trunk/example-projects/TextRulerExample/script/uima/ruta/example/Features.ruta

PACKAGE uima.ruta.example;

SCRIPT uima.ruta.example.Base;

ENGINE utils.PlainTextAnnotator;
TYPESYSTEM utils.PlainTextTypeSystem;

WORDLIST EditorMarkerList = 'EditorMarker.txt';
WORDLIST EnglishStopWordList = 'EnglishStopWords.txt';
WORDLIST FirstNameList = 'FirstNames.txt';
WORDLIST JournalVolumeMarkerList = 'JournalVolumeMarker.txt';
WORDLIST MonthList = 'Months.txt';
WORDLIST PagesMarkerList = 'PagesMarker.txt';
WORDLIST PublisherList = 'Publishers.txt';

DECLARE EditorMarker, EnglishStopWord, FirstName, JournalVolumeMarker, Month, PagesMarker, PublisherInd;
Document{ -> MARKFAST(EditorMarker, EditorMarkerList)};
Document{ -> MARKFAST(EnglishStopWord,EnglishStopWordList)};
Document{ -> MARKFAST(FirstName, FirstNameList)};
Document{ -> MARKFAST(JournalVolumeMarker, JournalVolumeMarkerList)};
Document{ -> MARKFAST(Month, MonthList)};
Document{ -> MARKFAST(PagesMarker, PagesMarkerList)};
Document{ -> MARKFAST(PublisherInd, PublisherList)};


DECLARE Reference;
Document{-> EXEC(PlainTextAnnotator, {Line, Paragraph})};
Document{-> RETAINTYPE(SPACE, BREAK)};
Line{-REGEXP("CORA:.*") -> MARK(Reference)};
Reference{-> TRIM(SPACE, BREAK)};
Document{-> RETAINTYPE};

DECLARE LParen, RParen;
SPECIAL{REGEXP("[(]") -> MARK(LParen)};
SPECIAL{REGEXP("[)]") -> MARK(RParen)};

DECLARE YearInd;
NUM{REGEXP("19..|20..") -> MARK(YearInd, 1, 2)} SW?{REGEXP("a|b|c|d", true)};
Document{-> RETAINTYPE(SPACE)};
CAP YearInd{-> UNMARK(YearInd)};
Document{-> RETAINTYPE};


DECLARE NameLinker;
W{-PARTOF(NameLinker), REGEXP("and", true) -> MARK(NameLinker)};
COMMA{-PARTOF(NameLinker) -> MARK(NameLinker)};
SEMICOLON{-PARTOF(NameLinker) -> MARK(NameLinker)};
SPECIAL{-PARTOF(NameLinker), REGEXP("&") -> MARK(NameLinker)};

DECLARE FirstNameInd, FirstNameInitial, SingleChar;
CW{-PARTOF(FirstNameInitial), REGEXP(".")} SPECIAL{-PARTOF(FirstNameInitial), REGEXP("-")} CW{REGEXP(".") -> MARK(FirstNameInitial,1,2,3,4)} PERIOD;
SPECIAL{-PARTOF(FirstNameInitial), REGEXP("-")} CW{REGEXP(".") -> MARK(FirstNameInitial,1,2,3)} PERIOD;
CW{-PARTOF(FirstNameInitial), REGEXP(".") -> MARK(FirstNameInitial,1,2)} PERIOD;
CW{-PARTOF(FirstNameInitial), REGEXP(".") -> MARK(FirstNameInitial)} COMMA;
CW{-PARTOF(FirstNameInitial), REGEXP(".") -> MARK(SingleChar)};

DECLARE Quote, QuotedStuff;
SPECIAL[1,2]{REGEXP("[\"'´`‘’“]"), -PARTOF(Quote) -> MARK(Quote)};
Document{-> RETAINTYPE(SPACE)};
W Quote{-> UNMARK(Quote)} W;
Document{-> RETAINTYPE};
BLOCK(InRef) Reference{}{
    Quote ANY+{-PARTOF(Quote) -> MARK(QuotedStuff, 1, 2, 3)} Quote;
}

DECLARE InInd;
W{REGEXP("In", true)-> MARK(InInd)};

DECLARE FirstToken, LastToken;
BLOCK(InRef) Reference{}{
    ANY{POSITION(Reference,1) -> MARK(FirstToken)};
    Document{-> MARKLAST(LastToken)};
}


DECLARE NumPeriod, NumComma, NumColon;
Document{-> RETAINTYPE(SPACE, BREAK)};
NUM PERIOD{-> MARKONCE(NumPeriod)} NUM;
NUM COMMA{-> MARKONCE(NumComma)} NUM;
NUM COLON{-> MARKONCE(NumColon)} NUM;
Document{-> RETAINTYPE};
DECLARE PeriodSep, CommaSep, ColonSep;
PERIOD{-PARTOF(FirstNameInitial), -PARTOF(NumPeriod), -PARTOF(FirstToken) -> MARKONCE (PeriodSep)};
COMMA{-PARTOF(FirstNameInitial), -PARTOF(NumComma), -PARTOF(FirstToken) -> MARKONCE (CommaSep)};
COLON{-PARTOF(FirstNameInitial), -PARTOF(NumColon), -PARTOF(FirstToken) -> MARKONCE (ColonSep)};