You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ctakes.apache.org by mm...@apache.org on 2016/12/16 03:55:38 UTC
svn commit: r1774552 [8/11] - in /ctakes/trunk:
ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/util/
ctakes-regression-test/desc/analysis_engine/
ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/
Modified: ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/edge_cases_plaintext_1.txt.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/edge_cases_plaintext_1.txt.xml?rev=1774552&r1=1774551&r2=1774552&view=diff
==============================================================================
--- ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/edge_cases_plaintext_1.txt.xml (original)
+++ ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/edge_cases_plaintext_1.txt.xml Fri Dec 16 03:55:37 2016
@@ -7,54 +7,54 @@
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="27" _ref_sofa="3" begin="55" end="117" sentenceNumber="1"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="33" _ref_sofa="3" begin="118" end="149" sentenceNumber="2"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="39" _ref_sofa="3" begin="151" end="210" sentenceNumber="3"/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="45" _ref_sofa="3" begin="117" end="118" tokenNumber="25" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="53" _ref_sofa="3" begin="0" end="7" tokenNumber="0" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="patient"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="65" _ref_sofa="3" begin="8" end="18" tokenNumber="1" normalizedForm="complain" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="complain"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="77" _ref_sofa="3" begin="19" end="23" tokenNumber="2" normalizedForm="that" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="that"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="45" _ref_sofa="3" begin="117" end="118" tokenNumber="25"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="53" _ref_sofa="3" begin="0" end="7" tokenNumber="0" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="65" _ref_sofa="3" begin="8" end="18" tokenNumber="1" normalizedForm="complained" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="77" _ref_sofa="3" begin="19" end="23" tokenNumber="2" normalizedForm="that" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="89" _ref_sofa="3" begin="24" end="27" tokenNumber="3" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="109" _ref_sofa="3" begin="31" end="34" tokenNumber="5" normalizedForm="ion" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="ion"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="121" _ref_sofa="3" begin="35" end="38" tokenNumber="6" normalizedForm="did" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="did"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="141" _ref_sofa="3" begin="42" end="46" tokenNumber="8" normalizedForm="make" partOfSpeech="VB" capitalization="0" numPosition="0" canonicalForm="make"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="153" _ref_sofa="3" begin="47" end="52" tokenNumber="9" normalizedForm="sense" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="sense"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="173" _ref_sofa="3" begin="55" end="59" tokenNumber="11" normalizedForm="thi" partOfSpeech="DT" capitalization="1" numPosition="0" canonicalForm="thi"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="185" _ref_sofa="3" begin="60" end="62" tokenNumber="12" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="is"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="197" _ref_sofa="3" begin="63" end="64" tokenNumber="13" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="209" _ref_sofa="3" begin="65" end="69" tokenNumber="14" normalizedForm="test" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="test"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="109" _ref_sofa="3" begin="31" end="34" tokenNumber="5" normalizedForm="ion" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="121" _ref_sofa="3" begin="35" end="38" tokenNumber="6" normalizedForm="did" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="141" _ref_sofa="3" begin="42" end="46" tokenNumber="8" normalizedForm="make" partOfSpeech="VB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="153" _ref_sofa="3" begin="47" end="52" tokenNumber="9" normalizedForm="sense" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="173" _ref_sofa="3" begin="55" end="59" tokenNumber="11" normalizedForm="This" partOfSpeech="DT" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="185" _ref_sofa="3" begin="60" end="62" tokenNumber="12" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="197" _ref_sofa="3" begin="63" end="64" tokenNumber="13" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="209" _ref_sofa="3" begin="65" end="69" tokenNumber="14" normalizedForm="test" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="221" _ref_sofa="3" begin="70" end="72" tokenNumber="15" normalizedForm="of" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="233" _ref_sofa="3" begin="73" end="75" tokenNumber="16" normalizedForm="an" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="an"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="245" _ref_sofa="3" begin="76" end="80" tokenNumber="17" normalizedForm="edge" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="edge"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="257" _ref_sofa="3" begin="81" end="85" tokenNumber="18" normalizedForm="case" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="case"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="233" _ref_sofa="3" begin="73" end="75" tokenNumber="16" normalizedForm="an" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="245" _ref_sofa="3" begin="76" end="80" tokenNumber="17" normalizedForm="edge" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="257" _ref_sofa="3" begin="81" end="85" tokenNumber="18" normalizedForm="case" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="269" _ref_sofa="3" begin="86" end="88" tokenNumber="19" normalizedForm="in" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="281" _ref_sofa="3" begin="89" end="100" tokenNumber="20" normalizedForm="contraction" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="contraction"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="281" _ref_sofa="3" begin="89" end="100" tokenNumber="20" normalizedForm="contraction" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="293" _ref_sofa="3" begin="101" end="103" tokenNumber="21" normalizedForm="in" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="305" _ref_sofa="3" begin="104" end="107" tokenNumber="22" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="317" _ref_sofa="3" begin="108" end="116" tokenNumber="23" normalizedForm="tokezi" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="tokezi"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="337" _ref_sofa="3" begin="118" end="125" tokenNumber="26" normalizedForm="aspirin" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="aspirin"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="349" _ref_sofa="3" begin="126" end="135" tokenNumber="27" normalizedForm="decreas" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="decreas"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="361" _ref_sofa="3" begin="136" end="140" tokenNumber="28" normalizedForm="from" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="from"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="399" _ref_sofa="3" begin="146" end="148" tokenNumber="32" normalizedForm="pm" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="pm"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="419" _ref_sofa="3" begin="151" end="155" tokenNumber="34" normalizedForm="thi" partOfSpeech="DT" capitalization="1" numPosition="0" canonicalForm="thi"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="431" _ref_sofa="3" begin="156" end="160" tokenNumber="35" normalizedForm="use" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="use"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="317" _ref_sofa="3" begin="108" end="116" tokenNumber="23" normalizedForm="tokezier" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="337" _ref_sofa="3" begin="118" end="125" tokenNumber="26" normalizedForm="aspirin" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="349" _ref_sofa="3" begin="126" end="135" tokenNumber="27" normalizedForm="decreased" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="361" _ref_sofa="3" begin="136" end="140" tokenNumber="28" normalizedForm="from" partOfSpeech="IN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="399" _ref_sofa="3" begin="146" end="148" tokenNumber="32" normalizedForm="PM" partOfSpeech="NN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="419" _ref_sofa="3" begin="151" end="155" tokenNumber="34" normalizedForm="This" partOfSpeech="DT" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="431" _ref_sofa="3" begin="156" end="160" tokenNumber="35" normalizedForm="used" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="443" _ref_sofa="3" begin="161" end="163" tokenNumber="36" normalizedForm="to" partOfSpeech="TO" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="455" _ref_sofa="3" begin="164" end="169" tokenNumber="37" normalizedForm="cause" partOfSpeech="VB" capitalization="0" numPosition="0" canonicalForm="cause"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="455" _ref_sofa="3" begin="164" end="169" tokenNumber="37" normalizedForm="cause" partOfSpeech="VB" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="467" _ref_sofa="3" begin="170" end="173" tokenNumber="38" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="479" _ref_sofa="3" begin="174" end="178" tokenNumber="39" normalizedForm="drug" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="drug"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="491" _ref_sofa="3" begin="179" end="182" tokenNumber="40" normalizedForm="ner" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="ner"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="479" _ref_sofa="3" begin="174" end="178" tokenNumber="39" normalizedForm="drug" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="491" _ref_sofa="3" begin="179" end="182" tokenNumber="40" normalizedForm="ner" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="503" _ref_sofa="3" begin="183" end="185" tokenNumber="41" normalizedForm="to" partOfSpeech="TO" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="515" _ref_sofa="3" begin="186" end="188" tokenNumber="42" normalizedForm="go" partOfSpeech="VB" capitalization="0" numPosition="0" canonicalForm="go"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="527" _ref_sofa="3" begin="189" end="193" tokenNumber="43" normalizedForm="into" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="into"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="539" _ref_sofa="3" begin="194" end="196" tokenNumber="44" normalizedForm="an" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="an"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="551" _ref_sofa="3" begin="197" end="204" tokenNumber="45" normalizedForm="infinte" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="infinte"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="563" _ref_sofa="3" begin="205" end="209" tokenNumber="46" normalizedForm="loop" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="loop"/>
- <org.apache.ctakes.typesystem.type.syntax.ContractionToken _indexed="1" _id="101" _ref_sofa="3" begin="28" end="31" tokenNumber="4" normalizedForm="n't" partOfSpeech="RB"/>
- <org.apache.ctakes.typesystem.type.syntax.ContractionToken _indexed="1" _id="133" _ref_sofa="3" begin="38" end="41" tokenNumber="7" normalizedForm="n't" partOfSpeech="RB"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="165" _ref_sofa="3" begin="52" end="53" tokenNumber="10" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="329" _ref_sofa="3" begin="116" end="117" tokenNumber="24" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="382" _ref_sofa="3" begin="142" end="143" tokenNumber="30" normalizedForm=":" partOfSpeech=":"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="411" _ref_sofa="3" begin="148" end="149" tokenNumber="33" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="575" _ref_sofa="3" begin="209" end="210" tokenNumber="47" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="373" _ref_sofa="3" begin="141" end="142" tokenNumber="29" normalizedForm="2" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="390" _ref_sofa="3" begin="143" end="145" tokenNumber="31" normalizedForm="00" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="515" _ref_sofa="3" begin="186" end="188" tokenNumber="42" normalizedForm="go" partOfSpeech="VB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="527" _ref_sofa="3" begin="189" end="193" tokenNumber="43" normalizedForm="into" partOfSpeech="IN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="539" _ref_sofa="3" begin="194" end="196" tokenNumber="44" normalizedForm="an" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="551" _ref_sofa="3" begin="197" end="204" tokenNumber="45" normalizedForm="infinte" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="563" _ref_sofa="3" begin="205" end="209" tokenNumber="46" normalizedForm="loop" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.ContractionToken _indexed="1" _id="101" _ref_sofa="3" begin="28" end="31" tokenNumber="4" partOfSpeech="RB"/>
+ <org.apache.ctakes.typesystem.type.syntax.ContractionToken _indexed="1" _id="133" _ref_sofa="3" begin="38" end="41" tokenNumber="7" partOfSpeech="RB"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="165" _ref_sofa="3" begin="52" end="53" tokenNumber="10" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="329" _ref_sofa="3" begin="116" end="117" tokenNumber="24" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="382" _ref_sofa="3" begin="142" end="143" tokenNumber="30" partOfSpeech=":"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="411" _ref_sofa="3" begin="148" end="149" tokenNumber="33" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="575" _ref_sofa="3" begin="209" end="210" tokenNumber="47" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="373" _ref_sofa="3" begin="141" end="142" tokenNumber="29" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="390" _ref_sofa="3" begin="143" end="145" tokenNumber="31" partOfSpeech="CD" numType="1"/>
<org.apache.ctakes.typesystem.type.textsem.RomanNumeralAnnotation _indexed="1" _id="583" _ref_sofa="3" begin="35" end="38" id="0" typeID="0" segmentID="SIMPLE_SEGMENT" discoveryTechnique="0" confidence="0.0" polarity="0" uncertainty="0" conditional="false" generic="false" historyOf="0"/>
<org.apache.ctakes.typesystem.type.syntax.NP _indexed="1" _id="601" _ref_sofa="3" begin="0" end="7" chunkType="NP"/>
<org.apache.ctakes.typesystem.type.syntax.NP _indexed="1" _id="616" _ref_sofa="3" begin="24" end="34" chunkType="NP"/>
Modified: ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note.xml?rev=1774552&r1=1774551&r2=1774552&view=diff
==============================================================================
--- ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note.xml (original)
+++ ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note.xml Fri Dec 16 03:55:37 2016
@@ -10,72 +10,72 @@
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="45" _ref_sofa="3" begin="194" end="253" sentenceNumber="4"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="51" _ref_sofa="3" begin="254" end="268" sentenceNumber="5"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="57" _ref_sofa="3" begin="269" end="296" sentenceNumber="6"/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="63" _ref_sofa="3" begin="22" end="23" tokenNumber="5" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="71" _ref_sofa="3" begin="165" end="166" tokenNumber="32" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="79" _ref_sofa="3" begin="166" end="167" tokenNumber="33" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="87" _ref_sofa="3" begin="193" end="194" tokenNumber="42" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="95" _ref_sofa="3" begin="253" end="254" tokenNumber="56" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="103" _ref_sofa="3" begin="268" end="269" tokenNumber="61" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="111" _ref_sofa="3" begin="296" end="297" tokenNumber="65" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="119" _ref_sofa="3" begin="0" end="10" tokenNumber="0" normalizedForm="impression" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="impression"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="139" _ref_sofa="3" begin="11" end="17" tokenNumber="2" normalizedForm="report" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="report"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="159" _ref_sofa="3" begin="18" end="22" tokenNumber="4" normalizedForm="plan" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="plan"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="63" _ref_sofa="3" begin="22" end="23" tokenNumber="5"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="71" _ref_sofa="3" begin="165" end="166" tokenNumber="32"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="79" _ref_sofa="3" begin="166" end="167" tokenNumber="33"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="87" _ref_sofa="3" begin="193" end="194" tokenNumber="42"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="95" _ref_sofa="3" begin="253" end="254" tokenNumber="56"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="103" _ref_sofa="3" begin="268" end="269" tokenNumber="61"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="111" _ref_sofa="3" begin="296" end="297" tokenNumber="65"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="119" _ref_sofa="3" begin="0" end="10" tokenNumber="0" normalizedForm="IMPRESSION" partOfSpeech="NN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="139" _ref_sofa="3" begin="11" end="17" tokenNumber="2" normalizedForm="REPORT" partOfSpeech="NN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="159" _ref_sofa="3" begin="18" end="22" tokenNumber="4" normalizedForm="PLAN" partOfSpeech="NN" capitalization="3" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="171" _ref_sofa="3" begin="23" end="26" tokenNumber="6" normalizedForm="The" partOfSpeech="DT" capitalization="1" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="183" _ref_sofa="3" begin="27" end="34" tokenNumber="7" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="patient"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="195" _ref_sofa="3" begin="35" end="38" tokenNumber="8" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="has"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="207" _ref_sofa="3" begin="39" end="43" tokenNumber="9" normalizedForm="very" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="very"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="219" _ref_sofa="3" begin="44" end="51" tokenNumber="10" normalizedForm="typical" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="typical"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="231" _ref_sofa="3" begin="52" end="59" tokenNumber="11" normalizedForm="history" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="history"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="183" _ref_sofa="3" begin="27" end="34" tokenNumber="7" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="195" _ref_sofa="3" begin="35" end="38" tokenNumber="8" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="207" _ref_sofa="3" begin="39" end="43" tokenNumber="9" normalizedForm="very" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="219" _ref_sofa="3" begin="44" end="51" tokenNumber="10" normalizedForm="typical" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="231" _ref_sofa="3" begin="52" end="59" tokenNumber="11" normalizedForm="history" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="243" _ref_sofa="3" begin="60" end="63" tokenNumber="12" normalizedForm="for" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="255" _ref_sofa="3" begin="64" end="76" tokenNumber="13" normalizedForm="claudication" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="claudication"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="275" _ref_sofa="3" begin="78" end="81" tokenNumber="15" normalizedForm="yet" partOfSpeech="IN" capitalization="1" numPosition="0" canonicalForm="yet"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="255" _ref_sofa="3" begin="64" end="76" tokenNumber="13" normalizedForm="claudication" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="275" _ref_sofa="3" begin="78" end="81" tokenNumber="15" normalizedForm="Yet" partOfSpeech="IN" capitalization="1" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="287" _ref_sofa="3" begin="82" end="85" tokenNumber="16" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="299" _ref_sofa="3" begin="86" end="93" tokenNumber="17" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="patient"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="311" _ref_sofa="3" begin="94" end="98" tokenNumber="18" normalizedForm="doe" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="doe"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="323" _ref_sofa="3" begin="99" end="102" tokenNumber="19" normalizedForm="not" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="not"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="335" _ref_sofa="3" begin="103" end="107" tokenNumber="20" normalizedForm="have" partOfSpeech="VB" capitalization="0" numPosition="0" canonicalForm="have"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="347" _ref_sofa="3" begin="108" end="111" tokenNumber="21" normalizedForm="any" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="any"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="359" _ref_sofa="3" begin="112" end="123" tokenNumber="22" normalizedForm="significant" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="significant"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="371" _ref_sofa="3" begin="124" end="129" tokenNumber="23" normalizedForm="bruit" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="bruit"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="383" _ref_sofa="3" begin="130" end="132" tokenNumber="24" normalizedForm="at" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="at"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="299" _ref_sofa="3" begin="86" end="93" tokenNumber="17" normalizedForm="patient" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="311" _ref_sofa="3" begin="94" end="98" tokenNumber="18" normalizedForm="does" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="323" _ref_sofa="3" begin="99" end="102" tokenNumber="19" normalizedForm="not" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="335" _ref_sofa="3" begin="103" end="107" tokenNumber="20" normalizedForm="have" partOfSpeech="VB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="347" _ref_sofa="3" begin="108" end="111" tokenNumber="21" normalizedForm="any" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="359" _ref_sofa="3" begin="112" end="123" tokenNumber="22" normalizedForm="significant" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="371" _ref_sofa="3" begin="124" end="129" tokenNumber="23" normalizedForm="bruit" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="383" _ref_sofa="3" begin="130" end="132" tokenNumber="24" normalizedForm="at" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="395" _ref_sofa="3" begin="133" end="136" tokenNumber="25" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="407" _ref_sofa="3" begin="137" end="143" tokenNumber="26" normalizedForm="pelvic" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="pelvic"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="419" _ref_sofa="3" begin="144" end="148" tokenNumber="27" normalizedForm="area" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="area"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="439" _ref_sofa="3" begin="150" end="159" tokenNumber="29" normalizedForm="abdominal" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="abdominal"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="451" _ref_sofa="3" begin="160" end="164" tokenNumber="30" normalizedForm="area" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="area"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="471" _ref_sofa="3" begin="167" end="174" tokenNumber="34" normalizedForm="aspirin" partOfSpeech="NNP" capitalization="1" numPosition="0" canonicalForm="aspirin"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="500" _ref_sofa="3" begin="179" end="181" tokenNumber="37" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="mg"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="512" _ref_sofa="3" begin="182" end="186" tokenNumber="38" normalizedForm="once" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="once"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="532" _ref_sofa="3" begin="187" end="192" tokenNumber="40" normalizedForm="a-day" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="a-day"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="552" _ref_sofa="3" begin="194" end="203" tokenNumber="43" normalizedForm="ibuprofen" partOfSpeech="NNP" capitalization="1" numPosition="0" canonicalForm="ibuprofen"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="564" _ref_sofa="3" begin="204" end="213" tokenNumber="44" normalizedForm="increas" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="increas"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="576" _ref_sofa="3" begin="214" end="218" tokenNumber="45" normalizedForm="from" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="from"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="597" _ref_sofa="3" begin="223" end="225" tokenNumber="47" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="mg"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="407" _ref_sofa="3" begin="137" end="143" tokenNumber="26" normalizedForm="pelvic" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="419" _ref_sofa="3" begin="144" end="148" tokenNumber="27" normalizedForm="area" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="439" _ref_sofa="3" begin="150" end="159" tokenNumber="29" normalizedForm="abdominal" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="451" _ref_sofa="3" begin="160" end="164" tokenNumber="30" normalizedForm="area" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="471" _ref_sofa="3" begin="167" end="174" tokenNumber="34" normalizedForm="Aspirin" partOfSpeech="NNP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="500" _ref_sofa="3" begin="179" end="181" tokenNumber="37" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="512" _ref_sofa="3" begin="182" end="186" tokenNumber="38" normalizedForm="once" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="532" _ref_sofa="3" begin="187" end="192" tokenNumber="40" normalizedForm="a-day" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="552" _ref_sofa="3" begin="194" end="203" tokenNumber="43" normalizedForm="Ibuprofen" partOfSpeech="NNP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="564" _ref_sofa="3" begin="204" end="213" tokenNumber="44" normalizedForm="increased" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="576" _ref_sofa="3" begin="214" end="218" tokenNumber="45" normalizedForm="from" partOfSpeech="IN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="597" _ref_sofa="3" begin="223" end="225" tokenNumber="47" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="609" _ref_sofa="3" begin="226" end="228" tokenNumber="48" normalizedForm="to" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="630" _ref_sofa="3" begin="233" end="235" tokenNumber="50" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="mg"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="642" _ref_sofa="3" begin="236" end="240" tokenNumber="51" normalizedForm="p.o." partOfSpeech="FW" capitalization="0" numPosition="0" canonicalForm="p.o."/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="654" _ref_sofa="3" begin="241" end="246" tokenNumber="52" normalizedForm="twice" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="twice"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="666" _ref_sofa="3" begin="247" end="248" tokenNumber="53" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="678" _ref_sofa="3" begin="249" end="252" tokenNumber="54" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="day"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="698" _ref_sofa="3" begin="254" end="261" tokenNumber="57" normalizedForm="aspirin" partOfSpeech="NNP" capitalization="1" numPosition="0" canonicalForm="aspirin"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="719" _ref_sofa="3" begin="265" end="267" tokenNumber="59" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="mg"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="739" _ref_sofa="3" begin="269" end="282" tokenNumber="62" normalizedForm="acetaminophen" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="acetaminophen"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="751" _ref_sofa="3" begin="283" end="295" tokenNumber="63" normalizedForm="discontinu" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="discontinu"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="131" _ref_sofa="3" begin="10" end="11" tokenNumber="1" normalizedForm="/" partOfSpeech="HYPH"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="151" _ref_sofa="3" begin="17" end="18" tokenNumber="3" normalizedForm="/" partOfSpeech="HYPH"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="267" _ref_sofa="3" begin="76" end="77" tokenNumber="14" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="431" _ref_sofa="3" begin="148" end="149" tokenNumber="28" normalizedForm="," partOfSpeech=","/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="463" _ref_sofa="3" begin="164" end="165" tokenNumber="31" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="492" _ref_sofa="3" begin="178" end="179" tokenNumber="36" normalizedForm="-" partOfSpeech="HYPH"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="524" _ref_sofa="3" begin="186" end="187" tokenNumber="39" normalizedForm="-" partOfSpeech="HYPH"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="544" _ref_sofa="3" begin="192" end="193" tokenNumber="41" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="690" _ref_sofa="3" begin="252" end="253" tokenNumber="55" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="731" _ref_sofa="3" begin="267" end="268" tokenNumber="60" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="763" _ref_sofa="3" begin="295" end="296" tokenNumber="64" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="483" _ref_sofa="3" begin="175" end="178" tokenNumber="35" normalizedForm="200" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="588" _ref_sofa="3" begin="219" end="222" tokenNumber="46" normalizedForm="200" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="621" _ref_sofa="3" begin="229" end="232" tokenNumber="49" normalizedForm="300" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="710" _ref_sofa="3" begin="262" end="264" tokenNumber="58" normalizedForm="80" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="630" _ref_sofa="3" begin="233" end="235" tokenNumber="50" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="642" _ref_sofa="3" begin="236" end="240" tokenNumber="51" normalizedForm="p.o." partOfSpeech="FW" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="654" _ref_sofa="3" begin="241" end="246" tokenNumber="52" normalizedForm="twice" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="666" _ref_sofa="3" begin="247" end="248" tokenNumber="53" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="678" _ref_sofa="3" begin="249" end="252" tokenNumber="54" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="698" _ref_sofa="3" begin="254" end="261" tokenNumber="57" normalizedForm="Aspirin" partOfSpeech="NNP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="719" _ref_sofa="3" begin="265" end="267" tokenNumber="59" normalizedForm="mg" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="739" _ref_sofa="3" begin="269" end="282" tokenNumber="62" normalizedForm="acetaminophen" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="751" _ref_sofa="3" begin="283" end="295" tokenNumber="63" normalizedForm="discontinued" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="131" _ref_sofa="3" begin="10" end="11" tokenNumber="1" partOfSpeech="HYPH"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="151" _ref_sofa="3" begin="17" end="18" tokenNumber="3" partOfSpeech="HYPH"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="267" _ref_sofa="3" begin="76" end="77" tokenNumber="14" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="431" _ref_sofa="3" begin="148" end="149" tokenNumber="28" partOfSpeech=","/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="463" _ref_sofa="3" begin="164" end="165" tokenNumber="31" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="492" _ref_sofa="3" begin="178" end="179" tokenNumber="36" partOfSpeech="HYPH"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="524" _ref_sofa="3" begin="186" end="187" tokenNumber="39" partOfSpeech="HYPH"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="544" _ref_sofa="3" begin="192" end="193" tokenNumber="41" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="690" _ref_sofa="3" begin="252" end="253" tokenNumber="55" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="731" _ref_sofa="3" begin="267" end="268" tokenNumber="60" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="763" _ref_sofa="3" begin="295" end="296" tokenNumber="64" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="483" _ref_sofa="3" begin="175" end="178" tokenNumber="35" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="588" _ref_sofa="3" begin="219" end="222" tokenNumber="46" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="621" _ref_sofa="3" begin="229" end="232" tokenNumber="49" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="710" _ref_sofa="3" begin="262" end="264" tokenNumber="58" partOfSpeech="CD" numType="1"/>
<org.apache.ctakes.typesystem.type.textsem.MeasurementAnnotation _indexed="1" _id="771" _ref_sofa="3" begin="219" end="225" id="2" typeID="0" segmentID="SIMPLE_SEGMENT" discoveryTechnique="0" confidence="0.0" polarity="0" uncertainty="0" conditional="false" generic="false" historyOf="0"/>
<org.apache.ctakes.typesystem.type.textsem.MeasurementAnnotation _indexed="1" _id="789" _ref_sofa="3" begin="229" end="235" id="3" typeID="0" segmentID="SIMPLE_SEGMENT" discoveryTechnique="0" confidence="0.0" polarity="0" uncertainty="0" conditional="false" generic="false" historyOf="0"/>
<org.apache.ctakes.typesystem.type.textsem.MeasurementAnnotation _indexed="1" _id="807" _ref_sofa="3" begin="262" end="267" id="5" typeID="0" segmentID="SIMPLE_SEGMENT" discoveryTechnique="0" confidence="0.0" polarity="0" uncertainty="0" conditional="false" generic="false" historyOf="0"/>
Modified: ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note_plaintext.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note_plaintext.xml?rev=1774552&r1=1774551&r2=1774552&view=diff
==============================================================================
--- ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note_plaintext.xml (original)
+++ ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/sample_note_plaintext.xml Fri Dec 16 03:55:37 2016
@@ -6,23 +6,23 @@
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="21" _ref_sofa="3" begin="0" end="27" sentenceNumber="0"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="27" _ref_sofa="3" begin="28" end="39" sentenceNumber="1"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="33" _ref_sofa="3" begin="41" end="66" sentenceNumber="2"/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="39" _ref_sofa="3" begin="27" end="28" tokenNumber="7" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="47" _ref_sofa="3" begin="66" end="67" tokenNumber="16" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="55" _ref_sofa="3" begin="0" end="1" tokenNumber="0" normalizedForm="s" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="s"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="75" _ref_sofa="3" begin="2" end="3" tokenNumber="2" normalizedForm="p" partOfSpeech="IN" capitalization="3" numPosition="0" canonicalForm="p"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="87" _ref_sofa="3" begin="4" end="9" tokenNumber="3" normalizedForm="right" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="right"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="99" _ref_sofa="3" begin="10" end="14" tokenNumber="4" normalizedForm="knee" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="knee"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="111" _ref_sofa="3" begin="15" end="26" tokenNumber="5" normalizedForm="arthroscopy" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="arthroscopy"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="131" _ref_sofa="3" begin="28" end="32" tokenNumber="8" normalizedForm="knee" partOfSpeech="NN" capitalization="1" numPosition="0" canonicalForm="knee"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="143" _ref_sofa="3" begin="33" end="38" tokenNumber="9" normalizedForm="x-ray" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="x-ray"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="163" _ref_sofa="3" begin="41" end="48" tokenNumber="11" normalizedForm="patient" partOfSpeech="NN" capitalization="1" numPosition="0" canonicalForm="patient"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="175" _ref_sofa="3" begin="49" end="55" tokenNumber="12" normalizedForm="denie" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="denie"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="187" _ref_sofa="3" begin="56" end="60" tokenNumber="13" normalizedForm="knee" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="knee"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="199" _ref_sofa="3" begin="61" end="65" tokenNumber="14" normalizedForm="pain" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="pain"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="67" _ref_sofa="3" begin="1" end="2" tokenNumber="1" normalizedForm="/" partOfSpeech="HYPH"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="123" _ref_sofa="3" begin="26" end="27" tokenNumber="6" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="155" _ref_sofa="3" begin="38" end="39" tokenNumber="10" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="211" _ref_sofa="3" begin="65" end="66" tokenNumber="15" normalizedForm="." partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="39" _ref_sofa="3" begin="27" end="28" tokenNumber="7"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="47" _ref_sofa="3" begin="66" end="67" tokenNumber="16"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="55" _ref_sofa="3" begin="0" end="1" tokenNumber="0" normalizedForm="S" partOfSpeech="NN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="75" _ref_sofa="3" begin="2" end="3" tokenNumber="2" normalizedForm="P" partOfSpeech="IN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="87" _ref_sofa="3" begin="4" end="9" tokenNumber="3" normalizedForm="right" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="99" _ref_sofa="3" begin="10" end="14" tokenNumber="4" normalizedForm="knee" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="111" _ref_sofa="3" begin="15" end="26" tokenNumber="5" normalizedForm="arthroscopy" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="131" _ref_sofa="3" begin="28" end="32" tokenNumber="8" normalizedForm="Knee" partOfSpeech="NN" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="143" _ref_sofa="3" begin="33" end="38" tokenNumber="9" normalizedForm="x-ray" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="163" _ref_sofa="3" begin="41" end="48" tokenNumber="11" normalizedForm="Patient" partOfSpeech="NN" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="175" _ref_sofa="3" begin="49" end="55" tokenNumber="12" normalizedForm="denies" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="187" _ref_sofa="3" begin="56" end="60" tokenNumber="13" normalizedForm="knee" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="199" _ref_sofa="3" begin="61" end="65" tokenNumber="14" normalizedForm="pain" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="67" _ref_sofa="3" begin="1" end="2" tokenNumber="1" partOfSpeech="HYPH"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="123" _ref_sofa="3" begin="26" end="27" tokenNumber="6" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="155" _ref_sofa="3" begin="38" end="39" tokenNumber="10" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="211" _ref_sofa="3" begin="65" end="66" tokenNumber="15" partOfSpeech="."/>
<org.apache.ctakes.typesystem.type.syntax.NP _indexed="1" _id="219" _ref_sofa="3" begin="0" end="1" chunkType="NP"/>
<org.apache.ctakes.typesystem.type.syntax.NP _indexed="1" _id="234" _ref_sofa="3" begin="4" end="26" chunkType="NP"/>
<org.apache.ctakes.typesystem.type.syntax.NP _indexed="1" _id="239" _ref_sofa="3" begin="28" end="38" chunkType="NP"/>