Update of /cvsroot/monetdb/pathfinder/modules/pftijah/Tests
In directory 23jxhf1.ch3.sourceforge.com:/tmp/cvs-serv28611/Tests
Modified Files:
Tag: Nov2009
colltest2.stable.err createcoll0.milS createcoll0.stable.out
createcoll1.milS createcoll1.stable.out createcoll1_frag.milS
createcoll1_frag.stable.out load.stable.out
load_bug2831472.milS load_bug2831472.stable.out
loadthesis.milS loadthesis.stable.out procs.stable.out
sigs.stable.out test_lms_or.stable.out
Log Message:
Backported:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/08 - hrode: pftijah.mx serialize_pftijah.mx
several small fixes for fragmented indexing
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/13 - hrode: tjc/tjc_main.c
initialization of default value for inexout param was missing
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/14 - hrode: pftijah.mx Tests/colltest2.stable.err
Tests/createcoll0.milS Tests/createcoll0.stable.out
Tests/createcoll1.milS Tests/createcoll1.stable.out
Tests/createcoll1_frag.milS Tests/createcoll1_frag.stable.out
Tests/load.stable.out Tests/load_bug2831472.milS
Tests/load_bug2831472.stable.out Tests/loadthesis.milS
Tests/loadthesis.stable.out Tests/procs.stable.out
Tests/sigs.stable.out Tests/test_lms_or.stable.out
- introduce fragmented indexing on XQuery level
- fixed bugs on MIL level function for fragemented indexing
- adapted the test cases
what still misses is the querying on the fragmented index,
but the default for indexing is currently set to create only
one single index, which allows querying to work as before
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/14 - stmane: pftijah.mx
found by icc:
removed set but unused variables
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/21 - jflokstra: pftijah.mx
- fix for ftiName MIL variable usage when pftijah mil functions are not called
from pftijah generated MIL scripts but from Pathfinder generated scripts.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/21 - jflokstra: pftijah.mx
- 2 more fixes to make ftcontains work
1) fix self inflicted pathfinder variable name problem
2) fix usage of ftindex (:~ ftiName + "0")
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/22 - jflokstra: pftijah.mx
- fix problem with pf:add-doc() on non tijah database.
- mark infinitely waiting ws_create(0) call with tj_tracers.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/26 - hrode: tjc/tjc_milprint.c
try to fix compilation problem
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/10/27 - stmane: tjc/tjc_milprint.c
back-porting
"
2009/10/26 - hrode: pathfinder/modules/pftijah/tjc/tjc_milprint.c,1.22
try to fix compilation problem
"
from the development trunk to the Nov2009 release candidate branch
to have the changes tested with nightly Candidate testing
(lacking resources, we currently don't have Current testing
in addition to Stable & Candidate testing)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/11/06 - hrode: pftijah.mx
avoid working set caching when the pf/tijah indexer serializes a document
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2009/11/06 - hrode: pftijah.mx
remove accidentally checked-in debugging output.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Index: loadthesis.milS
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/loadthesis.milS,v
retrieving revision 1.3
retrieving revision 1.3.28.1
diff -u -d -r1.3 -r1.3.28.1
--- loadthesis.milS 11 Mar 2007 23:26:38 -0000 1.3
+++ loadthesis.milS 11 Nov 2009 15:07:22 -0000 1.3.28.1
@@ -5,5 +5,5 @@
var path:=getenv("TSTSRCDIR");
# index thesis collection
-tj_init_collection("thesis",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("thesis",path+"/xml-docs/thesis.xml","thesis.xml",true);
+tj_init_collection_base("thesis",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("thesis",path+"/xml-docs/thesis.xml","thesis.xml",true);
Index: colltest2.stable.err
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/colltest2.stable.err,v
retrieving revision 1.10
retrieving revision 1.10.6.1
diff -u -d -r1.10 -r1.10.6.1
--- colltest2.stable.err 13 May 2009 07:38:26 -0000 1.10
+++ colltest2.stable.err 11 Nov 2009 15:07:22 -0000 1.10.6.1
@@ -10,7 +10,7 @@
# 16:06:32 > Mtimeout -timeout 60 MapiClient -lxquery -fxml -umonetdb
-Pmonetdb --host=localhost --port=31150 colltest2.xq
# 16:06:32 >
-MAPI = mone...@asbjorn:34593
+MAPI = mone...@asbjorn:36691
QUERY = let $opt := <TijahOptions debug="0" ft-index="FT_PFCOLL"
ir-model="NLLR"/>
ERROR = !ERROR: CMDtijah_query: Error (new NEXI syntax): A query with
startnodes should start with a relative path expression.
!ERROR: CMDtijah_query: operation failed.
Index: load_bug2831472.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/load_bug2831472.stable.out,v
retrieving revision 1.2
retrieving revision 1.2.4.1
diff -u -d -r1.2 -r1.2.4.1
--- load_bug2831472.stable.out 17 Sep 2009 10:58:59 -0000 1.2
+++ load_bug2831472.stable.out 11 Nov 2009 15:07:22 -0000 1.2.4.1
@@ -21,10 +21,10 @@
var path:=getenv("TSTSRCDIR");
# index thesis collection
-tj_init_collection("debates",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("debates",path+"/xml-docs/debates.xml","debates.xml",true);
-# Elapsed time = 441us [044us/node]
-# Shredded 1 XML document (debates.xml), total time after commit=0.016s
+tj_init_collection_base("debates",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("debates",path+"/xml-docs/debates.xml","debates.xml",true);
+# Elapsed time = 531us [053us/node]
+# Shredded 1 XML document (debates.xml), total time after commit=0.017s
quit();
# 17:24:22 >
Index: loadthesis.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/loadthesis.stable.out,v
retrieving revision 1.3
retrieving revision 1.3.28.1
diff -u -d -r1.3 -r1.3.28.1
--- loadthesis.stable.out 11 Mar 2007 23:26:38 -0000 1.3
+++ loadthesis.stable.out 11 Nov 2009 15:07:22 -0000 1.3.28.1
@@ -16,10 +16,10 @@
var path:=getenv("TSTSRCDIR");
# index thesis collection
-tj_init_collection("thesis",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("thesis",path+"/xml-docs/thesis.xml","thesis.xml",true);
-# Elapsed time = 765us [010us/node]
-# Shredded 1 XML document (thesis.xml), total time after commit=0.007s
+tj_init_collection_base("thesis",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("thesis",path+"/xml-docs/thesis.xml","thesis.xml",true);
+# Elapsed time = 544us [007us/node]
+# Shredded 1 XML document (thesis.xml), total time after commit=0.014s
quit();
# 11:32:35 >
Index: createcoll0.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll0.stable.out,v
retrieving revision 1.3
retrieving revision 1.3.28.1
diff -u -d -r1.3 -r1.3.28.1
--- createcoll0.stable.out 11 Mar 2007 23:26:38 -0000 1.3
+++ createcoll0.stable.out 11 Nov 2009 15:07:22 -0000 1.3.28.1
@@ -16,10 +16,10 @@
var path:=getenv("TSTSRCDIR");
# index collection 0
-tj_init_collection("testcoll0",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("testcoll0",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-# Elapsed time = 810us [013us/node]
-# Shredded 1 XML document (dilbert.xml), total time after commit=0.007s
+tj_init_collection_base("testcoll0",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("testcoll0",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+# Elapsed time = 570us [009us/node]
+# Shredded 1 XML document (dilbert.xml), total time after commit=0.104s
quit();
# 14:44:49 >
Index: createcoll1.milS
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll1.milS,v
retrieving revision 1.6
retrieving revision 1.6.16.1
diff -u -d -r1.6 -r1.6.16.1
--- createcoll1.milS 7 May 2008 12:29:24 -0000 1.6
+++ createcoll1.milS 11 Nov 2009 15:07:22 -0000 1.6.16.1
@@ -5,28 +5,20 @@
var path:=getenv("TSTSRCDIR");
# index collection at once
-tj_init_collection("testcoll1",
new(str,str).insert("stemmer","snowball-english"));
+tj_init_collection_base("testcoll1",
new(str,str).insert("stemmer","snowball-english"));
var docs := new(str,str);
docs.insert(path+"/xml-docs/dilbert.xml","dilbert.xml");
docs.insert(path+"/xml-docs/dilbert2.xml","dilbert2.xml");
docs.insert(path+"/xml-docs/special.xml","special.xml");
-tj_add2collection("testcoll1",docs,true);
+tj_add2collection_frag("testcoll1",docs,true);
# index collection incrementally
-tj_init_collection("testcoll2",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("testcoll2",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("testcoll2",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("testcoll2",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("testcoll2",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("testcoll2",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("testcoll2",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+tj_add2collection_frag("testcoll2",path+"/xml-docs/special.xml","special.xml",true);
# compare indexed collections
-var tids1 := bat(_tj_TermBat("testcoll1")).reverse().tsort();
-var tids2 := bat(_tj_TermBat("testcoll2")).reverse().tsort();
-var coll1 := indexfetchjoin(tids1, bat("tj_testcoll1_TermIndex"),
bat("tj_testcoll1_Terms"));
-var coll2 := indexfetchjoin(tids2, bat("tj_testcoll2_TermIndex"),
bat("tj_testcoll2_Terms"));
-diff(coll1,coll2).print();
-
-tids1 := bat(_tj_TagBat("testcoll1")).reverse().tsort();
-tids2 := bat(_tj_TagBat("testcoll2")).reverse().tsort();
-coll1 := indexfetchjoin(tids1, bat("tj_testcoll1_TagIndex"),
bat("tj_testcoll1_Tags"));
-coll2 := indexfetchjoin(tids2, bat("tj_testcoll2_TagIndex"),
bat("tj_testcoll2_Tags"));
+var coll1 := bat("tj_testcoll1_termfreq");
+var coll2 := bat("tj_testcoll2_termfreq");
diff(coll1,coll2).print();
Index: procs.stable.out
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/procs.stable.out,v
retrieving revision 1.59
retrieving revision 1.59.4.1
diff -u -d -r1.59 -r1.59.4.1
--- procs.stable.out 20 May 2009 14:37:58 -0000 1.59
+++ procs.stable.out 11 Nov 2009 15:07:22 -0000 1.59.4.1
@@ -20,12 +20,14 @@
[ "ADDHELP(str, str, str, str, str) : void"
]
[ "ALG_tj_add_fti_tape(str, BAT[oid,BAT], BAT[oid,BAT], BAT[void,any],
BAT[oid,BAT], BAT[str,BAT]) : BAT[str,BAT]" ]
[ "ALG_tj_docmgmt_tape(BAT[str,BAT], BAT[void,BAT], BAT[void,str],
BAT[void,str], BAT[void,str], BAT[void,lng]) : bit" ]
+[ "ALG_tj_docmgmt_tape2(BAT[str,BAT], BAT[void,BAT], BAT[void,str],
BAT[void,str], BAT[void,str], BAT[void,lng]) : bit"
]
[ "ALG_tj_ft_index_info(BAT[oid,BAT], BAT[void,any], BAT[oid,BAT]) :
BAT[void,BAT]"
]
[ "ALG_tj_ftfun_handler(bit, BAT[oid,BAT], BAT[oid,BAT], BAT[oid,BAT],
BAT[oid,BAT], BAT[void,any], BAT[oid,BAT], BAT[oid,BAT]) : BAT[void,BAT]"
]
[ "ALG_tj_pfop(BAT[oid,oid], BAT[oid,any], BAT[oid,any], BAT[oid,oid]) :
BAT[void,BAT]"
]
[ "ALG_tj_pfop(BAT[oid,oid], BAT[oid,any], BAT[oid,any], BAT[oid,oid],
BAT[oid,dbl]) : BAT[void,BAT]"
]
[ "ALG_tj_pfop(BAT[oid,oid], BAT[oid,any], int, BAT[oid,oid]) : BAT[void,BAT]"
]
[ "ALG_tj_query_handler(bit, BAT[oid,BAT], BAT[oid,BAT], BAT[oid,BAT],
BAT[void,any], BAT[oid,BAT], BAT[oid,BAT]) : BAT[void,BAT]" ]
+[ "ALG_tj_query_handler2(bit, BAT[oid,BAT], BAT[oid,BAT], BAT[oid,BAT],
BAT[void,any], BAT[oid,BAT], BAT[oid,BAT]) : BAT[void,BAT]"
]
[ "ALG_tj_query_nodes(BAT[void,any], BAT[oid,BAT], BAT[oid,BAT]) :
BAT[void,BAT]" ]
[ "ALG_tj_query_score(BAT[void,any], BAT[oid,BAT], BAT[oid,BAT], BAT[oid,BAT])
: BAT[void,BAT]" ]
[ "CTderive(BAT[oid,any], BAT[oid,any]) : grp"
]
@@ -112,15 +114,26 @@
[ "_tj_TagBat(str) : str"
]
[ "_tj_TermBat(str) : str"
]
[ "_tj_add2collection(str, BAT[oid,BAT], BAT[str,BAT], str, str, bit) : void"
]
+[ "_tj_add2collection_frag(str, BAT[str,BAT], str, str, bit) : void"
]
+[ "_tj_build_inverted_index_frag(str, BAT[str,BAT], BAT[str,BAT]) : void"
]
[ "_tj_chk_modified_fragments(str, BAT[str,BAT]) : BAT[void,str]"
]
[ "_tj_collection(str) : BAT[str,BAT]"
]
[ "_tj_collection_str(str) : BAT[void,BAT]"
]
[ "_tj_commit(BAT[str,BAT]) : void"
]
+[ "_tj_commit_frag(BAT[str,BAT], BAT[str,BAT]) : void"
]
+[ "_tj_create_commitBats() : BAT[str,BAT]"
]
[ "_tj_finalize_collection(str, BAT[str,BAT], bit) : void"
]
+[ "_tj_finalize_collection_frag(str, BAT[str,BAT], BAT[str,BAT], bit) : void"
]
+[ "_tj_get_collection_frag(str, BAT[str,BAT]) : void"
]
[ "_tj_get_parameter(BAT[str,BAT], str) : str"
]
+[ "_tj_get_parameter2(BAT[str,BAT], str) : str"
]
[ "_tj_init_collection(str, BAT[str,str], BAT[void,str], bit) : void"
]
+[ "_tj_init_collection_base(str, BAT[str,str], BAT[str,BAT]) : void"
]
+[ "_tj_init_collection_frag(str, int, BAT[str,BAT]) : void"
]
[ "_tj_safe_remove(str) : void"
]
+[ "_tj_set_forwardindex_access(BAT[str,BAT], int) : void"
]
[ "_tj_set_parameter(BAT[str,BAT], str, str) : void"
]
+[ "_tj_set_parameter2(BAT[str,BAT], str, str) : void"
]
[ "_ws_coll_isolate(lng, BAT[void,BAT], str, BAT[void,oid], BAT[void,oid],
BAT[void,oid], BAT[void,oid]) : void" ]
[ "_ws_free(lng) : BAT[void,any]"
]
[ "_ws_new(int, oid, int) : BAT[void,BAT]"
]
@@ -575,6 +588,7 @@
[ "rule(int, int, int, int, int) : rule"
]
[ "rule(int, str, int, int) : rule"
]
[ "rule(int, str, int, int, int) : rule"
]
+[ "run_nexi_query(str, BAT[str,str]) : BAT[oid,dbl]"
]
[ "run_tijah_query(str, BAT[str,str], bit, BAT[void,oid]) : BAT[oid,dbl]"
]
[ "runtime(lock, lock) : BAT[lock,BAT]"
]
[ "save(BAT[any::1,any::2]) : BAT[any::1,any::2]"
]
@@ -652,9 +666,12 @@
[ "timestamp_sub_sec_interval(timestamp, lng) : timestamp"
]
[ "tj_add2collection(str, BAT[str,str], bit) : void"
]
[ "tj_add2collection(str, str, str, bit) : void"
]
+[ "tj_add2collection_frag(str, BAT[str,str], bit) : void"
]
+[ "tj_add2collection_frag(str, str, str, bit) : void"
]
[ "tj_add_pre(BAT[oid,any]) : BAT[oid,oid]"
]
[ "tj_and_comb(BAT[any,any], BAT[any,any]) : BAT[any,any]"
]
[ "tj_and_nocomb(BAT[any,any], BAT[any,any]) : BAT[any,any]"
]
+[ "tj_collection_delete(str) : void"
]
[ "tj_contained_by_noprop_nest_nid(BAT[oid,oid], BAT[oid,oid]) : BAT[oid,any]"
]
[ "tj_contained_by_noprop_nest_pre(BAT[oid,oid], BAT[oid,oid]) : BAT[oid,any]"
]
[ "tj_contained_by_noprop_unnest_nid(BAT[oid,oid], BAT[oid,oid]) :
BAT[oid,any]"
]
@@ -674,43 +691,43 @@
[ "tj_containing_query_nest_nid_entity_LogSum(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_nest_nid_entity_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
[ "tj_containing_query_nest_nid_entity_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_phrase(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_LM(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_LMs(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_NLLR(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_OKAPI(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_nid_term_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_phrase(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_LM(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_LMs(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_NLLR(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_OKAPI(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_min(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_nid_term_plus(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
[ "tj_containing_query_nest_pre_entity_LogSum(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_nest_pre_entity_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
[ "tj_containing_query_nest_pre_entity_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_phrase(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_LM(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_LMs(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_NLLR(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_OKAPI(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_nest_pre_term_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_phrase(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_LM(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_LMs(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_NLLR(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_OKAPI(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_min(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_nest_pre_term_plus(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
[ "tj_containing_query_unnest_nid_entity_LogSum(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_unnest_nid_entity_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_unnest_nid_entity_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
-[ "tj_containing_query_unnest_nid_phrase(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_nid_term_LM(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_nid_term_LMs(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_nid_term_NLLR(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_nid_term_OKAPI(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
-[ "tj_containing_query_unnest_nid_term_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_nid_term_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_phrase(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_LM(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_LMs(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_NLLR(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_OKAPI(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_min(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_nid_term_plus(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
[ "tj_containing_query_unnest_pre_entity_LogSum(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_unnest_pre_entity_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
[ "tj_containing_query_unnest_pre_entity_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
-[ "tj_containing_query_unnest_pre_phrase(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_pre_term_LM(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_pre_term_LMs(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_pre_term_NLLR(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_pre_term_OKAPI(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]" ]
-[ "tj_containing_query_unnest_pre_term_min(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
-[ "tj_containing_query_unnest_pre_term_plus(BAT[oid,any], BAT[oid,dbl]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_phrase(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_LM(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_LMs(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_NLLR(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_OKAPI(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_min(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
+[ "tj_containing_query_unnest_pre_term_plus(BAT[oid,any], BAT[oid,BAT]) :
BAT[oid,dbl]"
]
[ "tj_delete_collection(str) : void"
]
[ "tj_delete_collection(str, bit) : void"
]
[ "tj_delete_global() : void"
]
@@ -719,8 +736,10 @@
[ "tj_extend_collection(str, BAT[void,str]) : void"
]
[ "tj_get_collection_lock(str) : lock"
]
[ "tj_get_ft_index(BAT[str,str], bit) : str"
]
+[ "tj_global_delete() : void"
]
[ "tj_init_collection(str, BAT[str,str]) : void"
]
[ "tj_init_collection(str, BAT[str,str], BAT[void,str]) : void"
]
+[ "tj_init_collection_base(str, BAT[str,str]) : void"
]
[ "tj_init_global() : void"
]
[ "tj_init_global(BAT[str,str]) : void"
]
[ "tj_init_global(BAT[str,str], bit) : void"
]
@@ -728,14 +747,19 @@
[ "tj_init_termHash(str) : void"
]
[ "tj_is_indexed(str) : bit"
]
[ "tj_is_indexed(str) : bit"
]
+[ "tj_merge_frag_results(BAT[void,BAT], int) : BAT[str,dbl]"
]
+[ "tj_merge_frag_results_inex(BAT[void,BAT], int) : BAT[str,dbl]"
]
[ "tj_nid2pre(BAT[oid,any]) : BAT[oid,any]"
]
[ "tj_nid2pre(BAT[oid,any], BAT[oid,str]) : BAT[oid,any]"
]
[ "tj_or_comb(BAT[any,any], BAT[any,any]) : BAT[any,any]"
]
[ "tj_or_nocomb(BAT[any,any], BAT[any,any]) : BAT[any,any]"
]
[ "tj_pfop(BAT[void,oid], BAT[void,any], BAT[void,int], BAT[void,oid]) :
BAT[void,BAT]"
]
[ "tj_play_doc_tape(BAT[void,BAT], BAT[void,oid], BAT[void,int],
BAT[void,lng], BAT[void,str]) : void"
]
+[ "tj_pre2inexpath(BAT[oid,dbl]) : BAT[str,dbl]"
]
[ "tj_pre2nid_noprop(BAT[oid,any]) : BAT[oid,any]"
]
[ "tj_pre2nid_prop(BAT[oid,any]) : BAT[oid,any]"
]
+[ "tj_pre2pfpre(BAT[oid,dbl]) : BAT[void,BAT]"
]
+[ "tj_prepare_query(BAT[str,dbl]) : BAT[void,BAT]"
]
[ "tj_prior_ls(BAT[oid,dbl]) : BAT[any,any]"
]
[ "tj_query_handler(bit, BAT[void,BAT], BAT[void,BAT], BAT[void,BAT],
BAT[oid,any], BAT[oid,BAT], BAT[void,lng], BAT[void,dbl], BAT[void,str],
BAT[void,BAT]) : BAT[void,BAT]" ]
[ "tj_rebuild_collection(str) : void"
]
@@ -770,6 +794,10 @@
[ "vx_maintain(BAT[oid,oid], BAT[oid,oid], BAT[oid,oid], BAT[oid,str]) :
BAT[int,oid]"
]
[ "vx_maintain(BAT[oid,oid], BAT[oid,str]) : BAT[int,oid]"
]
[ "vx_reduce(BAT[void,int], BAT[void,oid]) : BAT[oid,oid]"
]
+[ "ws_cache_end(BAT[any,any]) : void"
]
+[ "ws_cache_expr(BAT[any,any], str) : bit"
]
+[ "ws_cache_get(BAT[any,any], str) : bit"
]
+[ "ws_cache_put(BAT[any,any], str, BAT[any,any]) : void"
]
[ "ws_collection(BAT[void,BAT], BAT[oid,str], BAT[void,oid]) : BAT[oid,oid]"
]
[ "ws_collection_check(BAT[any::1,str]) : BAT[any::1,oid]"
]
[ "ws_collection_root(BAT[void,BAT], BAT[void,str]) : BAT[oid,oid]"
]
Index: createcoll1.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll1.stable.out,v
retrieving revision 1.7
retrieving revision 1.7.16.1
diff -u -d -r1.7 -r1.7.16.1
--- createcoll1.stable.out 7 May 2008 12:29:25 -0000 1.7
+++ createcoll1.stable.out 11 Nov 2009 15:07:22 -0000 1.7.16.1
@@ -16,40 +16,27 @@
var path:=getenv("TSTSRCDIR");
-tj_init_collection("testcoll1",
new(str,str).insert("stemmer","snowball-english"));
+# index collection at once
+tj_init_collection_base("testcoll1",
new(str,str).insert("stemmer","snowball-english"));
var docs := new(str,str);
docs.insert(path+"/xml-docs/dilbert.xml","dilbert.xml");
docs.insert(path+"/xml-docs/dilbert2.xml","dilbert2.xml");
docs.insert(path+"/xml-docs/special.xml","special.xml");
-tj_add2collection("testcoll1",docs,true);
-# Elapsed time = 740us [012us/node]
-# Shredded 1 XML document (dilbert.xml), total time after commit=0.007s
-# Elapsed time = 599us [010us/node]
-# Shredded 1 XML document (dilbert2.xml), total time after commit=0.005s
-# Elapsed time = 546us [024us/node]
-# Shredded 1 XML document (special.xml), total time after commit=0.005s
+tj_add2collection_frag("testcoll1",docs,true);
+# Elapsed time = 379us [006us/node]
+# Shredded 1 XML document (dilbert2.xml), total time after commit=0.016s
+# Elapsed time = 311us [014us/node]
+# Shredded 1 XML document (special.xml), total time after commit=0.010s
# index collection incrementally
-tj_init_collection("testcoll2",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("testcoll2",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("testcoll2",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("testcoll2",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("testcoll2",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("testcoll2",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("testcoll2",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+tj_add2collection_frag("testcoll2",path+"/xml-docs/special.xml","special.xml",true);
# compare indexed collections
-var tids1 := bat(_tj_TermBat("testcoll1")).reverse().tsort();
-var tids2 := bat(_tj_TermBat("testcoll2")).reverse().tsort();
-var coll1 := indexfetchjoin(tids1, bat("tj_testcoll1_TermIndex"),
bat("tj_testcoll1_Terms"));
-var coll2 := indexfetchjoin(tids2, bat("tj_testcoll2_TermIndex"),
bat("tj_testcoll2_Terms"));
-diff(coll1,coll2).print();
-#-----------------#
-# h t # name
-# oid oid # type
-#-----------------#
-
-tids1 := bat(_tj_TagBat("testcoll1")).reverse().tsort();
-tids2 := bat(_tj_TagBat("testcoll2")).reverse().tsort();
-coll1 := indexfetchjoin(tids1, bat("tj_testcoll1_TagIndex"),
bat("tj_testcoll1_Tags"));
-coll2 := indexfetchjoin(tids2, bat("tj_testcoll2_TagIndex"),
bat("tj_testcoll2_Tags"));
+var coll1 := bat("tj_testcoll1_termfreq");
+var coll2 := bat("tj_testcoll2_termfreq");
diff(coll1,coll2).print();
#-----------------#
# h t # name
Index: createcoll1_frag.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll1_frag.stable.out,v
retrieving revision 1.5
retrieving revision 1.5.16.1
diff -u -d -r1.5 -r1.5.16.1
--- createcoll1_frag.stable.out 7 May 2008 12:29:27 -0000 1.5
+++ createcoll1_frag.stable.out 11 Nov 2009 15:07:22 -0000 1.5.16.1
@@ -24,43 +24,39 @@
docs.insert(path+"/xml-docs/dilbert.xml","dilbert.xml");
docs.insert(path+"/xml-docs/dilbert2.xml","dilbert2.xml");
docs.insert(path+"/xml-docs/special.xml","special.xml");
-tj_init_collection("coll1_frag", coll_opt);
-tj_add2collection("coll1_frag",docs,true);
-# Elapsed time = 708us [012us/node]
-# Shredded 1 XML document (dilbert.xml), total time after commit=0.007s
-# Elapsed time = 571us [009us/node]
-# Shredded 1 XML document (dilbert2.xml), total time after commit=0.005s
-# Elapsed time = 551us [025us/node]
-# Shredded 1 XML document (special.xml), total time after commit=0.005s
+tj_init_collection_base("coll1_frag", coll_opt);
+tj_add2collection_frag("coll1_frag",docs,true);
# index collection incrementally
-tj_init_collection("coll2_frag", coll_opt);
-tj_add2collection("coll2_frag",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("coll2_frag",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("coll2_frag",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("coll2_frag", coll_opt);
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+
+
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/special.xml","special.xml",true);
+
+
coll_opt.replace("fragmentSize","60");
# index collection at once
-tj_init_collection("coll1_frag100", coll_opt);
-tj_add2collection("coll1_frag100",docs,true);
+tj_init_collection_base("coll1_frag100", coll_opt);
+tj_add2collection_frag("coll1_frag100",docs,true);
# index collection incrementally
-tj_init_collection("coll2_frag100", coll_opt);
-tj_add2collection("coll2_frag100",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("coll2_frag100",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("coll2_frag100",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("coll2_frag100", coll_opt);
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+
+
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/special.xml","special.xml",true);
# compare indexed collections
-var tids1 := bat(_tj_TermBat("coll1_frag")).sort().reverse();
-var tids2 := bat(_tj_TermBat("coll2_frag")).sort().reverse();
-var tids3 := bat(_tj_TermBat("coll1_frag100")).sort().reverse();
-var tids4 := bat(_tj_TermBat("coll2_frag100")).sort().reverse();
-var coll1 := indexfetchjoin(tids1, bat("tj_coll1_frag_TermIndex"),
bat("tj_coll1_frag_Terms"));
-var coll2 := indexfetchjoin(tids2, bat("tj_coll2_frag_TermIndex"),
bat("tj_coll2_frag_Terms"));
-var coll3 := indexfetchjoin(tids3, bat("tj_coll1_frag100_TermIndex"),
bat("tj_coll1_frag100_Terms"));
-var coll4 := indexfetchjoin(tids4, bat("tj_coll2_frag100_TermIndex"),
bat("tj_coll2_frag100_Terms"));
+var coll1 := bat("tj_coll1_frag_termfreq");
+var coll2 := bat("tj_coll2_frag_termfreq");
+var coll3 := bat("tj_coll1_frag100_termfreq");
+var coll4 := bat("tj_coll2_frag100_termfreq");
diff(coll1,coll2).print();
#-----------------#
Index: load.stable.out
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/load.stable.out,v
retrieving revision 1.13
retrieving revision 1.13.6.1
diff -u -d -r1.13 -r1.13.6.1
--- load.stable.out 13 May 2009 07:38:26 -0000 1.13
+++ load.stable.out 11 Nov 2009 15:07:22 -0000 1.13.6.1
@@ -42,48 +42,60 @@
# module usage_count # name
# str int # type
#---------------------------------#
-[ "aggrX3", 2 ]
-[ "alarm", 2 ]
+[ "aggrX3", 3 ]
+[ "alarm", 4 ]
[ "algebra", 1 ]
[ "arith", 1 ]
[ "bat", 1 ]
-[ "bat_arith", 1 ]
+[ "bat_arith", 2 ]
[ "builtin", 1 ]
[ "constant", 1 ]
-[ "lock", 1 ]
-[ "logger", 2 ]
+[ "lock", 4 ]
+[ "logger", 4 ]
[ "main", 1 ]
-[ "malalgebra", 2 ]
+[ "malalgebra", 4 ]
[ "mapi", 1 ]
[ "mkey", 1 ]
-[ "mmath", 2 ]
-[ "monettime", 1 ]
+[ "mmath", 3 ]
+[ "monettime", 3 ]
[ "pathfinder", 1 ]
-[ "pcre", 1 ]
+[ "pcre", 2 ]
[ "pf_standoff", 1 ]
-[ "pf_support", 1 ]
+[ "pf_support", 2 ]
[ "pftijah", 1 ]
[ "str", 1 ]
-[ "streams", 1 ]
+[ "streams", 3 ]
[ "sys", 1 ]
[ "trans", 1 ]
[ "xrpc_client", 1 ]
[ "xrpc_server", 1 ]
-[ "xtables", 2 ]
+[ "xtables", 3 ]
dropping module 'pathfinder'
#---------------------------------#
# module usage_count # name
# str int # type
#---------------------------------#
+[ "aggrX3", 1 ]
+[ "alarm", 2 ]
[ "algebra", 1 ]
[ "arith", 1 ]
[ "bat", 1 ]
+[ "bat_arith", 1 ]
[ "builtin", 1 ]
[ "constant", 1 ]
+[ "lock", 2 ]
+[ "logger", 2 ]
[ "main", 1 ]
+[ "malalgebra", 2 ]
+[ "mmath", 1 ]
+[ "monettime", 2 ]
+[ "pcre", 1 ]
+[ "pf_support", 1 ]
[ "str", 1 ]
+[ "streams", 1 ]
[ "sys", 1 ]
[ "trans", 1 ]
+[ "xtables", 1 ]
quit();
Index: createcoll0.milS
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll0.milS,v
retrieving revision 1.3
retrieving revision 1.3.28.1
diff -u -d -r1.3 -r1.3.28.1
--- createcoll0.milS 11 Mar 2007 23:26:38 -0000 1.3
+++ createcoll0.milS 11 Nov 2009 15:07:22 -0000 1.3.28.1
@@ -5,5 +5,5 @@
var path:=getenv("TSTSRCDIR");
# index collection 0
-tj_init_collection("testcoll0",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("testcoll0",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_init_collection_base("testcoll0",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("testcoll0",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
Index: test_lms_or.stable.out
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/test_lms_or.stable.out,v
retrieving revision 1.4
retrieving revision 1.4.8.1
diff -u -d -r1.4 -r1.4.8.1
--- test_lms_or.stable.out 6 Feb 2009 13:02:28 -0000 1.4
+++ test_lms_or.stable.out 11 Nov 2009 15:07:22 -0000 1.4.8.1
@@ -22,7 +22,7 @@
# 12:52:37 >
<?xml version="1.0" encoding="utf-8"?>
-<XQueryResult><node rank="1"><title>Pathfinder and TIJAH</title></node><node
rank="2"><title>Pathfinder</title></node><node
rank="3"><title>TIJAH</title></node><node
rank="4"><title>PF/Tijah</title></node></XQueryResult>
+<XQueryResult><node rank="1"><title>Pathfinder and TIJAH</title></node><node
rank="2"><title>TIJAH</title></node><node
rank="3"><title>Pathfinder</title></node><node
rank="4"><title>PF/Tijah</title></node></XQueryResult>
# 12:52:37 >
# 12:52:37 > Done.
Index: sigs.stable.out
===================================================================
RCS file: /cvsroot/monetdb/pathfinder/modules/pftijah/Tests/sigs.stable.out,v
retrieving revision 1.38
retrieving revision 1.38.4.1
diff -u -d -r1.38 -r1.38.4.1
--- sigs.stable.out 20 May 2009 14:37:58 -0000 1.38
+++ sigs.stable.out 11 Nov 2009 15:07:22 -0000 1.38.4.1
@@ -41,10 +41,12 @@
[ "pf2tijah_node(bit, BAT[oid,str], BAT[oid,oid], BAT[oid,oid], BAT[oid,oid],
BAT[oid,int], BAT[oid,str]) : BAT[oid,oid]"
]
[ "serialize_tijah_opt(BAT[void,BAT], int, BAT[void,oid], BAT[void,oid],
BAT[void,oid], BAT[void,int], BAT[void,lng], BAT[void,dbl], BAT[void,str]) :
BAT[str,str]" ]
[ "set_tailkeysorted(BAT[any,any]) : BAT[any,any]"
]
+[ "splitbat(BAT[void,oid], BAT[oid,any]) : BAT[void,BAT]"
]
[ "tijah_tokenize(str) : str"
]
[ "tijah_tokenize2bat(str) : BAT[void,str]"
]
[ "tj_add2collection(str, BAT[str,str], bit) : void"
]
[ "tj_add2collection(str, str, str, bit) : void"
]
+[ "tj_add2collection_frag(str, str, str, bit) : void"
]
[ "tj_checkHashTable(BAT[oid,str]) : void"
]
[ "tj_chk_dict_hash(BAT[void,str], BAT[void,str]) : void"
]
[ "tj_create_termdb(int, oid) : void"
]
@@ -52,6 +54,7 @@
[ "tj_delete_global() : void"
]
[ "tj_dispose_termdb() : void"
]
[ "tj_init_collection(str, BAT[str,str], BAT[void,str]) : void"
]
+[ "tj_init_collection_base(str, BAT[str,str]) : void"
]
[ "tj_init_global(BAT[str,str]) : void"
]
[ "tj_log(str, int) : void"
]
[ "tj_normalizeTerm(str, str) : str"
]
Index: load_bug2831472.milS
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/load_bug2831472.milS,v
retrieving revision 1.2
retrieving revision 1.2.4.1
diff -u -d -r1.2 -r1.2.4.1
--- load_bug2831472.milS 17 Sep 2009 10:58:47 -0000 1.2
+++ load_bug2831472.milS 11 Nov 2009 15:07:22 -0000 1.2.4.1
@@ -5,5 +5,5 @@
var path:=getenv("TSTSRCDIR");
# index thesis collection
-tj_init_collection("debates",
new(str,str).insert("stemmer","snowball-english"));
-tj_add2collection("debates",path+"/xml-docs/debates.xml","debates.xml",true);
+tj_init_collection_base("debates",
new(str,str).insert("stemmer","snowball-english"));
+tj_add2collection_frag("debates",path+"/xml-docs/debates.xml","debates.xml",true);
Index: createcoll1_frag.milS
===================================================================
RCS file:
/cvsroot/monetdb/pathfinder/modules/pftijah/Tests/createcoll1_frag.milS,v
retrieving revision 1.5
retrieving revision 1.5.16.1
diff -u -d -r1.5 -r1.5.16.1
--- createcoll1_frag.milS 7 May 2008 12:29:26 -0000 1.5
+++ createcoll1_frag.milS 11 Nov 2009 15:07:22 -0000 1.5.16.1
@@ -13,37 +13,33 @@
docs.insert(path+"/xml-docs/dilbert.xml","dilbert.xml");
docs.insert(path+"/xml-docs/dilbert2.xml","dilbert2.xml");
docs.insert(path+"/xml-docs/special.xml","special.xml");
-tj_init_collection("coll1_frag", coll_opt);
-tj_add2collection("coll1_frag",docs,true);
+tj_init_collection_base("coll1_frag", coll_opt);
+tj_add2collection_frag("coll1_frag",docs,true);
# index collection incrementally
-tj_init_collection("coll2_frag", coll_opt);
-tj_add2collection("coll2_frag",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("coll2_frag",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("coll2_frag",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("coll2_frag", coll_opt);
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+tj_add2collection_frag("coll2_frag",path+"/xml-docs/special.xml","special.xml",true);
coll_opt.replace("fragmentSize","60");
# index collection at once
-tj_init_collection("coll1_frag100", coll_opt);
-tj_add2collection("coll1_frag100",docs,true);
+tj_init_collection_base("coll1_frag100", coll_opt);
+tj_add2collection_frag("coll1_frag100",docs,true);
# index collection incrementally
-tj_init_collection("coll2_frag100", coll_opt);
-tj_add2collection("coll2_frag100",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
-tj_add2collection("coll2_frag100",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
-tj_add2collection("coll2_frag100",path+"/xml-docs/special.xml","special.xml",true);
+tj_init_collection_base("coll2_frag100", coll_opt);
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/dilbert.xml","dilbert.xml",true);
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/dilbert2.xml","dilbert2.xml",true);
+tj_add2collection_frag("coll2_frag100",path+"/xml-docs/special.xml","special.xml",true);
# compare indexed collections
-var tids1 := bat(_tj_TermBat("coll1_frag")).sort().reverse();
-var tids2 := bat(_tj_TermBat("coll2_frag")).sort().reverse();
-var tids3 := bat(_tj_TermBat("coll1_frag100")).sort().reverse();
-var tids4 := bat(_tj_TermBat("coll2_frag100")).sort().reverse();
-var coll1 := indexfetchjoin(tids1, bat("tj_coll1_frag_TermIndex"),
bat("tj_coll1_frag_Terms"));
-var coll2 := indexfetchjoin(tids2, bat("tj_coll2_frag_TermIndex"),
bat("tj_coll2_frag_Terms"));
-var coll3 := indexfetchjoin(tids3, bat("tj_coll1_frag100_TermIndex"),
bat("tj_coll1_frag100_Terms"));
-var coll4 := indexfetchjoin(tids4, bat("tj_coll2_frag100_TermIndex"),
bat("tj_coll2_frag100_Terms"));
+var coll1 := bat("tj_coll1_frag_termfreq");
+var coll2 := bat("tj_coll2_frag_termfreq");
+var coll3 := bat("tj_coll1_frag100_termfreq");
+var coll4 := bat("tj_coll2_frag100_termfreq");
diff(coll1,coll2).print();
diff(coll2,coll3).print();
------------------------------------------------------------------------------
Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day
trial. Simplify your report design, integration and deployment - and focus on
what you do best, core application coding. Discover what's new with
Crystal Reports now. http://p.sf.net/sfu/bobj-july
_______________________________________________
Monetdb-pf-checkins mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/monetdb-pf-checkins
