 @@ bool XmlDoc::set4 ( SpiderRequest *sreq ,
utf8Content = m_mime.getContent();
}
// use this to avoid ip lookup if it is not zero
if ( forcedIp ) {
m_ip = forcedIp;
m_ipValid = true;
}
// sometimes they supply the content they want! like when zaks'
// injects pages from PageInject.cpp
if ( utf8Content ) {
@ -1290,11 +1296,6 @@ bool XmlDoc::set4 ( SpiderRequest *sreq ,
// use this ip as well for now to avoid ip lookup
//m_ip = atoip("127.0.0.1");
//m_ipValid = true;
// use this to avoid ip lookup if it is not zero
if ( forcedIp ) {
m_ip = forcedIp;
m_ipValid = true;
}
// do not need robots.txt then
m_isAllowed = true;
m_isAllowedValid = true;