absee 0.0.0 → 0.0.1

data/lib/absee.rb

@@ -9,6 +9,15 @@
 #
 # MIT license 2012
 
+#opens the ABIF sequencing / chromatogram file
+#checks for ABIF file type
+#major ABIF versions greater than 1 are not supported
+#
+#== Parameters:
+#filename:: a string containing the filename (including the path and extensions)
+#
+#== Returns:
+#Six arrays: trace data for A, C, G, T, called sequence, and peak indexes
 def readAB(filename)
   #opens ab1 as a File object
   abFile = open(filename)
@@ -26,6 +35,14 @@ def readAB(filename)
   end
 end
 
+#process the opened ABIF filestream, and calls subsequent methods to extract the data
+#
+#== Parameters:
+#filestream:: an opened File
+#
+#== Returns:
+#Six arrays: trace data for A, C, G, T, called sequence, and peak indexes
+#readAB returns the results of this method
 def processAB(filestream)
   #// here, we can read the ABIF header information
   version = readUnsignedByte_2(4, filestream)
@@ -45,6 +62,14 @@ def processAB(filestream)
   return samples_a, samples_c, samples_g, samples_t, called_sequence, peakIndexes
 end
 
+#reads 2 unsigned bytes and orders by most significant byte first
+#
+#== Parameters:
+#offset:: how many bytes to offset for the read
+#filestream:: an opened File
+#
+#== Returns:
+#an int ordered by most significant byte first
 def readUnsignedByte_2(offset, filestream)
   #// most significant byte first
   #// |byte0|byte1| <= |unsigned int|
@@ -54,6 +79,14 @@ def readUnsignedByte_2(offset, filestream)
   return (byteArray.getbyte(0) << 8) | byteArray.getbyte(1)
 end
 
+#reads 4 unsigned bytes and orders by most significant byte first
+#
+#== Parameters:
+#offset:: how many bytes to offset for the read
+#filestream:: an opened File
+#
+#== Returns:
+#an int ordered by most significant byte first
 def readUnsignedByte_4(offset, filestream)
   byteArray = ""
   filestream.seek(offset, IO::SEEK_SET)
@@ -63,6 +96,16 @@ def readUnsignedByte_4(offset, filestream)
   return (byteArray.getbyte(0)<<24) | (byteArray.getbyte(1)<<16) | (byteArray.getbyte(2)<<8) | byteArray.getbyte(3)
 end
 
+#reads the data from the directory
+#
+#== Parameters:
+#dataOffset:: how many bytes to offset
+#numElements:: number of elements in the file computed by gatherInformation
+#filestream:: an opened File
+#
+#== Returns:
+#an array of arrays, each with information from the directory
+#[name, tag number, element type, element size, number of elements, data size, data offset]
 def readDirectoryEntry(filestream, dataOffset, numElements)
   filestream.seek(dataOffset, IO::SEEK_SET)
   byteArray = ""
@@ -109,7 +152,14 @@ end
 
 #directory structure
 #[name, tag number, element type, element size, number of elements, data size, data offset]
-#this is for easier access to the directory element
+#this is for easier index into the each directory array
+#
+#== Parameters:
+#array:: an array with information from the directory
+#element:: a string with type of information from the directory to retrieve: [name, tag_number, element_type, element_size, number_of_elements, data_size, data_offset
+#
+#== Returns:
+#the element from the array
 def get(array, element)
   if element == "name"
     return array[0]
@@ -130,7 +180,14 @@ def get(array, element)
   end
 end
 
-
+#counts the number of samples and number of bases contained in this ABIF file
+#
+#== Parameters:
+#directory:: an array of array generated from readDirectoryEntry
+#numElements:: an int indicating the number of elements in this ABIF file
+#
+#== Returns:
+#number of samples and number of bases contained in this ABIF file
 def gatherInformation(directory, numElements)
   numSamples = 0
   numBases = 0
@@ -148,6 +205,16 @@ def gatherInformation(directory, numElements)
   return numSamples, numBases
 end
 
+#extracts the trace information for the bases
+#
+#== Parameters:
+#filestream:: an open File
+#directory:: an array of array generated by readDirectoryEntry
+#numElements:: an int indicating the number of elements in this ABIF file
+#numSamples:: an int calculated by gatherInformation
+#
+#== Returns:
+#four arrays with trace data in the order ACGT
 def getSamples(filestream, directory, numElements, numSamples)
   samples_a = []
   samples_c = []
@@ -188,6 +255,16 @@ def getSamples(filestream, directory, numElements, numSamples)
   return samples_a, samples_c, samples_g, samples_t
 end
 
+#extracts the called sequence information
+#
+#== Parameters:
+#filestream:: an open File
+#directory:: an array of array generated by readDirectoryEntry
+#numElements:: an int indicating the number of elements in this ABIF file
+#numBases:: an int calculated by gatherInformation
+#
+#== Returns:
+#an array with the called sequence
 def getCalledSequence(filestream, directory, numElements, numBases)
   calledSequence = []
   (0..numElements-1).each do |i|
@@ -203,6 +280,16 @@ def getCalledSequence(filestream, directory, numElements, numBases)
   return calledSequence
 end
 
+#extracts the trace information for the bases
+#
+#== Parameters:
+#filestream:: an open File
+#directory:: an array of array generated by readDirectoryEntry
+#numElements:: an int indicating the number of elements in this ABIF file
+#numBases:: an int calculated by gatherInformation
+#
+#== Returns:
+#an array with the indexes of the peaks
 def getPeakIndexes(filestream, directory, numElements, numBases)
   peakIndexes = []
   (0..numElements-1).each do |i|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: absee
 version: !ruby/object:Gem::Version
-  version: 0.0.0
+  version: 0.0.1
   prerelease: 
 platform: ruby
 authors: