+ * The resulting parse tree may be further processed by hand (see
+ * the individual node-types' documentation for details on the
+ * 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.
+ *
+ * @param cql The query
+ * @return A CQLNode object which is the root of a parse
+ * tree representing the query. */
public CQLNode parse(String cql)
throws CQLParseException, IOException {
lexer = new CQLLexer(cql, LEXDEBUG);
lexer.nextToken();
debug("about to parse_query()");
- CQLNode root = parse_query("srw.serverChoice", new CQLRelation("="));
+ CQLNode root = parse_query("srw.serverChoice", new CQLRelation("scr"));
+ // ### "scr" above should arguably be "="
if (lexer.ttype != lexer.TT_EOF)
throw new CQLParseException("junk after end: " + lexer.render());
@@ -84,13 +102,19 @@ public class CQLParser {
CQLNode expr = parse_query(qualifier, relation);
match(')');
return expr;
- } else if (lexer.ttype != lexer.TT_WORD && lexer.ttype != '"') {
+ } else if (lexer.ttype != lexer.TT_WORD &&
+ lexer.ttype != lexer.TT_NUMBER &&
+ lexer.ttype != '"') {
throw new CQLParseException("expected qualifier or term, " +
"got " + lexer.render());
}
debug("non-parenthesised term");
- word = lexer.sval;
+ if (lexer.ttype == lexer.TT_NUMBER) {
+ word = lexer.render();
+ } else {
+ word = lexer.sval;
+ }
match(lexer.ttype);
if (!isBaseRelation())
break;
@@ -106,7 +130,7 @@ public class CQLParser {
lexer.ttype != lexer.TT_STEM)
throw new CQLParseException("expected relation modifier, "
+ "got " + lexer.render());
- relation.addModifier(lexer.sval);
+ relation.addModifier(lexer.sval.toLowerCase());
match(lexer.ttype);
}
@@ -129,7 +153,8 @@ public class CQLParser {
if (lexer.ttype != '/') {
// not an omitted default
switch (i) {
- // Assumes order is: relation/distance/unit/ordering
+ // Order should be: relation/distance/unit/ordering
+ // For now, use MA's: unit/relation/distance/ordering
case 0: gatherProxRelation(node); break;
case 1: gatherProxDistance(node); break;
case 2: gatherProxUnit(node); break;
@@ -181,7 +206,7 @@ public class CQLParser {
match(lexer.ttype);
}
- boolean isBaseRelation() {
+ private boolean isBaseRelation() {
debug("isBaseRelation: checking ttype=" + lexer.ttype +
" (" + lexer.render() + ")");
return (isProxRelation() ||
@@ -190,7 +215,7 @@ public class CQLParser {
lexer.ttype == lexer.TT_EXACT);
}
- boolean isProxRelation() {
+ private boolean isProxRelation() {
debug("isProxRelation: checking ttype=" + lexer.ttype +
" (" + lexer.render() + ")");
return (lexer.ttype == '<' ||
@@ -215,47 +240,83 @@ public class CQLParser {
}
- // Test harness.
- //
- // e.g. echo '(au=Kerninghan or au=Ritchie) and ti=Unix' |
- // java org.z3950.zing.cql.CQLParser
- // yields:
- //
+ * Reads a CQL query either from its command-line argument, if + * there is one, or standard input otherwise. So these two + * invocations are equivalent: + *
+ * CQLParser 'au=(Kerninghan or Ritchie) and ti=Unix' + * echo au=(Kerninghan or Ritchie) and ti=Unix | CQLParser + *+ * The test-harness parses the supplied query and renders is as + * XCQL, so that both of the invocations above produce the + * following output: + *
+ * <triple> + * <boolean> + * <value>and</value> + * </boolean> + * <triple> + * <boolean> + * <value>or</value> + * </boolean> + * <searchClause> + * <index>au</index> + * <relation> + * <value>=</value> + * </relation> + * <term>Kerninghan</term> + * </searchClause> + * <searchClause> + * <index>au</index> + * <relation> + * <value>=</value> + * </relation> + * <term>Ritchie</term> + * </searchClause> + * </triple> + * <searchClause> + * <index>ti</index> + * <relation> + * <value>=</value> + * </relation> + * <term>Unix</term> + * </searchClause> + * </triple> + *+ *
+ * @param -c
+ * Causes the output to be written in CQL rather than XCQL - that
+ * is, a query equivalent to that which was input, is output. In
+ * effect, the test harness acts as a query canonicaliser.
+ * @return
+ * The input query, either as XCQL [default] or CQL [if the
+ * -c option is supplied].
+ */
public static void main (String[] args) {
- boolean canonicalise = false;
+ char mode = 'x'; // x=XCQL, c=CQL, p=PQF
+ String pfile = null;
+
Vector argv = new Vector();
for (int i = 0; i < args.length; i++) {
argv.add(args[i]);
}
if (argv.size() > 0 && argv.get(0).equals("-c")) {
- canonicalise = true;
+ mode = 'c';
+ argv.remove(0);
+ } else if (argv.size() > 1 && argv.get(0).equals("-p")) {
+ mode = 'p';
+ argv.remove(0);
+ pfile = (String) argv.get(0);
argv.remove(0);
}
if (argv.size() > 1) {
- System.err.println("Usage: CQLParser [-c] [