DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Implementation

Mercurial (fddffdeab170)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */


/**
 * MODULE NOTES:
 * @update  gess 4/1/98
 * 
 * The scanner is a low-level service class that knows
 * how to consume characters out of an (internal) stream.
 * This class also offers a series of utility methods
 * that most tokenizers want, such as readUntil()
 * and SkipWhitespace().
 */


#ifndef SCANNER
#define SCANNER

#include "nsCOMPtr.h"
#include "nsString.h"
#include "nsIParser.h"
#include "nsIUnicodeDecoder.h"
#include "nsScannerString.h"

class nsReadEndCondition {
public:
  const char16_t *mChars;
  char16_t mFilter;
  explicit nsReadEndCondition(const char16_t* aTerminateChars);
private:
  nsReadEndCondition(const nsReadEndCondition& aOther); // No copying
  void operator=(const nsReadEndCondition& aOther); // No assigning
};

class nsScanner {
  public:

      /**
       *  Use this constructor for the XML fragment parsing case
       */
      explicit nsScanner(const nsAString& anHTMLString);

      /**
       *  Use this constructor if you want i/o to be based on 
       *  a file (therefore a stream) or just data you provide via Append().
       */
      nsScanner(nsString& aFilename, bool aCreateStream);

      ~nsScanner();

      /**
       *  retrieve next char from internal input stream
       *  
       *  @update  gess 3/25/98
       *  @param   ch is the char to accept new value
       *  @return  error code reflecting read status
       */
      nsresult GetChar(char16_t& ch);

      /**
       *  peek ahead to consume next char from scanner's internal
       *  input buffer
       *  
       *  @update  gess 3/25/98
       *  @param   ch is the char to accept new value
       *  @return  error code reflecting read status
       */
      nsresult Peek(char16_t& ch, uint32_t aOffset=0);

      nsresult Peek(nsAString& aStr, int32_t aNumChars, int32_t aOffset = 0);

      /**
       *  Skip over chars as long as they equal given char
       *  
       *  @update  gess 3/25/98
       *  @param   char to be skipped
       *  @return  error code
       */
      nsresult SkipOver(char16_t aSkipChar);

      /**
       *  Skip whitespace on scanner input stream
       *  
       *  @update  gess 3/25/98
       *  @return  error status
       */
      nsresult SkipWhitespace(int32_t& aNewlinesSkipped);

      /**
       *  Consume characters until you run into space, a '<', a '>', or a '/'.
       *  
       *  @param   aString - receives new data from stream
       *  @return  error code
       */
      nsresult ReadTagIdentifier(nsScannerSharedSubstring& aString);

      /**
       *  Consume characters until you run into a char that's not valid in an
       *  entity name
       *  
       *  @param   aString - receives new data from stream
       *  @return  error code
       */
      nsresult ReadEntityIdentifier(nsString& aString);
      nsresult ReadNumber(nsString& aString,int32_t aBase);
      nsresult ReadWhitespace(nsScannerSharedSubstring& aString, 
                              int32_t& aNewlinesSkipped,
                              bool& aHaveCR);
      nsresult ReadWhitespace(nsScannerIterator& aStart, 
                              nsScannerIterator& aEnd,
                              int32_t& aNewlinesSkipped);

      /**
       *  Consume characters until you find the terminal char
       *  
       *  @update  gess 3/25/98
       *  @param   aString receives new data from stream
       *  @param   aTerminal contains terminating char
       *  @param   addTerminal tells us whether to append terminal to aString
       *  @return  error code
       */
      nsresult ReadUntil(nsAString& aString,
                         char16_t aTerminal,
                         bool addTerminal);

      /**
       *  Consume characters until you find one contained in given
       *  terminal set.
       *  
       *  @update  gess 3/25/98
       *  @param   aString receives new data from stream
       *  @param   aTermSet contains set of terminating chars
       *  @param   addTerminal tells us whether to append terminal to aString
       *  @return  error code
       */
      nsresult ReadUntil(nsAString& aString,
                         const nsReadEndCondition& aEndCondition, 
                         bool addTerminal);

      nsresult ReadUntil(nsScannerSharedSubstring& aString,
                         const nsReadEndCondition& aEndCondition,
                         bool addTerminal);

      nsresult ReadUntil(nsScannerIterator& aStart,
                         nsScannerIterator& aEnd,
                         const nsReadEndCondition& aEndCondition, 
                         bool addTerminal);

      /**
       *  Records current offset position in input stream. This allows us
       *  to back up to this point if the need should arise, such as when
       *  tokenization gets interrupted.
       *  
       *  @update  gess 5/12/98
       *  @param   
       *  @return  
       */
      int32_t Mark(void);

      /**
       *  Resets current offset position of input stream to marked position. 
       *  This allows us to back up to this point if the need should arise, 
       *  such as when tokenization gets interrupted.
       *  NOTE: IT IS REALLY BAD FORM TO CALL RELEASE WITHOUT CALLING MARK FIRST!
       *  
       *  @update  gess 5/12/98
       *  @param   
       *  @return  
       */
      void RewindToMark(void);


      /**
       *  
       *  
       *  @update  harishd 01/12/99
       *  @param   
       *  @return  
       */
      bool UngetReadable(const nsAString& aBuffer);

      /**
       *  
       *  
       *  @update  gess 5/13/98
       *  @param   
       *  @return  
       */
      nsresult Append(const nsAString& aBuffer);

      /**
       *  
       *  
       *  @update  gess 5/21/98
       *  @param   
       *  @return  
       */
      nsresult Append(const char* aBuffer, uint32_t aLen,
                      nsIRequest *aRequest);

      /**
       *  Call this to copy bytes out of the scanner that have not yet been consumed
       *  by the tokenization process.
       *  
       *  @update  gess 5/12/98
       *  @param   aCopyBuffer is where the scanner buffer will be copied to
       *  @return  nada
       */
      void CopyUnusedData(nsString& aCopyBuffer);

      /**
       *  Retrieve the name of the file that the scanner is reading from.
       *  In some cases, it's just a given name, because the scanner isn't
       *  really reading from a file.
       *  
       *  @update  gess 5/12/98
       *  @return  
       */
      nsString& GetFilename(void);

      static void SelfTest();

      /**
       *  Use this setter to change the scanner's unicode decoder
       *
       *  @update  ftang 3/02/99
       *  @param   aCharset a normalized (alias resolved) charset name
       *  @param   aCharsetSource- where the charset info came from
       *  @return  
       */
      nsresult SetDocumentCharset(const nsACString& aCharset, int32_t aSource);

      void BindSubstring(nsScannerSubstring& aSubstring, const nsScannerIterator& aStart, const nsScannerIterator& aEnd);
      void CurrentPosition(nsScannerIterator& aPosition);
      void EndReading(nsScannerIterator& aPosition);
      void SetPosition(nsScannerIterator& aPosition,
                       bool aTruncate = false,
                       bool aReverse = false);
      void ReplaceCharacter(nsScannerIterator& aPosition,
                            char16_t aChar);

      /**
       * Internal method used to cause the internal buffer to
       * be filled with data. 
       *
       * @update  gess4/3/98
       */
      bool      IsIncremental(void) {return mIncremental;}
      void      SetIncremental(bool anIncrValue) {mIncremental=anIncrValue;}

      /**
       * Return the position of the first non-whitespace
       * character. This is only reliable before consumers start
       * reading from this scanner.
       */
      int32_t FirstNonWhitespacePosition()
      {
        return mFirstNonWhitespacePosition;
      }

      /**
       * Override replacement character used by nsIUnicodeDecoder.
       * Default behavior is that it uses nsIUnicodeDecoder's mapping.
       *
       * @param aReplacementCharacter the replacement character
       *        XML (expat) parser uses 0xffff
       */
      void OverrideReplacementCharacter(char16_t aReplacementCharacter);

  protected:

      bool AppendToBuffer(nsScannerString::Buffer *, nsIRequest *aRequest, int32_t aErrorPos = -1);
      bool AppendToBuffer(const nsAString& aStr)
      {
        nsScannerString::Buffer* buf = nsScannerString::AllocBufferFromString(aStr);
        if (!buf)
          return false;
        AppendToBuffer(buf, nullptr);
        return true;
      }

      nsScannerString*             mSlidingBuffer;
      nsScannerIterator            mCurrentPosition; // The position we will next read from in the scanner buffer
      nsScannerIterator            mMarkPosition;    // The position last marked (we may rewind to here)
      nsScannerIterator            mEndPosition;     // The current end of the scanner buffer
      nsScannerIterator            mFirstInvalidPosition; // The position of the first invalid character that was detected
      nsString        mFilename;
      uint32_t        mCountRemaining; // The number of bytes still to be read
                                       // from the scanner buffer
      bool            mIncremental;
      bool            mHasInvalidCharacter;
      char16_t       mReplacementCharacter;
      int32_t         mFirstNonWhitespacePosition;
      int32_t         mCharsetSource;
      nsCString       mCharset;
      nsCOMPtr<nsIUnicodeDecoder> mUnicodeDecoder;

  private:
      nsScanner &operator =(const nsScanner &); // Not implemented.
};

#endif