Class: SciYAG::Backends::MDBBackend

Inherits:
Backend
  • Object
show all
Includes:
Dobjects
Defined in:
lib/SciYAG/Backends/mdb.rb

Direct Known Subclasses

MDBCyclicVoltammogram, MDBEIS

Defined Under Namespace

Classes: DataSet

Constant Summary collapse

COL_SEP =

The separator for columns when reading the file.

"###"
MDB_EXPORT =

The command to run mdb-export

"mdb-export"
SUBSET_RE =

This RE tells if a set looks like it might contain a subset. Slurps anything until the last @.

/(.+)@(.+)/

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Backend

#base_line=, #clear_xy_filters, default_state, describe, #get_cached_entry, #has_set?, list_backends, list_descriptions, logger=, #meta_data, #pop_xy_filter, #push_xy_filter, #set_type, #xy_data, #xyz_data

Methods included from MetaBuilder::DescriptionExtend

#base_description, #create_factory, #describe, #description, #factory_class, #factory_description, #factory_description_hash, #factory_description_list, #group, #has_factory?, #inherit_parameters, #param, #param_accessor, #param_reader, #param_writer, #register_class, #set_description

Methods included from MetaBuilder::DescriptionInclude

#description, #get_param, #get_param_raw, #long_name, #option_parser_banner, #option_parser_fill, #option_parser_options, #parameter, #restore_state, #save_state, #set_param, #set_param_raw

Constructor Details

#initialize ⇒ MDBBackend

Returns a new instance of MDBBackend.



114
115
116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/SciYAG/Backends/mdb.rb', line 114

def initialize
  super()
  @data_set_table_name = nil           # has to be redefined by children
  # A hash holding dataset_name -> DataSet object
  @data_sets = {}
  @data_set_id = []         # The same as upper,
  # but with the set number

  # The column for different sets
  @data_set_name_col = "Series"

  # The current database
  @current_database = ""
end

Instance Attribute Details

#current_database ⇒ Object (readonly)

Returns the value of attribute current_database.



194
195
196
 
# File 'lib/SciYAG/Backends/mdb.rb', line 194

def current_database
  @current_database
end

#data_set_name_col ⇒ Object

If this attribute is set, the sets are further split for the different values of that column



49
50
51
 
# File 'lib/SciYAG/Backends/mdb.rb', line 49

def data_set_name_col
  @data_set_name_col
end

#data_set_table_name ⇒ Object

The table of the file where we want to look for data.



42
43
44
 
# File 'lib/SciYAG/Backends/mdb.rb', line 42

def data_set_table_name
  @data_set_table_name
end

#data_set_x_col ⇒ Object

The name of the X, Y and Z columns in the table.



45
46
47
 
# File 'lib/SciYAG/Backends/mdb.rb', line 45

def data_set_x_col
  @data_set_x_col
end

#data_set_y_col ⇒ Object

The name of the X, Y and Z columns in the table.



45
46
47
 
# File 'lib/SciYAG/Backends/mdb.rb', line 45

def data_set_y_col
  @data_set_y_col
end

#data_set_z_col ⇒ Object

The name of the X, Y and Z columns in the table.



45
46
47
 
# File 'lib/SciYAG/Backends/mdb.rb', line 45

def data_set_z_col
  @data_set_z_col
end

Instance Method Details

#expand_sets(set) ⇒ Object 



322
323
324
325
326
327
328
329
330
331
332
333
 
# File 'lib/SciYAG/Backends/mdb.rb', line 322

def expand_sets(set)
  if s = string_to_set(set)
    subs = s.subsets # we sort so that everything ids
    # looking fine.
    if subs.empty?
      return [set]
    else
      return subs.collect {|s| "#{set}@#{s}"}
    end
  end
  return [set]
end

#get_data(set) ⇒ Object

Internal function to get the data corresponding to one set.



289
290
291
292
293
294
295
296
297
298
299
300
301
 
# File 'lib/SciYAG/Backends/mdb.rb', line 289

def get_data(set)
  if set =~ SUBSET_RE
    s = string_to_set($1)
    raise "Set #{$1} is unkown" unless s
    return internal_to_external(s.x_data($2), 
                                s.y_data($2),
                                s.z_data($2))
  else
    s = string_to_set(set)
    raise "Set #{set} is unkown" unless s
    return internal_to_external(s.x_data, s.y_data, s.z_data)
  end
end

#internal_to_external(x, y, z) ⇒ Object

An internal function saying how to make a X,Y dataset from a x,y,z dataset. Can depend on many things. We just output X and Y cols here. Better be redefined by children.



284
285
286
 
# File 'lib/SciYAG/Backends/mdb.rb', line 284

def internal_to_external(x,y,z)
  return Function.new(x,y)
end

#mdb_export_table(file, table, header = false) ⇒ Object

Reads a table and returns the table of lines, optionnally beginning with the header



136
137
138
139
140
141
142
143
144
145
146
147
148
149
 
# File 'lib/SciYAG/Backends/mdb.rb', line 136

def mdb_export_table(file, table, header = false)
  cmd_line = "#{MDB_EXPORT} -Q -d '#{COL_SEP}' " + 
    if header
      " "
    else
      "-H "
    end +
    "'#{file}' '#{table}' "  +
    "| sort -n"             # we sort numerically with the program sort,
  # decently faster
  mdb = IO.popen(cmd_line)
  l = mdb.readlines
  return l
end

#mdb_table_to_hash(file, table) ⇒ Object

Reads a table and turns it into a list of hashes



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/SciYAG/Backends/mdb.rb', line 152

def mdb_table_to_hash(file, table) 
  pipe = IO.popen("#{MDB_EXPORT} -Q -d '#{COL_SEP}' -R '&&&&&' " +
                  "#{file} #{table}")
  header = pipe.readline.chomp.split(COL_SEP)
  raw_entries = pipe.read.split('&&&&&').map {|l| l.split(COL_SEP)}
  entries = []
  for raw_entry in raw_entries
    entry = {}
    header.length.times do |i|
      entry[header[i]] = raw_entry[i]
    end
    entries << entry
  end
  return entries
end

#query_xy_data(set) ⇒ Object

This is called by the architecture to get the data. It splits the set name into filename@cols, reads the file if necessary and calls get_data



306
307
308
309
 
# File 'lib/SciYAG/Backends/mdb.rb', line 306

def query_xy_data(set)
  data = get_data(set)
  return Function.new(data.x.dup, data.y.dup)
end

#read_mdb_file(file) ⇒ Object

Reads the contents of a MDB file according to different defaults.



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
 
# File 'lib/SciYAG/Backends/mdb.rb', line 200

def read_mdb_file(file)
  # First, make out the datasets from the file
  if @current_database == file
    return                  # We already read it !!
  end
  @current_database = file
  
  data_sets_properties =  mdb_table_to_hash(file, 'DataSetProperties')

  prospective_data_sets = []
  for set in data_sets_properties
    prospective_data_sets << DataSet.new(set["DataSetName"], 
                                         set["DataSetID"])
  end

  # We turn it into another array indexed on DataSetID for faster lookup
  @data_sets_ids = []
  for ds in prospective_data_sets
    @data_sets_ids[ds.data_set_id.to_i] = ds
  end
  
  # Now, we need to get data from the files
  raise "@data_set_table_name has to be set" unless @data_set_table_name
  raise "@data_set_y_col has to be set" unless @data_set_y_col
  raise "@data_set_x_col has to be set" unless @data_set_x_col
  raise "@data_set_z_col has to be set" unless @data_set_z_col
  
  l = mdb_export_table(file, @data_set_table_name, true)
  h = turn_header_into_hash(l)
  if h.key?(@data_set_x_col) and 
      h.key?(@data_set_y_col) and 
      h.key?(@data_set_z_col)
    # We first sort the data respective to the first column
    #         l.sort! do |a,b|
    #           i_a = a[0,a.index(COL_SEP)].to_i
    #           i_b = b[0,b.index(COL_SEP)].to_i
    #           i_a <=> i_b
    #         end
    x_col = h[@data_set_x_col]
    y_col = h[@data_set_y_col]
    z_col = h[@data_set_z_col]
    set_col = if @data_set_name_col
                h[@data_set_name_col]
              else 
                false
              end
    id = h["DataSetID"]
    

    l.each do |l|
      a = l.split(COL_SEP)
      ds = @data_sets_ids[a[id].to_i]
      x = safe_float(a[x_col])
      y = safe_float(a[y_col])
      z = safe_float(a[z_col])
      if data_set_name_col
        ds.add_point(x,y,z,a[set_col])
      else
        ds.add_point(x,y,z)
      end
    end
    
  else
    raise "It looks like #{@data_set_x_col} or #{@data_set_y_col} is " +
      "missing from the table #{@data_set_table_name} of file #{file}"
  end

  # Now, we populate the data_sets hash
  for ds in prospective_data_sets 
    @data_sets[ds.name] = ds
  end
end

#safe_float(x) ⇒ Object

Small helper function



183
184
185
186
187
188
189
 
# File 'lib/SciYAG/Backends/mdb.rb', line 183

def safe_float(x)
  begin
    Float(x)
  rescue
    0.0/0.0
  end
end

#sets_available ⇒ Object

I think it is better not to take the cycles into account: they will hinder the display for no good reason.



337
338
339
 
# File 'lib/SciYAG/Backends/mdb.rb', line 337

def sets_available
  return @data_sets.keys.sort
end

#string_to_set(str) ⇒ Object

Transforms a string into a set. If the set starts with a #, it means we’re directly interested in the number, not in the name. Can be a great deal useful, and much shorter…



314
315
316
317
318
319
320
 
# File 'lib/SciYAG/Backends/mdb.rb', line 314

def string_to_set(str)
  if str =~ /^\#(\d+)$/
    return @data_sets_ids[$1.to_i]
  else
    return @data_sets[str]
  end
end

#turn_header_into_hash(lines) ⇒ Object

Turns the first line returned by mdb_export_table into a nice header hash



170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/SciYAG/Backends/mdb.rb', line 170

def turn_header_into_hash(lines)
  header = lines.shift
  header = header.split(COL_SEP)
  header_hash = {}
  i = 0
  for name in header
    header_hash[name] = i
    i+=1
  end
  return header_hash
end