Forks/open-source-search-engine
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

link text extraction fixes

Browse Source
This commit is contained in:
Matt 2014-12-11 06:52:14 -08:00
parent 4f71a95da5
commit 27df9a4276
1 changed files with 10 additions and 5 deletions

15
XmlDoc.cpp

@ -29461,9 +29461,9 @@ Msg20Reply *XmlDoc::getMsg20Reply ( ) {
// caller shouldhave the callback set
if ( ! m_callback1 && ! m_callback2 ) { char *xx=NULL;*xx=0; }
char safeStack[100000];
safeStack[0] = 0;
safeStack[90000] = 0;
//char safeStack[100000];
//safeStack[0] = 0;
//safeStack[90000] = 0;
// int16_tcut
Msg20Reply *reply = &m_reply;
@ -29651,16 +29651,19 @@ Msg20Reply *XmlDoc::getMsg20Reply ( ) {
// lookup the tagdb rec fresh if setting for a summary. that way we
// can see if it is banned or not. but for getting m_getTermListBuf
// and stuff above, skip the tagrec lookup!
if ( m_req ) m_tagRecDataValid = false;
// save some time when SPIDERING/BUILDING by skipping fresh
// tagdb lookup and using tags in titlerec
if ( m_req && ! m_req->m_getLinkText && ! m_checkedUrlFilters )
m_tagRecDataValid = false;
// set and validate member vars
//if ( ! m_setFromTitleRec )
// // return NULL with g_errno set on error
// if ( ! set ( tr , NULL , m_niceness ) ) return NULL;
// set the tag rec
TagRec *gr = getTagRec();
if ( ! gr || gr == (void *)-1 ) return (Msg20Reply *)gr;
//reply-> ptr_tagRec = (char *)gr;
//reply->size_tagRec = gr->getSize();
@ -30183,6 +30186,8 @@ Msg20Reply *XmlDoc::getMsg20Reply ( ) {
// breathe
QUICKPOLL ( m_niceness );
// getLinkText is true if we are getting the anchor text for a
// supplied url as part of the SPIDER process..
// this was done by Msg23 before
if ( ! m_req->m_getLinkText ) {
m_replyValid = true;