Forks/privacore-open-source-search-engine
1
0
Fork 0
forked from Mirrors/privacore-open-source-search-engine
Code Pull Requests Activity

Merge branch 'master' into testing

Browse Source
This commit is contained in:
Matt Wells
2014-08-23 07:30:17 -07:00
parent 5d3fd80063 425b2bb81b
commit 80f73bf297
4 changed files with 30 additions and 12 deletions

4
Parms.cpp

@ -16140,7 +16140,9 @@ void Parms::init ( ) {
m->m_cgi = "usr";
m->m_off = (char *)&cr.m_useSimplifiedRedirects - x;
m->m_type = TYPE_BOOL;
m->m_def = "1";
// turn off for now. spider time deduping should help any issues
// by disabling this.
m->m_def = "0";
m->m_page = PAGE_SPIDER;
m->m_obj = OBJ_COLL;
m->m_flags = PF_CLONE;

6
XmlDoc.cpp

@ -528,7 +528,7 @@ void XmlDoc::reset ( ) {
// should point into a safebuf as well
//mfree ( ptr_linkInfo2 , size_linkInfo2, "LinkInfo2");
ptr_linkInfo2 = NULL;
m_linkInfo1Valid = false;
m_linkInfo2Valid = false;
}
if ( m_rawUtf8ContentValid && m_rawUtf8Content && !m_setFromTitleRec
// was content supplied by pageInject.cpp?
@ -21158,6 +21158,7 @@ char *XmlDoc::getMetaList ( bool forDelete ) {
// since we might have set it in copyFromOldDoc() above
ptr_linkInfo1 = NULL;
size_linkInfo1 = 0;
m_linkInfo1Valid = false;
// . if not using spiderdb we are done at this point
// . this happens for diffbot json replies (m_dx)
@ -23434,7 +23435,8 @@ void XmlDoc::copyFromOldDoc ( XmlDoc *od ) {
// we need the link info too!
ptr_linkInfo1 = od->ptr_linkInfo1;
size_linkInfo1 = od->size_linkInfo1;
m_linkInfo1Valid = true;
if ( ptr_linkInfo1 && size_linkInfo1 ) m_linkInfo1Valid = true;
else m_linkInfo1Valid = false;
// turn off for debug
ptr_sectiondbData = NULL;

4
html/admin.html

@ -96,7 +96,7 @@ A work-in-progress <a href=/compare.html>comparison to SOLR</a>.
<br><br><a name=quickstart></a>
<h1>Quick Start</h1>
&lt;<i>Last Updated June 2014</i>&gt;
&lt;<i>Last Updated August 2014</i>&gt;
<br>
<br>
@ -112,7 +112,7 @@ You will need an Intel or AMD system with at least 4GB of RAM for every gigablas
<b><font color=red>For Linux:</font></b>
<br><br>
1. Download the <a href=http://www.gigablast.com/gb-1.0-2.i386.rpm>Gigablast package for <b>RedHat</b> Linux</a> or the <a href=http://www.gigablast.com/gb_1.0-1_i386.deb>Gigablast package for <b>Ubuntu</b>/Debian Linux</a>.
1. Download the <a href=http://www.gigablast.com/gb-1.7-2.i386.rpm>Gigablast package for <b>RedHat</b> Linux</a> or the <a href=http://www.gigablast.com/gb_1.7-1_i386.deb>Gigablast package for <b>Ubuntu</b>/Debian Linux</a>.
<br><br>

28
html/compare.html

@ -121,7 +121,7 @@ Apache Open Source License 2
<td><b>HTTP API</b></td>
<!-- gb install -->
<td>
<a href=/api>here</a>
<a href=/api2.html>here</a>
</td>
<!-- solr install-->
<td>
@ -156,6 +156,20 @@ Apache Open Source License 2
</tr>
<tr valign=top>
<td><b>Github Star Ratings</b></td>
<!-- gb install -->
<td>
<a href=https://github.com/gigablast/open-source-search-engine>326</a> (8/2/2014)
</td>
<!-- solr install-->
<td>
<a href=https://github.com/apache/lucene-solr>767</a> (8/2/2014)
</td>
</tr>
@ -232,7 +246,7 @@ Many different packages quilted together. Apache, MySQL, Lucene, Tika, Zookeeper
<!--gigablast-->
<td>
<font color=green><b>
Use curl using args (including <i>delim</i>) listed <a href=/api.html#/admin/inject>here</a>
Use curl using args (including <i>delim</i>) listed <a href=/api2.html#/admin/inject>here</a>
</b></font>
<br>
</td>
@ -252,7 +266,7 @@ unsupported
<!--gigablast-->
<td>
Use curl to post the content of the file with args listed
<a href=/api.html#/admin/inject>here</a>
<a href=/api2.html#/admin/inject>here</a>
</td>
<!--solr-->
<td>
@ -270,7 +284,7 @@ You can index individual local files as such:
<!--gigablast-->
<td>
Use curl to inject the url with args listed
<a href=/api.html#/admin/inject>here</a>
<a href=/api2.html#/admin/inject>here</a>
</td>
<!--solr-->
@ -287,7 +301,7 @@ Use curl to inject the url with args listed
<!--gigablast-->
<td>
Use one curl command for each url, using the interface described
<a href=/api.html#/admin/inject>here</a></b>
<a href=/api2.html#/admin/inject>here</a></b>
</td>
<!--solr-->
<td>
@ -305,7 +319,7 @@ Use one curl command for each url, using the interface described
<!--gigablast-->
<td>
Use curl command to delete a url, using the interface described
<a href=/api.html#/admin/inject>here</a></b>
<a href=/api2.html#/admin/inject>here</a></b>
</td>
<!--solr-->
<td>
@ -321,7 +335,7 @@ You can delete individual documents by specifying queries that match just those
<td><b>Getting Results via cmdline</b></td>
<td>
Use curl command to do a search, using the interface described
<a href=/api.html#/search>here</a></b>
<a href=/api2.html#/search>here</a></b>
</td>
<td>
???