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 [3/11] - 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/doc1_07543210_sample_current.txt.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/doc1_07543210_sample_current.txt.xml?rev=1774552&r1=1774551&r2=1774552&view=diff
==============================================================================
--- ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/doc1_07543210_sample_current.txt.xml (original)
+++ ctakes/trunk/ctakes-regression-test/testdata/expectedoutput/RegressionPipelineCPETest/doc1_07543210_sample_current.txt.xml Fri Dec 16 03:55:37 2016
@@ -9,102 +9,102 @@
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="39" _ref_sofa="3" begin="208" end="278" sentenceNumber="3"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="45" _ref_sofa="3" begin="279" end="393" sentenceNumber="4"/>
<org.apache.ctakes.typesystem.type.textspan.Sentence _indexed="1" _id="51" _ref_sofa="3" begin="394" end="436" sentenceNumber="5"/>
- <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="57" _ref_sofa="3" begin="206" end="208" tokenNumber="43" normalizedForm=" "/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="65" _ref_sofa="3" begin="0" end="4" tokenNumber="0" normalizedForm="mis" partOfSpeech="NN" capitalization="1" numPosition="0" canonicalForm="mis"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="85" _ref_sofa="3" begin="6" end="8" tokenNumber="2" normalizedForm="cm" partOfSpeech="NN" capitalization="3" numPosition="0" canonicalForm="cm"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="97" _ref_sofa="3" begin="9" end="11" tokenNumber="3" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="is"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="109" _ref_sofa="3" begin="12" end="13" tokenNumber="4" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="121" _ref_sofa="3" begin="14" end="23" tokenNumber="5" normalizedForm="energetic" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="energetic"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="133" _ref_sofa="3" begin="24" end="29" tokenNumber="6" normalizedForm="yoing" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="yoing"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="145" _ref_sofa="3" begin="30" end="35" tokenNumber="7" normalizedForm="woman" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="woman"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="157" _ref_sofa="3" begin="36" end="39" tokenNumber="8" normalizedForm="who" partOfSpeech="WP" capitalization="0" numPosition="0" canonicalForm="who"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="169" _ref_sofa="3" begin="40" end="43" tokenNumber="9" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="has"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="181" _ref_sofa="3" begin="44" end="47" tokenNumber="10" normalizedForm="had" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="had"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="193" _ref_sofa="3" begin="48" end="53" tokenNumber="11" normalizedForm="bout" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="bout"/>
+ <org.apache.ctakes.typesystem.type.syntax.NewlineToken _indexed="1" _id="57" _ref_sofa="3" begin="206" end="208" tokenNumber="43"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="65" _ref_sofa="3" begin="0" end="4" tokenNumber="0" normalizedForm="Miss" partOfSpeech="NN" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="85" _ref_sofa="3" begin="6" end="8" tokenNumber="2" normalizedForm="CM" partOfSpeech="NN" capitalization="3" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="97" _ref_sofa="3" begin="9" end="11" tokenNumber="3" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="109" _ref_sofa="3" begin="12" end="13" tokenNumber="4" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="121" _ref_sofa="3" begin="14" end="23" tokenNumber="5" normalizedForm="energetic" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="133" _ref_sofa="3" begin="24" end="29" tokenNumber="6" normalizedForm="young" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="145" _ref_sofa="3" begin="30" end="35" tokenNumber="7" normalizedForm="woman" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="157" _ref_sofa="3" begin="36" end="39" tokenNumber="8" normalizedForm="who" partOfSpeech="WP" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="169" _ref_sofa="3" begin="40" end="43" tokenNumber="9" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="181" _ref_sofa="3" begin="44" end="47" tokenNumber="10" normalizedForm="had" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="193" _ref_sofa="3" begin="48" end="53" tokenNumber="11" normalizedForm="bouts" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="205" _ref_sofa="3" begin="54" end="58" tokenNumber="12" normalizedForm="with" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="217" _ref_sofa="3" begin="59" end="72" tokenNumber="13" normalizedForm="sleeplessnes" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="sleeplessnes"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="217" _ref_sofa="3" begin="59" end="72" tokenNumber="13" normalizedForm="sleeplessness" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="229" _ref_sofa="3" begin="73" end="76" tokenNumber="14" normalizedForm="for" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="241" _ref_sofa="3" begin="77" end="80" tokenNumber="15" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="253" _ref_sofa="3" begin="81" end="85" tokenNumber="16" normalizedForm="past" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="past"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="265" _ref_sofa="3" begin="86" end="90" tokenNumber="17" normalizedForm="year" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="year"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="277" _ref_sofa="3" begin="91" end="93" tokenNumber="18" normalizedForm="or" partOfSpeech="CC" capitalization="0" numPosition="0" canonicalForm="or"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="289" _ref_sofa="3" begin="94" end="96" tokenNumber="19" normalizedForm="so" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="so"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="309" _ref_sofa="3" begin="99" end="102" tokenNumber="21" normalizedForm="she" partOfSpeech="PRP" capitalization="1" numPosition="0" canonicalForm="she"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="321" _ref_sofa="3" begin="103" end="107" tokenNumber="22" normalizedForm="said" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="said"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="333" _ref_sofa="3" begin="108" end="112" tokenNumber="23" normalizedForm="that" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="that"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="345" _ref_sofa="3" begin="113" end="116" tokenNumber="24" normalizedForm="her" partOfSpeech="PRP$" capitalization="0" numPosition="0" canonicalForm="her"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="357" _ref_sofa="3" begin="117" end="125" tokenNumber="25" normalizedForm="insomnia" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="insomnia"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="369" _ref_sofa="3" begin="126" end="131" tokenNumber="26" normalizedForm="began" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="began"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="253" _ref_sofa="3" begin="81" end="85" tokenNumber="16" normalizedForm="past" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="265" _ref_sofa="3" begin="86" end="90" tokenNumber="17" normalizedForm="year" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="277" _ref_sofa="3" begin="91" end="93" tokenNumber="18" normalizedForm="or" partOfSpeech="CC" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="289" _ref_sofa="3" begin="94" end="96" tokenNumber="19" normalizedForm="so" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="309" _ref_sofa="3" begin="99" end="102" tokenNumber="21" normalizedForm="She" partOfSpeech="PRP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="321" _ref_sofa="3" begin="103" end="107" tokenNumber="22" normalizedForm="said" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="333" _ref_sofa="3" begin="108" end="112" tokenNumber="23" normalizedForm="that" partOfSpeech="IN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="345" _ref_sofa="3" begin="113" end="116" tokenNumber="24" normalizedForm="her" partOfSpeech="PRP$" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="357" _ref_sofa="3" begin="117" end="125" tokenNumber="25" normalizedForm="insomnia" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="369" _ref_sofa="3" begin="126" end="131" tokenNumber="26" normalizedForm="began" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="381" _ref_sofa="3" begin="132" end="136" tokenNumber="27" normalizedForm="with" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="393" _ref_sofa="3" begin="137" end="140" tokenNumber="28" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="405" _ref_sofa="3" begin="141" end="146" tokenNumber="29" normalizedForm="death" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="death"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="405" _ref_sofa="3" begin="141" end="146" tokenNumber="29" normalizedForm="death" partOfSpeech="NN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="417" _ref_sofa="3" begin="147" end="149" tokenNumber="30" normalizedForm="of" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="429" _ref_sofa="3" begin="150" end="153" tokenNumber="31" normalizedForm="her" partOfSpeech="PRP$" capitalization="0" numPosition="0" canonicalForm="her"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="441" _ref_sofa="3" begin="154" end="160" tokenNumber="32" normalizedForm="fath" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="fath"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="453" _ref_sofa="3" begin="161" end="164" tokenNumber="33" normalizedForm="who" partOfSpeech="WP" capitalization="0" numPosition="0" canonicalForm="who"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="465" _ref_sofa="3" begin="165" end="168" tokenNumber="34" normalizedForm="was" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="was"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="477" _ref_sofa="3" begin="169" end="175" tokenNumber="35" normalizedForm="kil" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="kil"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="429" _ref_sofa="3" begin="150" end="153" tokenNumber="31" normalizedForm="her" partOfSpeech="PRP$" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="441" _ref_sofa="3" begin="154" end="160" tokenNumber="32" normalizedForm="father" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="453" _ref_sofa="3" begin="161" end="164" tokenNumber="33" normalizedForm="who" partOfSpeech="WP" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="465" _ref_sofa="3" begin="165" end="168" tokenNumber="34" normalizedForm="was" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="477" _ref_sofa="3" begin="169" end="175" tokenNumber="35" normalizedForm="killed" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="489" _ref_sofa="3" begin="176" end="178" tokenNumber="36" normalizedForm="in" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="501" _ref_sofa="3" begin="179" end="180" tokenNumber="37" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="513" _ref_sofa="3" begin="181" end="186" tokenNumber="38" normalizedForm="train" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="train"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="525" _ref_sofa="3" begin="187" end="195" tokenNumber="39" normalizedForm="accident" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="accident"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="537" _ref_sofa="3" begin="196" end="200" tokenNumber="40" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="last"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="549" _ref_sofa="3" begin="201" end="205" tokenNumber="41" normalizedForm="year" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="year"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="569" _ref_sofa="3" begin="208" end="215" tokenNumber="44" normalizedForm="patient" partOfSpeech="NN" capitalization="1" numPosition="0" canonicalForm="patient"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="581" _ref_sofa="3" begin="216" end="218" tokenNumber="45" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="is"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="501" _ref_sofa="3" begin="179" end="180" tokenNumber="37" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="513" _ref_sofa="3" begin="181" end="186" tokenNumber="38" normalizedForm="train" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="525" _ref_sofa="3" begin="187" end="195" tokenNumber="39" normalizedForm="accident" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="537" _ref_sofa="3" begin="196" end="200" tokenNumber="40" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="549" _ref_sofa="3" begin="201" end="205" tokenNumber="41" normalizedForm="year" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="569" _ref_sofa="3" begin="208" end="215" tokenNumber="44" normalizedForm="Patient" partOfSpeech="NN" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="581" _ref_sofa="3" begin="216" end="218" tokenNumber="45" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="602" _ref_sofa="3" begin="222" end="225" tokenNumber="47" normalizedForm="and" partOfSpeech="CC" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="614" _ref_sofa="3" begin="226" end="232" tokenNumber="48" normalizedForm="claim" partOfSpeech="VBP" capitalization="0" numPosition="0" canonicalForm="claim"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="626" _ref_sofa="3" begin="233" end="236" tokenNumber="49" normalizedForm="she" partOfSpeech="PRP" capitalization="0" numPosition="0" canonicalForm="she"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="638" _ref_sofa="3" begin="237" end="240" tokenNumber="50" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="has"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="650" _ref_sofa="3" begin="241" end="247" tokenNumber="51" normalizedForm="smok" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="smok"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="614" _ref_sofa="3" begin="226" end="232" tokenNumber="48" normalizedForm="claims" partOfSpeech="VBP" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="626" _ref_sofa="3" begin="233" end="236" tokenNumber="49" normalizedForm="she" partOfSpeech="PRP" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="638" _ref_sofa="3" begin="237" end="240" tokenNumber="50" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="650" _ref_sofa="3" begin="241" end="247" tokenNumber="51" normalizedForm="smoked" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="662" _ref_sofa="3" begin="248" end="251" tokenNumber="52" normalizedForm="for" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="674" _ref_sofa="3" begin="252" end="255" tokenNumber="53" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="686" _ref_sofa="3" begin="256" end="260" tokenNumber="54" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="last"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="698" _ref_sofa="3" begin="261" end="265" tokenNumber="55" normalizedForm="five" partOfSpeech="CD" capitalization="0" numPosition="0" canonicalForm="five"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="710" _ref_sofa="3" begin="266" end="271" tokenNumber="56" normalizedForm="year" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="year"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="722" _ref_sofa="3" begin="272" end="274" tokenNumber="57" normalizedForm="or" partOfSpeech="CC" capitalization="0" numPosition="0" canonicalForm="or"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="734" _ref_sofa="3" begin="275" end="277" tokenNumber="58" normalizedForm="so" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="so"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="754" _ref_sofa="3" begin="279" end="282" tokenNumber="60" normalizedForm="she" partOfSpeech="PRP" capitalization="1" numPosition="0" canonicalForm="she"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="766" _ref_sofa="3" begin="283" end="287" tokenNumber="61" normalizedForm="use" partOfSpeech="VBD" capitalization="0" numPosition="0" canonicalForm="use"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="686" _ref_sofa="3" begin="256" end="260" tokenNumber="54" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="698" _ref_sofa="3" begin="261" end="265" tokenNumber="55" normalizedForm="five" partOfSpeech="CD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="710" _ref_sofa="3" begin="266" end="271" tokenNumber="56" normalizedForm="years" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="722" _ref_sofa="3" begin="272" end="274" tokenNumber="57" normalizedForm="or" partOfSpeech="CC" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="734" _ref_sofa="3" begin="275" end="277" tokenNumber="58" normalizedForm="so" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="754" _ref_sofa="3" begin="279" end="282" tokenNumber="60" normalizedForm="She" partOfSpeech="PRP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="766" _ref_sofa="3" begin="283" end="287" tokenNumber="61" normalizedForm="used" partOfSpeech="VBD" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="778" _ref_sofa="3" begin="288" end="290" tokenNumber="62" normalizedForm="to" partOfSpeech="TO" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="790" _ref_sofa="3" begin="291" end="296" tokenNumber="63" normalizedForm="smoke" partOfSpeech="VB" capitalization="0" numPosition="0" canonicalForm="smoke"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="802" _ref_sofa="3" begin="297" end="302" tokenNumber="64" normalizedForm="about" partOfSpeech="IN" capitalization="0" numPosition="0" canonicalForm="about"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="814" _ref_sofa="3" begin="303" end="307" tokenNumber="65" normalizedForm="half" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="half"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="826" _ref_sofa="3" begin="308" end="309" tokenNumber="66" normalizedForm="a" partOfSpeech="CD" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="838" _ref_sofa="3" begin="310" end="314" tokenNumber="67" normalizedForm="pack" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="pack"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="850" _ref_sofa="3" begin="315" end="316" tokenNumber="68" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="862" _ref_sofa="3" begin="317" end="320" tokenNumber="69" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="day"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="882" _ref_sofa="3" begin="322" end="325" tokenNumber="71" normalizedForm="but" partOfSpeech="CC" capitalization="0" numPosition="0" canonicalForm="but"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="790" _ref_sofa="3" begin="291" end="296" tokenNumber="63" normalizedForm="smoke" partOfSpeech="VB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="802" _ref_sofa="3" begin="297" end="302" tokenNumber="64" normalizedForm="about" partOfSpeech="IN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="814" _ref_sofa="3" begin="303" end="307" tokenNumber="65" normalizedForm="half" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="826" _ref_sofa="3" begin="308" end="309" tokenNumber="66" normalizedForm="a" partOfSpeech="CD" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="838" _ref_sofa="3" begin="310" end="314" tokenNumber="67" normalizedForm="pack" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="850" _ref_sofa="3" begin="315" end="316" tokenNumber="68" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="862" _ref_sofa="3" begin="317" end="320" tokenNumber="69" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="882" _ref_sofa="3" begin="322" end="325" tokenNumber="71" normalizedForm="but" partOfSpeech="CC" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="894" _ref_sofa="3" begin="326" end="329" tokenNumber="72" normalizedForm="for" partOfSpeech="IN" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="906" _ref_sofa="3" begin="330" end="333" tokenNumber="73" normalizedForm="the" partOfSpeech="DT" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="918" _ref_sofa="3" begin="334" end="338" tokenNumber="74" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0" canonicalForm="last"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="930" _ref_sofa="3" begin="339" end="344" tokenNumber="75" normalizedForm="month" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="month"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="942" _ref_sofa="3" begin="345" end="348" tokenNumber="76" normalizedForm="she" partOfSpeech="PRP" capitalization="0" numPosition="0" canonicalForm="she"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="954" _ref_sofa="3" begin="349" end="352" tokenNumber="77" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="has"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="966" _ref_sofa="3" begin="353" end="357" tokenNumber="78" normalizedForm="been" partOfSpeech="VBN" capitalization="0" numPosition="0" canonicalForm="been"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="978" _ref_sofa="3" begin="358" end="362" tokenNumber="79" normalizedForm="down" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="down"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="918" _ref_sofa="3" begin="334" end="338" tokenNumber="74" normalizedForm="last" partOfSpeech="JJ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="930" _ref_sofa="3" begin="339" end="344" tokenNumber="75" normalizedForm="month" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="942" _ref_sofa="3" begin="345" end="348" tokenNumber="76" normalizedForm="she" partOfSpeech="PRP" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="954" _ref_sofa="3" begin="349" end="352" tokenNumber="77" normalizedForm="has" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="966" _ref_sofa="3" begin="353" end="357" tokenNumber="78" normalizedForm="been" partOfSpeech="VBN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="978" _ref_sofa="3" begin="358" end="362" tokenNumber="79" normalizedForm="down" partOfSpeech="RB" capitalization="0" numPosition="0"/>
<org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="990" _ref_sofa="3" begin="363" end="365" tokenNumber="80" normalizedForm="to" partOfSpeech="IN" capitalization="0" numPosition="0"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1002" _ref_sofa="3" begin="366" end="371" tokenNumber="81" normalizedForm="about" partOfSpeech="RB" capitalization="0" numPosition="0" canonicalForm="about"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1040" _ref_sofa="3" begin="376" end="386" tokenNumber="85" normalizedForm="cigarette" partOfSpeech="NNS" capitalization="0" numPosition="0" canonicalForm="cigarette"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1052" _ref_sofa="3" begin="387" end="388" tokenNumber="86" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0" canonicalForm="a"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1064" _ref_sofa="3" begin="389" end="392" tokenNumber="87" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="day"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1084" _ref_sofa="3" begin="394" end="397" tokenNumber="89" normalizedForm="she" partOfSpeech="PRP" capitalization="1" numPosition="0" canonicalForm="she"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1096" _ref_sofa="3" begin="398" end="400" tokenNumber="90" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0" canonicalForm="is"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1108" _ref_sofa="3" begin="401" end="407" tokenNumber="91" normalizedForm="hav" partOfSpeech="VBG" capitalization="0" numPosition="0" canonicalForm="hav"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1120" _ref_sofa="3" begin="408" end="415" tokenNumber="92" normalizedForm="trouble" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="trouble"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1132" _ref_sofa="3" begin="416" end="424" tokenNumber="93" normalizedForm="stop" partOfSpeech="VBG" capitalization="0" numPosition="0" canonicalForm="stop"/>
- <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1144" _ref_sofa="3" begin="425" end="435" tokenNumber="94" normalizedForm="altogeth" partOfSpeech="NN" capitalization="0" numPosition="0" canonicalForm="altogeth"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="77" _ref_sofa="3" begin="4" end="5" tokenNumber="1" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="301" _ref_sofa="3" begin="96" end="97" tokenNumber="20" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="561" _ref_sofa="3" begin="205" end="206" tokenNumber="42" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="746" _ref_sofa="3" begin="277" end="278" tokenNumber="59" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="874" _ref_sofa="3" begin="320" end="321" tokenNumber="70" normalizedForm="," partOfSpeech=","/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1023" _ref_sofa="3" begin="373" end="374" tokenNumber="83" normalizedForm="-" partOfSpeech="SYM"/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1076" _ref_sofa="3" begin="392" end="393" tokenNumber="88" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1156" _ref_sofa="3" begin="435" end="436" tokenNumber="95" normalizedForm="." partOfSpeech="."/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="593" _ref_sofa="3" begin="219" end="221" tokenNumber="46" normalizedForm="25" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="1014" _ref_sofa="3" begin="372" end="373" tokenNumber="82" normalizedForm="3" partOfSpeech="CD" numType="1"/>
- <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="1031" _ref_sofa="3" begin="374" end="375" tokenNumber="84" normalizedForm="5" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1002" _ref_sofa="3" begin="366" end="371" tokenNumber="81" normalizedForm="about" partOfSpeech="RB" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1040" _ref_sofa="3" begin="376" end="386" tokenNumber="85" normalizedForm="cigarettes" partOfSpeech="NNS" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1052" _ref_sofa="3" begin="387" end="388" tokenNumber="86" normalizedForm="a" partOfSpeech="DT" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1064" _ref_sofa="3" begin="389" end="392" tokenNumber="87" normalizedForm="day" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1084" _ref_sofa="3" begin="394" end="397" tokenNumber="89" normalizedForm="She" partOfSpeech="PRP" capitalization="1" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1096" _ref_sofa="3" begin="398" end="400" tokenNumber="90" normalizedForm="is" partOfSpeech="VBZ" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1108" _ref_sofa="3" begin="401" end="407" tokenNumber="91" normalizedForm="having" partOfSpeech="VBG" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1120" _ref_sofa="3" begin="408" end="415" tokenNumber="92" normalizedForm="trouble" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1132" _ref_sofa="3" begin="416" end="424" tokenNumber="93" normalizedForm="stopping" partOfSpeech="VBG" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.WordToken _indexed="1" _id="1144" _ref_sofa="3" begin="425" end="435" tokenNumber="94" normalizedForm="altogether" partOfSpeech="NN" capitalization="0" numPosition="0"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="77" _ref_sofa="3" begin="4" end="5" tokenNumber="1" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="301" _ref_sofa="3" begin="96" end="97" tokenNumber="20" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="561" _ref_sofa="3" begin="205" end="206" tokenNumber="42" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="746" _ref_sofa="3" begin="277" end="278" tokenNumber="59" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="874" _ref_sofa="3" begin="320" end="321" tokenNumber="70" partOfSpeech=","/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1023" _ref_sofa="3" begin="373" end="374" tokenNumber="83" partOfSpeech="SYM"/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1076" _ref_sofa="3" begin="392" end="393" tokenNumber="88" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.PunctuationToken _indexed="1" _id="1156" _ref_sofa="3" begin="435" end="436" tokenNumber="95" partOfSpeech="."/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="593" _ref_sofa="3" begin="219" end="221" tokenNumber="46" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="1014" _ref_sofa="3" begin="372" end="373" tokenNumber="82" partOfSpeech="CD" numType="1"/>
+ <org.apache.ctakes.typesystem.type.syntax.NumToken _indexed="1" _id="1031" _ref_sofa="3" begin="374" end="375" tokenNumber="84" partOfSpeech="CD" numType="1"/>
<org.apache.ctakes.typesystem.type.textsem.RomanNumeralAnnotation _indexed="1" _id="1164" _ref_sofa="3" begin="6" end="8" 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.textsem.DateAnnotation _indexed="1" _id="1182" _ref_sofa="3" begin="372" end="375" 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.FractionAnnotation _indexed="1" _id="1200" _ref_sofa="3" begin="303" end="307" id="1" typeID="0" segmentID="SIMPLE_SEGMENT" discoveryTechnique="0" confidence="0.0" polarity="0" uncertainty="0" conditional="false" generic="false" historyOf="0"/>