diff --git a/tests/rules-data/match/repeat/cclmatch.xml b/tests/rules-data/match/repeat/cclmatch.xml new file mode 100644 index 0000000000000000000000000000000000000000..0cb604806b776ef09acdd404e840b881fd96d393 --- /dev/null +++ b/tests/rules-data/match/repeat/cclmatch.xml @@ -0,0 +1,85 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd"> +<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb"> +<chunkList> + <chunk id="ch1" type="p"> + <sentence> + <tok> + <orth>Na</orth> + <lex><base>na</base><ctag>prep:acc</ctag></lex> + <lex><base>na</base><ctag>prep:loc</ctag></lex> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + </tok> + <tok> + <orth>stole</orth> + <lex><base>stola</base><ctag>subst:pl:acc:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:nom:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:voc:f</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:loc:m3</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:voc:m3</ctag></lex> + </tok> + <tok> + <orth>pod</orth> + <lex><base>pod</base><ctag>prep:acc:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:gen:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:inst:nwok</ctag></lex> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + </tok> + <tok> + <orth>sufitem</orth> + <lex><base>sufit</base><ctag>subst:sg:inst:m3</ctag></lex> + </tok> + <tok> + <orth>pies</orth> + <lex><base>pies</base><ctag>subst:sg:nom:m2</ctag></lex> + </tok> + <tok> + <orth>stał</orth> + <lex><base>stać</base><ctag>praet:sg:m1:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m1:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:perf</ctag></lex> + </tok> + <ns/> + <tok> + <orth>.</orth> + <lex><base>.</base><ctag>interp</ctag></lex> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/repeat/cclmatch3.ccl b/tests/rules-data/match/repeat/cclmatch3.ccl new file mode 100644 index 0000000000000000000000000000000000000000..81cf3c67ad32dddd771f9598a961f16d2b5a01d7 --- /dev/null +++ b/tests/rules-data/match/repeat/cclmatch3.ccl @@ -0,0 +1,9 @@ +apply( + match( + optional(repeat(inter(class[0], {adj, pact, ppas}))), + inter(class[0], {subst, ger, depr}) + ), + actions( + mark(M, 'NP') + ) +) diff --git a/tests/rules-data/match/repeat/cclmatch3.out.xml b/tests/rules-data/match/repeat/cclmatch3.out.xml new file mode 100644 index 0000000000000000000000000000000000000000..5d77b0be9b4c30037efe39e7a2f76b8a928da636 --- /dev/null +++ b/tests/rules-data/match/repeat/cclmatch3.out.xml @@ -0,0 +1,94 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd"> +<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb"> +<chunkList> + <chunk id="ch1" type="p"> + <sentence> + <tok> + <orth>Na</orth> + <lex><base>na</base><ctag>prep:acc</ctag></lex> + <lex><base>na</base><ctag>prep:loc</ctag></lex> + <ann chan="NP">0</ann> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + <ann chan="NP" head="1">1</ann> + </tok> + <tok> + <orth>stole</orth> + <lex><base>stola</base><ctag>subst:pl:acc:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:nom:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:voc:f</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:loc:m3</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:voc:m3</ctag></lex> + <ann chan="NP">1</ann> + </tok> + <tok> + <orth>pod</orth> + <lex><base>pod</base><ctag>prep:acc:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:gen:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:inst:nwok</ctag></lex> + <ann chan="NP">0</ann> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + <ann chan="NP" head="1">2</ann> + </tok> + <tok> + <orth>sufitem</orth> + <lex><base>sufit</base><ctag>subst:sg:inst:m3</ctag></lex> + <ann chan="NP">2</ann> + </tok> + <tok> + <orth>pies</orth> + <lex><base>pies</base><ctag>subst:sg:nom:m2</ctag></lex> + <ann chan="NP" head="1">3</ann> + </tok> + <tok> + <orth>stał</orth> + <lex><base>stać</base><ctag>praet:sg:m1:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m1:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:perf</ctag></lex> + <ann chan="NP">0</ann> + </tok> + <ns/> + <tok> + <orth>.</orth> + <lex><base>.</base><ctag>interp</ctag></lex> + <ann chan="NP">0</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/repeat/cclmatch4.ccl b/tests/rules-data/match/repeat/cclmatch4.ccl new file mode 100644 index 0000000000000000000000000000000000000000..68a50fadac34bf64c6b521de63cc9b2c8850859a --- /dev/null +++ b/tests/rules-data/match/repeat/cclmatch4.ccl @@ -0,0 +1,12 @@ +apply( + match( + repeat( + optional(inter(class[0], {prep})), + optional(repeat(inter(class[0], {adj, pact, ppas}))), + inter(class[0], {subst, ger, depr}) + ) + ), + actions( + mark(M, 'MultiNP') + ) +) diff --git a/tests/rules-data/match/repeat/cclmatch4.out.xml b/tests/rules-data/match/repeat/cclmatch4.out.xml new file mode 100644 index 0000000000000000000000000000000000000000..bcdafa1f51925aa043b62c49fef209e6f3a81258 --- /dev/null +++ b/tests/rules-data/match/repeat/cclmatch4.out.xml @@ -0,0 +1,94 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd"> +<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb"> +<chunkList> + <chunk id="ch1" type="p"> + <sentence> + <tok> + <orth>Na</orth> + <lex><base>na</base><ctag>prep:acc</ctag></lex> + <lex><base>na</base><ctag>prep:loc</ctag></lex> + <ann chan="MultiNP" head="1">1</ann> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>stole</orth> + <lex><base>stola</base><ctag>subst:pl:acc:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:nom:f</ctag></lex> + <lex><base>stola</base><ctag>subst:pl:voc:f</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:loc:m3</ctag></lex> + <lex><base>stół</base><ctag>subst:sg:voc:m3</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>pod</orth> + <lex><base>pod</base><ctag>prep:acc:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:gen:nwok</ctag></lex> + <lex><base>pod</base><ctag>prep:inst:nwok</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>starym</orth> + <lex><base>stary</base><ctag>adj:pl:dat:f:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:pl:dat:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m1:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m2:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:m3:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:inst:n:pos</ctag></lex> + <lex><base>stary</base><ctag>adj:sg:loc:n:pos</ctag></lex> + <lex><base>stara</base><ctag>subst:pl:dat:f</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>sufitem</orth> + <lex><base>sufit</base><ctag>subst:sg:inst:m3</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>pies</orth> + <lex><base>pies</base><ctag>subst:sg:nom:m2</ctag></lex> + <ann chan="MultiNP">1</ann> + </tok> + <tok> + <orth>stał</orth> + <lex><base>stać</base><ctag>praet:sg:m1:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:imperf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m1:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m2:perf</ctag></lex> + <lex><base>stać</base><ctag>praet:sg:m3:perf</ctag></lex> + <ann chan="MultiNP">0</ann> + </tok> + <ns/> + <tok> + <orth>.</orth> + <lex><base>.</base><ctag>interp</ctag></lex> + <ann chan="MultiNP">0</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/single_tok/cclmatch.xml b/tests/rules-data/match/single_tok/cclmatch.xml new file mode 100644 index 0000000000000000000000000000000000000000..b23bc389cc4a3f21307c7467954fe218c562a644 --- /dev/null +++ b/tests/rules-data/match/single_tok/cclmatch.xml @@ -0,0 +1,33 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd"> +<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb"> +<chunkList> + <chunk id="ch1" type="p"> + <sentence> + <tok> + <orth>To</orth> + <lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex> + <lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex> + <lex><base>to</base><ctag>conj</ctag></lex> + <lex><base>to</base><ctag>pred</ctag></lex> + <lex><base>to</base><ctag>qub</ctag></lex> + <lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex> + <lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex> + <lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex> + </tok> + <tok> + <orth>jest</orth> + <lex><base>być</base><ctag>fin:sg:ter:imperf</ctag></lex> + </tok> + <tok> + <orth>wyżyna</orth> + <lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex> + </tok> + <tok> + <orth>pies</orth> + <lex><base>pies</base><ctag>subst:sg:nom:m2</ctag></lex> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/single_tok/cclmatch1.ccl b/tests/rules-data/match/single_tok/cclmatch1.ccl new file mode 100644 index 0000000000000000000000000000000000000000..0ee107574ecd4050814d839cf4a78fd2d3e5efcd --- /dev/null +++ b/tests/rules-data/match/single_tok/cclmatch1.ccl @@ -0,0 +1,8 @@ +apply( + match( + and( inter(class[0], {subst, ger, depr}), inter(cas[0], {nom}) ) + ), + actions( + mark($m:_M, 'N_NOM') + ) +) diff --git a/tests/rules-data/match/single_tok/cclmatch1.out.xml b/tests/rules-data/match/single_tok/cclmatch1.out.xml new file mode 100644 index 0000000000000000000000000000000000000000..0b09385e6e2c8c85764fcec63fff5ddbec83fe41 --- /dev/null +++ b/tests/rules-data/match/single_tok/cclmatch1.out.xml @@ -0,0 +1,37 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE cesAna SYSTEM "xcesAnaIPI.dtd"> +<cesAna xmlns:xlink="http://www.w3.org/1999/xlink" version="1.0" type="lex disamb"> +<chunkList> + <chunk id="ch1" type="p"> + <sentence> + <tok> + <orth>To</orth> + <lex><base>ten</base><ctag>adj:sg:nom:n:pos</ctag></lex> + <lex><base>ten</base><ctag>adj:sg:acc:n:pos</ctag></lex> + <lex><base>to</base><ctag>conj</ctag></lex> + <lex><base>to</base><ctag>pred</ctag></lex> + <lex><base>to</base><ctag>qub</ctag></lex> + <lex><base>to</base><ctag>subst:sg:nom:n</ctag></lex> + <lex><base>to</base><ctag>subst:sg:acc:n</ctag></lex> + <lex><base>to</base><ctag>subst:sg:voc:n</ctag></lex> + <ann chan="N_NOM" head="1">1</ann> + </tok> + <tok> + <orth>jest</orth> + <lex><base>być</base><ctag>fin:sg:ter:imperf</ctag></lex> + <ann chan="N_NOM">0</ann> + </tok> + <tok> + <orth>wyżyna</orth> + <lex><base>wyżyna</base><ctag>subst:sg:nom:f</ctag></lex> + <ann chan="N_NOM" head="1">2</ann> + </tok> + <tok> + <orth>pies</orth> + <lex><base>pies</base><ctag>subst:sg:nom:m2</ctag></lex> + <ann chan="N_NOM" head="1">3</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna>