forked from dkpro/dkpro-core
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request dkpro#1383 from dkpro/bugfix/1381-Annotations-star…
…ting-ending-in-inter-token-space-cause-exception dkpro#1381 - Annotations starting/ending in inter-token space cause exception
- Loading branch information
Showing
10 changed files
with
173 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
7 changes: 7 additions & 0 deletions
7
...banno-asl/src/test/resources/tsv3-suite/testAnnotationWithLeadingWhitespace/reference.tsv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
#FORMAT=WebAnno TSV 3.2 | ||
#T_SP=de.tudarmstadt.ukp.dkpro.core.api.ner.type.NamedEntity|identifier|value | ||
|
||
|
||
#Text=one two | ||
1-1 0-3 one _ _ | ||
1-2 5-8 two * * |
10 changes: 10 additions & 0 deletions
10
...banno-asl/src/test/resources/tsv3-suite/testAnnotationWithLeadingWhitespace/reference.xmi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
<?xml version="1.0" encoding="UTF-8"?><xmi:XMI xmlns:pos="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos.ecore" xmlns:tcas="http:///uima/tcas.ecore" xmlns:xmi="http://www.omg.org/XMI" xmlns:cas="http:///uima/cas.ecore" xmlns:tweet="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos/tweet.ecore" xmlns:morph="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/morph.ecore" xmlns:dependency="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/dependency.ecore" xmlns:type6="http:///de/tudarmstadt/ukp/dkpro/core/api/semantics/type.ecore" xmlns:type="http:///de/tudarmstadt/ukp/dkpro/core/api/anomaly/type.ecore" xmlns:type7="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type.ecore" xmlns:type3="http:///de/tudarmstadt/ukp/dkpro/core/api/metadata/type.ecore" xmlns:type4="http:///de/tudarmstadt/ukp/dkpro/core/api/ner/type.ecore" xmlns:type5="http:///de/tudarmstadt/ukp/dkpro/core/api/segmentation/type.ecore" xmlns:type2="http:///de/tudarmstadt/ukp/dkpro/core/api/coref/type.ecore" xmlns:constituent="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/constituent.ecore" xmlns:chunk="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/chunk.ecore" xmi:version="2.0"> | ||
<cas:NULL xmi:id="0"/> | ||
<type3:DocumentMetaData xmi:id="1" sofa="12" begin="0" end="8" documentId="doc" isLastSegment="false"/> | ||
<type5:Token xmi:id="19" sofa="12" begin="0" end="3" order="0"/> | ||
<type5:Token xmi:id="32" sofa="12" begin="5" end="8" order="0"/> | ||
<type5:Sentence xmi:id="45" sofa="12" begin="0" end="8"/> | ||
<type4:NamedEntity xmi:id="50" sofa="12" begin="4" end="8"/> | ||
<cas:Sofa xmi:id="12" sofaNum="1" sofaID="_InitialView" mimeType="text" sofaString="one two"/> | ||
<cas:View sofa="12" members="1 19 32 45 50"/> | ||
</xmi:XMI> |
7 changes: 7 additions & 0 deletions
7
...sl/src/test/resources/tsv3-suite/testAnnotationWithLeadingWhitespaceAtStart/reference.tsv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
#FORMAT=WebAnno TSV 3.2 | ||
#T_SP=de.tudarmstadt.ukp.dkpro.core.api.ner.type.NamedEntity|identifier|value | ||
|
||
|
||
#Text=one two | ||
1-1 1-4 one * * | ||
1-2 5-8 two _ _ |
10 changes: 10 additions & 0 deletions
10
...sl/src/test/resources/tsv3-suite/testAnnotationWithLeadingWhitespaceAtStart/reference.xmi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
<?xml version="1.0" encoding="UTF-8"?><xmi:XMI xmlns:pos="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos.ecore" xmlns:tcas="http:///uima/tcas.ecore" xmlns:xmi="http://www.omg.org/XMI" xmlns:cas="http:///uima/cas.ecore" xmlns:tweet="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos/tweet.ecore" xmlns:morph="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/morph.ecore" xmlns:dependency="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/dependency.ecore" xmlns:type6="http:///de/tudarmstadt/ukp/dkpro/core/api/semantics/type.ecore" xmlns:type="http:///de/tudarmstadt/ukp/dkpro/core/api/anomaly/type.ecore" xmlns:type7="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type.ecore" xmlns:type3="http:///de/tudarmstadt/ukp/dkpro/core/api/metadata/type.ecore" xmlns:type4="http:///de/tudarmstadt/ukp/dkpro/core/api/ner/type.ecore" xmlns:type5="http:///de/tudarmstadt/ukp/dkpro/core/api/segmentation/type.ecore" xmlns:type2="http:///de/tudarmstadt/ukp/dkpro/core/api/coref/type.ecore" xmlns:constituent="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/constituent.ecore" xmlns:chunk="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/chunk.ecore" xmi:version="2.0"> | ||
<cas:NULL xmi:id="0"/> | ||
<type3:DocumentMetaData xmi:id="1" sofa="12" begin="0" end="8" documentId="doc" isLastSegment="false"/> | ||
<type5:Token xmi:id="19" sofa="12" begin="1" end="4" order="0"/> | ||
<type5:Token xmi:id="32" sofa="12" begin="5" end="8" order="0"/> | ||
<type5:Sentence xmi:id="45" sofa="12" begin="1" end="8"/> | ||
<type4:NamedEntity xmi:id="50" sofa="12" begin="0" end="4"/> | ||
<cas:Sofa xmi:id="12" sofaNum="1" sofaID="_InitialView" mimeType="text" sofaString=" one two"/> | ||
<cas:View sofa="12" members="1 19 32 45 50"/> | ||
</xmi:XMI> |
7 changes: 7 additions & 0 deletions
7
...anno-asl/src/test/resources/tsv3-suite/testAnnotationWithTrailingWhitespace/reference.tsv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
#FORMAT=WebAnno TSV 3.2 | ||
#T_SP=de.tudarmstadt.ukp.dkpro.core.api.ner.type.NamedEntity|identifier|value | ||
|
||
|
||
#Text=one two | ||
1-1 0-3 one * * | ||
1-2 5-8 two _ _ |
10 changes: 10 additions & 0 deletions
10
...anno-asl/src/test/resources/tsv3-suite/testAnnotationWithTrailingWhitespace/reference.xmi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
<?xml version="1.0" encoding="UTF-8"?><xmi:XMI xmlns:pos="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos.ecore" xmlns:tcas="http:///uima/tcas.ecore" xmlns:xmi="http://www.omg.org/XMI" xmlns:cas="http:///uima/cas.ecore" xmlns:tweet="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos/tweet.ecore" xmlns:morph="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/morph.ecore" xmlns:dependency="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/dependency.ecore" xmlns:type6="http:///de/tudarmstadt/ukp/dkpro/core/api/semantics/type.ecore" xmlns:type="http:///de/tudarmstadt/ukp/dkpro/core/api/anomaly/type.ecore" xmlns:type7="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type.ecore" xmlns:type3="http:///de/tudarmstadt/ukp/dkpro/core/api/metadata/type.ecore" xmlns:type4="http:///de/tudarmstadt/ukp/dkpro/core/api/ner/type.ecore" xmlns:type5="http:///de/tudarmstadt/ukp/dkpro/core/api/segmentation/type.ecore" xmlns:type2="http:///de/tudarmstadt/ukp/dkpro/core/api/coref/type.ecore" xmlns:constituent="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/constituent.ecore" xmlns:chunk="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/chunk.ecore" xmi:version="2.0"> | ||
<cas:NULL xmi:id="0"/> | ||
<type3:DocumentMetaData xmi:id="1" sofa="12" begin="0" end="8" documentId="doc" isLastSegment="false"/> | ||
<type5:Token xmi:id="19" sofa="12" begin="0" end="3" order="0"/> | ||
<type5:Token xmi:id="32" sofa="12" begin="5" end="8" order="0"/> | ||
<type5:Sentence xmi:id="45" sofa="12" begin="0" end="8"/> | ||
<type4:NamedEntity xmi:id="50" sofa="12" begin="0" end="4"/> | ||
<cas:Sofa xmi:id="12" sofaNum="1" sofaID="_InitialView" mimeType="text" sofaString="one two"/> | ||
<cas:View sofa="12" members="1 19 32 45 50"/> | ||
</xmi:XMI> |
7 changes: 7 additions & 0 deletions
7
...asl/src/test/resources/tsv3-suite/testAnnotationWithTrailingWhitespaceAtEnd/reference.tsv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
#FORMAT=WebAnno TSV 3.2 | ||
#T_SP=de.tudarmstadt.ukp.dkpro.core.api.ner.type.NamedEntity|identifier|value | ||
|
||
|
||
#Text=one two | ||
1-1 0-3 one _ _ | ||
1-2 4-7 two * * |
10 changes: 10 additions & 0 deletions
10
...asl/src/test/resources/tsv3-suite/testAnnotationWithTrailingWhitespaceAtEnd/reference.xmi
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
<?xml version="1.0" encoding="UTF-8"?><xmi:XMI xmlns:pos="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos.ecore" xmlns:tcas="http:///uima/tcas.ecore" xmlns:xmi="http://www.omg.org/XMI" xmlns:cas="http:///uima/cas.ecore" xmlns:tweet="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/pos/tweet.ecore" xmlns:morph="http:///de/tudarmstadt/ukp/dkpro/core/api/lexmorph/type/morph.ecore" xmlns:dependency="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/dependency.ecore" xmlns:type6="http:///de/tudarmstadt/ukp/dkpro/core/api/semantics/type.ecore" xmlns:type="http:///de/tudarmstadt/ukp/dkpro/core/api/anomaly/type.ecore" xmlns:type7="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type.ecore" xmlns:type3="http:///de/tudarmstadt/ukp/dkpro/core/api/metadata/type.ecore" xmlns:type4="http:///de/tudarmstadt/ukp/dkpro/core/api/ner/type.ecore" xmlns:type5="http:///de/tudarmstadt/ukp/dkpro/core/api/segmentation/type.ecore" xmlns:type2="http:///de/tudarmstadt/ukp/dkpro/core/api/coref/type.ecore" xmlns:constituent="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/constituent.ecore" xmlns:chunk="http:///de/tudarmstadt/ukp/dkpro/core/api/syntax/type/chunk.ecore" xmi:version="2.0"> | ||
<cas:NULL xmi:id="0"/> | ||
<type3:DocumentMetaData xmi:id="1" sofa="12" begin="0" end="8" documentId="doc" isLastSegment="false"/> | ||
<type5:Token xmi:id="19" sofa="12" begin="0" end="3" order="0"/> | ||
<type5:Token xmi:id="32" sofa="12" begin="4" end="7" order="0"/> | ||
<type5:Sentence xmi:id="45" sofa="12" begin="0" end="7"/> | ||
<type4:NamedEntity xmi:id="50" sofa="12" begin="4" end="8"/> | ||
<cas:Sofa xmi:id="12" sofaNum="1" sofaID="_InitialView" mimeType="text" sofaString="one two "/> | ||
<cas:View sofa="12" members="1 19 32 45 50"/> | ||
</xmi:XMI> |