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

Compare commits

base: generic:140f18ff88c4b103f4de028bb59ab8b5603e4058
Branches Tags
generic:master
generic:simon
...
compare: generic:76c406dffc7daff55431be906d5a8e6c9db456a2
Branches Tags
generic:master
generic:simon

6 Commits
140f18ff88 ... 76c406dffc

Author SHA1 Message Date
Cyprian Laskowski 76c406dffc Redmine #1224: made sloleks-related adjustments to inventory and added related examples
2 years ago
Cyprian Laskowski 13791bdabe Redmine #969: added generated valency file to examples
2 years ago
Cyprian Laskowski 3a4097c6db Redmine #2246: added schemas and examples for structures and semantic types
2 years ago
Cyprian Laskowski 3fcc821d3f Redmine #1431: added sample from VSMS 1.0 xml
3 years ago
Cyprian Laskowski 35c1c2e135 Redmine #1102: made @targetLang optional
3 years ago
Cyprian Laskowski 6822bf61ef Redmine #1102: added reflexive_verb lemma type
3 years ago
13 changed files with 8469 additions and 168 deletions
Show Stats

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

File diff suppressed because it is too large Load Diff

86
examples/morphological_lexicon/Amanda.xml
Unescape View File

@ -0,0 +1,86 @@
<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
Unescape View File

@ -0,0 +1,75 @@
<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
Unescape View File

@ -0,0 +1,70 @@
<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>

84
examples/morphological_lexicon/gostja.xml
Unescape View File

@ -0,0 +1,84 @@
<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>

158
examples/morphological_lexicon/megla.xml
Unescape View File

@ -1,158 +0,0 @@
<lexicon>
<entry>
<head>
<headword>
<lemma orthography_ids="342" dynamic_accentuation_ids="81|83" pronunciation_ids="32" hyphenation_ids="" tonemic_accentuation_ids="85">agencija</lemma>
</headword>
<lexicalUnit sloleksId="LE_c77074df05d2719216d477bd01d418ad" sloleksKey="S_megla" type="single">
<lexeme lexical_unit_lexeme_id="83224">megla</lexeme>
</lexicalUnit>
<grammar>
<category>samostalnik</category>
<grammarFeature name="type">common</grammarFeature>
<grammarFeature name="gender">feminine</grammarFeature>
<!--grammarFeature name="pattern">Sz.1.2.o</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">Sozdr</msd>
<msd language="en" system="UD">AUX|...</msd>
<grammarFeatureList>
<grammarFeature name="number">dual</grammarFeature>
<grammarFeature name="case">genitive</grammarFeature>
</grammarFeatureList>
<formRepresentations>
<orthographyList>
<orthography id="342" morphologyPatterns="MP.1" status="preferred">
<form>megel</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">813</measure>
<measure type="frequency" source="GOS 1.0">432</measure>
</measureList>
</orthography>
<orthography id="343" morphologyPatterns="cjvt:MP.2">
<form>megla</form>
<measureList>
<measure type="frequency" source="Gigafida 2.0">9999</measure>
<measure type="frequency" source="GOS 1.0">888</measure>
</measureList>
</orthography>
</orthographyList>
<!-- Pri accentuantion in tonemic gre v resnici za dva načina naglaševanja, ali dovoljujemo potem povsem ločena elementa "tonemic" in "accentuation"? Če hočemo, da je vse pod "accentuation" in se razlikujeta po "type", potem je problem v glavi, kjer pri lemi navajamo npr. "accentuation_id", ki bi se potem moral pojaviti dvakrat? -->
<!-- Pri nekaterih vzorcih se stvari zelo ponavljajo; pri ZRC-ju npr. ločujejo meglA in mEgla -->
<accentuationList type="dynamic">
<accentuation id="81" orthography_id="342" stressPatterns="cjvt:AP.1|zrc:S202b" status="preferred">
<form>mègel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="82" orthography_id="343" stressPatterns="AP.1">
<form>meglá</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="83" orthography_id="342" stressPatterns="AP.2" status="preferred">
<form>mègel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="84" orthography_id="343" stressPatterns="AP.2">
<form>meglá</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<accentuationList type="tonemic">
<!-- tonemicPatterns je pri ZRC-ju v resnici združen z oblikoslovnim in naglasnim vzorcem, kar je mogoče problematično, saj bi ga v Sloleksu potem morali navesti tako pod orthography kot pod accentuation/tonemic. -->
<accentuation id="85" orthography_id="342" stressPatterns="S202b|S202i" status="preferred">
<form>mȅgel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="86" orthography_id="343" stressPatterns="S202b">
<form>meglā</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="87" orthography_id="342" stressPatterns="S202i">
<form>mȅgel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
<accentuation id="88" orthography_id="343" stressPatterns="S202i">
<form>meglā</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</accentuation>
</accentuationList>
<pronunciationList>
<pronunciation id="32" dynamic_accentuation_id="81" tonemic_accentuation_id="85" status="preferred">
<form script="IPA">mɛˈɡel</form>
<form script="SAMPA">mE"ɡel</form>
<measureList><!-- Ali obstaja več measureListov, po eden za vsak form? Ali pa povezujemo vsak measure z ustreznim form? -->
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="33" dynamic_accentuation_id="82" tonemic_accentuation_id="86">
<form script="IPA">mɛˈɡla</form>
<form script="SAMPA">mE"ɡla</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="34" dynamic_accentuation_id="82" norm="non-standard">
<form script="IPA">mɛˈγla</form>
<form script="SAMPA">mE"γla</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
<pronunciation id="35" dynamic_accentuation_id="81" norm="non-standard">
<form script="IPA">mɛˈγel</form>
<form script="SAMPA">mE"γel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</pronunciation>
</pronunciationList>
<hyphenationList>
<hyphenation id="7" orthography_id="342">
<form>me|gel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
<hyphenation id="8" orthography_id="81">
<form>mè|gel</form>
<measureList>
<measure type="frequency" source="XXX">7777</measure>
</measureList>
</hyphenation>
<hyphenation id="8" orthography_id="82">
<form>me|glá</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
Unescape View File

@ -0,0 +1,440 @@
<slonest>
<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>
</slonest>

4468
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
Unescape View File

@ -0,0 +1,221 @@
<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>

20
resources/schema/inventory.xsd
Unescape View File

@ -20,6 +20,7 @@
<xsd:enumeration value="single"/>
<xsd:enumeration value="phrase"/>
<xsd:enumeration value="compound"/>
<xsd:enumeration value="reflexive_verb"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
@ -146,10 +147,19 @@
</xsd:restriction>
</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 -->
<xsd:complexType name="grammarType">
<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="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:sequence>
</xsd:complexType>
@ -262,7 +272,7 @@
<xsd:complexType name="translationType">
<xsd:simpleContent>
<xsd:extension base="xsd:string">
<xsd:attribute name="targetLang" type="xsd:string" use="required"/> <!-- target language -->
<xsd:attribute name="targetLang" type="xsd:string"/> <!-- target language -->
<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:extension>
@ -574,12 +584,12 @@
<xsd:complexType name="accentuationType">
<xsd:sequence>
<xsd:element name="form" type="formType"/>
<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="stressPatterns" type="xsd:string"/>
<xsd:attribute name="accentuationPatterns" type="xsd:string"/>
<xsd:attribute name="status" type="xsd:string"/>
<xsd:attribute name="norm" type="xsd:string"/>
</xsd:complexType>
@ -620,6 +630,7 @@
<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">
@ -635,11 +646,12 @@
</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" maxOccurs="unbounded"/>
<xsd:element name="hyphenation" type="hyphenationType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>

31
resources/schema/semantic_types.xsd
Unescape View File

@ -0,0 +1,31 @@
<?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="SEMCODE" type="xsd:string"/>
</xsd:complexType>
<xsd:element name="slonest">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="semanticType" type="semanticTypeType" minOccurs="0" maxOccurs="unbounded"/>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:schema>

346
resources/schema/structures.xsd
Unescape View File

@ -0,0 +1,346 @@
<?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: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="system">
<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="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:sequence>
<xsd:attribute name="id" type="xsd:integer"/>
<xsd:attribute name="tempId" type="xsd:integer"/>
<xsd:attribute name="label" use="required" 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="other"/>
</xsd:restriction>
</xsd:simpleType>
</xsd:attribute>
</xsd:complexType>
</xsd:element>
</xsd:sequence>
</xsd:complexType>
</xsd:element>
</xsd:schema>

15
scripts/validate_examples
Unescape View File

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

Write Preview
Loading…
Cancel
Save