[ https://issues.apache.org/jira/browse/JENA-1584?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16569464#comment-16569464 ]
ASF GitHub Bot commented on JENA-1584: -------------------------------------- Github user kinow commented on a diff in the pull request: https://github.com/apache/jena/pull/455#discussion_r207735233 --- Diff: jena-arq/src/main/java/org/apache/jena/riot/lang/extra/javacc/ParseException.java --- @@ -0,0 +1,205 @@ +/* Generated By:JavaCC: Do not edit this line. ParseException.java Version 6.0 */ +/* JavaCCOptions:KEEP_LINE_COL=null */ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.jena.riot.lang.extra.javacc; + +/** + * This exception is thrown when parse errors are encountered. + * You can explicitly create objects of this exception type by + * calling the method generateParseException in the generated + * parser. + * + * You can modify this class to customize your error reporting + * mechanisms so long as you retain the public fields. + */ +public class ParseException extends Exception { + + /** + * The version identifier for this Serializable class. + * Increment only if the <i>serialized</i> form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /** + * This constructor is used by the method "generateParseException" + * in the generated parser. Calling this constructor generates + * a new object of this type with the fields "currentToken", + * "expectedTokenSequences", and "tokenImage" set. + */ + public ParseException(Token currentTokenVal, + int[][] expectedTokenSequencesVal, + String[] tokenImageVal + ) + { + super(initialise(currentTokenVal, expectedTokenSequencesVal, tokenImageVal)); + currentToken = currentTokenVal; + expectedTokenSequences = expectedTokenSequencesVal; + tokenImage = tokenImageVal; + } + + /** + * The following constructors are for use by you for whatever + * purpose you can think of. Constructing the exception in this + * manner makes the exception behave in the normal way - i.e., as + * documented in the class "Throwable". The fields "errorToken", + * "expectedTokenSequences", and "tokenImage" do not contain + * relevant information. The JavaCC generated code does not use + * these constructors. + */ + + public ParseException() { + super(); + } + + /** Constructor with message. */ + public ParseException(String message) { + super(message); + } + + + /** + * This is the last token that has been consumed successfully. If + * this object has been created due to a parse error, the token + * followng this token will (therefore) be the first error token. + */ + public Token currentToken; + + /** + * Each entry in this array is an array of integers. Each array + * of integers represents a sequence of tokens (by their ordinal + * values) that is expected at this point of the parse. + */ + public int[][] expectedTokenSequences; + + /** + * This is a reference to the "tokenImage" array of the generated + * parser within which the parse error occurred. This array is + * defined in the generated ...Constants interface. + */ + public String[] tokenImage; + + /** + * It uses "currentToken" and "expectedTokenSequences" to generate a parse + * error message and returns it. If this object has been created + * due to a parse error, and you do not catch it (it gets thrown + * from the parser) the correct error message + * gets displayed. + */ + private static String initialise(Token currentToken, + int[][] expectedTokenSequences, + String[] tokenImage) { + String eol = System.getProperty("line.separator", "\n"); + StringBuffer expected = new StringBuffer(); + int maxSize = 0; + for (int i = 0; i < expectedTokenSequences.length; i++) { + if (maxSize < expectedTokenSequences[i].length) { + maxSize = expectedTokenSequences[i].length; + } + for (int j = 0; j < expectedTokenSequences[i].length; j++) { + expected.append(tokenImage[expectedTokenSequences[i][j]]).append(' '); + } + if (expectedTokenSequences[i][expectedTokenSequences[i].length - 1] != 0) { + expected.append("..."); + } + expected.append(eol).append(" "); + } + String retval = "Encountered \""; + Token tok = currentToken.next; + for (int i = 0; i < maxSize; i++) { + if (i != 0) retval += " "; + if (tok.kind == 0) { + retval += tokenImage[0]; + break; + } + retval += " " + tokenImage[tok.kind]; + retval += " \""; + retval += add_escapes(tok.image); + retval += " \""; + tok = tok.next; + } + retval += "\" at line " + currentToken.next.beginLine + ", column " + currentToken.next.beginColumn; + retval += "." + eol; + if (expectedTokenSequences.length == 1) { + retval += "Was expecting:" + eol + " "; + } else { + retval += "Was expecting one of:" + eol + " "; + } + retval += expected.toString(); + return retval; + } + + /** + * The end of line string for this machine. + */ + protected String eol = System.getProperty("line.separator", "\n"); + + /** + * Used to convert raw characters to their escaped version + * when these raw version cannot be used as part of an ASCII + * string literal. + */ + static String add_escapes(String str) { + StringBuffer retval = new StringBuffer(); --- End diff -- See comment above about `StringBuffer` & `StringBuilder`... > Include a Javacc based Turtle parser in RIOT > -------------------------------------------- > > Key: JENA-1584 > URL: https://issues.apache.org/jira/browse/JENA-1584 > Project: Apache Jena > Issue Type: Improvement > Components: RIOT > Affects Versions: Jena 3.8.0 > Reporter: Andy Seaborne > Assignee: Andy Seaborne > Priority: Minor > Fix For: Jena 3.9.0 > > > Turtle is the basis for some additional languages (RDF*, SHACL and ShEX > compact forms). > The main RIOT Turtle parser is written for speed, with the tuned tokenizer > and directly written java grammar parser. This makes it harder to reuse and > extend. > This ticket proposes including another RDF 1.1 compliant Turtle parser based > on JavaCC to provide an easier route for additional languages by providing > all the details of Turtle such as the tokens and prefix name handling, in a > form more suitable as a base for the new language. It will still be by being > a copy of the parser, system, not class inheritance.) > RDF 1.1 Turtle and SPARQL 1.1 were aligned by the working groups and share > tokens and several grammar rules. > This would not be active by default (i.e. not a registered {{Lang}} and it's > parser factory but registered by automatic initialization). It's test suite > would be run in the build and pass the RDF 1.1 Turtle test suite. > > There is non-RDF1.1 Javacc Turtle parser in jena-core is based on the > pre-RDF1.1 state of Turtle. It is sufficient for the assembler tests that > read turtle files. It could be moved into the test area except there appear > to be some legacy applications that only use jena-core. > -- This message was sent by Atlassian JIRA (v7.6.3#76005)