cqp_syntax_test.cqp

# Comment with TODO

set pp no

set Registry "/some/path/to/a/directory";

info DICKENS;

show corpora;

show cd;

"interesting";

"interest(s|(ed|ing)(ly)?)?";

"\?";

"B\"ar";

"wahrung" %cd;

[word = "?" %l];

[lemma = "pole" %c];

[pos != "N.*"];

set Context 20;

set Context 5 words;

show +pos -lemma;

set ShowTagAttributes off;

set PrintStructures "novel_title, chapter_num";

set PrintStructures "";

set PrintOptions hdr;

set HistoryFile "/home/alexraw/.cqphistory";

set DefaultNonbrackAttr lemma;

[(lemma="go") & !(word="went"%c | word="gone"%c)]{1,2};

"no" "sooner" []* "than" within s;

sort Go by word %cd;

sort Last by word descending reverse;

sort by word %cd on matchend[-1] .. matchend[42];

source "script.txt";

Go = [lemma = "go"] "and" [];

show named;

count Go by lemma cut 5;

size DICKENS:Go;

cat Go > "go.txt";
cat Go >> "go.txt";

cat Go > "| grep '\?$' > go2.txt";

"in" @[pos="DT"] [lemma="case"];
"in" @[pos="DT"] @1[pos="J.*"]? [lemma="case"];
size A target;

group NP matchend word by target lemma;

group NP target lemma group by matchend lemma within novel cut 10;

A = intersection B C;
reduce A to 10%;

set A keyword nearest [pos="NNS?"] within right 5 words from match;
set A keyword NULL;

NPobj = [pos="V.*"] [pos="RB"]* <np> @[] []* </np>;


set Elephants keyword leftmost [pos="JJ.*"] within 3 words;

[pos = "ADJ." & _ < 500];

a:[pos="DT"] [pos="JJ"]* b:[pos="NNS?"] :: distabs(a,b) >= 5;

<np> []* ([pos="JJ.*"] []*){3,} </np>;

[pos="JJ.*"] ([]* [pos="JJ.*"]){2} within np cut 20 expand to np;

<np> a:[] []* </np> :: a.np_h = "bank";
<np> a:[] []* </np> :: a.np_h = "bank";

<np_h = "bank"> []* </np_h>;

(<np_h "bank">|<np_h1 "bank">|<np_h2 "bank">) []* (</np_h2>|</np_h1>|</np_h>);

"nuclear"%c "power"%c :EUROPARL-DE [lemma = "Kernkraft"];

Time = from Zeit to EUROPARL-EN

define $week +=
"Monday Tuesday Wednesday Thursday Friday";

[(lemma=RE($pref)) & (pos="VBG")];

<match> [pos = "W.*"];

[lemma = "horse" expand to p];

/np[tietie];
/codist[]

define macro find('$0=Tag $1=Property')
'<$0_f contains "$1"> []* </$0_f>';

tabulate A match[-5]..match[-1] lemma, matchend[1]..matchend[5] lemma;

[: ambiguity(/unify[agr, a,b,c]) >= 1 :]

MU(meet [pos = "NN.*"] [lemma = "lovely"] -2 2);

<<NP @0>> "after" <<@1 a: NP b:>> :: distabs(a, b) >= 2;