Module: StructuredCsv::Csv2Yaml

Defined in:
lib/structured_csv/csv2yaml.rb

Constant Summary collapse

CAST_DEFAULT_TYPE = 
"string".freeze

Class Method Summary collapse

Class Method Details

.cast_type(value, type_in_string) ⇒ Object 



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
 
# File 'lib/structured_csv/csv2yaml.rb', line 78

def self.cast_type(value, type_in_string)
  return if value.nil?

  type = type_in_string.downcase

  case type
  when "boolean"
    case value
    when /\A *true *\z/i
      true
    when /\A *false *\z/i
      false
    end
  when "integer"
    value.to_s.strip.to_i
  when "string"
    value.to_s.strip
  when /^array\{(.*)\}/
    val_type = Regexp.last_match[1] || CAST_DEFAULT_TYPE
    value.split(";").map do |v|
      # warn "cast type as #{v}, #{val_type.to_s}"
      cast_type(v, val_type.to_s)
    end
  else
    value.to_s
  end
end

.convert(csv_filename) ⇒ Object 



199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
 
# File 'lib/structured_csv/csv2yaml.rb', line 199

def self.convert(csv_filename)
  raw_data = StructuredCsv::Common.load_csv(csv_filename)

  metadata_section = get_portion(raw_data, "METADATA")
  data_section     = get_portion(raw_data, "DATA")

  # warn '----------'
  # pp data_section[:rows]
  # warn '----------'

  {
    "metadata" => parse_metadata(metadata_section[:rows]),
    "data"     => parse_data(data_section[:rows], data_section[:meta])
  }
end

.get_portion(csv, section_name) ⇒ Object 



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
 
# File 'lib/structured_csv/csv2yaml.rb', line 6

def self.get_portion(csv, section_name)
  first_row = nil
  last_row  = -1
  data_meta = {}

  warn "section_name #{section_name}"

  csv.each_with_index do |row, index|
    if first_row.nil? && is_start_of_portion?(row, section_name)
      # warn"found first"

      if row[1] && !row[1].empty?
        row[1].split(";").each do |opt|
          k, v                = opt.split("=")
          data_meta[k.to_sym] = v
        end
      end

      first_row = index + 1
      next
    end

    next unless !first_row.nil? && is_row_empty?(row)

    # warn "found last"
    last_row = index
    break
  end

  # warn "first #{first_row}  last #{last_row}"
  {
    first_row: first_row,
    last_row:  last_row,
    rows:      csv[(first_row.nil? ? 0 : first_row)..last_row],
    meta:      data_meta
  }
end

.is_row_empty?(row) ⇒ Boolean

Returns:

  • (Boolean) 


50
51
52
53
54
 
# File 'lib/structured_csv/csv2yaml.rb', line 50

def self.is_row_empty?(row)
  row.map do |f|
    f.is_a?(String) ? f.strip : f
  end.all?(&:nil?)
end

.is_start_of_portion?(row, section_name) ⇒ Boolean

Returns:

  • (Boolean) 


44
45
46
47
48
 
# File 'lib/structured_csv/csv2yaml.rb', line 44

def self.is_start_of_portion?(row, section_name)
  return false if row.first.nil?

  row.first.strip.to_s == section_name.to_s
end

.normalize_namespaces(hash) ⇒ Object

Structure all child hashes if the key is namespaced. e.g. { “hello.me” => data } becomes

{ "hello" => { "me" => data } }



219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
 
# File 'lib/structured_csv/csv2yaml.rb', line 219

def self.normalize_namespaces(hash)
  new_hash = {}

  hash.each_pair do |k, v|
    # warn"k (#{k}) v (#{v})"
    key_components = k.to_s.split(".")

    level          = new_hash
    last_component = key_components.pop
    key_components.each do |component|
      # warn"c (#{component})"
      level[component] ||= {}
      level              = level[component]
    end

    level[last_component] = v
  end

  new_hash
end

.parse_data(rows, data_meta) ⇒ Object 



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
 
# File 'lib/structured_csv/csv2yaml.rb', line 126

def self.parse_data(rows, data_meta)
  header    = []
  data_name = data_meta[:name]
  data_type = data_meta[:type] || "hash"
  data_key  = data_meta[:key]

  base_structure = case data_type
                   when "hash"
                     {}
                   when "array"
                     []
                   end

  rows.each_with_index do |row, index|
    # Assume the first column is always the key
    if index == 0
      # warn "row #{row}"
      header = row.map do |field|
        split_header_key_type(field) unless field.nil?
      end.compact

      data_key = header.first if data_type == "hash" && data_key.nil?

      next
    end
    # warn "header #{header.inspect}"

    # Skip all the empty rows
    next if is_row_empty?(row)

    # Skip if no key value
    next if row[0].nil?

    header_names = header.inject([]) do |acc, v|
      acc << v[:name]
    end

    row_values = []
    header.each_with_index do |h, i|
      v             = row[i]
      v             = v.strip unless v.nil?
      row_values[i] = cast_type(v, h[:type])
    end

    k = row_values[0]
    d = Hash[header_names[0..-1].zip(row_values[0..-1])]
    #  .transform_keys { |k| k.to_sym }

    # Remove keys if they point to nil
    d.keys.each do |k|
      d.delete(k) if d[k].nil?
    end

    case data_type
    when "hash"
      unless base_structure[k].nil?
        warn "[WARNING] there is already data inside key [#{k}] -- maybe you should set type=array?"
      end
      base_structure[k] = normalize_namespaces(d)
    when "array"
      base_structure << normalize_namespaces(d)
    end
  end

  if data_name
    base_structure = {
      data_name => base_structure
    }
  end

  base_structure
end

.parse_metadata(rows) ⇒ Object 



106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
 
# File 'lib/structured_csv/csv2yaml.rb', line 106

def self.parse_metadata(rows)
  hash = {}

  rows.each_with_index do |row, _index|
    # Skip all the empty rows
    next if is_row_empty?(row)

    name_type = split_header_key_type(row.first)
    key       = name_type[:name]
    type      = name_type[:type]

    value     = cast_type(row[1], type)
    hash[key] = value
  end

  # warn "=============================METADATA================="
  # pp hash
  normalize_namespaces(hash)
end

.split_header_key_type(header_field) ⇒ Object 



56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/structured_csv/csv2yaml.rb', line 56

def self.split_header_key_type(header_field)
  field_name = ""
  field_type = CAST_DEFAULT_TYPE

  # warn header_field
  arr = header_field.match(/\A([^\[]*)\[(.*)\]\Z/)

  if arr.nil?
    field_name = header_field
  else
    field_name = arr[1]
    field_type = arr[2]
  end

  {
    name: field_name,
    type: field_type
  }
end