did_parser 1.0.0

data/ext/did_parser/antlr4-upstream/runtime/Cpp/runtime/src/TokenStreamRewriter.h

@@ -0,0 +1,295 @@
+/* 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 "antlr4-common.h"
+
+namespace antlr4 {
+
+  /**
+   * Useful for rewriting out a buffered input token stream after doing some
+   * augmentation or other manipulations on it.
+   *
+   * <p>
+   * You can insert stuff, replace, and delete chunks. Note that the operations
+   * are done lazily--only if you convert the buffer to a {@link String} with
+   * {@link TokenStream#getText()}. This is very efficient because you are not
+   * moving data around all the time. As the buffer of tokens is converted to
+   * strings, the {@link #getText()} method(s) scan the input token stream and
+   * check to see if there is an operation at the current index. If so, the
+   * operation is done and then normal {@link String} rendering continues on the
+   * buffer. This is like having multiple Turing machine instruction streams
+   * (programs) operating on a single input tape. :)</p>
+   *
+   * <p>
+   * This rewriter makes no modifications to the token stream. It does not ask the
+   * stream to fill itself up nor does it advance the input cursor. The token
+   * stream {@link TokenStream#index()} will return the same value before and
+   * after any {@link #getText()} call.</p>
+   *
+   * <p>
+   * The rewriter only works on tokens that you have in the buffer and ignores the
+   * current input cursor. If you are buffering tokens on-demand, calling
+   * {@link #getText()} halfway through the input will only do rewrites for those
+   * tokens in the first half of the file.</p>
+   *
+   * <p>
+   * Since the operations are done lazily at {@link #getText}-time, operations do
+   * not screw up the token index values. That is, an insert operation at token
+   * index {@code i} does not change the index values for tokens
+   * {@code i}+1..n-1.</p>
+   *
+   * <p>
+   * Because operations never actually alter the buffer, you may always get the
+   * original token stream back without undoing anything. Since the instructions
+   * are queued up, you can easily simulate transactions and roll back any changes
+   * if there is an error just by removing instructions. For example,</p>
+   *
+   * <pre>
+   * CharStream input = new ANTLRFileStream("input");
+   * TLexer lex = new TLexer(input);
+   * CommonTokenStream tokens = new CommonTokenStream(lex);
+   * T parser = new T(tokens);
+   * TokenStreamRewriter rewriter = new TokenStreamRewriter(tokens);
+   * parser.startRule();
+   * </pre>
+   *
+   * <p>
+   * Then in the rules, you can execute (assuming rewriter is visible):</p>
+   *
+   * <pre>
+   * Token t,u;
+   * ...
+   * rewriter.insertAfter(t, "text to put after t");}
+   * rewriter.insertAfter(u, "text after u");}
+   * System.out.println(rewriter.getText());
+   * </pre>
+   *
+   * <p>
+   * You can also have multiple "instruction streams" and get multiple rewrites
+   * from a single pass over the input. Just name the instruction streams and use
+   * that name again when printing the buffer. This could be useful for generating
+   * a C file and also its header file--all from the same buffer:</p>
+   *
+   * <pre>
+   * rewriter.insertAfter("pass1", t, "text to put after t");}
+   * rewriter.insertAfter("pass2", u, "text after u");}
+   * System.out.println(rewriter.getText("pass1"));
+   * System.out.println(rewriter.getText("pass2"));
+   * </pre>
+   *
+   * <p>
+   * If you don't use named rewrite streams, a "default" stream is used as the
+   * first example shows.</p>
+   */
+  class ANTLR4CPP_PUBLIC TokenStreamRewriter {
+  public:
+    static const std::string DEFAULT_PROGRAM_NAME;
+    static constexpr size_t PROGRAM_INIT_SIZE = 100;
+    static constexpr size_t MIN_TOKEN_INDEX = 0;
+
+    TokenStreamRewriter(TokenStream *tokens);
+    virtual ~TokenStreamRewriter();
+
+    TokenStream *getTokenStream();
+
+    virtual void rollback(size_t instructionIndex);
+
+    /// Rollback the instruction stream for a program so that
+    /// the indicated instruction (via instructionIndex) is no
+    /// longer in the stream.  UNTESTED!
+    virtual void rollback(const std::string &programName, size_t instructionIndex);
+
+    virtual void deleteProgram();
+
+    /// Reset the program so that no instructions exist.
+    virtual void deleteProgram(const std::string &programName);
+    virtual void insertAfter(Token *t, const std::string& text);
+    virtual void insertAfter(size_t index, const std::string& text);
+    virtual void insertAfter(const std::string &programName, Token *t, const std::string& text);
+    virtual void insertAfter(const std::string &programName, size_t index, const std::string& text);
+
+    virtual void insertBefore(Token *t, const std::string& text);
+    virtual void insertBefore(size_t index, const std::string& text);
+    virtual void insertBefore(const std::string &programName, Token *t, const std::string& text);
+    virtual void insertBefore(const std::string &programName, size_t index, const std::string& text);
+
+    virtual void replace(size_t index, const std::string& text);
+    virtual void replace(size_t from, size_t to, const std::string& text);
+    virtual void replace(Token *indexT, const std::string& text);
+    virtual void replace(Token *from, Token *to, const std::string& text);
+    virtual void replace(const std::string &programName, size_t from, size_t to, const std::string& text);
+    virtual void replace(const std::string &programName, Token *from, Token *to, const std::string& text);
+
+    virtual void Delete(size_t index);
+    virtual void Delete(size_t from, size_t to);
+    virtual void Delete(Token *indexT);
+    virtual void Delete(Token *from, Token *to);
+    virtual void Delete(const std::string &programName, size_t from, size_t to);
+    virtual void Delete(const std::string &programName, Token *from, Token *to);
+
+    virtual size_t getLastRewriteTokenIndex();
+
+    /// Return the text from the original tokens altered per the
+    /// instructions given to this rewriter.
+    virtual std::string getText();
+
+    /** Return the text from the original tokens altered per the
+     *  instructions given to this rewriter in programName.
+     */
+    std::string getText(std::string programName);
+
+    /// Return the text associated with the tokens in the interval from the
+    /// original token stream but with the alterations given to this rewriter.
+    /// The interval refers to the indexes in the original token stream.
+    /// We do not alter the token stream in any way, so the indexes
+    /// and intervals are still consistent. Includes any operations done
+    /// to the first and last token in the interval. So, if you did an
+    /// insertBefore on the first token, you would get that insertion.
+    /// The same is true if you do an insertAfter the stop token.
+    virtual std::string getText(const misc::Interval &interval);
+
+    virtual std::string getText(const std::string &programName, const misc::Interval &interval);
+
+  protected:
+    class RewriteOperation {
+    public:
+      /// What index into rewrites List are we?
+      size_t index;
+      std::string text;
+
+      /// Token buffer index.
+      size_t instructionIndex;
+
+      RewriteOperation(TokenStreamRewriter *outerInstance, size_t index);
+      RewriteOperation(TokenStreamRewriter *outerInstance, size_t index, const std::string& text);
+      virtual ~RewriteOperation();
+
+      /// Execute the rewrite operation by possibly adding to the buffer.
+      /// Return the index of the next token to operate on.
+
+      virtual size_t execute(std::string *buf);
+      virtual std::string toString();
+
+    private:
+      TokenStreamRewriter *const outerInstance;
+      void InitializeInstanceFields();
+    };
+
+    class InsertBeforeOp : public RewriteOperation {
+    private:
+      TokenStreamRewriter *const outerInstance;
+
+    public:
+      InsertBeforeOp(TokenStreamRewriter *outerInstance, size_t index, const std::string& text);
+
+      virtual size_t execute(std::string *buf) override;
+    };
+
+    class ReplaceOp : public RewriteOperation {
+    private:
+      TokenStreamRewriter *const outerInstance;
+
+    public:
+      size_t lastIndex;
+
+      ReplaceOp(TokenStreamRewriter *outerInstance, size_t from, size_t to, const std::string& text);
+      virtual size_t execute(std::string *buf) override;
+      virtual std::string toString() override;
+
+    private:
+      void InitializeInstanceFields();
+    };
+
+    /// Our source stream
+    TokenStream *const tokens;
+
+    /// You may have multiple, named streams of rewrite operations.
+    /// I'm calling these things "programs."
+    /// Maps String (name) -> rewrite (List)
+    std::map<std::string, std::vector<RewriteOperation*>> _programs;
+
+    /// <summary>
+    /// Map String (program name) -> Integer index </summary>
+    std::map<std::string, size_t> _lastRewriteTokenIndexes;
+    virtual size_t getLastRewriteTokenIndex(const std::string &programName);
+    virtual void setLastRewriteTokenIndex(const std::string &programName, size_t i);
+    virtual std::vector<RewriteOperation*>& getProgram(const std::string &name);
+
+    /// <summary>
+    /// We need to combine operations and report invalid operations (like
+    ///  overlapping replaces that are not completed nested).  Inserts to
+    ///  same index need to be combined etc...   Here are the cases:
+    ///
+    ///  I.i.u I.j.v                                leave alone, nonoverlapping
+    ///  I.i.u I.i.v                                combine: Iivu
+    ///
+    ///  R.i-j.u R.x-y.v    | i-j in x-y            delete first R
+    ///  R.i-j.u R.i-j.v                            delete first R
+    ///  R.i-j.u R.x-y.v    | x-y in i-j            ERROR
+    ///  R.i-j.u R.x-y.v    | boundaries overlap    ERROR
+    ///
+    ///  Delete special case of replace (text==null):
+    ///  D.i-j.u D.x-y.v    | boundaries overlap    combine to max(min)..max(right)
+    ///
+    ///  I.i.u R.x-y.v | i in (x+1)-y           delete I (since insert before
+    ///                                         we're not deleting i)
+    ///  I.i.u R.x-y.v | i not in (x+1)-y       leave alone, nonoverlapping
+    ///  R.x-y.v I.i.u | i in x-y               ERROR
+    ///  R.x-y.v I.x.u                          R.x-y.uv (combine, delete I)
+    ///  R.x-y.v I.i.u | i not in x-y           leave alone, nonoverlapping
+    ///
+    ///  I.i.u = insert u before op @ index i
+    ///  R.x-y.u = replace x-y indexed tokens with u
+    ///
+    ///  First we need to examine replaces.  For any replace op:
+    ///
+    ///         1. wipe out any insertions before op within that range.
+    ///     2. Drop any replace op before that is contained completely within
+    ///         that range.
+    ///     3. Throw exception upon boundary overlap with any previous replace.
+    ///
+    ///  Then we can deal with inserts:
+    ///
+    ///         1. for any inserts to same index, combine even if not adjacent.
+    ///         2. for any prior replace with same left boundary, combine this
+    ///         insert with replace and delete this replace.
+    ///         3. throw exception if index in same range as previous replace
+    ///
+    ///  Don't actually delete; make op null in list. Easier to walk list.
+    ///  Later we can throw as we add to index -> op map.
+    ///
+    ///  Note that I.2 R.2-2 will wipe out I.2 even though, technically, the
+    ///  inserted stuff would be before the replace range.  But, if you
+    ///  add tokens in front of a method body '{' and then delete the method
+    ///  body, I think the stuff before the '{' you added should disappear too.
+    ///
+    ///  Return a map from token index to operation.
+    /// </summary>
+    virtual std::unordered_map<size_t, RewriteOperation*> reduceToSingleOperationPerIndex(std::vector<RewriteOperation*> &rewrites);
+
+    virtual std::string catOpText(std::string *a, std::string *b);
+
+    /// Get all operations before an index of a particular kind.
+    template <typename T>
+    std::vector<T *> getKindOfOps(std::vector<RewriteOperation *> rewrites, size_t before) {
+      std::vector<T *> ops;
+      for (size_t i = 0; i < before && i < rewrites.size(); i++) {
+        T *op = dynamic_cast<T *>(rewrites[i]);
+        if (op == nullptr) { // ignore deleted or non matching entries
+          continue;
+        }
+        ops.push_back(op);
+      }
+      return ops;
+    }
+
+  private:
+    std::vector<RewriteOperation *>& initializeProgram(const std::string &name);
+
+  };
+
+} // namespace antlr4

data/ext/did_parser/antlr4-upstream/runtime/Cpp/runtime/src/UnbufferedCharStream.cpp

@@ -0,0 +1,208 @@
+/* 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.
+ */
+
+#include "misc/Interval.h"
+#include "Exceptions.h"
+#include "support/Utf8.h"
+
+#include "UnbufferedCharStream.h"
+
+using namespace antlrcpp;
+using namespace antlr4;
+using namespace antlr4::misc;
+
+UnbufferedCharStream::UnbufferedCharStream(std::wistream &input)
+    : _p(0), _numMarkers(0), _lastChar(0), _lastCharBufferStart(0), _currentCharIndex(0), _input(input) {
+  // The vector's size is what used to be n in Java code.
+  fill(1); // prime
+}
+
+void UnbufferedCharStream::consume() {
+  if (LA(1) == EOF) {
+    throw IllegalStateException("cannot consume EOF");
+  }
+
+  // buf always has at least data[p==0] in this method due to ctor
+  _lastChar = _data[_p]; // track last char for LA(-1)
+
+  if (_p == _data.size() - 1 && _numMarkers == 0) {
+    size_t capacity = _data.capacity();
+    _data.clear();
+    _data.reserve(capacity);
+
+    _p = 0;
+    _lastCharBufferStart = _lastChar;
+  } else {
+    _p++;
+  }
+
+  _currentCharIndex++;
+  sync(1);
+}
+
+void UnbufferedCharStream::sync(size_t want) {
+  if (_p + want <= _data.size()) // Already enough data loaded?
+    return;
+
+  fill(_p + want - _data.size());
+}
+
+size_t UnbufferedCharStream::fill(size_t n) {
+  for (size_t i = 0; i < n; i++) {
+    if (_data.size() > 0 && _data.back() == 0xFFFF) {
+      return i;
+    }
+
+    try {
+      char32_t c = nextChar();
+      add(c);
+#if defined(_MSC_FULL_VER) && _MSC_FULL_VER < 190023026
+    } catch (IOException &ioe) {
+      // throw_with_nested is not available before VS 2015.
+      throw ioe;
+#else
+    } catch (IOException & /*ioe*/) {
+      std::throw_with_nested(RuntimeException());
+#endif
+    }
+  }
+
+  return n;
+}
+
+char32_t UnbufferedCharStream::nextChar()  {
+  return _input.get();
+}
+
+void UnbufferedCharStream::add(char32_t c) {
+  _data += c;
+}
+
+size_t UnbufferedCharStream::LA(ssize_t i) {
+  if (i == -1) { // special case
+    return _lastChar;
+  }
+
+  // We can look back only as many chars as we have buffered.
+  ssize_t index = static_cast<ssize_t>(_p) + i - 1;
+  if (index < 0) {
+    throw IndexOutOfBoundsException();
+  }
+
+  if (i > 0) {
+    sync(static_cast<size_t>(i)); // No need to sync if we look back.
+  }
+  if (static_cast<size_t>(index) >= _data.size()) {
+    return EOF;
+  }
+
+  if (_data[static_cast<size_t>(index)] == std::char_traits<wchar_t>::eof()) {
+    return EOF;
+  }
+
+  return _data[static_cast<size_t>(index)];
+}
+
+ssize_t UnbufferedCharStream::mark() {
+  if (_numMarkers == 0) {
+    _lastCharBufferStart = _lastChar;
+  }
+
+  ssize_t mark = -static_cast<ssize_t>(_numMarkers) - 1;
+  _numMarkers++;
+  return mark;
+}
+
+void UnbufferedCharStream::release(ssize_t marker) {
+  ssize_t expectedMark = -static_cast<ssize_t>(_numMarkers);
+  if (marker != expectedMark) {
+    throw IllegalStateException("release() called with an invalid marker.");
+  }
+
+  _numMarkers--;
+  if (_numMarkers == 0 && _p > 0) {
+    _data.erase(0, _p);
+    _p = 0;
+    _lastCharBufferStart = _lastChar;
+  }
+}
+
+size_t UnbufferedCharStream::index() {
+  return _currentCharIndex;
+}
+
+void UnbufferedCharStream::seek(size_t index) {
+  if (index == _currentCharIndex) {
+    return;
+  }
+
+  if (index > _currentCharIndex) {
+    sync(index - _currentCharIndex);
+    index = std::min(index, getBufferStartIndex() + _data.size() - 1);
+  }
+
+  // index == to bufferStartIndex should set p to 0
+  ssize_t i = static_cast<ssize_t>(index) - static_cast<ssize_t>(getBufferStartIndex());
+  if (i < 0) {
+    throw IllegalArgumentException(std::string("cannot seek to negative index ") + std::to_string(index));
+  } else if (i >= static_cast<ssize_t>(_data.size())) {
+    throw UnsupportedOperationException("Seek to index outside buffer: " + std::to_string(index) +
+                                        " not in " + std::to_string(getBufferStartIndex()) + ".." +
+                                        std::to_string(getBufferStartIndex() + _data.size()));
+  }
+
+  _p = static_cast<size_t>(i);
+  _currentCharIndex = index;
+  if (_p == 0) {
+    _lastChar = _lastCharBufferStart;
+  } else {
+    _lastChar = _data[_p - 1];
+  }
+}
+
+size_t UnbufferedCharStream::size() {
+  throw UnsupportedOperationException("Unbuffered stream cannot know its size");
+}
+
+std::string UnbufferedCharStream::getSourceName() const {
+  if (name.empty()) {
+    return UNKNOWN_SOURCE_NAME;
+  }
+
+  return name;
+}
+
+std::string UnbufferedCharStream::getText(const misc::Interval &interval) {
+  if (interval.a < 0 || interval.b < interval.a - 1) {
+    throw IllegalArgumentException("invalid interval");
+  }
+
+  size_t bufferStartIndex = getBufferStartIndex();
+  if (!_data.empty() && _data.back() == 0xFFFF) {
+    if (interval.a + interval.length() > bufferStartIndex + _data.size()) {
+      throw IllegalArgumentException("the interval extends past the end of the stream");
+    }
+  }
+
+  if (interval.a < static_cast<ssize_t>(bufferStartIndex) || interval.b >= ssize_t(bufferStartIndex + _data.size())) {
+    throw UnsupportedOperationException("interval " + interval.toString() + " outside buffer: " +
+      std::to_string(bufferStartIndex) + ".." + std::to_string(bufferStartIndex + _data.size() - 1));
+  }
+  // convert from absolute to local index
+  size_t i = interval.a - bufferStartIndex;
+  auto maybeUtf8 = Utf8::strictEncode(std::u32string_view(_data).substr(i, interval.length()));
+  if (!maybeUtf8.has_value()) {
+    throw IllegalArgumentException("Unbuffered stream contains invalid Unicode code points");
+  }
+  return std::move(maybeUtf8).value();
+}
+
+std::string UnbufferedCharStream::toString() const {
+  throw UnsupportedOperationException("Unbuffered stream cannot be materialized to a string");
+}
+
+size_t UnbufferedCharStream::getBufferStartIndex() const {
+  return _currentCharIndex - _p;
+}

data/ext/did_parser/antlr4-upstream/runtime/Cpp/runtime/src/UnbufferedCharStream.h

@@ -0,0 +1,117 @@
+/* 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 "CharStream.h"
+
+namespace antlr4 {
+
+  /// Do not buffer up the entire char stream. It does keep a small buffer
+  /// for efficiency and also buffers while a mark exists (set by the
+  /// lookahead prediction in parser). "Unbuffered" here refers to fact
+  /// that it doesn't buffer all data, not that's it's on demand loading of char.
+  class ANTLR4CPP_PUBLIC UnbufferedCharStream : public CharStream {
+  public:
+    /// The name or source of this char stream.
+    std::string name;
+
+    explicit UnbufferedCharStream(std::wistream &input);
+
+    void consume() override;
+    size_t LA(ssize_t i) override;
+
+    /// <summary>
+    /// Return a marker that we can release later.
+    /// <p/>
+    /// The specific marker value used for this class allows for some level of
+    /// protection against misuse where {@code seek()} is called on a mark or
+    /// {@code release()} is called in the wrong order.
+    /// </summary>
+    ssize_t mark() override;
+
+    /// <summary>
+    /// Decrement number of markers, resetting buffer if we hit 0. </summary>
+    /// <param name="marker"> </param>
+    void release(ssize_t marker) override;
+    size_t index() override;
+
+    /// <summary>
+    /// Seek to absolute character index, which might not be in the current
+    ///  sliding window.  Move {@code p} to {@code index-bufferStartIndex}.
+    /// </summary>
+    void seek(size_t index) override;
+    size_t size() override;
+    std::string getSourceName() const override;
+    std::string getText(const misc::Interval &interval) override;
+
+    std::string toString() const override;
+
+  protected:
+    /// A moving window buffer of the data being scanned. While there's a marker,
+    /// we keep adding to buffer. Otherwise, <seealso cref="#consume consume()"/> resets so
+    /// we start filling at index 0 again.
+    // UTF-32 encoded.
+    std::u32string _data;
+    typedef char32_t storage_type;
+
+    /// <summary>
+    /// 0..n-1 index into <seealso cref="#data data"/> of next character.
+    /// <p/>
+    /// The {@code LA(1)} character is {@code data[p]}. If {@code p == n}, we are
+    /// out of buffered characters.
+    /// </summary>
+    size_t _p;
+
+    /// <summary>
+    /// Count up with <seealso cref="#mark mark()"/> and down with
+    /// <seealso cref="#release release()"/>. When we {@code release()} the last mark,
+    /// {@code numMarkers} reaches 0 and we reset the buffer. Copy
+    /// {@code data[p]..data[n-1]} to {@code data[0]..data[(n-1)-p]}.
+    /// </summary>
+    size_t _numMarkers;
+
+    /// This is the {@code LA(-1)} character for the current position.
+    size_t _lastChar; // UTF-32
+
+    /// <summary>
+    /// When {@code numMarkers > 0}, this is the {@code LA(-1)} character for the
+    /// first character in <seealso cref="#data data"/>. Otherwise, this is unspecified.
+    /// </summary>
+    size_t _lastCharBufferStart; // UTF-32
+
+    /// <summary>
+    /// Absolute character index. It's the index of the character about to be
+    /// read via {@code LA(1)}. Goes from 0 to the number of characters in the
+    /// entire stream, although the stream size is unknown before the end is
+    /// reached.
+    /// </summary>
+    size_t _currentCharIndex;
+
+    std::wistream &_input;
+
+    /// <summary>
+    /// Make sure we have 'want' elements from current position <seealso cref="#p p"/>.
+    /// Last valid {@code p} index is {@code data.length-1}. {@code p+need-1} is
+    /// the char index 'need' elements ahead. If we need 1 element,
+    /// {@code (p+1-1)==p} must be less than {@code data.length}.
+    /// </summary>
+    virtual void sync(size_t want);
+
+    /// <summary>
+    /// Add {@code n} characters to the buffer. Returns the number of characters
+    /// actually added to the buffer. If the return value is less than {@code n},
+    /// then EOF was reached before {@code n} characters could be added.
+    /// </summary>
+    virtual size_t fill(size_t n);
+
+    /// Override to provide different source of characters than
+    /// <seealso cref="#input input"/>.
+    virtual char32_t nextChar();
+    virtual void add(char32_t c);
+    size_t getBufferStartIndex() const;
+  };
+
+} // namespace antlr4