csv 3.1.3 → 3.1.8

data/doc/csv/options/generating/write_nil_value.rdoc

@@ -0,0 +1,14 @@
+====== Option +write_nil_value+
+
+Specifies the object that is to be substituted for each +nil+-valued field.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:write_nil_value) # => nil
+
+Without the option:
+  str = CSV.generate_line(['a', nil, 'c', nil])
+  str # => "a,,c,\n"
+
+With the option:
+  str = CSV.generate_line(['a', nil, 'c', nil], write_nil_value: "x")
+  str # => "a,x,c,x\n"

data/doc/csv/options/parsing/converters.rdoc

@@ -0,0 +1,46 @@
+====== Option +converters+
+
+Specifies converters to be used in parsing fields.
+See {Field Converters}[#class-CSV-label-Field+Converters]
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:converters) # => nil
+
+The value may be a field converter name
+(see {Stored Converters}[#class-CSV-label-Stored+Converters]):
+  str = '1,2,3'
+  # Without a converter
+  array = CSV.parse_line(str)
+  array # => ["1", "2", "3"]
+  # With built-in converter :integer
+  array = CSV.parse_line(str, converters: :integer)
+  array # => [1, 2, 3]
+
+The value may be a converter list
+(see {Converter Lists}[#class-CSV-label-Converter+Lists]):
+  str = '1,3.14159'
+  # Without converters
+  array = CSV.parse_line(str)
+  array # => ["1", "3.14159"]
+  # With built-in converters
+  array = CSV.parse_line(str, converters: [:integer, :float])
+  array # => [1, 3.14159]
+
+The value may be a \Proc custom converter:
+(see {Custom Field Converters}[#class-CSV-label-Custom+Field+Converters]):
+  str = ' foo  ,  bar  ,  baz  '
+  # Without a converter
+  array = CSV.parse_line(str)
+  array # => [" foo  ", "  bar  ", "  baz  "]
+  # With a custom converter
+  array = CSV.parse_line(str, converters: proc {|field| field.strip })
+  array # => ["foo", "bar", "baz"]
+
+See also {Custom Field Converters}[#class-CSV-label-Custom+Field+Converters]
+
+---
+
+Raises an exception if the converter is not a converter name or a \Proc:
+  str = 'foo,0'
+  # Raises NoMethodError (undefined method `arity' for nil:NilClass)
+  CSV.parse(str, converters: :foo)

data/doc/csv/options/parsing/empty_value.rdoc

@@ -0,0 +1,13 @@
+====== Option +empty_value+
+
+Specifies the object that is to be substituted
+for each field that has an empty \String.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:empty_value) # => "" (empty string)
+
+With the default, <tt>""</tt>:
+  CSV.parse_line('a,"",b,"",c') # => ["a", "", "b", "", "c"]
+
+With a different object:
+  CSV.parse_line('a,"",b,"",c', empty_value: 'x') # => ["a", "x", "b", "x", "c"]

data/doc/csv/options/parsing/field_size_limit.rdoc

@@ -0,0 +1,39 @@
+====== Option +field_size_limit+
+
+Specifies the \Integer field size limit.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:field_size_limit) # => nil
+
+This is a maximum size CSV will read ahead looking for the closing quote for a field.
+(In truth, it reads to the first line ending beyond this 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 prevent what are effectively DoS attacks on the parser.
+However, this limit can cause a legitimate parse to fail;
+therefore the default value is +nil+ (no limit).
+
+For the examples in this section:
+  str = <<~EOT
+    "a","b"
+    "
+    2345
+    ",""
+  EOT
+  str # => "\"a\",\"b\"\n\"\n2345\n\",\"\"\n"
+
+Using the default +nil+:
+  ary = CSV.parse(str)
+  ary # => [["a", "b"], ["\n2345\n", ""]]
+
+Using <tt>50</tt>:
+  field_size_limit = 50
+  ary = CSV.parse(str, field_size_limit: field_size_limit)
+  ary # => [["a", "b"], ["\n2345\n", ""]]
+
+---
+
+Raises an exception if a field is too long:
+  big_str = "123456789\n" * 1024
+  # Raises CSV::MalformedCSVError (Field size exceeded in line 1.)
+  CSV.parse('valid,fields,"' + big_str + '"', field_size_limit: 2048)

data/doc/csv/options/parsing/header_converters.rdoc

@@ -0,0 +1,43 @@
+====== Option +header_converters+
+
+Specifies converters to be used in parsing headers.
+See {Header Converters}[#class-CSV-label-Header+Converters]
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:header_converters) # => nil
+
+Identical in functionality to option {converters}[#class-CSV-label-Option+converters]
+except that:
+- The converters apply only to the header row.
+- The built-in header converters are +:downcase+ and +:symbol+.
+
+This section assumes prior execution of:
+  str = <<-EOT
+  Name,Value
+  foo,0
+  bar,1
+  baz,2
+  EOT
+  # With no header converter
+  table = CSV.parse(str, headers: true)
+  table.headers # => ["Name", "Value"]
+
+The value may be a header converter name
+(see {Stored Converters}[#class-CSV-label-Stored+Converters]):
+  table = CSV.parse(str, headers: true, header_converters: :downcase)
+  table.headers # => ["name", "value"]
+
+The value may be a converter list
+(see {Converter Lists}[#class-CSV-label-Converter+Lists]):
+  header_converters = [:downcase, :symbol]
+  table = CSV.parse(str, headers: true, header_converters: header_converters)
+  table.headers # => [:name, :value]
+
+The value may be a \Proc custom converter
+(see {Custom Header Converters}[#class-CSV-label-Custom+Header+Converters]):
+  upcase_converter = proc {|field| field.upcase }
+  table = CSV.parse(str, headers: true, header_converters: upcase_converter)
+  table.headers # => ["NAME", "VALUE"]
+
+See also {Custom Header Converters}[#class-CSV-label-Custom+Header+Converters]
+

data/doc/csv/options/parsing/headers.rdoc

@@ -0,0 +1,63 @@
+====== Option +headers+
+
+Specifies a boolean, \Symbol, \Array, or \String to be used
+to define column headers.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:headers) # => false
+
+---
+
+Without +headers+:
+  str = <<-EOT
+  Name,Count
+  foo,0
+  bar,1
+  bax,2
+  EOT
+  csv = CSV.new(str)
+  csv # => #<CSV io_type:StringIO encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\"">
+  csv.headers # => nil
+  csv.shift # => ["Name", "Count"]
+
+---
+
+If set to +true+ or the \Symbol +:first_row+,
+the first row of the data is treated as a row of headers:
+  str = <<-EOT
+  Name,Count
+  foo,0
+  bar,1
+  bax,2
+  EOT
+  csv = CSV.new(str, headers: true)
+  csv # => #<CSV io_type:StringIO encoding:UTF-8 lineno:2 col_sep:"," row_sep:"\n" quote_char:"\"" headers:["Name", "Count"]>
+  csv.headers # => ["Name", "Count"]
+  csv.shift # => #<CSV::Row "Name":"bar" "Count":"1">
+
+---
+
+If set to an \Array, the \Array elements are treated as headers:
+  str = <<-EOT
+  foo,0
+  bar,1
+  bax,2
+  EOT
+  csv = CSV.new(str, headers: ['Name', 'Count'])
+  csv
+  csv.headers # => ["Name", "Count"]
+  csv.shift # => #<CSV::Row "Name":"bar" "Count":"1">
+
+---
+
+If set to a \String +str+, method <tt>CSV::parse_line(str, options)</tt> is called
+with the current +options+, and the returned \Array is treated as headers:
+  str = <<-EOT
+  foo,0
+  bar,1
+  bax,2
+  EOT
+  csv = CSV.new(str, headers: 'Name,Count')
+  csv
+  csv.headers # => ["Name", "Count"]
+  csv.shift # => #<CSV::Row "Name":"bar" "Count":"1">

data/doc/csv/options/parsing/liberal_parsing.rdoc

@@ -0,0 +1,19 @@
+====== Option +liberal_parsing+
+
+Specifies the boolean value that determines whether
+CSV will attempt to parse input not conformant with RFC 4180,
+such as double quotes in unquoted fields.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:liberal_parsing) # => false
+
+For examples in this section:
+  str = 'is,this "three, or four",fields'
+
+Without +liberal_parsing+:
+  # Raises CSV::MalformedCSVError (Illegal quoting in str 1.)
+  CSV.parse_line(str)
+
+With +liberal_parsing+:
+  ary = CSV.parse_line(str, liberal_parsing: true)
+  ary # => ["is", "this \"three", " or four\"", "fields"]

data/doc/csv/options/parsing/nil_value.rdoc

@@ -0,0 +1,12 @@
+====== Option +nil_value+
+
+Specifies the object that is to be substituted for each null (no-text) field.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:nil_value) # => nil
+
+With the default, +nil+:
+  CSV.parse_line('a,,b,,c') # => ["a", nil, "b", nil, "c"]
+
+With a different object:
+  CSV.parse_line('a,,b,,c', nil_value: 0) # => ["a", 0, "b", 0, "c"]

data/doc/csv/options/parsing/return_headers.rdoc

@@ -0,0 +1,22 @@
+====== Option +return_headers+
+
+Specifies the boolean that determines whether method #shift
+returns or ignores the header row.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:return_headers) # => false
+
+Examples:
+  str = <<-EOT
+  Name,Count
+  foo,0
+  bar,1
+  bax,2
+  EOT
+  # Without return_headers first row is str.
+  csv = CSV.new(str, headers: true)
+  csv.shift # => #<CSV::Row "Name":"foo" "Count":"0">
+  # With return_headers first row is headers.
+  csv = CSV.new(str, headers: true, return_headers: true)
+  csv.shift # => #<CSV::Row "Name":"Name" "Count":"Count">
+

data/doc/csv/options/parsing/skip_blanks.rdoc

@@ -0,0 +1,31 @@
+====== Option +skip_blanks+
+
+Specifies a boolean that determines whether blank lines in the input will be ignored;
+a line that contains a column separator is not considered to be blank.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:skip_blanks) # => false
+
+See also option {skiplines}[#class-CSV-label-Option+skip_lines].
+
+For examples in this section:
+  str = <<-EOT
+  foo,0
+
+  bar,1
+  baz,2
+
+  ,
+  EOT
+
+Using the default, +false+:
+  ary = CSV.parse(str)
+  ary # => [["foo", "0"], [], ["bar", "1"], ["baz", "2"], [], [nil, nil]]
+
+Using +true+:
+  ary = CSV.parse(str, skip_blanks: true)
+  ary # => [["foo", "0"], ["bar", "1"], ["baz", "2"], [nil, nil]]
+
+Using a truthy value:
+  ary = CSV.parse(str, skip_blanks: :foo)
+  ary # => [["foo", "0"], ["bar", "1"], ["baz", "2"], [nil, nil]]

data/doc/csv/options/parsing/skip_lines.rdoc

@@ -0,0 +1,37 @@
+====== Option +skip_lines+
+
+Specifies an object to use in identifying comment lines in the input that are to be ignored:
+* If a \Regexp, ignores lines that match it.
+* If a \String, converts it to a \Regexp, ignores lines that match it.
+* If +nil+, no lines are considered to be comments.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:skip_lines) # => nil
+
+For examples in this section:
+  str = <<-EOT
+  # Comment
+  foo,0
+  bar,1
+  baz,2
+  # Another comment
+  EOT
+  str # => "# Comment\nfoo,0\nbar,1\nbaz,2\n# Another comment\n"
+
+Using the default, +nil+:
+  ary = CSV.parse(str)
+  ary # => [["# Comment"], ["foo", "0"], ["bar", "1"], ["baz", "2"], ["# Another comment"]]
+
+Using a \Regexp:
+  ary = CSV.parse(str, skip_lines: /^#/)
+  ary # => [["foo", "0"], ["bar", "1"], ["baz", "2"]]
+
+Using a \String:
+  ary = CSV.parse(str, skip_lines: '#')
+  ary # => [["foo", "0"], ["bar", "1"], ["baz", "2"]]
+
+---
+
+Raises an exception if given an object that is not a \Regexp, a \String, or +nil+:
+  # Raises ArgumentError (:skip_lines has to respond to #match: 0)
+  CSV.parse(str, skip_lines: 0)

data/doc/csv/options/parsing/strip.rdoc

@@ -0,0 +1,15 @@
+====== Option +strip+
+
+Specifies the boolean value that determines whether
+whitespace is stripped from each input field.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:strip) # => false
+
+With default value +false+:
+  ary = CSV.parse_line(' a , b ')
+  ary # => [" a ", " b "]
+
+With value +true+:
+  ary = CSV.parse_line(' a , b ', strip: true)
+  ary # => ["a", "b"]

data/doc/csv/options/parsing/unconverted_fields.rdoc

@@ -0,0 +1,27 @@
+====== Option +unconverted_fields+
+
+Specifies the boolean that determines whether unconverted field values are to be available.
+
+Default value:
+  CSV::DEFAULT_OPTIONS.fetch(:unconverted_fields) # => nil
+
+The unconverted field values are those found in the source data,
+prior to any conversions performed via option +converters+.
+
+When option +unconverted_fields+ is +true+,
+each returned row (\Array or \CSV::Row) has an added method,
++unconverted_fields+, that returns the unconverted field values:
+  str = <<-EOT
+  foo,0
+  bar,1
+  baz,2
+  EOT
+  # Without unconverted_fields
+  csv = CSV.parse(str, converters: :integer)
+  csv # => [["foo", 0], ["bar", 1], ["baz", 2]]
+  csv.first.respond_to?(:unconverted_fields) # => false
+  # With unconverted_fields
+  csv = CSV.parse(str, converters: :integer, unconverted_fields: true)
+  csv # => [["foo", 0], ["bar", 1], ["baz", 2]]
+  csv.first.respond_to?(:unconverted_fields) # => true
+  csv.first.unconverted_fields # => ["foo", "0"]

data/doc/csv/recipes/filtering.rdoc

@@ -0,0 +1,158 @@
+== Recipes for Filtering \CSV
+
+These recipes are specific code examples for specific \CSV filtering tasks.
+
+For other recipes, see {Recipes for CSV}[./recipes_rdoc.html].
+
+All code snippets on this page assume that the following has been executed:
+  require 'csv'
+
+=== Contents
+
+- {Source and Output Formats}[#label-Source+and+Output+Formats]
+  - {Filtering String to String}[#label-Filtering+String+to+String]
+    - {Recipe: Filter String to String with Headers}[#label-Recipe-3A+Filter+String+to+String+with+Headers]
+    - {Recipe: Filter String to String Without Headers}[#label-Recipe-3A+Filter+String+to+String+Without+Headers]
+  - {Filtering String to IO Stream}[#label-Filtering+String+to+IO+Stream]
+    - {Recipe: Filter String to IO Stream with Headers}[#label-Recipe-3A+Filter+String+to+IO+Stream+with+Headers]
+    - {Recipe: Filter String to IO Stream Without Headers}[#label-Recipe-3A+Filter+String+to+IO+Stream+Without+Headers]
+  - {Filtering IO Stream to String}[#label-Filtering+IO+Stream+to+String]
+    - {Recipe: Filter IO Stream to String with Headers}[#label-Recipe-3A+Filter+IO+Stream+to+String+with+Headers]
+    - {Recipe: Filter IO Stream to String Without Headers}[#label-Recipe-3A+Filter+IO+Stream+to+String+Without+Headers]
+  - {Filtering IO Stream to IO Stream}[#label-Filtering+IO+Stream+to+IO+Stream]
+    - {Recipe: Filter IO Stream to IO Stream with Headers}[#label-Recipe-3A+Filter+IO+Stream+to+IO+Stream+with+Headers]
+    - {Recipe: Filter IO Stream to IO Stream Without Headers}[#label-Recipe-3A+Filter+IO+Stream+to+IO+Stream+Without+Headers]
+
+=== Source and Output Formats
+
+You can use a Unix-style "filter" for \CSV data.
+The filter reads source \CSV data and writes output \CSV data as modified by the filter.
+The input and output \CSV data may be any mixture of \Strings and \IO streams.
+
+==== Filtering \String to \String
+
+You can filter one \String to another, with or without headers.
+
+===== Recipe: Filter \String to \String with Headers
+
+Use class method CSV.filter with option +headers+ to filter a \String to another \String:
+  in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"
+  out_string = ''
+  CSV.filter(in_string, out_string, headers: true) do |row|
+    row[0] = row[0].upcase
+    row[1] *= 4
+  end
+  out_string # => "Name,Value\nFOO,0000\nBAR,1111\nBAZ,2222\n"
+
+===== Recipe: Filter \String to \String Without Headers
+
+Use class method CSV.filter without option +headers+ to filter a \String to another \String:
+  in_string = "foo,0\nbar,1\nbaz,2\n"
+  out_string = ''
+  CSV.filter(in_string, out_string) do |row|
+    row[0] = row[0].upcase
+    row[1] *= 4
+  end
+  out_string # => "FOO,0000\nBAR,1111\nBAZ,2222\n"
+
+==== Filtering \String to \IO Stream
+
+You can filter a \String to an \IO stream, with or without headers.
+
+===== Recipe: Filter \String to \IO Stream with Headers
+
+Use class method CSV.filter with option +headers+ to filter a \String to an \IO stream:
+  in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"
+  path = 't.csv'
+  File.open(path, 'w') do |out_io|
+    CSV.filter(in_string, out_io, headers: true) do |row|
+      row[0] = row[0].upcase
+      row[1] *= 4
+    end
+  end
+  p File.read(path) # => "Name,Value\nFOO,0000\nBAR,1111\nBAZ,2222\n"
+
+===== Recipe: Filter \String to \IO Stream Without Headers
+
+Use class method CSV.filter without option +headers+ to filter a \String to an \IO stream:
+  in_string = "foo,0\nbar,1\nbaz,2\n"
+  path = 't.csv'
+  File.open(path, 'w') do |out_io|
+    CSV.filter(in_string, out_io) do |row|
+      row[0] = row[0].upcase
+      row[1] *= 4
+    end
+  end
+  p File.read(path) # => "FOO,0000\nBAR,1111\nBAZ,2222\n"
+
+==== Filtering \IO Stream to \String
+
+You can filter an \IO stream to a \String, with or without headers.
+
+===== Recipe: Filter \IO Stream to \String with Headers
+
+Use class method CSV.filter with option +headers+ to filter an \IO stream to a \String:
+  in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"
+  path = 't.csv'
+  File.write(path, in_string)
+  out_string = ''
+  File.open(path, headers: true) do |in_io|
+    CSV.filter(in_io, out_string, headers: true) do |row|
+      row[0] = row[0].upcase
+      row[1] *= 4
+    end
+  end
+  out_string # => "Name,Value\nFOO,0000\nBAR,1111\nBAZ,2222\n"
+
+===== Recipe: Filter \IO Stream to \String Without Headers
+
+Use class method CSV.filter without option +headers+ to filter an \IO stream to a \String:
+  in_string = "foo,0\nbar,1\nbaz,2\n"
+  path = 't.csv'
+  File.write(path, in_string)
+  out_string = ''
+  File.open(path) do |in_io|
+    CSV.filter(in_io, out_string) do |row|
+      row[0] = row[0].upcase
+      row[1] *= 4
+    end
+  end
+  out_string # => "FOO,0000\nBAR,1111\nBAZ,2222\n"
+
+==== Filtering \IO Stream to \IO Stream
+
+You can filter an \IO stream to another \IO stream, with or without headers.
+
+===== Recipe: Filter \IO Stream to \IO Stream with Headers
+
+Use class method CSV.filter with option +headers+ to filter an \IO stream to another \IO stream:
+  in_path = 't.csv'
+  in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n"
+  File.write(in_path, in_string)
+  out_path = 'u.csv'
+  File.open(in_path) do |in_io|
+    File.open(out_path, 'w') do |out_io|
+      CSV.filter(in_io, out_io, headers: true) do |row|
+        row[0] = row[0].upcase
+        row[1] *= 4
+      end
+    end
+  end
+  p File.read(out_path) # => "Name,Value\nFOO,0000\nBAR,1111\nBAZ,2222\n"
+
+===== Recipe: Filter \IO Stream to \IO Stream Without Headers
+
+Use class method CSV.filter without option +headers+ to filter an \IO stream to another \IO stream:
+  in_path = 't.csv'
+  in_string = "foo,0\nbar,1\nbaz,2\n"
+  File.write(in_path, in_string)
+  out_path = 'u.csv'
+  File.open(in_path) do |in_io|
+    File.open(out_path, 'w') do |out_io|
+      CSV.filter(in_io, out_io) do |row|
+        row[0] = row[0].upcase
+        row[1] *= 4
+      end
+    end
+  end
+  p File.read(out_path) # => "FOO,0000\nBAR,1111\nBAZ,2222\n"