from src.ccl_parser import parse_ccl

example_ccl = """<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE chunkList SYSTEM "ccl.dtd">
<chunkList>
 <chunk type="p" id="ch1">
  <sentence id="s1">
   <tok>
    <orth>Marek</orth>
    <lex disamb="1"><base>Marek</base><ctag>subst:sg:nom:m1</ctag></lex>
    <lex disamb="1"><base>marek</base><ctag>subst:sg:nom:m1</ctag></lex>
    <ann chan="nam_liv" head="1">1</ann>
    <ann chan="nam_loc">0</ann>
   </tok>
   <tok>
    <orth>Kowalski</orth>
    <lex disamb="1"><base>Kowalski</base><ctag>subst:sg:nom:m1</ctag></lex>
    <ann chan="nam_liv">1</ann>
    <ann chan="nam_loc">0</ann>
   </tok>
   <tok>
    <orth>pojechał</orth>
    <lex disamb="1"><base>pojechać</base><ctag>praet:sg:m1:perf</ctag></lex>
    <ann chan="nam_liv">0</ann>
    <ann chan="nam_loc">0</ann>
   </tok>
   <tok>
    <orth>do</orth>
    <lex disamb="1"><base>do</base><ctag>prep:gen</ctag></lex>
    <ann chan="nam_liv">0</ann>
    <ann chan="nam_loc">0</ann>
   </tok>
   <tok>
    <orth>Wrocławia</orth>
    <lex disamb="1"><base>Wrocław</base><ctag>subst:sg:gen:m3</ctag></lex>
    <ann chan="nam_liv">0</ann>
    <ann chan="nam_loc" head="1">1</ann>
   </tok>
   <ns/>
   <tok>
    <orth>.</orth>
    <lex disamb="1"><base>.</base><ctag>interp</ctag></lex>
    <ann chan="nam_liv">0</ann>
    <ann chan="nam_loc">0</ann>
   </tok>
  </sentence>
 </chunk>
</chunkList>
"""

def test_parse_ccl():
    text, annotations = parse_ccl(example_ccl)
    
    assert text == "Marek Kowalski pojechał do Wrocławia."
    
    assert set(annotations.keys()) == set(["nam_liv", "nam_loc", "ctag"])
    
    assert annotations["nam_liv"] == [(0, 14, "Marek Kowalski")]
    assert annotations["nam_loc"] == [(27, 36, "Wrocławia")]
    assert annotations["ctag"] == [(0, 5, "subst:sg:nom:m1"), (6, 14, "subst:sg:nom:m1"), (15, 23, "praet:sg:m1:perf"), (24, 26, "prep:gen"), (27, 36, "subst:sg:gen:m3"), (36, 37, "interp")]