Big-Data-HPC-Platform/docs/ECLLanguageReference/ECLR_mods/ParSppt-NLPRecrd.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE sect1 PUBLIC "-//OASIS//DTD DocBook XML V4.5//EN"
"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd">
<sect1 id="NLP_RECORD_and_TRANSFORM_Functions">
  <title>NLP RECORD and TRANSFORM Functions</title>

  <para><emphasis>The following functions are used in field definition
  expressions within the RECORD structure<indexterm>
      <primary>RECORD structure</primary>
    </indexterm> or TRANSFORM function that defines the result set from the
  PARSE function<indexterm>
      <primary>PARSE function</primary>
    </indexterm>:</emphasis></para>

  <para><emphasis role="bold">MATCHED(</emphasis><emphasis>
  </emphasis><emphasis role="bold">[ </emphasis><emphasis>patternreference
  </emphasis><emphasis role="bold">] )</emphasis></para>

  <para><emphasis role="bold">MATCHED</emphasis> returns true or false as to
  whether the <emphasis>patternreference</emphasis> found a match. If the
  <emphasis>patternreference</emphasis> is omitted, it indicates whether the
  entire pattern matched or not (for use with the NOT MATCHED option).</para>

  <para><emphasis role="bold">MATCHTEXT</emphasis><emphasis>
  </emphasis><emphasis role="bold">[
  (</emphasis><emphasis>patternreference</emphasis><emphasis role="bold">)
  ]</emphasis></para>

  <para><emphasis role="bold">MATCHTEXT</emphasis> returns the matching ASCII
  text the <emphasis>patternreference</emphasis> found, or blank if not found.
  If the <emphasis>patternreference</emphasis> is omitted, MATCHTEXT returns
  all matching text.</para>

  <para><emphasis
  role="bold">MATCHUNICODE(</emphasis><emphasis>patternreference</emphasis><emphasis
  role="bold">)</emphasis></para>

  <para><emphasis role="bold">MATCHUNICODE</emphasis> returns the matching
  Unicode text the <emphasis>patternreference</emphasis> found, or blank if
  not found.</para>

  <para><emphasis
  role="bold">MATCHLENGTH(</emphasis><emphasis>patternreference</emphasis><emphasis
  role="bold">)</emphasis></para>

  <para><emphasis role="bold">MATCHLENGTH</emphasis> returns the number of
  characters in the matching text the <emphasis>patternreference</emphasis>
  found, or 0 if not found.</para>

  <para><emphasis
  role="bold">MATCHPOSITION(</emphasis><emphasis>patternreference</emphasis><emphasis
  role="bold">)</emphasis></para>

  <para><emphasis role="bold">MATCHPOSITION</emphasis> returns the position
  within the text of the first character in the matching text the
  <emphasis>patternreference</emphasis> found, or 0 if not found.</para>

  <para><emphasis
  role="bold">MATCHROW(</emphasis><emphasis>patternreference</emphasis><emphasis
  role="bold">)</emphasis></para>

  <para><emphasis role="bold">MATCHROW</emphasis> returns the entire row of
  the matching text the <emphasis>patternreference</emphasis> found for a RULE
  (valid only when the PARSE option is used on the PARSE function). This may
  be used to fully qualify a field in the RECORD structure of the row.</para>

  <sect2 id="Pattern_References">
    <title>Pattern References</title>

    <para>The <emphasis>patternreference</emphasis> parameter to these
    functions is a slash-delimited (/) list of previously defined PATTERN,
    TOKEN, or RULE attributes with or without an instance number appended in
    square brackets.</para>

    <para>If an instance number is supplied, the
    <emphasis>patternreference</emphasis> matches a particular occurrence,
    otherwise it matches any. The <emphasis>patternreference</emphasis>
    provides a path through the regular expression grammar to a particular
    result. The path to a particular attribute can either be fully or
    partially specified.</para>

    <para>Example:</para>

    <programlisting>PATTERN ws := PATTERN('[ \t\r\n]');
PATTERN arb := PATTERN('[-!.,\t a-zA-Z0-9]')+;
PATTERN number := PATTERN('[0-9]')+;
PATTERN age := '(' number OPT('/I') ')';
PATTERN role := '[' arb ']';
PATTERN m_rank := '&lt;' number '&gt;';
PATTERN actor := arb OPT(ws '(I)' ws);
          
NLP_layout_actor_movie := RECORD
  STRING30 actor_name := MATCHTEXT(actor);
  STRING50 movie_name := MATCHTEXT(arb[2]); //2nd instance of arb
  UNSIGNED2 movie_year := (UNSIGNED)MATCHTEXT(age/number);
                         //number within age
  STRING20 movie_role := MATCHTEXT(role/arb); //arb within role
  UNSIGNED1 cast_rank := (UNSIGNED)MATCHTEXT(m_rank/number);
END;
          
// This example demonstrates the use of productions in PARSE code
//(only supported in the tomita version of PARSE).
PATTERN ws := [' ','\t'];
TOKEN number := PATTERN('[0-9]+');
TOKEN plus := '+';
TOKEN minus := '-';

attrRec := RECORD
  INTEGER val;
END;

RULE(attrRec) e0 :=
          '(' USE(attrRec,expr)? ')' |
          number TRANSFORM(attrRec, SELF.val := (INTEGER)$1;) |
          '-' SELF TRANSFORM(attrRec, SELF.val := -$2.val;);
RULE(attrRec) e1 :=
          e0 |
          SELF '*' e0 TRANSFORM(attrRec, SELF.val := $1.val * $3.val;) |
          USE(attrRec, e1) '/' e0
               TRANSFORM(attrRec, SELF.val := $1.val / $3.val;);
RULE(attrRec) e2 :=
          e1 |
          SELF plus e1 TRANSFORM(attrRec, SELF.val := $1.val + $3.val;) |
          SELF minus e1 TRANSFORM(attrRec, SELF.val := $1.val - $3.val;);
RULE(attrRec) expr := e2;
 
infile := DATASET([{'1+2*3'},{'1+2*z'},{'1+2+(3+4)*4/2'}],
          { STRING line });
resultsRec := RECORD
  RECORDOF(infile);
  attrRec;
  STRING exprText;
  INTEGER value3;
END;

resultsRec extractResults(infile l, attrRec attr) := TRANSFORM
  SELF := l;
  SELF := attr;
  SELF.exprText := MATCHTEXT;
  SELF.value3 := MATCHROW(e0[3]).val;
END;

OUTPUT(PARSE(infile,line,expr,extractResults(LEFT, $1),
            FIRST,WHOLE,PARSE,SKIP(ws)));</programlisting>

    <para>See Also: <link linkend="PARSE">PARSE</link>, <link
    linkend="RECORD_Structure">RECORD Structure</link>, <link
    linkend="TRANSFORM_Structure">TRANSFORM Structure</link></para>
  </sect2>
</sect1>