generic/xml_schemas
16
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Compare commits

base: generic:master
Branches Tags
generic:master
generic:simon
..
compare: generic:simon
Branches Tags
generic:master
generic:simon

1 Commits
master ... simon

Author SHA1 Message Date
Simon Krek
2448a05c29 Testing git push 2020-03-11 14:56:16 +01:00
25 changed files with 132 additions and 13047 deletions
Show Stats Expand all files Collapse all files

1
.gitignore vendored
View File

@ -1 +0,0 @@
tmp

2623
examples/bilingual_dictionaries/vsms-sample.xml
View File

File diff suppressed because it is too large Load Diff

32
examples/bilingual_dictionaries/vsms1.xml
View File

@ -61,7 +61,7 @@
<label type="type3">value7</label> <label type="type3">value7</label>
</labelList> </labelList>
<translation targetLang="hun" source="source1">hiša</translation> <translation targetLang="hun" source="source1">hiša</translation>
<explanationList/> <explanation/>
</translationContainer> </translationContainer>
<translationContainer cluster="1"> <translationContainer cluster="1">
<translation targetLang="hun">dom</translation> <translation targetLang="hun">dom</translation>
@ -71,14 +71,12 @@
<exampleContainerList> <exampleContainerList>
<exampleContainer> <exampleContainer>
<corpusExample example_id="4343" modified="true" audio="audio-465346">Kupili smo <comp role="headword">hišo</comp>.</corpusExample> <corpusExample example_id="4343" modified="true" audio="audio-465346">Kupili smo <comp role="headword">hišo</comp>.</corpusExample>
<translationContainerList> <translationContainer>
<translationContainer> <labelList>
<labelList> <label type="type5">value8</label>
<label type="type5">value8</label> </labelList>
</labelList> <translation targetLang="hun">Blah blah blah 1.</translation>
<translation targetLang="hun">Blah blah blah 1.</translation> </translationContainer>
</translationContainer>
</translationContainerList>
</exampleContainer> </exampleContainer>
<exampleContainer> <exampleContainer>
<multiwordExample lexical_unit_id="19" type="collocation" audio="audio-56643"> <multiwordExample lexical_unit_id="19" type="collocation" audio="audio-56643">
@ -86,19 +84,15 @@
<comp role="collocate" sloleks="LE_blahblah">ogledati</comp> <comp role="collocate" sloleks="LE_blahblah">ogledati</comp>
<comp role="headword">hiša</comp> <comp role="headword">hiša</comp>
</multiwordExample> </multiwordExample>
<translationContainerList> <translationContainer>
<translationContainer> <translation targetLang="hun" source="source2" audio="audio-blah-77242">blah blah2</translation>
<translation targetLang="hun" source="source2" audio="audio-blah-77242">blah blah2</translation> </translationContainer>
</translationContainer>
</translationContainerList>
</exampleContainer> </exampleContainer>
<exampleContainer> <exampleContainer>
<corpusExample example_id="552439" modified="false" lexical_unit_id="19"><comp role="collocate">Ogledali</comp> smo <comp role="collocate">si</comp> <comp role="headword">hišo</comp>.</corpusExample> <corpusExample example_id="552439" modified="false" lexical_unit_id="19"><comp role="collocate">Ogledali</comp> smo <comp role="collocate">si</comp> <comp role="headword">hišo</comp>.</corpusExample>
<translationContainerList> <translationContainer>
<translationContainer> <translation targetLang="hun" source="source2">Blah blah blah 3.</translation>
<translation targetLang="hun" source="source2">Blah blah blah 3.</translation> </translationContainer>
</translationContainer>
</translationContainerList>
</exampleContainer> </exampleContainer>
</exampleContainerList> </exampleContainerList>
</sense> </sense>

84
examples/collocation_dictionary/collocations_manual_absorbirati.xml Normal file
View File

@ -0,0 +1,84 @@
<dictionary>
<entry>
<head>
<headword>
<lemma>absorbirati</lemma>
</headword>
<lexicalUnit id="294" type="single">
<lexeme>absorbirati</lexeme>
</lexicalUnit>
<grammar>
<category>glagol</category>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 1.0">3295</measure>
</measureList>
</head>
<body>
<senseList>
<sense id="1">
<syntacticStructureList>
<syntacticStructure id="34" name="gbz_pp_sbz2" pp="brez">
<exampleContainerList>
<exampleContainer>
<multiwordExample type="collocation" cluster="1" frequency="5" logDice="2.23">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_4485e634af6a4b16093fe3140632418a">brez</comp>
<comp num="3" role="collocate" sloleks="LE_b66fc194167f71cb086b3c0b80820711">težave</comp>
</multiwordExample>
</exampleContainer>
<exampleContainer>
<multiwordExample type="collocation" cluster="1" frequency="14" logDice="11.25">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_ba405c6d2b3a4b0cf9f6216af3812c6b">brez</comp>
<comp num="3" role="collocate" sloleks="LE_274a6fc240c9e3c4c2dc3e4804a0c11f">zahteve</comp>
</multiwordExample>
</exampleContainer>
</exampleContainerList>
</syntacticStructure>
<syntacticStructure id="34" name="gbz_pp_sbz2" pp="iz">
<exampleContainerList>
<exampleContainer>
<multiwordExample type="collocation" cluster="2" frequency="14" logDice="11.25">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_ba405c6d2b3a4b0cf9f6216af3812c6b">iz</comp>
<comp num="3" role="collocate" sloleks="LE_274a6fc240c9e3c4c2dc3e4804a0c11f">prebavila</comp>
</multiwordExample>
</exampleContainer>
<exampleContainer>
<multiwordExample type="collocation" cluster="2" frequency="14" logDice="11.25">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_ba405c6d2b3a4b0cf9f6216af3812c6b">iz</comp>
<comp num="3" role="collocate" sloleks="LE_274a6fc240c9e3c4c2dc3e4804a0c11f">želodca</comp>
</multiwordExample>
</exampleContainer>
</exampleContainerList>
</syntacticStructure>
</syntacticStructureList>
</sense>
<sense id="2">
<syntacticStructureList>
<syntacticStructure id="34" name="gbz_pp_sbz2" pp="brez">
<exampleContainerList>
<exampleContainer>
<multiwordExample type="collocation" cluster="1" frequency="5" logDice="2.23">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_4485e634af6a4b16093fe3140632418a">brez</comp>
<comp num="3" role="collocate" sloleks="LE_b66fc194167f71cb086b3c0b80820711">težave</comp>
</multiwordExample>
</exampleContainer>
<exampleContainer>
<multiwordExample type="collocation" cluster="2" frequency="14" logDice="11.25">
<comp num="1" role="headword" sloleks="LE_a293f9ab871299f116dff2cc1421367a">absorbirati</comp>
<comp num="2" role="other" sloleks="LE_ba405c6d2b3a4b0cf9f6216af3812c6b">brez</comp>
<comp num="3" role="collocate" sloleks="LE_274a6fc240c9e3c4c2dc3e4804a0c11f">prebavila</comp>
</multiwordExample>
</exampleContainer>
</exampleContainerList>
</syntacticStructure>
</syntacticStructureList>
</sense>
</senseList>
</body>
</entry>
</dictionary>

1
examples/monolingual_dictionaries/mononlingual_manual_example.xml
View File

@ -1,4 +1,5 @@
<dictionary> <dictionary>
<!-- testing git -->
<entry> <entry>
<head> <head>
<headword> <headword>

257
examples/monolingual_dictionaries/structure_pipeline_output.xml
View File

@ -1,257 +0,0 @@
<dictionary>
<entry>
<head>
<headword>
<lemma>obljubiti večno zvestobo komu</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="138">
<component num="1">
<lexeme lemma="obljubiti" msd="Ggdn">obljubiti</lexeme>
</component>
<component num="2">
<lexeme lemma="večen" msd="Ppnzet">večno</lexeme>
</component>
<component num="3">
<lexeme lemma="zvestoba" msd="Sozet">zvestobo</lexeme>
</component>
<component num="4">
<lexeme lemma="kdo" msd="Zv-med">komu</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>kovati koga/kaj v nebo</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="183">
<component num="1">
<lexeme lemma="kovati" msd="Ggnn">kovati</lexeme>
</component>
<component num="2">
<lexeme lemma="kdo" msd="Zv-met">koga</lexeme>
</component>
<component num="3">
<lexeme msd="U">/</lexeme>
</component>
<component num="4">
<lexeme lemma="kaj" msd="Zv-sei">kaj</lexeme>
</component>
<component num="5">
<lexeme lemma="v" msd="Dt">v</lexeme>
</component>
<component num="6">
<lexeme lemma="nebo" msd="Soset">nebo</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>kaj v malem</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="674">
<component num="1">
<lexeme lemma="kaj" msd="Zv-sei">kaj</lexeme>
</component>
<component num="2">
<lexeme lemma="v" msd="Dm">v</lexeme>
</component>
<component num="3">
<lexeme lemma="mali" msd="Ppnsem">malem</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>počutiti se kot riba na suhem</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="773">
<component num="1">
<lexeme lemma="počutiti" msd="Ggnn">počutiti</lexeme>
</component>
<component num="2">
<lexeme lemma="se" msd="Zp------k">se</lexeme>
</component>
<component num="3">
<lexeme lemma="kot" msd="Vd">kot</lexeme>
</component>
<component num="4">
<lexeme lemma="riba" msd="Sozei">riba</lexeme>
</component>
<component num="5">
<lexeme lemma="na" msd="Dm">na</lexeme>
</component>
<component num="6">
<lexeme lemma="suh" msd="Ppnsem">suhem</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>jemati koga/kaj pod drobnogled</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="183">
<component num="1">
<lexeme lemma="jemati" msd="Ggnn">jemati</lexeme>
</component>
<component num="2">
<lexeme lemma="kdo" msd="Zv-met">koga</lexeme>
</component>
<component num="3">
<lexeme msd="U">/</lexeme>
</component>
<component num="4">
<lexeme lemma="kaj" msd="Zv-set">kaj</lexeme>
</component>
<component num="5">
<lexeme lemma="pod" msd="Dt">pod</lexeme>
</component>
<component num="6">
<lexeme lemma="drobnogled" msd="Sometn">drobnogled</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>na slepo</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="892">
<component num="1">
<lexeme lemma="na" msd="Dt">na</lexeme>
</component>
<component num="2">
<lexeme lemma="slep" msd="Ppnset">slepo</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>bati se za svojo glavo</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="736">
<component num="1">
<lexeme lemma="bati" msd="Ggnn">bati</lexeme>
</component>
<component num="2">
<lexeme lemma="se" msd="Zp------k">se</lexeme>
</component>
<component num="3">
<lexeme lemma="za" msd="Dt">za</lexeme>
</component>
<component num="4">
<lexeme lemma="svoj" msd="Zp-zet">svojo</lexeme>
</component>
<component num="5">
<lexeme lemma="glava" msd="Sozet">glavo</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>luč na koncu tunela</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="730">
<component num="1">
<lexeme lemma="luč" msd="Sozei">luč</lexeme>
</component>
<component num="2">
<lexeme lemma="na" msd="Dm">na</lexeme>
</component>
<component num="3">
<lexeme lemma="konec" msd="Somem">koncu</lexeme>
</component>
<component num="4">
<lexeme lemma="tunel" msd="Somer">tunela</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>skrajni čas je, da</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="1545">
<component num="1">
<lexeme lemma="skrajen" msd="Ppnmeid">skrajni</lexeme>
</component>
<component num="2">
<lexeme lemma="čas" msd="Somei">čas</lexeme>
</component>
<component num="3">
<lexeme lemma="biti" msd="Gp-ste-n">je</lexeme>
</component>
<component num="4">
<lexeme msd="U">,</lexeme>
</component>
<component num="5">
<lexeme lemma="da" msd="Vd">da</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
<entry>
<head>
<headword>
<lemma>zardeti kot kuhan rak</lemma>
</headword>
<lexicalUnit type="MWE" structure_id="151">
<component num="1">
<lexeme lemma="zardeti" msd="Ggdn">zardeti</lexeme>
</component>
<component num="2">
<lexeme lemma="kot" msd="Vd">kot</lexeme>
</component>
<component num="3">
<lexeme lemma="kuhan" msd="Pdnmein">kuhan</lexeme>
</component>
<component num="4">
<lexeme lemma="rak" msd="Somei">rak</lexeme>
</component>
</lexicalUnit>
</head>
<body>
<senseList/>
</body>
</entry>
</dictionary>

86
examples/morphological_lexicon/Amanda.xml
View File

@ -1,86 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_ids="342" dynamic_accentuation_ids="81" pronunciation_ids="32|33" hyphenation_ids="7" tonemic_accentuation_ids="85">Amanda</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_Amanda" type="single">
<lexeme lexical_unit_lexeme_id="83224">Amanda</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<subcategory type="pronunciation">ambiguous</subcategory>
<grammarFeature name="type">proper</grammarFeature>
<grammarFeature name="gender">feminine</grammarFeature>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">285818</measure>
</measureList>
<relatedEntryList/>
</head>
<body>
<wordFormList>
<wordForm id="333330">
<msd language="sl" system="JOS">Slzei</msd>
<msd language="en" system="UD">PROPN|...</msd>
<grammarFeatureList>
<grammarFeature name="number">singular</grammarFeature>
<grammarFeature name="case">nominative</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="Sz.1.2.0">
<form>Amanda</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
</orthographyList>
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" accentuationPatterns="cjvt:AP.1|zrc:S202b">
<form>Amánda</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">77</measure>
</measureList>
</accentuation>
<accentuation id="82" orthography_id="342" accentuationPatterns="cjvt:no_accentuation|zrc:no_accentuation"/>
</accentuationList>
<accentuationList type="tonemic">
<accentuation id="85" orthography_id="342" accentuationPatterns="zrc:S202b|zrc:S202i">
<form>Amànda</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="115" type="slovene">
<form script="IPA">aˈmaːnda</form>
<form script="SAMPA">a"ma:nda</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="33" dynamic_accentuation_id="82" type="english">
<form script="IPA">əˈmɛːnda</form>
<form script="SAMPA">ə"mE:nda</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList>
<hyphenation id="7" orthography_id="342">
<form>A|man|da</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
</hyphenationList>
</formRepresentations>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>

75
examples/morphological_lexicon/PCR.xml
View File

@ -1,75 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_ids="342" dynamic_accentuation_ids="81" pronunciation_ids="32|33|34" hyphenation_ids="" tonemic_accentuation_ids="85">PCR</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_PCR" type="single">
<lexeme lexical_unit_lexeme_id="83224">PCR</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<subcategory type="pronunciation">acronym</subcategory>
<grammarFeature name="type">common</grammarFeature>
<grammarFeature name="gender">masculine</grammarFeature>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">285818</measure>
</measureList>
<relatedEntryList/>
</head>
<body>
<wordFormList>
<wordForm id="333330">
<msd language="sl" system="JOS">Somei</msd>
<msd language="en" system="UD">NOUN|...</msd>
<grammarFeatureList>
<grammarFeature name="number">singular</grammarFeature>
<grammarFeature name="case">nominative</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="Sm.5.1.o">
<form>PCR</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
</orthographyList>
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" accentuationPatterns="cjvt:no_accentuation"/>
</accentuationList>
<accentuationList type="tonemic">
<accentuation id="85" orthography_id="342" accentuationPatterns="zrc:no_accentuation"/>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="81" type="slovene_spelling_short" status="preferred">
<form script="IPA">ˈpəˈtsəˈrə</form>
<form script="SAMPA">"p@"ts@"r@</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="33" dynamic_accentuation_id="81" type="slovene_spelling_long">
<form script="IPA">ˈpeːˈʦeːˈɛɾ</form>
<form script="SAMPA">"pe:"tse:"E:r</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="34" dynamic_accentuation_id="81" type="english_spelling">
<form script="IPA">ˈpiːˈsiːˈaːɾ</form>
<form script="SAMPA">"pi:"si:"a:r</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList/>
</formRepresentations>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>

70
examples/morphological_lexicon/Shakespeare.xml
View File

@ -1,70 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_ids="342" dynamic_accentuation_ids="81" pronunciation_ids="32|33" hyphenation_ids="" tonemic_accentuation_ids="85">Shakespeare</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_Shakespeare" type="single">
<lexeme lexical_unit_lexeme_id="83224">Shakespeare</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<subcategory type="pronunciation">other</subcategory>
<grammarFeature name="type">proper</grammarFeature>
<grammarFeature name="gender">masculine</grammarFeature>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">285818</measure>
</measureList>
<relatedEntryList/>
</head>
<body>
<wordFormList>
<wordForm id="333330">
<msd language="sl" system="JOS">Slmei</msd>
<msd language="en" system="UD">PROPN|...</msd>
<grammarFeatureList>
<grammarFeature name="number">singular</grammarFeature>
<grammarFeature name="case">nominative</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="Sm.5.1.o">
<form>Shakespeare</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
</orthographyList>
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" accentuationPatterns="cjvt:no_accentuation"/>
</accentuationList>
<accentuationList type="tonemic">
<accentuation id="82" orthography_id="342" accentuationPatterns="cjvt:no_accentuation"/>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="81" status="preferred">
<form script="IPA">ˈʃɛːɪkspiɾ</form>
<form script="SAMPA">"SE:Ikspir</form>
<form script="slovene_phonetization">šêjkspir</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="33" dynamic_accentuation_id="81">
<form script="IPA">ˈʃeːkspiɾ</form>
<form script="SAMPA">"Se:kspir</form>
<form script="slovene_phonetization">šékspir</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList/>
</formRepresentations>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>

2629
examples/morphological_lexicon/clarin_sample.xml
View File

File diff suppressed because it is too large Load Diff

84
examples/morphological_lexicon/gostja.xml
View File

@ -1,84 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_ids="342" dynamic_accentuation_ids="81" pronunciation_ids="32" hyphenation_ids="7|8" tonemic_accentuation_ids="85">gostja</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_gostja" type="single">
<lexeme lexical_unit_lexeme_id="83224">gostja</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<subcategory type="pronunciation">slovene</subcategory>
<grammarFeature name="type">common</grammarFeature>
<grammarFeature name="gender">feminine</grammarFeature>
</grammar>
<measureList>
<measure type="frequency" source="Gigafida 2.0">285818</measure>
</measureList>
<relatedEntryList/>
</head>
<body>
<wordFormList>
<wordForm id="333330">
<msd language="sl" system="JOS">Sozei</msd>
<msd language="en" system="UD">NOUN|...</msd>
<grammarFeatureList>
<grammarFeature name="number">singular</grammarFeature>
<grammarFeature name="case">nominative</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="Sz.1.2.0">
<form>gostja</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
</orthographyList>
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" accentuationPatterns="cjvt:AP.1|zrc:S202b" status="preferred">
<form>gôstja</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">77</measure>
</measureList>
</accentuation>
</accentuationList>
<accentuationList type="tonemic">
<accentuation id="85" orthography_id="342" accentuationPatterns="zrc:S202b|zrc:S202i" status="preferred">
<form>góstja</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="81" tonemic_accentuation_id="85">
<form script="IPA">ˈɡo:stja</form>
<form script="SAMPA">"gO:stja</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList>
<hyphenation id="7" orthography_id="342" status="preferred">
<form>go|stja</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
<hyphenation id="8" orthography_id="342">
<form>gos|tja</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
</hyphenationList>
</formRepresentations>
</wordForm>
</wordFormList>
</body>
</entry>
</lexicon>

440
examples/semantic_types/semantic_types_sample.xml
View File

@ -1,440 +0,0 @@
<semanticTypes>
<semanticType SEMCODE="20">
<name sl="AKTIVNOST">ACT</name>
<semanticType SEMCODE="20.1">
<name sl="DEJANJE">ACTION</name>
<semanticType SEMCODE="20.1.2">
<name sl="čustveno">emotional</name>
</semanticType>
<semanticType SEMCODE="20.1.16">
<name sl="dogodek_človeški">event_human</name>
</semanticType>
<semanticType SEMCODE="20.1.14">
<name sl="družbeno">social</name>
</semanticType>
<semanticType SEMCODE="20.1.8">
<name sl="gibanje">movement</name>
</semanticType>
<semanticType SEMCODE="20.1.3">
<name sl="kognicija">cognition</name>
</semanticType>
<semanticType SEMCODE="20.1.4">
<name sl="komunikacija">communication</name>
<semanticType SEMCODE="20.1.4.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="20.1.4.2">
<name sl="nečloveška">nonhuman</name>
</semanticType>
<semanticType SEMCODE="20.1.4.3">
<name sl="pisna_govorna">written_spoken</name>
</semanticType>
<semanticType SEMCODE="20.1.4.4">
<name sl="telesna">physical</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="20.1.12">
<name sl="lastnina">property</name>
</semanticType>
<semanticType SEMCODE="20.1.13">
<name sl="medicinski_postopek">medical_procedure</name>
</semanticType>
<semanticType SEMCODE="20.1.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="20.1.5">
<name sl="percepcija">perception</name>
</semanticType>
<semanticType SEMCODE="20.1.18">
<name sl="pojav">phenomenon</name>
<semanticType SEMCODE="20.1.18.1">
<name sl="ostalo">other</name>
</semanticType>
<semanticType SEMCODE="20.1.18.2">
<name sl="zvočni">sound</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="20.1.6">
<name sl="sprememba">change</name>
</semanticType>
<semanticType SEMCODE="20.1.17">
<name sl="stanje">state</name>
<semanticType SEMCODE="20.1.17.1">
<name sl="fazno">phase</name>
</semanticType>
<semanticType SEMCODE="20.1.17.2">
<name sl="modalno">modal</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="20.1.7">
<name sl="stik">contact</name>
</semanticType>
<semanticType SEMCODE="20.1.15">
<name sl="tekmovanje">contest</name>
</semanticType>
<semanticType SEMCODE="20.1.9">
<name sl="telesno">physical</name>
<semanticType SEMCODE="20.1.9.1">
<name sl="nega">care</name>
</semanticType>
<semanticType SEMCODE="20.1.9.2">
<name sl="vitalno">vital</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="20.1.10">
<name sl="ustvarjanje">creation</name>
</semanticType>
<semanticType SEMCODE="20.1.11">
<name sl="zaužitje">consumption</name>
<semanticType SEMCODE="20.1.11.1">
<name sl="hrana_kuha">food_cooking</name>
</semanticType>
<semanticType SEMCODE="20.1.11.2">
<name sl="hrana_pridelava">food_production</name>
</semanticType>
<semanticType SEMCODE="20.1.11.3">
<name sl="hrana_uživanje">food_consumption</name>
</semanticType>
</semanticType>
</semanticType>
<semanticType SEMCODE="20.2">
<name sl="DEJAVNOST">ACTIVITY</name>
<semanticType SEMCODE="20.2.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="20.2.2">
<name sl="gospodarska">industrial</name>
</semanticType>
<semanticType SEMCODE="20.2.3">
<name sl="negospodarska">nonindustrial</name>
<semanticType SEMCODE="20.2.3.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="20.2.3.2">
<name sl="igra">game</name>
</semanticType>
<semanticType SEMCODE="20.2.3.3">
<name sl="ples">dance</name>
</semanticType>
<semanticType SEMCODE="20.2.3.4">
<name sl="šport">sport</name>
</semanticType>
</semanticType>
</semanticType>
</semanticType>
<semanticType SEMCODE="9">
<name sl="ARTEFAKT">ARTEFACT</name>
<semanticType SEMCODE="9.2">
<name sl="denar">money</name>
</semanticType>
<semanticType SEMCODE="9.3">
<name sl="dokument">document</name>
</semanticType>
<semanticType SEMCODE="9.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.4">
<name sl="glasbilo">instrument</name>
<semanticType SEMCODE="9.4.2">
<name sl="brenkalo">string_plucking</name>
</semanticType>
<semanticType SEMCODE="9.4.8">
<name sl="del_glasbila">part</name>
</semanticType>
<semanticType SEMCODE="9.4.3">
<name sl="godalo">string_bowing</name>
</semanticType>
<semanticType SEMCODE="9.4.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.4.4">
<name sl="pihalo">wind</name>
</semanticType>
<semanticType SEMCODE="9.4.9">
<name sl="pripomoček">tool</name>
</semanticType>
<semanticType SEMCODE="9.4.5">
<name sl="tipke">keyboard</name>
</semanticType>
<semanticType SEMCODE="9.4.6">
<name sl="tolkalo">percussion</name>
</semanticType>
<semanticType SEMCODE="9.4.7">
<name sl="trobilo">brass</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.5">
<name sl="komunikacija">communication</name>
<semanticType SEMCODE="9.5.1">
<name sl="IKT">ICT</name>
</semanticType>
<semanticType SEMCODE="9.5.2">
<name sl="znak_simbol">sign_symbol</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.6">
<name sl="naprava_pripomoček">device_apparatus</name>
<semanticType SEMCODE="9.6.1">
<name sl="naprava">device</name>
<semanticType SEMCODE="9.6.1.2">
<name sl="elektro_element">electrical_element</name>
</semanticType>
<semanticType SEMCODE="9.6.1.3">
<name sl="hišna">domestic</name>
</semanticType>
<semanticType SEMCODE="9.6.1.4">
<name sl="komunikacijska">communication</name>
</semanticType>
<semanticType SEMCODE="9.6.1.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.6.1.5">
<name sl="računalniška">computer</name>
</semanticType>
<semanticType SEMCODE="9.6.1.6">
<name sl="signalna">signalling</name>
</semanticType>
<semanticType SEMCODE="9.6.1.7">
<name sl="svetilna">light</name>
</semanticType>
<semanticType SEMCODE="9.6.1.8">
<name sl="zabavna">entertainment</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.6.2">
<name sl="orodje">tool</name>
</semanticType>
<semanticType SEMCODE="9.6.3">
<name sl="pripomoček">apparatus</name>
<semanticType SEMCODE="9.6.3.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.6.3.2">
<name sl="igrača">toy</name>
</semanticType>
<semanticType SEMCODE="9.6.3.3">
<name sl="kuhinjski">kitchen</name>
</semanticType>
<semanticType SEMCODE="9.6.3.4">
<name sl="merilni">measuring</name>
</semanticType>
<semanticType SEMCODE="9.6.3.5">
<name sl="pisarniški">office</name>
</semanticType>
<semanticType SEMCODE="9.6.3.6">
<name sl="svetilni">light</name>
</semanticType>
<semanticType SEMCODE="9.6.3.7">
<name sl="športni">sport</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.6.4">
<name sl="stroj">machine</name>
<semanticType SEMCODE="9.6.4.1">
<name sl="del_stroja">part</name>
</semanticType>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.7">
<name sl="oblačilo">apparel</name>
<semanticType SEMCODE="9.7.1">
<name sl="dodatek">accessory</name>
</semanticType>
<semanticType SEMCODE="9.7.2">
<name sl="nakit">jewellery</name>
</semanticType>
<semanticType SEMCODE="9.7.3">
<name sl="oblačilo">clothes</name>
</semanticType>
<semanticType SEMCODE="9.7.4">
<name sl="obutev">footgear</name>
</semanticType>
<semanticType SEMCODE="9.7.5">
<name sl="pokrivalo">headgear</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.8">
<name sl="orožje">weapon</name>
<semanticType SEMCODE="9.8.2">
<name sl="municija">ammunition</name>
</semanticType>
<semanticType SEMCODE="9.8.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.8.3">
<name sl="ročno">hand</name>
</semanticType>
<semanticType SEMCODE="9.8.4">
<name sl="vojaška_naprava">military_device</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.9">
<name sl="pohištvo_oprema">furniture_equipment</name>
<semanticType SEMCODE="9.9.1">
<name sl="del_opreme">part</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.10">
<name sl="posoda_shranjevanje">container_vessel</name>
</semanticType>
<semanticType SEMCODE="9.11">
<name sl="snov">substance</name>
<semanticType SEMCODE="9.11.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.11.2">
<name sl="farmacevtska">pharmaceutical</name>
</semanticType>
<semanticType SEMCODE="9.11.3">
<name sl="osebna_nega">body_care</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.12">
<name sl="tekstil">fabric</name>
</semanticType>
<semanticType SEMCODE="9.13">
<name sl="umetniški_izdelek">artwork</name>
</semanticType>
<semanticType SEMCODE="9.14">
<name sl="vozilo">vehicle</name>
<semanticType SEMCODE="9.14.1">
<name sl="kopensko">land</name>
</semanticType>
<semanticType SEMCODE="9.14.2">
<name sl="vesoljsko">space</name>
</semanticType>
<semanticType SEMCODE="9.14.3">
<name sl="vodno">water</name>
</semanticType>
<semanticType SEMCODE="9.14.4">
<name sl="zračno">air</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="9.15">
<name sl="zgradba">building</name>
<semanticType SEMCODE="9.15.2">
<name sl="bivališče">dwelling</name>
</semanticType>
<semanticType SEMCODE="9.15.3">
<name sl="del_zgradbe">part_of_building</name>
</semanticType>
<semanticType SEMCODE="9.15.4">
<name sl="delovišče">worksite</name>
</semanticType>
<semanticType SEMCODE="9.15.5">
<name sl="hramba">storage</name>
</semanticType>
<semanticType SEMCODE="9.15.6">
<name sl="infrastruktura">infrastructure</name>
</semanticType>
<semanticType SEMCODE="9.15.7">
<name sl="javnopolitična">public_political</name>
</semanticType>
<semanticType SEMCODE="9.15.8">
<name sl="kulturna">cultural</name>
</semanticType>
<semanticType SEMCODE="9.15.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="9.15.9">
<name sl="storitve">services</name>
</semanticType>
<semanticType SEMCODE="9.15.10">
<name sl="verska">religious</name>
</semanticType>
</semanticType>
</semanticType>
<semanticType SEMCODE="15">
<name sl="ČAS">TIME</name>
<semanticType SEMCODE="15.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="15.2">
<name sl="enota">unit</name>
</semanticType>
<semanticType SEMCODE="15.3">
<name sl="obdobje">period</name>
<semanticType SEMCODE="15.3.1">
<name sl="splošno">general</name>
</semanticType>
<semanticType SEMCODE="15.3.2">
<name sl="zgodovinsko">historic</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="15.4">
<name sl="trenutek">moment</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="1">
<name sl="ČLOVEK">HUMAN</name>
<semanticType SEMCODE="1.1">
<name sl="aktivnost">activity</name>
<semanticType SEMCODE="1.1.2">
<name sl="funkcija">function</name>
</semanticType>
<semanticType SEMCODE="1.1.3">
<name sl="nosilec">agent</name>
</semanticType>
<semanticType SEMCODE="1.1.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="1.1.4">
<name sl="poklic">profession</name>
</semanticType>
<semanticType SEMCODE="1.1.5">
<name sl="poklic_nosilec">profession_agent</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="1.2">
<name sl="lastnost">characteristic</name>
<semanticType SEMCODE="1.2.8">
<name sl="geografska">geographical</name>
</semanticType>
<semanticType SEMCODE="1.2.4">
<name sl="nazor">belief</name>
</semanticType>
<semanticType SEMCODE="1.2.6">
<name sl="nesorodstvena">nonkin</name>
</semanticType>
<semanticType SEMCODE="1.2.1">
<name sl="drugo">other</name>
</semanticType>
<semanticType SEMCODE="1.2.7">
<name sl="pripadnost">member</name>
</semanticType>
<semanticType SEMCODE="1.2.5">
<name sl="sorodstvena">kin</name>
</semanticType>
<semanticType SEMCODE="1.2.9">
<name sl="status">status</name>
</semanticType>
<semanticType SEMCODE="1.2.2">
<name sl="telesna">physical</name>
</semanticType>
<semanticType SEMCODE="1.2.3">
<name sl="umska_mentalna_vedenjska">intellectual_mental_behavioural</name>
</semanticType>
</semanticType>
<semanticType SEMCODE="1.3">
<name sl="mitologija">mythology</name>
</semanticType>
<semanticType SEMCODE="1.4">
<name sl="naziv">name</name>
<semanticType SEMCODE="1.4.3">
<name sl="akademski">academic</name>
</semanticType>
<semanticType SEMCODE="1.4.2">
<name sl="ime">personal</name>
</semanticType>
<semanticType SEMCODE="1.4.4">
<name sl="naslavljalni">title</name>
</semanticType>
<semanticType SEMCODE="1.4.5">
<name sl="plemiški">noble</name>
</semanticType>
<semanticType SEMCODE="1.4.1">
<name sl="vzdevek">nickname</name>
</semanticType>
</semanticType>
</semanticType>
</semanticTypes>

4276
examples/structures/structures_sample.xml
View File

File diff suppressed because it is too large Load Diff

221
examples/valency_lexicon/VS10_zvonkljati_sloleks22.xml
View File

@ -1,221 +0,0 @@
<dictionary xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="valency_lexicon.xsd">
<entry>
<head>
<headword>
<lemma>zvonkljati</lemma>
</headword>
<lexicalUnit>
<lexeme>zvonkljati</lexeme>
</lexicalUnit>
<grammar>
<category>glagol</category>
</grammar>
<measureList />
</head>
<body>
<statisticsContainerList>
<statisticsContainer>
<semanticRole>ACT</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.4000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.4000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>REC</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.4000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.4000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>CAUSE</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.2000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.2000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>MANN</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.2000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.2000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>LOC</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.6000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.6000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>COND</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.2000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.2000</measure>
</measureList>
</statisticsContainer>
<statisticsContainer>
<semanticRole>DUR</semanticRole>
<measureList>
<measure source="Gigafida 2.0" type="valency_pattern_ratio">0.2000</measure>
<measure source="Gigafida 2.0" type="valency_sentence_ratio">0.2000</measure>
</measureList>
</statisticsContainer>
</statisticsContainerList>
<senseList>
<sense>
<definitionList />
<valencyPatternList system="JOS">
<valencyPattern id="374">
<measureList>
<measure source="Gigafida 2.0" type="frequency_all">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>ACT</semanticRole>
<syntacticStructureList>
<syntacticStructure id="70" />
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>REC</semanticRole>
<syntacticStructureList>
<syntacticStructure id="22" />
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>CAUSE</semanticRole>
<syntacticStructureList>
<syntacticStructure id="13">
<component num="2">
<lexeme sloleks="274">z</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>KDO/KAJ zvonkljati KOMU/ČEMU ZAKAJ</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample corpusName="Gigafida 2.0" exampleId="GF5800693.856.5"><tree role="CAUSE"><comp num="2" structure_id="13">Z</comp> <comp num="3" structure_id="13">baldahina</comp> na odru za orkester</tree> je <comp role="headword">zvonkljala</comp> <tree role="REC"><comp num="2" structure_id="22">školjki</comp></tree> <tree role="ACT">podobna <comp num="1" structure_id="70">skleda</comp> s progastimi belimi rebri</tree>.</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
<valencyPattern id="6">
<measureList>
<measure source="Gigafida 2.0" type="frequency_all">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>ACT</semanticRole>
<syntacticStructureList>
<syntacticStructure id="70" />
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>MANN</semanticRole>
<syntacticStructureList>
<syntacticStructure id="13">
<component num="2">
<lexeme sloleks="244">prek</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>KDO/KAJ zvonkljati KAKO</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample corpusName="Gigafida 2.0" exampleId="GF0437765.773.8">Rajanje je preplavilo deželo, <tree role="ACT">stari egipčanski, babilonski, azteški, inkovski <comp num="1" structure_id="70">izganjalci</comp> zime, kurenti in Juriji</tree> so <comp role="headword">zvonkljali</comp> <tree role="MANN"><comp num="2" structure_id="13">prek</comp> <comp num="3" structure_id="13">polj</comp></tree>.</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
<valencyPattern id="62">
<measureList>
<measure source="Gigafida 2.0" type="frequency_all">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>LOC</semanticRole>
<syntacticStructureList>
<syntacticStructure id="15">
<component num="2">
<lexeme sloleks="234">po</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>COND</semanticRole>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>zvonkljati KJE POD KATERIM POGOJEM</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample corpusName="Gigafida 2.0" exampleId="GF9947624.333.2">Tako so <comp role="headword">zvonkljali</comp> <tree role="LOC"><comp num="2" structure_id="15">po</comp> izolski <comp num="3" structure_id="15">rivi</comp></tree>, <tree role="COND">da so</tree> še <tree role="COND">ribe gledale iz morja</tree>!</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
<valencyPattern id="391">
<measureList>
<measure source="Gigafida 2.0" type="frequency_all">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>REC</semanticRole>
<syntacticStructureList>
<syntacticStructure id="22" />
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>LOC</semanticRole>
<syntacticStructureList>
<syntacticStructure id="15">
<component num="2">
<lexeme sloleks="261">v</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
<semanticRoleContainer>
<semanticRole>DUR</semanticRole>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>zvonkljati KOMU/ČEMU KJE KOLIKO ČASA</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample corpusName="Gigafida 2.0" exampleId="GF1026195.985.2">Kje so tisti časi, ko se nihče ni razburjal, ker si je sloviti boksar Cassius Clay nadel ime Mohamed Ali in potem svoje nasprotnike še naprej pretepal, da <tree role="REC"><comp num="2" structure_id="22">jim</comp></tree> je še <tree role="DUR">mesece</tree> <comp role="headword">zvonkljalo</comp> <tree role="LOC"><comp num="2" structure_id="15">v</comp> <comp num="3" structure_id="15">glavah</comp></tree>, odtlej pod patronatom Alaha.</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
<valencyPattern id="27">
<measureList>
<measure source="Gigafida 2.0" type="frequency_all">1</measure>
</measureList>
<semanticRoleContainerList>
<semanticRoleContainer>
<semanticRole>LOC</semanticRole>
<syntacticStructureList>
<syntacticStructure id="15">
<component num="2">
<lexeme sloleks="216">na</lexeme>
</component>
</syntacticStructure>
</syntacticStructureList>
</semanticRoleContainer>
</semanticRoleContainerList>
<patternRepresentation>zvonkljati KJE</patternRepresentation>
<exampleContainerList>
<exampleContainer>
<corpusExample corpusName="Gigafida 2.0" exampleId="GF4530676.1098.1">Šla bova tja, kjer sneg leži v planinah,šla bova tja visoko nad borovje,šla k čredi, ki <comp role="headword">zvonklja</comp> <tree role="LOC"><comp num="2" structure_id="15">na</comp> <comp num="3" structure_id="15">košeninah</comp></tree>,<tree role="LOC">kjer se zavija v mavrično trakovjeJungfrau</tree>, <tree role="LOC">ki zlato sonce ima pod glavo</tree>,<tree role="LOC">kjer bistri jelen šviga skoz meglice</tree>,<tree role="LOC">kjer na oblake</tree>, <tree role="LOC">ki leté v daljavo</tree>,<tree role="LOC">mečejo senco orlov perutnice</tree>.</corpusExample>
</exampleContainer>
</exampleContainerList>
</valencyPattern>
</valencyPatternList>
</sense>
</senseList>
</body>
</entry>
</dictionary>

1578
examples/valency_lexicon/abdicirati.xml
View File

File diff suppressed because it is too large Load Diff

2
resources/schema/bilingual_dictionaries.xsd
View File

@ -35,14 +35,12 @@
<xsd:element name="sense" minOccurs="0" maxOccurs="unbounded"> <xsd:element name="sense" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType> <xsd:complexType>
<xsd:sequence> <xsd:sequence>
<xsd:element name="relatedSenseList" type="relatedSenseListType" minOccurs="0"/>
<xsd:element name="labelList" type="labelListType" minOccurs="0"/> <xsd:element name="labelList" type="labelListType" minOccurs="0"/>
<xsd:element name="definitionList" type="definitionListType" minOccurs="0"/> <xsd:element name="definitionList" type="definitionListType" minOccurs="0"/>
<xsd:element name="translationContainerList" type="translationContainerListType" minOccurs="0"/> <xsd:element name="translationContainerList" type="translationContainerListType" minOccurs="0"/>
<xsd:element name="exampleContainerList" type="exampleContainerListType" minOccurs="0"/> <xsd:element name="exampleContainerList" type="exampleContainerListType" minOccurs="0"/>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/> <xsd:attribute name="id" type="xsd:int"/>
<xsd:attribute name="dummy" type="xsd:boolean"/>
</xsd:complexType> </xsd:complexType>
</xsd:element> </xsd:element>
</xsd:sequence> </xsd:sequence>

26
resources/schema/morphological_lexicon.xsd → resources/schema/collocation_dictionary.xsd
View File

@ -5,7 +5,7 @@
schemaLocation="http://www.w3.org/2001/xml.xsd" /> schemaLocation="http://www.w3.org/2001/xml.xsd" />
<xsd:include schemaLocation="inventory.xsd"/> <xsd:include schemaLocation="inventory.xsd"/>
<xsd:element name="lexicon"> <xsd:element name="dictionary">
<xsd:complexType> <xsd:complexType>
<xsd:sequence> <xsd:sequence>
<xsd:element name="entry" minOccurs="0" maxOccurs="unbounded"> <xsd:element name="entry" minOccurs="0" maxOccurs="unbounded">
@ -16,19 +16,29 @@
<xsd:sequence> <xsd:sequence>
<xsd:element name="status" type="statusType" minOccurs="0"/> <xsd:element name="status" type="statusType" minOccurs="0"/>
<xsd:element name="headword" type="headwordType"/> <xsd:element name="headword" type="headwordType"/>
<xsd:element name="lexicalUnit" type="lexicalUnitType"/> <xsd:element name="lexicalUnit" type="lexicalUnitType" minOccurs="0"/>
<xsd:element name="grammar" type="grammarType"/> <xsd:element name="grammar" type="grammarType" minOccurs="0"/>
<xsd:element name="measureList" type="measureListType"/> <xsd:element name="measureList" type="measureListType" minOccurs="0"/>
<xsd:element name="relatedEntryList" type="relatedEntryListType" minOccurs="0"/>
<xsd:element name="labelList" type="labelListType" minOccurs="0"/>
<xsd:element name="comment" type="commentType" minOccurs="0"/>
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
</xsd:element> </xsd:element>
<xsd:element name="body"> <xsd:element name="body">
<xsd:complexType> <xsd:complexType>
<xsd:sequence> <xsd:sequence>
<xsd:element name="wordFormList" type="wordFormListType"/> <xsd:element name="senseList">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="sense" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="syntacticStructureList" type="syntacticStructureListType"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
</xsd:element> </xsd:element>

242
resources/schema/inventory.xsd
View File

@ -20,23 +20,9 @@
<xsd:enumeration value="single"/> <xsd:enumeration value="single"/>
<xsd:enumeration value="phrase"/> <xsd:enumeration value="phrase"/>
<xsd:enumeration value="compound"/> <xsd:enumeration value="compound"/>
<xsd:enumeration value="reflexive_verb"/>
</xsd:restriction> </xsd:restriction>
</xsd:simpleType> </xsd:simpleType>
</xsd:attribute> </xsd:attribute>
<xsd:attribute name="orthography_ids" type="xsd:string"/>
<xsd:attribute name="dynamic_accentuation_ids" type="xsd:string"/>
<xsd:attribute name="tonemic_accentuation_ids" type="xsd:string"/>
<xsd:attribute name="pronunciation_ids" type="xsd:string"/>
<xsd:attribute name="hyphenation_ids" type="xsd:string"/>
<xsd:attribute name="norm">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="non-standard"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:extension> </xsd:extension>
</xsd:simpleContent> </xsd:simpleContent>
</xsd:complexType> </xsd:complexType>
@ -62,13 +48,6 @@
</xsd:simpleContent> </xsd:simpleContent>
</xsd:complexType> </xsd:complexType>
<!-- List of grammatical features -->
<xsd:complexType name="grammarFeatureListType">
<xsd:sequence>
<xsd:element name="grammarFeature" type="grammarFeatureType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<!-- Lemma-disambiguating feature, more open-ended than grammarFeatureType --> <!-- Lemma-disambiguating feature, more open-ended than grammarFeatureType -->
<xsd:complexType name="homonymyFeatureType"> <xsd:complexType name="homonymyFeatureType">
<xsd:simpleContent> <xsd:simpleContent>
@ -114,10 +93,8 @@
<xsd:element name="component" type="componentType" minOccurs="2" maxOccurs="unbounded"/> <xsd:element name="component" type="componentType" minOccurs="2" maxOccurs="unbounded"/>
</xsd:choice> </xsd:choice>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/> <xsd:attribute name="id" type="xsd:int" use="required"/>
<xsd:attribute name="sloleksId" type="xsd:string"/> <xsd:attribute name="type" use="required"> <!-- types of headwords allowed; hmm, probably should standardise allowed settings -->
<xsd:attribute name="sloleksKey" type="xsd:string"/>
<xsd:attribute name="type"> <!-- types of headwords allowed; hmm, probably should standardise allowed settings -->
<xsd:simpleType> <xsd:simpleType>
<xsd:restriction base="xsd:string"> <xsd:restriction base="xsd:string">
<xsd:enumeration value="single"/> <xsd:enumeration value="single"/>
@ -144,25 +121,13 @@
<xsd:enumeration value="medmet"/> <xsd:enumeration value="medmet"/>
<xsd:enumeration value="okrajšava"/> <xsd:enumeration value="okrajšava"/>
<xsd:enumeration value="neuvrščeno"/> <xsd:enumeration value="neuvrščeno"/>
<xsd:enumeration value="stalna zveza"/>
<xsd:enumeration value="frazem"/>
<xsd:enumeration value="povratni glagol"/>
</xsd:restriction> </xsd:restriction>
</xsd:simpleType> </xsd:simpleType>
<xsd:complexType name="subcategoryType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="type" type="xsd:string"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<!-- Grammatical information --> <!-- Grammatical information -->
<xsd:complexType name="grammarType"> <xsd:complexType name="grammarType">
<xsd:sequence> <xsd:sequence>
<xsd:element name="category" type="categoryType" minOccurs="0"/> <!-- identifies the part of speech, unless it's not a single lexeme --> <xsd:element name="category" type="categoryType" minOccurs="0"/> <!-- identifies the part of speech, unless it's not a single lexeme -->
<xsd:element name="subcategory" type="subcategoryType" minOccurs="0" maxOccurs="unbounded"/> <!-- marks relevant subcategory information -->
<xsd:element name="grammarFeature" type="grammarFeatureType" minOccurs="0" maxOccurs="unbounded"/> <!-- relevant grammatical features --> <xsd:element name="grammarFeature" type="grammarFeatureType" minOccurs="0" maxOccurs="unbounded"/> <!-- relevant grammatical features -->
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
@ -172,7 +137,6 @@
<xsd:simpleContent> <xsd:simpleContent>
<xsd:extension base="xsd:decimal"> <xsd:extension base="xsd:decimal">
<xsd:attribute name="type" type="xsd:string" use="required"/> <!-- type of measure (e.g., frequency, logDice); hmm, probably should be enumerated --> <xsd:attribute name="type" type="xsd:string" use="required"/> <!-- type of measure (e.g., frequency, logDice); hmm, probably should be enumerated -->
<xsd:attribute name="corpus_id" type="xsd:int"/>
<xsd:attribute name="source" type="xsd:string"/> <!-- context of the measure, probably corpus name and version --> <xsd:attribute name="source" type="xsd:string"/> <!-- context of the measure, probably corpus name and version -->
</xsd:extension> </xsd:extension>
</xsd:simpleContent> </xsd:simpleContent>
@ -218,27 +182,6 @@
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
<!-- Related sense -->
<xsd:complexType name="relatedSenseType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="sense_id" type="xsd:int"/>
<xsd:attribute name="senseKey" type="xsd:string"/>
<xsd:attribute name="lexical_unit_id" type="xsd:int"/>
<xsd:attribute name="type" type="xsd:string"/>
<xsd:attribute name="synonymType" type="xsd:string"/>
<xsd:attribute name="synonymScore" type="xsd:decimal"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<!-- List of related senses -->
<xsd:complexType name="relatedSenseListType">
<xsd:sequence>
<xsd:element name="relatedSense" type="relatedSenseType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<!-- Name-value pair for providing extra information --> <!-- Name-value pair for providing extra information -->
<xsd:complexType name="labelType"> <xsd:complexType name="labelType">
<xsd:simpleContent> <xsd:simpleContent>
@ -278,7 +221,7 @@
<xsd:complexType name="translationType"> <xsd:complexType name="translationType">
<xsd:simpleContent> <xsd:simpleContent>
<xsd:extension base="xsd:string"> <xsd:extension base="xsd:string">
<xsd:attribute name="targetLang" type="xsd:string"/> <!-- target language --> <xsd:attribute name="targetLang" type="xsd:string" use="required"/> <!-- target language -->
<xsd:attribute name="source" type="xsd:string"/> <!-- where the translation comes from --> <xsd:attribute name="source" type="xsd:string"/> <!-- where the translation comes from -->
<xsd:attribute name="audio" type="xsd:string"/> <!-- legacy ID associated with an audio file --> <xsd:attribute name="audio" type="xsd:string"/> <!-- legacy ID associated with an audio file -->
</xsd:extension> </xsd:extension>
@ -309,19 +252,8 @@
</xsd:restriction> </xsd:restriction>
</xsd:simpleType> </xsd:simpleType>
</xsd:attribute> </xsd:attribute>
<xsd:attribute name="lemma" type="xsd:string"/>
<xsd:attribute name="msd" type="xsd:string"/> <!-- msd within the Slovene JOS system -->
<xsd:attribute name="sloleks" type="xsd:string"/> <!-- Sloleks ID --> <xsd:attribute name="sloleks" type="xsd:string"/> <!-- Sloleks ID -->
<xsd:attribute name="kol" type="xsd:string"/> <!-- legacy attribute for the word's lemma --> <xsd:attribute name="kol" type="xsd:string"/> <!-- legacy attribute for the word's lemma -->
<xsd:attribute name="lexical_unit_lexeme_id" type="xsd:int"/> <!-- ID within its lexical unit -->
<xsd:attribute name="lexeme_id" type="xsd:int"/> <!-- ID of the component's lexeme -->
<xsd:attribute name="space"> <!-- is the component followed by a space? only used if it isn't -->
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="false"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:extension> </xsd:extension>
</xsd:simpleContent> </xsd:simpleContent>
</xsd:complexType> </xsd:complexType>
@ -329,7 +261,7 @@
<!-- Mixed-content container element used in examples where roles can include multiple word components (e.g., semantic roles). --> <!-- Mixed-content container element used in examples where roles can include multiple word components (e.g., semantic roles). -->
<xsd:complexType name="exampleTreeType" mixed="true"> <xsd:complexType name="exampleTreeType" mixed="true">
<xsd:sequence> <xsd:sequence>
<xsd:element name="comp" type="compType" minOccurs="0" maxOccurs="unbounded"/> <!-- the tree contains one or more components --> <xsd:element name="comp" type="compType" maxOccurs="unbounded"/> <!-- the tree contains one or more components -->
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="role" type="semanticRoleType"/> <xsd:attribute name="role" type="semanticRoleType"/>
</xsd:complexType> </xsd:complexType>
@ -343,7 +275,6 @@
</xsd:choice> </xsd:choice>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="corpus_id" type="xsd:int"/> <xsd:attribute name="corpus_id" type="xsd:int"/>
<xsd:attribute name="corpusName" type="xsd:string"/>
<xsd:attribute name="example_id" type="xsd:int"/> <xsd:attribute name="example_id" type="xsd:int"/>
<xsd:attribute name="exampleId" type="xsd:string"/> <!-- the example's ID within the corpus itself --> <xsd:attribute name="exampleId" type="xsd:string"/> <!-- the example's ID within the corpus itself -->
<xsd:attribute name="modified" type="xsd:boolean"/> <!-- is the example text different than in the corpus? --> <xsd:attribute name="modified" type="xsd:boolean"/> <!-- is the example text different than in the corpus? -->
@ -367,7 +298,6 @@
<xsd:attribute name="lexical_unit_id" type="xsd:int"/> <xsd:attribute name="lexical_unit_id" type="xsd:int"/>
<xsd:attribute name="structure_id" type="xsd:int"/> <xsd:attribute name="structure_id" type="xsd:int"/>
<xsd:attribute name="structureName" type="xsd:string"/> <!-- a string name for the structure, especially if we don't have its ID --> <xsd:attribute name="structureName" type="xsd:string"/> <!-- a string name for the structure, especially if we don't have its ID -->
<xsd:attribute name="status" type="xsd:string"/>
<xsd:attribute name="frequency" type="xsd:int"/> <xsd:attribute name="frequency" type="xsd:int"/>
<xsd:attribute name="logDice" type="xsd:decimal"/> <xsd:attribute name="logDice" type="xsd:decimal"/>
<xsd:attribute name="audio" type="xsd:string"/> <!-- legacy ID associated with an audio file --> <xsd:attribute name="audio" type="xsd:string"/> <!-- legacy ID associated with an audio file -->
@ -378,13 +308,8 @@
<xsd:complexType name="translationContainerType"> <xsd:complexType name="translationContainerType">
<xsd:sequence> <xsd:sequence>
<xsd:element name="labelList" type="labelListType" minOccurs="0"/> <xsd:element name="labelList" type="labelListType" minOccurs="0"/>
<xsd:choice> <xsd:element name="translation" type="translationType"/>
<xsd:sequence> <xsd:element name="explanation" type="xsd:string" minOccurs="0"/> <!-- hmm: what's expected here? -->
<xsd:element name="translation" type="translationType"/>
<xsd:element name="explanationList" type="explanationListType" minOccurs="0"/>
</xsd:sequence>
<xsd:element name="explanationList" type="explanationListType"/>
</xsd:choice>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="cluster" type="xsd:int"/> <!-- number identifying a group of clustered translations --> <xsd:attribute name="cluster" type="xsd:int"/> <!-- number identifying a group of clustered translations -->
<xsd:attribute name="source" type="xsd:string"/> <!-- hmm, we already have @source under translationType, that's not enough? --> <xsd:attribute name="source" type="xsd:string"/> <!-- hmm, we already have @source under translationType, that's not enough? -->
@ -397,22 +322,6 @@
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
<!-- Explanation (in contrast with translation) -->
<xsd:complexType name="explanationType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="language" type="xsd:string"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<!-- List of explanations -->
<xsd:complexType name="explanationListType">
<xsd:sequence>
<xsd:element name="explanation" type="explanationType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<!-- Wrapper including an example and (possibly) its translation --> <!-- Wrapper including an example and (possibly) its translation -->
<xsd:complexType name="exampleContainerType"> <xsd:complexType name="exampleContainerType">
<xsd:sequence> <xsd:sequence>
@ -420,7 +329,7 @@
<xsd:element name="corpusExample" type="corpusExampleType"/> <xsd:element name="corpusExample" type="corpusExampleType"/>
<xsd:element name="multiwordExample" type="multipleLexemeExampleType"/> <xsd:element name="multiwordExample" type="multipleLexemeExampleType"/>
</xsd:choice> </xsd:choice>
<xsd:element name="translationContainerList" type="translationContainerListType" minOccurs="0"/> <xsd:element name="translationContainer" type="translationContainerType" minOccurs="0"/>
</xsd:sequence> </xsd:sequence>
</xsd:complexType> </xsd:complexType>
@ -511,7 +420,7 @@
<xsd:complexType name="semanticRoleContainerType"> <xsd:complexType name="semanticRoleContainerType">
<xsd:sequence> <xsd:sequence>
<xsd:element name="semanticRole" type="semanticRoleType"/> <xsd:element name="semanticRole" type="semanticRoleType"/>
<xsd:element name="syntacticStructureList" type="syntacticStructureListType" minOccurs="0" maxOccurs="1"/> <xsd:element name="syntacticStructureList" type="syntacticStructureListType"/>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="cluster" type="xsd:int"/> <!-- hmm, number identifying a group of clustered roles? --> <xsd:attribute name="cluster" type="xsd:int"/> <!-- hmm, number identifying a group of clustered roles? -->
</xsd:complexType> </xsd:complexType>
@ -544,141 +453,6 @@
<xsd:sequence> <xsd:sequence>
<xsd:element name="valencyPattern" type="valencyPatternType" minOccurs="0" maxOccurs="unbounded"/> <xsd:element name="valencyPattern" type="valencyPatternType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="system"> <!-- the system within which the structure is defined -->
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="JOS"/>
<xsd:enumeration value="UD"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<!-- MSD code, in a particular language -->
<xsd:complexType name="msdType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="language" type="xsd:string" use="required"/>
<xsd:attribute name="system" type="xsd:string" use="required"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<!-- Container for all kinds of form representation lists -->
<xsd:complexType name="formRepresentationsType">
<xsd:sequence>
<xsd:element name="orthographyList" type="orthographyListType"/>
<xsd:element name="accentuationList" type="accentuationListType" minOccurs="0" maxOccurs="2"/>
<xsd:element name="pronunciationList" type="pronunciationListType" minOccurs="0"/>
<xsd:element name="hyphenationList" type="hyphenationListType" minOccurs="0"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="orthographyType">
<xsd:sequence>
<xsd:element name="form" type="formType"/>
<xsd:element name="measureList" type="measureListType" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="morphologyPatterns" type="xsd:string"/>
<xsd:attribute name="status" type="xsd:string"/>
<xsd:attribute name="norm" type="xsd:string"/> <!-- closed set? -->
</xsd:complexType>
<xsd:complexType name="orthographyListType">
<xsd:sequence>
<xsd:element name="orthography" type="orthographyType" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="accentuationType">
<xsd:sequence>
<xsd:element name="form" type="formType" minOccurs="0"/>
<xsd:element name="measureList" type="measureListType" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="orthography_id" type="xsd:integer"/>
<xsd:attribute name="accentuationPatterns" type="xsd:string"/>
<xsd:attribute name="status" type="xsd:string"/>
<xsd:attribute name="norm" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="accentuationListType">
<xsd:sequence>
<xsd:element name="accentuation" type="accentuationType" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="type">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="dynamic"/>
<xsd:enumeration value="tonemic"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:simpleType name="formType">
<xsd:restriction base="xsd:string"/>
</xsd:simpleType>
<xsd:complexType name="pronunciationFormType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="script" type="xsd:string" use="required"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:complexType name="pronunciationType">
<xsd:sequence>
<xsd:element name="form" type="pronunciationFormType" maxOccurs="unbounded"/>
<xsd:element name="measureList" type="measureListType" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="dynamic_accentuation_id" type="xsd:integer"/>
<xsd:attribute name="tonemic_accentuation_id" type="xsd:integer"/>
<xsd:attribute name="status" type="xsd:string"/>
<xsd:attribute name="norm" type="xsd:string"/>
<xsd:attribute name="type" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="pronunciationListType">
<xsd:sequence>
<xsd:element name="pronunciation" type="pronunciationType" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="hyphenationType">
<xsd:sequence>
<xsd:element name="form" type="formType"/>
<xsd:element name="measureList" type="measureListType" minOccurs="0"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="orthography_id" type="xsd:integer"/>
<xsd:attribute name="status" type="xsd:string"/>
</xsd:complexType>
<xsd:complexType name="hyphenationListType">
<xsd:sequence>
<xsd:element name="hyphenation" type="hyphenationType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<!-- Word form wrapper -->
<xsd:complexType name="wordFormType">
<xsd:sequence>
<xsd:element name="msd" type="msdType" maxOccurs="unbounded"/>
<xsd:element name="grammarFeatureList" type="grammarFeatureListType" minOccurs="0"/>
<xsd:element name="formRepresentations" type="formRepresentationsType"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/>
</xsd:complexType>
<!-- List of word forms -->
<xsd:complexType name="wordFormListType">
<xsd:sequence>
<xsd:element name="wordForm" type="wordFormType" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType> </xsd:complexType>
</xsd:schema> </xsd:schema>

3
resources/schema/monolingual_dictionaries.xsd
View File

@ -35,14 +35,11 @@
<xsd:element name="sense" minOccurs="0" maxOccurs="unbounded"> <xsd:element name="sense" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType> <xsd:complexType>
<xsd:sequence> <xsd:sequence>
<xsd:element name="relatedSenseList" type="relatedSenseListType" minOccurs="0"/>
<xsd:element name="labelList" type="labelListType" minOccurs="0"/> <xsd:element name="labelList" type="labelListType" minOccurs="0"/>
<xsd:element name="definitionList" type="definitionListType" minOccurs="0"/> <xsd:element name="definitionList" type="definitionListType" minOccurs="0"/>
<xsd:element name="exampleContainerList" type="exampleContainerListType" minOccurs="0"/> <xsd:element name="exampleContainerList" type="exampleContainerListType" minOccurs="0"/>
</xsd:sequence> </xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/> <xsd:attribute name="id" type="xsd:int"/>
<xsd:attribute name="key" type="xsd:string"/>
<xsd:attribute name="dummy" type="xsd:boolean"/>
</xsd:complexType> </xsd:complexType>
</xsd:element> </xsd:element>
</xsd:sequence> </xsd:sequence>

32
resources/schema/semantic_types.xsd
View File

@ -1,32 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:import namespace="http://www.w3.org/XML/1998/namespace"
schemaLocation="http://www.w3.org/2001/xml.xsd" />
<xsd:complexType name="nameType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="sl" type="xsd:string"/>
</xsd:extension>
</xsd:simpleContent>
</xsd:complexType>
<xsd:complexType name="semanticTypeType">
<xsd:sequence>
<xsd:element name="name" type="nameType"/>
<xsd:element name="semanticType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:int"/>
<xsd:attribute name="SEMCODE" type="xsd:string"/>
</xsd:complexType>
<xsd:element name="semanticTypes">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="semanticType" type="semanticTypeType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:schema>

350
resources/schema/structures.xsd
View File

@ -1,350 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:import namespace="http://www.w3.org/XML/1998/namespace"
schemaLocation="http://www.w3.org/2001/xml.xsd" />
<xsd:complexType name="restrictionType">
<xsd:sequence>
<xsd:element name="feature" type="restrictionFeatureType" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="type">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="morphology"/>
<xsd:enumeration value="lexis"/>
<xsd:enumeration value="space"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="restrictionOrType">
<xsd:sequence>
<xsd:element name="restriction" type="restrictionType" minOccurs="2" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="representationType">
<xsd:sequence>
<xsd:element name="feature" type="representationFeatureType" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
<xsd:complexType name="restrictionFeatureType">
<xsd:attribute name="POS">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="noun"/>
<xsd:enumeration value="verb"/>
<xsd:enumeration value="adjective"/>
<xsd:enumeration value="adverb"/>
<xsd:enumeration value="pronoun"/>
<xsd:enumeration value="numeral"/>
<xsd:enumeration value="preposition"/>
<xsd:enumeration value="conjunction"/>
<xsd:enumeration value="particle"/>
<xsd:enumeration value="interjection"/>
<xsd:enumeration value="abbreviation"/>
<xsd:enumeration value="residual"/>
<xsd:enumeration value="punctuation"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="case">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="nominative"/>
<xsd:enumeration value="genitive"/>
<xsd:enumeration value="dative"/>
<xsd:enumeration value="accusative"/>
<xsd:enumeration value="locative"/>
<xsd:enumeration value="instrumental"/>
<xsd:enumeration value="genitive|accusative"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="type">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="main"/>
<xsd:enumeration value="auxiliary"/>
<xsd:enumeration value="reflexive"/>
<xsd:enumeration value="common"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="form">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="digit"/>
<xsd:enumeration value="roman"/>
<xsd:enumeration value="letter"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="clitic">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="yes"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="negative">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="yes"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="filter">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="negative"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="vform">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="present"/>
<xsd:enumeration value="infinitive"/>
<xsd:enumeration value="supine"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="lemma">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="in|ali"/>
<xsd:enumeration value="kot|kakor|ko"/>
<xsd:enumeration value="ne"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="level">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="lemma"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="contact">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="neither"/>
<xsd:enumeration value="left"/>
<xsd:enumeration value="right"/>
<xsd:enumeration value="both"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="representationFeatureType">
<xsd:attribute name="rendition">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="word_form"/>
<xsd:enumeration value="lemma"/>
<xsd:enumeration value="lexis"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="selection">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="msd"/>
<xsd:enumeration value="agreement"/>
<xsd:enumeration value="all"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="msd">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="number"/>
<xsd:enumeration value="gender+number+case"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="head_cid" type="xsd:integer"/>
<xsd:attribute name="case">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="nominative"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="vform">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="present"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="person">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="third"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="string">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="ne"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="format">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="lowercase"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="componentsComponentType">
<xsd:attribute name="cid" use="required" type="xsd:integer"/>
<xsd:attribute name="type" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="core"/>
<xsd:enumeration value="other"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="label" type="xsd:string"/>
<xsd:attribute name="status">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="forbidden"/>
<xsd:enumeration value="obligatory"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:complexType name="dependencyType">
<xsd:attribute name="from" use="required">
<xsd:simpleType>
<xsd:union>
<xsd:simpleType>
<xsd:restriction base="xsd:integer"/>
</xsd:simpleType>
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="#"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:union>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="to" use="required" type="xsd:integer"/>
<xsd:attribute name="label" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="#"/>
<xsd:enumeration value="modra"/>
<xsd:enumeration value="del"/>
<xsd:enumeration value="dol"/>
<xsd:enumeration value="ena"/>
<xsd:enumeration value="dve"/>
<xsd:enumeration value="tri"/>
<xsd:enumeration value="štiri"/>
<xsd:enumeration value="prir"/>
<xsd:enumeration value="vez"/>
<xsd:enumeration value="skup"/>
<xsd:enumeration value="tri|štiri"/>
<xsd:enumeration value="dve|tri|štiri"/>
<xsd:enumeration value="dol|dve|tri|štiri"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
<xsd:attribute name="order">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="to-from"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
<xsd:element name="syntactic_structures">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="syntactic_structure" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="components">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="component" type="componentsComponentType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="order" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="fixed"/>
<xsd:enumeration value="variable"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
</xsd:element>
<xsd:element name="dependencies">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="dependency" type="dependencyType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
<xsd:element name="definition">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="component" minOccurs="0" maxOccurs="unbounded">
<xsd:complexType>
<xsd:sequence>
<xsd:choice minOccurs="0">
<xsd:element name="restriction" type="restrictionType" maxOccurs="unbounded"/>
<xsd:element name="restriction_or" type="restrictionOrType" maxOccurs="unbounded"/>
</xsd:choice>
<xsd:element name="representation" type="representationType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
<xsd:attribute name="cid" type="xsd:integer"/>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="parent_id" type="xsd:integer"/>
<xsd:attribute name="tempId" type="xsd:integer"/>
<xsd:attribute name="label" type="xsd:string"/>
<xsd:attribute name="formal_descendants" type="xsd:string"/>
<xsd:attribute name="type" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="single"/>
<xsd:enumeration value="collocation"/>
<xsd:enumeration value="formal"/>
<xsd:enumeration value="other"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
<xsd:attribute name="system_type" use="required">
<xsd:simpleType>
<xsd:restriction base="xsd:string">
<xsd:enumeration value="JOS"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
</xsd:element>
</xsd:schema>

5
resources/schema/top_dictionaries.xsd
View File

@ -6,11 +6,10 @@ validated both with this schema and with an appropriate more specific schema bas
<xsd:import namespace="http://www.w3.org/XML/1998/namespace" schemaLocation="http://www.w3.org/2001/xml.xsd" /> <xsd:import namespace="http://www.w3.org/XML/1998/namespace" schemaLocation="http://www.w3.org/2001/xml.xsd" />
<!-- top-level element is a dictionary --> <!-- top-level element is a dictionary -->
<xsd:element name="dictionary" type="rootType"/> <xsd:element name="dictionary" type="dictionaryType"/>
<xsd:element name="lexicon" type="rootType"/>
<!-- top-level type consists of sequence of entries --> <!-- top-level type consists of sequence of entries -->
<xsd:complexType name="rootType"> <xsd:complexType name="dictionaryType">
<xsd:sequence> <xsd:sequence>
<xsd:element name="entry" type="entryType" minOccurs="0" maxOccurs="unbounded"/> <xsd:element name="entry" type="entryType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence> </xsd:sequence>

27
scripts/delexonomise.py
View File

@ -1,27 +0,0 @@
#!/usr/bin/python3
import lxml.etree as lxml
import sys
import codecs
import re
import os
input_file_name = sys.argv[1]
output_file_name = sys.argv[2]
temp_file_name = '/tmp/temp.xml'
tree = lxml.parse(input_file_name)
root = tree.getroot()
root.tag = 'dictionary'
tree.write(temp_file_name, encoding='UTF-8', pretty_print=True)
output_file = codecs.open(output_file_name, 'w')
temp_file = codecs.open(temp_file_name, 'r')
for line in temp_file:
line = re.sub(' xmlns:lxnm=".*?"', '', line)
line = re.sub(' lxnm:.+?=".*?"', '', line)
output_file.write(line)
temp_file.close()
output_file.close()
os.remove(temp_file_name)

20
scripts/get_sample.py
View File

@ -1,20 +0,0 @@
#!/usr/bin/python3
import lxml.etree as lxml
import sys
import random
input_file_name = sys.argv[1]
sample_size = int(sys.argv[2])
output_file_name = sys.argv[3]
tree = lxml.parse(input_file_name)
root = tree.getroot()
indexes = list(range(len(root.xpath('entry'))))
random.shuffle(indexes)
for (index, entry) in enumerate(root.xpath('entry')):
if (index not in indexes[:sample_size]):
root.remove(entry)
tree.write(output_file_name, encoding='UTF-8')

15
scripts/validate_examples
View File

@ -4,8 +4,7 @@ script_dir="$(dirname "$(readlink -f "$0")")"
cd $script_dir cd $script_dir
schema_dir=../resources/schema schema_dir=../resources/schema
top_schema=$schema_dir/top_dictionaries.xsd top_schema=$schema_dir/top_dictionaries.xsd # for now we only have dictionaries
dictionary_types=("bilingual_dictionaries collocation_dictionary monolingual_dictionaries morphological_lexicon valency_lexicon")
example_dir=../examples example_dir=../examples
for example_subdir in $example_dir/* for example_subdir in $example_dir/*
@ -14,13 +13,11 @@ do
bottom_schema=$schema_dir/$base.xsd bottom_schema=$schema_dir/$base.xsd
for example_file in $example_subdir/*.xml for example_file in $example_subdir/*.xml
do do
case $base in bilingual_dictionaries|collocation_dictionary|monolingual_dictionaries|morphological_lexicon|valency_lexicon) command="xmllint -schema $top_schema $example_file --noout"
command="xmllint -schema $top_schema $example_file --noout" echo $command
echo $command if ! $command; then
if ! $command; then exit 1
exit 1 fi
fi
esac
command="xmllint -schema $bottom_schema $example_file --noout" command="xmllint -schema $bottom_schema $example_file --noout"
echo $command echo $command
if ! $command; then if ! $command; then