finish a basic build of antlr

Author: alan23273850

include/antlr4-runtime/ANTLRErrorListener.h

@@ -0,0 +1,167 @@
+/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
+ * Use of this file is governed by the BSD 3-clause license that
+ * can be found in the LICENSE.txt file in the project root.
+ */
+
+#pragma once
+
+#include "RecognitionException.h"
+
+namespace antlrcpp {
+  class BitSet;
+}
+
+namespace antlr4 {
+
+  /// How to emit recognition errors (an interface in Java).
+  class ANTLR4CPP_PUBLIC ANTLRErrorListener {
+  public:
+    virtual ~ANTLRErrorListener();
+
+    /// <summary>
+    /// Upon syntax error, notify any interested parties. This is not how to
+    /// recover from errors or compute error messages. <seealso cref="ANTLRErrorStrategy"/>
+    /// specifies how to recover from syntax errors and how to compute error
+    /// messages. This listener's job is simply to emit a computed message,
+    /// though it has enough information to create its own message in many cases.
+    /// <p/>
+    /// The <seealso cref="RecognitionException"/> is non-null for all syntax errors except
+    /// when we discover mismatched token errors that we can recover from
+    /// in-line, without returning from the surrounding rule (via the single
+    /// token insertion and deletion mechanism).
+    /// </summary>
+    /// <param name="recognizer">
+    ///        What parser got the error. From this
+    /// 		  object, you can access the context as well
+    /// 		  as the input stream. </param>
+    /// <param name="offendingSymbol">
+    ///        The offending token in the input token
+    /// 		  stream, unless recognizer is a lexer (then it's null). If
+    /// 		  no viable alternative error, {@code e} has token at which we
+    /// 		  started production for the decision. </param>
+    /// <param name="line">
+    /// 		  The line number in the input where the error occurred. </param>
+    /// <param name="charPositionInLine">
+    /// 		  The character position within that line where the error occurred. </param>
+    /// <param name="msg">
+    /// 		  The message to emit. </param>
+    /// <param name="e">
+    ///        The exception generated by the parser that led to
+    ///        the reporting of an error. It is null in the case where
+    ///        the parser was able to recover in line without exiting the
+    ///        surrounding rule. </param>
+    virtual void syntaxError(Recognizer *recognizer, Token *offendingSymbol, size_t line,
+                             size_t charPositionInLine, const std::string &msg, std::exception_ptr e) = 0;
+
+    /**
+     * This method is called by the parser when a full-context prediction
+     * results in an ambiguity.
+     *
+     * <p>Each full-context prediction which does not result in a syntax error
+     * will call either {@link #reportContextSensitivity} or
+     * {@link #reportAmbiguity}.</p>
+     *
+     * <p>When {@code ambigAlts} is not null, it contains the set of potentially
+     * viable alternatives identified by the prediction algorithm. When
+     * {@code ambigAlts} is null, use {@link ATNConfigSet#getAlts} to obtain the
+     * represented alternatives from the {@code configs} argument.</p>
+     *
+     * <p>When {@code exact} is {@code true}, <em>all</em> of the potentially
+     * viable alternatives are truly viable, i.e. this is reporting an exact
+     * ambiguity. When {@code exact} is {@code false}, <em>at least two</em> of
+     * the potentially viable alternatives are viable for the current input, but
+     * the prediction algorithm terminated as soon as it determined that at
+     * least the <em>minimum</em> potentially viable alternative is truly
+     * viable.</p>
+     *
+     * <p>When the {@link PredictionMode#LL_EXACT_AMBIG_DETECTION} prediction
+     * mode is used, the parser is required to identify exact ambiguities so
+     * {@code exact} will always be {@code true}.</p>
+     *
+     * <p>This method is not used by lexers.</p>
+     *
+     * @param recognizer the parser instance
+     * @param dfa the DFA for the current decision
+     * @param startIndex the input index where the decision started
+     * @param stopIndex the input input where the ambiguity was identified
+     * @param exact {@code true} if the ambiguity is exactly known, otherwise
+     * {@code false}. This is always {@code true} when
+     * {@link PredictionMode#LL_EXACT_AMBIG_DETECTION} is used.
+     * @param ambigAlts the potentially ambiguous alternatives, or {@code null}
+     * to indicate that the potentially ambiguous alternatives are the complete
+     * set of represented alternatives in {@code configs}
+     * @param configs the ATN configuration set where the ambiguity was
+     * identified
+     */
+    virtual void reportAmbiguity(Parser *recognizer, const dfa::DFA &dfa, size_t startIndex, size_t stopIndex, bool exact,
+      const antlrcpp::BitSet &ambigAlts, atn::ATNConfigSet *configs) = 0;
+
+    /**
+     * This method is called when an SLL conflict occurs and the parser is about
+     * to use the full context information to make an LL decision.
+     *
+     * <p>If one or more configurations in {@code configs} contains a semantic
+     * predicate, the predicates are evaluated before this method is called. The
+     * subset of alternatives which are still viable after predicates are
+     * evaluated is reported in {@code conflictingAlts}.</p>
+     *
+     * <p>This method is not used by lexers.</p>
+     *
+     * @param recognizer the parser instance
+     * @param dfa the DFA for the current decision
+     * @param startIndex the input index where the decision started
+     * @param stopIndex the input index where the SLL conflict occurred
+     * @param conflictingAlts The specific conflicting alternatives. If this is
+     * {@code null}, the conflicting alternatives are all alternatives
+     * represented in {@code configs}. At the moment, conflictingAlts is non-null
+     * (for the reference implementation, but Sam's optimized version can see this
+     * as null).
+     * @param configs the ATN configuration set where the SLL conflict was
+     * detected
+     */
+    virtual void reportAttemptingFullContext(Parser *recognizer, const dfa::DFA &dfa, size_t startIndex, size_t stopIndex,
+      const antlrcpp::BitSet &conflictingAlts, atn::ATNConfigSet *configs) = 0;
+
+    /**
+     * This method is called by the parser when a full-context prediction has a
+     * unique result.
+     *
+     * <p>Each full-context prediction which does not result in a syntax error
+     * will call either {@link #reportContextSensitivity} or
+     * {@link #reportAmbiguity}.</p>
+     *
+     * <p>For prediction implementations that only evaluate full-context
+     * predictions when an SLL conflict is found (including the default
+     * {@link ParserATNSimulator} implementation), this method reports cases
+     * where SLL conflicts were resolved to unique full-context predictions,
+     * i.e. the decision was context-sensitive. This report does not necessarily
+     * indicate a problem, and it may appear even in completely unambiguous
+     * grammars.</p>
+     *
+     * <p>{@code configs} may have more than one represented alternative if the
+     * full-context prediction algorithm does not evaluate predicates before
+     * beginning the full-context prediction. In all cases, the final prediction
+     * is passed as the {@code prediction} argument.</p>
+     *
+     * <p>Note that the definition of "context sensitivity" in this method
+     * differs from the concept in {@link DecisionInfo#contextSensitivities}.
+     * This method reports all instances where an SLL conflict occurred but LL
+     * parsing produced a unique result, whether or not that unique result
+     * matches the minimum alternative in the SLL conflicting set.</p>
+     *
+     * <p>This method is not used by lexers.</p>
+     *
+     * @param recognizer the parser instance
+     * @param dfa the DFA for the current decision
+     * @param startIndex the input index where the decision started
+     * @param stopIndex the input index where the context sensitivity was
+     * finally determined
+     * @param prediction the unambiguous result of the full-context prediction
+     * @param configs the ATN configuration set where the unambiguous prediction
+     * was determined
+     */
+    virtual void reportContextSensitivity(Parser *recognizer, const dfa::DFA &dfa, size_t startIndex, size_t stopIndex,
+      size_t prediction, atn::ATNConfigSet *configs) = 0;
+  };
+
+} // namespace antlr4

include/antlr4-runtime/ANTLRErrorStrategy.h

@@ -0,0 +1,121 @@
+/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
+ * Use of this file is governed by the BSD 3-clause license that
+ * can be found in the LICENSE.txt file in the project root.
+ */
+
+#pragma once
+
+#include "Token.h"
+
+namespace antlr4 {
+
+  /// <summary>
+  /// The interface for defining strategies to deal with syntax errors encountered
+  /// during a parse by ANTLR-generated parsers. We distinguish between three
+  /// different kinds of errors:
+  ///
+  /// <ul>
+  /// <li>The parser could not figure out which path to take in the ATN (none of
+  /// the available alternatives could possibly match)</li>
+  /// <li>The current input does not match what we were looking for</li>
+  /// <li>A predicate evaluated to false</li>
+  /// </ul>
+  ///
+  /// Implementations of this interface report syntax errors by calling
+  /// <seealso cref="Parser#notifyErrorListeners"/>.
+  /// <p/>
+  /// TODO: what to do about lexers
+  /// </summary>
+  class ANTLR4CPP_PUBLIC ANTLRErrorStrategy {
+  public:
+
+    /// <summary>
+    /// Reset the error handler state for the specified {@code recognizer}. </summary>
+    /// <param name="recognizer"> the parser instance </param>
+    virtual ~ANTLRErrorStrategy();
+
+    virtual void reset(Parser *recognizer) = 0;
+
+    /**
+     * This method is called when an unexpected symbol is encountered during an
+     * inline match operation, such as {@link Parser#match}. If the error
+     * strategy successfully recovers from the match failure, this method
+     * returns the {@link Token} instance which should be treated as the
+     * successful result of the match.
+     *
+     * <p>This method handles the consumption of any tokens - the caller should
+     * <b>not</b> call {@link Parser#consume} after a successful recovery.</p>
+     *
+     * <p>Note that the calling code will not report an error if this method
+     * returns successfully. The error strategy implementation is responsible
+     * for calling {@link Parser#notifyErrorListeners} as appropriate.</p>
+     *
+     * @param recognizer the parser instance
+     * @throws RecognitionException if the error strategy was not able to
+     * recover from the unexpected input symbol
+     */
+    virtual Token* recoverInline(Parser *recognizer) = 0;
+
+    /// <summary>
+    /// This method is called to recover from exception {@code e}. This method is
+    /// called after <seealso cref="#reportError"/> by the default exception handler
+    /// generated for a rule method.
+    /// </summary>
+    /// <seealso cref= #reportError
+    /// </seealso>
+    /// <param name="recognizer"> the parser instance </param>
+    /// <param name="e"> the recognition exception to recover from </param>
+    /// <exception cref="RecognitionException"> if the error strategy could not recover from
+    /// the recognition exception </exception>
+    virtual void recover(Parser *recognizer, std::exception_ptr e) = 0;
+
+    /// <summary>
+    /// This method provides the error handler with an opportunity to handle
+    /// syntactic or semantic errors in the input stream before they result in a
+    /// <seealso cref="RecognitionException"/>.
+    /// <p/>
+    /// The generated code currently contains calls to <seealso cref="#sync"/> after
+    /// entering the decision state of a closure block ({@code (...)*} or
+    /// {@code (...)+}).
+    /// <p/>
+    /// For an implementation based on Jim Idle's "magic sync" mechanism, see
+    /// <seealso cref="DefaultErrorStrategy#sync"/>.
+    /// </summary>
+    /// <seealso cref= DefaultErrorStrategy#sync
+    /// </seealso>
+    /// <param name="recognizer"> the parser instance </param>
+    /// <exception cref="RecognitionException"> if an error is detected by the error
+    /// strategy but cannot be automatically recovered at the current state in
+    /// the parsing process </exception>
+    virtual void sync(Parser *recognizer) = 0;
+
+    /// <summary>
+    /// Tests whether or not {@code recognizer} is in the process of recovering
+    /// from an error. In error recovery mode, <seealso cref="Parser#consume"/> adds
+    /// symbols to the parse tree by calling
+    /// {@link Parser#createErrorNode(ParserRuleContext, Token)} then
+    /// {@link ParserRuleContext#addErrorNode(ErrorNode)} instead of
+    /// {@link Parser#createTerminalNode(ParserRuleContext, Token)}.
+    /// </summary>
+    /// <param name="recognizer"> the parser instance </param>
+    /// <returns> {@code true} if the parser is currently recovering from a parse
+    /// error, otherwise {@code false} </returns>
+    virtual bool inErrorRecoveryMode(Parser *recognizer) = 0;
+
+    /// <summary>
+    /// This method is called by when the parser successfully matches an input
+    /// symbol.
+    /// </summary>
+    /// <param name="recognizer"> the parser instance </param>
+    virtual void reportMatch(Parser *recognizer) = 0;
+
+    /// <summary>
+    /// Report any kind of <seealso cref="RecognitionException"/>. This method is called by
+    /// the default exception handler generated for a rule method.
+    /// </summary>
+    /// <param name="recognizer"> the parser instance </param>
+    /// <param name="e"> the recognition exception to report </param>
+    virtual void reportError(Parser *recognizer, const RecognitionException &e) = 0;
+  };
+
+} // namespace antlr4

include/antlr4-runtime/ANTLRFileStream.h

@@ -0,0 +1,30 @@
+/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
+ * Use of this file is governed by the BSD 3-clause license that
+ * can be found in the LICENSE.txt file in the project root.
+ */
+
+#pragma once
+
+#include "ANTLRInputStream.h"
+
+namespace antlr4 {
+
+  /// This is an ANTLRInputStream that is loaded from a file all at once
+  /// when you construct the object (or call load()).
+  // TODO: this class needs testing.
+  class ANTLR4CPP_PUBLIC ANTLRFileStream : public ANTLRInputStream {
+  public:
+    ANTLRFileStream() = default;
+    ANTLRFileStream(const std::string &) = delete;
+    ANTLRFileStream(const char *data, size_t length) = delete;
+    ANTLRFileStream(std::istream &stream) = delete;
+
+    // Assumes a file name encoded in UTF-8 and file content in the same encoding (with or w/o BOM).
+    virtual void loadFromFile(const std::string &fileName);
+    virtual std::string getSourceName() const override;
+
+  private:
+    std::string _fileName; // UTF-8 encoded file name.
+  };
+
+} // namespace antlr4