CSV类

CSV.foreach("path/to/file.csv") do |row|
  # use row here...
end

arr_of_arrs = CSV.read("path/to/file.csv")

CSV.parse("CSV,data,String") do |row|
  # use row here...
end

arr_of_arrs = CSV.parse("CSV,data,String")

CSV.open("path/to/file.csv", "wb") do |csv|
  csv << ["row", "of", "CSV", "data"]
  csv << ["another", "row"]
  # ...
end

csv_string = CSV.generate do |csv|
  csv << ["row", "of", "CSV", "data"]
  csv << ["another", "row"]
  # ...
end

csv_string = ["CSV", "data"].to_csv   # to CSV
csv_array  = "CSV,String".parse_csv   # from CSV

CSV             { |csv_out| csv_out << %w{my data here} }  # to $stdout
CSV(csv = "")   { |csv_str| csv_str << %w{my data here} }  # to a String
CSV($stderr)    { |csv_err| csv_err << %w{my data here} }  # to $stderr
CSV($stdin)     { |csv_in|  csv_in.each { |row| p row } }  # from $stdin

csv = CSV.new(io, options)
# ... read (with gets() or each()) from and write (with <<) to csv here ...

# File lib/csv.rb, line 1102
def self.filter(*args)
  # parse options for input, output, or both
  in_options, out_options = Hash.new, {row_sep: $INPUT_RECORD_SEPARATOR}
  if args.last.is_a? Hash
    args.pop.each do |key, value|
      case key.to_s
      when /\Ain(?:put)?_(.+)\Z/
        in_options[$1.to_sym] = value
      when /\Aout(?:put)?_(.+)\Z/
        out_options[$1.to_sym] = value
      else
        in_options[key]  = value
        out_options[key] = value
      end
    end
  end
  # build input and output wrappers
  input  = new(args.shift || ARGF,    in_options)
  output = new(args.shift || $stdout, out_options)

  # read, yield, write
  input.each do |row|
    yield row
    output << row
  end
end

# File lib/csv.rb, line 1143
def self.foreach(path, options = Hash.new, &block)
  return to_enum(__method__, path, options) unless block
  open(path, options) do |csv|
    csv.each(&block)
  end
end

# File lib/csv.rb, line 1168
def self.generate(*args)
  # add a default empty String, if none was given
  if args.first.is_a? String
    io = StringIO.new(args.shift)
    io.seek(0, IO::SEEK_END)
    args.unshift(io)
  else
    encoding = args[-1][:encoding] if args.last.is_a?(Hash)
    str      = String.new
    str.force_encoding(encoding) if encoding
    args.unshift(str)
  end
  csv = new(*args)  # wrap
  yield csv         # yield for appending
  csv.string        # return final String
end

# File lib/csv.rb, line 1198
def self.generate_line(row, options = Hash.new)
  options  = {row_sep: $INPUT_RECORD_SEPARATOR}.merge(options)
  encoding = options.delete(:encoding)
  str      = String.new
  if encoding
    str.force_encoding(encoding)
  elsif field = row.find { |f| not f.nil? }
    str.force_encoding(String(field).encoding)
  end
  (new(str, options) << row).string
end

# File lib/csv.rb, line 1062
def self.instance(data = $stdout, options = Hash.new)
  # create a _signature_ for this method call, data object and options
  sig = [data.object_id] +
        options.values_at(*DEFAULT_OPTIONS.keys.sort_by { |sym| sym.to_s })

  # fetch or create the instance for this signature
  @@instances ||= Hash.new
  instance    =   (@@instances[sig] ||= new(data, options))

  if block_given?
    yield instance  # run block, if given, returning result
  else
    instance        # or return the instance
  end
end

# File lib/csv.rb, line 1527
def initialize(data, options = Hash.new)
  if data.nil?
    raise ArgumentError.new("Cannot parse nil as CSV")
  end

  # build the options for this read/write
  options = DEFAULT_OPTIONS.merge(options)

  # create the IO object we will read from
  @io       = data.is_a?(String) ? StringIO.new(data) : data
  # honor the IO encoding if we can, otherwise default to ASCII-8BIT
  @encoding = raw_encoding(nil) ||
              ( if encoding = options.delete(:internal_encoding)
                  case encoding
                  when Encoding; encoding
                  else Encoding.find(encoding)
                  end
                end ) ||
              ( case encoding = options.delete(:encoding)
                when Encoding; encoding
                when /\A[^:]+/; Encoding.find($&)
                end ) ||
              Encoding.default_internal || Encoding.default_external
  #
  # prepare for building safe regular expressions in the target encoding,
  # if we can transcode the needed characters
  #
  @re_esc   =   "\\".encode(@encoding).freeze rescue ""
  @re_chars =   /#{%"[-\\]\\[\\.^$?*+{}()|# \r\n\t\f\v]".encode(@encoding)}/

  init_separators(options)
  init_parsers(options)
  init_converters(options)
  init_headers(options)
  init_comments(options)

  @force_encoding = !!(encoding || options.delete(:encoding))
  options.delete(:internal_encoding)
  options.delete(:external_encoding)
  unless options.empty?
    raise ArgumentError, "Unknown options:  #{options.keys.join(', ')}."
  end

  # track our own lineno since IO gets confused about line-ends is CSV fields
  @lineno = 0
end

# File lib/csv.rb, line 1273
def self.open(*args)
  # find the +options+ Hash
  options = if args.last.is_a? Hash then args.pop else Hash.new end
  # wrap a File opened with the remaining +args+ with no newline
  # decorator
  file_opts = {universal_newline: false}.merge(options)
  begin
    f = File.open(*args, file_opts)
  rescue ArgumentError => e
    raise unless /needs binmode/ =~ e.message and args.size == 1
    args << "rb"
    file_opts = {encoding: Encoding.default_external}.merge(file_opts)
    retry
  end
  begin
    csv = new(f, options)
  rescue Exception
    f.close
    raise
  end

  # handle blocks like Ruby's open(), not like the CSV library
  if block_given?
    begin
      yield csv
    ensure
      csv.close
    end
  else
    csv
  end
end

# File lib/csv.rb, line 1318
def self.parse(*args, &block)
  csv = new(*args)
  if block.nil?  # slurp contents, if no block is given
    begin
      csv.read
    ensure
      csv.close
    end
  else           # or pass each row to a provided block
    csv.each(&block)
  end
end

# File lib/csv.rb, line 1338
def self.parse_line(line, options = Hash.new)
  new(line, options).shift
end

# File lib/csv.rb, line 1353
def self.read(path, *options)
  open(path, *options) { |csv| csv.read }
end

# File lib/csv.rb, line 1358
def self.readlines(*args)
  read(*args)
end

CSV.read( path, { headers:           true,
                  converters:        :numeric,
                  header_converters: :symbol }.merge(options) )

# File lib/csv.rb, line 1369
def self.table(path, options = Hash.new)
  read( path, { headers:           true,
                converters:        :numeric,
                header_converters: :symbol }.merge(options) )
end

# File lib/csv.rb, line 1686
def <<(row)
  # make sure headers have been assigned
  if header_row? and [Array, String].include? @use_headers.class
    parse_headers  # won't read data for Array or String
    self << @headers if @write_headers
  end

  # handle CSV::Row objects and Hashes
  row = case row
        when self.class::Row then row.fields
        when Hash            then @headers.map { |header| row[header] }
        else                      row
        end

  @headers =  row if header_row?
  @lineno  += 1

  output = row.map(&@quote).join(@col_sep) + @row_sep  # quote and separate
  if @io.is_a?(StringIO)             and
     output.encoding != (encoding = raw_encoding)
    if @force_encoding
      output = output.encode(encoding)
    elsif (compatible_encoding = Encoding.compatible?(@io.string, output))
      @io.set_encoding(compatible_encoding)
      @io.seek(0, IO::SEEK_END)
    end
  end
  @io << output

  self  # for chaining
end

# File lib/csv.rb, line 1735
def convert(name = nil, &converter)
  add_converter(:converters, self.class::Converters, name, &converter)
end

# File lib/csv.rb, line 1600
def converters
  @converters.map do |converter|
    name = Converters.rassoc(converter)
    name ? name.first : converter
  end
end

# File lib/csv.rb, line 1766
def each
  if block_given?
    while row = shift
      yield row
    end
  else
    to_enum
  end
end

# File lib/csv.rb, line 1643
def force_quotes?()       @force_quotes       end

# File lib/csv.rb, line 1750
def header_convert(name = nil, &converter)
  add_converter( :header_converters,
                 self.class::HeaderConverters,
                 name,
                 &converter )
end

# File lib/csv.rb, line 1631
def header_converters
  @header_converters.map do |converter|
    name = HeaderConverters.rassoc(converter)
    name ? name.first : converter
  end
end

# File lib/csv.rb, line 1792
def header_row?
  @use_headers and @headers.nil?
end

# File lib/csv.rb, line 1616
def headers
  @headers || true if @use_headers
end

# File lib/csv.rb, line 1960
def inspect
  str = ["<#", self.class.to_s, " io_type:"]
  # show type of wrapped IO
  if    @io == $stdout then str << "$stdout"
  elsif @io == $stdin  then str << "$stdin"
  elsif @io == $stderr then str << "$stderr"
  else                      str << @io.class.to_s
  end
  # show IO.path(), if available
  if @io.respond_to?(:path) and (p = @io.path)
    str << " io_path:" << p.inspect
  end
  # show encoding
  str << " encoding:" << @encoding.name
  # show other attributes
  %w[ lineno     col_sep     row_sep
      quote_char skip_blanks liberal_parsing ].each do |attr_name|
    if a = instance_variable_get("@#{attr_name}")
      str << " " << attr_name << ":" << a.inspect
    end
  end
  if @use_headers
    str << " headers:" << headers.inspect
  end
  str << ">"
  begin
    str.join('')
  rescue  # any encoding error
    str.map do |s|
      e = Encoding::Converter.asciicompat_encoding(s.encoding)
      e ? s.encode(e) : s.force_encoding("ASCII-8BIT")
    end.join('')
  end
end

# File lib/csv.rb, line 1645
def liberal_parsing?()    @liberal_parsing    end

# File lib/csv.rb, line 1781
def read
  rows = to_a
  if @use_headers
    Table.new(rows)
  else
    rows
  end
end

# File lib/csv.rb, line 1623
def return_headers?()     @return_headers     end

# File lib/csv.rb, line 1670
def rewind
  @headers = nil
  @lineno  = 0

  @io.rewind
end

# File lib/csv.rb, line 1803
def shift
  #########################################################################
  ### This method is purposefully kept a bit long as simple conditional ###
  ### checks are faster than numerous (expensive) method calls.         ###
  #########################################################################

  # handle headers not based on document content
  if header_row? and @return_headers and
     [Array, String].include? @use_headers.class
    if @unconverted_fields
      return add_unconverted_fields(parse_headers, Array.new)
    else
      return parse_headers
    end
  end

  #
  # it can take multiple calls to <tt>@io.gets()</tt> to get a full line,
  # because of \r and/or \n characters embedded in quoted fields
  #
  in_extended_col = false
  csv             = Array.new

  loop do
    # add another read to the line
    unless parse = @io.gets(@row_sep)
      return nil
    end

    parse.sub!(@parsers[:line_end], "")

    if csv.empty?
      #
      # I believe a blank line should be an <tt>Array.new</tt>, not Ruby 1.8
      # CSV's <tt>[nil]</tt>
      #
      if parse.empty?
        @lineno += 1
        if @skip_blanks
          next
        elsif @unconverted_fields
          return add_unconverted_fields(Array.new, Array.new)
        elsif @use_headers
          return self.class::Row.new(Array.new, Array.new)
        else
          return Array.new
        end
      end
    end

    next if @skip_lines and @skip_lines.match parse

    parts =  parse.split(@col_sep, -1)
    if parts.empty?
      if in_extended_col
        csv[-1] << @col_sep   # will be replaced with a @row_sep after the parts.each loop
      else
        csv << nil
      end
    end

    # This loop is the hot path of csv parsing. Some things may be non-dry
    # for a reason. Make sure to benchmark when refactoring.
    parts.each do |part|
      if in_extended_col
        # If we are continuing a previous column
        if part[-1] == @quote_char && part.count(@quote_char) % 2 != 0
          # extended column ends
          csv[-1] = csv[-1].push(part[0..-2]).join("")
          if csv.last =~ @parsers[:stray_quote]
            raise MalformedCSVError,
                  "Missing or stray quote in line #{lineno + 1}"
          end
          csv.last.gsub!(@quote_char * 2, @quote_char)
          in_extended_col = false
        else
          csv.last.push(part, @col_sep)
        end
      elsif part[0] == @quote_char
        # If we are starting a new quoted column
        if part.count(@quote_char) % 2 != 0
          # start an extended column
          csv << [part[1..-1], @col_sep]
          in_extended_col =  true
        elsif part[-1] == @quote_char
          # regular quoted column
          csv << part[1..-2]
          if csv.last =~ @parsers[:stray_quote]
            raise MalformedCSVError,
                  "Missing or stray quote in line #{lineno + 1}"
          end
          csv.last.gsub!(@quote_char * 2, @quote_char)
        elsif @liberal_parsing
          csv << part
        else
          raise MalformedCSVError,
                "Missing or stray quote in line #{lineno + 1}"
        end
      elsif part =~ @parsers[:quote_or_nl]
        # Unquoted field with bad characters.
        if part =~ @parsers[:nl_or_lf]
          raise MalformedCSVError, "Unquoted fields do not allow " +
                                   "\\r or \\n (line #{lineno + 1})."
        else
          if @liberal_parsing
            csv << part
          else
            raise MalformedCSVError, "Illegal quoting in line #{lineno + 1}."
          end
        end
      else
        # Regular ole unquoted field.
        csv << (part.empty? ? nil : part)
      end
    end

    # Replace tacked on @col_sep with @row_sep if we are still in an extended
    # column.
    csv[-1][-1] = @row_sep if in_extended_col

    if in_extended_col
      # if we're at eof?(), a quoted field wasn't closed...
      if @io.eof?
        raise MalformedCSVError,
              "Unclosed quoted field on line #{lineno + 1}."
      elsif @field_size_limit and csv.last.sum(&:size) >= @field_size_limit
        raise MalformedCSVError, "Field size exceeded on line #{lineno + 1}."
      end
      # otherwise, we need to loop and pull some more data to complete the row
    else
      @lineno += 1

      # save fields unconverted fields, if needed...
      unconverted = csv.dup if @unconverted_fields

      # convert fields, if needed...
      csv = convert_fields(csv) unless @use_headers or @converters.empty?
      # parse out header rows and handle CSV::Row conversions...
      csv = parse_headers(csv)  if     @use_headers

      # inject unconverted fields and accessor, if requested...
      if @unconverted_fields and not csv.respond_to? :unconverted_fields
        add_unconverted_fields(csv, unconverted)
      end

      # return the results
      break csv
    end
  end
end

# File lib/csv.rb, line 1641
def skip_blanks?()        @skip_blanks        end

# File lib/csv.rb, line 1610
def unconverted_fields?() @unconverted_fields end

# File lib/csv.rb, line 1625
def write_headers?()      @write_headers      end

# File lib/csv.rb, line 2200
def add_converter(var_name, const, name = nil, &converter)
  if name.nil?  # custom converter
    instance_variable_get("@#{var_name}") << converter
  else          # named converter
    combo = const[name]
    case combo
    when Array  # combo converter
      combo.each do |converter_name|
        add_converter(var_name, const, converter_name)
      end
    else        # individual named converter
      instance_variable_get("@#{var_name}") << combo
    end
  end
end

# File lib/csv.rb, line 2287
def add_unconverted_fields(row, fields)
  class << row
    attr_reader :unconverted_fields
  end
  row.instance_eval { @unconverted_fields = fields }
  row
end

# File lib/csv.rb, line 2223
def convert_fields(fields, headers = false)
  # see if we are converting headers or fields
  converters = headers ? @header_converters : @converters

  fields.map.with_index do |field, index|
    converters.each do |converter|
      break if field.nil?
      field = if converter.arity == 1  # straight field converter
        converter[field]
      else                             # FieldInfo converter
        header = @use_headers && !headers ? @headers[index] : nil
        converter[field, FieldInfo.new(index, lineno, header)]
      end
      break unless field.is_a? String  # short-circuit pipeline for speed
    end
    field  # final state of each field, converted or original
  end
end

# File lib/csv.rb, line 2310
def encode_re(*chunks)
  Regexp.new(encode_str(*chunks))
end

# File lib/csv.rb, line 2318
def encode_str(*chunks)
  chunks.map { |chunk| chunk.encode(@encoding.name) }.join('')
end

# File lib/csv.rb, line 2302
def escape_re(str)
  str.gsub(@re_chars) {|c| @re_esc + c}
end

# File lib/csv.rb, line 2185
def init_comments(options)
  @skip_lines = options.delete(:skip_lines)
  @skip_lines = Regexp.new(@skip_lines) if @skip_lines.is_a? String
  if @skip_lines and not @skip_lines.respond_to?(:match)
    raise ArgumentError, ":skip_lines has to respond to matches"
  end
end

# File lib/csv.rb, line 2138
def init_converters(options, field_name = :converters)
  if field_name == :converters
    @unconverted_fields = options.delete(:unconverted_fields)
  end

  instance_variable_set("@#{field_name}", Array.new)

  # find the correct method to add the converters
  convert = method(field_name.to_s.sub(/ers\Z/, ""))

  # load converters
  unless options[field_name].nil?
    # allow a single converter not wrapped in an Array
    unless options[field_name].is_a? Array
      options[field_name] = [options[field_name]]
    end
    # load each converter...
    options[field_name].each do |converter|
      if converter.is_a? Proc  # custom code block
        convert.call(&converter)
      else                     # by name
        convert.call(converter)
      end
    end
  end

  options.delete(field_name)
end

# File lib/csv.rb, line 2168
def init_headers(options)
  @use_headers    = options.delete(:headers)
  @return_headers = options.delete(:return_headers)
  @write_headers  = options.delete(:write_headers)

  # headers must be delayed until shift(), in case they need a row of content
  @headers = nil

  init_converters(options, :header_converters)
end

# File lib/csv.rb, line 2106
def init_parsers(options)
  # store the parser behaviors
  @skip_blanks      = options.delete(:skip_blanks)
  @field_size_limit = options.delete(:field_size_limit)
  @liberal_parsing  = options.delete(:liberal_parsing)

  # prebuild Regexps for faster parsing
  esc_row_sep = escape_re(@row_sep)
  esc_quote   = escape_re(@quote_char)
  @parsers = {
    # for detecting parse errors
    quote_or_nl:    encode_re("[", esc_quote, "\r\n]"),
    nl_or_lf:       encode_re("[\r\n]"),
    stray_quote:    encode_re( "[^", esc_quote, "]", esc_quote,
                               "[^", esc_quote, "]" ),
    # safer than chomp!()
    line_end:       encode_re(esc_row_sep, "\\z"),
    # illegal unquoted characters
    return_newline: encode_str("\r\n")
  }
end

# File lib/csv.rb, line 2007
def init_separators(options)
  # store the selected separators
  @col_sep    = options.delete(:col_sep).to_s.encode(@encoding)
  @row_sep    = options.delete(:row_sep)  # encode after resolving :auto
  @quote_char = options.delete(:quote_char).to_s.encode(@encoding)

  if @quote_char.length != 1
    raise ArgumentError, ":quote_char has to be a single character String"
  end

  #
  # automatically discover row separator when requested
  # (not fully encoding safe)
  #
  if @row_sep == :auto
    if [ARGF, STDIN, STDOUT, STDERR].include?(@io) or
       (defined?(Zlib) and @io.class == Zlib::GzipWriter)
      @row_sep = $INPUT_RECORD_SEPARATOR
    else
      begin
        #
        # remember where we were (pos() will raise an exception if @io is pipe
        # or not opened for reading)
        #
        saved_pos = @io.pos
        while @row_sep == :auto
          #
          # if we run out of data, it's probably a single line
          # (ensure will set default value)
          #
          break unless sample = @io.gets(nil, 1024)
          # extend sample if we're unsure of the line ending
          if sample.end_with? encode_str("\r")
            sample << (@io.gets(nil, 1) || "")
          end

          # try to find a standard separator
          if sample =~ encode_re("\r\n?|\n")
            @row_sep = $&
            break
          end
        end

        # tricky seek() clone to work around GzipReader's lack of seek()
        @io.rewind
        # reset back to the remembered position
        while saved_pos > 1024  # avoid loading a lot of data into memory
          @io.read(1024)
          saved_pos -= 1024
        end
        @io.read(saved_pos) if saved_pos.nonzero?
      rescue IOError         # not opened for reading
        # do nothing:  ensure will set default
      rescue NoMethodError   # Zlib::GzipWriter doesn't have some IO methods
        # do nothing:  ensure will set default
      rescue SystemCallError # pipe
        # do nothing:  ensure will set default
      ensure
        #
        # set default if we failed to detect
        # (stream not opened for reading, a pipe, or a single line of data)
        #
        @row_sep = $INPUT_RECORD_SEPARATOR if @row_sep == :auto
      end
    end
  end
  @row_sep = @row_sep.to_s.encode(@encoding)

  # establish quoting rules
  @force_quotes   = options.delete(:force_quotes)
  do_quote        = lambda do |field|
    field         = String(field)
    encoded_quote = @quote_char.encode(field.encoding)
    encoded_quote                                +
    field.gsub(encoded_quote, encoded_quote * 2) +
    encoded_quote
  end
  quotable_chars = encode_str("\r\n", @col_sep, @quote_char)
  @quote         = if @force_quotes
    do_quote
  else
    lambda do |field|
      if field.nil?  # represent +nil+ fields as empty unquoted fields
        ""
      else
        field = String(field)  # Stringify fields
        # represent empty fields as empty quoted fields
        if field.empty? or
           field.count(quotable_chars).nonzero?
          do_quote.call(field)
        else
          field  # unquoted field
        end
      end
    end
  end
end

# File lib/csv.rb, line 2252
def parse_headers(row = nil)
  if @headers.nil?                # header row
    @headers = case @use_headers  # save headers
               # Array of headers
               when Array then @use_headers
               # CSV header String
               when String
                 self.class.parse_line( @use_headers,
                                        col_sep:    @col_sep,
                                        row_sep:    @row_sep,
                                        quote_char: @quote_char )
               # first row is headers
               else            row
               end

    # prepare converted and unconverted copies
    row      = @headers                       if row.nil?
    @headers = convert_fields(@headers, true)
    @headers.each { |h| h.freeze if h.is_a? String }

    if @return_headers                                     # return headers
      return self.class::Row.new(@headers, row, true)
    elsif not [Array, String].include? @use_headers.class  # skip to field row
      return shift
    end
  end

  self.class::Row.new(@headers, convert_fields(row))  # field row
end

# File lib/csv.rb, line 2328
def raw_encoding(default = Encoding::ASCII_8BIT)
  if @io.respond_to? :internal_encoding
    @io.internal_encoding || @io.external_encoding
  elsif @io.is_a? StringIO
    @io.string.encoding
  elsif @io.respond_to? :encoding
    @io.encoding
  else
    default
  end
end