Class SimpleCharStream

java.lang.Object
it.unimi.dsi.law.warc.filters.parser.SimpleCharStream

public class SimpleCharStream
extends Object
An implementation of interface CharStream, where the stream is assumed to contain only ASCII characters (without unicode processing).
  • Field Details

    • staticFlag

      public static final boolean staticFlag
      Whether parser is static.
      See Also:
      Constant Field Values
    • bufpos

      public int bufpos
      Position in buffer.
    • bufline

      protected int[] bufline
    • bufcolumn

      protected int[] bufcolumn
    • column

      protected int column
    • line

      protected int line
    • prevCharIsCR

      protected boolean prevCharIsCR
    • prevCharIsLF

      protected boolean prevCharIsLF
    • inputStream

      protected Reader inputStream
    • buffer

      protected char[] buffer
    • maxNextCharInd

      protected int maxNextCharInd
    • inBuf

      protected int inBuf
    • tabSize

      protected int tabSize
    • trackLineColumn

      protected boolean trackLineColumn
  • Constructor Details

  • Method Details

    • setTabSize

      public void setTabSize​(int i)
    • getTabSize

      public int getTabSize()
    • ExpandBuff

      protected void ExpandBuff​(boolean wrapAround)
    • FillBuff

      protected void FillBuff() throws IOException
      Throws:
      IOException
    • BeginToken

      public char BeginToken() throws IOException
      Start.
      Throws:
      IOException
    • UpdateLineColumn

      protected void UpdateLineColumn​(char c)
    • readChar

      public char readChar() throws IOException
      Read a character.
      Throws:
      IOException
    • getColumn

      @Deprecated public int getColumn()
      Deprecated.
    • getLine

      @Deprecated public int getLine()
      Deprecated.
    • getEndColumn

      public int getEndColumn()
      Get token end column number.
    • getEndLine

      public int getEndLine()
      Get token end line number.
    • getBeginColumn

      public int getBeginColumn()
      Get token beginning column number.
    • getBeginLine

      public int getBeginLine()
      Get token beginning line number.
    • backup

      public void backup​(int amount)
      Backup a number of characters.
    • ReInit

      public void ReInit​(Reader dstream, int startline, int startcolumn, int buffersize)
      Reinitialise.
    • ReInit

      public void ReInit​(Reader dstream, int startline, int startcolumn)
      Reinitialise.
    • ReInit

      public void ReInit​(Reader dstream)
      Reinitialise.
    • ReInit

      public void ReInit​(InputStream dstream, String encoding, int startline, int startcolumn, int buffersize) throws UnsupportedEncodingException
      Reinitialise.
      Throws:
      UnsupportedEncodingException
    • ReInit

      public void ReInit​(InputStream dstream, int startline, int startcolumn, int buffersize)
      Reinitialise.
    • ReInit

      public void ReInit​(InputStream dstream, String encoding) throws UnsupportedEncodingException
      Reinitialise.
      Throws:
      UnsupportedEncodingException
    • ReInit

      public void ReInit​(InputStream dstream)
      Reinitialise.
    • ReInit

      public void ReInit​(InputStream dstream, String encoding, int startline, int startcolumn) throws UnsupportedEncodingException
      Reinitialise.
      Throws:
      UnsupportedEncodingException
    • ReInit

      public void ReInit​(InputStream dstream, int startline, int startcolumn)
      Reinitialise.
    • GetImage

      public String GetImage()
      Get token literal value.
    • GetSuffix

      public char[] GetSuffix​(int len)
      Get the suffix.
    • Done

      public void Done()
      Reset buffer when finished.
    • adjustBeginLineColumn

      public void adjustBeginLineColumn​(int newLine, int newCol)
      Method to adjust line and column numbers for the start of a token.