tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

also index file path as terms

Browse Source
This commit is contained in:
dockes 2005-12-05 10:39:20 +00:00
parent 086d56c209
commit ce35b3a1b2
1 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/rcldb/rcldb.cpp
View File

@ -1,5 +1,5 @@
#ifndef lint #ifndef lint
static char rcsid[] = "@(#$Id: rcldb.cpp,v 1.42 2005-11-30 09:46:25 dockes Exp $ (C) 2004 J.F.Dockes"; static char rcsid[] = "@(#$Id: rcldb.cpp,v 1.43 2005-12-05 10:39:20 dockes Exp $ (C) 2004 J.F.Dockes";
#endif #endif
#include <stdio.h> #include <stdio.h>
#include <sys/stat.h> #include <sys/stat.h>
@ -305,39 +305,48 @@ bool Rcl::Db::add(const string &fn, const Rcl::Doc &idoc)
TextSplit splitter(&splitData); TextSplit splitter(&splitData);
///////// Split and index terms in document body and auxiliary fields // /////// Split and index terms in document body and auxiliary fields
// Split title and index terms
string noacc; string noacc;
// Split and index file name. This supposes that it's either ascii
// or utf-8. If this fails, we just go on. We need a config
// parameter for file name charset
if (dumb_string(fn, noacc)) {
splitter.text_to_words(noacc);
splitData.basepos += splitData.curpos + 100;
}
// Split and index title
if (!dumb_string(doc.title, noacc)) { if (!dumb_string(doc.title, noacc)) {
LOGERR(("Rcl::Db::add: unac failed\n")); LOGERR(("Rcl::Db::add: unac failed\n"));
return false; return false;
} }
splitter.text_to_words(noacc); splitter.text_to_words(noacc);
splitData.basepos += splitData.curpos + 100;
// Split body and index terms // Split body and index terms
splitData.basepos += splitData.curpos + 100;
if (!dumb_string(doc.text, noacc)) { if (!dumb_string(doc.text, noacc)) {
LOGERR(("Rcl::Db::add: dumb_string failed\n")); LOGERR(("Rcl::Db::add: dumb_string failed\n"));
return false; return false;
} }
splitter.text_to_words(noacc); splitter.text_to_words(noacc);
splitData.basepos += splitData.curpos + 100;
// Split keywords and index terms // Split keywords and index terms
splitData.basepos += splitData.curpos + 100;
if (!dumb_string(doc.keywords, noacc)) { if (!dumb_string(doc.keywords, noacc)) {
LOGERR(("Rcl::Db::add: dumb_string failed\n")); LOGERR(("Rcl::Db::add: dumb_string failed\n"));
return false; return false;
} }
splitter.text_to_words(noacc); splitter.text_to_words(noacc);
splitData.basepos += splitData.curpos + 100;
// Split abstract and index terms // Split abstract and index terms
splitData.basepos += splitData.curpos + 100;
if (!dumb_string(doc.abstract, noacc)) { if (!dumb_string(doc.abstract, noacc)) {
LOGERR(("Rcl::Db::add: dumb_string failed\n")); LOGERR(("Rcl::Db::add: dumb_string failed\n"));
return false; return false;
} }
splitter.text_to_words(noacc); splitter.text_to_words(noacc);
splitData.basepos += splitData.curpos + 100;
////// Special terms for metadata ////// Special terms for metadata
// Mime type // Mime type