From: William James <w_a_x_man@...>
Date: 2005-10-30T13:07:07+09:00
Subject: Faster CSV parsing

## Read, parse, and create csv records.

# The program conforms to the csv specification at this site:
# http://www.creativyst.com/Doc/Articles/CSV/CSV01.htm
# The only extra is that you can change the field-separator.
# For a field-separator other than a comma, for example
# a semicolon:
#   Csv.fs=";"
#
# After a record has been read and parsed,
# Csv.string contains the record in raw string format.
#


class Csv

  def Csv.unescape( array )
    array.map{|x| x.gsub( /""/, '"' ) }
  end


  @@fs = ","

  # Set regexp for parse.
  # @@fs is the field-separator, which must be
  # a single character.
  def Csv.make_regexp
    fs = @@fs
    if "^" == fs
      fs = "\\^"
    end

    @@regexp =
    ## Assumes embedded quotes are escaped as "".
      %r{
           \G   ## Anchor at end of previous match.
           [ \t]*   ## Leading spaces or tabs are discarded.
           (?:
               ##  For a field in quotes.
               " (  [^"]*  (?:  "" [^"]*  )*  ) "  |
               ##  For a field not in quotes.
                 (  [^"\n#{fs}]*?  )
           )
           [ \t]*
           [#{fs}]
        }mx



    ## When get_rec finds after reading a line that the record isn't
    ## complete, this regexp will be used to decide whether to read
    ## another line or to raise an exception.
    @@reading_regexp =
      %r{
          \A      # Anchor at beginning of string.
          (?:
             [ \t]*
             (?:
                 "  [^"]*  (?:  "" [^"]*  )*  "  |
                    [^"\n#{fs}]*?
             )
             [ \t]*
             [#{fs}]
          )*
          [ \t]*
          "  [^"]*  (?:  "" [^"]*  )*
          \Z      # Anchor at end of string.
        }mx

  end # def make_regexp

  Csv.make_regexp

  def Csv.parse( s )
    ary = (s + @@fs).scan( @@regexp )
    raise "\nBad csv record:\n#{s}\n" if $' != ""
    Csv.unescape( ary.flatten.compact )
  end

  @@string = nil

  def Csv.get_rec( file )
    return nil  if file.eof?
    @@string = ""
    begin
      if @@string.size>0
        raise "\nBad record:\n#{@@string}\n"  if
          @@string !~ @@reading_regexp
        raise "\nPremature end of csv file."  if file.eof?
      end
      @@string += file.gets
    end  until @@string.count( '"' ) % 2 == 0
    @@string.chomp!
    Csv.parse( @@string )
  end

  def Csv.string
    @@string
  end

  def Csv.fs=( s )
    raise "\nCsv.fs must be a single character.\n" if s.size != 1
    @@fs = s
    Csv.make_regexp
  end

  def Csv.fs
    @@fs
  end

  def Csv.to_csv( array )
    s = ''
    array.map { |item|
      str = item.to_s
      # Quote the string if it contains the field-separator or
      # a " or a newline or a carriage-return, or if it has leading or
      # trailing whitespace.
      if str.index(@@fs) or /^\s|["\r\n]|\s$/.match(str)
        str = '"' + str.gsub( /"/, '""' ) + '"'
      end
      str
    }.join(@@fs)
  end

end # class Csv