Class: Bio::FlatFile::AutoDetect

Inherits:
Object
  • Object
show all
Includes:
TSort
Defined in:
lib/bio/io/flatfile.rb

Overview

AutoDetect automatically determines database class of given data.

Defined Under Namespace

Classes: RuleDebug, RuleProc, RuleRegexp, RuleRegexp2, RuleSpecial, RuleTemplate, RulesArray

Constant Summary collapse

TopRule =

Special element that is always top priority.

RuleSpecial.new('top')
BottomRule =

Special element that is always bottom priority.

RuleSpecial.new('bottom')

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ AutoDetect

Creates a new Autodetect object



984
985
986
987
988
989
990
991
 
# File 'lib/bio/io/flatfile.rb', line 984

def initialize
  # stores autodetection rules.
  @rules = Hash.new
  # stores elements (cache)
  @elements = nil
  self.add(TopRule)
  self.add(BottomRule)
end

Class Method Details

.[](*arg) ⇒ Object

make a new autodetect object



1119
1120
1121
1122
1123
 
# File 'lib/bio/io/flatfile.rb', line 1119

def self.[](*arg)
  a = self.new
  arg.each { |e| a.add(e) }
  a
end

.default ⇒ Object

returns the default autodetect object



1106
1107
1108
1109
1110
1111
 
# File 'lib/bio/io/flatfile.rb', line 1106

def self.default
  unless @default then
    @default = self.make_default
  end
  @default
end

.default=(ad) ⇒ Object

sets the default autodetect object.



1114
1115
1116
 
# File 'lib/bio/io/flatfile.rb', line 1114

def self.default=(ad)
  @default = ad
end

.make_default ⇒ Object

make a default of default autodetect object



1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
 
# File 'lib/bio/io/flatfile.rb', line 1126

def self.make_default
  a = self[
    genbank  = RuleRegexp[ 'Bio::GenBank',
      /^LOCUS       .+ bp .*[a-z]*[DR]?NA/ ],
    genpept  = RuleRegexp[ 'Bio::GenPept',
      /^LOCUS       .+ aa .+/ ],
    medline  = RuleRegexp[ 'Bio::MEDLINE',
      /^PMID\- [0-9]+$/ ],
    embl     = RuleRegexp[ 'Bio::EMBL',
      /^ID   .+\; .*(DNA|RNA|XXX)\;/ ],
    sptr     = RuleRegexp2[ 'Bio::SPTR',
      /^ID   .+\; *PRT\;/,
      /^ID   [-A-Za-z0-9_\.]+ .+\; *[0-9]+ *AA\./ ],
    prosite  = RuleRegexp[ 'Bio::PROSITE',
      /^ID   [-A-Za-z0-9_\.]+\; (PATTERN|RULE|MATRIX)\.$/ ],
    transfac = RuleRegexp[ 'Bio::TRANSFAC',
      /^AC  [-A-Za-z0-9_\.]+$/ ],

    aaindex  = RuleProc.new('Bio::AAindex1', 'Bio::AAindex2') do |text|
      if /^H [-A-Z0-9_\.]+$/ =~ text then
        if text =~ /^M [rc]/ then
          Bio::AAindex2
        elsif text =~ /^I    A\/L/ then
          Bio::AAindex1
        else
          false #fail to determine
        end
      else
        nil
      end
    end,

    litdb    = RuleRegexp[ 'Bio::LITDB',
      /^CODE        [0-9]+$/ ],
    brite    = RuleRegexp[ 'Bio::KEGG::BRITE',
      /^Entry           [A-Z0-9]+/ ],
    orthology = RuleRegexp[ 'Bio::KEGG::ORTHOLOGY',
      /^ENTRY       .+ KO\s*/ ],
    drug     = RuleRegexp[ 'Bio::KEGG::DRUG',
      /^ENTRY       .+ Drug\s*/ ],
    glycan   = RuleRegexp[ 'Bio::KEGG::GLYCAN',
      /^ENTRY       .+ Glycan\s*/ ],
    enzyme   = RuleRegexp2[ 'Bio::KEGG::ENZYME',
      /^ENTRY       EC [0-9\.]+$/,
      /^ENTRY       .+ Enzyme\s*/
    ],
    compound = RuleRegexp2[ 'Bio::KEGG::COMPOUND',
      /^ENTRY       C[A-Za-z0-9\._]+$/,
      /^ENTRY       .+ Compound\s*/
    ],
    reaction = RuleRegexp2[ 'Bio::KEGG::REACTION',
      /^ENTRY       R[A-Za-z0-9\._]+$/,
      /^ENTRY       .+ Reaction\s*/
    ],
    genes    = RuleRegexp[ 'Bio::KEGG::GENES',
      /^ENTRY       .+ (CDS|gene|.*RNA|Contig) / ],
    genome   = RuleRegexp[ 'Bio::KEGG::GENOME',
      /^ENTRY       [a-z]+$/ ],

    fantom = RuleProc.new('Bio::FANTOM::MaXML::Cluster',
                          'Bio::FANTOM::MaXML::Sequence') do |text|
      if /\<\!DOCTYPE\s+maxml\-(sequences|clusters)\s+SYSTEM/ =~ text
        case $1
        when 'clusters'
          Bio::FANTOM::MaXML::Cluster
        when 'sequences'
          Bio::FANTOM::MaXML::Sequence
        else
          nil #unknown
        end
      else
        nil
      end
    end,

    pdb = RuleRegexp[ 'Bio::PDB',
      /^HEADER    .{40}\d\d\-[A-Z]{3}\-\d\d   [0-9A-Z]{4}/ ],
    het = RuleRegexp[ 'Bio::PDB::ChemicalComponent',
      /^RESIDUE +.+ +\d+\s*$/ ],

    clustal = RuleRegexp2[ 'Bio::ClustalW::Report',
    /^CLUSTAL .*\(.*\).*sequence +alignment/,
    /^CLUSTAL FORMAT for T-COFFEE/ ],

    gcg_msf = RuleRegexp[ 'Bio::GCG::Msf',
    /^!!(N|A)A_MULTIPLE_ALIGNMENT .+/ ],

    gcg_seq = RuleRegexp[ 'Bio::GCG::Seq',
    /^!!(N|A)A_SEQUENCE .+/ ],

    blastxml = RuleRegexp[ 'Bio::Blast::Report',
      /\<\!DOCTYPE BlastOutput PUBLIC / ],
    wublast  = RuleRegexp[ 'Bio::Blast::WU::Report',
      /^BLAST.? +[\-\.\w]+\-WashU +\[[\-\.\w ]+\]/ ],
    wutblast = RuleRegexp[ 'Bio::Blast::WU::Report_TBlast',
      /^TBLAST.? +[\-\.\w]+\-WashU +\[[\-\.\w ]+\]/ ],
    blast    = RuleRegexp[ 'Bio::Blast::Default::Report',
      /^BLAST.? +[\-\.\w]+ +\[[\-\.\w ]+\]/ ],
    tblast   = RuleRegexp[ 'Bio::Blast::Default::Report_TBlast',
      /^TBLAST.? +[\-\.\w]+ +\[[\-\.\w ]+\]/ ],

    blat   = RuleRegexp[ 'Bio::Blat::Report',
      /^psLayout version \d+/ ],
    spidey = RuleRegexp[ 'Bio::Spidey::Report',
      /^\-\-SPIDEY version .+\-\-$/ ],
    hmmer  = RuleRegexp[ 'Bio::HMMER::Report',
      /^HMMER +\d+\./ ],
    sim4   = RuleRegexp[ 'Bio::Sim4::Report',
      /^seq1 \= .*\, \d+ bp(\r|\r?\n)seq2 \= .*\, \d+ bp(\r|\r?\n)/ ],

    fastaformat = RuleProc.new('Bio::FastaFormat',
                               'Bio::NBRF',
                               'Bio::FastaNumericFormat') do |text|
      if /^>.+$/ =~ text
        case text
        when /^>([PF]1|[DR][LC]|N[13]|XX)\;.+/
          Bio::NBRF
        when /^>.+$\s+(^\#.*$\s*)*^\s*\d*\s*[-a-zA-Z_\.\[\]\(\)\*\+\$]+/
            Bio::FastaFormat
        when /^>.+$\s+^\s*\d+(\s+\d+)*\s*$/
          Bio::FastaNumericFormat
        else
          false
        end
      else
        nil
      end
    end
  ]

  # dependencies
  # NCBI
  genbank.is_prior_to genpept
  # EMBL/UniProt
  embl.is_prior_to sptr
  sptr.is_prior_to prosite
  prosite.is_prior_to transfac
  # KEGG
  #aaindex.is_prior_to litdb
  #litdb.is_prior_to brite
  brite.is_prior_to orthology
  orthology.is_prior_to drug
  drug.is_prior_to glycan
  glycan.is_prior_to enzyme
  enzyme.is_prior_to compound
  compound.is_prior_to reaction
  reaction.is_prior_to genes
  genes.is_prior_to genome
  # PDB
  pdb.is_prior_to het
  # BLAST
  wublast.is_prior_to wutblast
  wutblast.is_prior_to blast
  blast.is_prior_to tblast
  # FastaFormat
  BottomRule.is_prior_to(fastaformat)

  # for debug
  #debug_first = RuleDebug.new('debug_first')
  #a.add(debug_first)
  #debug_first.is_prior_to(TopRule)

  ## for debug
  #debug_last = RuleDebug.new('debug_last')
  #a.add(debug_last)
  #BottomRule.is_prior_to(debug_last)
  #fastaformat.is_prior_to(debug_last)

  a.rehash
  return a
end

Instance Method Details

#add(elem) ⇒ Object

Adds a new element. Returns elem.



995
996
997
998
999
1000
 
# File 'lib/bio/io/flatfile.rb', line 995

def add(elem)
  raise 'element name conflicts' if @rules[elem.name]
  @elements = nil
  @rules[elem.name] = elem
  elem
end

#autodetect(text, meta = {}) ⇒ Object

Autodetect from the text. Returns a database class if succeeded. Returns nil if failed.



1063
1064
1065
1066
1067
1068
1069
1070
1071
 
# File 'lib/bio/io/flatfile.rb', line 1063

def autodetect(text, meta = {})
  r = nil
  elements.each do |e|
    #$stderr.puts e.name
    r = e.guess(text, meta)
    break if r
  end
  r
end

#autodetect_flatfile(ff, lines = 31) ⇒ Object

autodetect from the FlatFile object. Returns a database class if succeeded. Returns nil if failed.



1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
 
# File 'lib/bio/io/flatfile.rb', line 1076

def autodetect_flatfile(ff, lines = 31)
  meta = {}
  stream = ff.instance_eval { @stream }
  begin
    path = stream.path
  rescue NameError
  end
  if path then
    meta[:path] = path
    # call autodetect onece with meta and without any read action
    if r = self.autodetect(stream.prefetch_buffer, meta)
      return r
    end
  end
  # reading stream
  1.upto(lines) do |x|
    break unless line = stream.prefetch_gets
    if line.strip.size > 0 then
      if r = self.autodetect(stream.prefetch_buffer, meta)
        return r
      end
    end
  end
  return nil
end

#each_rule(&x) ⇒ Object

Iterates over each element.



1056
1057
1058
 
# File 'lib/bio/io/flatfile.rb', line 1056

def each_rule(&x) #:yields: elem
  elements.each(&x)
end

#elements ⇒ Object

Returns current elements as an array whose order fulfills all elements’ priorities.



1033
1034
1035
1036
1037
1038
1039
1040
 
# File 'lib/bio/io/flatfile.rb', line 1033

def elements
  unless @elements
    ary = tsort
    ary.reverse!
    @elements = ary
  end
  @elements
end

#inspect ⇒ Object

visualizes the object (mainly for debug)



1049
1050
1051
1052
1053
 
# File 'lib/bio/io/flatfile.rb', line 1049

def inspect
  "<#{self.class.to_s} " +
    self.elements.collect { |e| e.name.inspect }.join(' ') +
    ">"
end

#rehash ⇒ Object

rebuilds the object and clears internal cache.



1043
1044
1045
1046
 
# File 'lib/bio/io/flatfile.rb', line 1043

def rehash
  @rules.rehash
  @elements = nil
end

#tsort_each_child(elem) ⇒ Object

(required by TSort.) For a given element, yields each child (= lower priority elements) of the element.



1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
 
# File 'lib/bio/io/flatfile.rb', line 1011

def tsort_each_child(elem)
  if elem == TopRule then
    @rules.each_value do |e|
      yield e unless e == TopRule or 
        e.lower_priority_elements.index(TopRule)
    end
  elsif elem == BottomRule then
    @rules.each_value do |e|
      yield e if e.higher_priority_elements.index(BottomRule)
    end
  else
    elem.lower_priority_elements.each do |e|
      yield e if e != BottomRule
    end
    unless elem.higher_priority_elements.index(BottomRule)
      yield BottomRule
    end
  end
end

#tsort_each_node(&x) ⇒ Object

(required by TSort.) For all elements, yields each element.



1004
1005
1006
 
# File 'lib/bio/io/flatfile.rb', line 1004

def tsort_each_node(&x)
  @rules.each_value(&x)
end