TextTokenizer.cs 13.7 KB
Newer Older
1
#region Copyright notice and license
Jon Skeet's avatar
Jon Skeet committed
2 3 4 5
// Protocol Buffers - Google's data interchange format
// Copyright 2008 Google Inc.  All rights reserved.
// http://github.com/jskeet/dotnet-protobufs/
// Original C++/Java/Python code:
Jon Skeet's avatar
Jon Skeet committed
6 7
// http://code.google.com/p/protobuf/
//
Jon Skeet's avatar
Jon Skeet committed
8 9 10
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
Jon Skeet's avatar
Jon Skeet committed
11
//
Jon Skeet's avatar
Jon Skeet committed
12 13 14 15 16 17 18 19 20
//     * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//     * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
Jon Skeet's avatar
Jon Skeet committed
21
//
Jon Skeet's avatar
Jon Skeet committed
22 23 24 25 26 27 28 29 30 31 32
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 34
#endregion

Jon Skeet's avatar
Jon Skeet committed
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
using System;
using System.Globalization;
using System.Text.RegularExpressions;

namespace Google.ProtocolBuffers {
  /// <summary>
  /// Represents a stream of tokens parsed from a string.
  /// </summary>
  internal sealed class TextTokenizer {
    private readonly string text;
    private string currentToken;

    /// <summary>
    /// The character index within the text to perform the next regex match at.
    /// </summary>
    private int matchPos = 0;

    /// <summary>
    /// The character index within the text at which the current token begins.
    /// </summary>
    private int pos = 0;

    /// <summary>
    /// The line number of the current token.
    /// </summary>
    private int line = 0;
    /// <summary>
    /// The column number of the current token.
    /// </summary>
    private int column = 0;

    /// <summary>
    /// The line number of the previous token.
    /// </summary>
    private int previousLine = 0;
    /// <summary>
    /// The column number of the previous token.
    /// </summary>
    private int previousColumn = 0;

75
    // Note: atomic groups used to mimic possessive quantifiers in Java in both of these regexes
76 77
    internal static readonly Regex WhitespaceAndCommentPattern = new Regex("\\G(?>(\\s|(#.*$))+)",
        SilverlightCompatibility.CompiledRegexWhereAvailable | RegexOptions.Multiline);
Jon Skeet's avatar
Jon Skeet committed
78
    private static readonly Regex TokenPattern = new Regex(
79 80 81 82
      "\\G[a-zA-Z_](?>[0-9a-zA-Z_+-]*)|" +              // an identifier
      "\\G[0-9+-](?>[0-9a-zA-Z_.+-]*)|" +                  // a number
      "\\G\"(?>([^\"\\\n\\\\]|\\\\.)*)(\"|\\\\?$)|" +    // a double-quoted string
      "\\G\'(?>([^\"\\\n\\\\]|\\\\.)*)(\'|\\\\?$)",      // a single-quoted string
83
      SilverlightCompatibility.CompiledRegexWhereAvailable | RegexOptions.Multiline);
Jon Skeet's avatar
Jon Skeet committed
84

85 86 87 88 89 90
    private static readonly Regex DoubleInfinity = new Regex("^-?inf(inity)?$",
      SilverlightCompatibility.CompiledRegexWhereAvailable | RegexOptions.IgnoreCase);
    private static readonly Regex FloatInfinity = new Regex("^-?inf(inity)?f?$",
      SilverlightCompatibility.CompiledRegexWhereAvailable | RegexOptions.IgnoreCase);
    private static readonly Regex FloatNan = new Regex("^nanf?$",
      SilverlightCompatibility.CompiledRegexWhereAvailable | RegexOptions.IgnoreCase);
Jon Skeet's avatar
Jon Skeet committed
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412

    /** Construct a tokenizer that parses tokens from the given text. */
    public TextTokenizer(string text) {
      this.text = text;
      SkipWhitespace();
      NextToken();
    }

    /// <summary>
    /// Are we at the end of the input?
    /// </summary>
    public bool AtEnd {
      get { return currentToken.Length == 0; }
    }

    /// <summary>
    /// Advances to the next token.
    /// </summary>
    public void NextToken() {
      previousLine = line;
      previousColumn = column;

      // Advance the line counter to the current position.
      while (pos < matchPos) {
        if (text[pos] == '\n') {
          ++line;
          column = 0;
        } else {
          ++column;
        }
        ++pos;
      }

      // Match the next token.
      if (matchPos == text.Length) {
        // EOF
        currentToken = "";
      } else {
        Match match = TokenPattern.Match(text, matchPos);
        if (match.Success) {
          currentToken = match.Value;
          matchPos += match.Length;
        } else {
          // Take one character.
          currentToken = text[matchPos].ToString();
          matchPos++;
        }

        SkipWhitespace();
      }
    }

    /// <summary>
    /// Skip over any whitespace so that matchPos starts at the next token.
    /// </summary>
    private void SkipWhitespace() {
      Match match = WhitespaceAndCommentPattern.Match(text, matchPos);
      if (match.Success) {
        matchPos += match.Length;
      }
    }

    /// <summary>
    /// If the next token exactly matches the given token, consume it and return
    /// true. Otherwise, return false without doing anything.
    /// </summary>
    public bool TryConsume(string token) {
      if (currentToken == token) {
        NextToken();
        return true;
      }
      return false;
    }

    /*
     * If the next token exactly matches {@code token}, consume it.  Otherwise,
     * throw a {@link ParseException}.
     */
    /// <summary>
    /// If the next token exactly matches the specified one, consume it.
    /// Otherwise, throw a FormatException.
    /// </summary>
    /// <param name="token"></param>
    public void Consume(string token) {
      if (!TryConsume(token)) {
        throw CreateFormatException("Expected \"" + token + "\".");
      }
    }

    /// <summary>
    /// Returns true if the next token is an integer, but does not consume it.
    /// </summary>
    public bool LookingAtInteger() {
      if (currentToken.Length == 0) {
        return false;
      }

      char c = currentToken[0];
      return ('0' <= c && c <= '9') || c == '-' || c == '+';
    }

    /// <summary>
    /// If the next token is an identifier, consume it and return its value.
    /// Otherwise, throw a FormatException.
    /// </summary>
    public string ConsumeIdentifier() {
      foreach (char c in currentToken) {
        if (('a' <= c && c <= 'z') ||
            ('A' <= c && c <= 'Z') ||
            ('0' <= c && c <= '9') ||
            (c == '_') || (c == '.')) {
          // OK
        } else {
          throw CreateFormatException("Expected identifier.");
        }
      }

      string result = currentToken;
      NextToken();
      return result;
    }

    /// <summary>
    /// If the next token is a 32-bit signed integer, consume it and return its 
    /// value. Otherwise, throw a FormatException.
    /// </summary>
    public int ConsumeInt32()  {
      try {
        int result = TextFormat.ParseInt32(currentToken);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateIntegerParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a 32-bit unsigned integer, consume it and return its
    /// value. Otherwise, throw a FormatException.
    /// </summary>
    public uint ConsumeUInt32() {
      try {
        uint result = TextFormat.ParseUInt32(currentToken);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateIntegerParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a 64-bit signed integer, consume it and return its
    /// value. Otherwise, throw a FormatException.
    /// </summary>
    public long ConsumeInt64() {
      try {
        long result = TextFormat.ParseInt64(currentToken);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateIntegerParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a 64-bit unsigned integer, consume it and return its
    /// value. Otherwise, throw a FormatException.
    /// </summary>
    public ulong ConsumeUInt64() {
      try {
        ulong result = TextFormat.ParseUInt64(currentToken);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateIntegerParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a double, consume it and return its value.
    /// Otherwise, throw a FormatException.
    /// </summary>
    public double ConsumeDouble() {
      // We need to parse infinity and nan separately because
      // double.Parse() does not accept "inf", "infinity", or "nan".
      if (DoubleInfinity.IsMatch(currentToken)) {
        bool negative = currentToken.StartsWith("-");
        NextToken();
        return negative ? double.NegativeInfinity : double.PositiveInfinity;
      }
      if (currentToken.Equals("nan", StringComparison.InvariantCultureIgnoreCase)) {
        NextToken();
        return Double.NaN;
      }

      try {
        double result = double.Parse(currentToken, CultureInfo.InvariantCulture);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateFloatParseException(e);
      } catch (OverflowException e) {
        throw CreateFloatParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a float, consume it and return its value.
    /// Otherwise, throw a FormatException.
    /// </summary>
    public float ConsumeFloat() {
      // We need to parse infinity and nan separately because
      // Float.parseFloat() does not accept "inf", "infinity", or "nan".
      if (FloatInfinity.IsMatch(currentToken)) {
        bool negative = currentToken.StartsWith("-");
        NextToken();
        return negative ? float.NegativeInfinity : float.PositiveInfinity;
      }
      if (FloatNan.IsMatch(currentToken)) {
        NextToken();
        return float.NaN;
      }

      if (currentToken.EndsWith("f")) {
        currentToken = currentToken.TrimEnd('f');
      }

      try {
        float result = float.Parse(currentToken, CultureInfo.InvariantCulture);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateFloatParseException(e);
      } catch (OverflowException e) {
        throw CreateFloatParseException(e);
      }
    }

    /// <summary>
    /// If the next token is a Boolean, consume it and return its value.
    /// Otherwise, throw a FormatException.    
    /// </summary>
    public bool ConsumeBoolean() {
      if (currentToken == "true") {
        NextToken();
        return true;
      } 
      if (currentToken == "false") {
        NextToken();
        return false;
      }
      throw CreateFormatException("Expected \"true\" or \"false\".");
    }

    /// <summary>
    /// If the next token is a string, consume it and return its (unescaped) value.
    /// Otherwise, throw a FormatException.
    /// </summary>
    public string ConsumeString() {
      return ConsumeByteString().ToStringUtf8();
    }

    /// <summary>
    /// If the next token is a string, consume it, unescape it as a
    /// ByteString and return it. Otherwise, throw a FormatException.
    /// </summary>
    public ByteString ConsumeByteString() {
      char quote = currentToken.Length > 0 ? currentToken[0] : '\0';
      if (quote != '\"' && quote != '\'') {
        throw CreateFormatException("Expected string.");
      }

      if (currentToken.Length < 2 ||
          currentToken[currentToken.Length-1] != quote) {
        throw CreateFormatException("String missing ending quote.");
      }

      try {
        string escaped = currentToken.Substring(1, currentToken.Length - 2);
        ByteString result = TextFormat.UnescapeBytes(escaped);
        NextToken();
        return result;
      } catch (FormatException e) {
        throw CreateFormatException(e.Message);
      }
    }

    /// <summary>
    /// Returns a format exception with the current line and column numbers
    /// in the description, suitable for throwing.
    /// </summary>
    public FormatException CreateFormatException(string description) {
      // Note:  People generally prefer one-based line and column numbers.
      return new FormatException((line + 1) + ":" + (column + 1) + ": " + description);
    }

    /// <summary>
    /// Returns a format exception with the line and column numbers of the
    /// previous token in the description, suitable for throwing.
    /// </summary>
    public FormatException CreateFormatExceptionPreviousToken(string description) {
      // Note:  People generally prefer one-based line and column numbers.
      return new FormatException((previousLine + 1) + ":" + (previousColumn + 1) + ": " + description);
    }

    /// <summary>
    /// Constructs an appropriate FormatException for the given existing exception
    /// when trying to parse an integer.
    /// </summary>
    private FormatException CreateIntegerParseException(FormatException e) {
      return CreateFormatException("Couldn't parse integer: " + e.Message);
    }

    /// <summary>
    /// Constructs an appropriate FormatException for the given existing exception
    /// when trying to parse a float or double.
    /// </summary>
    private FormatException CreateFloatParseException(Exception e) {
      return CreateFormatException("Couldn't parse number: " + e.Message);
    }
  }
}