Commit f6370a60 authored by Arndt Heilmann's avatar Arndt Heilmann
Browse files

Added Files and Folders

parents
<DTAGalign alignment="yawat" source="en" target="de">
<alignFile href="P01_SG12_T01.src" key="a" sign="" />
<alignFile href="P01_SG12_T01.tgt" key="b" sign="" />
<align in="b1" out="a2" />
<align in="b2" out="a1" />
<align in="b3" out="a1" />
<align in="b5" out="a4" />
<align in="b6" out="a5" />
<align in="b6" out="a6" />
<align in="b7" out="a5" />
<align in="b7" out="a6" />
<align in="b8" out="a3" />
<align in="b9" out="a8" />
<align in="b10" out="a7" />
<align in="b11" out="a7" />
<align in="b12" out="a7" />
<align in="b13" out="a8" />
<align in="b14" out="a9" />
<align in="b15" out="a10" />
<align in="b16" out="a11" />
<align in="b17" out="a16" />
<align in="b18" out="a17" />
<align in="b19" out="a18" />
<align in="b20" out="a19" />
<align in="b21" out="a20" />
<align in="b22" out="a21" />
<align in="b22" out="a22" />
<align in="b23" out="a23" />
<align in="b24" out="a15" />
<align in="b25" out="a13" />
<align in="b26" out="a12" />
<align in="b27" out="a14" />
<align in="b28" out="a12" />
<align in="b29" out="a12" />
<align in="b30" out="a24" />
<align in="b31" out="a28" />
<align in="b32" out="a25" />
<align in="b32" out="a26" />
<align in="b32" out="a27" />
<align in="b33" out="a28" />
<align in="b34" out="a29" />
<align in="b35" out="a30" />
<align in="b36" out="a31" />
<align in="b37" out="a32" />
<align in="b38" out="a33" />
<align in="b39" out="a34" />
<align in="b40" out="a35" />
<align in="b40" out="a36" />
<align in="b42" out="a37" />
<align in="b43" out="a38" />
<align in="b44" out="a39" />
<align in="b45" out="a40" />
<align in="b46" out="a41" />
<align in="b47" out="a42" />
<align in="b48" out="a43" />
<align in="b48" out="a44" />
<align in="b49" out="a38" />
<align in="b50" out="a45" />
<align in="b51" out="a46" />
<align in="b52" out="a49" />
<align in="b53" out="a48" />
<align in="b54" out="a57" />
<align in="b55" out="a58" />
<align in="b55" out="a59" />
<align in="b56" out="a60" />
<align in="b57" out="a52" />
<align in="b58" out="a53" />
<align in="b58" out="a54" />
<align in="b58" out="a55" />
<align in="b59" out="a56" />
<align in="b60" out="a51" />
<align in="b61" out="a50" />
<align in="b62" out="a61" />
<align in="b63" out="a62" />
<align in="b64" out="a63" />
<align in="b64" out="a64" />
<align in="b65" out="a65" />
<align in="b66" out="a66" />
<align in="b66" out="a67" />
<align in="b67" out="a68" />
<align in="b68" out="a69" />
<align in="b69" out="a70" />
<align in="b70" out="a71" />
<align in="b70" out="a72" />
<align in="b70" out="a73" />
<align in="b71" out="a74" />
<align in="b72" out="a75" />
<align in="b73" out="a76" />
<align in="b74" out="a77" />
<align in="b75" out="a81" />
<align in="b75" out="a82" />
<align in="b76" out="a83" />
<align in="b77" out="a84" />
<align in="b79" out="a80" />
<align in="b80" out="a78" />
<align in="b80" out="a79" />
<align in="b81" out="a85" />
<align in="b82" out="a86" />
<align in="b82" out="a87" />
<align in="b83" out="a86" />
<align in="b83" out="a87" />
<align in="b84" out="a88" />
<align in="b85" out="a89" />
<align in="b86" out="a90" />
<align in="b88" out="a91" />
<align in="b89" out="a92" />
<align in="b90" out="a93" />
<align in="b90" out="a94" />
<align in="b90" out="a95" />
<align in="b91" out="a97" />
<align in="b91" out="a98" />
<align in="b92" out="a99" />
<align in="b93" out="a96" />
<align in="b94" out="a93" />
<align in="b94" out="a94" />
<align in="b94" out="a95" />
<align in="b95" out="a100" />
<align in="b96" out="a101" />
<align in="b97" out="a102" />
<align in="b98" out="a103" />
<align in="b99" out="a104" />
<align in="b99" out="a105" />
<align in="b100" out="a107" />
<align in="b101" out="a106" />
<align in="b102" out="a106" />
<align in="b103" out="a108" />
<align in="b103" out="a109" />
<align in="b103" out="a110" />
<align in="b103" out="a111" />
<align in="b104" out="a112" />
<align in="b104" out="a113" />
<align in="b104" out="a114" />
<align in="b104" out="a115" />
<align in="b104" out="a116" />
<align in="b105" out="a112" />
<align in="b105" out="a113" />
<align in="b105" out="a114" />
<align in="b105" out="a115" />
<align in="b105" out="a116" />
<align in="b106" out="a108" />
<align in="b106" out="a109" />
<align in="b106" out="a110" />
<align in="b106" out="a111" />
<align in="b107" out="a117" />
<align in="b108" out="a118" />
<align in="b109" out="a119" />
<align in="b110" out="a120" />
<align in="b111" out="a121" />
<align in="b113" out="a122" />
<align in="b114" out="a123" />
<align in="b114" out="a124" />
<align in="b114" out="a125" />
<align in="b114" out="a126" />
<align in="b114" out="a127" />
<align in="b115" out="a123" />
<align in="b115" out="a124" />
<align in="b115" out="a125" />
<align in="b115" out="a126" />
<align in="b115" out="a127" />
<align in="b116" out="a128" />
<align in="b117" out="a128" />
<align in="b118" out="a128" />
<align in="b120" out="a129" />
<align in="b121" out="a130" />
<align in="b122" out="a131" />
<align in="b123" out="a131" />
<align in="b124" out="a133" />
<align in="b125" out="a134" />
<align in="b126" out="a135" />
<align in="b127" out="a132" />
<align in="b128" out="a136" />
<align in="b129" out="a137" />
<align in="b130" out="a138" />
<align in="b130" out="a139" />
<align in="b131" out="a140" />
<align in="b132" out="a141" />
<align in="b133" out="a142" />
<align in="b135" out="a143" />
<align in="b136" out="a144" />
<align in="b137" out="a145" />
<align in="b138" out="a146" />
<align in="b138" out="a147" />
<align in="b139" out="a148" />
<align in="b140" out="a152" />
<align in="b141" out="a154" />
<align in="b142" out="a155" />
<align in="b142" out="a156" />
<align in="b143" out="a157" />
<align in="b144" out="a158" />
<align in="b144" out="a159" />
<align in="b145" out="a158" />
<align in="b145" out="a159" />
<align in="b146" out="a154" />
<align in="b147" out="a153" />
<align in="b148" out="a160" />
<salign src="1" tgt="1" />
<salign src="2" tgt="2" />
<salign src="3" tgt="3" />
<salign src="4" tgt="4" />
<salign src="5" tgt="5" />
<salign src="6" tgt="6" />
<salign src="7" tgt="7" />
<salign src="8" tgt="8" />
<salign src="9" tgt="9" />
<salign src="10" tgt="10" />
<salign src="11" tgt="10" />
</DTAGalign>
\ No newline at end of file
This diff is collapsed.
<?xml version='1.0' encoding='UTF-8'?>
<Text language="de" lexFreq="yes" lemmatizer="tree-tagger" sent_segmenter="nltk_sent_tokenizer" tagger="tree-tagger">
<W cur="1" id="1" lemma="Krankenpfleger" pos="NN" space="&#10;" Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.1428571428571429">Krankenpfleger</W>
<W cur="16" id="2" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.16666666666666663">des</W>
<W cur="20" id="3" lemma="Tod" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.16666666666666663">Todes</W>
<W cur="26" id="4" lemma="werden" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0">wird</W>
<W cur="31" id="5" lemma="vierfach" pos="ADJD" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.125">vierfach</W>
<W cur="40" id="6" lemma="zu" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.0">zu</W>
<W cur="43" id="7" lemma="lebenslänglich" pos="ADJD" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.2857142857142857">lebenslänglich</W>
<W cur="58" id="8" lemma="verurteilen" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="1" formal_similarity="0.19999999999999996">verurteilt</W>
<W cur="69" id="9" lemma="die" pos="ART" space="&#10;" Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.19999999999999996">Der</W>
<W cur="73" id="10" lemma="in" pos="APPRART" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.125">im</W>
<W cur="76" id="11" lemma="Krankenhaus" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.09090909090909094">Krankenhaus</W>
<W cur="88" id="12" lemma="angestellt" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.18181818181818177">angestellte</W>
<W cur="100" id="13" lemma="Krankenpfleger" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.1428571428571429">Krankenpfleger</W>
<W cur="115" id="14" lemma="Colin" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="1.0">Colin</W>
<W cur="121" id="15" lemma="_" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="1.0">Norris</W>
<W cur="128" id="16" lemma="werden" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.19999999999999996">wurde</W>
<W cur="134" id="17" lemma="für" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.6666666666666667">für</W>
<W cur="138" id="18" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">den</W>
<W cur="142" id="19" lemma="Mord" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">Mord</W>
<W cur="147" id="20" lemma="an" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">an</W>
<W cur="150" id="21" lemma="vier" pos="CARD" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.25">vier</W>
<W cur="155" id="22" lemma="sein" pos="PPOSAT" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">seiner</W>
<W cur="162" id="23" lemma="Patient" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.7777777777777778">Patienten</W>
<W cur="172" id="24" lemma="heute" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">heute</W>
<W cur="178" id="25" lemma="zu" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">zu</W>
<W cur="181" id="26" lemma="eine" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.30000000000000004">einer</W>
<W cur="187" id="27" lemma="lebenslänglich" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.1875">lebenslänglichen</W>
<W cur="204" id="28" lemma="Gefängnisstrafe" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.1333333333333333">Gefängnisstrafe</W>
<W cur="220" id="29" lemma="verurteilen" pos="VVPP" space=" " Prob1="-50" Prob2="-50" segId="2" formal_similarity="0.0">verurteilt</W>
<W cur="230" id="30" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="2" formal_similarity="1.0">.</W>
<W cur="232" id="31" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.16666666666666663">Der</W>
<W cur="236" id="32" lemma="_" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.2727272727272727">32-jährige</W>
<W cur="247" id="33" lemma="_" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="1.0">Norris</W>
<W cur="254" id="34" lemma="aus" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.0">aus</W>
<W cur="258" id="35" lemma="Glasgow" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="1.0">Glasgow</W>
<W cur="266" id="36" lemma="töten" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.0">tötete</W>
<W cur="273" id="37" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.33333333333333337">die</W>
<W cur="277" id="38" lemma="vier" pos="CARD" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.25">vier</W>
<W cur="282" id="39" lemma="Frau" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.33333333333333337">Frauen</W>
<W cur="289" id="40" lemma="@card@" pos="CARD" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.5714285714285714">2002</W>
<W cur="293" id="41" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="3" formal_similarity="0">,</W>
<W cur="295" id="42" lemma="indem" pos="KOUS" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.0">indem</W>
<W cur="301" id="43" lemma="er" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.0">er</W>
<W cur="304" id="44" lemma="sie" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.4">ihnen</W>
<W cur="310" id="45" lemma="groß" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.19999999999999996">große</W>
<W cur="316" id="46" lemma="Menge" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.1428571428571429">Mengen</W>
<W cur="323" id="47" lemma="an" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.0">an</W>
<W cur="326" id="48" lemma="_" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.2222222222222222">Schlafmedikamenten</W>
<W cur="345" id="49" lemma="verabreichen" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="3" formal_similarity="0.08333333333333337">verabreichte</W>
<W cur="357" id="50" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="3" formal_similarity="1.0">.</W>
<W cur="359" id="51" lemma="gestern" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.5555555555555556">Gestern</W>
<W cur="367" id="52" lemma="werden" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.19999999999999996">wurde</W>
<W cur="373" id="53" lemma="er" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.0">er</W>
<W cur="376" id="54" lemma="nach" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.0">nach</W>
<W cur="381" id="55" lemma="lang" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.16666666666666663">langem</W>
<W cur="388" id="56" lemma="Gerichtsverfahren" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.17647058823529416">Gerichtsverfahren</W>
<W cur="406" id="57" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.0">des</W>
<W cur="410" id="58" lemma="vierfach" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.1428571428571429">vierfachen</W>
<W cur="421" id="59" lemma="Mord" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.6666666666666667">Mordes</W>
<W cur="428" id="60" lemma="schuldig" pos="ADJD" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.125">schuldig</W>
<W cur="437" id="61" lemma="sprechen" pos="VVPP" space=" " Prob1="-50" Prob2="-50" segId="4" formal_similarity="0.09999999999999998">gesprochen</W>
<W cur="447" id="62" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="4" formal_similarity="1.0">.</W>
<W cur="449" id="63" lemma="er" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.0">Er</W>
<W cur="452" id="64" lemma="erhalten" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.11111111111111116">erhielt</W>
<W cur="460" id="65" lemma="viermal" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.1428571428571429">viermal</W>
<W cur="468" id="66" lemma="lebenslänglich" pos="ADJD" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.2857142857142857">lebenslänglich</W>
<W cur="482" id="67" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="5" formal_similarity="1.0">,</W>
<W cur="484" id="68" lemma="einmal" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.16666666666666663">einmal</W>
<W cur="491" id="69" lemma="für" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.6666666666666667">für</W>
<W cur="495" id="70" lemma="jed" pos="PIAT" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.0">jeden</W>
<W cur="501" id="71" lemma="Mord" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="5" formal_similarity="0.0">Mord</W>
<W cur="505" id="72" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="5" formal_similarity="1.0">.</W>
<W cur="507" id="73" lemma="er" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.0">Er</W>
<W cur="510" id="74" lemma="werden" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.5">wird</W>
<W cur="515" id="75" lemma="mindeste" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.2222222222222222">mindestes</W>
<W cur="525" id="76" lemma="30" pos="CARD" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="1.0">30</W>
<W cur="528" id="77" lemma="Jahr" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.19999999999999996">Jahre</W>
<W cur="534" id="78" lemma="davon" pos="PAV" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0">davon</W>
<W cur="540" id="79" lemma="absitzen" pos="VVINF" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.25">absitzen</W>
<W cur="549" id="80" lemma="müssen" pos="VMINF" space=" " Prob1="-50" Prob2="-50" segId="6" formal_similarity="0.0">müssen</W>
<W cur="555" id="81" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="6" formal_similarity="1.0">.</W>
<W cur="557" id="82" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.1428571428571429">Der</W>
<W cur="561" id="83" lemma="Polizeibeamte" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.4285714285714286">Polizeibeamte</W>
<W cur="575" id="84" lemma="Chris" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="1.0">Chris</W>
<W cur="581" id="85" lemma="_" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="1.0">Gregg</W>
<W cur="587" id="86" lemma="sagen" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.4">sagte</W>
<W cur="592" id="87" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="7" formal_similarity="0">,</W>
<W cur="594" id="88" lemma="dass" pos="KOUS" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.0">dass</W>
<W cur="599" id="89" lemma="_" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="1.0">Norris</W>
<W cur="606" id="90" lemma="sich" pos="PRF" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.06666666666666665">sich</W>
<W cur="611" id="91" lemma="in" pos="APPRART" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.0">im</W>
<W cur="614" id="92" lemma="Krankenhaus" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.09090909090909094">Krankenhaus</W>
<W cur="626" id="93" lemma="auffällig" pos="ADJD" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.0">auffällig</W>
<W cur="636" id="94" lemma="verhalten" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="7" formal_similarity="0.1333333333333333">verhielt</W>
<W cur="644" id="95" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="7" formal_similarity="1.0">.</W>
<W cur="646" id="96" lemma="nur" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.25">Nur</W>
<W cur="650" id="97" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.33333333333333337">die</W>
<W cur="654" id="98" lemma="Aufmerksamkeit" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.2142857142857143">Aufmerksamkeit</W>
<W cur="669" id="99" lemma="ander" pos="PIAT" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.25">anderer</W>
<W cur="677" id="100" lemma="Angestellte" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.16666666666666663">Angestellter</W>
<W cur="690" id="101" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.125">des</W>
<W cur="694" id="102" lemma="Krankenhaus" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.07692307692307687">Krankenhauses</W>
<W cur="708" id="103" lemma="können" pos="VMFIN" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.15384615384615385">konnte</W>
<W cur="715" id="104" lemma="weit" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.08695652173913049">weitere</W>
<W cur="723" id="105" lemma="Mord" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.13043478260869568">Morde</W>
<W cur="729" id="106" lemma="verhindern" pos="VVINF" space=" " Prob1="-50" Prob2="-50" segId="8" formal_similarity="0.0">verhindern</W>
<W cur="739" id="107" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="8" formal_similarity="1.0">.</W>
<W cur="741" id="108" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.33333333333333337">Die</W>
<W cur="745" id="109" lemma="Polizei" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.7142857142857143">Polizei</W>
<W cur="753" id="110" lemma="haben" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.5">hat</W>
<W cur="757" id="111" lemma="herausfinden" pos="VVPP" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.2857142857142857">herausgefunden</W>
<W cur="771" id="112" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="9" formal_similarity="0">,</W>
<W cur="773" id="113" lemma="dass" pos="KOUS" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.0">dass</W>
<W cur="778" id="114" lemma="_" pos="NE" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.14814814814814814">Norris</W>
<W cur="785" id="115" lemma="Motiv" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.18518518518518523">Motiv</W>
<W cur="791" id="116" lemma="sich" pos="PRF" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.0">sich</W>
<W cur="796" id="117" lemma="darin" pos="PAV" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.19999999999999996">darin</W>
<W cur="802" id="118" lemma="begründen" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.0">begründete</W>
<W cur="812" id="119" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="9" formal_similarity="0">,</W>
<W cur="814" id="120" lemma="dass" pos="KOUS" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.0">dass</W>
<W cur="819" id="121" lemma="er" pos="PPER" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.16666666666666663">er</W>
<W cur="822" id="122" lemma="nicht" pos="PTKNEG" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.125">nicht</W>
<W cur="828" id="123" lemma="gerne" pos="ADV" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.125">gerne</W>
<W cur="834" id="124" lemma="mit" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.5">mit</W>
<W cur="838" id="125" lemma="alt" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.19999999999999996">alten</W>
<W cur="844" id="126" lemma="Mensch" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.25">Menschen</W>
<W cur="853" id="127" lemma="arbeiten" pos="VVFIN" space=" " Prob1="-50" Prob2="-50" segId="9" formal_similarity="0.11111111111111116">arbeitete</W>
<W cur="862" id="128" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="9" formal_similarity="1.0">.</W>
<W cur="864" id="129" lemma="all" pos="PIAT" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.75">Alle</W>
<W cur="869" id="130" lemma="sein" pos="PPOSAT" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.0">seine</W>
<W cur="875" id="131" lemma="Opfer" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.0">Opfer</W>
<W cur="881" id="132" lemma="sein" pos="VAFIN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.6">waren</W>
<W cur="887" id="133" lemma="alt" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.25">alte</W>
<W cur="891" id="134" lemma="," pos="$," Prob1="-50" Prob2="-50" segId="10" formal_similarity="0">,</W>
<W cur="893" id="135" lemma="schwach" pos="ADJA" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.125">schwache</W>
<W cur="902" id="136" lemma="Frau" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.33333333333333337">Frauen</W>
<W cur="909" id="137" lemma="mit" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.5">mit</W>
<W cur="913" id="138" lemma="Herzproblem" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.6428571428571428">Herzproblemen</W>
<W cur="927" id="139" lemma="und" pos="KON" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.0">und</W>
<W cur="931" id="140" lemma="können" pos="VMFIN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.1428571428571429">konnten</W>
<W cur="939" id="141" lemma="als" pos="KOKOM" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.09999999999999998">als</W>
<W cur="943" id="142" lemma="Bürde" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.5">Bürde</W>
<W cur="949" id="143" lemma="für" pos="APPR" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.0">für</W>
<W cur="953" id="144" lemma="die" pos="ART" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.1428571428571429">das</W>
<W cur="957" id="145" lemma="Krankenhauspersonal" pos="NN" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.10526315789473684">Krankenhauspersonal</W>
<W cur="977" id="146" lemma="sehen" pos="VVPP" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.30000000000000004">gesehen</W>
<W cur="985" id="147" lemma="werden" pos="VAINF" space=" " Prob1="-50" Prob2="-50" segId="10" formal_similarity="0.16666666666666663">werden</W>
<W cur="991" id="148" lemma="." pos="$." Prob1="-50" Prob2="-50" segId="10" formal_similarity="1.0">.</W>
</Text>
\ No newline at end of file
This diff is collapsed.
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 8 17:15:55 2017
@author: Arndt
"""
import os
import numpy as np
from lxml import etree
SegmentTokDict={}
TokSegmentTokDict={}
AlignSegmentTokDict={}
alignmentdictTTST={}
alignmentdictSTTT={}
tokenidentifierdictwithspace={}
tokenidentifierdict={}
tokencursordict={}
cursortokendict={}
for dirs,subdirs,files in os.walk('..\\Alignments\\'):
for file in files:
if file.endswith("src") :
with open(dirs+"//"+file,"r",encoding="utf-8") as myfile:
mytext=myfile.read()
mytext=mytext.replace("\"s","\" s")
# mytext=bytearray(mytext, 'utf8')#("\"s","\" s")
root = etree.fromstring(bytes(mytext,"utf-8"))
file=file.replace(".src","")
for Token in root.iter("W"):
if int(Token.attrib["id"]) not in SegmentTokDict.setdefault(file,{}).setdefault("SourceText",{}).setdefault(int(Token.attrib["segId"]),[]):
SegmentTokDict.setdefault(file,{}).setdefault("SourceText",{}).setdefault(int(Token.attrib["segId"]),[]).append(int(Token.attrib["id"]))
TokSegmentTokDict.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):int(Token.attrib["segId"])})
try:
tokenidentifierdictwithspace.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):Token.attrib["space"]+Token.text.replace("\'","\'").replace("’","\'")})
except:
tokenidentifierdictwithspace.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):Token.text.replace("\'","\'").replace("’","\'")})
tokenidentifierdict.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):Token.text.replace("\'","\'").replace("’","\'")})
tokencursordict.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):Token.attrib["cur"]})
cursortokendict.setdefault(file,{}).setdefault("SourceText",{}).update({Token.attrib["cur"]:int(Token.attrib["id"])})
elif file.endswith("tgt"):
with open(dirs+"//"+file,"r",encoding="utf-8") as myfile:
mytext=myfile.read()
mytext=mytext.replace("\"s","\" s")
# mytext=bytearray(mytext, 'utf8')#("\"s","\" s")
root = etree.fromstring(bytes(mytext,"utf-8"))
file=file.replace(".tgt","")
for Token in root.iter("W"):
if int(Token.attrib["id"]) not in SegmentTokDict.setdefault(file,{}).setdefault("FinalText",{}).setdefault(int(Token.attrib["segId"]),[]):
SegmentTokDict.setdefault(file,{}).setdefault("FinalText",{}).setdefault(int(Token.attrib["segId"]),[]).append(int(Token.attrib["id"]))
TokSegmentTokDict.setdefault(file,{}).setdefault("FinalText",{}).update({int(Token.attrib["id"]):int(Token.attrib["segId"])})
try:
tokenidentifierdictwithspace.setdefault(file,{}).setdefault("FinalText",{}).update({int(Token.attrib["id"]):Token.attrib["space"]+Token.text.replace("\'","\'").replace("’","\'")})
except:
tokenidentifierdictwithspace.setdefault(file,{}).setdefault("FinalText",{}).update({int(Token.attrib["id"]):Token.text.replace("\'","\'").replace("’","\'")})
tokenidentifierdict.setdefault(file,{}).setdefault("FinalText",{}).update({int(Token.attrib["id"]):Token.text.replace("\'","\'").replace("’","\'")})
elif file.endswith("atag"):
with open(dirs+"//"+file,"r",encoding="utf-8") as myfile:
mytext=myfile.read()
mytext=mytext.replace("\"s","\" s")
# mytext=bytearray(mytext, 'utf8')#("\"s","\" s")
root = etree.fromstring(bytes(mytext,"utf-8"))
file=file.replace(".atag","")
alignmentdictSTTT.setdefault(file,{})
alignmentdictTTST.setdefault(file,{})
for alignment in root.iter("align"):
alignmentdictSTTT.setdefault(file,{}).setdefault(int(alignment.attrib["out"].replace("a","")),[]).append(int(alignment.attrib["in"].replace("b","")))
#
for alignment in root.iter("align"):
alignmentdictTTST.setdefault(file,{}).setdefault(int(alignment.attrib["in"].replace("b","")),[]).append(int(alignment.attrib["out"].replace("a","")))
for alignment in root.iter("salign"):
AlignSegmentTokDict.setdefault("SourceText",{}).setdefault(file,{}).setdefault(int(alignment.attrib["src"]),[]).append(int(alignment.attrib["tgt"]))
AlignSegmentTokDict.setdefault("FinalText",{}).setdefault(file,{}).setdefault(int(alignment.attrib["tgt"]),[]).append(int(alignment.attrib["src"]))
# TokSegmentTokDict.setdefault(file,{}).setdefault("SourceText",{}).update({int(Token.attrib["id"]):int(Token.attrib["segId"])})
#%%
# import os
KDdict={}
TokKDdict={}
for dirs,subdirs,files in os.walk("../KDFiles"):
for file in files:
if file.endswith(".kd") :
with open(dirs+"\\"+file,"r",encoding="utf-8") as infile:
for i,line in enumerate(infile):
line=line.replace("\n","").split("\t")
for j,item in enumerate(line):
try:
line[j]=int(line[j])
except:
pass
if i==0:
header=line
else:
for j,item in enumerate(line):
if header[j]=="Char":
item=item.replace("\"","")
if line[header.index("Type")]=="Mdel":
item=f"[{item}]"
if header[j]=="Time":
KDdict.setdefault(line[header.index("Session")],{}).setdefault(line[header.index("Id")],{}).setdefault("OrigTime",item)
KDdict.setdefault(line[header.index("Session")],{}).setdefault(line[header.index("Id")],{}).setdefault(header[j],item)
TokKDdict.setdefault(line[header.index("Session")],{}).setdefault(line[header.index("TTid")],{}).setdefault(header[j],[]).append(item)
#%%
import re
print("Gather Translog")
from lxml import etree
import time
TranslogPositionDict={}
cursorxydict={}
tokenxydict={}
Translationslist={}
KDinformdict={}
for dirs,subdirs,files in os.walk('..\Translogs\\'):
for file in files:
print(file)
cursorlist=[]
cursordict={}
Xdict={}
Ydict={}
# XYrangedict={}
wordmargin=""
cursorlist=[]
identifier=0
tokendict={}
trackinglist=[]
# print(file)
# if xmlfile.endswith(".xml"):
with open(dirs+"//"+file,"r", encoding="utf-8") as myfile:
root = etree.parse(myfile)
file=file.replace(".xml","")
ylevellist=[]
Translationslist.setdefault("FinalText",{}).update({file:file[-5:]})
Translationslist.setdefault("SourceText",{}).setdefault(file[-5:],[]).append(file)
for element in root.iter("Key"):
if int(element.attrib["Time"]) not in KDinformdict.setdefault(file,{}).setdefault("FinalText",{}):
KDinformdict.setdefault(file,{}).setdefault("FinalText",{}).update({int(element.attrib["Time"]):element.attrib})
else:
KDinformdict.setdefault(file,{}).setdefault("FinalText",{}).update({int(element.attrib["Time"])+1:element.attrib})
#%%
for translation in KDdict:
controllist=[]
for mod in KDdict[translation]:
searchterm=KDdict[translation][mod]["OrigTime"]
if searchterm in KDinformdict[translation]["FinalText"]:
controllist.append(searchterm)
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("X",int(KDinformdict[translation]["FinalText"][searchterm]["X"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Y",int(KDinformdict[translation]["FinalText"][searchterm]["Y"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Value",KDinformdict[translation]["FinalText"][searchterm]["Value"])
if KDinformdict[translation]["FinalText"][searchterm]["Value"]=="#":
KDdict[translation][mod]["Char"]="#"
# if KDinformdict[translation]["FinalText"][searchterm]["Value"]=="&quot;":
# KDdict[translation][mod]["Char"]=""
if "Height" in KDdict.setdefault(translation,{}).setdefault(mod,{}):
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Width",int(KDinformdict[translation]["FinalText"][searchterm]["Height"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Width",int(KDinformdict[translation]["FinalText"][searchterm]["Width"]))
# break
else:
comparelist=[]
for item in KDinformdict[translation]["FinalText"]:
comparelist.append(abs(item-searchterm))
searchterm=list(KDinformdict[translation]["FinalText"].keys())[comparelist.index(min(comparelist))]
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("X",int(KDinformdict[translation]["FinalText"][searchterm]["X"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Y",int(KDinformdict[translation]["FinalText"][searchterm]["Y"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Value",KDinformdict[translation]["FinalText"][searchterm]["Value"])
if "Height" in KDdict.setdefault(translation,{}).setdefault(mod,{}):
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Width",int(KDinformdict[translation]["FinalText"][searchterm]["Height"]))
KDdict.setdefault(translation,{}).setdefault(mod,{}).setdefault("Width",int(KDinformdict[translation]["FinalText"][searchterm]["Width"]))
# break
#%%
for translation in TokKDdict:
with open("C:\\Users\\Arndt\\Desktop\\TRICKLET\\AMP22\\Tables\\PuzzlesUpd\\"+translation+".pzl","w",encoding="utf-8") as outfile:
for i,token in enumerate(sorted(list(TokKDdict[translation].keys()))):
line=[]
header=[]
if i==0: