Archives/gnosygnu_xowa
1
0
Fork 0
mirror of https://github.com/gnosygnu/xowa.git synced 2025-05-31 22:44:34 +00:00
Code Issues Projects Releases Wiki Activity

Mass_parse: Do not fail when generating full-text search indexes

Browse Source
This commit is contained in:
gnosygnu 2017-04-08 08:14:21 -04:00
parent 5fef0af3a5
commit 680e6b88d6
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
400_xowa/src/gplx/xowa/addons/wikis/fulltexts/core/Xofulltext_extractor.java
View File

@ -66,7 +66,6 @@ public class Xofulltext_extractor implements Mwh_doc_wkr {
// add to bfr // add to bfr
bfr.Add_mid(src, itm_bgn, itm_end); bfr.Add_mid(src, itm_bgn, itm_end);
} }
public byte[] Extract(byte[] src) { public byte[] Extract(byte[] src) {
doc_parser.Parse(this, src, 0, src.length); doc_parser.Parse(this, src, 0, src.length);
return bfr.To_bry_and_clear(); return bfr.To_bry_and_clear();

7
400_xowa/src/gplx/xowa/addons/wikis/fulltexts/indexers/bldrs/Xofulltext_indexer_wkr.java
View File

@ -33,9 +33,10 @@ public class Xofulltext_indexer_wkr {
); );
} }
public void Index(Xoae_page wpg) { public void Index(Xoae_page wpg) {
byte[] html = extractor.Extract(wpg.Db().Html().Html_bry()); synchronized (index_wtr) {// NOTE:synchronized needed for mass_parse; don't launch separate indexer per mp_thread b/c (a) lucene may not handle it well; (b) everything needs to be serialized to the same lucene dir, so no real performance benefits; DATE:2017-04-08
byte[] html = extractor.Extract(wpg.Db().Html().Html_bry());
Index(wpg.Db().Page().Id(), wpg.Db().Page().Score(), wpg.Ttl().Page_txt(), html); Index(wpg.Db().Page().Id(), wpg.Db().Page().Score(), wpg.Ttl().Page_txt(), html);
}
} }
public void Index(int page_id, int score, byte[] ttl, byte[] html) { public void Index(int page_id, int score, byte[] ttl, byte[] html) {
Gflucene_doc_data data = new Gflucene_doc_data(page_id, score, String_.new_u8(ttl), String_.new_u8(html)); Gflucene_doc_data data = new Gflucene_doc_data(page_id, score, String_.new_u8(ttl), String_.new_u8(html));