Revision control

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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
/* -*- 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/. */

/**
 * Lexical analyzer for XPath expressions
 */

#include "txExprLexer.h"
#include "nsGkAtoms.h"
#include "nsString.h"
#include "nsError.h"
#include "txXMLUtils.h"

/**
 * Creates a new ExprLexer
 */
txExprLexer::txExprLexer()
  : mCurrentItem(nullptr),
    mFirstItem(nullptr),
    mLastItem(nullptr),
    mTokenCount(0)
{
}

/**
 * Destroys this instance of an txExprLexer
 */
txExprLexer::~txExprLexer()
{
  //-- delete tokens
  Token* tok = mFirstItem;
  while (tok) {
    Token* temp = tok->mNext;
    delete tok;
    tok = temp;
  }
  mCurrentItem = nullptr;
}

Token*
txExprLexer::nextToken()
{
  if (!mCurrentItem) {
    NS_NOTREACHED("nextToken called on uninitialized lexer");
    return nullptr;
  }

  if (mCurrentItem->mType == Token::END) {
    // Do not progress beyond the end token
    return mCurrentItem;
  }

  Token* token = mCurrentItem;
  mCurrentItem = mCurrentItem->mNext;
  return token;
}

void
txExprLexer::addToken(Token* aToken)
{
  if (mLastItem) {
    mLastItem->mNext = aToken;
  }
  if (!mFirstItem) {
    mFirstItem = aToken;
    mCurrentItem = aToken;
  }
  mLastItem = aToken;
  ++mTokenCount;
}

/**
 * Returns true if the following Token should be an operator.
 * This is a helper for the first bullet of [XPath 3.7]
 *  Lexical Structure
 */
bool
txExprLexer::nextIsOperatorToken(Token* aToken)
{
  if (!aToken || aToken->mType == Token::NULL_TOKEN) {
    return false;
  }
  /* This relies on the tokens having the right order in txExprLexer.h */
  return aToken->mType < Token::COMMA ||
    aToken->mType > Token::UNION_OP;

}

/**
 * Parses the given string into a sequence of Tokens
 */
nsresult
txExprLexer::parse(const nsAString& aPattern)
{
  iterator start, end;
  start = aPattern.BeginReading(mPosition);
  aPattern.EndReading(end);

  //-- initialize previous token, this will automatically get
  //-- deleted when it goes out of scope
  Token nullToken(nullptr, nullptr, Token::NULL_TOKEN);

  Token::Type defType;
  Token* newToken = nullptr;
  Token* prevToken = &nullToken;
  bool isToken;

  while (mPosition < end) {

    defType = Token::CNAME;
    isToken = true;

    if (*mPosition == DOLLAR_SIGN) {
      if (++mPosition == end || !XMLUtils::isLetter(*mPosition)) {
        return NS_ERROR_XPATH_INVALID_VAR_NAME;
      }
      defType = Token::VAR_REFERENCE;
    }
    // just reuse the QName parsing, which will use defType
    // the token to construct

    if (XMLUtils::isLetter(*mPosition)) {
      // NCName, can get QName or OperatorName;
      //  FunctionName, NodeName, and AxisSpecifier may want whitespace,
      //  and are dealt with below
      start = mPosition;
      while (++mPosition < end && XMLUtils::isNCNameChar(*mPosition)) {
        /* just go */
      }
      if (mPosition < end && *mPosition == COLON) {
        // try QName or wildcard, might need to step back for axis
        if (++mPosition == end) {
          return NS_ERROR_XPATH_UNEXPECTED_END;
        }
        if (XMLUtils::isLetter(*mPosition)) {
          while (++mPosition < end && XMLUtils::isNCNameChar(*mPosition)) {
            /* just go */
          }
        }
        else if (*mPosition == '*' && defType != Token::VAR_REFERENCE) {
          // eat wildcard for NameTest, bail for var ref at COLON
          ++mPosition;
        }
        else {
          --mPosition; // step back
        }
      }
      if (nextIsOperatorToken(prevToken)) {
        nsDependentSubstring op(Substring(start, mPosition));
        if (nsGkAtoms::_and->Equals(op)) {
          defType = Token::AND_OP;
        }
        else if (nsGkAtoms::_or->Equals(op)) {
          defType = Token::OR_OP;
        }
        else if (nsGkAtoms::mod->Equals(op)) {
          defType = Token::MODULUS_OP;
        }
        else if (nsGkAtoms::div->Equals(op)) {
          defType = Token::DIVIDE_OP;
        }
        else {
          // XXX QUESTION: spec is not too precise
          // badops is sure an error, but is bad:ops, too? We say yes!
          return NS_ERROR_XPATH_OPERATOR_EXPECTED;
        }
      }
      newToken = new Token(start, mPosition, defType);
    }
    else if (isXPathDigit(*mPosition)) {
      start = mPosition;
      while (++mPosition < end && isXPathDigit(*mPosition)) {
        /* just go */
      }
      if (mPosition < end && *mPosition == '.') {
        while (++mPosition < end && isXPathDigit(*mPosition)) {
          /* just go */
        }
      }
      newToken = new Token(start, mPosition, Token::NUMBER);
    }
    else {
      switch (*mPosition) {
        //-- ignore whitespace
      case SPACE:
      case TX_TAB:
      case TX_CR:
      case TX_LF:
        ++mPosition;
        isToken = false;
        break;
      case S_QUOTE :
      case D_QUOTE :
        start = mPosition;
        while (++mPosition < end && *mPosition != *start) {
          // eat literal
        }
        if (mPosition == end) {
          mPosition = start;
          return NS_ERROR_XPATH_UNCLOSED_LITERAL;
        }
        newToken = new Token(start + 1, mPosition, Token::LITERAL);
        ++mPosition;
        break;
      case PERIOD:
        // period can be .., .(DIGITS)+ or ., check next
        if (++mPosition == end) {
          newToken = new Token(mPosition - 1, Token::SELF_NODE);
        }
        else if (isXPathDigit(*mPosition)) {
          start = mPosition - 1;
          while (++mPosition < end && isXPathDigit(*mPosition)) {
            /* just go */
          }
          newToken = new Token(start, mPosition, Token::NUMBER);
        }
        else if (*mPosition == PERIOD) {
          ++mPosition;
          newToken = new Token(mPosition - 2, mPosition, Token::PARENT_NODE);
        }
        else {
          newToken = new Token(mPosition - 1, Token::SELF_NODE);
        }
        break;
      case COLON: // QNames are dealt above, must be axis ident
        if (++mPosition >= end || *mPosition != COLON ||
            prevToken->mType != Token::CNAME) {
          return NS_ERROR_XPATH_BAD_COLON;
        }
        prevToken->mType = Token::AXIS_IDENTIFIER;
        ++mPosition;
        isToken = false;
        break;
      case FORWARD_SLASH :
        if (++mPosition < end && *mPosition == FORWARD_SLASH) {
          ++mPosition;
          newToken = new Token(mPosition - 2, mPosition, Token::ANCESTOR_OP);
        }
        else {
          newToken = new Token(mPosition - 1, Token::PARENT_OP);
        }
        break;
      case BANG : // can only be !=
        if (++mPosition < end && *mPosition == EQUAL) {
          ++mPosition;
          newToken = new Token(mPosition - 2, mPosition, Token::NOT_EQUAL_OP);
          break;
        }
        // Error ! is not not()
        return NS_ERROR_XPATH_BAD_BANG;
      case EQUAL:
        newToken = new Token(mPosition, Token::EQUAL_OP);
        ++mPosition;
        break;
      case L_ANGLE:
        if (++mPosition == end) {
          return NS_ERROR_XPATH_UNEXPECTED_END;
        }
        if (*mPosition == EQUAL) {
          ++mPosition;
          newToken = new Token(mPosition - 2, mPosition,
                               Token::LESS_OR_EQUAL_OP);
        }
        else {
          newToken = new Token(mPosition - 1, Token::LESS_THAN_OP);
        }
        break;
      case R_ANGLE:
        if (++mPosition == end) {
          return NS_ERROR_XPATH_UNEXPECTED_END;
        }
        if (*mPosition == EQUAL) {
          ++mPosition;
          newToken = new Token(mPosition - 2, mPosition,
                               Token::GREATER_OR_EQUAL_OP);
        }
        else {
          newToken = new Token(mPosition - 1, Token::GREATER_THAN_OP);
        }
        break;
      case HYPHEN :
        newToken = new Token(mPosition, Token::SUBTRACTION_OP);
        ++mPosition;
        break;
      case ASTERISK:
        if (nextIsOperatorToken(prevToken)) {
          newToken = new Token(mPosition, Token::MULTIPLY_OP);
        }
        else {
          newToken = new Token(mPosition, Token::CNAME);
        }
        ++mPosition;
        break;
      case L_PAREN:
        if (prevToken->mType == Token::CNAME) {
          const nsDependentSubstring& val = prevToken->Value();
          if (val.EqualsLiteral("comment")) {
            prevToken->mType = Token::COMMENT_AND_PAREN;
          }
          else if (val.EqualsLiteral("node")) {
            prevToken->mType = Token::NODE_AND_PAREN;
          }
          else if (val.EqualsLiteral("processing-instruction")) {
            prevToken->mType = Token::PROC_INST_AND_PAREN;
          }
          else if (val.EqualsLiteral("text")) {
            prevToken->mType = Token::TEXT_AND_PAREN;
          }
          else {
            prevToken->mType = Token::FUNCTION_NAME_AND_PAREN;
          }
          isToken = false;
        }
        else {
          newToken = new Token(mPosition, Token::L_PAREN);
        }
        ++mPosition;
        break;
      case R_PAREN:
        newToken = new Token(mPosition, Token::R_PAREN);
        ++mPosition;
        break;
      case L_BRACKET:
        newToken = new Token(mPosition, Token::L_BRACKET);
        ++mPosition;
        break;
      case R_BRACKET:
        newToken = new Token(mPosition, Token::R_BRACKET);
        ++mPosition;
        break;
      case COMMA:
        newToken = new Token(mPosition, Token::COMMA);
        ++mPosition;
        break;
      case AT_SIGN :
        newToken = new Token(mPosition, Token::AT_SIGN);
        ++mPosition;
        break;
      case PLUS:
        newToken = new Token(mPosition, Token::ADDITION_OP);
        ++mPosition;
        break;
      case VERT_BAR:
        newToken = new Token(mPosition, Token::UNION_OP);
        ++mPosition;
        break;
      default:
        // Error, don't grok character :-(
        return NS_ERROR_XPATH_ILLEGAL_CHAR;
      }
    }
    if (isToken) {
      NS_ENSURE_TRUE(newToken, NS_ERROR_OUT_OF_MEMORY);
      NS_ENSURE_TRUE(newToken != mLastItem, NS_ERROR_FAILURE);
      prevToken = newToken;
      addToken(newToken);
    }
  }

  // add a endToken to the list
  newToken = new Token(end, end, Token::END);
  addToken(newToken);

  return NS_OK;
}