diff --git a/tests/rules-data/match/variants/cclmatch.xml b/tests/rules-data/match/variants/cclmatch.xml new file mode 100644 index 0000000000000000000000000000000000000000..7b48741fe5a6070eb919fa18884500f8d394eb62 --- /dev/null +++ b/tests/rules-data/match/variants/cclmatch.xml @@ -0,0 +1,70 @@ +<?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> + <sentence> + <tok> + <orth>Dwa</orth> + <lex><base>dwa</base><ctag>other</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">1</ann> + </tok> + <tok> + <orth>wielkie</orth> + <lex><base>wielki</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">2</ann> + </tok> + <tok> + <orth>włochate</orth> + <lex><base>włochaty</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + </tok> + <tok> + <orth>zapchlone</orth> + <lex><base>zapchlić</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + </tok> + <tok> + <orth>koty</orth> + <lex><base>kot</base><ctag>noun</ctag></lex> + <ann chan="A" head="1">1</ann> + <ann chan="B" head="1">3</ann> + </tok> + <tok> + <orth>zjadły</orth> + <lex><base>zjeść</base><ctag>verb</ctag></lex> + <ann chan="A">0</ann> + <ann chan="B" head="1">4</ann> + </tok> + <tok> + <orth>pięć</orth> + <lex><base>pięć</base><ctag>other</ctag></lex> + <ann chan="A" head="1">2</ann> + <ann chan="B">4</ann> + </tok> + <tok> + <orth>tłustych</orth> + <lex><base>tłusty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + </tok> + <tok> + <orth>soczystych</orth> + <lex><base>soczysty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + </tok> + <tok> + <orth>much</orth> + <lex><base>mucha</base><ctag>noun</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">0</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/variants/cclmatch1.ccl b/tests/rules-data/match/variants/cclmatch1.ccl new file mode 100644 index 0000000000000000000000000000000000000000..5e4efc1b1ae12cc59b9b0390d4bcefcffdad3ab0 --- /dev/null +++ b/tests/rules-data/match/variants/cclmatch1.ccl @@ -0,0 +1,18 @@ +apply( + match( + longest( + variant( + inter(class[0], {noun}), + inter(class[0], {verb}) + ), + variant( + is("B") + ), + variant( + inter(class[0], {adj}) + ) + ) + ), + actions(mark(M, "C")) +) + diff --git a/tests/rules-data/match/variants/cclmatch1.out.xml b/tests/rules-data/match/variants/cclmatch1.out.xml new file mode 100644 index 0000000000000000000000000000000000000000..b7c686294cbb038e18ba79fedf4372a817e7ee8f --- /dev/null +++ b/tests/rules-data/match/variants/cclmatch1.out.xml @@ -0,0 +1,80 @@ +<?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> + <sentence> + <tok> + <orth>Dwa</orth> + <lex><base>dwa</base><ctag>other</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">1</ann> + <ann chan="C" head="1">1</ann> + </tok> + <tok> + <orth>wielkie</orth> + <lex><base>wielki</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">2</ann> + <ann chan="C" head="1">2</ann> + </tok> + <tok> + <orth>włochate</orth> + <lex><base>włochaty</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + <ann chan="C">2</ann> + </tok> + <tok> + <orth>zapchlone</orth> + <lex><base>zapchlić</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + <ann chan="C">2</ann> + </tok> + <tok> + <orth>koty</orth> + <lex><base>kot</base><ctag>noun</ctag></lex> + <ann chan="A" head="1">1</ann> + <ann chan="B" head="1">3</ann> + <ann chan="C" head="1">3</ann> + </tok> + <tok> + <orth>zjadły</orth> + <lex><base>zjeść</base><ctag>verb</ctag></lex> + <ann chan="A">0</ann> + <ann chan="B" head="1">4</ann> + <ann chan="C">3</ann> + </tok> + <tok> + <orth>pięć</orth> + <lex><base>pięć</base><ctag>other</ctag></lex> + <ann chan="A" head="1">2</ann> + <ann chan="B">4</ann> + <ann chan="C">0</ann> + </tok> + <tok> + <orth>tłustych</orth> + <lex><base>tłusty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + <ann chan="C" head="1">4</ann> + </tok> + <tok> + <orth>soczystych</orth> + <lex><base>soczysty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + <ann chan="C" head="1">5</ann> + </tok> + <tok> + <orth>much</orth> + <lex><base>mucha</base><ctag>noun</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">0</ann> + <ann chan="C">0</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/variants/cclmatch2.ccl b/tests/rules-data/match/variants/cclmatch2.ccl new file mode 100644 index 0000000000000000000000000000000000000000..bb5fdaaec67fb1dbdb806eafdbbaa1c23a29c27e --- /dev/null +++ b/tests/rules-data/match/variants/cclmatch2.ccl @@ -0,0 +1,18 @@ +apply( + match( + oneof( + variant( + inter(class[0], {adj}) + ), + variant( + inter(class[0], {noun}), + inter(class[0], {verb}) + ), + variant( + is("B") + ) + ) + ), + actions(mark(M, "C")) +) + diff --git a/tests/rules-data/match/variants/cclmatch2.out.xml b/tests/rules-data/match/variants/cclmatch2.out.xml new file mode 100644 index 0000000000000000000000000000000000000000..12272275fd27b06ca59d01275599b2c3a5bcebd9 --- /dev/null +++ b/tests/rules-data/match/variants/cclmatch2.out.xml @@ -0,0 +1,80 @@ +<?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> + <sentence> + <tok> + <orth>Dwa</orth> + <lex><base>dwa</base><ctag>other</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">1</ann> + <ann chan="C" head="1">1</ann> + </tok> + <tok> + <orth>wielkie</orth> + <lex><base>wielki</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B" head="1">2</ann> + <ann chan="C" head="1">2</ann> + </tok> + <tok> + <orth>włochate</orth> + <lex><base>włochaty</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + <ann chan="C" head="1">3</ann> + </tok> + <tok> + <orth>zapchlone</orth> + <lex><base>zapchlić</base><ctag>adj</ctag></lex> + <ann chan="A">1</ann> + <ann chan="B">2</ann> + <ann chan="C" head="1">4</ann> + </tok> + <tok> + <orth>koty</orth> + <lex><base>kot</base><ctag>noun</ctag></lex> + <ann chan="A" head="1">1</ann> + <ann chan="B" head="1">3</ann> + <ann chan="C" head="1">5</ann> + </tok> + <tok> + <orth>zjadły</orth> + <lex><base>zjeść</base><ctag>verb</ctag></lex> + <ann chan="A">0</ann> + <ann chan="B" head="1">4</ann> + <ann chan="C">5</ann> + </tok> + <tok> + <orth>pięć</orth> + <lex><base>pięć</base><ctag>other</ctag></lex> + <ann chan="A" head="1">2</ann> + <ann chan="B">4</ann> + <ann chan="C">0</ann> + </tok> + <tok> + <orth>tłustych</orth> + <lex><base>tłusty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + <ann chan="C" head="1">6</ann> + </tok> + <tok> + <orth>soczystych</orth> + <lex><base>soczysty</base><ctag>adj</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">4</ann> + <ann chan="C" head="1">7</ann> + </tok> + <tok> + <orth>much</orth> + <lex><base>mucha</base><ctag>noun</ctag></lex> + <ann chan="A">2</ann> + <ann chan="B">0</ann> + <ann chan="C">0</ann> + </tok> + </sentence> + </chunk> +</chunkList> +</cesAna> diff --git a/tests/rules-data/match/variants/simple.is-the-tagset b/tests/rules-data/match/variants/simple.is-the-tagset new file mode 100644 index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc --- /dev/null +++ b/tests/rules-data/match/variants/simple.is-the-tagset @@ -0,0 +1 @@ +