Parent Directory
| 
Revision Log
Revision 1.6 - (view) (download) (as text)
| 1 : | chenry | 1.1 | use strict; |
| 2 : | use FileHandle; | ||
| 3 : | |||
| 4 : | #--- This function just prints the given array reference to file with a different array element on each line ---# | ||
| 5 : | sub PrintArrayToFile { | ||
| 6 : | my ($Filename,$ArrayRef) = @_; | ||
| 7 : | |||
| 8 : | if (open (OUTPUT, ">$Filename")) { | ||
| 9 : | foreach my $Item (@{$ArrayRef}) { | ||
| 10 : | if (length($Item) > 0) { | ||
| 11 : | print OUTPUT $Item."\n"; | ||
| 12 : | } | ||
| 13 : | } | ||
| 14 : | close(OUTPUT); | ||
| 15 : | } else { | ||
| 16 : | die "Cannot open $Filename: $!"; | ||
| 17 : | } | ||
| 18 : | } | ||
| 19 : | |||
| 20 : | sub PrintTwoDimensionalArrayToFile { | ||
| 21 : | my ($Filename,$ArrayRef,$Delimiter) = @_; | ||
| 22 : | |||
| 23 : | if (open (OUTPUT, ">$Filename")) { | ||
| 24 : | foreach my $Item (@{$ArrayRef}) { | ||
| 25 : | if (@{$Item} > 0) { | ||
| 26 : | print OUTPUT join($Delimiter,@{$Item})."\n"; | ||
| 27 : | } | ||
| 28 : | } | ||
| 29 : | close(OUTPUT); | ||
| 30 : | } else { | ||
| 31 : | die "Cannot open $Filename: $!"; | ||
| 32 : | } | ||
| 33 : | } | ||
| 34 : | |||
| 35 : | |||
| 36 : | #--- This function removes the specified line from the file with the input filename if the line exists in the file ---# | ||
| 37 : | sub RemoveSpecificLineFromFile { | ||
| 38 : | my ($Filename,$DelLine,$Delimiter) = @_; | ||
| 39 : | |||
| 40 : | #Note that I donot specify the delimiter to the file upload function because I want to preserve the entire content of the file | ||
| 41 : | my $FileArray = &LoadSingleColumnFile($Filename,""); | ||
| 42 : | my $Count = 0; | ||
| 43 : | foreach my $Item (@{$FileArray}) { | ||
| 44 : | my @Data = split(/$Delimiter/,$Item); | ||
| 45 : | if ($Data[0] eq $DelLine) { | ||
| 46 : | delete $FileArray->[$Count]; | ||
| 47 : | } | ||
| 48 : | $Count++; | ||
| 49 : | } | ||
| 50 : | &PrintArrayToFile($Filename,$FileArray); | ||
| 51 : | } | ||
| 52 : | |||
| 53 : | #--- This function adds the input line to the file with the input filename if the line does not already exist in the file ---# | ||
| 54 : | sub AddLineToFileUnique { | ||
| 55 : | my ($Filename,$NewLine,$Delimiter) = @_; | ||
| 56 : | my $FileArray = &LoadSingleColumnFile($Filename,$Delimiter); | ||
| 57 : | chenry | 1.3 | my $LastLineLength = 0; |
| 58 : | chenry | 1.1 | foreach my $Item (@{$FileArray}) { |
| 59 : | chenry | 1.3 | $LastLineLength = length($Item); |
| 60 : | chenry | 1.1 | if ($Item eq $NewLine) { |
| 61 : | return; | ||
| 62 : | } | ||
| 63 : | } | ||
| 64 : | if (open (OUTPUT, ">>$Filename")) { | ||
| 65 : | chenry | 1.3 | if ($LastLineLength > 0) { |
| 66 : | print OUTPUT "\n"; | ||
| 67 : | } | ||
| 68 : | chenry | 1.1 | print OUTPUT $NewLine."\n"; |
| 69 : | close(OUTPUT); | ||
| 70 : | } else { | ||
| 71 : | die "Cannot open $Filename: $!"; | ||
| 72 : | } | ||
| 73 : | } | ||
| 74 : | |||
| 75 : | #--- This function saves the input hash back to a file where each data item is stored on a separate line with the file headings stored in the first column of data ---# | ||
| 76 : | sub SaveHashToHorizontalDataFile { | ||
| 77 : | my ($Filename,$Delimiter,$DataHashRef) = @_; | ||
| 78 : | |||
| 79 : | if (!defined($DataHashRef->{"orderedkeys"})) { | ||
| 80 : | my @Keys = keys(%{$DataHashRef}); | ||
| 81 : | push(@{$DataHashRef->{"orderedkeys"}},@Keys); | ||
| 82 : | } | ||
| 83 : | |||
| 84 : | if ($Filename eq "") { | ||
| 85 : | open (HASHTOHORIZONTALOUTPUT, ">&STDOUT"); | ||
| 86 : | } else { | ||
| 87 : | open (HASHTOHORIZONTALOUTPUT, ">$Filename"); | ||
| 88 : | } | ||
| 89 : | |||
| 90 : | if (open (HASHTOHORIZONTALOUTPUT, ">$Filename")) { | ||
| 91 : | my @ReactionKeys = @{$DataHashRef->{"orderedkeys"}}; | ||
| 92 : | foreach my $Item (@ReactionKeys) { | ||
| 93 : | if (defined($DataHashRef->{"keytranslation"}) && defined($DataHashRef->{"keytranslation"}->{$Item})) { | ||
| 94 : | $Item = $DataHashRef->{"keytranslation"}->{$Item}; | ||
| 95 : | } | ||
| 96 : | if (defined($DataHashRef->{$Item}) && @{$DataHashRef->{$Item}} > 0) { | ||
| 97 : | print HASHTOHORIZONTALOUTPUT $Item.$Delimiter.join($Delimiter,@{$DataHashRef->{"$Item"}})."\n"; | ||
| 98 : | } | ||
| 99 : | } | ||
| 100 : | close(HASHTOHORIZONTALOUTPUT); | ||
| 101 : | } else { | ||
| 102 : | die "Cannot open $Filename: $!"; | ||
| 103 : | } | ||
| 104 : | |||
| 105 : | return $DataHashRef; | ||
| 106 : | } | ||
| 107 : | |||
| 108 : | #--- This function loads a file where each data item is stored on a separate line with the file headings stored in the first column of data ---# | ||
| 109 : | sub LoadHorizontalDataFile { | ||
| 110 : | my ($Filename,$Delimiter,$HeadingTranslation) = @_; | ||
| 111 : | |||
| 112 : | my $DataHashRef = {}; | ||
| 113 : | |||
| 114 : | if (open (INPUT, "<$Filename")) { | ||
| 115 : | while (my $Line = <INPUT>) { | ||
| 116 : | chomp($Line); | ||
| 117 : | my @Data = split(/$Delimiter/,$Line); | ||
| 118 : | if (defined($HeadingTranslation) && defined($HeadingTranslation->{$Data[0]})) { | ||
| 119 : | $DataHashRef->{"keytranslation"}->{$HeadingTranslation->{$Data[0]}} = $Data[0]; | ||
| 120 : | $Data[0] = $HeadingTranslation->{$Data[0]}; | ||
| 121 : | } | ||
| 122 : | for (my $i=1; $i < @Data; $i++) { | ||
| 123 : | $DataHashRef->{$Data[0]}->[$i-1] = $Data[$i]; | ||
| 124 : | } | ||
| 125 : | if (@Data > 1) { | ||
| 126 : | push(@{$DataHashRef->{"orderedkeys"}},$Data[0]); | ||
| 127 : | } | ||
| 128 : | } | ||
| 129 : | close(INPUT); | ||
| 130 : | } else { | ||
| 131 : | die "Cannot open $Filename: $!"; | ||
| 132 : | } | ||
| 133 : | |||
| 134 : | return $DataHashRef; | ||
| 135 : | } | ||
| 136 : | |||
| 137 : | |||
| 138 : | #--- This function loads a file containing a simple list and returns a reference to an array containing that list ---# | ||
| 139 : | #--- Note that when a delimiter is supplied, each line in the file is broken up with the delimiter, and only the first element from each line is stored in the returned list ---# | ||
| 140 : | sub LoadSingleColumnFile { | ||
| 141 : | my ($Filename,$Delimiter) = @_; | ||
| 142 : | |||
| 143 : | my $DataArrayRef = []; | ||
| 144 : | if (open (INPUT, "<$Filename")) { | ||
| 145 : | while (my $Line = <INPUT>) { | ||
| 146 : | chomp($Line); | ||
| 147 : | |||
| 148 : | if (length($Delimiter) > 0) { | ||
| 149 : | my @Data = split(/$Delimiter/,$Line); | ||
| 150 : | $Line = $Data[0]; | ||
| 151 : | } | ||
| 152 : | |||
| 153 : | push(@{$DataArrayRef},$Line); | ||
| 154 : | } | ||
| 155 : | close(INPUT); | ||
| 156 : | } else { | ||
| 157 : | die "Cannot open $Filename: $!"; | ||
| 158 : | } | ||
| 159 : | return $DataArrayRef; | ||
| 160 : | } | ||
| 161 : | |||
| 162 : | #--- This function loads a file containing multiple columns of data with no file headings ---# | ||
| 163 : | sub LoadMultipleColumnFile { | ||
| 164 : | my ($Filename,$Delimiter) = @_; | ||
| 165 : | |||
| 166 : | my $DataArrayRefArrayRef = []; | ||
| 167 : | if (open (INPUT, "<$Filename")) { | ||
| 168 : | while (my $Line = <INPUT>) { | ||
| 169 : | chomp($Line); | ||
| 170 : | my $Data = []; | ||
| 171 : | $Data->[0] = $Line; | ||
| 172 : | if (length($Delimiter) > 0) { | ||
| 173 : | @{$Data} = split(/$Delimiter/,$Line); | ||
| 174 : | } | ||
| 175 : | push(@{$DataArrayRefArrayRef},$Data); | ||
| 176 : | } | ||
| 177 : | close(INPUT); | ||
| 178 : | } else { | ||
| 179 : | die "Cannot open $Filename: $!"; | ||
| 180 : | } | ||
| 181 : | return $DataArrayRefArrayRef; | ||
| 182 : | } | ||
| 183 : | |||
| 184 : | #--- This function loads a file containing multiple columns of data with file headings at the top ---# | ||
| 185 : | sub LoadMultipleLabeledColumnFile { | ||
| 186 : | my ($Filename,$ColumnDelimiter,$ItemDelimiter,$HeadingRowNumber) = @_; | ||
| 187 : | if (!defined($HeadingRowNumber) || $HeadingRowNumber eq "") { | ||
| 188 : | $HeadingRowNumber = 0; | ||
| 189 : | } | ||
| 190 : | my $DataHashRefArrayRef = []; | ||
| 191 : | if (open (INPUT, "<$Filename")) { | ||
| 192 : | my $Line = <INPUT>; | ||
| 193 : | for (my $i=0; $i < $HeadingRowNumber; $i++) { | ||
| 194 : | $Line = <INPUT>; | ||
| 195 : | } | ||
| 196 : | chomp($Line); | ||
| 197 : | if (length($ColumnDelimiter) > 0) { | ||
| 198 : | my @Headings = split(/$ColumnDelimiter/,$Line); | ||
| 199 : | chenry | 1.2 | my $First = 1; |
| 200 : | chenry | 1.1 | while ($Line = <INPUT>) { |
| 201 : | chomp($Line); | ||
| 202 : | my @Data = split(/$ColumnDelimiter/,$Line); | ||
| 203 : | my $ArrayRefHashRef; | ||
| 204 : | for (my $i=0; $i < @Headings; $i++) { | ||
| 205 : | if (defined($Data[$i]) && length($Data[$i]) > 0) { | ||
| 206 : | chenry | 1.3 | if (defined($ItemDelimiter) && length($ItemDelimiter) > 0) { |
| 207 : | chenry | 1.1 | my @TempArray = split(/$ItemDelimiter/,$Data[$i]); |
| 208 : | foreach my $Item (@TempArray) { | ||
| 209 : | push(@{$ArrayRefHashRef->{$Headings[$i]}},$Item); | ||
| 210 : | } | ||
| 211 : | } else { | ||
| 212 : | $ArrayRefHashRef->{$Headings[$i]}->[0] = $Data[$i]; | ||
| 213 : | } | ||
| 214 : | } | ||
| 215 : | } | ||
| 216 : | chenry | 1.2 | if ($First == 1) { |
| 217 : | $First = 0; | ||
| 218 : | push(@{$ArrayRefHashRef->{"orderedkeys"}},@Headings); | ||
| 219 : | } | ||
| 220 : | push(@{$DataHashRefArrayRef},$ArrayRefHashRef); | ||
| 221 : | chenry | 1.1 | } |
| 222 : | } | ||
| 223 : | close(INPUT); | ||
| 224 : | } else { | ||
| 225 : | die "Cannot open $Filename: $!"; | ||
| 226 : | } | ||
| 227 : | return $DataHashRefArrayRef; | ||
| 228 : | } | ||
| 229 : | |||
| 230 : | sub PrintHashArrayToFile { | ||
| 231 : | chenry | 1.3 | my ($Filename,$HashArrayRef,$HeaderRef,$ExtraHeaders) = @_; |
| 232 : | chenry | 1.5 | |
| 233 : | chenry | 1.2 | if (!defined($HeaderRef) || $HeaderRef == 0 || $HeaderRef eq "") { |
| 234 : | if (!defined($HashArrayRef->[0]) || !defined($HashArrayRef->[0]->{"orderedkeys"})) { | ||
| 235 : | chenry | 1.5 | return; |
| 236 : | chenry | 1.2 | } else { |
| 237 : | $HeaderRef = $HashArrayRef->[0]->{"orderedkeys"}; | ||
| 238 : | } | ||
| 239 : | } | ||
| 240 : | chenry | 1.5 | |
| 241 : | chenry | 1.1 | if (open (HASHARRAYTOFILE, ">$Filename")) { |
| 242 : | chenry | 1.3 | if (defined($ExtraHeaders)) { |
| 243 : | print HASHARRAYTOFILE $ExtraHeaders; | ||
| 244 : | chenry | 1.1 | } |
| 245 : | chenry | 1.5 | print HASHARRAYTOFILE join(";",@{$HeaderRef})."\n"; |
| 246 : | chenry | 1.1 | for (my $i=0; $i < @{$HashArrayRef}; $i++) { |
| 247 : | for (my $j=0; $j < @{$HeaderRef}; $j++) { | ||
| 248 : | if ($j > 0) { | ||
| 249 : | chenry | 1.5 | print HASHARRAYTOFILE ";"; |
| 250 : | chenry | 1.1 | } |
| 251 : | if (defined($HashArrayRef->[$i]->{$HeaderRef->[$j]})) { | ||
| 252 : | print HASHARRAYTOFILE join("|",@{$HashArrayRef->[$i]->{$HeaderRef->[$j]}}); | ||
| 253 : | } | ||
| 254 : | } | ||
| 255 : | chenry | 1.5 | print HASHARRAYTOFILE "\n"; |
| 256 : | chenry | 1.1 | } |
| 257 : | close (HASHARRAYTOFILE); | ||
| 258 : | } | ||
| 259 : | } | ||
| 260 : | |||
| 261 : | chenry | 1.4 | sub LoadTable { |
| 262 : | chenry | 1.5 | my ($VariableHash,$Filename,$Delimiter,$ItemDelimiter,$HeadingLine,$HashColumns) = @_; |
| 263 : | |||
| 264 : | chenry | 1.4 | #Checking that the table file exists |
| 265 : | if (!-e $Filename) { | ||
| 266 : | chenry | 1.5 | return undef; |
| 267 : | chenry | 1.4 | } |
| 268 : | chenry | 1.5 | |
| 269 : | chenry | 1.4 | #Sanity checking input values |
| 270 : | if (!defined($HeadingLine) || $HeadingLine eq "") { | ||
| 271 : | $HeadingLine = 0; | ||
| 272 : | } | ||
| 273 : | if (!defined($Delimiter) || $Delimiter eq "") { | ||
| 274 : | $Delimiter = ";"; | ||
| 275 : | } | ||
| 276 : | chenry | 1.5 | if ($Delimiter eq "|") { |
| 277 : | $Delimiter = "\\|"; | ||
| 278 : | } | ||
| 279 : | chenry | 1.4 | if (!defined($ItemDelimiter) || $ItemDelimiter eq "") { |
| 280 : | $ItemDelimiter = ""; | ||
| 281 : | chenry | 1.5 | } elsif ($ItemDelimiter eq "|") { |
| 282 : | $ItemDelimiter = "\\|"; | ||
| 283 : | chenry | 1.4 | } |
| 284 : | chenry | 1.5 | |
| 285 : | chenry | 1.4 | #Loading the data table |
| 286 : | my $Table; | ||
| 287 : | my $Prefix; | ||
| 288 : | my @Headings; | ||
| 289 : | if (!open (TABLEINPUT, "<$Filename")) { | ||
| 290 : | return undef; | ||
| 291 : | } | ||
| 292 : | my $Line = <TABLEINPUT>; | ||
| 293 : | for (my $i=0; $i < $HeadingLine; $i++) { | ||
| 294 : | chenry | 1.5 | $Prefix .= $Line; |
| 295 : | chenry | 1.4 | $Line = <TABLEINPUT>; |
| 296 : | } | ||
| 297 : | chomp($Line); | ||
| 298 : | chenry | 1.5 | |
| 299 : | chenry | 1.4 | @Headings = split(/$Delimiter/,$Line); |
| 300 : | while ($Line = <TABLEINPUT>) { | ||
| 301 : | chomp($Line); | ||
| 302 : | my @Data = split(/$Delimiter/,$Line); | ||
| 303 : | my $ArrayRefHashRef; | ||
| 304 : | for (my $i=0; $i < @Headings; $i++) { | ||
| 305 : | if (defined($Data[$i]) && length($Data[$i]) > 0) { | ||
| 306 : | if (defined($ItemDelimiter) && length($ItemDelimiter) > 0) { | ||
| 307 : | my @TempArray = split(/$ItemDelimiter/,$Data[$i]); | ||
| 308 : | foreach my $Item (@TempArray) { | ||
| 309 : | push(@{$ArrayRefHashRef->{$Headings[$i]}},$Item); | ||
| 310 : | } | ||
| 311 : | } else { | ||
| 312 : | $ArrayRefHashRef->{$Headings[$i]}->[0] = $Data[$i]; | ||
| 313 : | } | ||
| 314 : | } | ||
| 315 : | } | ||
| 316 : | push(@{$Table->{"array"}},$ArrayRefHashRef); | ||
| 317 : | } | ||
| 318 : | close(TABLEINPUT); | ||
| 319 : | chenry | 1.5 | |
| 320 : | chenry | 1.4 | #Loading file IO parameters |
| 321 : | $Table->{"file IO settings"}->{"filename"}->[0] = $Filename; | ||
| 322 : | chenry | 1.5 | if ($Delimiter eq "\\|") { |
| 323 : | $Delimiter = "|"; | ||
| 324 : | } | ||
| 325 : | chenry | 1.4 | $Table->{"file IO settings"}->{"delimiter"}->[0] = $Delimiter; |
| 326 : | chenry | 1.5 | if ($ItemDelimiter eq "\\|") { |
| 327 : | $ItemDelimiter = "|"; | ||
| 328 : | } | ||
| 329 : | chenry | 1.4 | $Table->{"file IO settings"}->{"item delimiter"}->[0] = $ItemDelimiter; |
| 330 : | $Table->{"file IO settings"}->{"file prefix"}->[0] = $Prefix; | ||
| 331 : | push(@{$Table->{"file IO settings"}->{"orderedkeys"}},@Headings); | ||
| 332 : | #Replacing variables in variable columns with variable values and loading hash with hash column keys | ||
| 333 : | foreach my $ItemData (@{$Table->{"array"}}) { | ||
| 334 : | if (defined($HashColumns) && $HashColumns ne "") { | ||
| 335 : | foreach my $Heading (@{$HashColumns}) { | ||
| 336 : | if (defined($ItemData->{$Heading})) { | ||
| 337 : | for (my $i=0; $i < @{$ItemData->{$Heading}}; $i++) { | ||
| 338 : | push(@{$Table->{$ItemData->{$Heading}->[$i]}},$ItemData); | ||
| 339 : | chenry | 1.5 | push(@{$Table->{"hash columns"}->{$Heading}->{$ItemData->{$Heading}->[$i]}},$ItemData); |
| 340 : | chenry | 1.4 | } |
| 341 : | } | ||
| 342 : | } | ||
| 343 : | } | ||
| 344 : | } | ||
| 345 : | chenry | 1.5 | |
| 346 : | chenry | 1.4 | return $Table; |
| 347 : | } | ||
| 348 : | |||
| 349 : | sub SaveTable { | ||
| 350 : | my ($TableRef) = @_; | ||
| 351 : | chenry | 1.5 | |
| 352 : | chenry | 1.4 | #Checking that a filename exists |
| 353 : | if (!defined($TableRef->{"array"}) || !defined($TableRef->{"file IO settings"}->{"filename"}) || !defined($TableRef->{"file IO settings"}->{"orderedkeys"})) { | ||
| 354 : | return -1; | ||
| 355 : | } | ||
| 356 : | chenry | 1.5 | |
| 357 : | chenry | 1.4 | my $Filename = $TableRef->{"file IO settings"}->{"filename"}->[0]; |
| 358 : | my $Delimiter = ";"; | ||
| 359 : | my $ItemDelimiter = "|"; | ||
| 360 : | my $Prefix = ""; | ||
| 361 : | if (defined($TableRef->{"file IO settings"}->{"delimiter"})) { | ||
| 362 : | chenry | 1.5 | $Delimiter = $TableRef->{"file IO settings"}->{"delimiter"}->[0]; |
| 363 : | if ($Delimiter eq "\\|" || $Delimiter eq "\|") { | ||
| 364 : | $Delimiter = "|"; | ||
| 365 : | } | ||
| 366 : | chenry | 1.4 | } |
| 367 : | if (defined($TableRef->{"file IO settings"}->{"item delimiter"})) { | ||
| 368 : | $ItemDelimiter = $TableRef->{"file IO settings"}->{"item delimiter"}->[0]; | ||
| 369 : | chenry | 1.5 | if ($ItemDelimiter eq "\\|" || $ItemDelimiter eq "\|") { |
| 370 : | $ItemDelimiter = "|"; | ||
| 371 : | } | ||
| 372 : | chenry | 1.4 | } |
| 373 : | if (defined($TableRef->{"file IO settings"}->{"file prefix"})) { | ||
| 374 : | $Prefix = $TableRef->{"file IO settings"}->{"file prefix"}->[0]; | ||
| 375 : | } | ||
| 376 : | chenry | 1.5 | |
| 377 : | chenry | 1.4 | #Opening the file |
| 378 : | if (defined($TableRef->{"file IO settings"}->{"append"})) { | ||
| 379 : | if (!open (SAVINGTABLE, ">>$Filename")) { | ||
| 380 : | return -1; | ||
| 381 : | } | ||
| 382 : | } else { | ||
| 383 : | if (!open (SAVINGTABLE, ">$Filename")) { | ||
| 384 : | return -1; | ||
| 385 : | } | ||
| 386 : | } | ||
| 387 : | chenry | 1.5 | |
| 388 : | if (defined($Prefix)) { | ||
| 389 : | print SAVINGTABLE $Prefix; | ||
| 390 : | } | ||
| 391 : | print SAVINGTABLE join($Delimiter,@{$TableRef->{"file IO settings"}->{"orderedkeys"}})."\n"; | ||
| 392 : | chenry | 1.4 | for (my $i=0; $i < @{$TableRef->{"array"}}; $i++) { |
| 393 : | for (my $j=0; $j < @{$TableRef->{"file IO settings"}->{"orderedkeys"}}; $j++) { | ||
| 394 : | if ($j > 0) { | ||
| 395 : | chenry | 1.5 | print SAVINGTABLE $Delimiter; |
| 396 : | chenry | 1.4 | } |
| 397 : | if (defined($TableRef->{"array"}->[$i]->{$TableRef->{"file IO settings"}->{"orderedkeys"}->[$j]})) { | ||
| 398 : | print SAVINGTABLE join($ItemDelimiter,@{$TableRef->{"array"}->[$i]->{$TableRef->{"file IO settings"}->{"orderedkeys"}->[$j]}}); | ||
| 399 : | } | ||
| 400 : | } | ||
| 401 : | chenry | 1.5 | print SAVINGTABLE "\n"; |
| 402 : | chenry | 1.4 | } |
| 403 : | close (SAVINGTABLE); | ||
| 404 : | } | ||
| 405 : | |||
| 406 : | chenry | 1.5 | sub copy_table_row { |
| 407 : | my ($InRow) = @_; | ||
| 408 : | |||
| 409 : | my $NewRow; | ||
| 410 : | my @Headings = keys(%{$InRow}); | ||
| 411 : | foreach my $Heading (@Headings) { | ||
| 412 : | push(@{$NewRow->{$Heading}},@{$InRow->{$Heading}}); | ||
| 413 : | } | ||
| 414 : | |||
| 415 : | return $NewRow; | ||
| 416 : | } | ||
| 417 : | |||
| 418 : | chenry | 1.1 | #--- This function loads a file with the following on each line: $A$Delimiter$B and maps $A to $B in the first returned hash reference and $B to $A in the second returned hash reference ---# |
| 419 : | sub LoadSeparateTranslationFiles { | ||
| 420 : | my ($Filename,$Delimiter) = @_; | ||
| 421 : | my $HashReferenceForward = {}; | ||
| 422 : | my $HashReferenceReverse = {}; | ||
| 423 : | |||
| 424 : | if (open (INPUT, "<$Filename")) { | ||
| 425 : | while (my $Line = <INPUT>) { | ||
| 426 : | chomp($Line); | ||
| 427 : | my @Data = split(/$Delimiter/,$Line); | ||
| 428 : | if (@Data >= 2) { | ||
| 429 : | chenry | 1.5 | if (!defined($HashReferenceForward->{$Data[0]})) { |
| 430 : | $HashReferenceForward->{$Data[0]} = $Data[1]; | ||
| 431 : | } | ||
| 432 : | if (!defined($HashReferenceForward->{$Data[1]})) { | ||
| 433 : | $HashReferenceReverse->{$Data[1]} = $Data[0]; | ||
| 434 : | } | ||
| 435 : | chenry | 1.1 | } |
| 436 : | } | ||
| 437 : | close(INPUT); | ||
| 438 : | } | ||
| 439 : | |||
| 440 : | return ($HashReferenceForward,$HashReferenceReverse); | ||
| 441 : | } | ||
| 442 : | |||
| 443 : | #--- This function breaks down the input filename into a directory, filename, and extension ---# | ||
| 444 : | sub ParseFilename { | ||
| 445 : | my ($Filename) = @_; | ||
| 446 : | |||
| 447 : | my $Directory = ""; | ||
| 448 : | my $Extension = ""; | ||
| 449 : | chenry | 1.3 | if ($Filename =~ m/^(.+\/)([^\/]+)\.([^\.]+)/) { |
| 450 : | $Directory = $1; | ||
| 451 : | $Filename = $2; | ||
| 452 : | $Extension = $3; | ||
| 453 : | chenry | 1.1 | } |
| 454 : | |||
| 455 : | return ($Filename,$Directory,$Extension); | ||
| 456 : | } | ||
| 457 : | |||
| 458 : | #--- This function compares the files listed in two separate directories and returns the list of new files and updated files ---# | ||
| 459 : | sub CompareDirectories { | ||
| 460 : | my ($NewDirectory,$OldDirectory,$ComparisonType) = @_; | ||
| 461 : | |||
| 462 : | my $Command = "ls -la ".$NewDirectory." > ".$NewDirectory."FileList.txt"; | ||
| 463 : | system($Command); | ||
| 464 : | $Command = "ls -la ".$OldDirectory." > ".$OldDirectory."FileList.txt"; | ||
| 465 : | system($Command); | ||
| 466 : | |||
| 467 : | my $NewFileData = &LoadMultipleColumnFile($NewDirectory."FileList.txt","\\s"); | ||
| 468 : | my $OldFileData = &LoadMultipleColumnFile($OldDirectory."FileList.txt","\\s"); | ||
| 469 : | |||
| 470 : | my $UpdatedFiles = []; | ||
| 471 : | my $NewFiles = []; | ||
| 472 : | |||
| 473 : | my %FilenameHash; | ||
| 474 : | foreach my $File (@{$OldFileData}) { | ||
| 475 : | if ($ComparisonType eq "date") { | ||
| 476 : | $FilenameHash{$File->[$#{$File}]} = $File->[$#{$File}-2].":".$File->[$#{$File}-1]; | ||
| 477 : | } elsif ($ComparisonType eq "size") { | ||
| 478 : | $FilenameHash{$File->[$#{$File}]} = $File->[$#{$File}-3]; | ||
| 479 : | } | ||
| 480 : | } | ||
| 481 : | foreach my $File (@{$NewFileData}) { | ||
| 482 : | if (defined($FilenameHash{$File->[$#{$File}]})) { | ||
| 483 : | if ($ComparisonType eq "date" && $FilenameHash{$File->[$#{$File}]} ne $File->[$#{$File}-2].":".$File->[$#{$File}-1]) { | ||
| 484 : | push(@{$UpdatedFiles},$File->[$#{$File}]); | ||
| 485 : | } elsif ($ComparisonType eq "size" && $FilenameHash{$File->[$#{$File}]} ne $File->[$#{$File}-3]) { | ||
| 486 : | push(@{$UpdatedFiles},$File->[$#{$File}]); | ||
| 487 : | } | ||
| 488 : | } else { | ||
| 489 : | $FilenameHash{$File->[$#{$File}]} = $File->[$#{$File}-2].":".$File->[$#{$File}-1]; | ||
| 490 : | push(@{$NewFiles},$File->[$#{$File}]); | ||
| 491 : | } | ||
| 492 : | } | ||
| 493 : | |||
| 494 : | return ($NewFiles,$UpdatedFiles); | ||
| 495 : | } | ||
| 496 : | |||
| 497 : | sub RemoveHFromFormula { | ||
| 498 : | my ($Formula) = @_; | ||
| 499 : | my @Data = split(/H/,$Formula); | ||
| 500 : | |||
| 501 : | if (@Data == 1) { | ||
| 502 : | return $Formula; | ||
| 503 : | } | ||
| 504 : | |||
| 505 : | while ($Data[1] =~ m/^\d/) { | ||
| 506 : | $Data[1] = substr($Data[1],1); | ||
| 507 : | } | ||
| 508 : | |||
| 509 : | return $Data[0].$Data[1]; | ||
| 510 : | } | ||
| 511 : | |||
| 512 : | sub CompareArrays { | ||
| 513 : | my ($ArrayOne,$ArrayTwo) = @_; | ||
| 514 : | |||
| 515 : | my $ArrayOneExtra = (); | ||
| 516 : | my $ArrayTwoExtra = (); | ||
| 517 : | my $ArrayOverlap = (); | ||
| 518 : | my %ArrayTwoHash; | ||
| 519 : | |||
| 520 : | for (my $i=0; $i < @{$ArrayOne}; $i++) { | ||
| 521 : | my $Match = 0; | ||
| 522 : | for (my $j=0; $j < @{$ArrayTwo}; $j++) { | ||
| 523 : | if ($ArrayOne->[$i] eq $ArrayTwo->[$j]) { | ||
| 524 : | $ArrayTwoHash{$ArrayOne->[$i]} = 1; | ||
| 525 : | $Match = 1; | ||
| 526 : | push(@{$ArrayOverlap},$ArrayOne->[$i]); | ||
| 527 : | $j = @{$ArrayTwo}; | ||
| 528 : | } | ||
| 529 : | } | ||
| 530 : | if ($Match == 0) { | ||
| 531 : | push(@{$ArrayOneExtra},$ArrayOne->[$i]); | ||
| 532 : | } | ||
| 533 : | } | ||
| 534 : | for (my $j=0; $j < @{$ArrayTwo}; $j++) { | ||
| 535 : | if (!defined($ArrayTwoHash{$ArrayTwo->[$j]})) { | ||
| 536 : | push(@{$ArrayTwoExtra},$ArrayTwo->[$j]); | ||
| 537 : | } | ||
| 538 : | } | ||
| 539 : | |||
| 540 : | return ($ArrayOneExtra,$ArrayTwoExtra,$ArrayOverlap); | ||
| 541 : | } | ||
| 542 : | |||
| 543 : | sub ReplaceLineSubstringsFromHash { | ||
| 544 : | my ($Translation, $Line) = @_; | ||
| 545 : | |||
| 546 : | my @Data = keys(%{$Translation}); | ||
| 547 : | for (my $i=0; $i < @Data; $i++) { | ||
| 548 : | my $FindString = $Data[$i]; | ||
| 549 : | my $ReplaceString = $Translation->{$Data[$i]}; | ||
| 550 : | $Line =~ s/([\,\s\;\+\[])$FindString([\,\s\;\+\[])/$1$ReplaceString$2/g; | ||
| 551 : | $Line =~ s/$FindString$/$ReplaceString/g; | ||
| 552 : | $Line =~ s/^$FindString/$ReplaceString/g; | ||
| 553 : | } | ||
| 554 : | |||
| 555 : | return $Line; | ||
| 556 : | } | ||
| 557 : | |||
| 558 : | sub FindArrayElement { | ||
| 559 : | my ($ArrayRef,$Value) = @_; | ||
| 560 : | |||
| 561 : | if (!defined($ArrayRef)) { | ||
| 562 : | return -1; | ||
| 563 : | } | ||
| 564 : | |||
| 565 : | for (my $i=0;$i < @{$ArrayRef};$i++) { | ||
| 566 : | if ($ArrayRef->[$i] eq $Value) { | ||
| 567 : | return $i; | ||
| 568 : | } | ||
| 569 : | } | ||
| 570 : | |||
| 571 : | return -1; | ||
| 572 : | } | ||
| 573 : | |||
| 574 : | sub RemoveArrayElement { | ||
| 575 : | my ($ArrayRef,$Value) = @_; | ||
| 576 : | |||
| 577 : | chenry | 1.5 | for (my $i=0;$i < @{$ArrayRef};$i++) { |
| 578 : | if ($ArrayRef->[$i] eq $Value) { | ||
| 579 : | splice(@{$ArrayRef},$i,1); | ||
| 580 : | chenry | 1.1 | $i--; |
| 581 : | chenry | 1.5 | } |
| 582 : | } | ||
| 583 : | chenry | 1.1 | |
| 584 : | chenry | 1.5 | return $ArrayRef; |
| 585 : | chenry | 1.1 | } |
| 586 : | |||
| 587 : | sub FormatNumber { | ||
| 588 : | my ($OriginalNumber,$Digits,$ZeroEquivalence) = @_; | ||
| 589 : | chenry | 1.5 | |
| 590 : | chenry | 1.1 | if (abs($OriginalNumber) < $ZeroEquivalence) { |
| 591 : | $OriginalNumber = "0."; | ||
| 592 : | for (my $i=0; $i < $Digits;$i++) { | ||
| 593 : | $OriginalNumber .= "0" | ||
| 594 : | } | ||
| 595 : | return $OriginalNumber | ||
| 596 : | } | ||
| 597 : | chenry | 1.5 | |
| 598 : | chenry | 1.1 | if ($OriginalNumber > 1 || $OriginalNumber < -1) { |
| 599 : | $OriginalNumber = $OriginalNumber*(10**$Digits); | ||
| 600 : | $OriginalNumber = int($OriginalNumber + .5 * ($OriginalNumber <=> 0)); | ||
| 601 : | $OriginalNumber = $OriginalNumber/(10**$Digits); | ||
| 602 : | return $OriginalNumber; | ||
| 603 : | } | ||
| 604 : | chenry | 1.5 | |
| 605 : | chenry | 1.1 | my $Zeros = 0; |
| 606 : | while (abs($OriginalNumber) < 10**$Zeros) { | ||
| 607 : | chenry | 1.5 | $Zeros--; |
| 608 : | chenry | 1.1 | } |
| 609 : | chenry | 1.5 | |
| 610 : | chenry | 1.1 | $OriginalNumber = $OriginalNumber*10**-$Zeros; |
| 611 : | $OriginalNumber = $OriginalNumber*(10**$Digits); | ||
| 612 : | $OriginalNumber = int($OriginalNumber + .5 * ($OriginalNumber <=> 0)); | ||
| 613 : | $OriginalNumber = $OriginalNumber/(10**$Digits); | ||
| 614 : | if ($Zeros > -4) { | ||
| 615 : | chenry | 1.5 | $OriginalNumber = $OriginalNumber/(10**-$Zeros); |
| 616 : | chenry | 1.1 | } else { |
| 617 : | $OriginalNumber .= "e".$Zeros; | ||
| 618 : | } | ||
| 619 : | chenry | 1.5 | |
| 620 : | chenry | 1.1 | return $OriginalNumber; |
| 621 : | } | ||
| 622 : | |||
| 623 : | sub ConvertToSearchNames { | ||
| 624 : | my ($InName) = @_; | ||
| 625 : | chenry | 1.5 | |
| 626 : | chenry | 1.1 | if ($InName =~ m/-$/) { |
| 627 : | return $InName; | ||
| 628 : | } | ||
| 629 : | chenry | 1.5 | |
| 630 : | chenry | 1.1 | #I convert all names to lowercase to help with matching |
| 631 : | $InName = lc($InName); | ||
| 632 : | #I remove all spaces from all names to help with matching | ||
| 633 : | $InName =~ s/\s//g; | ||
| 634 : | chenry | 1.5 | $InName =~ s/,//g; |
| 635 : | chenry | 1.1 | $InName =~ s/-//g; |
| 636 : | $InName =~ s/_//g; | ||
| 637 : | $InName =~ s/\(//g; | ||
| 638 : | $InName =~ s/\)//g; | ||
| 639 : | $InName =~ s/\[//g; | ||
| 640 : | $InName =~ s/\]//g; | ||
| 641 : | $InName =~ s/\://g; | ||
| 642 : | chenry | 1.5 | $InName =~ s/’//g; |
| 643 : | $InName =~ s/'//g; | ||
| 644 : | chenry | 1.1 | $InName =~ s/\;//g; |
| 645 : | chenry | 1.5 | |
| 646 : | chenry | 1.1 | my $NameOne = $InName; |
| 647 : | $InName =~ s/icacid/ate/g; | ||
| 648 : | if ($NameOne eq $InName) { | ||
| 649 : | return ($NameOne); | ||
| 650 : | } else { | ||
| 651 : | return ($NameOne,$InName); | ||
| 652 : | } | ||
| 653 : | } | ||
| 654 : | chenry | 1.5 | |
| 655 : | sub ConvertToNeutralFormula { | ||
| 656 : | my ($NeutralFormula,$Charge) = @_; | ||
| 657 : | |||
| 658 : | if (!defined($NeutralFormula)) { | ||
| 659 : | $NeutralFormula = ""; | ||
| 660 : | } elsif ($NeutralFormula eq "H") { | ||
| 661 : | #Do nothing | ||
| 662 : | } elsif (defined($Charge) && $Charge ne "0") { | ||
| 663 : | my $CurrentH = 0; | ||
| 664 : | if ($NeutralFormula =~ m/H(\d+)/) { | ||
| 665 : | $CurrentH = $1; | ||
| 666 : | } elsif ($NeutralFormula =~ m/H[A-Z]/ || $NeutralFormula =~ m/H$/) { | ||
| 667 : | $CurrentH = 1; | ||
| 668 : | } | ||
| 669 : | my $NewH = $CurrentH; | ||
| 670 : | if ($Charge >= $CurrentH) { | ||
| 671 : | $NewH = 0; | ||
| 672 : | } else { | ||
| 673 : | $NewH = $CurrentH - $Charge; | ||
| 674 : | } | ||
| 675 : | my $Replace = "H"; | ||
| 676 : | if ($NewH > 1) { | ||
| 677 : | $Replace = "H".$NewH; | ||
| 678 : | } elsif ($NewH == 0) { | ||
| 679 : | $Replace = ""; | ||
| 680 : | } | ||
| 681 : | if ($CurrentH == 0 && $NewH > 0) { | ||
| 682 : | $NeutralFormula .= "H"; | ||
| 683 : | if ($NewH > 1) { | ||
| 684 : | $NeutralFormula .= $NewH; | ||
| 685 : | } | ||
| 686 : | } elsif ($CurrentH == 1) { | ||
| 687 : | $NeutralFormula =~ s/H$/$Replace/; | ||
| 688 : | $NeutralFormula =~ s/H([A-Z])/$Replace$1/; | ||
| 689 : | } else { | ||
| 690 : | my $Match = "H".$CurrentH; | ||
| 691 : | $NeutralFormula =~ s/$Match/$Replace/; | ||
| 692 : | } | ||
| 693 : | } | ||
| 694 : | |||
| 695 : | return $NeutralFormula; | ||
| 696 : | } | ||
| 697 : | |||
| 698 : | chenry | 1.1 | sub CountFileLines { |
| 699 : | my ($filename) = @_; | ||
| 700 : | my $lines = 0; | ||
| 701 : | open(FILE, $filename) or die "Can't open `$filename': $!"; | ||
| 702 : | while(<FILE>) { | ||
| 703 : | $lines++; | ||
| 704 : | chenry | 1.5 | } |
| 705 : | chenry | 1.1 | close FILE; |
| 706 : | return $lines; | ||
| 707 : | } | ||
| 708 : | |||
| 709 : | sub ManipulateFormula { | ||
| 710 : | my ($OriginalFormula) = @_; | ||
| 711 : | |||
| 712 : | my %Atoms; | ||
| 713 : | my $CurrentAtomType = ""; | ||
| 714 : | my $CurrentAtomNumber = ""; | ||
| 715 : | for (my $i=0; $i < length($OriginalFormula); $i++) { | ||
| 716 : | my $CurrentLetter = substr($OriginalFormula,$i,1); | ||
| 717 : | if ($CurrentLetter =~ m/[A-Z]/) { | ||
| 718 : | if ($CurrentAtomType ne "") { | ||
| 719 : | if ($CurrentAtomNumber eq "1") { | ||
| 720 : | chenry | 1.5 | $CurrentAtomNumber = ""; |
| 721 : | chenry | 1.1 | } |
| 722 : | $Atoms{$CurrentAtomType} = $CurrentAtomNumber; | ||
| 723 : | } | ||
| 724 : | $CurrentAtomType = $CurrentLetter; | ||
| 725 : | $CurrentAtomNumber = ""; | ||
| 726 : | } elsif ($CurrentLetter =~ m/[a-z]/) { | ||
| 727 : | $CurrentAtomType .= $CurrentLetter; | ||
| 728 : | } elsif ($CurrentLetter =~ m/[\d]/) { | ||
| 729 : | $CurrentAtomNumber .= $CurrentLetter; | ||
| 730 : | } else { | ||
| 731 : | if ($CurrentAtomType ne "") { | ||
| 732 : | $Atoms{$CurrentAtomType} = $CurrentAtomNumber; | ||
| 733 : | } | ||
| 734 : | $CurrentAtomType = ""; | ||
| 735 : | } | ||
| 736 : | } | ||
| 737 : | if ($CurrentAtomType ne "") { | ||
| 738 : | if ($CurrentAtomNumber eq "1") { | ||
| 739 : | chenry | 1.5 | $CurrentAtomNumber = ""; |
| 740 : | chenry | 1.1 | } |
| 741 : | $Atoms{$CurrentAtomType} = $CurrentAtomNumber; | ||
| 742 : | } | ||
| 743 : | |||
| 744 : | my @SortedAtoms = sort(keys(%Atoms)); | ||
| 745 : | my $StandardFormula; | ||
| 746 : | my $CompareFormula; | ||
| 747 : | for (my $i=0; $i < @SortedAtoms; $i++) { | ||
| 748 : | $StandardFormula .= $SortedAtoms[$i]; | ||
| 749 : | $StandardFormula .= $Atoms{$SortedAtoms[$i]}; | ||
| 750 : | if ($SortedAtoms[$i] ne "H") { | ||
| 751 : | $CompareFormula .= $SortedAtoms[$i]; | ||
| 752 : | $CompareFormula .= $Atoms{$SortedAtoms[$i]}; | ||
| 753 : | } | ||
| 754 : | } | ||
| 755 : | |||
| 756 : | return ($StandardFormula,$CompareFormula); | ||
| 757 : | } | ||
| 758 : | |||
| 759 : | |||
| 760 : | |||
| 761 : | sub ParseGPRFile { | ||
| 762 : | my ($Filename,$ReactionData) = @_; | ||
| 763 : | chenry | 1.5 | |
| 764 : | chenry | 1.1 | my $GPRData = &LoadMultipleColumnFile($Filename,"\t"); |
| 765 : | chenry | 1.5 | |
| 766 : | chenry | 1.1 | for (my $i=0; $i < @{$GPRData}; $i++) { |
| 767 : | if (@{$GPRData->[$i]} >= 3) { | ||
| 768 : | if (!defined($ReactionData->{$GPRData->[$i]->[2]})) { | ||
| 769 : | $ReactionData->{$GPRData->[$i]->[2]}->{"ID"} = $GPRData->[$i]->[2]; | ||
| 770 : | } | ||
| 771 : | if (length($GPRData->[$i]->[1]) > 0) { | ||
| 772 : | $ReactionData->{$GPRData->[$i]->[2]}->{"EC"} = $GPRData->[$i]->[1]; | ||
| 773 : | } | ||
| 774 : | for (my $j=4; $j < @{$GPRData->[$i]}; $j++) { | ||
| 775 : | if (length($GPRData->[$i]->[$j]) > 0) { | ||
| 776 : | if ($GPRData->[$i]->[$j] =~ m/_$/) { | ||
| 777 : | $GPRData->[$i]->[$j] = chop($GPRData->[$i]->[$j]); | ||
| 778 : | } | ||
| 779 : | push(@{$ReactionData->{$GPRData->[$i]->[2]}->{"GENE ID"}},$GPRData->[$i]->[$j]); | ||
| 780 : | } | ||
| 781 : | } | ||
| 782 : | } | ||
| 783 : | } | ||
| 784 : | chenry | 1.5 | |
| 785 : | chenry | 1.1 | return ($ReactionData); |
| 786 : | } | ||
| 787 : | |||
| 788 : | sub ParseSBMLFile { | ||
| 789 : | my ($Filename,$ReactionData,$CompoundData) = @_; | ||
| 790 : | chenry | 1.5 | |
| 791 : | chenry | 1.1 | my $SBMLData = &LoadSingleColumnFile($Filename,""); |
| 792 : | chenry | 1.5 | |
| 793 : | chenry | 1.1 | my $HandlingSpecies = 0; |
| 794 : | my $HandlingReactions = 0; | ||
| 795 : | my $HandlingReactants = 0; | ||
| 796 : | my $HandlingProducts = 0; | ||
| 797 : | my $ReactionID = ""; | ||
| 798 : | my $ReactionReactants = ""; | ||
| 799 : | my $ReactionSign = ""; | ||
| 800 : | my $ReactionProducts = ""; | ||
| 801 : | for (my $i=0; $i < @{$SBMLData}; $i++) { | ||
| 802 : | if ($SBMLData->[$i] =~ m/^<listOfSpecies>/) { | ||
| 803 : | $HandlingSpecies = 1; | ||
| 804 : | } elsif ($SBMLData->[$i] =~ m/^<\/listOfSpecies>/) { | ||
| 805 : | $HandlingSpecies = 0; | ||
| 806 : | } elsif ($SBMLData->[$i] =~ m/^<listOfReactions>/) { | ||
| 807 : | $HandlingReactions = 1; | ||
| 808 : | } elsif ($SBMLData->[$i] =~ m/^<\/listOfReactions>/) { | ||
| 809 : | $HandlingReactions = 0; | ||
| 810 : | } elsif ($HandlingSpecies == 1 && $SBMLData->[$i] =~ m/^<species/) { | ||
| 811 : | #Parsing out the compound ID | ||
| 812 : | if ($SBMLData->[$i] =~ m/id="([^"]+)"/) { | ||
| 813 : | my $ID = $1; | ||
| 814 : | if ($ID =~ m/^_/) { | ||
| 815 : | $ID = substr($ID,1); | ||
| 816 : | } | ||
| 817 : | if ($ID =~ m/_[a-z]$/) { | ||
| 818 : | chop($ID); | ||
| 819 : | chop($ID); | ||
| 820 : | } | ||
| 821 : | if (length($ID) > 0) { | ||
| 822 : | #Parsing out the compound name | ||
| 823 : | if (!defined($CompoundData->{$ID})) { | ||
| 824 : | $CompoundData->{$ID}->{"ID"} = $ID; | ||
| 825 : | } | ||
| 826 : | if ($SBMLData->[$i] =~ m/name="([^"]+)"/) { | ||
| 827 : | my $Name = $1; | ||
| 828 : | if ($Name =~ m/^_/) { | ||
| 829 : | $Name = substr($Name,1); | ||
| 830 : | } | ||
| 831 : | $Name =~ s/_/ /g; | ||
| 832 : | if (length($Name) > 0 && (!defined($CompoundData->{$ID}->{"NAME"}) || &FindArrayElement($CompoundData->{$ID}->{"NAME"},$Name) == -1)) { | ||
| 833 : | push(@{$CompoundData->{$ID}->{"NAME"}},$Name); | ||
| 834 : | } | ||
| 835 : | } | ||
| 836 : | } | ||
| 837 : | } | ||
| 838 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<reaction/) { | ||
| 839 : | $ReactionSign = " <=> "; | ||
| 840 : | if ($SBMLData->[$i] =~ m/reversible="false"/) { | ||
| 841 : | $ReactionSign = " => "; | ||
| 842 : | } | ||
| 843 : | if ($SBMLData->[$i] =~ m/id="([^"]+)"/) { | ||
| 844 : | $ReactionID = $1; | ||
| 845 : | if (length($ReactionID) > 0) { | ||
| 846 : | if (!defined($ReactionData->{$ReactionID})) { | ||
| 847 : | $ReactionData->{$ReactionID}->{"ID"} = $ReactionID; | ||
| 848 : | } | ||
| 849 : | if ($SBMLData->[$i] =~ m/name="([^"]+)"/) { | ||
| 850 : | my $Name = $1; | ||
| 851 : | if ($Name =~ m/^_/) { | ||
| 852 : | $Name = substr($Name,1); | ||
| 853 : | } | ||
| 854 : | $Name =~ s/_/ /g; | ||
| 855 : | if (length($Name) > 0 && (!defined($ReactionData->{$ReactionID}->{"NAME"}) || &FindArrayElement($ReactionData->{$ReactionID}->{"NAME"},$Name) == -1)) { | ||
| 856 : | push(@{$ReactionData->{$ReactionID}->{"NAME"}},$Name); | ||
| 857 : | } | ||
| 858 : | } | ||
| 859 : | chenry | 1.5 | |
| 860 : | chenry | 1.1 | } |
| 861 : | } | ||
| 862 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<\/reaction>/) { | ||
| 863 : | $ReactionID = ""; | ||
| 864 : | $ReactionReactants = ""; | ||
| 865 : | $ReactionSign = ""; | ||
| 866 : | $ReactionProducts = ""; | ||
| 867 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<html:p>EC Number:\s([^<]+)/) { | ||
| 868 : | my $ECNumber = $1; | ||
| 869 : | if (length($ECNumber) > 3 && (!defined($ReactionData->{$ReactionID}->{"EC"}) || &FindArrayElement($ReactionData->{$ReactionID}->{"EC"},$ECNumber) == -1)) { | ||
| 870 : | push(@{$ReactionData->{$ReactionID}->{"EC"}},$ECNumber); | ||
| 871 : | } | ||
| 872 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<html:p>Confidence Level:\s([^<]+)/) { | ||
| 873 : | my $Confidence = $1; | ||
| 874 : | if (length($Confidence) > 0) { | ||
| 875 : | $ReactionData->{$ReactionID}->{"CONFIDENCE"} = $Confidence; | ||
| 876 : | } | ||
| 877 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<html:p>LOCUS:/) { | ||
| 878 : | $_ = $SBMLData->[$i]; | ||
| 879 : | my @GeneArray = /<html:p>LOCUS:([^\#]+)/g; | ||
| 880 : | for (my $j=0; $j < @GeneArray; $j++) { | ||
| 881 : | if (length($GeneArray[$j]) > 0 && (!defined($ReactionData->{$ReactionID}->{"GENES"}) || &FindArrayElement($ReactionData->{$ReactionID}->{"GENES"},$GeneArray[$j]) == -1)) { | ||
| 882 : | push(@{$ReactionData->{$ReactionID}->{"GENES"}},$GeneArray[$j]); | ||
| 883 : | } | ||
| 884 : | } | ||
| 885 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<listOfReactants>/) { | ||
| 886 : | $HandlingReactants = 1; | ||
| 887 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<\/listOfReactants>/) { | ||
| 888 : | $HandlingReactants = 0; | ||
| 889 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<listOfProducts>/) { | ||
| 890 : | $HandlingProducts = 1; | ||
| 891 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<\/listOfProducts>/) { | ||
| 892 : | $HandlingProducts = 0; | ||
| 893 : | if (length($ReactionID) > 0 && defined($ReactionData->{$ReactionID})) { | ||
| 894 : | my $Equation = $ReactionReactants.$ReactionSign.$ReactionProducts; | ||
| 895 : | $ReactionData->{$ReactionID}->{"EQUATION"} = $Equation; | ||
| 896 : | } | ||
| 897 : | } elsif ($HandlingReactions == 1 && $SBMLData->[$i] =~ m/^<speciesReference/) { | ||
| 898 : | if ($SBMLData->[$i] =~ m/species="([^"]+)"/) { | ||
| 899 : | my $SpeciesID = $1; | ||
| 900 : | if ($SpeciesID =~ m/^_/) { | ||
| 901 : | $SpeciesID = substr($SpeciesID,1); | ||
| 902 : | } | ||
| 903 : | my $Compartment = ""; | ||
| 904 : | if ($SpeciesID =~ m/_([a-z])$/) { | ||
| 905 : | $Compartment = $1; | ||
| 906 : | chop($SpeciesID); | ||
| 907 : | chop($SpeciesID); | ||
| 908 : | } | ||
| 909 : | my $Stoichiometry = ""; | ||
| 910 : | if ($SBMLData->[$i] =~ m/stoichiometry="([^"]+)"/) { | ||
| 911 : | $Stoichiometry = $1; | ||
| 912 : | } | ||
| 913 : | if (length($Stoichiometry) > 0 && length($SpeciesID) > 0) { | ||
| 914 : | my $SpeciesString = ""; | ||
| 915 : | if ($Stoichiometry ne "1") { | ||
| 916 : | $SpeciesString .= "(".$Stoichiometry.") "; | ||
| 917 : | } | ||
| 918 : | $SpeciesString .= "$SpeciesID"; | ||
| 919 : | if (length($Compartment) > 0 && $Compartment ne "c") { | ||
| 920 : | $SpeciesString .= "[".$Compartment."]"; | ||
| 921 : | } | ||
| 922 : | if ($HandlingReactants == 1) { | ||
| 923 : | if (length($ReactionReactants) > 0) { | ||
| 924 : | $ReactionReactants .= " + "; | ||
| 925 : | } | ||
| 926 : | $ReactionReactants .= $SpeciesString; | ||
| 927 : | } elsif ($HandlingProducts == 1) { | ||
| 928 : | if (length($ReactionProducts) > 0) { | ||
| 929 : | $ReactionProducts .= " + "; | ||
| 930 : | } | ||
| 931 : | $ReactionProducts .= $SpeciesString; | ||
| 932 : | } | ||
| 933 : | } | ||
| 934 : | } | ||
| 935 : | } | ||
| 936 : | } | ||
| 937 : | chenry | 1.5 | |
| 938 : | chenry | 1.1 | return ($ReactionData,$CompoundData); |
| 939 : | } | ||
| 940 : | |||
| 941 : | sub SearchTranslationDataForMatchingID { | ||
| 942 : | my ($Filename,$SearchText) = @_; | ||
| 943 : | chenry | 1.5 | |
| 944 : | chenry | 1.1 | #Declaring the reference to the array where the results will ultimately be stored |
| 945 : | my $MatchingIDs = (); | ||
| 946 : | chenry | 1.5 | |
| 947 : | chenry | 1.1 | #If the search text is blank or the input file does not exist, I return an empty array |
| 948 : | if (length($SearchText) == 0 || !(-e $Filename)) { | ||
| 949 : | return $MatchingIDs; | ||
| 950 : | } | ||
| 951 : | chenry | 1.5 | |
| 952 : | chenry | 1.1 | #Loading the translation file |
| 953 : | my %IDHash; | ||
| 954 : | my $TranslationData = &LoadMultipleColumnFile($Filename,"\t"); | ||
| 955 : | my %UniqueKeysHash; | ||
| 956 : | for (my $i=0; $i < @{$TranslationData}; $i++) { | ||
| 957 : | if (@{$TranslationData->[$i]} >= 2) { | ||
| 958 : | push(@{$UniqueKeysHash{$TranslationData->[$i]->[1]}},$TranslationData->[$i]->[0]); | ||
| 959 : | } | ||
| 960 : | } | ||
| 961 : | #Searching through the keys of the translation file for my search text and storing matching ids in a hash | ||
| 962 : | my @AllKeys = keys(%UniqueKeysHash); | ||
| 963 : | for (my $i=0; $i < @AllKeys; $i++) { | ||
| 964 : | if ($AllKeys[$i] =~ m/$SearchText/) { | ||
| 965 : | for (my $j=0; $j < @{$UniqueKeysHash{$AllKeys[$i]}}; $j++) { | ||
| 966 : | $IDHash{$UniqueKeysHash{$AllKeys[$i]}->[$j]} = 1; | ||
| 967 : | } | ||
| 968 : | } | ||
| 969 : | } | ||
| 970 : | chenry | 1.5 | |
| 971 : | chenry | 1.1 | #Putting the matching hash keys into an array and sorting it |
| 972 : | push(@{$MatchingIDs},keys(%IDHash)); | ||
| 973 : | if (defined($MatchingIDs)) { | ||
| 974 : | @{$MatchingIDs} = sort(@{$MatchingIDs}) | ||
| 975 : | } | ||
| 976 : | chenry | 1.5 | |
| 977 : | chenry | 1.1 | return $MatchingIDs; |
| 978 : | } | ||
| 979 : | |||
| 980 : | sub BackupFile { | ||
| 981 : | my ($CurrentFilename,$BackupFilename) = @_; | ||
| 982 : | chenry | 1.5 | |
| 983 : | chenry | 1.1 | if (-e $CurrentFilename) { |
| 984 : | if (-e $BackupFilename) { | ||
| 985 : | unlink($BackupFilename); | ||
| 986 : | } | ||
| 987 : | rename($CurrentFilename,$BackupFilename); | ||
| 988 : | } | ||
| 989 : | } | ||
| 990 : | |||
| 991 : | sub Date { | ||
| 992 : | chenry | 1.4 | my ($Time) = @_; |
| 993 : | chenry | 1.5 | if (!defined($Time)) { |
| 994 : | $Time = time(); | ||
| 995 : | } | ||
| 996 : | chenry | 1.4 | my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($Time); |
| 997 : | chenry | 1.5 | |
| 998 : | chenry | 1.4 | return ($mon+1)."/".($mday)."/".($year+1900); |
| 999 : | chenry | 1.1 | } |
| 1000 : | |||
| 1001 : | sub MergeArraysUnique { | ||
| 1002 : | my @ArrayRefs = @_; | ||
| 1003 : | chenry | 1.5 | |
| 1004 : | chenry | 1.1 | my $ResultArray = (); |
| 1005 : | my %EntryHash; | ||
| 1006 : | for (my $i=0; $i < @ArrayRefs; $i++) { | ||
| 1007 : | if (defined($ArrayRefs[$i])) { | ||
| 1008 : | for (my $j=0; $j < @{$ArrayRefs[$i]}; $j++) { | ||
| 1009 : | if (!defined($EntryHash{$ArrayRefs[$i]->[$j]})) { | ||
| 1010 : | push(@{$ResultArray},$ArrayRefs[$i]->[$j]); | ||
| 1011 : | $EntryHash{$ArrayRefs[$i]->[$j]} = 1; | ||
| 1012 : | } | ||
| 1013 : | } | ||
| 1014 : | } | ||
| 1015 : | } | ||
| 1016 : | chenry | 1.5 | |
| 1017 : | chenry | 1.1 | return $ResultArray |
| 1018 : | } | ||
| 1019 : | |||
| 1020 : | #Opens up every file in a directory, searches each line for the search expression, and replaces the objects matching the search expression according to the translation hash | ||
| 1021 : | sub TranslateFileData { | ||
| 1022 : | my ($TranslationHash,$FilenameExpression,$SearchExpression,$Recursive,$MakeUnique,$SortLines) = @_; | ||
| 1023 : | chenry | 1.5 | |
| 1024 : | chenry | 1.1 | #Checking the search expression if one was provided |
| 1025 : | if (defined($SearchExpression) && length($SearchExpression) > 0) { | ||
| 1026 : | if (index($SearchExpression,"(") == -1 || index($SearchExpression,"(") == -1) { | ||
| 1027 : | $SearchExpression = "(".$SearchExpression.")"; | ||
| 1028 : | } | ||
| 1029 : | chenry | 1.5 | } |
| 1030 : | chenry | 1.1 | |
| 1031 : | #Finding all matching filenames | ||
| 1032 : | my @MatchingFiles; | ||
| 1033 : | if ($Recursive == 1 && $FilenameExpression =~ m/\/$/) { | ||
| 1034 : | @MatchingFiles = &RecursiveGlob($FilenameExpression); | ||
| 1035 : | } else { | ||
| 1036 : | @MatchingFiles = glob($FilenameExpression); | ||
| 1037 : | } | ||
| 1038 : | chenry | 1.5 | |
| 1039 : | chenry | 1.1 | #Exiting if no matching filenames were found |
| 1040 : | if (@MatchingFiles == 0) { | ||
| 1041 : | print "No matching files!\n"; | ||
| 1042 : | return; | ||
| 1043 : | } | ||
| 1044 : | chenry | 1.5 | |
| 1045 : | chenry | 1.1 | #Loading the translation file |
| 1046 : | if (!(-e $TranslationHash)) { | ||
| 1047 : | print "Could not find translation file: ".$TranslationHash."!\n"; | ||
| 1048 : | return; | ||
| 1049 : | } | ||
| 1050 : | my ($Ignore,$ReverseTranslation) = &LoadSeparateTranslationFiles($TranslationHash,"\t"); | ||
| 1051 : | |||
| 1052 : | #Scanning through all matching filenames | ||
| 1053 : | my @TranslationKeys = keys(%{$ReverseTranslation}); | ||
| 1054 : | chenry | 1.5 | |
| 1055 : | chenry | 1.1 | for (my $i=0; $i < @MatchingFiles; $i++) { |
| 1056 : | #Loading the file data into an array | ||
| 1057 : | my $FileData = &LoadSingleColumnFile($MatchingFiles[$i],""); | ||
| 1058 : | #Scanning through each fileline | ||
| 1059 : | my $MatchCount = 0; | ||
| 1060 : | for (my $j=0; $j < @{$FileData}; $j++) { | ||
| 1061 : | if (defined($SearchExpression) && length($SearchExpression) > 0) { | ||
| 1062 : | #This should be faster | ||
| 1063 : | $_ = $FileData->[$j]; | ||
| 1064 : | my @MatchingGroups = /$SearchExpression/g; | ||
| 1065 : | for (my $k=0; $k < @MatchingGroups;$k++) { | ||
| 1066 : | if (defined($ReverseTranslation->{$MatchingGroups[$k]})) { | ||
| 1067 : | $MatchCount++; | ||
| 1068 : | my $VarOne = $MatchingGroups[$k]; | ||
| 1069 : | my $VarTwo = $ReverseTranslation->{$MatchingGroups[$k]}; | ||
| 1070 : | $FileData->[$j] =~ s/$VarOne/$VarTwo/; | ||
| 1071 : | chenry | 1.5 | } |
| 1072 : | chenry | 1.1 | } |
| 1073 : | } else { | ||
| 1074 : | #This will be slower | ||
| 1075 : | for (my $k=0; $k < @TranslationKeys;$k++) { | ||
| 1076 : | my $VarOne = $TranslationKeys[$k]; | ||
| 1077 : | my $VarTwo = $ReverseTranslation->{$TranslationKeys[$k]}; | ||
| 1078 : | $FileData->[$j] =~ s/$VarOne/$VarTwo/g; | ||
| 1079 : | } | ||
| 1080 : | } | ||
| 1081 : | chenry | 1.5 | |
| 1082 : | chenry | 1.1 | } |
| 1083 : | #Saving the modified file data back to the file | ||
| 1084 : | print $MatchingFiles[$i]."\n"; | ||
| 1085 : | print $MatchCount."\n"; | ||
| 1086 : | #Making the array unique if requested | ||
| 1087 : | if (defined($MakeUnique) && $MakeUnique == 1) { | ||
| 1088 : | $FileData = &MergeArraysUnique($FileData); | ||
| 1089 : | } | ||
| 1090 : | #Sort file lines | ||
| 1091 : | if (defined($SortLines) && $SortLines == 1) { | ||
| 1092 : | @{$FileData} = sort(@{$FileData}); | ||
| 1093 : | } | ||
| 1094 : | &PrintArrayToFile($MatchingFiles[$i],$FileData); | ||
| 1095 : | chenry | 1.5 | } |
| 1096 : | chenry | 1.1 | } |
| 1097 : | |||
| 1098 : | sub RecursiveGlob { | ||
| 1099 : | my($path) = @_; | ||
| 1100 : | chenry | 1.5 | |
| 1101 : | my @FileList; | ||
| 1102 : | |||
| 1103 : | chenry | 1.1 | ## append a trailing / if it's not there |
| 1104 : | $path .= '/' if($path !~ /\/$/); | ||
| 1105 : | chenry | 1.5 | |
| 1106 : | chenry | 1.1 | ## loop through the files contained in the directory |
| 1107 : | for my $eachFile (glob($path.'*')) { | ||
| 1108 : | ## if the file is a directory | ||
| 1109 : | if( -d $eachFile) { | ||
| 1110 : | ## pass the directory to the routine ( recursion ) | ||
| 1111 : | push(@FileList,RecursiveGlob($eachFile)); | ||
| 1112 : | } else { | ||
| 1113 : | push(@FileList,$eachFile); | ||
| 1114 : | } | ||
| 1115 : | } | ||
| 1116 : | chenry | 1.5 | |
| 1117 : | chenry | 1.1 | return @FileList; |
| 1118 : | } | ||
| 1119 : | |||
| 1120 : | sub PrintHashToFile { | ||
| 1121 : | my($HashRef,$Filename) = @_; | ||
| 1122 : | chenry | 1.5 | |
| 1123 : | chenry | 1.1 | if ($Filename == "") { |
| 1124 : | open (HASHOUTPUT, ">&STDOUT"); | ||
| 1125 : | } else { | ||
| 1126 : | open (HASHOUTPUT, ">$Filename"); | ||
| 1127 : | } | ||
| 1128 : | my @Headings = keys(%{$HashRef}); | ||
| 1129 : | my @FirstHeadings; | ||
| 1130 : | my @SecondHeadings; | ||
| 1131 : | for (my $i=0; $i < @Headings; $i++) { | ||
| 1132 : | if (ref($HashRef->{$Headings[$i]}) eq "HASH") { | ||
| 1133 : | my @SubHeadings = keys(%{$HashRef->{$Headings[$i]}}); | ||
| 1134 : | for (my $j=0; $j < @SubHeadings;$j++) { | ||
| 1135 : | push(@FirstHeadings,$Headings[$i]); | ||
| 1136 : | push(@SecondHeadings,$SubHeadings[$j]); | ||
| 1137 : | } | ||
| 1138 : | } else { | ||
| 1139 : | push(@FirstHeadings,$Headings[$i]); | ||
| 1140 : | push(@SecondHeadings,$Headings[$i]); | ||
| 1141 : | } | ||
| 1142 : | } | ||
| 1143 : | #Printing headers | ||
| 1144 : | print HASHOUTPUT "FIRST HEADING;"; | ||
| 1145 : | print HASHOUTPUT join(";",@FirstHeadings)."\n"; | ||
| 1146 : | print HASHOUTPUT "SECOND HEADING;"; | ||
| 1147 : | print HASHOUTPUT join(";",@SecondHeadings)."\n"; | ||
| 1148 : | #Printing the number of data entries | ||
| 1149 : | print HASHOUTPUT "Number of entries;"; | ||
| 1150 : | for (my $i=0; $i < @FirstHeadings; $i++) { | ||
| 1151 : | if ($i > 0) { | ||
| 1152 : | print HASHOUTPUT ";"; | ||
| 1153 : | } | ||
| 1154 : | if ($FirstHeadings[$i] ne $SecondHeadings[$i]) { | ||
| 1155 : | chenry | 1.5 | if (defined($HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]})) { |
| 1156 : | chenry | 1.1 | if (@{$HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}} == 1) { |
| 1157 : | print HASHOUTPUT $HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}->[0]; | ||
| 1158 : | } else { | ||
| 1159 : | my $NumEntries = @{$HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}}; | ||
| 1160 : | print HASHOUTPUT $NumEntries; | ||
| 1161 : | } | ||
| 1162 : | } else { | ||
| 1163 : | print HASHOUTPUT 0; | ||
| 1164 : | } | ||
| 1165 : | } else { | ||
| 1166 : | chenry | 1.5 | if (defined($HashRef->{$FirstHeadings[$i]})) { |
| 1167 : | chenry | 1.1 | if (@{$HashRef->{$FirstHeadings[$i]}} == 1) { |
| 1168 : | print HASHOUTPUT $HashRef->{$FirstHeadings[$i]}->[0]; | ||
| 1169 : | } else { | ||
| 1170 : | my $NumEntries = @{$HashRef->{$FirstHeadings[$i]}}; | ||
| 1171 : | print HASHOUTPUT $NumEntries; | ||
| 1172 : | } | ||
| 1173 : | } else { | ||
| 1174 : | print HASHOUTPUT 0; | ||
| 1175 : | } | ||
| 1176 : | } | ||
| 1177 : | } | ||
| 1178 : | print HASHOUTPUT "\n"; | ||
| 1179 : | #Printing data | ||
| 1180 : | my $Continue = 1; | ||
| 1181 : | my $Count = 0; | ||
| 1182 : | while($Continue == 1) { | ||
| 1183 : | print HASHOUTPUT ($Count+1).";"; | ||
| 1184 : | $Continue = 0; | ||
| 1185 : | for (my $i=0; $i < @FirstHeadings; $i++) { | ||
| 1186 : | if ($FirstHeadings[$i] ne $SecondHeadings[$i]) { | ||
| 1187 : | if (defined($HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]})) { | ||
| 1188 : | if (@{$HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}} > 1 && defined($HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}->[$Count])) { | ||
| 1189 : | print HASHOUTPUT $HashRef->{$FirstHeadings[$i]}->{$SecondHeadings[$i]}->[$Count]; | ||
| 1190 : | $Continue = 1; | ||
| 1191 : | } | ||
| 1192 : | } | ||
| 1193 : | } else { | ||
| 1194 : | if (defined($HashRef->{$FirstHeadings[$i]})) { | ||
| 1195 : | if (@{$HashRef->{$FirstHeadings[$i]}} > 1 && defined($HashRef->{$FirstHeadings[$i]}->[$Count])) { | ||
| 1196 : | print HASHOUTPUT $HashRef->{$FirstHeadings[$i]}->[$Count]; | ||
| 1197 : | chenry | 1.5 | $Continue = 1; |
| 1198 : | chenry | 1.1 | } |
| 1199 : | } | ||
| 1200 : | } | ||
| 1201 : | print HASHOUTPUT ";"; | ||
| 1202 : | } | ||
| 1203 : | $Count++; | ||
| 1204 : | print HASHOUTPUT "\n"; | ||
| 1205 : | } | ||
| 1206 : | close(HASHOUTPUT); | ||
| 1207 : | } | ||
| 1208 : | |||
| 1209 : | sub CreateHistogramHash { | ||
| 1210 : | my($ArrayRef) = @_; | ||
| 1211 : | chenry | 1.5 | |
| 1212 : | chenry | 1.1 | my $HashRef; |
| 1213 : | for (my $i=0; $i < @{$ArrayRef}; $i++) { | ||
| 1214 : | my @TempArray = split(/\|/,$ArrayRef->[$i]); | ||
| 1215 : | for (my $j=0; $j < @TempArray; $j++) { | ||
| 1216 : | if (defined($HashRef->{$TempArray[$j]})) { | ||
| 1217 : | $HashRef->{$TempArray[$j]}->[0]++; | ||
| 1218 : | } else { | ||
| 1219 : | $HashRef->{$TempArray[$j]}->[0] = 1; | ||
| 1220 : | } | ||
| 1221 : | } | ||
| 1222 : | } | ||
| 1223 : | chenry | 1.5 | |
| 1224 : | chenry | 1.1 | return $HashRef; |
| 1225 : | } | ||
| 1226 : | |||
| 1227 : | chenry | 1.5 | #init_hoh will take a directory like peg or rxn and create a hash of hashes |
| 1228 : | chenry | 1.1 | #my $dir_all = '/disks/www/Network_Data/MinOrg'; |
| 1229 : | #$dir_peg = "$dir_all/peg"; | ||
| 1230 : | #%hoh_peg = &init_hoh($dir_peg); | ||
| 1231 : | # $hoh_peg{'peg.1234'}{REACTIONS} will be an @array of reactions associated with peg.1234 | ||
| 1232 : | sub init_hoh{ | ||
| 1233 : | chenry | 1.5 | my $dir = shift @_; |
| 1234 : | chenry | 1.1 | my %hash; |
| 1235 : | opendir my $DH, $dir or die "cannot open '$dir' $!"; | ||
| 1236 : | while (my $file = readdir $DH ) { | ||
| 1237 : | chomp $file; | ||
| 1238 : | next if $file =~ /~$/; | ||
| 1239 : | next if -d $file; | ||
| 1240 : | open my $FH, "<", "$dir/$file" or die "Cannot open '$dir/$file' $!"; | ||
| 1241 : | while ( my $line = <$FH> ) { | ||
| 1242 : | chomp $line; | ||
| 1243 : | next if /^#/ || !length($line); | ||
| 1244 : | my ($key, @values ) = split(/\t/, $line); | ||
| 1245 : | $hash{ $file }{ $key } = \@values; | ||
| 1246 : | } | ||
| 1247 : | close $FH; | ||
| 1248 : | } | ||
| 1249 : | return %hash; | ||
| 1250 : | } | ||
| 1251 : | |||
| 1252 : | sub AddElementsUnique { | ||
| 1253 : | my ($ArrayRef,@NewElements) = @_; | ||
| 1254 : | chenry | 1.5 | |
| 1255 : | chenry | 1.1 | my $ArrayValueHash; |
| 1256 : | my $NewArray; | ||
| 1257 : | if (defined($ArrayRef) && @{$ArrayRef} > 0) { | ||
| 1258 : | for (my $i=0; $i < @$ArrayRef; $i++) { | ||
| 1259 : | if (!defined($ArrayValueHash->{$ArrayRef->[$i]})) { | ||
| 1260 : | push(@{$NewArray},$ArrayRef->[$i]); | ||
| 1261 : | $ArrayValueHash->{$ArrayRef->[$i]} = @{$NewArray}-1; | ||
| 1262 : | } | ||
| 1263 : | } | ||
| 1264 : | } | ||
| 1265 : | chenry | 1.5 | |
| 1266 : | chenry | 1.1 | my $NumberOfMatches = 0; |
| 1267 : | for (my $i=0; $i < @NewElements; $i++) { | ||
| 1268 : | if (length($NewElements[$i]) > 0 && !defined($ArrayValueHash->{$NewElements[$i]})) { | ||
| 1269 : | push(@{$NewArray},$NewElements[$i]); | ||
| 1270 : | $ArrayValueHash->{$NewElements[$i]} = @{$NewArray}-1; | ||
| 1271 : | } else { | ||
| 1272 : | $NumberOfMatches++; | ||
| 1273 : | } | ||
| 1274 : | } | ||
| 1275 : | chenry | 1.5 | |
| 1276 : | chenry | 1.1 | return ($NewArray,$NumberOfMatches); |
| 1277 : | } | ||
| 1278 : | |||
| 1279 : | sub PutArrayInHash { | ||
| 1280 : | chenry | 1.6 | my (@ArrayRef) = @_; |
| 1281 : | chenry | 1.5 | |
| 1282 : | chenry | 1.1 | my $HashRef; |
| 1283 : | chenry | 1.6 | for (my $i=0; $i < @ArrayRef; $i++) { |
| 1284 : | $HashRef->{$ArrayRef[$i]} = $i; | ||
| 1285 : | chenry | 1.1 | } |
| 1286 : | chenry | 1.5 | |
| 1287 : | chenry | 1.1 | return $HashRef; |
| 1288 : | } | ||
| 1289 : | |||
| 1290 : | chenry | 1.4 | sub RefineOrganismName { |
| 1291 : | my ($Name) = @_; | ||
| 1292 : | chenry | 1.5 | |
| 1293 : | chenry | 1.4 | my @Temp = split(/\s/,$Name); |
| 1294 : | if (@Temp >= 2) { | ||
| 1295 : | $Name = substr(shift(@Temp),0,1).". ".lc(join(" ",@Temp)); | ||
| 1296 : | } | ||
| 1297 : | $Name =~ s/str\.\s//g; | ||
| 1298 : | my $Find = "subsp. ".$Temp[0]; | ||
| 1299 : | $Name =~ s/$Find//g; | ||
| 1300 : | chenry | 1.5 | |
| 1301 : | chenry | 1.4 | return $Name; |
| 1302 : | } | ||
| 1303 : | |||
| 1304 : | chenry | 1.6 | sub RemoveDuplicates { |
| 1305 : | my (@OriginalArray) = @_; | ||
| 1306 : | |||
| 1307 : | my %Hash; | ||
| 1308 : | foreach my $Element (@OriginalArray) { | ||
| 1309 : | $Hash{$Element} = 1; | ||
| 1310 : | } | ||
| 1311 : | @OriginalArray = sort(keys(%Hash)); | ||
| 1312 : | |||
| 1313 : | return @OriginalArray; | ||
| 1314 : | } | ||
| 1315 : | |||
| 1316 : | chenry | 1.1 | 1; |
| MCS Webmaster | ViewVC Help |
| Powered by ViewVC 1.0.3 |