X-Git-Url: http://jsfdemo.indexdata.com/?a=blobdiff_plain;f=src%2Forg%2Fz3950%2Fzing%2Fcql%2FCQLParser.java;h=13e505e9bb0f34f863a034005c2bb7f2bdda7958;hb=18405938a115378cc571d697060ac40775c62fb7;hp=eadedefd8571df176225017f3d5ae0abbd2823fa;hpb=64483d3d31c182adfb96fd75f8be10ff9f374d34;p=cql-java-moved-to-github.git diff --git a/src/org/z3950/zing/cql/CQLParser.java b/src/org/z3950/zing/cql/CQLParser.java index eadedef..13e505e 100644 --- a/src/org/z3950/zing/cql/CQLParser.java +++ b/src/org/z3950/zing/cql/CQLParser.java @@ -1,4 +1,4 @@ -// $Id: CQLParser.java,v 1.20 2002-11-14 22:04:16 mike Exp $ +// $Id: CQLParser.java,v 1.23 2003-09-04 21:56:46 mike Exp $ package org.z3950.zing.cql; import java.io.IOException; @@ -12,7 +12,7 @@ import java.io.FileNotFoundException; /** * Compiles CQL strings into parse trees of CQLNode subtypes. * - * @version $Id: CQLParser.java,v 1.20 2002-11-14 22:04:16 mike Exp $ + * @version $Id: CQLParser.java,v 1.23 2003-09-04 21:56:46 mike Exp $ * @see http://zing.z3950.org/cql/index.html */ @@ -34,8 +34,10 @@ public class CQLParser { * data structure) or, more often, simply rendered out in the * desired form using one of the back-ends. toCQL() * returns a decompiled CQL query equivalent to the one that was - * compiled in the first place; and toXCQL() returns an - * XML snippet representing the query. + * compiled in the first place; toXCQL() returns an + * XML snippet representing the query; and toPQF() + * returns the query rendered in Index Data's Prefix Query + * Format. * * @param cql The query * @return A CQLNode object which is the root of a parse @@ -112,16 +114,26 @@ public class CQLParser { break; qualifier = word; - relation = new CQLRelation(lexer.render(lexer.ttype, false)); + relation = new CQLRelation(lexer.ttype == lexer.TT_WORD ? + lexer.sval : + lexer.render(lexer.ttype, false)); match(lexer.ttype); while (lexer.ttype == '/') { match('/'); if (lexer.ttype != lexer.TT_RELEVANT && lexer.ttype != lexer.TT_FUZZY && - lexer.ttype != lexer.TT_STEM) + lexer.ttype != lexer.TT_STEM && + lexer.ttype != lexer.TT_PHONETIC && + lexer.ttype != lexer.TT_WORD) throw new CQLParseException("expected relation modifier, " + "got " + lexer.render()); + if (lexer.ttype == lexer.TT_WORD && + lexer.sval.indexOf('.') == -1) + throw new CQLParseException("unknown first-class " + + "relation modifier: " + + lexer.sval); + relation.addModifier(lexer.sval.toLowerCase()); match(lexer.ttype); } @@ -146,7 +158,7 @@ public class CQLParser { name = identifier; identifier = matchSymbol("prefix-identifer"); } - CQLNode term = parseTerm(qualifier, relation); + CQLNode term = parseQuery(qualifier, relation); return new CQLPrefixNode(name, identifier, term); } @@ -213,16 +225,25 @@ public class CQLParser { match(lexer.ttype); } - private boolean isBaseRelation() { + private boolean isBaseRelation() + throws CQLParseException { debug("isBaseRelation: checking ttype=" + lexer.ttype + " (" + lexer.render() + ")"); + + if (lexer.ttype == lexer.TT_WORD && + lexer.sval.indexOf('.') == -1) + throw new CQLParseException("unknown first-class relation: " + + lexer.sval); + return (isProxRelation() || lexer.ttype == lexer.TT_ANY || lexer.ttype == lexer.TT_ALL || lexer.ttype == lexer.TT_EXACT || - lexer.ttype == lexer.TT_SCR); + lexer.ttype == lexer.TT_SCR || + lexer.ttype == lexer.TT_WORD); } + // Checks for a relation that may be used inside a prox operator private boolean isProxRelation() { debug("isProxRelation: checking ttype=" + lexer.ttype + " (" + lexer.render() + ")"); @@ -257,6 +278,8 @@ public class CQLParser { // The following is a complete list of keywords. Because // they're listed here, they can be used unquoted as // qualifiers, terms, prefix names and prefix identifiers. + // ### Instead, we should ask the lexer whether what we + // have is a keyword, and let the knowledge reside there. lexer.ttype == lexer.TT_AND || lexer.ttype == lexer.TT_OR || lexer.ttype == lexer.TT_NOT || @@ -273,7 +296,8 @@ public class CQLParser { lexer.ttype == lexer.TT_RELEVANT || lexer.ttype == lexer.TT_FUZZY || lexer.ttype == lexer.TT_STEM || - lexer.ttype == lexer.TT_SCR) { + lexer.ttype == lexer.TT_SCR || + lexer.ttype == lexer.TT_PHONETIC) { String symbol = (lexer.ttype == lexer.TT_NUMBER) ? lexer.render() : lexer.sval; match(lexer.ttype);