diff --git a/NEWS b/NEWS index 9a1c0275c2..d26523352f 100644 --- a/NEWS +++ b/NEWS @@ -343,7 +343,7 @@ CGI:: CSV:: - * Upgrade to 3.0.9. + * Upgrade to 3.1.2. See https://github.com/ruby/csv/blob/master/NEWS.md. Date:: diff --git a/lib/csv.rb b/lib/csv.rb index 60dbbcc230..8aa65868b7 100644 --- a/lib/csv.rb +++ b/lib/csv.rb @@ -10,18 +10,18 @@ # # Welcome to the new and improved CSV. # -# This version of the CSV library began its life as FasterCSV. FasterCSV was -# intended as a replacement to Ruby's then standard CSV library. It was +# This version of the CSV library began its life as FasterCSV. FasterCSV was +# intended as a replacement to Ruby's then standard CSV library. It was # designed to address concerns users of that library had and it had three # primary goals: # # 1. Be significantly faster than CSV while remaining a pure Ruby library. -# 2. Use a smaller and easier to maintain code base. (FasterCSV eventually -# grew larger, was also but considerably richer in features. The parsing +# 2. Use a smaller and easier to maintain code base. (FasterCSV eventually +# grew larger, was also but considerably richer in features. The parsing # core remains quite small.) # 3. Improve on the CSV interface. # -# Obviously, the last one is subjective. I did try to defer to the original +# Obviously, the last one is subjective. I did try to defer to the original # interface whenever I didn't have a compelling reason to change it though, so # hopefully this won't be too radically different. # @@ -29,20 +29,20 @@ # the original library as of Ruby 1.9. If you are migrating code from 1.8 or # earlier, you may have to change your code to comply with the new interface. # -# == What's Different From the Old CSV? +# == What's the Different From the Old CSV? # # I'm sure I'll miss something, but I'll try to mention most of the major # differences I am aware of, to help others quickly get up to speed: # # === CSV Parsing # -# * This parser is m17n aware. See CSV for full details. +# * This parser is m17n aware. See CSV for full details. # * This library has a stricter parser and will throw MalformedCSVErrors on # problematic data. -# * This library has a less liberal idea of a line ending than CSV. What you -# set as the :row_sep is law. It can auto-detect your line endings +# * This library has a less liberal idea of a line ending than CSV. What you +# set as the :row_sep is law. It can auto-detect your line endings # though. -# * The old library returned empty lines as [nil]. This library calls +# * The old library returned empty lines as [nil]. This library calls # them []. # * This library has a much faster parser. # @@ -56,9 +56,9 @@ # * CSV now has a new() method used to wrap objects like String and IO for # reading and writing. # * CSV::generate() is different from the old method. -# * CSV no longer supports partial reads. It works line-by-line. +# * CSV no longer supports partial reads. It works line-by-line. # * CSV no longer allows the instance methods to override the separators for -# performance reasons. They must be set in the constructor. +# performance reasons. They must be set in the constructor. # # If you use this library and find yourself missing any functionality I have # trimmed, please {let me know}[mailto:james@grayproductions.net]. @@ -70,16 +70,16 @@ # == What is CSV, really? # # CSV maintains a pretty strict definition of CSV taken directly from -# {the RFC}[http://www.ietf.org/rfc/rfc4180.txt]. I relax the rules in only one -# place and that is to make using this library easier. CSV will parse all valid +# {the RFC}[http://www.ietf.org/rfc/rfc4180.txt]. I relax the rules in only one +# place and that is to make using this library easier. CSV will parse all valid # CSV. # -# What you don't want to do is feed CSV invalid data. Because of the way the +# What you don't want to do is to feed CSV invalid data. Because of the way the # CSV format works, it's common for a parser to need to read until the end of -# the file to be sure a field is invalid. This eats a lot of time and memory. +# the file to be sure a field is invalid. This consumes a lot of time and memory. # # Luckily, when working with invalid CSV, Ruby's built-in methods will almost -# always be superior in every way. For example, parsing non-quoted fields is as +# always be superior in every way. For example, parsing non-quoted fields is as # easy as: # # data.split(",") @@ -104,7 +104,7 @@ require_relative "csv/writer" using CSV::MatchP if CSV.const_defined?(:MatchP) # -# This class provides a complete interface to CSV files and data. It offers +# 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. # @@ -184,7 +184,7 @@ using CSV::MatchP if CSV.const_defined?(:MatchP) # === CSV with headers # # CSV allows to specify column names of CSV file, whether they are in data, or -# provided separately. If headers specified, reading methods return an instance +# provided separately. If headers are specified, reading methods return an instance # of CSV::Table, consisting of CSV::Row. # # # Headers are part of data @@ -223,42 +223,42 @@ using CSV::MatchP if CSV.const_defined?(:MatchP) # == CSV and Character Encodings (M17n or Multilingualization) # # This new CSV parser is m17n savvy. The parser works in the Encoding of the IO -# or String object being read from or written to. Your data is never transcoded +# or String object being read from or written to. Your data is never transcoded # (unless you ask Ruby to transcode it for you) and will literally be parsed in -# the Encoding it is in. Thus CSV will return Arrays or Rows of Strings in the -# Encoding of your data. This is accomplished by transcoding the parser itself +# the Encoding it is in. Thus CSV will return Arrays or Rows of Strings in the +# Encoding of your data. This is accomplished by transcoding the parser itself # into your Encoding. # # Some transcoding must take place, of course, to accomplish this multiencoding -# support. For example, :col_sep, :row_sep, and +# support. For example, :col_sep, :row_sep, and # :quote_char must be transcoded to match your data. Hopefully this # makes the entire process feel transparent, since CSV's defaults should just -# magically work for your data. However, you can set these values manually in +# magically work for your data. However, you can set these values manually in # the target Encoding to avoid the translation. # # It's also important to note that while all of CSV's core parser is now -# Encoding agnostic, some features are not. For example, the built-in +# Encoding agnostic, some features are not. For example, the built-in # converters will try to transcode data to UTF-8 before making conversions. # Again, you can provide custom converters that are aware of your Encodings to -# avoid this translation. It's just too hard for me to support native +# avoid this translation. It's just too hard for me to support native # conversions in all of Ruby's Encodings. # -# Anyway, the practical side of this is simple: make sure IO and String objects +# Anyway, the practical side of this is simple: make sure IO and String objects # passed into CSV have the proper Encoding set and everything should just work. # CSV methods that allow you to open IO objects (CSV::foreach(), CSV::open(), # CSV::read(), and CSV::readlines()) do allow you to specify the Encoding. # # One minor exception comes when generating CSV into a String with an Encoding -# that is not ASCII compatible. There's no existing data for CSV to use to +# that is not ASCII compatible. There's no existing data for CSV to use to # prepare itself and thus you will probably need to manually specify the desired -# Encoding for most of those cases. It will try to guess using the fields in a +# Encoding for most of those cases. It will try to guess using the fields in a # row of output though, when using CSV::generate_line() or Array#to_csv(). # # I try to point out any other Encoding issues in the documentation of methods # as they come up. # # This has been tested to the best of my ability with all non-"dummy" Encodings -# Ruby ships with. However, it is brave new code and may have some bugs. +# Ruby ships with. However, it is brave new code and may have some bugs. # Please feel free to {report}[mailto:james@grayproductions.net] any issues you # find with it. # @@ -354,7 +354,7 @@ class CSV # # This Hash holds the built-in header converters of CSV that can be accessed - # by name. You can select HeaderConverters with CSV.header_convert() or + # by name. You can select HeaderConverters with CSV.header_convert() or # through the +options+ Hash passed to CSV::new(). # # :downcase:: Calls downcase() on the header String. @@ -364,13 +364,13 @@ class CSV # and finally to_sym() is called. # # All built-in header converters transcode header data to UTF-8 before - # attempting a conversion. If your data cannot be transcoded to UTF-8 the + # attempting a conversion. If your data cannot be transcoded to UTF-8 the # conversion will fail and the header will remain unchanged. # # This Hash is intentionally left unfrozen and users should feel free to add # values to it that can be accessed by all CSV objects. # - # To add a combo field, the value should be an Array of names. Combo fields + # To add a combo field, the value should be an Array of names. Combo fields # can be nested with other combo fields. # HeaderConverters = { @@ -382,7 +382,7 @@ class CSV } # - # The options used when no overrides are given by calling code. They are: + # The options used when no overrides are given by calling code. They are: # # :col_sep:: "," # :row_sep:: :auto @@ -416,331 +416,337 @@ class CSV quote_empty: true, }.freeze - # - # This method will return a CSV instance, just like CSV::new(), but the - # instance will be cached and returned for all future calls to this method for - # the same +data+ object (tested by Object#object_id()) with the same - # +options+. - # - # If a block is given, the instance is passed to the block and the return - # value becomes the return value of the block. - # - def self.instance(data = $stdout, **options) - # 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 }) + class << self + # + # This method will return a CSV instance, just like CSV::new(), but the + # instance will be cached and returned for all future calls to this method for + # the same +data+ object (tested by Object#object_id()) with the same + # +options+. + # + # If a block is given, the instance is passed to the block and the return + # value becomes the return value of the block. + # + def instance(data = $stdout, **options) + # 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)) + # 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 - - # - # :call-seq: - # filter( **options ) { |row| ... } - # filter( input, **options ) { |row| ... } - # filter( input, output, **options ) { |row| ... } - # - # This method is a convenience for building Unix-like filters for CSV data. - # Each row is yielded to the provided block which can alter it as needed. - # After the block returns, the row is appended to +output+ altered or not. - # - # The +input+ and +output+ arguments can be anything CSV::new() accepts - # (generally String or IO objects). If not given, they default to - # ARGF and $stdout. - # - # The +options+ parameter is also filtered down to CSV::new() after some - # clever key parsing. Any key beginning with :in_ or - # :input_ will have that leading identifier stripped and will only - # be used in the +options+ Hash for the +input+ object. Keys starting with - # :out_ or :output_ affect only +output+. All other keys - # are assigned to both objects. - # - # The :output_row_sep +option+ defaults to - # $INPUT_RECORD_SEPARATOR ($/). - # - def self.filter(input=nil, output=nil, **options) - # parse options for input, output, or both - in_options, out_options = Hash.new, {row_sep: $INPUT_RECORD_SEPARATOR} - options.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 + if block_given? + yield instance # run block, if given, returning result else - in_options[key] = value - out_options[key] = value + instance # or return the instance end end - # build input and output wrappers - input = new(input || ARGF, **in_options) - output = new(output || $stdout, **out_options) - # read, yield, write - input.each do |row| - yield row - output << row + # + # :call-seq: + # filter( **options ) { |row| ... } + # filter( input, **options ) { |row| ... } + # filter( input, output, **options ) { |row| ... } + # + # This method is a convenience for building Unix-like filters for CSV data. + # Each row is yielded to the provided block which can alter it as needed. + # After the block returns, the row is appended to +output+ altered or not. + # + # The +input+ and +output+ arguments can be anything CSV::new() accepts + # (generally String or IO objects). If not given, they default to + # ARGF and $stdout. + # + # The +options+ parameter is also filtered down to CSV::new() after some + # clever key parsing. Any key beginning with :in_ or + # :input_ will have that leading identifier stripped and will only + # be used in the +options+ Hash for the +input+ object. Keys starting with + # :out_ or :output_ affect only +output+. All other keys + # are assigned to both objects. + # + # The :output_row_sep +option+ defaults to + # $INPUT_RECORD_SEPARATOR ($/). + # + def filter(input=nil, output=nil, **options) + # parse options for input, output, or both + in_options, out_options = Hash.new, {row_sep: $INPUT_RECORD_SEPARATOR} + options.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 + # build input and output wrappers + input = new(input || ARGF, **in_options) + output = new(output || $stdout, **out_options) + + # read, yield, write + input.each do |row| + yield row + output << row + end end - end - # - # This method is intended as the primary interface for reading CSV files. You - # pass a +path+ and any +options+ you wish to set for the read. Each row of - # file will be passed to the provided +block+ in turn. - # - # The +options+ parameter can be anything CSV::new() understands. This method - # also understands an additional :encoding parameter that you can use - # to specify the Encoding of the data in the file to be read. You must provide - # this unless your data is in Encoding::default_external(). CSV will use this - # to determine how to parse the data. You may provide a second Encoding to - # have the data transcoded as it is read. For example, - # encoding: "UTF-32BE:UTF-8" would read UTF-32BE data from the file - # but transcode it to UTF-8 before CSV parses it. - # - def self.foreach(path, mode="r", **options, &block) - return to_enum(__method__, path, mode, **options) unless block_given? - open(path, mode, **options) do |csv| - csv.each(&block) + # + # This method is intended as the primary interface for reading CSV files. You + # pass a +path+ and any +options+ you wish to set for the read. Each row of + # file will be passed to the provided +block+ in turn. + # + # The +options+ parameter can be anything CSV::new() understands. This method + # also understands an additional :encoding parameter that you can use + # to specify the Encoding of the data in the file to be read. You must provide + # this unless your data is in Encoding::default_external(). CSV will use this + # to determine how to parse the data. You may provide a second Encoding to + # have the data transcoded as it is read. For example, + # encoding: "UTF-32BE:UTF-8" would read UTF-32BE data from the file + # but transcode it to UTF-8 before CSV parses it. + # + def foreach(path, mode="r", **options, &block) + return to_enum(__method__, path, mode, **options) unless block_given? + open(path, mode, **options) do |csv| + csv.each(&block) + end end - end - # - # :call-seq: - # generate( str, **options ) { |csv| ... } - # generate( **options ) { |csv| ... } - # - # This method wraps a String you provide, or an empty default String, in a - # CSV object which is passed to the provided block. You can use the block to - # append CSV rows to the String and when the block exits, the final String - # will be returned. - # - # Note that a passed String *is* modified by this method. Call dup() before - # passing if you need a new String. - # - # The +options+ parameter can be anything CSV::new() understands. This method - # understands an additional :encoding parameter when not passed a - # String to set the base Encoding for the output. CSV needs this hint if you - # plan to output non-ASCII compatible data. - # - def self.generate(str=nil, **options) - # add a default empty String, if none was given - if str - str = StringIO.new(str) - str.seek(0, IO::SEEK_END) - else - encoding = options[:encoding] + # + # :call-seq: + # generate( str, **options ) { |csv| ... } + # generate( **options ) { |csv| ... } + # + # This method wraps a String you provide, or an empty default String, in a + # CSV object which is passed to the provided block. You can use the block to + # append CSV rows to the String and when the block exits, the final String + # will be returned. + # + # Note that a passed String *is* modified by this method. Call dup() before + # passing if you need a new String. + # + # The +options+ parameter can be anything CSV::new() understands. This method + # understands an additional :encoding parameter when not passed a + # String to set the base Encoding for the output. CSV needs this hint if you + # plan to output non-ASCII compatible data. + # + def generate(str=nil, **options) + # add a default empty String, if none was given + if str + str = StringIO.new(str) + str.seek(0, IO::SEEK_END) + else + encoding = options[:encoding] + str = +"" + str.force_encoding(encoding) if encoding + end + csv = new(str, **options) # wrap + yield csv # yield for appending + csv.string # return final String + end + + # + # This method is a shortcut for converting a single row (Array) into a CSV + # String. + # + # The +options+ parameter can be anything CSV::new() understands. This method + # understands an additional :encoding parameter to set the base + # Encoding for the output. This method will try to guess your Encoding from + # the first non-+nil+ field in +row+, if possible, but you may need to use + # this parameter as a backup plan. + # + # The :row_sep +option+ defaults to $INPUT_RECORD_SEPARATOR + # ($/) when calling this method. + # + def generate_line(row, **options) + options = {row_sep: $INPUT_RECORD_SEPARATOR}.merge(options) str = +"" - str.force_encoding(encoding) if encoding - end - csv = new(str, **options) # wrap - yield csv # yield for appending - csv.string # return final String - end - - # - # This method is a shortcut for converting a single row (Array) into a CSV - # String. - # - # The +options+ parameter can be anything CSV::new() understands. This method - # understands an additional :encoding parameter to set the base - # Encoding for the output. This method will try to guess your Encoding from - # the first non-+nil+ field in +row+, if possible, but you may need to use - # this parameter as a backup plan. - # - # The :row_sep +option+ defaults to $INPUT_RECORD_SEPARATOR - # ($/) when calling this method. - # - def self.generate_line(row, **options) - options = {row_sep: $INPUT_RECORD_SEPARATOR}.merge(options) - str = +"" - if options[:encoding] - str.force_encoding(options[:encoding]) - elsif field = row.find {|f| f.is_a?(String)} - str.force_encoding(field.encoding) - end - (new(str, **options) << row).string - end - - # - # :call-seq: - # open( filename, mode = "rb", **options ) { |faster_csv| ... } - # open( filename, **options ) { |faster_csv| ... } - # open( filename, mode = "rb", **options ) - # open( filename, **options ) - # - # This method opens an IO object, and wraps that with CSV. This is intended - # as the primary interface for writing a CSV file. - # - # You must pass a +filename+ and may optionally add a +mode+ for Ruby's - # open(). You may also pass an optional Hash containing any +options+ - # CSV::new() understands as the final argument. - # - # This method works like Ruby's open() call, in that it will pass a CSV object - # to a provided block and close it when the block terminates, or it will - # return the CSV object when no block is provided. (*Note*: This is different - # from the Ruby 1.8 CSV library which passed rows to the block. Use - # CSV::foreach() for that behavior.) - # - # You must provide a +mode+ with an embedded Encoding designator unless your - # data is in Encoding::default_external(). CSV will check the Encoding of the - # underlying IO object (set by the +mode+ you pass) to determine how to parse - # the data. You may provide a second Encoding to have the data transcoded as - # it is read just as you can with a normal call to IO::open(). For example, - # "rb:UTF-32BE:UTF-8" would read UTF-32BE data from the file but - # transcode it to UTF-8 before CSV parses it. - # - # An opened CSV object will delegate to many IO methods for convenience. You - # may call: - # - # * binmode() - # * binmode?() - # * close() - # * close_read() - # * close_write() - # * closed?() - # * eof() - # * eof?() - # * external_encoding() - # * fcntl() - # * fileno() - # * flock() - # * flush() - # * fsync() - # * internal_encoding() - # * ioctl() - # * isatty() - # * path() - # * pid() - # * pos() - # * pos=() - # * reopen() - # * seek() - # * stat() - # * sync() - # * sync=() - # * tell() - # * to_i() - # * to_io() - # * truncate() - # * tty?() - # - def self.open(filename, mode="r", **options) - # wrap a File opened with the remaining +args+ with no newline - # decorator - file_opts = {universal_newline: false}.merge(options) - - begin - f = File.open(filename, mode, **file_opts) - rescue ArgumentError => e - raise unless /needs binmode/.match?(e.message) and mode == "r" - mode = "rb" - file_opts = {encoding: Encoding.default_external}.merge(file_opts) - retry - end - begin - csv = new(f, **options) - rescue Exception - f.close - raise + if options[:encoding] + str.force_encoding(options[:encoding]) + elsif field = row.find {|f| f.is_a?(String)} + str.force_encoding(field.encoding) + end + (new(str, **options) << row).string end - # handle blocks like Ruby's open(), not like the CSV library - if block_given? + # + # :call-seq: + # open( filename, mode = "rb", **options ) { |faster_csv| ... } + # open( filename, **options ) { |faster_csv| ... } + # open( filename, mode = "rb", **options ) + # open( filename, **options ) + # + # This method opens an IO object, and wraps that with CSV. This is intended + # as the primary interface for writing a CSV file. + # + # You must pass a +filename+ and may optionally add a +mode+ for Ruby's + # open(). You may also pass an optional Hash containing any +options+ + # CSV::new() understands as the final argument. + # + # This method works like Ruby's open() call, in that it will pass a CSV object + # to a provided block and close it when the block terminates, or it will + # return the CSV object when no block is provided. (*Note*: This is different + # from the Ruby 1.8 CSV library which passed rows to the block. Use + # CSV::foreach() for that behavior.) + # + # You must provide a +mode+ with an embedded Encoding designator unless your + # data is in Encoding::default_external(). CSV will check the Encoding of the + # underlying IO object (set by the +mode+ you pass) to determine how to parse + # the data. You may provide a second Encoding to have the data transcoded as + # it is read just as you can with a normal call to IO::open(). For example, + # "rb:UTF-32BE:UTF-8" would read UTF-32BE data from the file but + # transcode it to UTF-8 before CSV parses it. + # + # An opened CSV object will delegate to many IO methods for convenience. You + # may call: + # + # * binmode() + # * binmode?() + # * close() + # * close_read() + # * close_write() + # * closed?() + # * eof() + # * eof?() + # * external_encoding() + # * fcntl() + # * fileno() + # * flock() + # * flush() + # * fsync() + # * internal_encoding() + # * ioctl() + # * isatty() + # * path() + # * pid() + # * pos() + # * pos=() + # * reopen() + # * seek() + # * stat() + # * sync() + # * sync=() + # * tell() + # * to_i() + # * to_io() + # * truncate() + # * tty?() + # + def open(filename, mode="r", **options) + # wrap a File opened with the remaining +args+ with no newline + # decorator + file_opts = {universal_newline: false}.merge(options) + begin - yield csv + f = File.open(filename, mode, **file_opts) + rescue ArgumentError => e + raise unless /needs binmode/.match?(e.message) and mode == "r" + mode = "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 + + # + # :call-seq: + # parse( str, **options ) { |row| ... } + # parse( str, **options ) + # + # This method can be used to easily parse CSV out of a String. You may either + # provide a +block+ which will be called with each row of the String in turn, + # or just use the returned Array of Arrays (when no +block+ is given). + # + # You pass your +str+ to read from, and an optional +options+ containing + # anything CSV::new() understands. + # + def parse(str, **options, &block) + csv = new(str, **options) + + return csv.each(&block) if block_given? + + # slurp contents, if no block is given + begin + csv.read ensure csv.close end - else - csv end - end - # - # :call-seq: - # parse( str, **options ) { |row| ... } - # parse( str, **options ) - # - # This method can be used to easily parse CSV out of a String. You may either - # provide a +block+ which will be called with each row of the String in turn, - # or just use the returned Array of Arrays (when no +block+ is given). - # - # You pass your +str+ to read from, and an optional +options+ containing - # anything CSV::new() understands. - # - def self.parse(*args, **options, &block) - csv = new(*args, **options) - - return csv.each(&block) if block_given? - - # slurp contents, if no block is given - begin - csv.read - ensure - csv.close + # + # This method is a shortcut for converting a single line of a CSV String into + # an Array. Note that if +line+ contains multiple rows, anything beyond the + # first row is ignored. + # + # The +options+ parameter can be anything CSV::new() understands. + # + def parse_line(line, **options) + new(line, **options).shift end - end - # - # This method is a shortcut for converting a single line of a CSV String into - # an Array. Note that if +line+ contains multiple rows, anything beyond the - # first row is ignored. - # - # The +options+ parameter can be anything CSV::new() understands. - # - def self.parse_line(line, **options) - new(line, **options).shift - end + # + # Use to slurp a CSV file into an Array of Arrays. Pass the +path+ to the + # file and any +options+ CSV::new() understands. This method also understands + # an additional :encoding parameter that you can use to specify the + # Encoding of the data in the file to be read. You must provide this unless + # your data is in Encoding::default_external(). CSV will use this to determine + # how to parse the data. You may provide a second Encoding to have the data + # transcoded as it is read. For example, + # encoding: "UTF-32BE:UTF-8" would read UTF-32BE data from the file + # but transcode it to UTF-8 before CSV parses it. + # + def read(path, **options) + open(path, **options) { |csv| csv.read } + end - # - # Use to slurp a CSV file into an Array of Arrays. Pass the +path+ to the - # file and any +options+ CSV::new() understands. This method also understands - # an additional :encoding parameter that you can use to specify the - # Encoding of the data in the file to be read. You must provide this unless - # your data is in Encoding::default_external(). CSV will use this to determine - # how to parse the data. You may provide a second Encoding to have the data - # transcoded as it is read. For example, - # encoding: "UTF-32BE:UTF-8" would read UTF-32BE data from the file - # but transcode it to UTF-8 before CSV parses it. - # - def self.read(*args, **options) - open(*args, **options) { |csv| csv.read } - end + # Alias for CSV::read(). + def readlines(path, **options) + read(path, **options) + end - # Alias for CSV::read(). - def self.readlines(*args, **options) - read(*args, **options) - end - - # - # A shortcut for: - # - # CSV.read( path, { headers: true, - # converters: :numeric, - # header_converters: :symbol }.merge(options) ) - # - def self.table(path, **options) - read( path, **{ headers: true, - converters: :numeric, - header_converters: :symbol }.merge(options) ) + # + # A shortcut for: + # + # CSV.read( path, { headers: true, + # converters: :numeric, + # header_converters: :symbol }.merge(options) ) + # + def table(path, **options) + default_options = { + headers: true, + converters: :numeric, + header_converters: :symbol, + } + options = default_options.merge(options) + read(path, **options) + end end # # This constructor will wrap either a String or IO object passed in +data+ for - # reading and/or writing. In addition to the CSV instance methods, several IO - # methods are delegated. (See CSV::open() for a complete list.) If you pass + # reading and/or writing. In addition to the CSV instance methods, several IO + # methods are delegated. (See CSV::open() for a complete list.) If you pass # a String for +data+, you can later retrieve it (after writing to it, for # example) with CSV.string(). # # Note that a wrapped String will be positioned at the beginning (for - # reading). If you want it at the end (for writing), use CSV::generate(). + # reading). If you want it at the end (for writing), use CSV::generate(). # If you want any other positioning, pass a preset StringIO object instead. # # You may set any reading and/or writing preferences in the +options+ Hash. @@ -750,25 +756,25 @@ class CSV # This String will be transcoded into # the data's Encoding before parsing. # :row_sep:: The String appended to the end of each - # row. This can be set to the special + # row. This can be set to the special # :auto setting, which requests # that CSV automatically discover this - # from the data. Auto-discovery reads + # from the data. Auto-discovery reads # ahead in the data looking for the next # "\r\n", "\n", or - # "\r" sequence. A sequence + # "\r" sequence. A sequence # will be selected even if it occurs in # a quoted field, assuming that you # would have the same line endings - # there. If none of those sequences is + # there. If none of those sequences is # found, +data+ is ARGF, # STDIN, STDOUT, or # STDERR, or the stream is only # available for output, the default # $INPUT_RECORD_SEPARATOR - # ($/) is used. Obviously, - # discovery takes a little time. Set - # manually if speed is important. Also + # ($/) is used. Obviously, + # discovery takes a little time. Set + # manually if speed is important. Also # note that IO objects should be opened # in binary mode on Windows if this # feature will be used as the @@ -780,7 +786,7 @@ class CSV # before parsing. # :quote_char:: The character used to quote fields. # This has to be a single character - # String. This is useful for + # String. This is useful for # application that incorrectly use # ' as the quote character # instead of the correct ". @@ -791,21 +797,21 @@ class CSV # before parsing. # :field_size_limit:: This is a maximum size CSV will read # ahead looking for the closing quote - # for a field. (In truth, it reads to + # for a field. (In truth, it reads to # the first line ending beyond this - # size.) If a quote cannot be found + # size.) If a quote cannot be found # within the limit CSV will raise a # MalformedCSVError, assuming the data - # is faulty. You can use this limit to + # is faulty. You can use this limit to # prevent what are effectively DoS - # attacks on the parser. However, this + # attacks on the parser. However, this # limit can cause a legitimate parse to # fail and thus is set to +nil+, or off, # by default. # :converters:: An Array of names from the Converters # Hash and/or lambdas that handle custom - # conversion. A single converter - # doesn't have to be in an Array. All + # conversion. A single converter + # doesn't have to be in an Array. All # built-in converters try to transcode # fields to UTF-8 before converting. # The conversion will fail if the data @@ -815,7 +821,7 @@ class CSV # unconverted_fields() method will be # added to all returned rows (Array or # CSV::Row) that will return the fields - # as they were before conversion. Note + # as they were before conversion. Note # that :headers supplied by # Array or String were not fields of the # document and thus will have an empty @@ -823,21 +829,21 @@ class CSV # :headers:: If set to :first_row or # +true+, the initial row of the CSV # file will be treated as a row of - # headers. If set to an Array, the + # headers. If set to an Array, the # contents will be used as the headers. # If set to a String, the String is run # through a call of CSV::parse_line() # with the same :col_sep, # :row_sep, and # :quote_char as this instance - # to produce an Array of headers. This + # to produce an Array of headers. This # setting causes CSV#shift() to return # rows as CSV::Row objects instead of # Arrays and CSV#read() to return # CSV::Table objects instead of an Array # of Arrays. # :return_headers:: When +false+, header rows are silently - # swallowed. If set to +true+, header + # swallowed. If set to +true+, header # rows are returned in a CSV::Row object # with identical headers and # fields (save that the fields do not go @@ -848,12 +854,12 @@ class CSV # :header_converters:: Identical in functionality to # :converters save that the # conversions are only made to header - # rows. All built-in converters try to + # rows. All built-in converters try to # transcode headers to UTF-8 before - # converting. The conversion will fail + # converting. The conversion will fail # if the data cannot be transcoded, # leaving the header unchanged. - # :skip_blanks:: When set to a +true+ value, CSV will + # :skip_blanks:: When setting a +true+ value, CSV will # skip over any empty rows. Note that # this setting will not skip rows that # contain column separators, even if @@ -863,9 +869,9 @@ class CSV # using :skip_lines, or # inspecting fields.compact.empty? on # each row. - # :force_quotes:: When set to a +true+ value, CSV will + # :force_quotes:: When setting a +true+ value, CSV will # quote all CSV fields it creates. - # :skip_lines:: When set to an object responding to + # :skip_lines:: When setting an object responding to # match, every line matching # it is considered a comment and ignored # during parsing. When set to a String, @@ -874,17 +880,17 @@ class CSV # a comment. If the passed object does # not respond to match, # ArgumentError is thrown. - # :liberal_parsing:: When set to a +true+ value, CSV will + # :liberal_parsing:: When setting a +true+ value, CSV will # attempt to parse input not conformant # with RFC 4180, such as double quotes # in unquoted fields. # :nil_value:: When set an object, any values of an - # empty field are replaced by the set + # empty field is replaced by the set # object, not nil. - # :empty_value:: When set an object, any values of a + # :empty_value:: When setting an object, any values of a # blank string field is replaced by # the set object. - # :quote_empty:: When set to a +true+ value, CSV will + # :quote_empty:: When setting a +true+ value, CSV will # quote empty values with double quotes. # When +false+, CSV will emit an # empty string for an empty field value. @@ -901,11 +907,11 @@ class CSV # :write_empty_value:: When a String or +nil+ value, # empty value(s) on each line will be # replaced with the specified value. - # :strip:: When set to a +true+ value, CSV will + # :strip:: When setting a +true+ value, CSV will # strip "\t\r\n\f\v" around the values. # If you specify a string instead of # +true+, CSV will strip string. The - # length of string must be 1. + # length of the string must be 1. # # See CSV::DEFAULT_OPTIONS for the default settings. # @@ -939,8 +945,12 @@ class CSV strip: false) raise ArgumentError.new("Cannot parse nil as CSV") if data.nil? - # create the IO object we will read from - @io = data.is_a?(String) ? StringIO.new(data) : data + if data.is_a?(String) + @io = StringIO.new(data) + @io.set_encoding(encoding || data.encoding) + else + @io = data + end @encoding = determine_encoding(encoding, internal_encoding) @base_fields_converter_options = { @@ -992,41 +1002,47 @@ class CSV end # - # The encoded :col_sep used in parsing and writing. See CSV::new - # for details. + # The encoded :col_sep used in parsing and writing. + # See CSV::new for details. # def col_sep parser.column_separator end # - # The encoded :row_sep used in parsing and writing. See CSV::new - # for details. + # The encoded :row_sep used in parsing and writing. + # See CSV::new for details. # def row_sep parser.row_separator end # - # The encoded :quote_char used in parsing and writing. See CSV::new - # for details. + # The encoded :quote_char used in parsing and writing. + # See CSV::new for details. # def quote_char parser.quote_character end - # The limit for field size, if any. See CSV::new for details. + # + # The limit for field size, if any. + # See CSV::new for details. + # def field_size_limit parser.field_size_limit end - # The regex marking a line as a comment. See CSV::new for details + # + # The regex marking a line as a comment. + # See CSV::new for details. + # def skip_lines parser.skip_lines end # - # Returns the current list of converters in effect. See CSV::new for details. + # Returns the current list of converters in effect. See CSV::new for details. # Built-in converters will be returned by name, while others will be returned # as is. # @@ -1036,9 +1052,10 @@ class CSV name ? name.first : converter end end + # - # Returns +true+ if unconverted_fields() to parsed results. See CSV::new - # for details. + # Returns +true+ if unconverted_fields() to parsed results. + # See CSV::new for details. # def unconverted_fields? parser.unconverted_fields? @@ -1046,8 +1063,8 @@ class CSV # # 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. + # yet been read, or the actual headers after they have been read. + # See CSV::new for details. # def headers if @writer @@ -1068,14 +1085,17 @@ class CSV parser.return_headers? end - # Returns +true+ if headers are written in output. See CSV::new for details. + # + # Returns +true+ if headers are written in output. + # See CSV::new for details. + # 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 + # 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 @@ -1201,7 +1221,7 @@ class CSV # # The primary write method for wrapped Strings and IOs, +row+ (an Array or - # CSV::Row) is converted to CSV and appended to the data source. When a + # CSV::Row) is converted to CSV and appended to the data source. When a # CSV::Row is passed, only the row's fields() are appended to the output. # # The data source must be open for writing. @@ -1223,9 +1243,9 @@ class CSV # block that handles a custom conversion. # # If you provide a block that takes one argument, it will be passed the field - # and is expected to return the converted value or the field itself. If your + # and is expected to return the converted value or the field itself. If your # block takes two arguments, it will also be passed a CSV::FieldInfo Struct, - # containing details about the field. Again, the block should return a + # containing details about the field. Again, the block should return a # converted field or the field itself. # def convert(name = nil, &converter) @@ -1377,9 +1397,9 @@ class CSV # # Processes +fields+ with @converters, or @header_converters - # if +headers+ is passed as +true+, returning the converted field set. Any + # if +headers+ is passed as +true+, returning the converted field set. Any # converter that changes the field into something other than a String halts - # the pipeline of conversion for that field. This is primarily an efficiency + # the pipeline of conversion for that field. This is primarily an efficiency # shortcut. # def convert_fields(fields, headers = false) diff --git a/lib/csv/fields_converter.rb b/lib/csv/fields_converter.rb index c2fa5798ff..a751c9ea1d 100644 --- a/lib/csv/fields_converter.rb +++ b/lib/csv/fields_converter.rb @@ -1,8 +1,14 @@ # frozen_string_literal: true class CSV + # Note: Don't use this class directly. This is an internal class. class FieldsConverter include Enumerable + # + # A CSV::FieldsConverter is a data structure for storing the + # fields converter properties to be passed as a parameter + # when parsing a new file (e.g. CSV::Parser.new(@io, parser_options)) + # def initialize(options={}) @converters = [] diff --git a/lib/csv/parser.rb b/lib/csv/parser.rb index 2ef2a28ff3..42145f8923 100644 --- a/lib/csv/parser.rb +++ b/lib/csv/parser.rb @@ -11,10 +11,31 @@ using CSV::DeleteSuffix if CSV.const_defined?(:DeleteSuffix) using CSV::MatchP if CSV.const_defined?(:MatchP) class CSV + # Note: Don't use this class directly. This is an internal class. class Parser + # + # A CSV::Parser is m17n aware. The parser works in the Encoding of the IO + # or String object being read from or written to. Your data is never transcoded + # (unless you ask Ruby to transcode it for you) and will literally be parsed in + # the Encoding it is in. Thus CSV will return Arrays or Rows of Strings in the + # Encoding of your data. This is accomplished by transcoding the parser itself + # into your Encoding. + # + + # Raised when encoding is invalid. class InvalidEncoding < StandardError end + # + # CSV::Scanner receives a CSV output, scans it and return the content. + # It also controls the life cycle of the object with its methods +keep_start+, + # +keep_end+, +keep_back+, +keep_drop+. + # + # Uses StringScanner (the official strscan gem). Strscan provides lexical + # scanning operations on a String. We inherit its object and take advantage + # on the methods. For more information, please visit: + # https://ruby-doc.org/stdlib-2.6.1/libdoc/strscan/rdoc/StringScanner.html + # class Scanner < StringScanner alias_method :scan_all, :scan @@ -38,7 +59,7 @@ class CSV def keep_end start = @keeps.pop - string[start, pos - start] + string.byteslice(start, pos - start) end def keep_back @@ -50,6 +71,18 @@ class CSV end end + # + # CSV::InputsScanner receives IO inputs, encoding and the chunk_size. + # It also controls the life cycle of the object with its methods +keep_start+, + # +keep_end+, +keep_back+, +keep_drop+. + # + # CSV::InputsScanner.scan() tries to match with pattern at the current position. + # If there's a match, the scanner advances the “scan pointer” and returns the matched string. + # Otherwise, the scanner returns nil. + # + # CSV::InputsScanner.rest() returns the “rest” of the string (i.e. everything after the scan pointer). + # If there is no more data (eos? = true), it returns "". + # class InputsScanner def initialize(inputs, encoding, chunk_size: 8192) @inputs = inputs.dup @@ -137,7 +170,7 @@ class CSV def keep_end start, buffer = @keeps.pop - keep = @scanner.string[start, @scanner.pos - start] + keep = @scanner.string.byteslice(start, @scanner.pos - start) if buffer buffer << keep keep = buffer @@ -192,7 +225,7 @@ class CSV input = @inputs.first case input when StringIO - string = input.string + string = input.read raise InvalidEncoding unless string.valid_encoding? @scanner = StringScanner.new(string) @inputs.shift @@ -319,6 +352,7 @@ class CSV end private + # A set of tasks to prepare the file in order to parse it def prepare prepare_variable prepare_quote_character @@ -447,7 +481,13 @@ class CSV end def prepare_separators - @column_separator = @options[:column_separator].to_s.encode(@encoding) + column_separator = @options[:column_separator] + @column_separator = column_separator.to_s.encode(@encoding) + if @column_separator.size < 1 + message = ":col_sep must be 1 or more characters: " + message += column_separator.inspect + raise ArgumentError, message + end @row_separator = resolve_row_separator(@options[:row_separator]).encode(@encoding) @@ -534,7 +574,9 @@ class CSV cr = "\r".encode(@encoding) lf = "\n".encode(@encoding) if @input.is_a?(StringIO) - separator = detect_row_separator(@input.string, cr, lf) + pos = @input.pos + separator = detect_row_separator(@input.read, cr, lf) + @input.seek(pos) elsif @input.respond_to?(:gets) if @input.is_a?(File) chunk_size = 32 * 1024 @@ -651,7 +693,9 @@ class CSV return false if @quote_character.nil? if @input.is_a?(StringIO) - sample = @input.string + pos = @input.pos + sample = @input.read + @input.seek(pos) else return false if @samples.empty? sample = @samples.first @@ -684,7 +728,7 @@ class CSV UnoptimizedStringIO.new(sample) end if @input.is_a?(StringIO) - inputs << UnoptimizedStringIO.new(@input.string) + inputs << UnoptimizedStringIO.new(@input.read) else inputs << @input end @@ -697,7 +741,7 @@ class CSV def build_scanner string = nil if @samples.empty? and @input.is_a?(StringIO) - string = @input.string + string = @input.read elsif @samples.size == 1 and @input.respond_to?(:eof?) and @input.eof? string = @samples[0] end diff --git a/lib/csv/row.rb b/lib/csv/row.rb index 1e1f27587b..4aa0f30911 100644 --- a/lib/csv/row.rb +++ b/lib/csv/row.rb @@ -4,7 +4,7 @@ require "forwardable" class CSV # - # A CSV::Row is part Array and part Hash. It retains an order for the fields + # A CSV::Row is part Array and part Hash. It retains an order for the fields # and allows duplicates just as an Array would, but also allows you to access # fields by name just as you could if they were in a Hash. # @@ -13,13 +13,13 @@ class CSV # class Row # - # Construct a new CSV::Row from +headers+ and +fields+, which are expected - # to be Arrays. If one Array is shorter than the other, it will be padded + # Constructs a new CSV::Row from +headers+ and +fields+, which are expected + # to be Arrays. If one Array is shorter than the other, it will be padded # with +nil+ objects. # # The optional +header_row+ parameter can be set to +true+ to indicate, via # CSV::Row.header_row?() and CSV::Row.field_row?(), that this is a header - # row. Otherwise, the row is assumes to be a field row. + # row. Otherwise, the row assumes to be a field row. # # A CSV::Row object supports the following Array methods through delegation: # @@ -74,11 +74,11 @@ class CSV # field( header, offset ) # field( index ) # - # This method will return the field value by +header+ or +index+. If a field + # This method will return the field value by +header+ or +index+. If a field # is not found, +nil+ is returned. # # When provided, +offset+ ensures that a header match occurs on or later - # than the +offset+ index. You can use this to find duplicate headers, + # than the +offset+ index. You can use this to find duplicate headers, # without resorting to hard-coding exact indices. # def field(header_or_index, minimum_index = 0) @@ -142,7 +142,7 @@ class CSV # assigns the +value+. # # Assigning past the end of the row with an index will set all pairs between - # to [nil, nil]. Assigning to an unused header appends the new + # to [nil, nil]. Assigning to an unused header appends the new # pair. # def []=(*args) @@ -172,8 +172,8 @@ class CSV # <<( header_and_field_hash ) # # If a two-element Array is provided, it is assumed to be a header and field - # and the pair is appended. A Hash works the same way with the key being - # the header and the value being the field. Anything else is assumed to be + # and the pair is appended. A Hash works the same way with the key being + # the header and the value being the field. Anything else is assumed to be # a lone field which is appended with a +nil+ header. # # This method returns the row for chaining. @@ -191,7 +191,7 @@ class CSV end # - # A shortcut for appending multiple fields. Equivalent to: + # A shortcut for appending multiple fields. Equivalent to: # # args.each { |arg| csv_row << arg } # @@ -209,8 +209,8 @@ class CSV # delete( header, offset ) # delete( index ) # - # Used to remove a pair from the row by +header+ or +index+. The pair is - # located as described in CSV::Row.field(). The deleted pair is returned, + # Removes a pair from the row by +header+ or +index+. The pair is + # located as described in CSV::Row.field(). The deleted pair is returned, # or +nil+ if a pair could not be found. # def delete(header_or_index, minimum_index = 0) @@ -325,7 +325,7 @@ class CSV end # - # Collapses the row into a simple Hash. Be warned that this discards field + # Collapses the row into a simple Hash. Be warned that this discards field # order and clobbers duplicate fields. # def to_h @@ -340,7 +340,7 @@ class CSV alias_method :to_ary, :to_a # - # Returns the row as a CSV String. Headers are not used. Equivalent to: + # Returns the row as a CSV String. Headers are not used. Equivalent to: # # csv_row.fields.to_csv( options ) # @@ -367,7 +367,9 @@ class CSV end end + # # A summary of fields, by header, in an ASCII compatible String. + # def inspect str = ["#<", self.class.to_s] each do |header, field| diff --git a/lib/csv/table.rb b/lib/csv/table.rb index 29b188a6d7..e6c1ee11fa 100644 --- a/lib/csv/table.rb +++ b/lib/csv/table.rb @@ -5,7 +5,7 @@ require "forwardable" class CSV # # A CSV::Table is a two-dimensional data structure for representing CSV - # documents. Tables allow you to work with the data by row or column, + # documents. Tables allow you to work with the data by row or column, # manipulate the data, and even convert the results back to CSV, if needed. # # All tables returned by CSV will be constructed from this class, if header @@ -13,8 +13,8 @@ class CSV # class Table # - # Construct a new CSV::Table from +array_of_rows+, which are expected - # to be CSV::Row objects. All rows are assumed to have the same headers. + # Constructs a new CSV::Table from +array_of_rows+, which are expected + # to be CSV::Row objects. All rows are assumed to have the same headers. # # The optional +headers+ parameter can be set to Array of headers. # If headers aren't set, headers are fetched from CSV::Row objects. @@ -55,11 +55,11 @@ class CSV def_delegators :@table, :empty?, :length, :size # - # Returns a duplicate table object, in column mode. This is handy for + # Returns a duplicate table object, in column mode. This is handy for # chaining in a single call without changing the table mode, but be aware # that this method can consume a fair amount of memory for bigger data sets. # - # This method returns the duplicate table for chaining. Don't chain + # This method returns the duplicate table for chaining. Don't chain # destructive methods (like []=()) this way though, since you are working # with a duplicate. # @@ -68,7 +68,7 @@ class CSV end # - # Switches the mode of this table to column mode. All calls to indexing and + # Switches the mode of this table to column mode. All calls to indexing and # iteration methods will work with columns until the mode is changed again. # # This method returns the table and is safe to chain. @@ -80,7 +80,7 @@ class CSV end # - # Returns a duplicate table object, in mixed mode. This is handy for + # Returns a duplicate table object, in mixed mode. This is handy for # chaining in a single call without changing the table mode, but be aware # that this method can consume a fair amount of memory for bigger data sets. # @@ -93,9 +93,9 @@ class CSV end # - # Switches the mode of this table to mixed mode. All calls to indexing and + # Switches the mode of this table to mixed mode. All calls to indexing and # iteration methods will use the default intelligent indexing system until - # the mode is changed again. In mixed mode an index is assumed to be a row + # the mode is changed again. In mixed mode an index is assumed to be a row # reference while anything else is assumed to be column access by headers. # # This method returns the table and is safe to chain. @@ -120,7 +120,7 @@ class CSV end # - # Switches the mode of this table to row mode. All calls to indexing and + # Switches the mode of this table to row mode. All calls to indexing and # iteration methods will work with rows until the mode is changed again. # # This method returns the table and is safe to chain. @@ -146,7 +146,7 @@ class CSV # # In the default mixed mode, this method returns rows for index access and - # columns for header access. You can force the index association by first + # columns for header access. You can force the index association by first # calling by_col!() or by_row!(). # # Columns are returned as an Array of values. Altering that Array has no @@ -163,18 +163,18 @@ class CSV # # In the default mixed mode, this method assigns rows for index access and - # columns for header access. You can force the index association by first + # columns for header access. You can force the index association by first # calling by_col!() or by_row!(). # # Rows may be set to an Array of values (which will inherit the table's # headers()) or a CSV::Row. # # Columns may be set to a single value, which is copied to each row of the - # column, or an Array of values. Arrays of values are assigned to rows top - # to bottom in row major order. Excess values are ignored and if the Array + # column, or an Array of values. Arrays of values are assigned to rows top + # to bottom in row major order. Excess values are ignored and if the Array # does not have a value for each row the extra rows will receive a +nil+. # - # Assigning to an existing column or row clobbers the data. Assigning to + # Assigning to an existing column or row clobbers the data. Assigning to # new columns creates them at the right end of the table. # def []=(index_or_header, value) @@ -212,9 +212,9 @@ class CSV # # The mixed mode default is to treat a list of indices as row access, - # returning the rows indicated. Anything else is considered columnar - # access. For columnar access, the return set has an Array for each row - # with the values indicated by the headers in each Array. You can force + # returning the rows indicated. Anything else is considered columnar + # access. For columnar access, the return set has an Array for each row + # with the values indicated by the headers in each Array. You can force # column or row mode using by_col!() or by_row!(). # # You cannot mix column and row access. @@ -234,7 +234,7 @@ class CSV end # - # Adds a new row to the bottom end of this table. You can provide an Array, + # Adds a new row to the bottom end of this table. You can provide an Array, # which will be converted to a CSV::Row (inheriting the table's headers()), # or a CSV::Row. # @@ -251,7 +251,7 @@ class CSV end # - # A shortcut for appending multiple rows. Equivalent to: + # A shortcut for appending multiple rows. Equivalent to: # # rows.each { |row| self << row } # @@ -264,9 +264,9 @@ class CSV end # - # Removes and returns the indicated columns or rows. In the default mixed + # Removes and returns the indicated columns or rows. In the default mixed # mode indices refer to rows and everything else is assumed to be a column - # headers. Use by_col!() or by_row!() to force the lookup. + # headers. Use by_col!() or by_row!() to force the lookup. # def delete(*indexes_or_headers) if indexes_or_headers.empty? @@ -293,9 +293,9 @@ class CSV end # - # Removes any column or row for which the block returns +true+. In the + # Removes any column or row for which the block returns +true+. In the # default mixed mode or row mode, iteration is the standard row major - # walking of rows. In column mode, iteration will +yield+ two element + # walking of rows. In column mode, iteration will +yield+ two element # tuples containing the column name and an Array of values for that column. # # This method returns the table for chaining. @@ -321,7 +321,7 @@ class CSV # # In the default mixed mode or row mode, iteration is the standard row major - # walking of rows. In column mode, iteration will +yield+ two element + # walking of rows. In column mode, iteration will +yield+ two element # tuples containing the column name and an Array of values for that column. # # This method returns the table for chaining. @@ -347,7 +347,7 @@ class CSV end # - # Returns the table as an Array of Arrays. Headers will be the first row, + # Returns the table as an Array of Arrays. Headers will be the first row, # then all of the field rows will follow. # def to_a @@ -360,7 +360,7 @@ class CSV end # - # Returns the table as a complete CSV String. Headers will be listed first, + # Returns the table as a complete CSV String. Headers will be listed first, # then all of the field rows. # # This method assumes you want the Table.headers(), unless you explicitly diff --git a/lib/csv/version.rb b/lib/csv/version.rb index ce55373f02..072400fe01 100644 --- a/lib/csv/version.rb +++ b/lib/csv/version.rb @@ -2,5 +2,5 @@ class CSV # The version of the installed library. - VERSION = "3.1.1" + VERSION = "3.1.2" end diff --git a/lib/csv/writer.rb b/lib/csv/writer.rb index 1682ac03ea..9243d23641 100644 --- a/lib/csv/writer.rb +++ b/lib/csv/writer.rb @@ -6,7 +6,12 @@ require_relative "row" using CSV::MatchP if CSV.const_defined?(:MatchP) class CSV + # Note: Don't use this class directly. This is an internal class. class Writer + # + # A CSV::Writer receives an output, prepares the header, format and output. + # It allows us to write new rows in the object and rewind it. + # attr_reader :lineno attr_reader :headers @@ -22,6 +27,9 @@ class CSV @fields_converter = @options[:fields_converter] end + # + # Adds a new row + # def <<(row) case row when Row @@ -47,6 +55,9 @@ class CSV self end + # + # Winds back to the beginning + # def rewind @lineno = 0 @headers = nil if @options[:headers].nil? diff --git a/test/csv/parse/test_general.rb b/test/csv/parse/test_general.rb index f340921854..655bb26560 100644 --- a/test/csv/parse/test_general.rb +++ b/test/csv/parse/test_general.rb @@ -233,11 +233,21 @@ line,5,jkl assert_equal([["a"]], CSV.parse("a\r\n")) end + def test_seeked_string_io + input_with_bom = StringIO.new("\ufeffあ,い,う\r\na,b,c\r\n") + input_with_bom.read(3) + assert_equal([ + ["あ", "い", "う"], + ["a", "b", "c"], + ], + CSV.new(input_with_bom).each.to_a) + end + private - def assert_parse_errors_out(*args, **options) + def assert_parse_errors_out(data, **options) assert_raise(CSV::MalformedCSVError) do Timeout.timeout(0.2) do - CSV.parse(*args, **options) + CSV.parse(data, **options) fail("Parse didn't error out") end end diff --git a/test/csv/parse/test_header.rb b/test/csv/parse/test_header.rb index 61346c2aac..481c5107c6 100644 --- a/test/csv/parse/test_header.rb +++ b/test/csv/parse/test_header.rb @@ -312,12 +312,12 @@ A end def test_parse_empty - assert_equal(CSV::Table.new([], **{}), + assert_equal(CSV::Table.new([]), CSV.parse("", headers: true)) end def test_parse_empty_line - assert_equal(CSV::Table.new([], **{}), + assert_equal(CSV::Table.new([]), CSV.parse("\n", headers: true)) end diff --git a/test/csv/parse/test_rewind.rb b/test/csv/parse/test_rewind.rb index 43fd8da159..0aa403b756 100644 --- a/test/csv/parse/test_rewind.rb +++ b/test/csv/parse/test_rewind.rb @@ -6,7 +6,7 @@ require_relative "../helper" class TestCSVParseRewind < Test::Unit::TestCase extend DifferentOFS - def parse(data, options={}) + def parse(data, **options) csv = CSV.new(data, **options) records = csv.to_a csv.rewind diff --git a/test/csv/test_encodings.rb b/test/csv/test_encodings.rb index 151ce7048c..acee03db45 100755 --- a/test/csv/test_encodings.rb +++ b/test/csv/test_encodings.rb @@ -268,11 +268,11 @@ class TestCSVEncodings < Test::Unit::TestCase private - def assert_parses(fields, encoding, options = { }) + def assert_parses(fields, encoding, **options) encoding = Encoding.find(encoding) unless encoding.is_a? Encoding orig_fields = fields fields = encode_ary(fields, encoding) - data = ary_to_data(fields, options) + data = ary_to_data(fields, **options) parsed = CSV.parse(data, **options) assert_equal(fields, parsed) parsed.flatten.each_with_index do |field, i| @@ -285,7 +285,9 @@ class TestCSVEncodings < Test::Unit::TestCase end end begin - CSV.open(@temp_csv_path, "rb:#{encoding}:#{__ENCODING__}", **options) do |csv| + CSV.open(@temp_csv_path, + "rb:#{encoding}:#{__ENCODING__}", + **options) do |csv| csv.each_with_index do |row, i| assert_equal(orig_fields[i], row) end @@ -315,7 +317,7 @@ class TestCSVEncodings < Test::Unit::TestCase ary.map { |row| row.map { |field| field.encode(encoding) } } end - def ary_to_data(ary, options = { }) + def ary_to_data(ary, **options) encoding = ary.flatten.first.encoding quote_char = (options[:quote_char] || '"').encode(encoding) col_sep = (options[:col_sep] || ",").encode(encoding) @@ -327,9 +329,9 @@ class TestCSVEncodings < Test::Unit::TestCase }.join('').encode(encoding) end - def encode_for_tests(data, options = { }) - yield ary_to_data(encode_ary(data, "UTF-8"), options) - yield ary_to_data(encode_ary(data, "UTF-16BE"), options) + def encode_for_tests(data, **options) + yield ary_to_data(encode_ary(data, "UTF-8"), **options) + yield ary_to_data(encode_ary(data, "UTF-16BE"), **options) end def each_encoding diff --git a/test/csv/test_features.rb b/test/csv/test_features.rb index 306b880f6f..d6eb2dc13b 100755 --- a/test/csv/test_features.rb +++ b/test/csv/test_features.rb @@ -52,6 +52,20 @@ line,4,jkl assert_equal([",,,", nil], CSV.parse_line(",,,;", col_sep: ";")) end + def test_col_sep_nil + assert_raise_with_message(ArgumentError, + ":col_sep must be 1 or more characters: nil") do + CSV.parse(@sample_data, col_sep: nil) + end + end + + def test_col_sep_empty + assert_raise_with_message(ArgumentError, + ":col_sep must be 1 or more characters: \"\"") do + CSV.parse(@sample_data, col_sep: "") + end + end + def test_row_sep error = assert_raise(CSV::MalformedCSVError) do CSV.parse_line("1,2,3\n,4,5\r\n", row_sep: "\r\n") @@ -110,10 +124,10 @@ line,4,jkl def test_line lines = [ - %Q(abc,def\n), - %Q(abc,"d\nef"\n), - %Q(abc,"d\r\nef"\n), - %Q(abc,"d\ref") + %Q(\u{3000}abc,def\n), + %Q(\u{3000}abc,"d\nef"\n), + %Q(\u{3000}abc,"d\r\nef"\n), + %Q(\u{3000}abc,"d\ref") ] csv = CSV.new(lines.join('')) lines.each do |line| diff --git a/test/csv/write/test_general.rb b/test/csv/write/test_general.rb index c879f54e74..d157b74ba1 100644 --- a/test/csv/write/test_general.rb +++ b/test/csv/write/test_general.rb @@ -205,6 +205,32 @@ module TestCSVWriteGeneral assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), generate_line(row)) end + + def test_encoding_with_default_internal + with_default_internal(Encoding::UTF_8) do + row = ["あ", "い", "う"].collect {|field| field.encode("EUC-JP")} + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), + generate_line(row, encoding: Encoding::EUC_JP)) + end + end + + def test_with_default_internal + with_default_internal(Encoding::UTF_8) do + row = ["あ", "い", "う"].collect {|field| field.encode("EUC-JP")} + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), + generate_line(row)) + end + end + + def with_default_internal(encoding) + original = Encoding.default_internal + begin + Encoding.default_internal = encoding + yield + ensure + Encoding.default_internal = original + end + end end class TestCSVWriteGeneralGenerateLine < Test::Unit::TestCase