edu.stanford.nlp.trees.tregex.tsurgeon.TokenMgrError Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation

Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.

There is a newer version: 4.5.7

Show newest version

/* Generated By:JavaCC: Do not edit this line. TokenMgrError.java Version 6.0 */
/* JavaCCOptions: */
package edu.stanford.nlp.trees.tregex.tsurgeon;

/** Token Manager Error. */
class TokenMgrError extends Error
{

  /**
   * The version identifier for this Serializable class.
   * Increment only if the serialized form of the
   * class changes.
   */
  private static final long serialVersionUID = 1L;

  /*
   * Ordinals for various reasons why an Error of this type can be thrown.
   */

  /**
   * Lexical error occurred.
   */
  static final int LEXICAL_ERROR = 0;

  /**
   * An attempt was made to create a second instance of a static token manager.
   */
  static final int STATIC_LEXER_ERROR = 1;

  /**
   * Tried to change to an invalid lexical state.
   */
  static final int INVALID_LEXICAL_STATE = 2;

  /**
   * Detected (and bailed out of) an infinite loop in the token manager.
   */
  static final int LOOP_DETECTED = 3;

  /**
   * Indicates the reason why the exception is thrown. It will have
   * one of the above 4 values.
   */
  int errorCode;

  /**
   * Replaces unprintable characters by their escaped (or unicode escaped)
   * equivalents in the given string
   */
  protected static final String addEscapes(String str) {
    StringBuffer retval = new StringBuffer();
    char ch;
    for (int i = 0; i < str.length(); i++) {
      switch (str.charAt(i))
      {
        case 0 :
          continue;
        case '\b':
          retval.append("\\b");
          continue;
        case '\t':
          retval.append("\\t");
          continue;
        case '\n':
          retval.append("\\n");
          continue;
        case '\f':
          retval.append("\\f");
          continue;
        case '\r':
          retval.append("\\r");
          continue;
        case '\"':
          retval.append("\\\"");
          continue;
        case '\'':
          retval.append("\\\'");
          continue;
        case '\\':
          retval.append("\\\\");
          continue;
        default:
          if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) {
            String s = "0000" + Integer.toString(ch, 16);
            retval.append("\\u" + s.substring(s.length() - 4, s.length()));
          } else {
            retval.append(ch);
          }
          continue;
      }
    }
    return retval.toString();
  }

  /**
   * Returns a detailed message for the Error when it is thrown by the
   * token manager to indicate a lexical error.
   * Parameters :
   *    EOFSeen     : indicates if EOF caused the lexical error
   *    curLexState : lexical state in which this error occurred
   *    errorLine   : line number when the error occurred
   *    errorColumn : column number when the error occurred
   *    errorAfter  : prefix that was seen before this error occurred
   *    curchar     : the offending character
   * Note: You can customize the lexical error message by modifying this method.
   */
  protected static String LexicalError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar) {
    return("Lexical error at line " +
          errorLine + ", column " +
          errorColumn + ".  Encountered: " +
          (EOFSeen ? " " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" + (int)curChar + "), ") +
          "after : \"" + addEscapes(errorAfter) + "\"");
  }

  /**
   * You can also modify the body of this method to customize your error messages.
   * For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not
   * of end-users concern, so you can return something like :
   *
   *     "Internal Error : Please file a bug report .... "
   *
   * from this method for such cases in the release version of your parser.
   */
  public String getMessage() {
    return super.getMessage();
  }

  /*
   * Constructors of various flavors follow.
   */

  /** No arg constructor. */
  public TokenMgrError() {
  }

  /** Constructor with message and reason. */
  public TokenMgrError(String message, int reason) {
    super(message);
    errorCode = reason;
  }

  /** Full Constructor. */
  public TokenMgrError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar, int reason) {
    this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason);
  }
}
/* JavaCC - OriginalChecksum=eae672316ea72765d1e1aceea1e1b495 (do not edit this line) */