diff options
author | Hiroshi SHIBATA <[email protected]> | 2024-01-22 17:23:16 +0900 |
---|---|---|
committer | Hiroshi SHIBATA <[email protected]> | 2024-01-22 18:23:05 +0900 |
commit | e195710d10225458008b79dbb734b1cddcd6230d (patch) | |
tree | d861ef13268fcfca3862c5ae28f32780198cf18c /lib | |
parent | a70e500494015b54fffd5a83104684eb66239a30 (diff) |
Extract csv
Diffstat (limited to 'lib')
-rw-r--r-- | lib/csv.rb | 2882 | ||||
-rw-r--r-- | lib/csv/core_ext/array.rb | 9 | ||||
-rw-r--r-- | lib/csv/core_ext/string.rb | 9 | ||||
-rw-r--r-- | lib/csv/csv.gemspec | 64 | ||||
-rw-r--r-- | lib/csv/fields_converter.rb | 89 | ||||
-rw-r--r-- | lib/csv/input_record_separator.rb | 18 | ||||
-rw-r--r-- | lib/csv/parser.rb | 1288 | ||||
-rw-r--r-- | lib/csv/row.rb | 757 | ||||
-rw-r--r-- | lib/csv/table.rb | 1055 | ||||
-rw-r--r-- | lib/csv/version.rb | 6 | ||||
-rw-r--r-- | lib/csv/writer.rb | 210 |
11 files changed, 0 insertions, 6387 deletions
diff --git a/lib/csv.rb b/lib/csv.rb deleted file mode 100644 index e8aa20ddd2..0000000000 --- a/lib/csv.rb +++ /dev/null @@ -1,2882 +0,0 @@ -# encoding: US-ASCII -# frozen_string_literal: true -# = csv.rb -- CSV Reading and Writing -# -# Created by James Edward Gray II on 2005-10-31. -# -# See CSV for documentation. -# -# == Description -# -# 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 -# 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 -# core remains quite small.) -# 3. Improve on the CSV interface. -# -# 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. -# -# We must have met our goals because FasterCSV was renamed to CSV and replaced -# 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 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 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 <tt>:row_sep</tt> is law. It can auto-detect your line endings -# though. -# * The old library returned empty lines as <tt>[nil]</tt>. This library calls -# them <tt>[]</tt>. -# * This library has a much faster parser. -# -# === Interface -# -# * CSV now uses keyword parameters to set options. -# * CSV no longer has generate_row() or parse_row(). -# * The old CSV's Reader and Writer classes have been dropped. -# * CSV::open() is now more like Ruby's open(). -# * CSV objects now support most standard IO methods. -# * 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 allows the instance methods to override the separators for -# 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:[email protected]]. -# -# == Documentation -# -# See CSV for documentation. -# -# == What is CSV, really? -# -# CSV maintains a pretty strict definition of CSV taken directly from -# {the RFC}[https://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 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 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 -# easy as: -# -# data.split(",") -# -# == Questions and/or Comments -# -# Feel free to email {James Edward Gray II}[mailto:[email protected]] -# with any questions. - -require "forwardable" -require "date" -require "stringio" - -require_relative "csv/fields_converter" -require_relative "csv/input_record_separator" -require_relative "csv/parser" -require_relative "csv/row" -require_relative "csv/table" -require_relative "csv/writer" - -# == \CSV -# -# === \CSV Data -# -# \CSV (comma-separated values) data is a text representation of a table: -# - A _row_ _separator_ delimits table rows. -# A common row separator is the newline character <tt>"\n"</tt>. -# - A _column_ _separator_ delimits fields in a row. -# A common column separator is the comma character <tt>","</tt>. -# -# This \CSV \String, with row separator <tt>"\n"</tt> -# and column separator <tt>","</tt>, -# has three rows and two columns: -# "foo,0\nbar,1\nbaz,2\n" -# -# Despite the name \CSV, a \CSV representation can use different separators. -# -# For more about tables, see the Wikipedia article -# "{Table (information)}[https://en.wikipedia.org/wiki/Table_(information)]", -# especially its section -# "{Simple table}[https://en.wikipedia.org/wiki/Table_(information)#Simple_table]" -# -# == \Class \CSV -# -# Class \CSV provides methods for: -# - Parsing \CSV data from a \String object, a \File (via its file path), or an \IO object. -# - Generating \CSV data to a \String object. -# -# To make \CSV available: -# require 'csv' -# -# All examples here assume that this has been done. -# -# == Keeping It Simple -# -# A \CSV object has dozens of instance methods that offer fine-grained control -# of parsing and generating \CSV data. -# For many needs, though, simpler approaches will do. -# -# This section summarizes the singleton methods in \CSV -# that allow you to parse and generate without explicitly -# creating \CSV objects. -# For details, follow the links. -# -# === Simple Parsing -# -# Parsing methods commonly return either of: -# - An \Array of Arrays of Strings: -# - The outer \Array is the entire "table". -# - Each inner \Array is a row. -# - Each \String is a field. -# - A CSV::Table object. For details, see -# {\CSV with Headers}[#class-CSV-label-CSV+with+Headers]. -# -# ==== Parsing a \String -# -# The input to be parsed can be a string: -# string = "foo,0\nbar,1\nbaz,2\n" -# -# \Method CSV.parse returns the entire \CSV data: -# CSV.parse(string) # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# \Method CSV.parse_line returns only the first row: -# CSV.parse_line(string) # => ["foo", "0"] -# -# \CSV extends class \String with instance method String#parse_csv, -# which also returns only the first row: -# string.parse_csv # => ["foo", "0"] -# -# ==== Parsing Via a \File Path -# -# The input to be parsed can be in a file: -# string = "foo,0\nbar,1\nbaz,2\n" -# path = 't.csv' -# File.write(path, string) -# -# \Method CSV.read returns the entire \CSV data: -# CSV.read(path) # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# \Method CSV.foreach iterates, passing each row to the given block: -# CSV.foreach(path) do |row| -# p row -# end -# Output: -# ["foo", "0"] -# ["bar", "1"] -# ["baz", "2"] -# -# \Method CSV.table returns the entire \CSV data as a CSV::Table object: -# CSV.table(path) # => #<CSV::Table mode:col_or_row row_count:3> -# -# ==== Parsing from an Open \IO Stream -# -# The input to be parsed can be in an open \IO stream: -# -# \Method CSV.read returns the entire \CSV data: -# File.open(path) do |file| -# CSV.read(file) -# end # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# As does method CSV.parse: -# File.open(path) do |file| -# CSV.parse(file) -# end # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# \Method CSV.parse_line returns only the first row: -# File.open(path) do |file| -# CSV.parse_line(file) -# end # => ["foo", "0"] -# -# \Method CSV.foreach iterates, passing each row to the given block: -# File.open(path) do |file| -# CSV.foreach(file) do |row| -# p row -# end -# end -# Output: -# ["foo", "0"] -# ["bar", "1"] -# ["baz", "2"] -# -# \Method CSV.table returns the entire \CSV data as a CSV::Table object: -# File.open(path) do |file| -# CSV.table(file) -# end # => #<CSV::Table mode:col_or_row row_count:3> -# -# === Simple Generating -# -# \Method CSV.generate returns a \String; -# this example uses method CSV#<< to append the rows -# that are to be generated: -# output_string = CSV.generate do |csv| -# csv << ['foo', 0] -# csv << ['bar', 1] -# csv << ['baz', 2] -# end -# output_string # => "foo,0\nbar,1\nbaz,2\n" -# -# \Method CSV.generate_line returns a \String containing the single row -# constructed from an \Array: -# CSV.generate_line(['foo', '0']) # => "foo,0\n" -# -# \CSV extends class \Array with instance method <tt>Array#to_csv</tt>, -# which forms an \Array into a \String: -# ['foo', '0'].to_csv # => "foo,0\n" -# -# === "Filtering" \CSV -# -# \Method CSV.filter provides a Unix-style filter for \CSV data. -# The input data is processed to form the output data: -# 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" -# -# == \CSV Objects -# -# There are three ways to create a \CSV object: -# - \Method CSV.new returns a new \CSV object. -# - \Method CSV.instance returns a new or cached \CSV object. -# - \Method \CSV() also returns a new or cached \CSV object. -# -# === Instance Methods -# -# \CSV has three groups of instance methods: -# - Its own internally defined instance methods. -# - Methods included by module Enumerable. -# - Methods delegated to class IO. See below. -# -# ==== Delegated Methods -# -# For convenience, a CSV object will delegate to many methods in class IO. -# (A few have wrapper "guard code" in \CSV.) You may call: -# * IO#binmode -# * #binmode? -# * IO#close -# * IO#close_read -# * IO#close_write -# * IO#closed? -# * #eof -# * #eof? -# * IO#external_encoding -# * IO#fcntl -# * IO#fileno -# * #flock -# * IO#flush -# * IO#fsync -# * IO#internal_encoding -# * #ioctl -# * IO#isatty -# * #path -# * IO#pid -# * IO#pos -# * IO#pos= -# * IO#reopen -# * #rewind -# * IO#seek -# * #stat -# * IO#string -# * IO#sync -# * IO#sync= -# * IO#tell -# * #to_i -# * #to_io -# * IO#truncate -# * IO#tty? -# -# === Options -# -# The default values for options are: -# DEFAULT_OPTIONS = { -# # For both parsing and generating. -# col_sep: ",", -# row_sep: :auto, -# quote_char: '"', -# # For parsing. -# field_size_limit: nil, -# converters: nil, -# unconverted_fields: nil, -# headers: false, -# return_headers: false, -# header_converters: nil, -# skip_blanks: false, -# skip_lines: nil, -# liberal_parsing: false, -# nil_value: nil, -# empty_value: "", -# strip: false, -# # For generating. -# write_headers: nil, -# quote_empty: true, -# force_quotes: false, -# write_converters: nil, -# write_nil_value: nil, -# write_empty_value: "", -# } -# -# ==== Options for Parsing -# -# Options for parsing, described in detail below, include: -# - +row_sep+: Specifies the row separator; used to delimit rows. -# - +col_sep+: Specifies the column separator; used to delimit fields. -# - +quote_char+: Specifies the quote character; used to quote fields. -# - +field_size_limit+: Specifies the maximum field size + 1 allowed. -# Deprecated since 3.2.3. Use +max_field_size+ instead. -# - +max_field_size+: Specifies the maximum field size allowed. -# - +converters+: Specifies the field converters to be used. -# - +unconverted_fields+: Specifies whether unconverted fields are to be available. -# - +headers+: Specifies whether data contains headers, -# or specifies the headers themselves. -# - +return_headers+: Specifies whether headers are to be returned. -# - +header_converters+: Specifies the header converters to be used. -# - +skip_blanks+: Specifies whether blanks lines are to be ignored. -# - +skip_lines+: Specifies how comments lines are to be recognized. -# - +strip+: Specifies whether leading and trailing whitespace are to be -# stripped from fields. This must be compatible with +col_sep+; if it is not, -# then an +ArgumentError+ exception will be raised. -# - +liberal_parsing+: Specifies whether \CSV should attempt to parse -# non-compliant data. -# - +nil_value+: Specifies the object that is to be substituted for each null (no-text) field. -# - +empty_value+: Specifies the object that is to be substituted for each empty field. -# -# :include: ../doc/csv/options/common/row_sep.rdoc -# -# :include: ../doc/csv/options/common/col_sep.rdoc -# -# :include: ../doc/csv/options/common/quote_char.rdoc -# -# :include: ../doc/csv/options/parsing/field_size_limit.rdoc -# -# :include: ../doc/csv/options/parsing/converters.rdoc -# -# :include: ../doc/csv/options/parsing/unconverted_fields.rdoc -# -# :include: ../doc/csv/options/parsing/headers.rdoc -# -# :include: ../doc/csv/options/parsing/return_headers.rdoc -# -# :include: ../doc/csv/options/parsing/header_converters.rdoc -# -# :include: ../doc/csv/options/parsing/skip_blanks.rdoc -# -# :include: ../doc/csv/options/parsing/skip_lines.rdoc -# -# :include: ../doc/csv/options/parsing/strip.rdoc -# -# :include: ../doc/csv/options/parsing/liberal_parsing.rdoc -# -# :include: ../doc/csv/options/parsing/nil_value.rdoc -# -# :include: ../doc/csv/options/parsing/empty_value.rdoc -# -# ==== Options for Generating -# -# Options for generating, described in detail below, include: -# - +row_sep+: Specifies the row separator; used to delimit rows. -# - +col_sep+: Specifies the column separator; used to delimit fields. -# - +quote_char+: Specifies the quote character; used to quote fields. -# - +write_headers+: Specifies whether headers are to be written. -# - +force_quotes+: Specifies whether each output field is to be quoted. -# - +quote_empty+: Specifies whether each empty output field is to be quoted. -# - +write_converters+: Specifies the field converters to be used in writing. -# - +write_nil_value+: Specifies the object that is to be substituted for each +nil+-valued field. -# - +write_empty_value+: Specifies the object that is to be substituted for each empty field. -# -# :include: ../doc/csv/options/common/row_sep.rdoc -# -# :include: ../doc/csv/options/common/col_sep.rdoc -# -# :include: ../doc/csv/options/common/quote_char.rdoc -# -# :include: ../doc/csv/options/generating/write_headers.rdoc -# -# :include: ../doc/csv/options/generating/force_quotes.rdoc -# -# :include: ../doc/csv/options/generating/quote_empty.rdoc -# -# :include: ../doc/csv/options/generating/write_converters.rdoc -# -# :include: ../doc/csv/options/generating/write_nil_value.rdoc -# -# :include: ../doc/csv/options/generating/write_empty_value.rdoc -# -# === \CSV with Headers -# -# CSV allows to specify column names of CSV file, whether they are in data, or -# provided separately. If headers are specified, reading methods return an instance -# of CSV::Table, consisting of CSV::Row. -# -# # Headers are part of data -# data = CSV.parse(<<~ROWS, headers: true) -# Name,Department,Salary -# Bob,Engineering,1000 -# Jane,Sales,2000 -# John,Management,5000 -# ROWS -# -# data.class #=> CSV::Table -# 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,Engineering,1000', headers: %i[name department salary]) -# data.first #=> #<CSV::Row name:"Bob" department:"Engineering" salary:"1000"> -# -# === \Converters -# -# By default, each value (field or header) parsed by \CSV is formed into a \String. -# You can use a _field_ _converter_ or _header_ _converter_ -# to intercept and modify the parsed values: -# - See {Field Converters}[#class-CSV-label-Field+Converters]. -# - See {Header Converters}[#class-CSV-label-Header+Converters]. -# -# Also by default, each value to be written during generation is written 'as-is'. -# You can use a _write_ _converter_ to modify values before writing. -# - See {Write Converters}[#class-CSV-label-Write+Converters]. -# -# ==== Specifying \Converters -# -# You can specify converters for parsing or generating in the +options+ -# argument to various \CSV methods: -# - Option +converters+ for converting parsed field values. -# - Option +header_converters+ for converting parsed header values. -# - Option +write_converters+ for converting values to be written (generated). -# -# There are three forms for specifying converters: -# - A converter proc: executable code to be used for conversion. -# - A converter name: the name of a stored converter. -# - A converter list: an array of converter procs, converter names, and converter lists. -# -# ===== Converter Procs -# -# This converter proc, +strip_converter+, accepts a value +field+ -# and returns <tt>field.strip</tt>: -# strip_converter = proc {|field| field.strip } -# In this call to <tt>CSV.parse</tt>, -# the keyword argument <tt>converters: string_converter</tt> -# specifies that: -# - \Proc +string_converter+ is to be called for each parsed field. -# - The converter's return value is to replace the +field+ value. -# Example: -# string = " foo , 0 \n bar , 1 \n baz , 2 \n" -# array = CSV.parse(string, converters: strip_converter) -# array # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# A converter proc can receive a second argument, +field_info+, -# that contains details about the field. -# This modified +strip_converter+ displays its arguments: -# strip_converter = proc do |field, field_info| -# p [field, field_info] -# field.strip -# end -# string = " foo , 0 \n bar , 1 \n baz , 2 \n" -# array = CSV.parse(string, converters: strip_converter) -# array # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# Output: -# [" foo ", #<struct CSV::FieldInfo index=0, line=1, header=nil>] -# [" 0 ", #<struct CSV::FieldInfo index=1, line=1, header=nil>] -# [" bar ", #<struct CSV::FieldInfo index=0, line=2, header=nil>] -# [" 1 ", #<struct CSV::FieldInfo index=1, line=2, header=nil>] -# [" baz ", #<struct CSV::FieldInfo index=0, line=3, header=nil>] -# [" 2 ", #<struct CSV::FieldInfo index=1, line=3, header=nil>] -# Each CSV::FieldInfo object shows: -# - The 0-based field index. -# - The 1-based line index. -# - The field header, if any. -# -# ===== Stored \Converters -# -# A converter may be given a name and stored in a structure where -# the parsing methods can find it by name. -# -# The storage structure for field converters is the \Hash CSV::Converters. -# It has several built-in converter procs: -# - <tt>:integer</tt>: converts each \String-embedded integer into a true \Integer. -# - <tt>:float</tt>: converts each \String-embedded float into a true \Float. -# - <tt>:date</tt>: converts each \String-embedded date into a true \Date. -# - <tt>:date_time</tt>: converts each \String-embedded date-time into a true \DateTime -# . -# This example creates a converter proc, then stores it: -# strip_converter = proc {|field| field.strip } -# CSV::Converters[:strip] = strip_converter -# Then the parsing method call can refer to the converter -# by its name, <tt>:strip</tt>: -# string = " foo , 0 \n bar , 1 \n baz , 2 \n" -# array = CSV.parse(string, converters: :strip) -# array # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# The storage structure for header converters is the \Hash CSV::HeaderConverters, -# which works in the same way. -# It also has built-in converter procs: -# - <tt>:downcase</tt>: Downcases each header. -# - <tt>:symbol</tt>: Converts each header to a \Symbol. -# -# There is no such storage structure for write headers. -# -# In order for the parsing methods to access stored converters in non-main-Ractors, the -# storage structure must be made shareable first. -# Therefore, <tt>Ractor.make_shareable(CSV::Converters)</tt> and -# <tt>Ractor.make_shareable(CSV::HeaderConverters)</tt> must be called before the creation -# of Ractors that use the converters stored in these structures. (Since making the storage -# structures shareable involves freezing them, any custom converters that are to be used -# must be added first.) -# -# ===== Converter Lists -# -# A _converter_ _list_ is an \Array that may include any assortment of: -# - Converter procs. -# - Names of stored converters. -# - Nested converter lists. -# -# Examples: -# numeric_converters = [:integer, :float] -# date_converters = [:date, :date_time] -# [numeric_converters, strip_converter] -# [strip_converter, date_converters, :float] -# -# Like a converter proc, a converter list may be named and stored in either -# \CSV::Converters or CSV::HeaderConverters: -# CSV::Converters[:custom] = [strip_converter, date_converters, :float] -# CSV::HeaderConverters[:custom] = [:downcase, :symbol] -# -# There are two built-in converter lists: -# CSV::Converters[:numeric] # => [:integer, :float] -# CSV::Converters[:all] # => [:date_time, :numeric] -# -# ==== Field \Converters -# -# With no conversion, all parsed fields in all rows become Strings: -# string = "foo,0\nbar,1\nbaz,2\n" -# ary = CSV.parse(string) -# ary # => # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# When you specify a field converter, each parsed field is passed to the converter; -# its return value becomes the stored value for the field. -# A converter might, for example, convert an integer embedded in a \String -# into a true \Integer. -# (In fact, that's what built-in field converter +:integer+ does.) -# -# There are three ways to use field \converters. -# -# - Using option {converters}[#class-CSV-label-Option+converters] with a parsing method: -# ary = CSV.parse(string, converters: :integer) -# ary # => [0, 1, 2] # => [["foo", 0], ["bar", 1], ["baz", 2]] -# - Using option {converters}[#class-CSV-label-Option+converters] with a new \CSV instance: -# csv = CSV.new(string, converters: :integer) -# # Field converters in effect: -# csv.converters # => [:integer] -# csv.read # => [["foo", 0], ["bar", 1], ["baz", 2]] -# - Using method #convert to add a field converter to a \CSV instance: -# csv = CSV.new(string) -# # Add a converter. -# csv.convert(:integer) -# csv.converters # => [:integer] -# csv.read # => [["foo", 0], ["bar", 1], ["baz", 2]] -# -# Installing a field converter does not affect already-read rows: -# csv = CSV.new(string) -# csv.shift # => ["foo", "0"] -# # Add a converter. -# csv.convert(:integer) -# csv.converters # => [:integer] -# csv.read # => [["bar", 1], ["baz", 2]] -# -# There are additional built-in \converters, and custom \converters are also supported. -# -# ===== Built-In Field \Converters -# -# The built-in field converters are in \Hash CSV::Converters: -# - Each key is a field converter name. -# - Each value is one of: -# - A \Proc field converter. -# - An \Array of field converter names. -# -# Display: -# CSV::Converters.each_pair do |name, value| -# if value.kind_of?(Proc) -# p [name, value.class] -# else -# p [name, value] -# end -# end -# Output: -# [:integer, Proc] -# [:float, Proc] -# [:numeric, [:integer, :float]] -# [:date, Proc] -# [:date_time, Proc] -# [:all, [:date_time, :numeric]] -# -# Each of these converters transcodes values to UTF-8 before attempting conversion. -# If a value cannot be transcoded to UTF-8 the conversion will -# fail and the value will remain unconverted. -# -# Converter +:integer+ converts each field that Integer() accepts: -# data = '0,1,2,x' -# # Without the converter -# csv = CSV.parse_line(data) -# csv # => ["0", "1", "2", "x"] -# # With the converter -# csv = CSV.parse_line(data, converters: :integer) -# csv # => [0, 1, 2, "x"] -# -# Converter +:float+ converts each field that Float() accepts: -# data = '1.0,3.14159,x' -# # Without the converter -# csv = CSV.parse_line(data) -# csv # => ["1.0", "3.14159", "x"] -# # With the converter -# csv = CSV.parse_line(data, converters: :float) -# csv # => [1.0, 3.14159, "x"] -# -# Converter +:numeric+ converts with both +:integer+ and +:float+.. -# -# Converter +:date+ converts each field that Date::parse accepts: -# data = '2001-02-03,x' -# # Without the converter -# csv = CSV.parse_line(data) -# csv # => ["2001-02-03", "x"] -# # With the converter -# csv = CSV.parse_line(data, converters: :date) -# csv # => [#<Date: 2001-02-03 ((2451944j,0s,0n),+0s,2299161j)>, "x"] -# -# Converter +:date_time+ converts each field that DateTime::parse accepts: -# data = '2020-05-07T14:59:00-05:00,x' -# # Without the converter -# csv = CSV.parse_line(data) -# csv # => ["2020-05-07T14:59:00-05:00", "x"] -# # With the converter -# csv = CSV.parse_line(data, converters: :date_time) -# csv # => [#<DateTime: 2020-05-07T14:59:00-05:00 ((2458977j,71940s,0n),-18000s,2299161j)>, "x"] -# -# Converter +:numeric+ converts with both +:date_time+ and +:numeric+.. -# -# As seen above, method #convert adds \converters to a \CSV instance, -# and method #converters returns an \Array of the \converters in effect: -# csv = CSV.new('0,1,2') -# csv.converters # => [] -# csv.convert(:integer) -# csv.converters # => [:integer] -# csv.convert(:date) -# csv.converters # => [:integer, :date] -# -# ===== Custom Field \Converters -# -# You can define a custom field converter: -# strip_converter = proc {|field| field.strip } -# string = " foo , 0 \n bar , 1 \n baz , 2 \n" -# array = CSV.parse(string, converters: strip_converter) -# array # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# You can register the converter in \Converters \Hash, -# which allows you to refer to it by name: -# CSV::Converters[:strip] = strip_converter -# string = " foo , 0 \n bar , 1 \n baz , 2 \n" -# array = CSV.parse(string, converters: :strip) -# array # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] -# -# ==== Header \Converters -# -# Header converters operate only on headers (and not on other rows). -# -# There are three ways to use header \converters; -# these examples use built-in header converter +:downcase+, -# which downcases each parsed header. -# -# - Option +header_converters+ with a singleton parsing method: -# string = "Name,Count\nFoo,0\n,Bar,1\nBaz,2" -# tbl = CSV.parse(string, headers: true, header_converters: :downcase) -# tbl.class # => CSV::Table -# tbl.headers # => ["name", "count"] -# -# - Option +header_converters+ with a new \CSV instance: -# csv = CSV.new(string, header_converters: :downcase) -# # Header converters in effect: -# csv.header_converters # => [:downcase] -# tbl = CSV.parse(string, headers: true) -# tbl.headers # => ["Name", "Count"] -# -# - Method #header_convert adds a header converter to a \CSV instance: -# csv = CSV.new(string) -# # Add a header converter. -# csv.header_convert(:downcase) -# csv.header_converters # => [:downcase] -# tbl = CSV.parse(string, headers: true) -# tbl.headers # => ["Name", "Count"] -# -# ===== Built-In Header \Converters -# -# The built-in header \converters are in \Hash CSV::HeaderConverters. -# The keys there are the names of the \converters: -# CSV::HeaderConverters.keys # => [:downcase, :symbol] -# -# Converter +:downcase+ converts each header by downcasing it: -# string = "Name,Count\nFoo,0\n,Bar,1\nBaz,2" -# tbl = CSV.parse(string, headers: true, header_converters: :downcase) -# tbl.class # => CSV::Table -# tbl.headers # => ["name", "count"] -# -# Converter +:symbol+ converts each header by making it into a \Symbol: -# string = "Name,Count\nFoo,0\n,Bar,1\nBaz,2" -# tbl = CSV.parse(string, headers: true, header_converters: :symbol) -# tbl.headers # => [:name, :count] -# Details: -# - Strips leading and trailing whitespace. -# - Downcases the header. -# - Replaces embedded spaces with underscores. -# - Removes non-word characters. -# - Makes the string into a \Symbol. -# -# ===== Custom Header \Converters -# -# You can define a custom header converter: -# upcase_converter = proc {|header| header.upcase } -# string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" -# table = CSV.parse(string, headers: true, header_converters: upcase_converter) -# table # => #<CSV::Table mode:col_or_row row_count:4> -# table.headers # => ["NAME", "VALUE"] -# You can register the converter in \HeaderConverters \Hash, -# which allows you to refer to it by name: -# CSV::HeaderConverters[:upcase] = upcase_converter -# table = CSV.parse(string, headers: true, header_converters: :upcase) -# table # => #<CSV::Table mode:col_or_row row_count:4> -# table.headers # => ["NAME", "VALUE"] -# -# ===== Write \Converters -# -# When you specify a write converter for generating \CSV, -# each field to be written is passed to the converter; -# its return value becomes the new value for the field. -# A converter might, for example, strip whitespace from a field. -# -# Using no write converter (all fields unmodified): -# output_string = CSV.generate do |csv| -# csv << [' foo ', 0] -# csv << [' bar ', 1] -# csv << [' baz ', 2] -# end -# output_string # => " foo ,0\n bar ,1\n baz ,2\n" -# Using option +write_converters+ with two custom write converters: -# strip_converter = proc {|field| field.respond_to?(:strip) ? field.strip : field } -# upcase_converter = proc {|field| field.respond_to?(:upcase) ? field.upcase : field } -# write_converters = [strip_converter, upcase_converter] -# output_string = CSV.generate(write_converters: write_converters) do |csv| -# csv << [' foo ', 0] -# csv << [' bar ', 1] -# csv << [' baz ', 2] -# end -# output_string # => "FOO,0\nBAR,1\nBAZ,2\n" -# -# === 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 -# (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. -# -# Some transcoding must take place, of course, to accomplish this multiencoding -# support. For example, <tt>:col_sep</tt>, <tt>:row_sep</tt>, and -# <tt>:quote_char</tt> 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 -# 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 -# 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 -# conversions in all of Ruby's Encodings. -# -# 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 -# 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 -# 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. -# Please feel free to {report}[mailto:[email protected]] any issues you -# find with it. -# -class CSV - - # The error thrown when the parser encounters illegal CSV formatting. - class MalformedCSVError < RuntimeError - attr_reader :line_number - alias_method :lineno, :line_number - def initialize(message, line_number) - @line_number = line_number - super("#{message} in line #{line_number}.") - end - end - - # The error thrown when the parser encounters invalid encoding in CSV. - class InvalidEncodingError < MalformedCSVError - attr_reader :encoding - def initialize(encoding, line_number) - @encoding = encoding - super("Invalid byte sequence in #{encoding}", line_number) - end - end - - # - # A FieldInfo Struct contains details about a field's position in the data - # source it was read from. CSV will pass this Struct to some blocks that make - # decisions based on field structure. See CSV.convert_fields() for an - # example. - # - # <b><tt>index</tt></b>:: The zero-based index of the field in its row. - # <b><tt>line</tt></b>:: The line of the data source this row is from. - # <b><tt>header</tt></b>:: The header for the column, when available. - # <b><tt>quoted?</tt></b>:: True or false, whether the original value is quoted or not. - # - FieldInfo = Struct.new(:index, :line, :header, :quoted?) - - # A Regexp used to find and convert some common Date formats. - DateMatcher = / \A(?: (\w+,?\s+)?\w+\s+\d{1,2},?\s+\d{2,4} | - \d{4}-\d{2}-\d{2} )\z /x - # A Regexp used to find and convert some common DateTime formats. - DateTimeMatcher = - / \A(?: (\w+,?\s+)?\w+\s+\d{1,2}\s+\d{1,2}:\d{1,2}:\d{1,2},?\s+\d{2,4} | - # ISO-8601 and RFC-3339 (space instead of T) recognized by DateTime.parse - \d{4}-\d{2}-\d{2} - (?:[T\s]\d{2}:\d{2}(?::\d{2}(?:\.\d+)?(?:[+-]\d{2}(?::\d{2})|Z)?)?)? - )\z /x - - # The encoding used by all converters. - ConverterEncoding = Encoding.find("UTF-8") - - # A \Hash containing the names and \Procs for the built-in field converters. - # See {Built-In Field Converters}[#class-CSV-label-Built-In+Field+Converters]. - # - # This \Hash is intentionally left unfrozen, and may be extended with - # custom field converters. - # See {Custom Field Converters}[#class-CSV-label-Custom+Field+Converters]. - Converters = { - integer: lambda { |f| - Integer(f.encode(ConverterEncoding)) rescue f - }, - float: lambda { |f| - Float(f.encode(ConverterEncoding)) rescue f - }, - numeric: [:integer, :float], - date: lambda { |f| - begin - e = f.encode(ConverterEncoding) - e.match?(DateMatcher) ? Date.parse(e) : f - rescue # encoding conversion or date parse errors - f - end - }, - date_time: lambda { |f| - begin - e = f.encode(ConverterEncoding) - e.match?(DateTimeMatcher) ? DateTime.parse(e) : f - rescue # encoding conversion or date parse errors - f - end - }, - all: [:date_time, :numeric], - } - - # A \Hash containing the names and \Procs for the built-in header converters. - # See {Built-In Header Converters}[#class-CSV-label-Built-In+Header+Converters]. - # - # This \Hash is intentionally left unfrozen, and may be extended with - # custom field converters. - # See {Custom Header Converters}[#class-CSV-label-Custom+Header+Converters]. - HeaderConverters = { - downcase: lambda { |h| h.encode(ConverterEncoding).downcase }, - symbol: lambda { |h| - h.encode(ConverterEncoding).downcase.gsub(/[^\s\w]+/, "").strip. - gsub(/\s+/, "_").to_sym - }, - symbol_raw: lambda { |h| h.encode(ConverterEncoding).to_sym } - } - - # Default values for method options. - DEFAULT_OPTIONS = { - # For both parsing and generating. - col_sep: ",", - row_sep: :auto, - quote_char: '"', - # For parsing. - field_size_limit: nil, - max_field_size: nil, - converters: nil, - unconverted_fields: nil, - headers: false, - return_headers: false, - header_converters: nil, - skip_blanks: false, - skip_lines: nil, - liberal_parsing: false, - nil_value: nil, - empty_value: "", - strip: false, - # For generating. - write_headers: nil, - quote_empty: true, - force_quotes: false, - write_converters: nil, - write_nil_value: nil, - write_empty_value: "", - }.freeze - - class << self - # :call-seq: - # instance(string, **options) - # instance(io = $stdout, **options) - # instance(string, **options) {|csv| ... } - # instance(io = $stdout, **options) {|csv| ... } - # - # Creates or retrieves cached \CSV objects. - # For arguments and options, see CSV.new. - # - # This API is not Ractor-safe. - # - # --- - # - # With no block given, returns a \CSV object. - # - # The first call to +instance+ creates and caches a \CSV object: - # s0 = 's0' - # csv0 = CSV.instance(s0) - # csv0.class # => CSV - # - # Subsequent calls to +instance+ with that _same_ +string+ or +io+ - # retrieve that same cached object: - # csv1 = CSV.instance(s0) - # csv1.class # => CSV - # csv1.equal?(csv0) # => true # Same CSV object - # - # A subsequent call to +instance+ with a _different_ +string+ or +io+ - # creates and caches a _different_ \CSV object. - # s1 = 's1' - # csv2 = CSV.instance(s1) - # csv2.equal?(csv0) # => false # Different CSV object - # - # All the cached objects remains available: - # csv3 = CSV.instance(s0) - # csv3.equal?(csv0) # true # Same CSV object - # csv4 = CSV.instance(s1) - # csv4.equal?(csv2) # true # Same CSV object - # - # --- - # - # When a block is given, calls the block with the created or retrieved - # \CSV object; returns the block's return value: - # CSV.instance(s0) {|csv| :foo } # => :foo - 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) - - # 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(in_string_or_io, **options) {|row| ... } -> array_of_arrays or csv_table - # filter(in_string_or_io, out_string_or_io, **options) {|row| ... } -> array_of_arrays or csv_table - # filter(**options) {|row| ... } -> array_of_arrays or csv_table - # - # - Parses \CSV from a source (\String, \IO stream, or ARGF). - # - Calls the given block with each parsed row: - # - Without headers, each row is an \Array. - # - With headers, each row is a CSV::Row. - # - Generates \CSV to an output (\String, \IO stream, or STDOUT). - # - Returns the parsed source: - # - Without headers, an \Array of \Arrays. - # - With headers, a CSV::Table. - # - # When +in_string_or_io+ is given, but not +out_string_or_io+, - # parses from the given +in_string_or_io+ - # and generates to STDOUT. - # - # \String input without headers: - # - # in_string = "foo,0\nbar,1\nbaz,2" - # CSV.filter(in_string) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end # => [["FOO", 0], ["BAR", -1], ["BAZ", -2]] - # - # Output (to STDOUT): - # - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # \String input with headers: - # - # in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2" - # CSV.filter(in_string, headers: true) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end # => #<CSV::Table mode:col_or_row row_count:4> - # - # Output (to STDOUT): - # - # Name,Value - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # \IO stream input without headers: - # - # File.write('t.csv', "foo,0\nbar,1\nbaz,2") - # File.open('t.csv') do |in_io| - # CSV.filter(in_io) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # end # => [["FOO", 0], ["BAR", -1], ["BAZ", -2]] - # - # Output (to STDOUT): - # - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # \IO stream input with headers: - # - # File.write('t.csv', "Name,Value\nfoo,0\nbar,1\nbaz,2") - # File.open('t.csv') do |in_io| - # CSV.filter(in_io, headers: true) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # end # => #<CSV::Table mode:col_or_row row_count:4> - # - # Output (to STDOUT): - # - # Name,Value - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # When both +in_string_or_io+ and +out_string_or_io+ are given, - # parses from +in_string_or_io+ and generates to +out_string_or_io+. - # - # \String output without headers: - # - # in_string = "foo,0\nbar,1\nbaz,2" - # out_string = '' - # CSV.filter(in_string, out_string) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end # => [["FOO", 0], ["BAR", -1], ["BAZ", -2]] - # out_string # => "FOO,0\nBAR,-1\nBAZ,-2\n" - # - # \String output with headers: - # - # in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2" - # out_string = '' - # CSV.filter(in_string, out_string, headers: true) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end # => #<CSV::Table mode:col_or_row row_count:4> - # out_string # => "Name,Value\nFOO,0\nBAR,-1\nBAZ,-2\n" - # - # \IO stream output without headers: - # - # in_string = "foo,0\nbar,1\nbaz,2" - # File.open('t.csv', 'w') do |out_io| - # CSV.filter(in_string, out_io) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # end # => [["FOO", 0], ["BAR", -1], ["BAZ", -2]] - # File.read('t.csv') # => "FOO,0\nBAR,-1\nBAZ,-2\n" - # - # \IO stream output with headers: - # - # in_string = "Name,Value\nfoo,0\nbar,1\nbaz,2" - # File.open('t.csv', 'w') do |out_io| - # CSV.filter(in_string, out_io, headers: true) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # end # => #<CSV::Table mode:col_or_row row_count:4> - # File.read('t.csv') # => "Name,Value\nFOO,0\nBAR,-1\nBAZ,-2\n" - # - # When neither +in_string_or_io+ nor +out_string_or_io+ given, - # parses from {ARGF}[rdoc-ref:ARGF] - # and generates to STDOUT. - # - # Without headers: - # - # # Put Ruby code into a file. - # ruby = <<-EOT - # require 'csv' - # CSV.filter do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # EOT - # File.write('t.rb', ruby) - # # Put some CSV into a file. - # File.write('t.csv', "foo,0\nbar,1\nbaz,2") - # # Run the Ruby code with CSV filename as argument. - # system(Gem.ruby, "t.rb", "t.csv") - # - # Output (to STDOUT): - # - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # With headers: - # - # # Put Ruby code into a file. - # ruby = <<-EOT - # require 'csv' - # CSV.filter(headers: true) do |row| - # row[0].upcase! - # row[1] = - row[1].to_i - # end - # EOT - # File.write('t.rb', ruby) - # # Put some CSV into a file. - # File.write('t.csv', "Name,Value\nfoo,0\nbar,1\nbaz,2") - # # Run the Ruby code with CSV filename as argument. - # system(Gem.ruby, "t.rb", "t.csv") - # - # Output (to STDOUT): - # - # Name,Value - # FOO,0 - # BAR,-1 - # BAZ,-2 - # - # Arguments: - # - # * Argument +in_string_or_io+ must be a \String or an \IO stream. - # * Argument +out_string_or_io+ must be a \String or an \IO stream. - # * Arguments <tt>**options</tt> must be keyword options. - # See {Options for Parsing}[#class-CSV-label-Options+for+Parsing]. - def filter(input=nil, output=nil, **options) - # parse options for input, output, or both - in_options, out_options = Hash.new, {row_sep: InputRecordSeparator.value} - options.each do |key, value| - case key - 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) - - # process headers - need_manual_header_output = - (in_options[:headers] and - out_options[:headers] == true and - out_options[:write_headers]) - if need_manual_header_output - first_row = input.shift - if first_row - if first_row.is_a?(Row) - headers = first_row.headers - yield headers - output << headers - end - yield first_row - output << first_row - end - end - - # read, yield, write - input.each do |row| - yield row - output << row - end - end - - # - # :call-seq: - # foreach(path_or_io, mode='r', **options) {|row| ... ) - # foreach(path_or_io, mode='r', **options) -> new_enumerator - # - # Calls the block with each row read from source +path_or_io+. - # - # \Path input without headers: - # - # string = "foo,0\nbar,1\nbaz,2\n" - # in_path = 't.csv' - # File.write(in_path, string) - # CSV.foreach(in_path) {|row| p row } - # - # Output: - # - # ["foo", "0"] - # ["bar", "1"] - # ["baz", "2"] - # - # \Path input with headers: - # - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # in_path = 't.csv' - # File.write(in_path, string) - # CSV.foreach(in_path, headers: true) {|row| p row } - # - # Output: - # - # <CSV::Row "Name":"foo" "Value":"0"> - # <CSV::Row "Name":"bar" "Value":"1"> - # <CSV::Row "Name":"baz" "Value":"2"> - # - # \IO stream input without headers: - # - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # File.open('t.csv') do |in_io| - # CSV.foreach(in_io) {|row| p row } - # end - # - # Output: - # - # ["foo", "0"] - # ["bar", "1"] - # ["baz", "2"] - # - # \IO stream input with headers: - # - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # File.open('t.csv') do |in_io| - # CSV.foreach(in_io, headers: true) {|row| p row } - # end - # - # Output: - # - # <CSV::Row "Name":"foo" "Value":"0"> - # <CSV::Row "Name":"bar" "Value":"1"> - # <CSV::Row "Name":"baz" "Value":"2"> - # - # With no block given, returns an \Enumerator: - # - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.foreach(path) # => #<Enumerator: CSV:foreach("t.csv", "r")> - # - # Arguments: - # * Argument +path_or_io+ must be a file path or an \IO stream. - # * Argument +mode+, if given, must be a \File mode. - # See {Access Modes}[rdoc-ref:File@Access+Modes]. - # * Arguments <tt>**options</tt> must be keyword options. - # See {Options for Parsing}[#class-CSV-label-Options+for+Parsing]. - # * This method optionally accepts an additional <tt>:encoding</tt> option - # that you can use to specify the Encoding of the data read from +path+ or +io+. - # You must provide this unless your data is in the encoding - # given by <tt>Encoding::default_external</tt>. - # Parsing 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 parsing. - 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 - - # - # :call-seq: - # generate(csv_string, **options) {|csv| ... } - # generate(**options) {|csv| ... } - # - # * Argument +csv_string+, if given, must be a \String object; - # defaults to a new empty \String. - # * Arguments +options+, if given, should be generating options. - # See {Options for Generating}[#class-CSV-label-Options+for+Generating]. - # - # --- - # - # Creates a new \CSV object via <tt>CSV.new(csv_string, **options)</tt>; - # calls the block with the \CSV object, which the block may modify; - # returns the \String generated from the \CSV object. - # - # Note that a passed \String *is* modified by this method. - # Pass <tt>csv_string</tt>.dup if the \String must be preserved. - # - # This method has one additional option: <tt>:encoding</tt>, - # which sets the base Encoding for the output if no no +str+ is specified. - # CSV needs this hint if you plan to output non-ASCII compatible data. - # - # --- - # - # Add lines: - # input_string = "foo,0\nbar,1\nbaz,2\n" - # output_string = CSV.generate(input_string) do |csv| - # csv << ['bat', 3] - # csv << ['bam', 4] - # end - # output_string # => "foo,0\nbar,1\nbaz,2\nbat,3\nbam,4\n" - # input_string # => "foo,0\nbar,1\nbaz,2\nbat,3\nbam,4\n" - # output_string.equal?(input_string) # => true # Same string, modified - # - # Add lines into new string, preserving old string: - # input_string = "foo,0\nbar,1\nbaz,2\n" - # output_string = CSV.generate(input_string.dup) do |csv| - # csv << ['bat', 3] - # csv << ['bam', 4] - # end - # output_string # => "foo,0\nbar,1\nbaz,2\nbat,3\nbam,4\n" - # input_string # => "foo,0\nbar,1\nbaz,2\n" - # output_string.equal?(input_string) # => false # Different strings - # - # Create lines from nothing: - # output_string = CSV.generate do |csv| - # csv << ['foo', 0] - # csv << ['bar', 1] - # csv << ['baz', 2] - # end - # output_string # => "foo,0\nbar,1\nbaz,2\n" - # - # --- - # - # Raises an exception if +csv_string+ is not a \String object: - # # Raises TypeError (no implicit conversion of Integer into String) - # CSV.generate(0) - # - def generate(str=nil, **options) - encoding = options[:encoding] - # add a default empty String, if none was given - if str - str = StringIO.new(str) - str.seek(0, IO::SEEK_END) - str.set_encoding(encoding) if encoding - else - str = +"" - str.force_encoding(encoding) if encoding - end - csv = new(str, **options) # wrap - yield csv # yield for appending - csv.string # return final String - end - - # :call-seq: - # CSV.generate_line(ary) - # CSV.generate_line(ary, **options) - # - # Returns the \String created by generating \CSV from +ary+ - # using the specified +options+. - # - # Argument +ary+ must be an \Array. - # - # Special options: - # * Option <tt>:row_sep</tt> defaults to <tt>"\n"> on Ruby 3.0 or later - # and <tt>$INPUT_RECORD_SEPARATOR</tt> (<tt>$/</tt>) otherwise.: - # $INPUT_RECORD_SEPARATOR # => "\n" - # * This method accepts an additional option, <tt>:encoding</tt>, which sets the base - # Encoding for the output. This method will try to guess your Encoding from - # the first non-+nil+ field in +row+, if possible, but you may need to use - # this parameter as a backup plan. - # - # For other +options+, - # see {Options for Generating}[#class-CSV-label-Options+for+Generating]. - # - # --- - # - # Returns the \String generated from an \Array: - # CSV.generate_line(['foo', '0']) # => "foo,0\n" - # - # --- - # - # Raises an exception if +ary+ is not an \Array: - # # Raises NoMethodError (undefined method `find' for :foo:Symbol) - # CSV.generate_line(:foo) - # - def generate_line(row, **options) - options = {row_sep: InputRecordSeparator.value}.merge(options) - str = +"" - if options[:encoding] - str.force_encoding(options[:encoding]) - else - fallback_encoding = nil - output_encoding = nil - row.each do |field| - next unless field.is_a?(String) - fallback_encoding ||= field.encoding - next if field.ascii_only? - output_encoding = field.encoding - break - end - output_encoding ||= fallback_encoding - if output_encoding - str.force_encoding(output_encoding) - end - end - (new(str, **options) << row).string - end - - # :call-seq: - # CSV.generate_lines(rows) - # CSV.generate_lines(rows, **options) - # - # Returns the \String created by generating \CSV from - # using the specified +options+. - # - # Argument +rows+ must be an \Array of row. Row is \Array of \String or \CSV::Row. - # - # Special options: - # * Option <tt>:row_sep</tt> defaults to <tt>"\n"</tt> on Ruby 3.0 or later - # and <tt>$INPUT_RECORD_SEPARATOR</tt> (<tt>$/</tt>) otherwise.: - # $INPUT_RECORD_SEPARATOR # => "\n" - # * This method accepts an additional option, <tt>:encoding</tt>, which sets 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. - # - # For other +options+, - # see {Options for Generating}[#class-CSV-label-Options+for+Generating]. - # - # --- - # - # Returns the \String generated from an - # CSV.generate_lines([['foo', '0'], ['bar', '1'], ['baz', '2']]) # => "foo,0\nbar,1\nbaz,2\n" - # - # --- - # - # Raises an exception - # # Raises NoMethodError (undefined method `each' for :foo:Symbol) - # CSV.generate_lines(:foo) - # - def generate_lines(rows, **options) - self.generate(**options) do |csv| - rows.each do |row| - csv << row - end - end - end - - # - # :call-seq: - # open(file_path, mode = "rb", **options ) -> new_csv - # open(io, mode = "rb", **options ) -> new_csv - # open(file_path, mode = "rb", **options ) { |csv| ... } -> object - # open(io, mode = "rb", **options ) { |csv| ... } -> object - # - # possible options elements: - # keyword form: - # :invalid => nil # raise error on invalid byte sequence (default) - # :invalid => :replace # replace invalid byte sequence - # :undef => :replace # replace undefined conversion - # :replace => string # replacement string ("?" or "\uFFFD" if not specified) - # - # * Argument +path+, if given, must be the path to a file. - # :include: ../doc/csv/arguments/io.rdoc - # * Argument +mode+, if given, must be a \File mode. - # See {Access Modes}[rdoc-ref:File@Access+Modes]. - # * Arguments <tt>**options</tt> must be keyword options. - # See {Options for Generating}[#class-CSV-label-Options+for+Generating]. - # * This method optionally accepts an additional <tt>:encoding</tt> option - # that you can use to specify the Encoding of the data read from +path+ or +io+. - # You must provide this unless your data is in the encoding - # given by <tt>Encoding::default_external</tt>. - # Parsing 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 parsing. - # - # --- - # - # These examples assume prior execution of: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # --- - # - # With no block given, returns a new \CSV object. - # - # Create a \CSV object using a file path: - # csv = CSV.open(path) - # csv # => #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # Create a \CSV object using an open \File: - # csv = CSV.open(File.open(path)) - # csv # => #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # --- - # - # With a block given, calls the block with the created \CSV object; - # returns the block's return value: - # - # Using a file path: - # csv = CSV.open(path) {|csv| p csv} - # csv # => #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # Output: - # #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # Using an open \File: - # csv = CSV.open(File.open(path)) {|csv| p csv} - # csv # => #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # Output: - # #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # --- - # - # Raises an exception if the argument is not a \String object or \IO object: - # # Raises TypeError (no implicit conversion of Symbol into String) - # CSV.open(:foo) - def open(filename, mode="r", **options) - # wrap a File opened with the remaining +args+ with no newline - # decorator - file_opts = options.dup - unless file_opts.key?(:newline) - file_opts[:universal_newline] ||= false - end - options.delete(:invalid) - options.delete(:undef) - options.delete(:replace) - options.delete_if {|k, _| /newline\z/.match?(k)} - - 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 - 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(string) -> array_of_arrays - # parse(io) -> array_of_arrays - # parse(string, headers: ..., **options) -> csv_table - # parse(io, headers: ..., **options) -> csv_table - # parse(string, **options) {|row| ... } - # parse(io, **options) {|row| ... } - # - # Parses +string+ or +io+ using the specified +options+. - # - # - Argument +string+ should be a \String object; - # it will be put into a new StringIO object positioned at the beginning. - # :include: ../doc/csv/arguments/io.rdoc - # - Argument +options+: see {Options for Parsing}[#class-CSV-label-Options+for+Parsing] - # - # ====== Without Option +headers+ - # - # Without {option +headers+}[#class-CSV-label-Option+headers] case. - # - # These examples assume prior execution of: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # --- - # - # With no block given, returns an \Array of Arrays formed from the source. - # - # Parse a \String: - # a_of_a = CSV.parse(string) - # a_of_a # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # Parse an open \File: - # a_of_a = File.open(path) do |file| - # CSV.parse(file) - # end - # a_of_a # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # --- - # - # With a block given, calls the block with each parsed row: - # - # Parse a \String: - # CSV.parse(string) {|row| p row } - # - # Output: - # ["foo", "0"] - # ["bar", "1"] - # ["baz", "2"] - # - # Parse an open \File: - # File.open(path) do |file| - # CSV.parse(file) {|row| p row } - # end - # - # Output: - # ["foo", "0"] - # ["bar", "1"] - # ["baz", "2"] - # - # ====== With Option +headers+ - # - # With {option +headers+}[#class-CSV-label-Option+headers] case. - # - # These examples assume prior execution of: - # string = "Name,Count\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # --- - # - # With no block given, returns a CSV::Table object formed from the source. - # - # Parse a \String: - # csv_table = CSV.parse(string, headers: ['Name', 'Count']) - # csv_table # => #<CSV::Table mode:col_or_row row_count:5> - # - # Parse an open \File: - # csv_table = File.open(path) do |file| - # CSV.parse(file, headers: ['Name', 'Count']) - # end - # csv_table # => #<CSV::Table mode:col_or_row row_count:4> - # - # --- - # - # With a block given, calls the block with each parsed row, - # which has been formed into a CSV::Row object: - # - # Parse a \String: - # CSV.parse(string, headers: ['Name', 'Count']) {|row| p row } - # - # Output: - # # <CSV::Row "Name":"foo" "Count":"0"> - # # <CSV::Row "Name":"bar" "Count":"1"> - # # <CSV::Row "Name":"baz" "Count":"2"> - # - # Parse an open \File: - # File.open(path) do |file| - # CSV.parse(file, headers: ['Name', 'Count']) {|row| p row } - # end - # - # Output: - # # <CSV::Row "Name":"foo" "Count":"0"> - # # <CSV::Row "Name":"bar" "Count":"1"> - # # <CSV::Row "Name":"baz" "Count":"2"> - # - # --- - # - # Raises an exception if the argument is not a \String object or \IO object: - # # Raises NoMethodError (undefined method `close' for :foo:Symbol) - # CSV.parse(:foo) - 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 - end - - # :call-seq: - # CSV.parse_line(string) -> new_array or nil - # CSV.parse_line(io) -> new_array or nil - # CSV.parse_line(string, **options) -> new_array or nil - # CSV.parse_line(io, **options) -> new_array or nil - # CSV.parse_line(string, headers: true, **options) -> csv_row or nil - # CSV.parse_line(io, headers: true, **options) -> csv_row or nil - # - # Returns the data created by parsing the first line of +string+ or +io+ - # using the specified +options+. - # - # - Argument +string+ should be a \String object; - # it will be put into a new StringIO object positioned at the beginning. - # :include: ../doc/csv/arguments/io.rdoc - # - Argument +options+: see {Options for Parsing}[#class-CSV-label-Options+for+Parsing] - # - # ====== Without Option +headers+ - # - # Without option +headers+, returns the first row as a new \Array. - # - # These examples assume prior execution of: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # Parse the first line from a \String object: - # CSV.parse_line(string) # => ["foo", "0"] - # - # Parse the first line from a File object: - # File.open(path) do |file| - # CSV.parse_line(file) # => ["foo", "0"] - # end # => ["foo", "0"] - # - # Returns +nil+ if the argument is an empty \String: - # CSV.parse_line('') # => nil - # - # ====== With Option +headers+ - # - # With {option +headers+}[#class-CSV-label-Option+headers], - # returns the first row as a CSV::Row object. - # - # These examples assume prior execution of: - # string = "Name,Count\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # Parse the first line from a \String object: - # CSV.parse_line(string, headers: true) # => #<CSV::Row "Name":"foo" "Count":"0"> - # - # Parse the first line from a File object: - # File.open(path) do |file| - # CSV.parse_line(file, headers: true) - # end # => #<CSV::Row "Name":"foo" "Count":"0"> - # - # --- - # - # Raises an exception if the argument is +nil+: - # # Raises ArgumentError (Cannot parse nil as CSV): - # CSV.parse_line(nil) - # - def parse_line(line, **options) - new(line, **options).each.first - end - - # - # :call-seq: - # read(source, **options) -> array_of_arrays - # read(source, headers: true, **options) -> csv_table - # - # Opens the given +source+ with the given +options+ (see CSV.open), - # reads the source (see CSV#read), and returns the result, - # which will be either an \Array of Arrays or a CSV::Table. - # - # Without headers: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.read(path) # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # With headers: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.read(path, headers: true) # => #<CSV::Table mode:col_or_row row_count:4> - def read(path, **options) - open(path, **options) { |csv| csv.read } - end - - # :call-seq: - # CSV.readlines(source, **options) - # - # Alias for CSV.read. - def readlines(path, **options) - read(path, **options) - end - - # :call-seq: - # CSV.table(source, **options) - # - # Calls CSV.read with +source+, +options+, and certain default options: - # - +headers+: +true+ - # - +converters+: +:numeric+ - # - +header_converters+: +:symbol+ - # - # Returns a CSV::Table object. - # - # Example: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.table(path) # => #<CSV::Table mode:col_or_row row_count:4> - def table(path, **options) - default_options = { - headers: true, - converters: :numeric, - header_converters: :symbol, - } - options = default_options.merge(options) - read(path, **options) - end - end - - # :call-seq: - # CSV.new(string) - # CSV.new(io) - # CSV.new(string, **options) - # CSV.new(io, **options) - # - # Returns the new \CSV object created using +string+ or +io+ - # and the specified +options+. - # - # - Argument +string+ should be a \String object; - # it will be put into a new StringIO object positioned at the beginning. - # :include: ../doc/csv/arguments/io.rdoc - # - Argument +options+: See: - # * {Options for Parsing}[#class-CSV-label-Options+for+Parsing] - # * {Options for Generating}[#class-CSV-label-Options+for+Generating] - # For performance reasons, the options cannot be overridden - # in a \CSV object, so those specified here will endure. - # - # In addition to the \CSV instance methods, several \IO methods are delegated. - # See {Delegated Methods}[#class-CSV-label-Delegated+Methods]. - # - # --- - # - # Create a \CSV object from a \String object: - # csv = CSV.new('foo,0') - # csv # => #<CSV io_type:StringIO encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # Create a \CSV object from a \File object: - # File.write('t.csv', 'foo,0') - # csv = CSV.new(File.open('t.csv')) - # csv # => #<CSV io_type:File io_path:"t.csv" encoding:UTF-8 lineno:0 col_sep:"," row_sep:"\n" quote_char:"\""> - # - # --- - # - # Raises an exception if the argument is +nil+: - # # Raises ArgumentError (Cannot parse nil as CSV): - # CSV.new(nil) - # - def initialize(data, - col_sep: ",", - row_sep: :auto, - quote_char: '"', - field_size_limit: nil, - max_field_size: 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: "", - strip: false, - quote_empty: true, - write_converters: nil, - write_nil_value: nil, - write_empty_value: "") - raise ArgumentError.new("Cannot parse nil as CSV") if data.nil? - - if data.is_a?(String) - if encoding - if encoding.is_a?(String) - data_external_encoding, data_internal_encoding = encoding.split(":", 2) - if data_internal_encoding - data = data.encode(data_internal_encoding, data_external_encoding) - else - data = data.dup.force_encoding(data_external_encoding) - end - else - data = data.dup.force_encoding(encoding) - end - end - @io = StringIO.new(data) - else - @io = data - end - @encoding = determine_encoding(encoding, internal_encoding) - - @base_fields_converter_options = { - nil_value: nil_value, - empty_value: empty_value, - } - @write_fields_converter_options = { - nil_value: write_nil_value, - empty_value: write_empty_value, - } - @initial_converters = converters - @initial_header_converters = header_converters - @initial_write_converters = write_converters - - if max_field_size.nil? and field_size_limit - max_field_size = field_size_limit - 1 - end - @parser_options = { - column_separator: col_sep, - row_separator: row_sep, - quote_character: quote_char, - max_field_size: max_field_size, - 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, - strip: strip, - } - @parser = nil - @parser_enumerator = nil - @eof_error = 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, - quote_empty: quote_empty, - } - - @writer = nil - writer if @writer_options[:write_headers] - end - - # :call-seq: - # csv.col_sep -> string - # - # Returns the encoded column separator; used for parsing and writing; - # see {Option +col_sep+}[#class-CSV-label-Option+col_sep]: - # CSV.new('').col_sep # => "," - def col_sep - parser.column_separator - end - - # :call-seq: - # csv.row_sep -> string - # - # Returns the encoded row separator; used for parsing and writing; - # see {Option +row_sep+}[#class-CSV-label-Option+row_sep]: - # CSV.new('').row_sep # => "\n" - def row_sep - parser.row_separator - end - - # :call-seq: - # csv.quote_char -> character - # - # Returns the encoded quote character; used for parsing and writing; - # see {Option +quote_char+}[#class-CSV-label-Option+quote_char]: - # CSV.new('').quote_char # => "\"" - def quote_char - parser.quote_character - end - - # :call-seq: - # csv.field_size_limit -> integer or nil - # - # Returns the limit for field size; used for parsing; - # see {Option +field_size_limit+}[#class-CSV-label-Option+field_size_limit]: - # CSV.new('').field_size_limit # => nil - # - # Deprecated since 3.2.3. Use +max_field_size+ instead. - def field_size_limit - parser.field_size_limit - end - - # :call-seq: - # csv.max_field_size -> integer or nil - # - # Returns the limit for field size; used for parsing; - # see {Option +max_field_size+}[#class-CSV-label-Option+max_field_size]: - # CSV.new('').max_field_size # => nil - # - # Since 3.2.3. - def max_field_size - parser.max_field_size - end - - # :call-seq: - # csv.skip_lines -> regexp or nil - # - # Returns the \Regexp used to identify comment lines; used for parsing; - # see {Option +skip_lines+}[#class-CSV-label-Option+skip_lines]: - # CSV.new('').skip_lines # => nil - def skip_lines - parser.skip_lines - end - - # :call-seq: - # csv.converters -> array - # - # Returns an \Array containing field converters; - # see {Field Converters}[#class-CSV-label-Field+Converters]: - # csv = CSV.new('') - # csv.converters # => [] - # csv.convert(:integer) - # csv.converters # => [:integer] - # csv.convert(proc {|x| x.to_s }) - # csv.converters - # - # Notes that you need to call - # +Ractor.make_shareable(CSV::Converters)+ on the main Ractor to use - # this method. - def converters - parser_fields_converter.map do |converter| - name = Converters.rassoc(converter) - name ? name.first : converter - end - end - - # :call-seq: - # csv.unconverted_fields? -> object - # - # Returns the value that determines whether unconverted fields are to be - # available; used for parsing; - # see {Option +unconverted_fields+}[#class-CSV-label-Option+unconverted_fields]: - # CSV.new('').unconverted_fields? # => nil - def unconverted_fields? - parser.unconverted_fields? - end - - # :call-seq: - # csv.headers -> object - # - # Returns the value that determines whether headers are used; used for parsing; - # see {Option +headers+}[#class-CSV-label-Option+headers]: - # CSV.new('').headers # => nil - def 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 - - # :call-seq: - # csv.return_headers? -> true or false - # - # Returns the value that determines whether headers are to be returned; used for parsing; - # see {Option +return_headers+}[#class-CSV-label-Option+return_headers]: - # CSV.new('').return_headers? # => false - def return_headers? - parser.return_headers? - end - - # :call-seq: - # csv.write_headers? -> true or false - # - # Returns the value that determines whether headers are to be written; used for generating; - # see {Option +write_headers+}[#class-CSV-label-Option+write_headers]: - # CSV.new('').write_headers? # => nil - def write_headers? - @writer_options[:write_headers] - end - - # :call-seq: - # csv.header_converters -> array - # - # Returns an \Array containing header converters; used for parsing; - # see {Header Converters}[#class-CSV-label-Header+Converters]: - # CSV.new('').header_converters # => [] - # - # Notes that you need to call - # +Ractor.make_shareable(CSV::HeaderConverters)+ on the main Ractor - # to use this method. - def header_converters - header_fields_converter.map do |converter| - name = HeaderConverters.rassoc(converter) - name ? name.first : converter - end - end - - # :call-seq: - # csv.skip_blanks? -> true or false - # - # Returns the value that determines whether blank lines are to be ignored; used for parsing; - # see {Option +skip_blanks+}[#class-CSV-label-Option+skip_blanks]: - # CSV.new('').skip_blanks? # => false - def skip_blanks? - parser.skip_blanks? - end - - # :call-seq: - # csv.force_quotes? -> true or false - # - # Returns the value that determines whether all output fields are to be quoted; - # used for generating; - # see {Option +force_quotes+}[#class-CSV-label-Option+force_quotes]: - # CSV.new('').force_quotes? # => false - def force_quotes? - @writer_options[:force_quotes] - end - - # :call-seq: - # csv.liberal_parsing? -> true or false - # - # Returns the value that determines whether illegal input is to be handled; used for parsing; - # see {Option +liberal_parsing+}[#class-CSV-label-Option+liberal_parsing]: - # CSV.new('').liberal_parsing? # => false - def liberal_parsing? - parser.liberal_parsing? - end - - # :call-seq: - # csv.encoding -> encoding - # - # Returns the encoding used for parsing and generating; - # see {Character Encodings (M17n or Multilingualization)}[#class-CSV-label-Character+Encodings+-28M17n+or+Multilingualization-29]: - # CSV.new('').encoding # => #<Encoding:UTF-8> - attr_reader :encoding - - # :call-seq: - # csv.line_no -> integer - # - # Returns the count of the rows parsed or generated. - # - # Parsing: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.open(path) do |csv| - # csv.each do |row| - # p [csv.lineno, row] - # end - # end - # Output: - # [1, ["foo", "0"]] - # [2, ["bar", "1"]] - # [3, ["baz", "2"]] - # - # Generating: - # CSV.generate do |csv| - # p csv.lineno; csv << ['foo', 0] - # p csv.lineno; csv << ['bar', 1] - # p csv.lineno; csv << ['baz', 2] - # end - # Output: - # 0 - # 1 - # 2 - def lineno - if @writer - @writer.lineno - else - parser.lineno - end - end - - # :call-seq: - # csv.line -> array - # - # Returns the line most recently read: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # CSV.open(path) do |csv| - # csv.each do |row| - # p [csv.lineno, csv.line] - # end - # end - # Output: - # [1, "foo,0\n"] - # [2, "bar,1\n"] - # [3, "baz,2\n"] - def line - parser.line - end - - ### IO and StringIO Delegation ### - - extend Forwardable - def_delegators :@io, :binmode, :close, :close_read, :close_write, - :closed?, :external_encoding, :fcntl, - :fileno, :flush, :fsync, :internal_encoding, - :isatty, :pid, :pos, :pos=, :reopen, - :seek, :string, :sync, :sync=, :tell, - :truncate, :tty? - - def binmode? - if @io.respond_to?(:binmode?) - @io.binmode? - else - false - end - end - - def flock(*args) - raise NotImplementedError unless @io.respond_to?(:flock) - @io.flock(*args) - end - - def ioctl(*args) - raise NotImplementedError unless @io.respond_to?(:ioctl) - @io.ioctl(*args) - end - - def path - @io.path if @io.respond_to?(:path) - end - - def stat(*args) - raise NotImplementedError unless @io.respond_to?(:stat) - @io.stat(*args) - end - - def to_i - raise NotImplementedError unless @io.respond_to?(:to_i) - @io.to_i - end - - def to_io - @io.respond_to?(:to_io) ? @io.to_io : @io - end - - def eof? - return false if @eof_error - begin - parser_enumerator.peek - false - rescue MalformedCSVError => error - @eof_error = error - false - rescue StopIteration - true - end - end - alias_method :eof, :eof? - - # Rewinds the underlying IO object and resets CSV's lineno() counter. - def rewind - @parser = nil - @parser_enumerator = nil - @eof_error = nil - @writer.rewind if @writer - @io.rewind - end - - ### End Delegation ### - - # :call-seq: - # csv << row -> self - # - # Appends a row to +self+. - # - # - Argument +row+ must be an \Array object or a CSV::Row object. - # - The output stream must be open for writing. - # - # --- - # - # Append Arrays: - # CSV.generate do |csv| - # csv << ['foo', 0] - # csv << ['bar', 1] - # csv << ['baz', 2] - # end # => "foo,0\nbar,1\nbaz,2\n" - # - # Append CSV::Rows: - # headers = [] - # CSV.generate do |csv| - # csv << CSV::Row.new(headers, ['foo', 0]) - # csv << CSV::Row.new(headers, ['bar', 1]) - # csv << CSV::Row.new(headers, ['baz', 2]) - # end # => "foo,0\nbar,1\nbaz,2\n" - # - # Headers in CSV::Row objects are not appended: - # headers = ['Name', 'Count'] - # CSV.generate do |csv| - # csv << CSV::Row.new(headers, ['foo', 0]) - # csv << CSV::Row.new(headers, ['bar', 1]) - # csv << CSV::Row.new(headers, ['baz', 2]) - # end # => "foo,0\nbar,1\nbaz,2\n" - # - # --- - # - # Raises an exception if +row+ is not an \Array or \CSV::Row: - # CSV.generate do |csv| - # # Raises NoMethodError (undefined method `collect' for :foo:Symbol) - # csv << :foo - # end - # - # Raises an exception if the output stream is not opened for writing: - # path = 't.csv' - # File.write(path, '') - # File.open(path) do |file| - # CSV.open(file) do |csv| - # # Raises IOError (not opened for writing) - # csv << ['foo', 0] - # end - # end - def <<(row) - writer << row - self - end - alias_method :add_row, :<< - alias_method :puts, :<< - - # :call-seq: - # convert(converter_name) -> array_of_procs - # convert {|field, field_info| ... } -> array_of_procs - # - # - With no block, installs a field converter (a \Proc). - # - With a block, defines and installs a custom field converter. - # - Returns the \Array of installed field converters. - # - # - Argument +converter_name+, if given, should be the name - # of an existing field converter. - # - # See {Field Converters}[#class-CSV-label-Field+Converters]. - # --- - # - # With no block, installs a field converter: - # csv = CSV.new('') - # csv.convert(:integer) - # csv.convert(:float) - # csv.convert(:date) - # csv.converters # => [:integer, :float, :date] - # - # --- - # - # The block, if given, is called for each field: - # - Argument +field+ is the field value. - # - Argument +field_info+ is a CSV::FieldInfo object - # containing details about the field. - # - # The examples here assume the prior execution of: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # Example giving a block: - # csv = CSV.open(path) - # csv.convert {|field, field_info| p [field, field_info]; field.upcase } - # csv.read # => [["FOO", "0"], ["BAR", "1"], ["BAZ", "2"]] - # - # Output: - # ["foo", #<struct CSV::FieldInfo index=0, line=1, header=nil>] - # ["0", #<struct CSV::FieldInfo index=1, line=1, header=nil>] - # ["bar", #<struct CSV::FieldInfo index=0, line=2, header=nil>] - # ["1", #<struct CSV::FieldInfo index=1, line=2, header=nil>] - # ["baz", #<struct CSV::FieldInfo index=0, line=3, header=nil>] - # ["2", #<struct CSV::FieldInfo index=1, line=3, header=nil>] - # - # The block need not return a \String object: - # csv = CSV.open(path) - # csv.convert {|field, field_info| field.to_sym } - # csv.read # => [[:foo, :"0"], [:bar, :"1"], [:baz, :"2"]] - # - # If +converter_name+ is given, the block is not called: - # csv = CSV.open(path) - # csv.convert(:integer) {|field, field_info| fail 'Cannot happen' } - # csv.read # => [["foo", 0], ["bar", 1], ["baz", 2]] - # - # --- - # - # Raises a parse-time exception if +converter_name+ is not the name of a built-in - # field converter: - # csv = CSV.open(path) - # csv.convert(:nosuch) => [nil] - # # Raises NoMethodError (undefined method `arity' for nil:NilClass) - # csv.read - def convert(name = nil, &converter) - parser_fields_converter.add_converter(name, &converter) - end - - # :call-seq: - # header_convert(converter_name) -> array_of_procs - # header_convert {|header, field_info| ... } -> array_of_procs - # - # - With no block, installs a header converter (a \Proc). - # - With a block, defines and installs a custom header converter. - # - Returns the \Array of installed header converters. - # - # - Argument +converter_name+, if given, should be the name - # of an existing header converter. - # - # See {Header Converters}[#class-CSV-label-Header+Converters]. - # --- - # - # With no block, installs a header converter: - # csv = CSV.new('') - # csv.header_convert(:symbol) - # csv.header_convert(:downcase) - # csv.header_converters # => [:symbol, :downcase] - # - # --- - # - # The block, if given, is called for each header: - # - Argument +header+ is the header value. - # - Argument +field_info+ is a CSV::FieldInfo object - # containing details about the header. - # - # The examples here assume the prior execution of: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # - # Example giving a block: - # csv = CSV.open(path, headers: true) - # csv.header_convert {|header, field_info| p [header, field_info]; header.upcase } - # table = csv.read - # table # => #<CSV::Table mode:col_or_row row_count:4> - # table.headers # => ["NAME", "VALUE"] - # - # Output: - # ["Name", #<struct CSV::FieldInfo index=0, line=1, header=nil>] - # ["Value", #<struct CSV::FieldInfo index=1, line=1, header=nil>] - - # The block need not return a \String object: - # csv = CSV.open(path, headers: true) - # csv.header_convert {|header, field_info| header.to_sym } - # table = csv.read - # table.headers # => [:Name, :Value] - # - # If +converter_name+ is given, the block is not called: - # csv = CSV.open(path, headers: true) - # csv.header_convert(:downcase) {|header, field_info| fail 'Cannot happen' } - # table = csv.read - # table.headers # => ["name", "value"] - # --- - # - # Raises a parse-time exception if +converter_name+ is not the name of a built-in - # field converter: - # csv = CSV.open(path, headers: true) - # csv.header_convert(:nosuch) - # # Raises NoMethodError (undefined method `arity' for nil:NilClass) - # csv.read - def header_convert(name = nil, &converter) - header_fields_converter.add_converter(name, &converter) - end - - include Enumerable - - # :call-seq: - # csv.each -> enumerator - # csv.each {|row| ...} - # - # Calls the block with each successive row. - # The data source must be opened for reading. - # - # Without headers: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.each do |row| - # p row - # end - # Output: - # ["foo", "0"] - # ["bar", "1"] - # ["baz", "2"] - # - # With headers: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string, headers: true) - # csv.each do |row| - # p row - # end - # Output: - # <CSV::Row "Name":"foo" "Value":"0"> - # <CSV::Row "Name":"bar" "Value":"1"> - # <CSV::Row "Name":"baz" "Value":"2"> - # - # --- - # - # Raises an exception if the source is not opened for reading: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.close - # # Raises IOError (not opened for reading) - # csv.each do |row| - # p row - # end - def each(&block) - return to_enum(__method__) unless block_given? - begin - while true - yield(parser_enumerator.next) - end - rescue StopIteration - end - end - - # :call-seq: - # csv.read -> array or csv_table - # - # Forms the remaining rows from +self+ into: - # - A CSV::Table object, if headers are in use. - # - An \Array of Arrays, otherwise. - # - # The data source must be opened for reading. - # - # Without headers: - # string = "foo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # csv = CSV.open(path) - # csv.read # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # With headers: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # path = 't.csv' - # File.write(path, string) - # csv = CSV.open(path, headers: true) - # csv.read # => #<CSV::Table mode:col_or_row row_count:4> - # - # --- - # - # Raises an exception if the source is not opened for reading: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.close - # # Raises IOError (not opened for reading) - # csv.read - def read - rows = to_a - if parser.use_headers? - Table.new(rows, headers: parser.headers) - else - rows - end - end - alias_method :readlines, :read - - # :call-seq: - # csv.header_row? -> true or false - # - # Returns +true+ if the next row to be read is a header row\; - # +false+ otherwise. - # - # Without headers: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.header_row? # => false - # - # With headers: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string, headers: true) - # csv.header_row? # => true - # csv.shift # => #<CSV::Row "Name":"foo" "Value":"0"> - # csv.header_row? # => false - # - # --- - # - # Raises an exception if the source is not opened for reading: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.close - # # Raises IOError (not opened for reading) - # csv.header_row? - def header_row? - parser.header_row? - end - - # :call-seq: - # csv.shift -> array, csv_row, or nil - # - # Returns the next row of data as: - # - An \Array if no headers are used. - # - A CSV::Row object if headers are used. - # - # The data source must be opened for reading. - # - # Without headers: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.shift # => ["foo", "0"] - # csv.shift # => ["bar", "1"] - # csv.shift # => ["baz", "2"] - # csv.shift # => nil - # - # With headers: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string, headers: true) - # csv.shift # => #<CSV::Row "Name":"foo" "Value":"0"> - # csv.shift # => #<CSV::Row "Name":"bar" "Value":"1"> - # csv.shift # => #<CSV::Row "Name":"baz" "Value":"2"> - # csv.shift # => nil - # - # --- - # - # Raises an exception if the source is not opened for reading: - # string = "foo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string) - # csv.close - # # Raises IOError (not opened for reading) - # csv.shift - def shift - if @eof_error - eof_error, @eof_error = @eof_error, nil - raise eof_error - end - begin - parser_enumerator.next - rescue StopIteration - nil - end - end - alias_method :gets, :shift - alias_method :readline, :shift - - # :call-seq: - # csv.inspect -> string - # - # Returns a \String showing certain properties of +self+: - # string = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # csv = CSV.new(string, headers: true) - # s = csv.inspect - # s # => "#<CSV io_type:StringIO encoding:UTF-8 lineno:0 col_sep:\",\" row_sep:\"\\n\" quote_char:\"\\\"\" headers:true>" - def inspect - str = ["#<", self.class.to_s, " io_type:"] - # show type of wrapped IO - if @io == $stdout then str << "$stdout" - elsif @io == $stdin then str << "$stdin" - elsif @io == $stderr then str << "$stderr" - else str << @io.class.to_s - end - # show IO.path(), if available - if @io.respond_to?(:path) and (p = @io.path) - str << " io_path:" << p.inspect - end - # show encoding - str << " encoding:" << @encoding.name - # show other attributes - ["lineno", "col_sep", "row_sep", "quote_char"].each do |attr_name| - if a = __send__(attr_name) - str << " " << attr_name << ":" << a.inspect - end - end - ["skip_blanks", "liberal_parsing"].each do |attr_name| - if a = __send__("#{attr_name}?") - str << " " << attr_name << ":" << a.inspect - end - end - _headers = headers - str << " headers:" << _headers.inspect if _headers - str << ">" - begin - str.join('') - rescue # any encoding error - str.map do |s| - e = Encoding::Converter.asciicompat_encoding(s.encoding) - e ? s.encode(e) : s.force_encoding("ASCII-8BIT") - end.join('') - end - end - - private - - def determine_encoding(encoding, internal_encoding) - # honor the IO encoding if we can, otherwise default to ASCII-8BIT - io_encoding = raw_encoding - return io_encoding if io_encoding - - return Encoding.find(internal_encoding) if internal_encoding - - if encoding - encoding, = encoding.split(":", 2) if encoding.is_a?(String) - return Encoding.find(encoding) - end - - Encoding.default_internal || Encoding.default_external - end - - def normalize_converters(converters) - converters ||= [] - unless converters.is_a?(Array) - converters = [converters] - end - converters.collect do |converter| - case converter - when Proc # custom code block - [nil, converter] - else # by name - [converter, nil] - end - end - end - - # - # Processes +fields+ with <tt>@converters</tt>, or <tt>@header_converters</tt> - # 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 - # shortcut. - # - def convert_fields(fields, headers = false) - if headers - header_fields_converter.convert(fields, nil, 0) - else - parser_fields_converter.convert(fields, @headers, lineno) - end - end - - # - # 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 - - def parser_fields_converter - @parser_fields_converter ||= build_parser_fields_converter - end - - def build_parser_fields_converter - specific_options = { - builtin_converters_name: :Converters, - } - options = @base_fields_converter_options.merge(specific_options) - build_fields_converter(@initial_converters, options) - end - - def header_fields_converter - @header_fields_converter ||= build_header_fields_converter - end - - def build_header_fields_converter - specific_options = { - builtin_converters_name: :HeaderConverters, - accept_nil: true, - } - options = @base_fields_converter_options.merge(specific_options) - build_fields_converter(@initial_header_converters, options) - end - - def writer_fields_converter - @writer_fields_converter ||= build_writer_fields_converter - end - - def build_writer_fields_converter - build_fields_converter(@initial_write_converters, - @write_fields_converter_options) - end - - def build_fields_converter(initial_converters, options) - fields_converter = FieldsConverter.new(options) - normalize_converters(initial_converters).each do |name, converter| - fields_converter.add_converter(name, &converter) - end - fields_converter - end - - def parser - @parser ||= Parser.new(@io, parser_options) - end - - def parser_options - @parser_options.merge(header_fields_converter: header_fields_converter, - fields_converter: parser_fields_converter) - end - - def parser_enumerator - @parser_enumerator ||= parser.parse - end - - def writer - @writer ||= Writer.new(@io, writer_options) - end - - def writer_options - @writer_options.merge(header_fields_converter: header_fields_converter, - fields_converter: writer_fields_converter) - end -end - -# Passes +args+ to CSV::instance. -# -# CSV("CSV,data").read -# #=> [["CSV", "data"]] -# -# If a block is given, the instance is passed the block and the return value -# becomes the return value of the block. -# -# CSV("CSV,data") { |c| -# c.read.any? { |a| a.include?("data") } -# } #=> true -# -# CSV("CSV,data") { |c| -# c.read.any? { |a| a.include?("zombies") } -# } #=> false -# -# CSV options may also be given. -# -# io = StringIO.new -# CSV(io, col_sep: ";") { |csv| csv << ["a", "b", "c"] } -# -# This API is not Ractor-safe. -# -def CSV(*args, **options, &block) - CSV.instance(*args, **options, &block) -end - -require_relative "csv/version" -require_relative "csv/core_ext/array" -require_relative "csv/core_ext/string" diff --git a/lib/csv/core_ext/array.rb b/lib/csv/core_ext/array.rb deleted file mode 100644 index 8beb06b082..0000000000 --- a/lib/csv/core_ext/array.rb +++ /dev/null @@ -1,9 +0,0 @@ -class Array # :nodoc: - # Equivalent to CSV::generate_line(self, options) - # - # ["CSV", "data"].to_csv - # #=> "CSV,data\n" - def to_csv(**options) - CSV.generate_line(self, **options) - end -end diff --git a/lib/csv/core_ext/string.rb b/lib/csv/core_ext/string.rb deleted file mode 100644 index 9b1d31c2a4..0000000000 --- a/lib/csv/core_ext/string.rb +++ /dev/null @@ -1,9 +0,0 @@ -class String # :nodoc: - # Equivalent to CSV::parse_line(self, options) - # - # "CSV,data".parse_csv - # #=> ["CSV", "data"] - def parse_csv(**options) - CSV.parse_line(self, **options) - end -end diff --git a/lib/csv/csv.gemspec b/lib/csv/csv.gemspec deleted file mode 100644 index 11c5b0f2a6..0000000000 --- a/lib/csv/csv.gemspec +++ /dev/null @@ -1,64 +0,0 @@ -# frozen_string_literal: true - -begin - require_relative "lib/csv/version" -rescue LoadError - # for Ruby core repository - require_relative "version" -end - -Gem::Specification.new do |spec| - spec.name = "csv" - spec.version = CSV::VERSION - spec.authors = ["James Edward Gray II", "Kouhei Sutou"] - spec.email = [nil, "[email protected]"] - - spec.summary = "CSV Reading and Writing" - spec.description = "The CSV library 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." - spec.homepage = "https://github.com/ruby/csv" - spec.licenses = ["Ruby", "BSD-2-Clause"] - - lib_path = "lib" - spec.require_paths = [lib_path] - files = [] - lib_dir = File.join(__dir__, lib_path) - if File.exist?(lib_dir) - Dir.chdir(lib_dir) do - Dir.glob("**/*.rb").each do |file| - files << "lib/#{file}" - end - end - end - doc_dir = File.join(__dir__, "doc") - if File.exist?(doc_dir) - Dir.chdir(doc_dir) do - Dir.glob("**/*.rdoc").each do |rdoc_file| - files << "doc/#{rdoc_file}" - end - end - end - spec.files = files - spec.rdoc_options.concat(["--main", "README.md"]) - rdoc_files = [ - "LICENSE.txt", - "NEWS.md", - "README.md", - ] - recipes_dir = File.join(doc_dir, "csv", "recipes") - if File.exist?(recipes_dir) - Dir.chdir(recipes_dir) do - Dir.glob("**/*.rdoc").each do |recipe_file| - rdoc_files << "doc/csv/recipes/#{recipe_file}" - end - end - end - spec.extra_rdoc_files = rdoc_files - - spec.required_ruby_version = ">= 2.5.0" - - # spec.add_dependency "stringio", ">= 0.1.3" - spec.add_development_dependency "bundler" - spec.add_development_dependency "rake" - spec.add_development_dependency "benchmark_driver" - spec.add_development_dependency "test-unit", ">= 3.4.8" -end diff --git a/lib/csv/fields_converter.rb b/lib/csv/fields_converter.rb deleted file mode 100644 index d15977d379..0000000000 --- a/lib/csv/fields_converter.rb +++ /dev/null @@ -1,89 +0,0 @@ -# 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 = [] - @nil_value = options[:nil_value] - @empty_value = options[:empty_value] - @empty_value_is_empty_string = (@empty_value == "") - @accept_nil = options[:accept_nil] - @builtin_converters_name = options[:builtin_converters_name] - @need_static_convert = need_static_convert? - end - - def add_converter(name=nil, &converter) - if name.nil? # custom converter - @converters << converter - else # named converter - combo = builtin_converters[name] - case combo - when Array # combo converter - combo.each do |sub_name| - add_converter(sub_name) - end - else # individual named converter - @converters << combo - end - end - end - - def each(&block) - @converters.each(&block) - end - - def empty? - @converters.empty? - end - - def convert(fields, headers, lineno, quoted_fields) - return fields unless need_convert? - - fields.collect.with_index do |field, index| - if field.nil? - field = @nil_value - elsif field.is_a?(String) and field.empty? - field = @empty_value unless @empty_value_is_empty_string - end - @converters.each do |converter| - break if field.nil? and @accept_nil - if converter.arity == 1 # straight field converter - field = converter[field] - else # FieldInfo converter - if headers - header = headers[index] - else - header = nil - end - quoted = quoted_fields[index] - field = converter[field, FieldInfo.new(index, lineno, header, quoted)] - end - break unless field.is_a?(String) # short-circuit pipeline for speed - end - field # final state of each field, converted or original - end - end - - private - def need_static_convert? - not (@nil_value.nil? and @empty_value_is_empty_string) - end - - def need_convert? - @need_static_convert or - (not @converters.empty?) - end - - def builtin_converters - @builtin_converters ||= ::CSV.const_get(@builtin_converters_name) - end - end -end diff --git a/lib/csv/input_record_separator.rb b/lib/csv/input_record_separator.rb deleted file mode 100644 index 7a99343c0c..0000000000 --- a/lib/csv/input_record_separator.rb +++ /dev/null @@ -1,18 +0,0 @@ -require "English" -require "stringio" - -class CSV - module InputRecordSeparator - class << self - if RUBY_VERSION >= "3.0.0" - def value - "\n" - end - else - def value - $INPUT_RECORD_SEPARATOR - end - end - end - end -end diff --git a/lib/csv/parser.rb b/lib/csv/parser.rb deleted file mode 100644 index 4da87fbac8..0000000000 --- a/lib/csv/parser.rb +++ /dev/null @@ -1,1288 +0,0 @@ -# frozen_string_literal: true - -require "strscan" - -require_relative "input_record_separator" -require_relative "row" -require_relative "table" - -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 - - # Raised when unexpected case is happen. - class UnexpectedError < 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 - - def initialize(*args) - super - @keeps = [] - end - - def each_line(row_separator) - position = pos - rest.each_line(row_separator) do |line| - position += line.bytesize - self.pos = position - yield(line) - end - end - - def keep_start - @keeps.push(pos) - end - - def keep_end - start = @keeps.pop - string.byteslice(start, pos - start) - end - - def keep_back - self.pos = @keeps.pop - end - - def keep_drop - @keeps.pop - 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, row_separator, chunk_size: 8192) - @inputs = inputs.dup - @encoding = encoding - @row_separator = row_separator - @chunk_size = chunk_size - @last_scanner = @inputs.empty? - @keeps = [] - read_chunk - end - - def each_line(row_separator) - return enum_for(__method__, row_separator) unless block_given? - buffer = nil - input = @scanner.rest - position = @scanner.pos - offset = 0 - n_row_separator_chars = row_separator.size - # trace(__method__, :start, input) - while true - input.each_line(row_separator) do |line| - @scanner.pos += line.bytesize - if buffer - if n_row_separator_chars == 2 and - buffer.end_with?(row_separator[0]) and - line.start_with?(row_separator[1]) - buffer << line[0] - line = line[1..-1] - position += buffer.bytesize + offset - @scanner.pos = position - offset = 0 - yield(buffer) - buffer = nil - next if line.empty? - else - buffer << line - line = buffer - buffer = nil - end - end - if line.end_with?(row_separator) - position += line.bytesize + offset - @scanner.pos = position - offset = 0 - yield(line) - else - buffer = line - end - end - break unless read_chunk - input = @scanner.rest - position = @scanner.pos - offset = -buffer.bytesize if buffer - end - yield(buffer) if buffer - end - - def scan(pattern) - # trace(__method__, pattern, :start) - value = @scanner.scan(pattern) - # trace(__method__, pattern, :done, :last, value) if @last_scanner - return value if @last_scanner - - read_chunk if value and @scanner.eos? - # trace(__method__, pattern, :done, value) - value - end - - def scan_all(pattern) - # trace(__method__, pattern, :start) - value = @scanner.scan(pattern) - # trace(__method__, pattern, :done, :last, value) if @last_scanner - return value if @last_scanner - - # trace(__method__, pattern, :done, :nil) if value.nil? - return nil if value.nil? - while @scanner.eos? and read_chunk and (sub_value = @scanner.scan(pattern)) - # trace(__method__, pattern, :sub, sub_value) - value << sub_value - end - # trace(__method__, pattern, :done, value) - value - end - - def eos? - @scanner.eos? - end - - def keep_start - # trace(__method__, :start) - adjust_last_keep - @keeps.push([@scanner, @scanner.pos, nil]) - # trace(__method__, :done) - end - - def keep_end - # trace(__method__, :start) - scanner, start, buffer = @keeps.pop - if scanner == @scanner - keep = @scanner.string.byteslice(start, @scanner.pos - start) - else - keep = @scanner.string.byteslice(0, @scanner.pos) - end - if buffer - buffer << keep - keep = buffer - end - # trace(__method__, :done, keep) - keep - end - - def keep_back - # trace(__method__, :start) - scanner, start, buffer = @keeps.pop - if buffer - # trace(__method__, :rescan, start, buffer) - string = @scanner.string - if scanner == @scanner - keep = string.byteslice(start, - string.bytesize - @scanner.pos - start) - else - keep = string - end - if keep and not keep.empty? - @inputs.unshift(StringIO.new(keep)) - @last_scanner = false - end - @scanner = StringScanner.new(buffer) - else - if @scanner != scanner - message = "scanners are different but no buffer: " - message += "#{@scanner.inspect}(#{@scanner.object_id}): " - message += "#{scanner.inspect}(#{scanner.object_id})" - raise UnexpectedError, message - end - # trace(__method__, :repos, start, buffer) - @scanner.pos = start - end - read_chunk if @scanner.eos? - end - - def keep_drop - _, _, buffer = @keeps.pop - # trace(__method__, :done, :empty) unless buffer - return unless buffer - - last_keep = @keeps.last - # trace(__method__, :done, :no_last_keep) unless last_keep - return unless last_keep - - if last_keep[2] - last_keep[2] << buffer - else - last_keep[2] = buffer - end - # trace(__method__, :done) - end - - def rest - @scanner.rest - end - - def check(pattern) - @scanner.check(pattern) - end - - private - def trace(*args) - pp([*args, @scanner, @scanner&.string, @scanner&.pos, @keeps]) - end - - def adjust_last_keep - # trace(__method__, :start) - - keep = @keeps.last - # trace(__method__, :done, :empty) if keep.nil? - return if keep.nil? - - scanner, start, buffer = keep - string = @scanner.string - if @scanner != scanner - start = 0 - end - if start == 0 and @scanner.eos? - keep_data = string - else - keep_data = string.byteslice(start, @scanner.pos - start) - end - if keep_data - if buffer - buffer << keep_data - else - keep[2] = keep_data.dup - end - end - - # trace(__method__, :done) - end - - def read_chunk - return false if @last_scanner - - adjust_last_keep - - input = @inputs.first - case input - when StringIO - string = input.read - raise InvalidEncoding unless string.valid_encoding? - # trace(__method__, :stringio, string) - @scanner = StringScanner.new(string) - @inputs.shift - @last_scanner = @inputs.empty? - true - else - chunk = input.gets(@row_separator, @chunk_size) - if chunk - raise InvalidEncoding unless chunk.valid_encoding? - # trace(__method__, :chunk, chunk) - @scanner = StringScanner.new(chunk) - if input.respond_to?(:eof?) and input.eof? - @inputs.shift - @last_scanner = @inputs.empty? - end - true - else - # trace(__method__, :no_chunk) - @scanner = StringScanner.new("".encode(@encoding)) - @inputs.shift - @last_scanner = @inputs.empty? - if @last_scanner - false - else - read_chunk - end - end - end - end - end - - def initialize(input, options) - @input = input - @options = options - @samples = [] - - prepare - end - - def column_separator - @column_separator - end - - def row_separator - @row_separator - end - - def quote_character - @quote_character - end - - def field_size_limit - @max_field_size&.succ - end - - def max_field_size - @max_field_size - end - - def skip_lines - @skip_lines - end - - def unconverted_fields? - @unconverted_fields - end - - def headers - @headers - end - - def header_row? - @use_headers and @headers.nil? - end - - def return_headers? - @return_headers - end - - def skip_blanks? - @skip_blanks - end - - def liberal_parsing? - @liberal_parsing - end - - def lineno - @lineno - end - - def line - last_line - end - - def parse(&block) - return to_enum(__method__) unless block_given? - - if @return_headers and @headers and @raw_headers - headers = Row.new(@headers, @raw_headers, true) - if @unconverted_fields - headers = add_unconverted_fields(headers, []) - end - yield headers - end - - begin - @scanner ||= build_scanner - if quote_character.nil? - parse_no_quote(&block) - elsif @need_robust_parsing - parse_quotable_robust(&block) - else - parse_quotable_loose(&block) - end - rescue InvalidEncoding - if @scanner - ignore_broken_line - lineno = @lineno - else - lineno = @lineno + 1 - end - raise InvalidEncodingError.new(@encoding, lineno) - rescue UnexpectedError => error - if @scanner - ignore_broken_line - lineno = @lineno - else - lineno = @lineno + 1 - end - message = "This should not be happen: #{error.message}: " - message += "Please report this to https://github.com/ruby/csv/issues" - raise MalformedCSVError.new(message, lineno) - end - end - - def use_headers? - @use_headers - end - - private - # A set of tasks to prepare the file in order to parse it - def prepare - prepare_variable - prepare_quote_character - prepare_backslash - prepare_skip_lines - prepare_strip - prepare_separators - validate_strip_and_col_sep_options - prepare_quoted - prepare_unquoted - prepare_line - prepare_header - prepare_parser - end - - def prepare_variable - @need_robust_parsing = false - @encoding = @options[:encoding] - liberal_parsing = @options[:liberal_parsing] - if liberal_parsing - @liberal_parsing = true - if liberal_parsing.is_a?(Hash) - @double_quote_outside_quote = - liberal_parsing[:double_quote_outside_quote] - @backslash_quote = liberal_parsing[:backslash_quote] - else - @double_quote_outside_quote = false - @backslash_quote = false - end - @need_robust_parsing = true - else - @liberal_parsing = false - @backslash_quote = false - end - @unconverted_fields = @options[:unconverted_fields] - @max_field_size = @options[:max_field_size] - @skip_blanks = @options[:skip_blanks] - @fields_converter = @options[:fields_converter] - @header_fields_converter = @options[:header_fields_converter] - end - - def prepare_quote_character - @quote_character = @options[:quote_character] - if @quote_character.nil? - @escaped_quote_character = nil - @escaped_quote = nil - else - @quote_character = @quote_character.to_s.encode(@encoding) - if @quote_character.length != 1 - message = ":quote_char has to be nil or a single character String" - raise ArgumentError, message - end - @escaped_quote_character = Regexp.escape(@quote_character) - @escaped_quote = Regexp.new(@escaped_quote_character) - end - end - - def prepare_backslash - return unless @backslash_quote - - @backslash_character = "\\".encode(@encoding) - - @escaped_backslash_character = Regexp.escape(@backslash_character) - @escaped_backslash = Regexp.new(@escaped_backslash_character) - if @quote_character.nil? - @backslash_quote_character = nil - else - @backslash_quote_character = - @backslash_character + @escaped_quote_character - end - end - - def prepare_skip_lines - skip_lines = @options[:skip_lines] - case skip_lines - when String - @skip_lines = skip_lines.encode(@encoding) - when Regexp, nil - @skip_lines = skip_lines - else - unless skip_lines.respond_to?(:match) - message = - ":skip_lines has to respond to \#match: #{skip_lines.inspect}" - raise ArgumentError, message - end - @skip_lines = skip_lines - end - end - - def prepare_strip - @strip = @options[:strip] - @escaped_strip = nil - @strip_value = nil - @rstrip_value = nil - if @strip.is_a?(String) - case @strip.length - when 0 - raise ArgumentError, ":strip must not be an empty String" - when 1 - # ok - else - raise ArgumentError, ":strip doesn't support 2 or more characters yet" - end - @strip = @strip.encode(@encoding) - @escaped_strip = Regexp.escape(@strip) - if @quote_character - @strip_value = Regexp.new(@escaped_strip + - "+".encode(@encoding)) - @rstrip_value = Regexp.new(@escaped_strip + - "+\\z".encode(@encoding)) - end - @need_robust_parsing = true - elsif @strip - strip_values = " \t\f\v" - @escaped_strip = strip_values.encode(@encoding) - if @quote_character - @strip_value = Regexp.new("[#{strip_values}]+".encode(@encoding)) - @rstrip_value = Regexp.new("[#{strip_values}]+\\z".encode(@encoding)) - end - @need_robust_parsing = true - end - end - - begin - StringScanner.new("x").scan("x") - rescue TypeError - STRING_SCANNER_SCAN_ACCEPT_STRING = false - else - STRING_SCANNER_SCAN_ACCEPT_STRING = true - end - - def prepare_separators - 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) - - @escaped_column_separator = Regexp.escape(@column_separator) - @escaped_first_column_separator = Regexp.escape(@column_separator[0]) - if @column_separator.size > 1 - @column_end = Regexp.new(@escaped_column_separator) - @column_ends = @column_separator.each_char.collect do |char| - Regexp.new(Regexp.escape(char)) - end - @first_column_separators = Regexp.new(@escaped_first_column_separator + - "+".encode(@encoding)) - else - if STRING_SCANNER_SCAN_ACCEPT_STRING - @column_end = @column_separator - else - @column_end = Regexp.new(@escaped_column_separator) - end - @column_ends = nil - @first_column_separators = nil - end - - escaped_row_separator = Regexp.escape(@row_separator) - @row_end = Regexp.new(escaped_row_separator) - if @row_separator.size > 1 - @row_ends = @row_separator.each_char.collect do |char| - Regexp.new(Regexp.escape(char)) - end - else - @row_ends = nil - end - - @cr = "\r".encode(@encoding) - @lf = "\n".encode(@encoding) - @line_end = Regexp.new("\r\n|\n|\r".encode(@encoding)) - @not_line_end = Regexp.new("[^\r\n]+".encode(@encoding)) - end - - # This method verifies that there are no (obvious) ambiguities with the - # provided +col_sep+ and +strip+ parsing options. For example, if +col_sep+ - # and +strip+ were both equal to +\t+, then there would be no clear way to - # parse the input. - def validate_strip_and_col_sep_options - return unless @strip - - if @strip.is_a?(String) - if @column_separator.start_with?(@strip) || @column_separator.end_with?(@strip) - raise ArgumentError, - "The provided strip (#{@escaped_strip}) and " \ - "col_sep (#{@escaped_column_separator}) options are incompatible." - end - else - if Regexp.new("\\A[#{@escaped_strip}]|[#{@escaped_strip}]\\z").match?(@column_separator) - raise ArgumentError, - "The provided strip (true) and " \ - "col_sep (#{@escaped_column_separator}) options are incompatible." - end - end - end - - def prepare_quoted - if @quote_character - @quotes = Regexp.new(@escaped_quote_character + - "+".encode(@encoding)) - no_quoted_values = @escaped_quote_character.dup - if @backslash_quote - no_quoted_values << @escaped_backslash_character - end - @quoted_value = Regexp.new("[^".encode(@encoding) + - no_quoted_values + - "]+".encode(@encoding)) - end - if @escaped_strip - @split_column_separator = Regexp.new(@escaped_strip + - "*".encode(@encoding) + - @escaped_column_separator + - @escaped_strip + - "*".encode(@encoding)) - else - if @column_separator == " ".encode(@encoding) - @split_column_separator = Regexp.new(@escaped_column_separator) - else - @split_column_separator = @column_separator - end - end - end - - def prepare_unquoted - return if @quote_character.nil? - - no_unquoted_values = "\r\n".encode(@encoding) - no_unquoted_values << @escaped_first_column_separator - unless @liberal_parsing - no_unquoted_values << @escaped_quote_character - end - @unquoted_value = Regexp.new("[^".encode(@encoding) + - no_unquoted_values + - "]+".encode(@encoding)) - end - - def resolve_row_separator(separator) - if separator == :auto - cr = "\r".encode(@encoding) - lf = "\n".encode(@encoding) - if @input.is_a?(StringIO) - 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 - else - chunk_size = 1024 - end - begin - while separator == :auto - # - # if we run out of data, it's probably a single line - # (ensure will set default value) - # - break unless sample = @input.gets(nil, chunk_size) - - # extend sample if we're unsure of the line ending - if sample.end_with?(cr) - sample << (@input.gets(nil, 1) || "") - end - - @samples << sample - - separator = detect_row_separator(sample, cr, lf) - end - rescue IOError - # do nothing: ensure will set default - end - end - separator = InputRecordSeparator.value if separator == :auto - end - separator.to_s.encode(@encoding) - end - - def detect_row_separator(sample, cr, lf) - lf_index = sample.index(lf) - if lf_index - cr_index = sample[0, lf_index].index(cr) - else - cr_index = sample.index(cr) - end - if cr_index and lf_index - if cr_index + 1 == lf_index - cr + lf - elsif cr_index < lf_index - cr - else - lf - end - elsif cr_index - cr - elsif lf_index - lf - else - :auto - end - end - - def prepare_line - @lineno = 0 - @last_line = nil - @scanner = nil - end - - def last_line - if @scanner - @last_line ||= @scanner.keep_end - else - @last_line - end - end - - def prepare_header - @return_headers = @options[:return_headers] - - headers = @options[:headers] - case headers - when Array - @raw_headers = headers - quoted_fields = [false] * @raw_headers.size - @use_headers = true - when String - @raw_headers, quoted_fields = parse_headers(headers) - @use_headers = true - when nil, false - @raw_headers = nil - @use_headers = false - else - @raw_headers = nil - @use_headers = true - end - if @raw_headers - @headers = adjust_headers(@raw_headers, quoted_fields) - else - @headers = nil - end - end - - def parse_headers(row) - quoted_fields = [] - converter = lambda do |field, info| - quoted_fields << info.quoted? - field - end - headers = CSV.parse_line(row, - col_sep: @column_separator, - row_sep: @row_separator, - quote_char: @quote_character, - converters: [converter]) - [headers, quoted_fields] - end - - def adjust_headers(headers, quoted_fields) - adjusted_headers = @header_fields_converter.convert(headers, nil, @lineno, quoted_fields) - adjusted_headers.each {|h| h.freeze if h.is_a? String} - adjusted_headers - end - - def prepare_parser - @may_quoted = may_quoted? - end - - def may_quoted? - return false if @quote_character.nil? - - if @input.is_a?(StringIO) - pos = @input.pos - sample = @input.read - @input.seek(pos) - else - return false if @samples.empty? - sample = @samples.first - end - sample[0, 128].index(@quote_character) - end - - class UnoptimizedStringIO # :nodoc: - def initialize(string) - @io = StringIO.new(string, "rb:#{string.encoding}") - end - - def gets(*args) - @io.gets(*args) - end - - def each_line(*args, &block) - @io.each_line(*args, &block) - end - - def eof? - @io.eof? - end - end - - SCANNER_TEST = (ENV["CSV_PARSER_SCANNER_TEST"] == "yes") - if SCANNER_TEST - SCANNER_TEST_CHUNK_SIZE_NAME = "CSV_PARSER_SCANNER_TEST_CHUNK_SIZE" - SCANNER_TEST_CHUNK_SIZE_VALUE = ENV[SCANNER_TEST_CHUNK_SIZE_NAME] - def build_scanner - inputs = @samples.collect do |sample| - UnoptimizedStringIO.new(sample) - end - if @input.is_a?(StringIO) - inputs << UnoptimizedStringIO.new(@input.read) - else - inputs << @input - end - begin - chunk_size_value = ENV[SCANNER_TEST_CHUNK_SIZE_NAME] - rescue # Ractor::IsolationError - # Ractor on Ruby 3.0 can't read ENV value. - chunk_size_value = SCANNER_TEST_CHUNK_SIZE_VALUE - end - chunk_size = Integer((chunk_size_value || "1"), 10) - InputsScanner.new(inputs, - @encoding, - @row_separator, - chunk_size: chunk_size) - end - else - def build_scanner - string = nil - if @samples.empty? and @input.is_a?(StringIO) - string = @input.read - elsif @samples.size == 1 and - @input != ARGF and - @input.respond_to?(:eof?) and - @input.eof? - string = @samples[0] - end - if string - unless string.valid_encoding? - index = string.lines(@row_separator).index do |line| - !line.valid_encoding? - end - if index - raise InvalidEncodingError.new(@encoding, @lineno + index + 1) - end - end - Scanner.new(string) - else - inputs = @samples.collect do |sample| - StringIO.new(sample) - end - inputs << @input - InputsScanner.new(inputs, @encoding, @row_separator) - end - end - end - - def skip_needless_lines - return unless @skip_lines - - until @scanner.eos? - @scanner.keep_start - line = @scanner.scan_all(@not_line_end) || "".encode(@encoding) - line << @row_separator if parse_row_end - if skip_line?(line) - @lineno += 1 - @scanner.keep_drop - else - @scanner.keep_back - return - end - end - end - - def skip_line?(line) - line = line.delete_suffix(@row_separator) - case @skip_lines - when String - line.include?(@skip_lines) - when Regexp - @skip_lines.match?(line) - else - @skip_lines.match(line) - end - end - - def validate_field_size(field) - return unless @max_field_size - return if field.size <= @max_field_size - ignore_broken_line - message = "Field size exceeded: #{field.size} > #{@max_field_size}" - raise MalformedCSVError.new(message, @lineno) - end - - def parse_no_quote(&block) - @scanner.each_line(@row_separator) do |line| - next if @skip_lines and skip_line?(line) - original_line = line - line = line.delete_suffix(@row_separator) - - if line.empty? - next if @skip_blanks - row = [] - quoted_fields = [] - else - line = strip_value(line) - row = line.split(@split_column_separator, -1) - quoted_fields = [false] * row.size - if @max_field_size - row.each do |column| - validate_field_size(column) - end - end - n_columns = row.size - i = 0 - while i < n_columns - row[i] = nil if row[i].empty? - i += 1 - end - end - @last_line = original_line - emit_row(row, quoted_fields, &block) - end - end - - def parse_quotable_loose(&block) - @scanner.keep_start - @scanner.each_line(@row_separator) do |line| - if @skip_lines and skip_line?(line) - @scanner.keep_drop - @scanner.keep_start - next - end - original_line = line - line = line.delete_suffix(@row_separator) - - if line.empty? - if @skip_blanks - @scanner.keep_drop - @scanner.keep_start - next - end - row = [] - quoted_fields = [] - elsif line.include?(@cr) or line.include?(@lf) - @scanner.keep_back - @need_robust_parsing = true - return parse_quotable_robust(&block) - else - row = line.split(@split_column_separator, -1) - quoted_fields = [] - n_columns = row.size - i = 0 - while i < n_columns - column = row[i] - if column.empty? - quoted_fields << false - row[i] = nil - else - n_quotes = column.count(@quote_character) - if n_quotes.zero? - quoted_fields << false - # no quote - elsif n_quotes == 2 and - column.start_with?(@quote_character) and - column.end_with?(@quote_character) - quoted_fields << true - row[i] = column[1..-2] - else - @scanner.keep_back - @need_robust_parsing = true - return parse_quotable_robust(&block) - end - validate_field_size(row[i]) - end - i += 1 - end - end - @scanner.keep_drop - @scanner.keep_start - @last_line = original_line - emit_row(row, quoted_fields, &block) - end - @scanner.keep_drop - end - - def parse_quotable_robust(&block) - row = [] - quoted_fields = [] - skip_needless_lines - start_row - while true - @quoted_column_value = false - @unquoted_column_value = false - @scanner.scan_all(@strip_value) if @strip_value - value = parse_column_value - if value - @scanner.scan_all(@strip_value) if @strip_value - validate_field_size(value) - end - if parse_column_end - row << value - quoted_fields << @quoted_column_value - elsif parse_row_end - if row.empty? and value.nil? - emit_row([], [], &block) unless @skip_blanks - else - row << value - quoted_fields << @quoted_column_value - emit_row(row, quoted_fields, &block) - row = [] - quoted_fields = [] - end - skip_needless_lines - start_row - elsif @scanner.eos? - break if row.empty? and value.nil? - row << value - quoted_fields << @quoted_column_value - emit_row(row, quoted_fields, &block) - break - else - if @quoted_column_value - if liberal_parsing? and (new_line = @scanner.check(@line_end)) - message = - "Illegal end-of-line sequence outside of a quoted field " + - "<#{new_line.inspect}>" - else - message = "Any value after quoted field isn't allowed" - end - ignore_broken_line - raise MalformedCSVError.new(message, @lineno) - elsif @unquoted_column_value and - (new_line = @scanner.scan(@line_end)) - ignore_broken_line - message = "Unquoted fields do not allow new line " + - "<#{new_line.inspect}>" - raise MalformedCSVError.new(message, @lineno) - elsif @scanner.rest.start_with?(@quote_character) - ignore_broken_line - message = "Illegal quoting" - raise MalformedCSVError.new(message, @lineno) - elsif (new_line = @scanner.scan(@line_end)) - ignore_broken_line - message = "New line must be <#{@row_separator.inspect}> " + - "not <#{new_line.inspect}>" - raise MalformedCSVError.new(message, @lineno) - else - ignore_broken_line - raise MalformedCSVError.new("TODO: Meaningful message", - @lineno) - end - end - end - end - - def parse_column_value - if @liberal_parsing - quoted_value = parse_quoted_column_value - if quoted_value - @scanner.scan_all(@strip_value) if @strip_value - unquoted_value = parse_unquoted_column_value - if unquoted_value - if @double_quote_outside_quote - unquoted_value = unquoted_value.gsub(@quote_character * 2, - @quote_character) - if quoted_value.empty? # %Q{""...} case - return @quote_character + unquoted_value - end - end - @quote_character + quoted_value + @quote_character + unquoted_value - else - quoted_value - end - else - parse_unquoted_column_value - end - elsif @may_quoted - parse_quoted_column_value || - parse_unquoted_column_value - else - parse_unquoted_column_value || - parse_quoted_column_value - end - end - - def parse_unquoted_column_value - value = @scanner.scan_all(@unquoted_value) - return nil unless value - - @unquoted_column_value = true - if @first_column_separators - while true - @scanner.keep_start - is_column_end = @column_ends.all? do |column_end| - @scanner.scan(column_end) - end - @scanner.keep_back - break if is_column_end - sub_separator = @scanner.scan_all(@first_column_separators) - break if sub_separator.nil? - value << sub_separator - sub_value = @scanner.scan_all(@unquoted_value) - break if sub_value.nil? - value << sub_value - end - end - value.gsub!(@backslash_quote_character, @quote_character) if @backslash_quote - if @rstrip_value - value.gsub!(@rstrip_value, "") - end - value - end - - def parse_quoted_column_value - quotes = @scanner.scan_all(@quotes) - return nil unless quotes - - @quoted_column_value = true - n_quotes = quotes.size - if (n_quotes % 2).zero? - quotes[0, (n_quotes - 2) / 2] - else - value = quotes[0, n_quotes / 2] - while true - quoted_value = @scanner.scan_all(@quoted_value) - value << quoted_value if quoted_value - if @backslash_quote - if @scanner.scan(@escaped_backslash) - if @scanner.scan(@escaped_quote) - value << @quote_character - else - value << @backslash_character - end - next - end - end - - quotes = @scanner.scan_all(@quotes) - unless quotes - ignore_broken_line - message = "Unclosed quoted field" - raise MalformedCSVError.new(message, @lineno) - end - n_quotes = quotes.size - if n_quotes == 1 - break - else - value << quotes[0, n_quotes / 2] - break if (n_quotes % 2) == 1 - end - end - value - end - end - - def parse_column_end - return true if @scanner.scan(@column_end) - return false unless @column_ends - - @scanner.keep_start - if @column_ends.all? {|column_end| @scanner.scan(column_end)} - @scanner.keep_drop - true - else - @scanner.keep_back - false - end - end - - def parse_row_end - return true if @scanner.scan(@row_end) - return false unless @row_ends - @scanner.keep_start - if @row_ends.all? {|row_end| @scanner.scan(row_end)} - @scanner.keep_drop - true - else - @scanner.keep_back - false - end - end - - def strip_value(value) - return value unless @strip - return value if value.nil? - - case @strip - when String - while value.delete_prefix!(@strip) - # do nothing - end - while value.delete_suffix!(@strip) - # do nothing - end - else - value.strip! - end - value - end - - def ignore_broken_line - @scanner.scan_all(@not_line_end) - @scanner.scan_all(@line_end) - @lineno += 1 - end - - def start_row - if @last_line - @last_line = nil - else - @scanner.keep_drop - end - @scanner.keep_start - end - - def emit_row(row, quoted_fields, &block) - @lineno += 1 - - raw_row = row - if @use_headers - if @headers.nil? - @headers = adjust_headers(row, quoted_fields) - return unless @return_headers - row = Row.new(@headers, row, true) - else - row = Row.new(@headers, - @fields_converter.convert(raw_row, @headers, @lineno, quoted_fields)) - end - else - # convert fields, if needed... - row = @fields_converter.convert(raw_row, nil, @lineno, quoted_fields) - end - - # inject unconverted fields and accessor, if requested... - if @unconverted_fields and not row.respond_to?(:unconverted_fields) - add_unconverted_fields(row, raw_row) - end - - yield(row) - 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 - end - row.instance_variable_set(:@unconverted_fields, fields) - row - end - end -end diff --git a/lib/csv/row.rb b/lib/csv/row.rb deleted file mode 100644 index 86323f7d0a..0000000000 --- a/lib/csv/row.rb +++ /dev/null @@ -1,757 +0,0 @@ -# frozen_string_literal: true - -require "forwardable" - -class CSV - # = \CSV::Row - # A \CSV::Row instance represents a \CSV table row. - # (see {class CSV}[../CSV.html]). - # - # The instance may have: - # - Fields: each is an object, not necessarily a \String. - # - Headers: each serves a key, and also need not be a \String. - # - # === Instance Methods - # - # \CSV::Row has three groups of instance methods: - # - Its own internally defined instance methods. - # - Methods included by module Enumerable. - # - Methods delegated to class Array.: - # * Array#empty? - # * Array#length - # * Array#size - # - # == Creating a \CSV::Row Instance - # - # Commonly, a new \CSV::Row instance is created by parsing \CSV source - # that has headers: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.each {|row| p row } - # Output: - # #<CSV::Row "Name":"foo" "Value":"0"> - # #<CSV::Row "Name":"bar" "Value":"1"> - # #<CSV::Row "Name":"baz" "Value":"2"> - # - # You can also create a row directly. See ::new. - # - # == Headers - # - # Like a \CSV::Table, a \CSV::Row has headers. - # - # A \CSV::Row that was created by parsing \CSV source - # inherits its headers from the table: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table.first - # row.headers # => ["Name", "Value"] - # - # You can also create a new row with headers; - # like the keys in a \Hash, the headers need not be Strings: - # row = CSV::Row.new([:name, :value], ['foo', 0]) - # row.headers # => [:name, :value] - # - # The new row retains its headers even if added to a table - # that has headers: - # table << row # => #<CSV::Table mode:col_or_row row_count:5> - # row.headers # => [:name, :value] - # row[:name] # => "foo" - # row['Name'] # => nil - # - # - # - # == Accessing Fields - # - # You may access a field in a \CSV::Row with either its \Integer index - # (\Array-style) or its header (\Hash-style). - # - # Fetch a field using method #[]: - # row = CSV::Row.new(['Name', 'Value'], ['foo', 0]) - # row[1] # => 0 - # row['Value'] # => 0 - # - # Set a field using method #[]=: - # row = CSV::Row.new(['Name', 'Value'], ['foo', 0]) - # row # => #<CSV::Row "Name":"foo" "Value":0> - # row[0] = 'bar' - # row['Value'] = 1 - # row # => #<CSV::Row "Name":"bar" "Value":1> - # - class Row - # :call-seq: - # CSV::Row.new(headers, fields, header_row = false) -> csv_row - # - # Returns the new \CSV::Row instance constructed from - # arguments +headers+ and +fields+; both should be Arrays; - # note that the fields need not be Strings: - # row = CSV::Row.new(['Name', 'Value'], ['foo', 0]) - # row # => #<CSV::Row "Name":"foo" "Value":0> - # - # If the \Array lengths are different, the shorter is +nil+-filled: - # row = CSV::Row.new(['Name', 'Value', 'Date', 'Size'], ['foo', 0]) - # row # => #<CSV::Row "Name":"foo" "Value":0 "Date":nil "Size":nil> - # - # Each \CSV::Row object is either a <i>field row</i> or a <i>header row</i>; - # by default, a new row is a field row; for the row created above: - # row.field_row? # => true - # row.header_row? # => false - # - # If the optional argument +header_row+ is given as +true+, - # the created row is a header row: - # row = CSV::Row.new(['Name', 'Value'], ['foo', 0], header_row = true) - # row # => #<CSV::Row "Name":"foo" "Value":0> - # row.field_row? # => false - # row.header_row? # => true - def initialize(headers, fields, header_row = false) - @header_row = header_row - headers.each { |h| h.freeze if h.is_a? String } - - # handle extra headers or fields - @row = if headers.size >= fields.size - headers.zip(fields) - else - fields.zip(headers).each(&:reverse!) - end - end - - # Internal data format used to compare equality. - attr_reader :row - protected :row - - ### Array Delegation ### - - extend Forwardable - def_delegators :@row, :empty?, :length, :size - - # :call-seq: - # row.initialize_copy(other_row) -> self - # - # Calls superclass method. - def initialize_copy(other) - super_return_value = super - @row = @row.collect(&:dup) - super_return_value - end - - # :call-seq: - # row.header_row? -> true or false - # - # Returns +true+ if this is a header row, +false+ otherwise. - def header_row? - @header_row - end - - # :call-seq: - # row.field_row? -> true or false - # - # Returns +true+ if this is a field row, +false+ otherwise. - def field_row? - not header_row? - end - - # :call-seq: - # row.headers -> array_of_headers - # - # Returns the headers for this row: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table.first - # row.headers # => ["Name", "Value"] - def headers - @row.map(&:first) - end - - # :call-seq: - # field(index) -> value - # field(header) -> value - # field(header, offset) -> value - # - # Returns the field value for the given +index+ or +header+. - # - # --- - # - # Fetch field value by \Integer index: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.field(0) # => "foo" - # row.field(1) # => "bar" - # - # Counts backward from the last column if +index+ is negative: - # row.field(-1) # => "0" - # row.field(-2) # => "foo" - # - # Returns +nil+ if +index+ is out of range: - # row.field(2) # => nil - # row.field(-3) # => nil - # - # --- - # - # Fetch field value by header (first found): - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.field('Name') # => "Foo" - # - # Fetch field value by header, ignoring +offset+ leading fields: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.field('Name', 2) # => "Baz" - # - # Returns +nil+ if the header does not exist. - def field(header_or_index, minimum_index = 0) - # locate the pair - finder = (header_or_index.is_a?(Integer) || header_or_index.is_a?(Range)) ? :[] : :assoc - pair = @row[minimum_index..-1].public_send(finder, header_or_index) - - # return the field if we have a pair - if pair.nil? - nil - else - header_or_index.is_a?(Range) ? pair.map(&:last) : pair.last - end - end - alias_method :[], :field - - # - # :call-seq: - # fetch(header) -> value - # fetch(header, default) -> value - # fetch(header) {|row| ... } -> value - # - # Returns the field value as specified by +header+. - # - # --- - # - # With the single argument +header+, returns the field value - # for that header (first found): - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.fetch('Name') # => "Foo" - # - # Raises exception +KeyError+ if the header does not exist. - # - # --- - # - # With arguments +header+ and +default+ given, - # returns the field value for the header (first found) - # if the header exists, otherwise returns +default+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.fetch('Name', '') # => "Foo" - # row.fetch(:nosuch, '') # => "" - # - # --- - # - # With argument +header+ and a block given, - # returns the field value for the header (first found) - # if the header exists; otherwise calls the block - # and returns its return value: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.fetch('Name') {|header| fail 'Cannot happen' } # => "Foo" - # row.fetch(:nosuch) {|header| "Header '#{header} not found'" } # => "Header 'nosuch not found'" - def fetch(header, *varargs) - raise ArgumentError, "Too many arguments" if varargs.length > 1 - pair = @row.assoc(header) - if pair - pair.last - else - if block_given? - yield header - elsif varargs.empty? - raise KeyError, "key not found: #{header}" - else - varargs.first - end - end - end - - # :call-seq: - # row.has_key?(header) -> true or false - # - # Returns +true+ if there is a field with the given +header+, - # +false+ otherwise. - def has_key?(header) - [email protected](header) - end - alias_method :include?, :has_key? - alias_method :key?, :has_key? - alias_method :member?, :has_key? - alias_method :header?, :has_key? - - # - # :call-seq: - # row[index] = value -> value - # row[header, offset] = value -> value - # row[header] = value -> value - # - # Assigns the field value for the given +index+ or +header+; - # returns +value+. - # - # --- - # - # Assign field value by \Integer index: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row[0] = 'Bat' - # row[1] = 3 - # row # => #<CSV::Row "Name":"Bat" "Value":3> - # - # Counts backward from the last column if +index+ is negative: - # row[-1] = 4 - # row[-2] = 'Bam' - # row # => #<CSV::Row "Name":"Bam" "Value":4> - # - # Extends the row with <tt>nil:nil</tt> if positive +index+ is not in the row: - # row[4] = 5 - # row # => #<CSV::Row "Name":"bad" "Value":4 nil:nil nil:nil nil:5> - # - # Raises IndexError if negative +index+ is too small (too far from zero). - # - # --- - # - # Assign field value by header (first found): - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row['Name'] = 'Bat' - # row # => #<CSV::Row "Name":"Bat" "Name":"Bar" "Name":"Baz"> - # - # Assign field value by header, ignoring +offset+ leading fields: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row['Name', 2] = 4 - # row # => #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":4> - # - # Append new field by (new) header: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row['New'] = 6 - # row# => #<CSV::Row "Name":"foo" "Value":"0" "New":6> - def []=(*args) - value = args.pop - - if args.first.is_a? Integer - if @row[args.first].nil? # extending past the end with index - @row[args.first] = [nil, value] - @row.map! { |pair| pair.nil? ? [nil, nil] : pair } - else # normal index assignment - @row[args.first][1] = value - end - else - index = index(*args) - if index.nil? # appending a field - self << [args.first, value] - else # normal header assignment - @row[index][1] = value - end - end - end - - # - # :call-seq: - # row << [header, value] -> self - # row << hash -> self - # row << value -> self - # - # Adds a field to +self+; returns +self+: - # - # If the argument is a 2-element \Array <tt>[header, value]</tt>, - # a field is added with the given +header+ and +value+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row << ['NAME', 'Bat'] - # row # => #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":"Baz" "NAME":"Bat"> - # - # If the argument is a \Hash, each <tt>key-value</tt> pair is added - # as a field with header +key+ and value +value+. - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row << {NAME: 'Bat', name: 'Bam'} - # row # => #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":"Baz" NAME:"Bat" name:"Bam"> - # - # Otherwise, the given +value+ is added as a field with no header. - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row << 'Bag' - # row # => #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":"Baz" nil:"Bag"> - def <<(arg) - if arg.is_a?(Array) and arg.size == 2 # appending a header and name - @row << arg - elsif arg.is_a?(Hash) # append header and name pairs - arg.each { |pair| @row << pair } - else # append field value - @row << [nil, arg] - end - - self # for chaining - end - - # :call-seq: - # row.push(*values) -> self - # - # Appends each of the given +values+ to +self+ as a field; returns +self+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.push('Bat', 'Bam') - # row # => #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":"Baz" nil:"Bat" nil:"Bam"> - def push(*args) - args.each { |arg| self << arg } - - self # for chaining - end - - # - # :call-seq: - # delete(index) -> [header, value] or nil - # delete(header) -> [header, value] or empty_array - # delete(header, offset) -> [header, value] or empty_array - # - # Removes a specified field from +self+; returns the 2-element \Array - # <tt>[header, value]</tt> if the field exists. - # - # If an \Integer argument +index+ is given, - # removes and returns the field at offset +index+, - # or returns +nil+ if the field does not exist: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.delete(1) # => ["Name", "Bar"] - # row.delete(50) # => nil - # - # Otherwise, if the single argument +header+ is given, - # removes and returns the first-found field with the given header, - # of returns a new empty \Array if the field does not exist: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.delete('Name') # => ["Name", "Foo"] - # row.delete('NAME') # => [] - # - # If argument +header+ and \Integer argument +offset+ are given, - # removes and returns the first-found field with the given header - # whose +index+ is at least as large as +offset+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.delete('Name', 1) # => ["Name", "Bar"] - # row.delete('NAME', 1) # => [] - def delete(header_or_index, minimum_index = 0) - if header_or_index.is_a? Integer # by index - @row.delete_at(header_or_index) - elsif i = index(header_or_index, minimum_index) # by header - @row.delete_at(i) - else - [ ] - end - end - - # :call-seq: - # row.delete_if {|header, value| ... } -> self - # - # Removes fields from +self+ as selected by the block; returns +self+. - # - # Removes each field for which the block returns a truthy value: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.delete_if {|header, value| value.start_with?('B') } # => true - # row # => #<CSV::Row "Name":"Foo"> - # row.delete_if {|header, value| header.start_with?('B') } # => false - # - # If no block is given, returns a new Enumerator: - # row.delete_if # => #<Enumerator: #<CSV::Row "Name":"Foo">:delete_if> - def delete_if(&block) - return enum_for(__method__) { size } unless block_given? - - @row.delete_if(&block) - - self # for chaining - end - - # :call-seq: - # self.fields(*specifiers) -> array_of_fields - # - # Returns field values per the given +specifiers+, which may be any mixture of: - # - \Integer index. - # - \Range of \Integer indexes. - # - 2-element \Array containing a header and offset. - # - Header. - # - \Range of headers. - # - # For +specifier+ in one of the first four cases above, - # returns the result of <tt>self.field(specifier)</tt>; see #field. - # - # Although there may be any number of +specifiers+, - # the examples here will illustrate one at a time. - # - # When the specifier is an \Integer +index+, - # returns <tt>self.field(index)</tt>L - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.fields(1) # => ["Bar"] - # - # When the specifier is a \Range of \Integers +range+, - # returns <tt>self.field(range)</tt>: - # row.fields(1..2) # => ["Bar", "Baz"] - # - # When the specifier is a 2-element \Array +array+, - # returns <tt>self.field(array)</tt>L - # row.fields('Name', 1) # => ["Foo", "Bar"] - # - # When the specifier is a header +header+, - # returns <tt>self.field(header)</tt>L - # row.fields('Name') # => ["Foo"] - # - # When the specifier is a \Range of headers +range+, - # forms a new \Range +new_range+ from the indexes of - # <tt>range.start</tt> and <tt>range.end</tt>, - # and returns <tt>self.field(new_range)</tt>: - # source = "Name,NAME,name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.fields('Name'..'NAME') # => ["Foo", "Bar"] - # - # Returns all fields if no argument given: - # row.fields # => ["Foo", "Bar", "Baz"] - def fields(*headers_and_or_indices) - if headers_and_or_indices.empty? # return all fields--no arguments - @row.map(&:last) - else # or work like values_at() - all = [] - headers_and_or_indices.each do |h_or_i| - if h_or_i.is_a? Range - index_begin = h_or_i.begin.is_a?(Integer) ? h_or_i.begin : - index(h_or_i.begin) - index_end = h_or_i.end.is_a?(Integer) ? h_or_i.end : - index(h_or_i.end) - new_range = h_or_i.exclude_end? ? (index_begin...index_end) : - (index_begin..index_end) - all.concat(fields.values_at(new_range)) - else - all << field(*Array(h_or_i)) - end - end - return all - end - end - alias_method :values_at, :fields - - # :call-seq: - # index(header) -> index - # index(header, offset) -> index - # - # Returns the index for the given header, if it exists; - # otherwise returns +nil+. - # - # With the single argument +header+, returns the index - # of the first-found field with the given +header+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.index('Name') # => 0 - # row.index('NAME') # => nil - # - # With arguments +header+ and +offset+, - # returns the index of the first-found field with given +header+, - # but ignoring the first +offset+ fields: - # row.index('Name', 1) # => 1 - # row.index('Name', 3) # => nil - def index(header, minimum_index = 0) - # find the pair - index = headers[minimum_index..-1].index(header) - # return the index at the right offset, if we found one - index.nil? ? nil : index + minimum_index - end - - # :call-seq: - # row.field?(value) -> true or false - # - # Returns +true+ if +value+ is a field in this row, +false+ otherwise: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.field?('Bar') # => true - # row.field?('BAR') # => false - def field?(data) - fields.include? data - end - - include Enumerable - - # :call-seq: - # row.each {|header, value| ... } -> self - # - # Calls the block with each header-value pair; returns +self+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.each {|header, value| p [header, value] } - # Output: - # ["Name", "Foo"] - # ["Name", "Bar"] - # ["Name", "Baz"] - # - # If no block is given, returns a new Enumerator: - # row.each # => #<Enumerator: #<CSV::Row "Name":"Foo" "Name":"Bar" "Name":"Baz">:each> - def each(&block) - return enum_for(__method__) { size } unless block_given? - - @row.each(&block) - - self # for chaining - end - - alias_method :each_pair, :each - - # :call-seq: - # row == other -> true or false - # - # Returns +true+ if +other+ is a /CSV::Row that has the same - # fields (headers and values) in the same order as +self+; - # otherwise returns +false+: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # other_row = table[0] - # row == other_row # => true - # other_row = table[1] - # row == other_row # => false - def ==(other) - return @row == other.row if other.is_a? CSV::Row - @row == other - end - - # :call-seq: - # row.to_h -> hash - # - # Returns the new \Hash formed by adding each header-value pair in +self+ - # as a key-value pair in the \Hash. - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.to_h # => {"Name"=>"foo", "Value"=>"0"} - # - # Header order is preserved, but repeated headers are ignored: - # source = "Name,Name,Name\nFoo,Bar,Baz\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.to_h # => {"Name"=>"Foo"} - def to_h - hash = {} - each do |key, _value| - hash[key] = self[key] unless hash.key?(key) - end - hash - end - alias_method :to_hash, :to_h - - # :call-seq: - # row.deconstruct_keys(keys) -> hash - # - # Returns the new \Hash suitable for pattern matching containing only the - # keys specified as an argument. - def deconstruct_keys(keys) - if keys.nil? - to_h - else - keys.to_h { |key| [key, self[key]] } - end - end - - alias_method :to_ary, :to_a - - # :call-seq: - # row.deconstruct -> array - # - # Returns the new \Array suitable for pattern matching containing the values - # of the row. - def deconstruct - fields - end - - # :call-seq: - # row.to_csv -> csv_string - # - # Returns the row as a \CSV String. Headers are not included: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.to_csv # => "foo,0\n" - def to_csv(**options) - fields.to_csv(**options) - end - alias_method :to_s, :to_csv - - # :call-seq: - # row.dig(index_or_header, *identifiers) -> object - # - # Finds and returns the object in nested object that is specified - # by +index_or_header+ and +specifiers+. - # - # The nested objects may be instances of various classes. - # See {Dig Methods}[rdoc-ref:dig_methods.rdoc]. - # - # Examples: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.dig(1) # => "0" - # row.dig('Value') # => "0" - # row.dig(5) # => nil - def dig(index_or_header, *indexes) - value = field(index_or_header) - if value.nil? - nil - elsif indexes.empty? - value - else - unless value.respond_to?(:dig) - raise TypeError, "#{value.class} does not have \#dig method" - end - value.dig(*indexes) - end - end - - # :call-seq: - # row.inspect -> string - # - # Returns an ASCII-compatible \String showing: - # - Class \CSV::Row. - # - Header-value pairs. - # Example: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # row = table[0] - # row.inspect # => "#<CSV::Row \"Name\":\"foo\" \"Value\":\"0\">" - def inspect - str = ["#<", self.class.to_s] - each do |header, field| - str << " " << (header.is_a?(Symbol) ? header.to_s : header.inspect) << - ":" << field.inspect - end - str << ">" - begin - str.join('') - rescue # any encoding error - str.map do |s| - e = Encoding::Converter.asciicompat_encoding(s.encoding) - e ? s.encode(e) : s.force_encoding("ASCII-8BIT") - end.join('') - end - end - end -end diff --git a/lib/csv/table.rb b/lib/csv/table.rb deleted file mode 100644 index fb19f5453f..0000000000 --- a/lib/csv/table.rb +++ /dev/null @@ -1,1055 +0,0 @@ -# frozen_string_literal: true - -require "forwardable" - -class CSV - # = \CSV::Table - # A \CSV::Table instance represents \CSV data. - # (see {class CSV}[../CSV.html]). - # - # The instance may have: - # - Rows: each is a Table::Row object. - # - Headers: names for the columns. - # - # === Instance Methods - # - # \CSV::Table has three groups of instance methods: - # - Its own internally defined instance methods. - # - Methods included by module Enumerable. - # - Methods delegated to class Array.: - # * Array#empty? - # * Array#length - # * Array#size - # - # == Creating a \CSV::Table Instance - # - # Commonly, a new \CSV::Table instance is created by parsing \CSV source - # using headers: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.class # => CSV::Table - # - # You can also create an instance directly. See ::new. - # - # == Headers - # - # If a table has headers, the headers serve as labels for the columns of data. - # Each header serves as the label for its column. - # - # The headers for a \CSV::Table object are stored as an \Array of Strings. - # - # Commonly, headers are defined in the first row of \CSV source: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.headers # => ["Name", "Value"] - # - # If no headers are defined, the \Array is empty: - # table = CSV::Table.new([]) - # table.headers # => [] - # - # == Access Modes - # - # \CSV::Table provides three modes for accessing table data: - # - \Row mode. - # - Column mode. - # - Mixed mode (the default for a new table). - # - # The access mode for a\CSV::Table instance affects the behavior - # of some of its instance methods: - # - #[] - # - #[]= - # - #delete - # - #delete_if - # - #each - # - #values_at - # - # === \Row Mode - # - # Set a table to row mode with method #by_row!: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # - # Specify a single row by an \Integer index: - # # Get a row. - # table[1] # => #<CSV::Row "Name":"bar" "Value":"1"> - # # Set a row, then get it. - # table[1] = CSV::Row.new(['Name', 'Value'], ['bam', 3]) - # table[1] # => #<CSV::Row "Name":"bam" "Value":3> - # - # Specify a sequence of rows by a \Range: - # # Get rows. - # table[1..2] # => [#<CSV::Row "Name":"bam" "Value":3>, #<CSV::Row "Name":"baz" "Value":"2">] - # # Set rows, then get them. - # table[1..2] = [ - # CSV::Row.new(['Name', 'Value'], ['bat', 4]), - # CSV::Row.new(['Name', 'Value'], ['bad', 5]), - # ] - # table[1..2] # => [["Name", #<CSV::Row "Name":"bat" "Value":4>], ["Value", #<CSV::Row "Name":"bad" "Value":5>]] - # - # === Column Mode - # - # Set a table to column mode with method #by_col!: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # - # Specify a column by an \Integer index: - # # Get a column. - # table[0] - # # Set a column, then get it. - # table[0] = ['FOO', 'BAR', 'BAZ'] - # table[0] # => ["FOO", "BAR", "BAZ"] - # - # Specify a column by its \String header: - # # Get a column. - # table['Name'] # => ["FOO", "BAR", "BAZ"] - # # Set a column, then get it. - # table['Name'] = ['Foo', 'Bar', 'Baz'] - # table['Name'] # => ["Foo", "Bar", "Baz"] - # - # === Mixed Mode - # - # In mixed mode, you can refer to either rows or columns: - # - An \Integer index refers to a row. - # - A \Range index refers to multiple rows. - # - A \String index refers to a column. - # - # Set a table to mixed mode with method #by_col_or_row!: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col_or_row! # => #<CSV::Table mode:col_or_row row_count:4> - # - # Specify a single row by an \Integer index: - # # Get a row. - # table[1] # => #<CSV::Row "Name":"bar" "Value":"1"> - # # Set a row, then get it. - # table[1] = CSV::Row.new(['Name', 'Value'], ['bam', 3]) - # table[1] # => #<CSV::Row "Name":"bam" "Value":3> - # - # Specify a sequence of rows by a \Range: - # # Get rows. - # table[1..2] # => [#<CSV::Row "Name":"bam" "Value":3>, #<CSV::Row "Name":"baz" "Value":"2">] - # # Set rows, then get them. - # table[1] = CSV::Row.new(['Name', 'Value'], ['bat', 4]) - # table[2] = CSV::Row.new(['Name', 'Value'], ['bad', 5]) - # table[1..2] # => [["Name", #<CSV::Row "Name":"bat" "Value":4>], ["Value", #<CSV::Row "Name":"bad" "Value":5>]] - # - # Specify a column by its \String header: - # # Get a column. - # table['Name'] # => ["foo", "bat", "bad"] - # # Set a column, then get it. - # table['Name'] = ['Foo', 'Bar', 'Baz'] - # table['Name'] # => ["Foo", "Bar", "Baz"] - class Table - # :call-seq: - # CSV::Table.new(array_of_rows, headers = nil) -> csv_table - # - # Returns a new \CSV::Table object. - # - # - Argument +array_of_rows+ must be an \Array of CSV::Row objects. - # - Argument +headers+, if given, may be an \Array of Strings. - # - # --- - # - # Create an empty \CSV::Table object: - # table = CSV::Table.new([]) - # table # => #<CSV::Table mode:col_or_row row_count:1> - # - # Create a non-empty \CSV::Table object: - # rows = [ - # CSV::Row.new([], []), - # CSV::Row.new([], []), - # CSV::Row.new([], []), - # ] - # table = CSV::Table.new(rows) - # table # => #<CSV::Table mode:col_or_row row_count:4> - # - # --- - # - # If argument +headers+ is an \Array of Strings, - # those Strings become the table's headers: - # table = CSV::Table.new([], headers: ['Name', 'Age']) - # table.headers # => ["Name", "Age"] - # - # If argument +headers+ is not given and the table has rows, - # the headers are taken from the first row: - # rows = [ - # CSV::Row.new(['Foo', 'Bar'], []), - # CSV::Row.new(['foo', 'bar'], []), - # CSV::Row.new(['FOO', 'BAR'], []), - # ] - # table = CSV::Table.new(rows) - # table.headers # => ["Foo", "Bar"] - # - # If argument +headers+ is not given and the table is empty (has no rows), - # the headers are also empty: - # table = CSV::Table.new([]) - # table.headers # => [] - # - # --- - # - # Raises an exception if argument +array_of_rows+ is not an \Array object: - # # Raises NoMethodError (undefined method `first' for :foo:Symbol): - # CSV::Table.new(:foo) - # - # Raises an exception if an element of +array_of_rows+ is not a \CSV::Table object: - # # Raises NoMethodError (undefined method `headers' for :foo:Symbol): - # CSV::Table.new([:foo]) - def initialize(array_of_rows, headers: nil) - @table = array_of_rows - @headers = headers - unless @headers - if @table.empty? - @headers = [] - else - @headers = @table.first.headers - end - end - - @mode = :col_or_row - end - - # The current access mode for indexing and iteration. - attr_reader :mode - - # Internal data format used to compare equality. - attr_reader :table - protected :table - - ### Array Delegation ### - - extend Forwardable - def_delegators :@table, :empty?, :length, :size - - # :call-seq: - # table.by_col -> table_dup - # - # Returns a duplicate of +self+, in column mode - # (see {Column Mode}[#class-CSV::Table-label-Column+Mode]): - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.mode # => :col_or_row - # dup_table = table.by_col - # dup_table.mode # => :col - # dup_table.equal?(table) # => false # It's a dup - # - # This may be used to chain method calls without changing the mode - # (but also will affect performance and memory usage): - # dup_table.by_col['Name'] - # - # Also note that changes to the duplicate table will not affect the original. - def by_col - self.class.new(@table.dup).by_col! - end - - # :call-seq: - # table.by_col! -> self - # - # Sets the mode for +self+ to column mode - # (see {Column Mode}[#class-CSV::Table-label-Column+Mode]); returns +self+: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.mode # => :col_or_row - # table1 = table.by_col! - # table.mode # => :col - # table1.equal?(table) # => true # Returned self - def by_col! - @mode = :col - - self - end - - # :call-seq: - # table.by_col_or_row -> table_dup - # - # Returns a duplicate of +self+, in mixed mode - # (see {Mixed Mode}[#class-CSV::Table-label-Mixed+Mode]): - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true).by_col! - # table.mode # => :col - # dup_table = table.by_col_or_row - # dup_table.mode # => :col_or_row - # dup_table.equal?(table) # => false # It's a dup - # - # This may be used to chain method calls without changing the mode - # (but also will affect performance and memory usage): - # dup_table.by_col_or_row['Name'] - # - # Also note that changes to the duplicate table will not affect the original. - def by_col_or_row - self.class.new(@table.dup).by_col_or_row! - end - - # :call-seq: - # table.by_col_or_row! -> self - # - # Sets the mode for +self+ to mixed mode - # (see {Mixed Mode}[#class-CSV::Table-label-Mixed+Mode]); returns +self+: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true).by_col! - # table.mode # => :col - # table1 = table.by_col_or_row! - # table.mode # => :col_or_row - # table1.equal?(table) # => true # Returned self - def by_col_or_row! - @mode = :col_or_row - - self - end - - # :call-seq: - # table.by_row -> table_dup - # - # Returns a duplicate of +self+, in row mode - # (see {Row Mode}[#class-CSV::Table-label-Row+Mode]): - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.mode # => :col_or_row - # dup_table = table.by_row - # dup_table.mode # => :row - # dup_table.equal?(table) # => false # It's a dup - # - # This may be used to chain method calls without changing the mode - # (but also will affect performance and memory usage): - # dup_table.by_row[1] - # - # Also note that changes to the duplicate table will not affect the original. - def by_row - self.class.new(@table.dup).by_row! - end - - # :call-seq: - # table.by_row! -> self - # - # Sets the mode for +self+ to row mode - # (see {Row Mode}[#class-CSV::Table-label-Row+Mode]); returns +self+: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.mode # => :col_or_row - # table1 = table.by_row! - # table.mode # => :row - # table1.equal?(table) # => true # Returned self - def by_row! - @mode = :row - - self - end - - # :call-seq: - # table.headers -> array_of_headers - # - # Returns a new \Array containing the \String headers for the table. - # - # If the table is not empty, returns the headers from the first row: - # rows = [ - # CSV::Row.new(['Foo', 'Bar'], []), - # CSV::Row.new(['FOO', 'BAR'], []), - # CSV::Row.new(['foo', 'bar'], []), - # ] - # table = CSV::Table.new(rows) - # table.headers # => ["Foo", "Bar"] - # table.delete(0) - # table.headers # => ["FOO", "BAR"] - # table.delete(0) - # table.headers # => ["foo", "bar"] - # - # If the table is empty, returns a copy of the headers in the table itself: - # table.delete(0) - # table.headers # => ["Foo", "Bar"] - def headers - if @table.empty? - @headers.dup - else - @table.first.headers - end - end - - # :call-seq: - # table[n] -> row or column_data - # table[range] -> array_of_rows or array_of_column_data - # table[header] -> array_of_column_data - # - # Returns data from the table; does not modify the table. - # - # --- - # - # Fetch a \Row by Its \Integer Index:: - # - Form: <tt>table[n]</tt>, +n+ an integer. - # - Access mode: <tt>:row</tt> or <tt>:col_or_row</tt>. - # - Return value: _nth_ row of the table, if that row exists; - # otherwise +nil+. - # - # Returns the _nth_ row of the table if that row exists: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # table[1] # => #<CSV::Row "Name":"bar" "Value":"1"> - # table.by_col_or_row! # => #<CSV::Table mode:col_or_row row_count:4> - # table[1] # => #<CSV::Row "Name":"bar" "Value":"1"> - # - # Counts backward from the last row if +n+ is negative: - # table[-1] # => #<CSV::Row "Name":"baz" "Value":"2"> - # - # Returns +nil+ if +n+ is too large or too small: - # table[4] # => nil - # table[-4] # => nil - # - # Raises an exception if the access mode is <tt>:row</tt> - # and +n+ is not an \Integer: - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # # Raises TypeError (no implicit conversion of String into Integer): - # table['Name'] - # - # --- - # - # Fetch a Column by Its \Integer Index:: - # - Form: <tt>table[n]</tt>, +n+ an \Integer. - # - Access mode: <tt>:col</tt>. - # - Return value: _nth_ column of the table, if that column exists; - # otherwise an \Array of +nil+ fields of length <tt>self.size</tt>. - # - # Returns the _nth_ column of the table if that column exists: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # table[1] # => ["0", "1", "2"] - # - # Counts backward from the last column if +n+ is negative: - # table[-2] # => ["foo", "bar", "baz"] - # - # Returns an \Array of +nil+ fields if +n+ is too large or too small: - # table[4] # => [nil, nil, nil] - # table[-4] # => [nil, nil, nil] - # - # --- - # - # Fetch Rows by \Range:: - # - Form: <tt>table[range]</tt>, +range+ a \Range object. - # - Access mode: <tt>:row</tt> or <tt>:col_or_row</tt>. - # - Return value: rows from the table, beginning at row <tt>range.start</tt>, - # if those rows exists. - # - # Returns rows from the table, beginning at row <tt>range.first</tt>, - # if those rows exist: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # rows = table[1..2] # => #<CSV::Row "Name":"bar" "Value":"1"> - # rows # => [#<CSV::Row "Name":"bar" "Value":"1">, #<CSV::Row "Name":"baz" "Value":"2">] - # table.by_col_or_row! # => #<CSV::Table mode:col_or_row row_count:4> - # rows = table[1..2] # => #<CSV::Row "Name":"bar" "Value":"1"> - # rows # => [#<CSV::Row "Name":"bar" "Value":"1">, #<CSV::Row "Name":"baz" "Value":"2">] - # - # If there are too few rows, returns all from <tt>range.start</tt> to the end: - # rows = table[1..50] # => #<CSV::Row "Name":"bar" "Value":"1"> - # rows # => [#<CSV::Row "Name":"bar" "Value":"1">, #<CSV::Row "Name":"baz" "Value":"2">] - # - # Special case: if <tt>range.start == table.size</tt>, returns an empty \Array: - # table[table.size..50] # => [] - # - # If <tt>range.end</tt> is negative, calculates the ending index from the end: - # rows = table[0..-1] - # rows # => [#<CSV::Row "Name":"foo" "Value":"0">, #<CSV::Row "Name":"bar" "Value":"1">, #<CSV::Row "Name":"baz" "Value":"2">] - # - # If <tt>range.start</tt> is negative, calculates the starting index from the end: - # rows = table[-1..2] - # rows # => [#<CSV::Row "Name":"baz" "Value":"2">] - # - # If <tt>range.start</tt> is larger than <tt>table.size</tt>, returns +nil+: - # table[4..4] # => nil - # - # --- - # - # Fetch Columns by \Range:: - # - Form: <tt>table[range]</tt>, +range+ a \Range object. - # - Access mode: <tt>:col</tt>. - # - Return value: column data from the table, beginning at column <tt>range.start</tt>, - # if those columns exist. - # - # Returns column values from the table, if the column exists; - # the values are arranged by row: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col! - # table[0..1] # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # Special case: if <tt>range.start == headers.size</tt>, - # returns an \Array (size: <tt>table.size</tt>) of empty \Arrays: - # table[table.headers.size..50] # => [[], [], []] - # - # If <tt>range.end</tt> is negative, calculates the ending index from the end: - # table[0..-1] # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # If <tt>range.start</tt> is negative, calculates the starting index from the end: - # table[-2..2] # => [["foo", "0"], ["bar", "1"], ["baz", "2"]] - # - # If <tt>range.start</tt> is larger than <tt>table.size</tt>, - # returns an \Array of +nil+ values: - # table[4..4] # => [nil, nil, nil] - # - # --- - # - # Fetch a Column by Its \String Header:: - # - Form: <tt>table[header]</tt>, +header+ a \String header. - # - Access mode: <tt>:col</tt> or <tt>:col_or_row</tt> - # - Return value: column data from the table, if that +header+ exists. - # - # Returns column values from the table, if the column exists: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # table['Name'] # => ["foo", "bar", "baz"] - # table.by_col_or_row! # => #<CSV::Table mode:col_or_row row_count:4> - # col = table['Name'] - # col # => ["foo", "bar", "baz"] - # - # Modifying the returned column values does not modify the table: - # col[0] = 'bat' - # col # => ["bat", "bar", "baz"] - # table['Name'] # => ["foo", "bar", "baz"] - # - # Returns an \Array of +nil+ values if there is no such column: - # table['Nosuch'] # => [nil, nil, nil] - def [](index_or_header) - if @mode == :row or # by index - (@mode == :col_or_row and (index_or_header.is_a?(Integer) or index_or_header.is_a?(Range))) - @table[index_or_header] - else # by header - @table.map { |row| row[index_or_header] } - end - end - - # :call-seq: - # table[n] = row -> row - # table[n] = field_or_array_of_fields -> field_or_array_of_fields - # table[header] = field_or_array_of_fields -> field_or_array_of_fields - # - # Puts data onto the table. - # - # --- - # - # Set a \Row by Its \Integer Index:: - # - Form: <tt>table[n] = row</tt>, +n+ an \Integer, - # +row+ a \CSV::Row instance or an \Array of fields. - # - Access mode: <tt>:row</tt> or <tt>:col_or_row</tt>. - # - Return value: +row+. - # - # If the row exists, it is replaced: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # new_row = CSV::Row.new(['Name', 'Value'], ['bat', 3]) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # return_value = table[0] = new_row - # return_value.equal?(new_row) # => true # Returned the row - # table[0].to_h # => {"Name"=>"bat", "Value"=>3} - # - # With access mode <tt>:col_or_row</tt>: - # table.by_col_or_row! # => #<CSV::Table mode:col_or_row row_count:4> - # table[0] = CSV::Row.new(['Name', 'Value'], ['bam', 4]) - # table[0].to_h # => {"Name"=>"bam", "Value"=>4} - # - # With an \Array instead of a \CSV::Row, inherits headers from the table: - # array = ['bad', 5] - # return_value = table[0] = array - # return_value.equal?(array) # => true # Returned the array - # table[0].to_h # => {"Name"=>"bad", "Value"=>5} - # - # If the row does not exist, extends the table by adding rows: - # assigns rows with +nil+ as needed: - # table.size # => 3 - # table[5] = ['bag', 6] - # table.size # => 6 - # table[3] # => nil - # table[4]# => nil - # table[5].to_h # => {"Name"=>"bag", "Value"=>6} - # - # Note that the +nil+ rows are actually +nil+, not a row of +nil+ fields. - # - # --- - # - # Set a Column by Its \Integer Index:: - # - Form: <tt>table[n] = array_of_fields</tt>, +n+ an \Integer, - # +array_of_fields+ an \Array of \String fields. - # - Access mode: <tt>:col</tt>. - # - Return value: +array_of_fields+. - # - # If the column exists, it is replaced: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # new_col = [3, 4, 5] - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # return_value = table[1] = new_col - # return_value.equal?(new_col) # => true # Returned the column - # table[1] # => [3, 4, 5] - # # The rows, as revised: - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # table[0].to_h # => {"Name"=>"foo", "Value"=>3} - # table[1].to_h # => {"Name"=>"bar", "Value"=>4} - # table[2].to_h # => {"Name"=>"baz", "Value"=>5} - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # - # If there are too few values, fills with +nil+ values: - # table[1] = [0] - # table[1] # => [0, nil, nil] - # - # If there are too many values, ignores the extra values: - # table[1] = [0, 1, 2, 3, 4] - # table[1] # => [0, 1, 2] - # - # If a single value is given, replaces all fields in the column with that value: - # table[1] = 'bat' - # table[1] # => ["bat", "bat", "bat"] - # - # --- - # - # Set a Column by Its \String Header:: - # - Form: <tt>table[header] = field_or_array_of_fields</tt>, - # +header+ a \String header, +field_or_array_of_fields+ a field value - # or an \Array of \String fields. - # - Access mode: <tt>:col</tt> or <tt>:col_or_row</tt>. - # - Return value: +field_or_array_of_fields+. - # - # If the column exists, it is replaced: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # new_col = [3, 4, 5] - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # return_value = table['Value'] = new_col - # return_value.equal?(new_col) # => true # Returned the column - # table['Value'] # => [3, 4, 5] - # # The rows, as revised: - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # table[0].to_h # => {"Name"=>"foo", "Value"=>3} - # table[1].to_h # => {"Name"=>"bar", "Value"=>4} - # table[2].to_h # => {"Name"=>"baz", "Value"=>5} - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # - # If there are too few values, fills with +nil+ values: - # table['Value'] = [0] - # table['Value'] # => [0, nil, nil] - # - # If there are too many values, ignores the extra values: - # table['Value'] = [0, 1, 2, 3, 4] - # table['Value'] # => [0, 1, 2] - # - # If the column does not exist, extends the table by adding columns: - # table['Note'] = ['x', 'y', 'z'] - # table['Note'] # => ["x", "y", "z"] - # # The rows, as revised: - # table.by_row! - # table[0].to_h # => {"Name"=>"foo", "Value"=>0, "Note"=>"x"} - # table[1].to_h # => {"Name"=>"bar", "Value"=>1, "Note"=>"y"} - # table[2].to_h # => {"Name"=>"baz", "Value"=>2, "Note"=>"z"} - # table.by_col! - # - # If a single value is given, replaces all fields in the column with that value: - # table['Value'] = 'bat' - # table['Value'] # => ["bat", "bat", "bat"] - def []=(index_or_header, value) - if @mode == :row or # by index - (@mode == :col_or_row and index_or_header.is_a? Integer) - if value.is_a? Array - @table[index_or_header] = Row.new(headers, value) - else - @table[index_or_header] = value - end - else # set column - unless index_or_header.is_a? Integer - index = @headers.index(index_or_header) || @headers.size - @headers[index] = index_or_header - end - if value.is_a? Array # multiple values - @table.each_with_index do |row, i| - if row.header_row? - row[index_or_header] = index_or_header - else - row[index_or_header] = value[i] - end - end - else # repeated value - @table.each do |row| - if row.header_row? - row[index_or_header] = index_or_header - else - row[index_or_header] = value - end - end - end - end - end - - # :call-seq: - # table.values_at(*indexes) -> array_of_rows - # table.values_at(*headers) -> array_of_columns_data - # - # If the access mode is <tt>:row</tt> or <tt>:col_or_row</tt>, - # and each argument is either an \Integer or a \Range, - # returns rows. - # Otherwise, returns columns data. - # - # In either case, the returned values are in the order - # specified by the arguments. Arguments may be repeated. - # - # --- - # - # Returns rows as an \Array of \CSV::Row objects. - # - # No argument: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.values_at # => [] - # - # One index: - # values = table.values_at(0) - # values # => [#<CSV::Row "Name":"foo" "Value":"0">] - # - # Two indexes: - # values = table.values_at(2, 0) - # values # => [#<CSV::Row "Name":"baz" "Value":"2">, #<CSV::Row "Name":"foo" "Value":"0">] - # - # One \Range: - # values = table.values_at(1..2) - # values # => [#<CSV::Row "Name":"bar" "Value":"1">, #<CSV::Row "Name":"baz" "Value":"2">] - # - # \Ranges and indexes: - # values = table.values_at(0..1, 1..2, 0, 2) - # pp values - # Output: - # [#<CSV::Row "Name":"foo" "Value":"0">, - # #<CSV::Row "Name":"bar" "Value":"1">, - # #<CSV::Row "Name":"bar" "Value":"1">, - # #<CSV::Row "Name":"baz" "Value":"2">, - # #<CSV::Row "Name":"foo" "Value":"0">, - # #<CSV::Row "Name":"baz" "Value":"2">] - # - # --- - # - # Returns columns data as row Arrays, - # each consisting of the specified columns data for that row: - # values = table.values_at('Name') - # values # => [["foo"], ["bar"], ["baz"]] - # values = table.values_at('Value', 'Name') - # values # => [["0", "foo"], ["1", "bar"], ["2", "baz"]] - def values_at(*indices_or_headers) - if @mode == :row or # by indices - ( @mode == :col_or_row and indices_or_headers.all? do |index| - index.is_a?(Integer) or - ( index.is_a?(Range) and - index.first.is_a?(Integer) and - index.last.is_a?(Integer) ) - end ) - @table.values_at(*indices_or_headers) - else # by headers - @table.map { |row| row.values_at(*indices_or_headers) } - end - end - - # :call-seq: - # table << row_or_array -> self - # - # If +row_or_array+ is a \CSV::Row object, - # it is appended to the table: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table << CSV::Row.new(table.headers, ['bat', 3]) - # table[3] # => #<CSV::Row "Name":"bat" "Value":3> - # - # If +row_or_array+ is an \Array, it is used to create a new - # \CSV::Row object which is then appended to the table: - # table << ['bam', 4] - # table[4] # => #<CSV::Row "Name":"bam" "Value":4> - def <<(row_or_array) - if row_or_array.is_a? Array # append Array - @table << Row.new(headers, row_or_array) - else # append Row - @table << row_or_array - end - - self # for chaining - end - - # - # :call-seq: - # table.push(*rows_or_arrays) -> self - # - # A shortcut for appending multiple rows. Equivalent to: - # rows.each {|row| self << row } - # - # Each argument may be either a \CSV::Row object or an \Array: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # rows = [ - # CSV::Row.new(table.headers, ['bat', 3]), - # ['bam', 4] - # ] - # table.push(*rows) - # table[3..4] # => [#<CSV::Row "Name":"bat" "Value":3>, #<CSV::Row "Name":"bam" "Value":4>] - def push(*rows) - rows.each { |row| self << row } - - self # for chaining - end - - # :call-seq: - # table.delete(*indexes) -> deleted_values - # table.delete(*headers) -> deleted_values - # - # If the access mode is <tt>:row</tt> or <tt>:col_or_row</tt>, - # and each argument is either an \Integer or a \Range, - # returns deleted rows. - # Otherwise, returns deleted columns data. - # - # In either case, the returned values are in the order - # specified by the arguments. Arguments may be repeated. - # - # --- - # - # Returns rows as an \Array of \CSV::Row objects. - # - # One index: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # deleted_values = table.delete(0) - # deleted_values # => [#<CSV::Row "Name":"foo" "Value":"0">] - # - # Two indexes: - # table = CSV.parse(source, headers: true) - # deleted_values = table.delete(2, 0) - # deleted_values # => [#<CSV::Row "Name":"baz" "Value":"2">, #<CSV::Row "Name":"foo" "Value":"0">] - # - # --- - # - # Returns columns data as column Arrays. - # - # One header: - # table = CSV.parse(source, headers: true) - # deleted_values = table.delete('Name') - # deleted_values # => ["foo", "bar", "baz"] - # - # Two headers: - # table = CSV.parse(source, headers: true) - # deleted_values = table.delete('Value', 'Name') - # deleted_values # => [["0", "1", "2"], ["foo", "bar", "baz"]] - def delete(*indexes_or_headers) - if indexes_or_headers.empty? - raise ArgumentError, "wrong number of arguments (given 0, expected 1+)" - end - deleted_values = indexes_or_headers.map do |index_or_header| - if @mode == :row or # by index - (@mode == :col_or_row and index_or_header.is_a? Integer) - @table.delete_at(index_or_header) - else # by header - if index_or_header.is_a? Integer - @headers.delete_at(index_or_header) - else - @headers.delete(index_or_header) - end - @table.map { |row| row.delete(index_or_header).last } - end - end - if indexes_or_headers.size == 1 - deleted_values[0] - else - deleted_values - end - end - - # :call-seq: - # table.delete_if {|row_or_column| ... } -> self - # - # Removes rows or columns for which the block returns a truthy value; - # returns +self+. - # - # Removes rows when the access mode is <tt>:row</tt> or <tt>:col_or_row</tt>; - # calls the block with each \CSV::Row object: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # table.size # => 3 - # table.delete_if {|row| row['Name'].start_with?('b') } - # table.size # => 1 - # - # Removes columns when the access mode is <tt>:col</tt>; - # calls the block with each column as a 2-element array - # containing the header and an \Array of column fields: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # table.headers.size # => 2 - # table.delete_if {|column_data| column_data[1].include?('2') } - # table.headers.size # => 1 - # - # Returns a new \Enumerator if no block is given: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.delete_if # => #<Enumerator: #<CSV::Table mode:col_or_row row_count:4>:delete_if> - def delete_if(&block) - return enum_for(__method__) { @mode == :row or @mode == :col_or_row ? size : headers.size } unless block_given? - - if @mode == :row or @mode == :col_or_row # by index - @table.delete_if(&block) - else # by header - headers.each do |header| - delete(header) if yield([header, self[header]]) - end - end - - self # for chaining - end - - include Enumerable - - # :call-seq: - # table.each {|row_or_column| ... ) -> self - # - # Calls the block with each row or column; returns +self+. - # - # When the access mode is <tt>:row</tt> or <tt>:col_or_row</tt>, - # calls the block with each \CSV::Row object: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.by_row! # => #<CSV::Table mode:row row_count:4> - # table.each {|row| p row } - # Output: - # #<CSV::Row "Name":"foo" "Value":"0"> - # #<CSV::Row "Name":"bar" "Value":"1"> - # #<CSV::Row "Name":"baz" "Value":"2"> - # - # When the access mode is <tt>:col</tt>, - # calls the block with each column as a 2-element array - # containing the header and an \Array of column fields: - # table.by_col! # => #<CSV::Table mode:col row_count:4> - # table.each {|column_data| p column_data } - # Output: - # ["Name", ["foo", "bar", "baz"]] - # ["Value", ["0", "1", "2"]] - # - # Returns a new \Enumerator if no block is given: - # table.each # => #<Enumerator: #<CSV::Table mode:col row_count:4>:each> - def each(&block) - return enum_for(__method__) { @mode == :col ? headers.size : size } unless block_given? - - if @mode == :col - headers.each.with_index do |header, i| - yield([header, @table.map {|row| row[header, i]}]) - end - else - @table.each(&block) - end - - self # for chaining - end - - # :call-seq: - # table == other_table -> true or false - # - # Returns +true+ if all each row of +self+ <tt>==</tt> - # the corresponding row of +other_table+, otherwise, +false+. - # - # The access mode does no affect the result. - # - # Equal tables: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # other_table = CSV.parse(source, headers: true) - # table == other_table # => true - # - # Different row count: - # other_table.delete(2) - # table == other_table # => false - # - # Different last row: - # other_table << ['bat', 3] - # table == other_table # => false - def ==(other) - return @table == other.table if other.is_a? CSV::Table - @table == other - end - - # :call-seq: - # table.to_a -> array_of_arrays - # - # Returns the table as an \Array of \Arrays; - # the headers are in the first row: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.to_a # => [["Name", "Value"], ["foo", "0"], ["bar", "1"], ["baz", "2"]] - def to_a - array = [headers] - @table.each do |row| - array.push(row.fields) unless row.header_row? - end - - array - end - - # :call-seq: - # table.to_csv(**options) -> csv_string - # - # Returns the table as \CSV string. - # See {Options for Generating}[../CSV.html#class-CSV-label-Options+for+Generating]. - # - # Defaults option +write_headers+ to +true+: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.to_csv # => "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # - # Omits the headers if option +write_headers+ is given as +false+ - # (see {Option +write_headers+}[../CSV.html#class-CSV-label-Option+write_headers]): - # table.to_csv(write_headers: false) # => "foo,0\nbar,1\nbaz,2\n" - # - # Limit rows if option +limit+ is given like +2+: - # table.to_csv(limit: 2) # => "Name,Value\nfoo,0\nbar,1\n" - def to_csv(write_headers: true, limit: nil, **options) - array = write_headers ? [headers.to_csv(**options)] : [] - limit ||= @table.size - limit = @table.size + 1 + limit if limit < 0 - limit = 0 if limit < 0 - @table.first(limit).each do |row| - array.push(row.fields.to_csv(**options)) unless row.header_row? - end - - array.join("") - end - alias_method :to_s, :to_csv - - # - # Extracts the nested value specified by the sequence of +index+ or +header+ objects by calling dig at each step, - # returning nil if any intermediate step is nil. - # - def dig(index_or_header, *index_or_headers) - value = self[index_or_header] - if value.nil? - nil - elsif index_or_headers.empty? - value - else - unless value.respond_to?(:dig) - raise TypeError, "#{value.class} does not have \#dig method" - end - value.dig(*index_or_headers) - end - end - - # :call-seq: - # table.inspect => string - # - # Returns a <tt>US-ASCII</tt>-encoded \String showing table: - # - Class: <tt>CSV::Table</tt>. - # - Access mode: <tt>:row</tt>, <tt>:col</tt>, or <tt>:col_or_row</tt>. - # - Size: Row count, including the header row. - # - # Example: - # source = "Name,Value\nfoo,0\nbar,1\nbaz,2\n" - # table = CSV.parse(source, headers: true) - # table.inspect # => "#<CSV::Table mode:col_or_row row_count:4>\nName,Value\nfoo,0\nbar,1\nbaz,2\n" - # - def inspect - inspected = +"#<#{self.class} mode:#{@mode} row_count:#{to_a.size}>" - summary = to_csv(limit: 5) - inspected << "\n" << summary if summary.encoding.ascii_compatible? - inspected - end - end -end diff --git a/lib/csv/version.rb b/lib/csv/version.rb deleted file mode 100644 index 100c684ac4..0000000000 --- a/lib/csv/version.rb +++ /dev/null @@ -1,6 +0,0 @@ -# frozen_string_literal: true - -class CSV - # The version of the installed library. - VERSION = "3.2.9" -end diff --git a/lib/csv/writer.rb b/lib/csv/writer.rb deleted file mode 100644 index 030a295bc9..0000000000 --- a/lib/csv/writer.rb +++ /dev/null @@ -1,210 +0,0 @@ -# frozen_string_literal: true - -require_relative "input_record_separator" -require_relative "row" - -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 - - def initialize(output, options) - @output = output - @options = options - @lineno = 0 - @fields_converter = nil - prepare - if @options[:write_headers] and @headers - self << @headers - end - @fields_converter = @options[:fields_converter] - end - - # - # Adds a new row - # - def <<(row) - case row - when Row - row = row.fields - when Hash - row = @headers.collect {|header| row[header]} - end - - @headers ||= row if @use_headers - @lineno += 1 - - if @fields_converter - quoted_fields = [false] * row.size - row = @fields_converter.convert(row, nil, lineno, quoted_fields) - end - - i = -1 - converted_row = row.collect do |field| - i += 1 - quote(field, i) - end - line = converted_row.join(@column_separator) + @row_separator - if @output_encoding - line = line.encode(@output_encoding) - end - @output << line - - self - end - - # - # Winds back to the beginning - # - def rewind - @lineno = 0 - @headers = nil if @options[:headers].nil? - end - - private - def prepare - @encoding = @options[:encoding] - - prepare_header - prepare_format - prepare_output - end - - def prepare_header - headers = @options[:headers] - case headers - when Array - @headers = headers - @use_headers = true - when String - @headers = CSV.parse_line(headers, - col_sep: @options[:column_separator], - row_sep: @options[:row_separator], - quote_char: @options[:quote_character]) - @use_headers = true - when true - @headers = nil - @use_headers = true - else - @headers = nil - @use_headers = false - end - return unless @headers - - converter = @options[:header_fields_converter] - @headers = converter.convert(@headers, nil, 0, []) - @headers.each do |header| - header.freeze if header.is_a?(String) - end - end - - def prepare_force_quotes_fields(force_quotes) - @force_quotes_fields = {} - force_quotes.each do |name_or_index| - case name_or_index - when Integer - index = name_or_index - @force_quotes_fields[index] = true - when String, Symbol - name = name_or_index.to_s - if @headers.nil? - message = ":headers is required when you use field name " + - "in :force_quotes: " + - "#{name_or_index.inspect}: #{force_quotes.inspect}" - raise ArgumentError, message - end - index = @headers.index(name) - next if index.nil? - @force_quotes_fields[index] = true - else - message = ":force_quotes element must be " + - "field index or field name: " + - "#{name_or_index.inspect}: #{force_quotes.inspect}" - raise ArgumentError, message - end - end - end - - def prepare_format - @column_separator = @options[:column_separator].to_s.encode(@encoding) - row_separator = @options[:row_separator] - if row_separator == :auto - @row_separator = InputRecordSeparator.value.encode(@encoding) - else - @row_separator = row_separator.to_s.encode(@encoding) - end - @quote_character = @options[:quote_character] - force_quotes = @options[:force_quotes] - if force_quotes.is_a?(Array) - prepare_force_quotes_fields(force_quotes) - @force_quotes = false - elsif force_quotes - @force_quotes_fields = nil - @force_quotes = true - else - @force_quotes_fields = nil - @force_quotes = false - end - unless @force_quotes - @quotable_pattern = - Regexp.new("[\r\n".encode(@encoding) + - Regexp.escape(@column_separator) + - Regexp.escape(@quote_character.encode(@encoding)) + - "]".encode(@encoding)) - end - @quote_empty = @options.fetch(:quote_empty, true) - end - - def prepare_output - @output_encoding = nil - return unless @output.is_a?(StringIO) - - output_encoding = @output.internal_encoding || @output.external_encoding - if @encoding != output_encoding - if @options[:force_encoding] - @output_encoding = output_encoding - else - compatible_encoding = Encoding.compatible?(@encoding, output_encoding) - if compatible_encoding - @output.set_encoding(compatible_encoding) - @output.seek(0, IO::SEEK_END) - end - end - end - end - - def quote_field(field) - field = String(field) - encoded_quote_character = @quote_character.encode(field.encoding) - encoded_quote_character + - field.gsub(encoded_quote_character, - encoded_quote_character * 2) + - encoded_quote_character - end - - def quote(field, i) - if @force_quotes - quote_field(field) - elsif @force_quotes_fields and @force_quotes_fields[i] - quote_field(field) - else - if field.nil? # represent +nil+ fields as empty unquoted fields - "" - else - field = String(field) # Stringify fields - # represent empty fields as empty quoted fields - if (@quote_empty and field.empty?) or (field.valid_encoding? and @quotable_pattern.match?(field)) - quote_field(field) - else - field # unquoted field - end - end - end - end - end -end |