Class: CsvHuman::Tag

Inherits:
Object
  • Object
show all
Defined in:
lib/csvhuman/tag.rb

Constant Summary collapse

SEP_REGEX =

1) plus (with optional hashtag and/or optional leading and trailing spaces)

2) hashtag (with optional leading and trailing spaces)
3) spaces only (not followed by plus) or
 note: plus pattern must go first (otherwise "sector  + en" becomes ["sector", "", "en"])

/(?:  \s*\++
          (?:\s*\#+)?
      \s*  )
     |
 (?:  \s*\#+\s*  )
     |
 (?:  \s+)
/x

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(name, attributes = nil, type = String) ⇒ Tag

Returns a new instance of Tag.



118
119
120
121
122
123
 
# File 'lib/csvhuman/tag.rb', line 118

def initialize( name, attributes=nil, type=String )
  @name       = name
  ## sorted a-z - note: make sure attributes is [] NOT nil if empty - why? why not?

  @attributes = attributes || []
  @type       = type         ## type class (defaults to String)

end

Instance Attribute Details

#attributes ⇒ Object (readonly)

use attribs or something shorter - why? why not?



115
116
117
 
# File 'lib/csvhuman/tag.rb', line 115

def attributes
  @attributes
end

#name ⇒ Object (readonly)

Returns the value of attribute name.



114
115
116
 
# File 'lib/csvhuman/tag.rb', line 114

def name
  @name
end

#type ⇒ Object (readonly)

Returns the value of attribute type.



116
117
118
 
# File 'lib/csvhuman/tag.rb', line 116

def type
  @type
end

Class Method Details

.guess_type(name, attributes) ⇒ Object 



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
 
# File 'lib/csvhuman/tag.rb', line 60

def self.guess_type( name, attributes )

  if name == 'date'
     Date
  ## todo/fix: add more well-known names with num required!!!

  elsif ['affected', 'inneed', 'targeted', 'reached', 'population'].include?( name )
     Integer
  else
    ## check attributes

    if attributes.nil? || attributes.empty?
      String  ## assume (default to) string

    elsif attributes.include?( 'num' ) ||
          attributes.include?( 'id')   ## assume id is (always) a rowid - why? why not?

      Integer
    elsif attributes.include?( 'date' )   ### todo/check: exists +date?

      Date
    elsif name == 'geo' && (attributes.include?('lat') ||
                            attributes.include?('lon') ||
                            attributes.include?('elevation'))
      Float
    elsif attributes.include?( 'killed' ) ||
          attributes.include?( 'injured' ) ||
          attributes.include?( 'infected' ) ||
          attributes.include?( 'displaced' ) ||
          attributes.include?( 'idps' ) ||
          attributes.include?( 'refugees' ) ||
          attributes.include?( 'abducted' ) ||
          attributes.include?( 'threatened' ) ||
          attributes.include?( 'affected' ) ||
          attributes.include?( 'inneed' ) ||
          attributes.include?( 'targeted' ) ||
          attributes.include?( 'reached' )
      Integer
    else
      String   ## assume (default to) string

    end
  end
end

.normalize(value) ⇒ Object

todo: rename to pretty or something or add alias



43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
 
# File 'lib/csvhuman/tag.rb', line 43

def self.normalize( value )   ## todo: rename to pretty or something or add alias

  parts = split( value )
  name       = parts[0]
  attributes = parts[1..-1]   ## note: might be nil


  buf = ''
  if name  ## note: name might be nil too e.g. value = "" or value = "   "

    buf << '#' + name
    if attributes && attributes.size > 0
      buf << ' +'
      buf << attributes.join(' +')
    end
  end
  buf
end

.parse(value) ⇒ Object 



101
102
103
104
105
106
107
108
109
 
# File 'lib/csvhuman/tag.rb', line 101

def self.parse( value )
  parts = split( value )

  name       = parts[0]
  attributes = parts[1..-1]   ## todo/fix: check if nil (make it empty array [] always) - why? why not?

  type       = guess_type( name, attributes )

  new( name, attributes, type )
end

.split(value) ⇒ Object 



24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/csvhuman/tag.rb', line 24

def self.split( value )
  value = value.strip
  value = value.downcase
  while value.start_with?('#') do   ## allow one or more hashes

    value = value[1..-1]    ## remove leading #

    value = value.strip   ## strip (optional) leading spaces (again)

  end
  ## pp value

  parts = value.split( SEP_REGEX )

  ## sort attributes a-z

  if parts.size > 2
     [parts[0]] + parts[1..-1].sort
  else
    parts
  end
end

Instance Method Details

#key ⇒ Object 



126
127
128
129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/csvhuman/tag.rb', line 126

def key
  ## convenience short cut for "standard/default" string key

  ##   cache/pre-built/memoize - why? why not?

  ##  builds:

  ##   population+affected+children+f


  buf = ''
  buf << @name
  if @attributes && @attributes.size > 0
    buf << '+'
    buf << @attributes.join('+')
  end
  buf
end

#to_s ⇒ Object 



141
142
143
144
145
146
147
148
149
150
151
152
153
154
 
# File 'lib/csvhuman/tag.rb', line 141

def to_s
  ## cache/pre-built/memoize - why? why not?

  ##

  ##  builds

  ##     #population +affected +children +f


  buf = ''
  buf << '#' + @name
  if @attributes && @attributes.size > 0
    buf << ' +'
    buf << @attributes.join(' +')
  end
  buf
end

#typecast(value) ⇒ Object

use convert or call - why? why not?



157
158
159
160
161
162
163
164
165
166
167
168
 
# File 'lib/csvhuman/tag.rb', line 157

def typecast( value )   ## use convert or call - why? why not?

  if @type == Integer
    conv_to_i( value )
  elsif @type == Float
    conv_to_f( value )
  elsif @type == Date
    conv_to_date( value )
  else   ## assume String

    # pass through as is

    value
  end
end