Class: ValuesReader

Inherits:
Object
  • Object
show all
Includes:
LogUtils::Logging
Defined in:
lib/textutils/reader/values_reader.rb

Instance Method Summary collapse

Constructor Details

#initialize(path, more_values = {}) ⇒ ValuesReader

Returns a new instance of ValuesReader.



7
8
9
10
11
12
13
# File 'lib/textutils/reader/values_reader.rb', line 7

def initialize( path, more_values={} )
  @path = path

  @more_values = more_values

  @data = File.read_utf8( @path )
end

Instance Method Details

#each_lineObject

support multi line records



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
# File 'lib/textutils/reader/values_reader.rb', line 24

def each_line   # support multi line records

  inside_line = false   # todo: find a better name? e.g. line_found?
  attribs = {}     # rename to new_attributes?
  more_cols = []   # rename to more_values?
    

  @data.each_line do |line|

    ## allow alternative comment lines
    ## e.g. -- comment or
    ##      % comment
    ##  why?  # might get used by markdown for marking headers, for example

    ## NB: for now alternative comment lines not allowed as end of line style e.g
    ##  some data, more data   -- comment here

    if line =~ /^\s*#/ || line =~ /^\s*--/ || line =~ /^\s*%/
      # skip komments and do NOT copy to result (keep comments secret!)
      logger.debug 'skipping comment line'
      next
    end

    if line =~ /^\s*$/
      # kommentar oder leerzeile überspringen 
      logger.debug 'skipping blank line'
      next
    end

    # pass 1) remove possible trailing eol comment
    ##  e.g    -> nyc, New York   # Sample EOL Comment Here (with or without commas,,,,)
    ## becomes -> nyc, New York

    line = line.sub( /\s+#.+$/, '' )

    # pass 2) remove leading and trailing whitespace
    
    line = line.strip


    ### check for multiline record
    ##    must start with key and colon   e.g.   brands: 
    if line =~ /^[a-z][a-z0-9.]*[a-z0-9]:/
       # NB: every additional line is one value e.g. city:wien, etc.
       #  allows you to use any chars
       logger.debug "   multi-line record - add key-value >#{line}<"

       more_cols.unshift( line.dup )   # add value upfront to array (first value); lets us keep (optional) tags as last entry; fix!! see valuereaderEx v2
       next
    else
      # NB: new record clears/ends multi-line record
      
      if inside_line  # check if we already processed a line? if yes; yield last line
        yield( attribs, more_cols )
        attribs   = {}
        more_cols = []
      end
      inside_line = true
    end


    ### guard escaped commas (e.g. \,)
    line = line.gsub( '\,', '@commma@' )
    
    ## use generic separator (allow us to configure separator)
    line = line.gsub( ',', '@sep@')
    
    ## restore escaped commas (before split)
    line = line.gsub( '@commma@', ',' )


    logger.debug "line: >>#{line}<<"

    values = line.split( '@sep@' )
    
    # pass 1) remove leading and trailing whitespace for values

    values = values.map { |value| value.strip }

    ##### todo remove support of comment column? (NB: must NOT include commas)
    # pass 2) remove comment columns
    
    values = values.select do |value|
      if value =~ /^#/  ## start with # treat it as a comment column; e.g. remove it
        logger.debug "   removing column with value >>#{value}<<"
        false
      else
        true
      end
    end
    
    logger.debug "  values: >>#{values.join('<< >>')}<<"
    
    
    ### todo/fix: allow check - do NOT allow mixed use of with key and w/o key
    ##  either use keys or do NOT use keys; do NOT mix in a single fixture file
    
    
    ### support autogenerate key from first title value
    
    # if it looks like a key (only a-z lower case allowed); assume it's a key
    #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
    #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.

    # fix/todo: add support for leading underscore _
    #   or allow keys starting w/ digits?
    if values[0] =~ /^([a-z][a-z0-9.]*[a-z0-9]|[a-z])$/    # NB: key must start w/ a-z letter (NB: minimum one letter possible)
      key_col         = values[0]
      title_col       = values[1]
      more_cols       = values[2..-1]
    else
      key_col         = '<auto>'
      title_col       = values[0]
      more_cols       = values[1..-1]
    end

    attribs = {}

    ## title (split of optional synonyms)
    # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
    titles = title_col.split('|')
    
    attribs[ :title ]    =  titles[0]
   
    ## add optional synonyms if present
    attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
    
    if key_col == '<auto>'
      ## autogenerate key from first title
      key_col = title_to_key( titles[0] )
      logger.debug "   autogen key >#{key_col}< from title >#{titles[0]}<, textutils version #{TextUtils::VERSION}"
    end
    
    attribs[ :key ] = key_col
    
    attribs = attribs.merge( @more_values )  # e.g. merge country_id and other defaults if present
                      
  end # each lines

  # do NOT forget to yield last line (if present/processed)
  if inside_line
    yield( attribs, more_cols )
  end


end

#each_line_old_single_line_records_onlyObject



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
# File 'lib/textutils/reader/values_reader.rb', line 173

def each_line_old_single_line_records_only
    
  @data.each_line do |line|

    ## allow alternative comment lines
    ## e.g. -- comment or
    ##      % comment
    ##  why?  # might get used by markdown for marking headers, for example

    ## NB: for now alternative comment lines not allowed as end of line style e.g
    ##  some data, more data   -- comment here

    if line =~ /^\s*#/ || line =~ /^\s*--/ || line =~ /^\s*%/
      # skip komments and do NOT copy to result (keep comments secret!)
      logger.debug 'skipping comment line'
      next
    end

    if line =~ /^\s*$/
      # kommentar oder leerzeile überspringen 
      logger.debug 'skipping blank line'
      next
    end


    # pass 1) remove possible trailing eol comment
    ##  e.g    -> nyc, New York   # Sample EOL Comment Here (with or without commas,,,,)
    ## becomes -> nyc, New York

    line = line.sub( /\s+#.+$/, '' )

    # pass 2) remove leading and trailing whitespace
    
    line = line.strip

    ### guard escaped commas (e.g. \,)
    line = line.gsub( '\,', '@commma@' )
    
    ## use generic separator (allow us to configure separator)
    line = line.gsub( ',', '@sep@')
    
    ## restore escaped commas (before split)
    line = line.gsub( '@commma@', ',' )


    logger.debug "line: >>#{line}<<"

    values = line.split( '@sep@' )
    
    # pass 1) remove leading and trailing whitespace for values

    values = values.map { |value| value.strip }

    ##### todo remove support of comment column? (NB: must NOT include commas)
    # pass 2) remove comment columns
    
    values = values.select do |value|
      if value =~ /^#/  ## start with # treat it as a comment column; e.g. remove it
        logger.debug "   removing column with value >>#{value}<<"
        false
      else
        true
      end
    end
    
    logger.debug "  values: >>#{values.join('<< >>')}<<"
    
    
    ### todo/fix: allow check - do NOT allow mixed use of with key and w/o key
    ##  either use keys or do NOT use keys; do NOT mix in a single fixture file
    
    
    ### support autogenerate key from first title value
    
    # if it looks like a key (only a-z lower case allowed); assume it's a key
    #   - also allow . in keys e.g. world.quali.america, at.cup, etc.
    #   - also allow 0-9 in keys e.g. at.2, at.3.1, etc.

    # fix/todo: add support for leading underscore _
    #   or allow keys starting w/ digits?
    if values[0] =~ /^([a-z][a-z0-9.]*[a-z0-9]|[a-z])$/    # NB: key must start w/ a-z letter (NB: minimum one letter possible)
      key_col         = values[0]
      title_col       = values[1]
      more_cols       = values[2..-1]
    else
      key_col         = '<auto>'
      title_col       = values[0]
      more_cols       = values[1..-1]
    end

    attribs = {}

    ## title (split of optional synonyms)
    # e.g. FC Bayern Muenchen|Bayern Muenchen|Bayern
    titles = title_col.split('|')
    
    attribs[ :title ]    =  titles[0]
   
    ## add optional synonyms if present
    attribs[ :synonyms ] =  titles[1..-1].join('|')  if titles.size > 1
    
    if key_col == '<auto>'
      ## autogenerate key from first title
      key_col = title_to_key( titles[0] )
      logger.debug "   autogen key >#{key_col}< from title >#{titles[0]}<, textutils version #{TextUtils::VERSION}"
    end
    
    attribs[ :key ] = key_col
    
    attribs = attribs.merge( @more_values )  # e.g. merge country_id and other defaults if present
                      
    yield( attribs, more_cols )

  end # each lines

end

#title_to_key(title) ⇒ Object



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
# File 'lib/textutils/reader/values_reader.rb', line 292

def title_to_key( title )

    ## NB: downcase does NOT work for accented chars (thus, include in alternatives)
    key = title.downcase

    ### remove optional english translation in square brackets ([]) e.g. Wien [Vienna]
    key = key.gsub( /\[.+\]/, '' )

    ## remove optional longer title part in () e.g. Las Palmas (de Gran Canaria), Palma (de Mallorca)
    key = key.gsub( /\(.+\)/, '' )
    
    ## remove optional longer title part in {} e.g. Ottakringer {Bio} or {Alkoholfrei}
    ## todo: use for autotags? e.g. {Bio} => bio 
    key = key.gsub( /\{.+\}/, '' )

    ## remove all whitespace and punctuation
    key = key.gsub( /[ \t_\-\.()\[\]'"\/]/, '' )

    ## remove special chars (e.g. %°&)
    key = key.gsub( /[%&°]/, '' )

    ##  turn accented char into ascii look alike if possible
    ##
    ## todo: add some more
    ## see http://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references  for more
    
    ## todo: add unicode codepoint name
    
    alternatives = [
      ['ß', 'ss'],
      ['æ', 'ae'],
      ['ä', 'ae'],
      ['ā', 'a' ],  # e.g. Liepājas
      ['á', 'a' ],  # e.g. Bogotá, Králové
      ['ã', 'a' ],  # e.g  São Paulo
      ['ă', 'a' ],  # e.g. Chișinău
      ['â', 'a' ],  # e.g  Goiânia
      ['å', 'a' ],  # e.g. Vålerenga
      ['ą', 'a' ],  # e.g. Śląsk
      ['ç', 'c' ],  # e.g. São Gonçalo, Iguaçu, Neftçi
      ['ć', 'c' ],  # e.g. Budućnost
      ['č', 'c' ],  # e.g. Tradiční, Výčepní
      ['é', 'e' ],  # e.g. Vélez, Králové
      ['è', 'e' ],  # e.g. Rivières
      ['ê', 'e' ],  # e.g. Grêmio
      ['ě', 'e' ],  # e.g. Budějovice
      ['ĕ', 'e' ],  # e.g. Svĕtlý
      ['ė', 'e' ],  # e.g. Vėtra
      ['ë', 'e' ],  # e.g. Skënderbeu
      ['ğ', 'g' ],  # e.g. Qarabağ
      ['ì', 'i' ],  # e.g. Potosì
      ['í', 'i' ],  # e.g. Ústí
      ['ł', 'l' ],  # e.g. Wisła, Wrocław
      ['ñ', 'n' ],  # e.g. Porteño
      ['ň', 'n' ],  # e.g. Plzeň, Třeboň
      ['ö', 'oe'],
      ['ő', 'o' ],  # e.g. Győri
      ['ó', 'o' ],  # e.g. Colón, Łódź, Kraków
      ['õ', 'o' ],  # e.g. Nõmme
      ['ø', 'o' ],  # e.g. Fuglafjørdur, København
      ['ř', 'r' ],  # e.g. Třeboň
      ['ș', 's' ],  # e.g. Chișinău, București
      ['ş', 's' ],  # e.g. Beşiktaş
      ['š', 's' ],  # e.g. Košice
      ['ť', 't' ],  # e.g. Měšťan
      ['ü', 'ue'],
      ['ú', 'u' ],  # e.g. Fútbol
      ['ū', 'u' ],  # e.g. Sūduva
      ['ů', 'u' ],  # e.g. Sládkův
      ['ı', 'u' ],  # e.g. Bakı   # use u?? (Baku) why-why not?
      ['ý', 'y' ],  # e.g. Nefitrovaný
      ['ź', 'z' ],  # e.g. Łódź
      ['ž', 'z' ],  # e.g. Domžale, Petržalka

      ['Č', 'c' ],  # e.g. České
      ['İ', 'i' ],  # e.g. İnter
      ['Í', 'i' ],  # e.g. ÍBV
      ['Ł', 'l' ],  # e.g. Łódź
      ['Ö', 'oe' ], # e.g. Örebro
      ['Ř', 'r' ],  # e.g. Řezák
      ['Ś', 's' ],  # e.g. Śląsk
      ['Š', 's' ],  # e.g. MŠK
      ['Ş', 's' ],  # e.g. Şüvälan
      ['Ú', 'u' ],  # e.g. Ústí, Újpest
      ['Ž', 'z' ]   # e.g. Žilina
    ]
    
    alternatives.each do |alt|
      key = key.gsub( alt[0], alt[1] )
    end

    key
end