You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@asterixdb.apache.org by bu...@apache.org on 2016/03/28 22:18:46 UTC
[19/51] [partial] incubator-asterixdb git commit: ASTERIXDB-1226:
implement SQL++ core group-by semantics and syntatic sugars.
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_3/dblp-csx-2_3.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_3/dblp-csx-2_3.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_3/dblp-csx-2_3.3.ast
index 90cb49f..1276294 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_3/dblp-csx-2_3.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_3/dblp-csx-2_3.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,244 +67,304 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
FROM [ FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
FROM [ FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
FunctionCall fuzzyjoin.len@1[
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
]
- Variable [ Name=tokensDBLP ]
+ Variable [ Name=$tokensDBLP ]
FunctionCall fuzzyjoin.len@1[
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- Variable [ Name=sim ]
+ Variable [ Name=$idCSX ]
+ Variable [ Name=$sim ]
:=
- Variable [ Name=sim ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$sim ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_4/dblp-csx-2_4.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_4/dblp-csx-2_4.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_4/dblp-csx-2_4.3.ast
index 037d123..5358e91 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_4/dblp-csx-2_4.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_4/dblp-csx-2_4.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,245 +67,310 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensUnrankedDBLP ]
+Let Variable [ Name=$tokensUnrankedDBLP ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedDBLP ]
+ FROM [ Variable [ Name=$tokensUnrankedDBLP ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensUnrankedCSX ]
+Let Variable [ Name=$tokensUnrankedCSX ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedCSX ]
+ FROM [ Variable [ Name=$tokensUnrankedCSX ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedDBLP ]
+ Variable [ Name=$tokensUnrankedDBLP ]
]
- Variable [ Name=tokensDBLP ]
+ Variable [ Name=$tokensDBLP ]
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedCSX ]
+ Variable [ Name=$tokensUnrankedCSX ]
]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- Variable [ Name=sim ]
+ Variable [ Name=$idCSX ]
+ Variable [ Name=$sim ]
:=
- Variable [ Name=sim ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$sim ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.1/dblp-csx-2_5.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.1/dblp-csx-2_5.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.1/dblp-csx-2_5.3.ast
index ed1f277..c925dea 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.1/dblp-csx-2_5.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.1/dblp-csx-2_5.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,253 +67,323 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensUnrankedDBLP ]
+Let Variable [ Name=$tokensUnrankedDBLP ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
-LetVariable [ Name=lenDBLP ]
+Let Variable [ Name=$lenDBLP ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedDBLP ]
+ Variable [ Name=$tokensUnrankedDBLP ]
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedDBLP ]
+ FROM [ Variable [ Name=$tokensUnrankedDBLP ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensUnrankedCSX ]
+Let Variable [ Name=$tokensUnrankedCSX ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
-LetVariable [ Name=lenCSX ]
+Let Variable [ Name=$lenCSX ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedCSX ]
+ Variable [ Name=$tokensUnrankedCSX ]
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedCSX ]
+ FROM [ Variable [ Name=$tokensUnrankedCSX ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$lenDBLP ]
+ Variable [ Name=$tokensDBLP ]
+ Variable [ Name=$lenCSX ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$idCSX ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.2/dblp-csx-2_5.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.2/dblp-csx-2_5.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.2/dblp-csx-2_5.3.ast
index ed1f277..c925dea 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.2/dblp-csx-2_5.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.2/dblp-csx-2_5.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,253 +67,323 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensUnrankedDBLP ]
+Let Variable [ Name=$tokensUnrankedDBLP ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
-LetVariable [ Name=lenDBLP ]
+Let Variable [ Name=$lenDBLP ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedDBLP ]
+ Variable [ Name=$tokensUnrankedDBLP ]
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedDBLP ]
+ FROM [ Variable [ Name=$tokensUnrankedDBLP ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensUnrankedCSX ]
+Let Variable [ Name=$tokensUnrankedCSX ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
-LetVariable [ Name=lenCSX ]
+Let Variable [ Name=$lenCSX ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedCSX ]
+ Variable [ Name=$tokensUnrankedCSX ]
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedCSX ]
+ FROM [ Variable [ Name=$tokensUnrankedCSX ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$lenDBLP ]
+ Variable [ Name=$tokensDBLP ]
+ Variable [ Name=$lenCSX ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$idCSX ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3.1/dblp-csx-2_5.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3.1/dblp-csx-2_5.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3.1/dblp-csx-2_5.3.ast
index 5844826..8ddc7b1 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3.1/dblp-csx-2_5.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3.1/dblp-csx-2_5.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,256 +67,326 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensUnrankedDBLP ]
+Let Variable [ Name=$tokensUnrankedDBLP ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
-LetVariable [ Name=lenDBLP ]
+Let Variable [ Name=$lenDBLP ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedDBLP ]
+ Variable [ Name=$tokensUnrankedDBLP ]
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedDBLP ]
+ FROM [ Variable [ Name=$tokensUnrankedDBLP ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensUnrankedCSX ]
+Let Variable [ Name=$tokensUnrankedCSX ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
-LetVariable [ Name=lenCSX ]
+Let Variable [ Name=$lenCSX ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedCSX ]
+ Variable [ Name=$tokensUnrankedCSX ]
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedCSX ]
+ FROM [ Variable [ Name=$tokensUnrankedCSX ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGroupped ]
+ Variable [ Name=$tokenGroupped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$lenDBLP ]
+ Variable [ Name=$tokensDBLP ]
+ Variable [ Name=$lenCSX ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- Variable [ Name=sim ]
+ Variable [ Name=$idCSX ]
+ Variable [ Name=$sim ]
:=
- Variable [ Name=sim ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$sim ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC
http://git-wip-us.apache.org/repos/asf/incubator-asterixdb/blob/acc12a9b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3/dblp-csx-2_5.3.ast
----------------------------------------------------------------------
diff --git a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3/dblp-csx-2_5.3.ast b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3/dblp-csx-2_5.3.ast
index ed1f277..c925dea 100644
--- a/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3/dblp-csx-2_5.3.ast
+++ b/asterix-app/src/test/resources/runtimets/results_parser_sqlpp/fuzzyjoin/dblp-csx-2_5.3/dblp-csx-2_5.3.ast
@@ -6,18 +6,18 @@ RecordConstructor [
(
LiteralExpr [STRING] [idDBLP]
:
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
)
(
LiteralExpr [STRING] [idCSX]
:
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
)
(
LiteralExpr [STRING] [sim]
:
IndexAccessor [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
Index: LiteralExpr [LONG] [0]
]
)
@@ -27,7 +27,7 @@ FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -44,13 +44,13 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
,
FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [CSX]
]
AS
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
,
FunctionCall fuzzyjoin.subset-collection@3[
FunctionCall Metadata.dataset@1[
@@ -67,253 +67,323 @@ FROM [ FunctionCall Metadata.dataset@1[
]
]
AS
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
-LetVariable [ Name=idDBLP ]
+Let Variable [ Name=$idDBLP ]
:=
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=id
]
-LetVariable [ Name=tokensUnrankedDBLP ]
+Let Variable [ Name=$tokensUnrankedDBLP ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperDBLP ]
+ Variable [ Name=$paperDBLP ]
Field=title
]
]
-LetVariable [ Name=lenDBLP ]
+Let Variable [ Name=$lenDBLP ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedDBLP ]
+ Variable [ Name=$tokensUnrankedDBLP ]
]
-LetVariable [ Name=tokensDBLP ]
+Let Variable [ Name=$tokensDBLP ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedDBLP ]
+ FROM [ Variable [ Name=$tokensUnrankedDBLP ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#1 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#2 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#1 ]
+ AS
+ Variable [ Name=#2 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=idCSX ]
+Let Variable [ Name=$idCSX ]
:=
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=id
]
-LetVariable [ Name=tokensUnrankedCSX ]
+Let Variable [ Name=$tokensUnrankedCSX ]
:=
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paperCSX ]
+ Variable [ Name=$paperCSX ]
Field=title
]
]
-LetVariable [ Name=lenCSX ]
+Let Variable [ Name=$lenCSX ]
:=
FunctionCall fuzzyjoin.len@1[
- Variable [ Name=tokensUnrankedCSX ]
+ Variable [ Name=$tokensUnrankedCSX ]
]
-LetVariable [ Name=tokensCSX ]
+Let Variable [ Name=$tokensCSX ]
:=
(
SELECT ELEMENT [
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
- FROM [ Variable [ Name=tokensUnrankedCSX ]
+ FROM [ Variable [ Name=$tokensUnrankedCSX ]
AS
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
,
(
SELECT ELEMENT [
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
]
FROM [ FunctionCall Metadata.dataset@1[
LiteralExpr [STRING] [DBLP]
]
AS
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
,
FunctionCall fuzzyjoin.counthashed-word-tokens@1[
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=title
]
]
AS
- Variable [ Name=token ]
+ Variable [ Name=$token ]
]
- LetVariable [ Name=id ]
+ Let Variable [ Name=$id ]
:=
FieldAccessor [
- Variable [ Name=paper ]
+ Variable [ Name=$paper ]
Field=id
]
Groupby
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
:=
- Variable [ Name=token ]
- With
- Variable [ Name=id ]
- Variable [ Name=paper ]
- Variable [ Name=token ]
- Variable [ Name=tokenUnranked ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$token ]
+ GROUP AS
+ Variable [ Name=#3 ]
+ (
+ Variable [ Name=$id ]
+ AS id
+ Variable [ Name=$token ]
+ AS token
+ Variable [ Name=$paper ]
+ AS paper
+ Variable [ Name=$tokenUnranked ]
+ AS tokenUnranked
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
FunctionCall fuzzyjoin.count@1[
- Variable [ Name=id ]
+ (
+ SELECT ELEMENT [
+ FieldAccessor [
+ Variable [ Name=#4 ]
+ Field=id
+ ]
+ ]
+ FROM [ Variable [ Name=#3 ]
+ AS
+ Variable [ Name=#4 ]
+ ]
+ )
]
ASC
- Variable [ Name=tokenGrouped ]
+ Variable [ Name=$tokenGrouped ]
ASC
)
AS
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
AT
- Variable [ Name=i ]
+ Variable [ Name=$i ]
]
Where
OperatorExpr [
- Variable [ Name=tokenUnranked ]
+ Variable [ Name=$tokenUnranked ]
=
- Variable [ Name=tokenRanked ]
+ Variable [ Name=$tokenRanked ]
]
Orderby
- Variable [ Name=i ]
+ Variable [ Name=$i ]
ASC
)
-LetVariable [ Name=sim ]
+Let Variable [ Name=$sim ]
:=
FunctionCall fuzzyjoin.similarity-jaccard-prefix@6[
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$lenDBLP ]
+ Variable [ Name=$tokensDBLP ]
+ Variable [ Name=$lenCSX ]
+ Variable [ Name=$tokensCSX ]
+ Variable [ Name=$prefixTokenDBLP ]
LiteralExpr [FLOAT] [0.5]
]
Where
OperatorExpr [
OperatorExpr [
- Variable [ Name=prefixTokenDBLP ]
+ Variable [ Name=$prefixTokenDBLP ]
=
- Variable [ Name=prefixTokenCSX ]
+ Variable [ Name=$prefixTokenCSX ]
]
and
OperatorExpr [
- Variable [ Name=sim ]
+ Variable [ Name=$sim ]
>=
LiteralExpr [FLOAT] [0.5]
]
]
Groupby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
:=
- Variable [ Name=idDBLP ]
- Variable [ Name=idCSX ]
+ Variable [ Name=$idDBLP ]
+ Variable [ Name=$idCSX ]
:=
- Variable [ Name=idCSX ]
- With
- Variable [ Name=sim ]
- Variable [ Name=tokensCSX ]
- Variable [ Name=lenCSX ]
- Variable [ Name=tokensUnrankedCSX ]
- Variable [ Name=idCSX ]
- Variable [ Name=tokensDBLP ]
- Variable [ Name=lenDBLP ]
- Variable [ Name=tokensUnrankedDBLP ]
- Variable [ Name=idDBLP ]
- Variable [ Name=paperDBLP ]
- Variable [ Name=prefixTokenDBLP ]
- Variable [ Name=prefixTokenCSX ]
- Variable [ Name=paperCSX ]
+ Variable [ Name=$idCSX ]
+ GROUP AS
+ Variable [ Name=#5 ]
+ (
+ Variable [ Name=$sim ]
+ AS sim
+ Variable [ Name=$tokensCSX ]
+ AS tokensCSX
+ Variable [ Name=$lenCSX ]
+ AS lenCSX
+ Variable [ Name=$tokensUnrankedCSX ]
+ AS tokensUnrankedCSX
+ Variable [ Name=$idCSX ]
+ AS idCSX
+ Variable [ Name=$tokensDBLP ]
+ AS tokensDBLP
+ Variable [ Name=$lenDBLP ]
+ AS lenDBLP
+ Variable [ Name=$tokensUnrankedDBLP ]
+ AS tokensUnrankedDBLP
+ Variable [ Name=$idDBLP ]
+ AS idDBLP
+ Variable [ Name=$prefixTokenCSX ]
+ AS prefixTokenCSX
+ Variable [ Name=$paperCSX ]
+ AS paperCSX
+ Variable [ Name=$prefixTokenDBLP ]
+ AS prefixTokenDBLP
+ Variable [ Name=$paperDBLP ]
+ AS paperDBLP
+ )
Orderby
- Variable [ Name=idDBLP ]
+ Variable [ Name=$idDBLP ]
ASC
- Variable [ Name=idCSX ]
+ Variable [ Name=$idCSX ]
ASC