summaryrefslogtreecommitdiff
path: root/lib/csv/row.rb
blob: c79d75cd8a163c3983d09f8db2f5a3f494feb3e7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
# frozen_string_literal: true

require "forwardable"

class CSV
  #
  # A CSV::Row is part Array and part Hash.  It retains an order for the fields
  # and allows duplicates just as an Array would, but also allows you to access
  # fields by name just as you could if they were in a Hash.
  #
  # All rows returned by CSV will be constructed from this class, if header row
  # processing is activated.
  #
  class Row
    #
    # Construct a new CSV::Row from +headers+ and +fields+, which are expected
    # to be Arrays.  If one Array is shorter than the other, it will be padded
    # with +nil+ objects.
    #
    # The optional +header_row+ parameter can be set to +true+ to indicate, via
    # CSV::Row.header_row?() and CSV::Row.field_row?(), that this is a header
    # row.  Otherwise, the row is assumes to be a field row.
    #
    # A CSV::Row object supports the following Array methods through delegation:
    #
    # * empty?()
    # * length()
    # * size()
    #
    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

    def initialize_copy(other)
      super
      @row = @row.dup
    end

    # Returns +true+ if this is a header row.
    def header_row?
      @header_row
    end

    # Returns +true+ if this is a field row.
    def field_row?
      not header_row?
    end

    # Returns the headers of this row.
    def headers
      @row.map(&:first)
    end

    #
    # :call-seq:
    #   field( header )
    #   field( header, offset )
    #   field( index )
    #
    # This method will return the field value by +header+ or +index+.  If a field
    # is not found, +nil+ is returned.
    #
    # When provided, +offset+ ensures that a header match occurs on or later
    # than the +offset+ index.  You can use this to find duplicate headers,
    # without resorting to hard-coding exact indices.
    #
    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].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 )
    #   fetch( header ) { |row| ... }
    #   fetch( header, default )
    #
    # This method will fetch the field value by +header+. It has the same
    # behavior as Hash#fetch: if there is a field with the given +header+, its
    # value is returned. Otherwise, if a block is given, it is yielded the
    # +header+ and its result is returned; if a +default+ is given as the
    # second argument, it is returned; otherwise a KeyError is raised.
    #
    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

    # Returns +true+ if there is a field with the given +header+.
    def has_key?(header)
      !!@row.assoc(header)
    end
    alias_method :include?, :has_key?
    alias_method :key?,     :has_key?
    alias_method :member?,  :has_key?
    alias_method :header?,  :has_key?

    #
    # :call-seq:
    #   []=( header, value )
    #   []=( header, offset, value )
    #   []=( index, value )
    #
    # Looks up the field by the semantics described in CSV::Row.field() and
    # assigns the +value+.
    #
    # Assigning past the end of the row with an index will set all pairs between
    # to <tt>[nil, nil]</tt>.  Assigning to an unused header appends the new
    # pair.
    #
    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:
    #   <<( field )
    #   <<( header_and_field_array )
    #   <<( header_and_field_hash )
    #
    # If a two-element Array is provided, it is assumed to be a header and field
    # and the pair is appended.  A Hash works the same way with the key being
    # the header and the value being the field.  Anything else is assumed to be
    # a lone field which is appended with a +nil+ header.
    #
    # This method returns the row for chaining.
    #
    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

    #
    # A shortcut for appending multiple fields.  Equivalent to:
    #
    #   args.each { |arg| csv_row << arg }
    #
    # This method returns the row for chaining.
    #
    def push(*args)
      args.each { |arg| self << arg }

      self  # for chaining
    end

    #
    # :call-seq:
    #   delete( header )
    #   delete( header, offset )
    #   delete( index )
    #
    # Used to remove a pair from the row by +header+ or +index+.  The pair is
    # located as described in CSV::Row.field().  The deleted pair is returned,
    # or +nil+ if a pair could not be found.
    #
    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

    #
    # The provided +block+ is passed a header and field for each pair in the row
    # and expected to return +true+ or +false+, depending on whether the pair
    # should be deleted.
    #
    # This method returns the row for chaining.
    #
    # If no block is given, an Enumerator is returned.
    #
    def delete_if(&block)
      return enum_for(__method__) { size } unless block_given?

      @row.delete_if(&block)

      self  # for chaining
    end

    #
    # This method accepts any number of arguments which can be headers, indices,
    # Ranges of either, or two-element Arrays containing a header and offset.
    # Each argument will be replaced with a field lookup as described in
    # CSV::Row.field().
    #
    # If called with no arguments, all fields are returned.
    #
    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( header, offset )
    #
    # This method will return the index of a field with the provided +header+.
    # The +offset+ can be used to locate duplicate header names, as described in
    # CSV::Row.field().
    #
    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

    #
    # Returns +true+ if +data+ matches a field in this row, and +false+
    # otherwise.
    #
    def field?(data)
      fields.include? data
    end

    include Enumerable

    #
    # Yields each pair of the row as header and field tuples (much like
    # iterating over a Hash). This method returns the row for chaining.
    #
    # If no block is given, an Enumerator is returned.
    #
    # Support for Enumerable.
    #
    def each(&block)
      return enum_for(__method__) { size } unless block_given?

      @row.each(&block)

      self  # for chaining
    end

    alias_method :each_pair, :each

    #
    # Returns +true+ if this row contains the same headers and fields in the
    # same order as +other+.
    #
    def ==(other)
      return @row == other.row if other.is_a? CSV::Row
      @row == other
    end

    #
    # Collapses the row into a simple Hash.  Be warned that this discards field
    # order and clobbers duplicate fields.
    #
    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

    alias_method :to_ary, :to_a

    #
    # Returns the row as a CSV String.  Headers are not used.  Equivalent to:
    #
    #   csv_row.fields.to_csv( options )
    #
    def to_csv(**options)
      fields.to_csv(options)
    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, *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

    # A summary of fields, by header, in an ASCII compatible String.
    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