diff options
Diffstat (limited to 'lib/csv.rb')
-rw-r--r-- | lib/csv.rb | 837 |
1 files changed, 222 insertions, 615 deletions
diff --git a/lib/csv.rb b/lib/csv.rb index dca2a45b6a..ebdc6e5c6d 100644 --- a/lib/csv.rb +++ b/lib/csv.rb @@ -93,36 +93,22 @@ require "forwardable" require "English" require "date" require "stringio" -require_relative "csv/table" -require_relative "csv/row" -# This provides String#match? and Regexp#match? for Ruby 2.3. -unless String.method_defined?(:match?) - class CSV - module MatchP - refine String do - def match?(pattern) - self =~ pattern - end - end - - refine Regexp do - def match?(string) - self =~ string - end - end - end - end +require_relative "csv/fields_converter" +require_relative "csv/match_p" +require_relative "csv/parser" +require_relative "csv/row" +require_relative "csv/table" +require_relative "csv/writer" - using CSV::MatchP -end +using CSV::MatchP if CSV.const_defined?(:MatchP) # # This class provides a complete interface to CSV files and data. It offers # tools to enable you to read and write to and from Strings or IO objects, as # needed. # -# The most generic interface of a class is: +# The most generic interface of the library is: # # csv = CSV.new(string_or_io, **options) # @@ -204,18 +190,18 @@ end # # Headers are part of data # data = CSV.parse(<<~ROWS, headers: true) # Name,Department,Salary -# Bob,Engeneering,1000 +# Bob,Engineering,1000 # Jane,Sales,2000 # John,Management,5000 # ROWS # # data.class #=> CSV::Table -# data.first #=> #<CSV::Row "Name":"Bob" "Department":"Engeneering" "Salary":"1000"> -# data.first.to_h #=> {"Name"=>"Bob", "Department"=>"Engeneering", "Salary"=>"1000"} +# data.first #=> #<CSV::Row "Name":"Bob" "Department":"Engineering" "Salary":"1000"> +# data.first.to_h #=> {"Name"=>"Bob", "Department"=>"Engineering", "Salary"=>"1000"} # # # Headers provided by developer # data = CSV.parse('Bob,Engeneering,1000', headers: %i[name department salary]) -# data.first #=> #<CSV::Row name:"Bob" department:"Engeneering" salary:"1000"> +# data.first #=> #<CSV::Row name:"Bob" department:"Engineering" salary:"1000"> # # === Typed data reading # @@ -902,10 +888,24 @@ class CSV # Options cannot be overridden in the instance methods for performance reasons, # so be sure to set what you want here. # - def initialize(data, col_sep: ",", row_sep: :auto, quote_char: '"', field_size_limit: nil, - converters: nil, unconverted_fields: nil, headers: false, return_headers: false, - write_headers: nil, header_converters: nil, skip_blanks: false, force_quotes: false, - skip_lines: nil, liberal_parsing: false, internal_encoding: nil, external_encoding: nil, encoding: nil, + def initialize(data, + col_sep: ",", + row_sep: :auto, + quote_char: '"', + field_size_limit: nil, + converters: nil, + unconverted_fields: nil, + headers: false, + return_headers: false, + write_headers: nil, + header_converters: nil, + skip_blanks: false, + force_quotes: false, + skip_lines: nil, + liberal_parsing: false, + internal_encoding: nil, + external_encoding: nil, + encoding: nil, nil_value: nil, empty_value: "") raise ArgumentError.new("Cannot parse nil as CSV") if data.nil? @@ -913,64 +913,79 @@ class CSV # create the IO object we will read from @io = data.is_a?(String) ? StringIO.new(data) : data @encoding = determine_encoding(encoding, internal_encoding) - # - # 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)}/ - @unconverted_fields = unconverted_fields - - # Stores header row settings and loads header converters, if needed. - @use_headers = headers - @return_headers = return_headers - @write_headers = write_headers - - # headers must be delayed until shift(), in case they need a row of content - @headers = nil - - @nil_value = nil_value - @empty_value = empty_value - @empty_value_is_empty_string = (empty_value == "") - - init_separators(col_sep, row_sep, quote_char, force_quotes) - init_parsers(skip_blanks, field_size_limit, liberal_parsing) - init_converters(converters, :@converters, :convert) - init_converters(header_converters, :@header_converters, :header_convert) - init_comments(skip_lines) - - @force_encoding = !!encoding - - # track our own lineno since IO gets confused about line-ends is CSV fields - @lineno = 0 - - # make sure headers have been assigned - if header_row? and [Array, String].include? @use_headers.class and @write_headers - parse_headers # won't read data for Array or String - self << @headers - end + + @base_fields_converter_options = { + nil_value: nil_value, + empty_value: empty_value, + } + @initial_converters = converters + @initial_header_converters = header_converters + + @parser_options = { + column_separator: col_sep, + row_separator: row_sep, + quote_character: quote_char, + field_size_limit: field_size_limit, + unconverted_fields: unconverted_fields, + headers: headers, + return_headers: return_headers, + skip_blanks: skip_blanks, + skip_lines: skip_lines, + liberal_parsing: liberal_parsing, + encoding: @encoding, + nil_value: nil_value, + empty_value: empty_value, + } + @parser = nil + + @writer_options = { + encoding: @encoding, + force_encoding: (not encoding.nil?), + force_quotes: force_quotes, + headers: headers, + write_headers: write_headers, + column_separator: col_sep, + row_separator: row_sep, + quote_character: quote_char, + } + + @writer = nil + writer if @writer_options[:write_headers] end # # The encoded <tt>:col_sep</tt> used in parsing and writing. See CSV::new # for details. # - attr_reader :col_sep + def col_sep + parser.column_separator + end + # # The encoded <tt>:row_sep</tt> used in parsing and writing. See CSV::new # for details. # - attr_reader :row_sep + def row_sep + parser.row_separator + end + # # The encoded <tt>:quote_char</tt> used in parsing and writing. See CSV::new # for details. # - attr_reader :quote_char + def quote_char + parser.quote_character + end + # The limit for field size, if any. See CSV::new for details. - attr_reader :field_size_limit + def field_size_limit + parser.field_size_limit + end # The regex marking a line as a comment. See CSV::new for details - attr_reader :skip_lines + def skip_lines + parser.skip_lines + end # # Returns the current list of converters in effect. See CSV::new for details. @@ -978,7 +993,7 @@ class CSV # as is. # def converters - @converters.map do |converter| + fields_converter.map do |converter| name = Converters.rassoc(converter) name ? name.first : converter end @@ -987,42 +1002,68 @@ class CSV # Returns +true+ if unconverted_fields() to parsed results. See CSV::new # for details. # - def unconverted_fields?() @unconverted_fields end + def unconverted_fields? + parser.unconverted_fields? + end + # # Returns +nil+ if headers will not be used, +true+ if they will but have not # yet been read, or the actual headers after they have been read. See # CSV::new for details. # def headers - @headers || true if @use_headers + if @writer + @writer.headers + else + parsed_headers = parser.headers + return parsed_headers if parsed_headers + raw_headers = @parser_options[:headers] + raw_headers = nil if raw_headers == false + raw_headers + end end # # Returns +true+ if headers will be returned as a row of results. # See CSV::new for details. # - def return_headers?() @return_headers end + def return_headers? + parser.return_headers? + end + # Returns +true+ if headers are written in output. See CSV::new for details. - def write_headers?() @write_headers end + def write_headers? + @writer_options[:write_headers] + end + # # Returns the current list of converters in effect for headers. See CSV::new # for details. Built-in converters will be returned by name, while others # will be returned as is. # def header_converters - @header_converters.map do |converter| + header_fields_converter.map do |converter| name = HeaderConverters.rassoc(converter) name ? name.first : converter end end + # # Returns +true+ blank lines are skipped by the parser. See CSV::new # for details. # - def skip_blanks?() @skip_blanks end + def skip_blanks? + parser.skip_blanks? + end + # Returns +true+ if all output fields are quoted. See CSV::new for details. - def force_quotes?() @force_quotes end + def force_quotes? + @writer_options[:force_quotes] + end + # Returns +true+ if illegal input is handled. See CSV::new for details. - def liberal_parsing?() @liberal_parsing end + def liberal_parsing? + parser.liberal_parsing? + end # # The Encoding CSV is parsing or writing in. This will be the Encoding you @@ -1031,10 +1072,23 @@ class CSV attr_reader :encoding # - # The line number of the last row read from this file. Fields with nested + # The line number of the last row read from this file. Fields with nested # line-end characters will not affect this count. # - attr_reader :lineno, :line + def lineno + if @writer + @writer.lineno + else + parser.lineno + end + end + + # + # The last row read from this file. + # + def line + parser.line + end ### IO and StringIO Delegation ### @@ -1048,9 +1102,9 @@ class CSV # Rewinds the underlying IO object and resets CSV's lineno() counter. def rewind - @headers = nil - @lineno = 0 - + @parser = nil + @parser_enumerator = nil + @writer.rewind if @writer @io.rewind end @@ -1064,34 +1118,8 @@ class CSV # The data source must be open for writing. # def <<(row) - # make sure headers have been assigned - if header_row? and [Array, String].include? @use_headers.class and !@write_headers - parse_headers # won't read data for Array or String - 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 + writer << row + self end alias_method :add_row, :<< alias_method :puts, :<< @@ -1112,7 +1140,7 @@ class CSV # converted field or the field itself. # def convert(name = nil, &converter) - add_converter(:@converters, self.class::Converters, name, &converter) + fields_converter.add_converter(name, &converter) end # @@ -1127,10 +1155,7 @@ class CSV # effect. # def header_convert(name = nil, &converter) - add_converter( :@header_converters, - self.class::HeaderConverters, - name, - &converter ) + header_fields_converter.add_converter(name, &converter) end include Enumerable @@ -1142,14 +1167,8 @@ class CSV # # The data source must be open for reading. # - def each - if block_given? - while row = shift - yield row - end - else - to_enum - end + def each(&block) + parser.parse(&block) end # @@ -1159,8 +1178,9 @@ class CSV # def read rows = to_a - if @use_headers - Table.new(rows) + headers = parser.headers + if headers + Table.new(rows, headers: headers) else rows end @@ -1169,7 +1189,7 @@ class CSV # Returns +true+ if the next row read will be a header row. def header_row? - @use_headers and @headers.nil? + parser.header_row? end # @@ -1180,171 +1200,11 @@ class CSV # The data source must be open for reading. # 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 - - if in_extended_col - @line.concat(parse) - else - @line = parse.clone - end - - begin - parse.sub!(@parsers[:line_end], "") - rescue ArgumentError - unless parse.valid_encoding? - message = "Invalid byte sequence in #{parse.encoding}" - raise MalformedCSVError.new(message, lineno + 1) - end - raise - 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(@headers, Array.new) - else - return Array.new - end - end - end - - next if @skip_lines and @skip_lines.match parse - - parts = parse.split(@col_sep_split_separator, -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.end_with?(@quote_char) && part.count(@quote_char) % 2 != 0 - # extended column ends - csv.last << part[0..-2] - if csv.last.match?(@parsers[:stray_quote]) - raise MalformedCSVError.new("Missing or stray quote", - lineno + 1) - end - csv.last.gsub!(@double_quote_char, @quote_char) - in_extended_col = false - else - csv.last << part << @col_sep - end - elsif part.start_with?(@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.end_with?(@quote_char) - # regular quoted column - csv << part[1..-2] - if csv.last.match?(@parsers[:stray_quote]) - raise MalformedCSVError.new("Missing or stray quote", - lineno + 1) - end - csv.last.gsub!(@double_quote_char, @quote_char) - elsif @liberal_parsing - csv << part - else - raise MalformedCSVError.new("Missing or stray quote", - lineno + 1) - end - elsif part.match?(@parsers[:quote_or_nl]) - # Unquoted field with bad characters. - if part.match?(@parsers[:nl_or_lf]) - message = "Unquoted fields do not allow \\r or \\n" - raise MalformedCSVError.new(message, lineno + 1) - else - if @liberal_parsing - csv << part - else - raise MalformedCSVError.new("Illegal quoting", 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.new("Unclosed quoted field", - lineno + 1) - elsif @field_size_limit and csv.last.size >= @field_size_limit - raise MalformedCSVError.new("Field size exceeded", - 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 - - if @use_headers - # parse out header rows and handle CSV::Row conversions... - csv = parse_headers(csv) - else - # convert fields, if needed... - csv = convert_fields(csv) - end - - # 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 + @parser_enumerator ||= parser.parse + begin + @parser_enumerator.next + rescue StopIteration + nil end end alias_method :gets, :shift @@ -1369,15 +1229,19 @@ class CSV # 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}") + ["lineno", "col_sep", "row_sep", "quote_char"].each do |attr_name| + if a = __send__(attr_name) str << " " << attr_name << ":" << a.inspect end end - if @use_headers - str << " headers:" << headers.inspect + ["skip_blanks", "liberal_parsing"].each do |attr_name| + if a = __send__("#{attr_name}?") + str << " " << attr_name << ":" << a.inspect + end end + _headers = headers + _headers = headers + str << " headers:" << _headers.inspect if _headers str << ">" begin str.join('') @@ -1393,7 +1257,7 @@ class CSV def determine_encoding(encoding, internal_encoding) # honor the IO encoding if we can, otherwise default to ASCII-8BIT - io_encoding = raw_encoding(nil) + io_encoding = raw_encoding return io_encoding if io_encoding return Encoding.find(internal_encoding) if internal_encoding @@ -1406,216 +1270,17 @@ class CSV Encoding.default_internal || Encoding.default_external end - # - # Stores the indicated separators for later use. - # - # If auto-discovery was requested for <tt>@row_sep</tt>, this method will read - # ahead in the <tt>@io</tt> and try to find one. +ARGF+, +STDIN+, +STDOUT+, - # +STDERR+ and any stream open for output only with a default - # <tt>@row_sep</tt> of <tt>$INPUT_RECORD_SEPARATOR</tt> (<tt>$/</tt>). - # - # This method also establishes the quoting rules used for CSV output. - # - def init_separators(col_sep, row_sep, quote_char, force_quotes) - # store the selected separators - @col_sep = col_sep.to_s.encode(@encoding) - if @col_sep == " " - @col_sep_split_separator = Regexp.new(/#{Regexp.escape(@col_sep)}/) - else - @col_sep_split_separator = @col_sep - end - @row_sep = row_sep # encode after resolving :auto - @quote_char = quote_char.to_s.encode(@encoding) - @double_quote_char = @quote_char * 2 - - 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) - - cr = encode_str("\r") - lf = encode_str("\n") - # extend sample if we're unsure of the line ending - if sample.end_with?(cr) - sample << (@io.gets(nil, 1) || "") - end - - # try to find a standard separator - sample.each_char.each_cons(2) do |char, next_char| - case char - when cr - if next_char == lf - @row_sep = encode_str("\r\n") - else - @row_sep = cr - end - break - when lf - @row_sep = lf - break - end - 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 = 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 - - # Pre-compiles parsers and stores them by name for access during reads. - def init_parsers(skip_blanks, field_size_limit, liberal_parsing) - # store the parser behaviors - @skip_blanks = skip_blanks - @field_size_limit = field_size_limit - @liberal_parsing = 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 - - # - # Loads any converters requested during construction. - # - # If +field_name+ is set <tt>:converters</tt> (the default) field converters - # are set. When +field_name+ is <tt>:header_converters</tt> header converters - # are added instead. - # - # The <tt>:unconverted_fields</tt> option is also activated for - # <tt>:converters</tt> calls, if requested. - # - def init_converters(converters, ivar_name, convert_method) - converters = case converters - when nil then [] - when Array then converters - else [converters] - end - instance_variable_set(ivar_name, []) - convert = method(convert_method) - - # load converters - converters.each do |converter| - if converter.is_a? Proc # custom code block - convert.call(&converter) - else # by name - convert.call(converter) - end - end - end - - # Stores the pattern of comments to skip from the provided options. - # - # The pattern must respond to +.match+, else ArgumentError is raised. - # Strings are converted to a Regexp. - # - # See also CSV.new - def init_comments(skip_lines) - @skip_lines = skip_lines - @skip_lines = Regexp.new(Regexp.escape(@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" + def normalize_converters(converters) + converters ||= [] + unless converters.is_a?(Array) + converters = [converters] end - end - # - # The actual work method for adding converters, used by both CSV.convert() and - # CSV.header_convert(). - # - # This method requires the +var_name+ of the instance variable to place the - # converters in, the +const+ Hash to lookup named converters in, and the - # normal parameters of the CSV.convert() and CSV.header_convert() methods. - # - 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 + converters.collect do |converter| + case converter + when Proc # custom code block + [nil, converter] + else # by name + [converter, nil] end end end @@ -1629,131 +1294,73 @@ class CSV # def convert_fields(fields, headers = false) if headers - converters = @header_converters + header_fields_converter.convert(fields, nil, 0) else - converters = @converters - if !@use_headers and - converters.empty? and - @nil_value.nil? and - @empty_value_is_empty_string - return fields - end + fields_converter.convert(fields, @headers, lineno) end + end - fields.map.with_index do |field, index| - if field.nil? - field = @nil_value - elsif field.empty? - field = @empty_value unless @empty_value_is_empty_string - end - converters.each do |converter| - break if headers && 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 + # + # Returns the encoding of the internal IO object. + # + def raw_encoding + if @io.respond_to? :internal_encoding + @io.internal_encoding || @io.external_encoding + elsif @io.respond_to? :encoding + @io.encoding + else + nil end end - # - # This method is used to turn a finished +row+ into a CSV::Row. Header rows - # are also dealt with here, either by returning a CSV::Row with identical - # headers and fields (save that the fields do not go through the converters) - # or by reading past them to return a field row. Headers are also saved in - # <tt>@headers</tt> for use in future rows. - # - # When +nil+, +row+ is assumed to be a header row not based on an actual row - # of the stream. - # - 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 + def fields_converter + @fields_converter ||= build_fields_converter + end + + def build_fields_converter + specific_options = { + builtin_converters: Converters, + } + options = @base_fields_converter_options.merge(specific_options) + fields_converter = FieldsConverter.new(options) + normalize_converters(@initial_converters).each do |name, converter| + fields_converter.add_converter(name, &converter) end + fields_converter + end - self.class::Row.new(@headers, convert_fields(row)) # field row + def header_fields_converter + @header_fields_converter ||= build_header_fields_converter end - # - # This method injects an instance variable <tt>unconverted_fields</tt> into - # +row+ and an accessor method for +row+ called unconverted_fields(). The - # variable is set to the contents of +fields+. - # - def add_unconverted_fields(row, fields) - class << row - attr_reader :unconverted_fields + def build_header_fields_converter + specific_options = { + builtin_converters: HeaderConverters, + accept_nil: true, + } + options = @base_fields_converter_options.merge(specific_options) + fields_converter = FieldsConverter.new(options) + normalize_converters(@initial_header_converters).each do |name, converter| + fields_converter.add_converter(name, &converter) end - row.instance_variable_set(:@unconverted_fields, fields) - row + fields_converter end - # - # This method is an encoding safe version of Regexp::escape(). It will escape - # any characters that would change the meaning of a regular expression in the - # encoding of +str+. Regular expression characters that cannot be transcoded - # to the target encoding will be skipped and no escaping will be performed if - # a backslash cannot be transcoded. - # - def escape_re(str) - str.gsub(@re_chars) {|c| @re_esc + c} + def parser + @parser ||= Parser.new(@io, parser_options) end - # - # Builds a regular expression in <tt>@encoding</tt>. All +chunks+ will be - # transcoded to that encoding. - # - def encode_re(*chunks) - Regexp.new(encode_str(*chunks)) + def parser_options + @parser_options.merge(fields_converter: fields_converter, + header_fields_converter: header_fields_converter) end - # - # Builds a String in <tt>@encoding</tt>. All +chunks+ will be transcoded to - # that encoding. - # - def encode_str(*chunks) - chunks.map { |chunk| chunk.encode(@encoding.name) }.join('') + def writer + @writer ||= Writer.new(@io, writer_options) end - # - # Returns the encoding of the internal IO object or the +default+ if the - # encoding cannot be determined. - # - 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 + def writer_options + @writer_options.merge(header_fields_converter: header_fields_converter) end end |