resources.splitter.grammar.find-no-space.jape Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of lang-german Show documentation

Support for processing German documents

The newest version!

/*
*  cr.jape
*
* Copyright (c) 1998-2004, The University of Sheffield.
*
*  This file is part of GATE (see http://gate.ac.uk/), and is free
*  software, licenced under the GNU Library General Public License,
*  Version 2, June 1991 (in the distribution as file licence.html,
*  and also available at http://gate.ac.uk/gate/licence.html).
*
*  Diana Maynard, 10 Sep 2001
* 
*  $Id: find-no-space.jape 6377 2004-11-24 16:35:18Z diana $
*/

Phase:	find
Input: Token SpaceToken Lookup
Options: control = appelt

Macro: FULLSTOP
(
 {Token.string=="."}
)

Macro: THREEDOTS
(
 {Token.string=="."}
 {Token.string=="."}
 {Token.string=="."}
)

Macro: PUNCT
(
 ({Token.string == "!"} | 
  {Token.string == "?"}
 )
)

Rule: Ldots
(
 ({Token})?
 THREEDOTS (FULLSTOP)+
):fake
-->
{}

Rule: Split1
(
 (PUNCT|FULLSTOP|THREEDOTS)
 ({Token.string == "\""})?
)
:split
-->
:split.Split = {kind = "internal"}

//
Rule: CR
// must be at least 2 CRs or Newlines plus optional spaces to generate a split
(

// change to at least 1 CR
 ({SpaceToken.string == "\n"}|
  ({SpaceToken.string=="\n"}{SpaceToken.string=="\r"}))
 ({SpaceToken.kind == space})*

 ({SpaceToken.string == "\n"}
  | ({SpaceToken.string=="\n"}{SpaceToken.string=="\r"})
  | {SpaceToken.string=="\n\r"}
  | {SpaceToken.string=="\r\n"} )+
 ({SpaceToken.kind == space})*
):cr
-->
:cr.Split = {kind = "external"}


Rule:Fake
(
 ({Token}{Token.string == "."})+
 ({Token.kind == number})
):fake
-->
{}


Rule: Abbrev1
(
 {Lookup.majorType == "splitter_abbreviation"}
 {Token.string == "."}
):fake
-->
{}

Rule: Abbrev2
({Token.orth=="upperInitial", Token.length=="1"} FULLSTOP)+
:fake
-->
{}