bio-table 0.0.1

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.rspec

@@ -0,0 +1 @@
+--color

data/.travis.yml

@@ -0,0 +1,12 @@
+language: ruby
+rvm:
+  - 1.9.2
+  - 1.9.3
+  - jruby-19mode # JRuby in 1.9 mode
+  - rbx-19mode
+#  - 1.8.7
+#  - jruby-18mode # JRuby in 1.8 mode
+#  - rbx-18mode
+
+# uncomment this line if your project needs to run something other than `rake`:
+# script: bundle exec rspec spec

data/Gemfile

@@ -0,0 +1,18 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+gem "bio-logger"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "rspec", "~> 2.8.0"
+  gem "rdoc", "~> 3.12"
+  gem "cucumber", ">= 0"
+  gem "bundler", "> 1.0.0"
+  gem "jeweler", "~> 1.8.3"
+  gem "bio", ">= 1.4.2"
+  gem "rdoc", "~> 3.12"
+end

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2012 Pjotr Prins
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,283 @@
+# bio-table
+
+[![Build Status](https://secure.travis-ci.org/pjotrp/bioruby-table.png)](http://travis-ci.org/pjotrp/bioruby-table)
+
+Tables of data are often used in bioinformatics, especially in
+conjunction with Excel spreadsheets and DB queries. This biogem
+contains support for reading tables, writing tables, and manipulation
+of rows and columns, both using a command line interface and through a
+Ruby library. If you don't like R dataframes, maybe you like this.
+Also, because bio-table is command line driven, it easily fits in a
+pipe-line setup. 
+
+Quick example, say we want to filter out rows that contain certain
+p-values listed in the 4th column:
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values[3] <= 0.05"
+```
+
+bio-table should be lazy, be good for big data, and the library
+support a functional style of programming. You don't need to know Ruby
+to use the command line interface (CLI).
+
+Note: this software is under active development!
+
+## Installation
+
+```sh
+    gem install bio-table
+```
+
+## The command line interface (CLI)
+
+### Transforming a table
+
+Tables can be transformed through the command line. To transform a
+comma separated file to a tab delimited one
+
+```
+    bio-table test/data/input/table1.csv --in-format csv --format tab > test1.tab
+```
+
+Tab is actually the general default. Still, if the file name ends in
+csv, it will assume CSV. To convert the table back
+
+```
+    bio-table test1.tab --format csv > table1.csv
+```
+
+To filter out rows that contain certain values
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values[3] <= 0.05" > test1a.tab
+```
+
+The filter ignores the header row, and the row names. If you need
+either, use the switches --with-header and --with-rownames. With math, list all rows 
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values[3]-values[6] >= 0.05" > test1a.tab
+```
+
+or, list all rows that have a least a field with values >= 1000.0
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values.max >= 1000.0" > test1a.tab
+```
+
+Produce all rows that have at least 3 values above 3.0 and 1 one value
+above 10.0:
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values.max >= 10.0 and values.count{|x| x>=3.0} > 3"
+```
+
+How is that for expressiveness? Looks like Ruby to me.
+
+The --num-filter will convert fields lazily to numerical values (only
+valid numbers are converted). If there are NA (nil) values in the table, you
+may wish to remove them, like this
+
+```
+    bio-table test/data/input/table1.csv --num-filter "values[0..12].compact.max >= 1000.0" > test1a.tab
+```
+
+which takes the first 13 fields and compact removes the nil values.
+
+Also string comparisons and regular expressions can be used. E.g.
+filter on rownames and a row field both containing 'BGT'
+
+```
+    # not yet implemented
+    bio-table test/data/input/table1.csv --filter "rowname =~ /BGT/ and field[1] =~ /BGT/" > test1a.tab
+```
+
+To reorder/reduce table columns by name
+
+```
+    bio-table test/data/input/table1.csv --columns AJ,B6,Axb1,Axb4,AXB13,Axb15,Axb19 > test1a.tab
+```
+
+or use their index numbers
+
+```
+    bio-table test/data/input/table1.csv --columns 0,1,8,2,4,6 > test1a.tab
+```
+
+### Sorting a table
+
+To sort a table on column 4 and 2
+
+```
+    # not yet implemented
+    bio-table test/data/input/table1.csv --sort 4,2 > test1a.tab
+```
+
+Note: not all is implemented (just yet). Please check bio-table --help first.
+
+### Combining a table
+
+You can combine/concat tables by passing in multiple file names
+
+    bio-table test/data/input/table1.csv test/data/input/table2.csv
+
+assuming they have the same headers (you can use the --columns switch!)
+
+### Splitting a table
+
+Splitting a table by column is possible by named or indexed columns,
+see the --columns switch.
+
+more soon
+
+### Diffing and overlapping tables
+
+With two tables it may be interesting to see the differences, or
+overlap, based on shared columns. The bio-table diff command shows the
+difference between two tables using the row names (i.e. those rows
+with rownames that appear in table2, but not in table1)
+
+    bio-table --diff 0 table1.csv table2.csv 
+
+To find it the other way, switch the file names
+
+    bio-table --diff 0 table1.csv table2.csv 
+
+To diff on something else
+
+    bio-table --diff 0,3 table2.csv table1.csv 
+
+creates a (hopefully unique) key using columns 0 and 3 (0 is the rownames column).
+
+Similarly
+
+    bio-table --overlap 2 table1.csv table2.csv
+
+finds the overlapping rows, based on column 2 (NYI)
+
+### Different parsers
+
+more soon
+
+## Usage
+
+```ruby
+    require 'bio-table'
+    include BioTable
+```
+
+### Reading, transforming, and writing a table
+
+Note: the Ruby API below is a work in progress.
+
+Tables are two dimensional matrixes, which can be read from a file
+
+```
+    t = Table.read_file('test/data/input/table1.csv')
+    p t.header              # print the header array
+    p t.name[0],t[0]        # print the row name and row row
+    p t[0][0]               # print the top corner field
+```
+
+The table reader has quite a few options for defining field separator,
+which column to use for names etc. More interestingly you can pass a
+function to limit the amount of row read into memory:
+
+```
+    t = Table.read_file('test/data/input/table1.csv',
+      :by_row => { | row | row[0..3] } )
+```
+
+will create a table of the column name +row[0]+ and 2 table fields. You can use
+the same idea to reformat and reorder table columns when reading data
+into the table. E.g.
+
+```
+    t = Table.read_file('test/data/input/table1.csv',
+      :by_row => { | row | [row.rowname, row[0..3], row[6].to_i].flatten } )
+```
+
+When a header can not be transformed, it may fail. You can test for
+the header with row.header?, but in this case you
+can pass in a :by_header, which will have :by_row only call on
+actual table rows.
+
+```
+    t = Table.read_file('test/data/input/table1.csv',
+      :by_header => { | header | ["Row name", header[0..3], header[6]].flatten } )
+      :by_row => { | row | [row.rowname, row[0..3], row[6].to_i].flatten } )
+```
+
+When by_row returns nil or false, the table row is skipped. One way to
+transform a file, and not loading it in memory, is
+
+```
+    f = File.new('test.tab','w')
+    t = Table.read_file('test/data/input/table1.csv', 
+      :by_row => { | row | 
+        TableRow::write(f,[row.rowname,row[0..3],row[6].to_i].flatten, :separator => "\t") 
+        nil   # don't create a table in memory, effectively a filter
+      })
+```
+
+Another function is :filter which only acts on rows, but can not
+transform them.
+
+To write a full table from memory to file use
+
+```
+    t.write_file('test1a.csv')
+```
+
+again columns can be reordered/transformed using a function. Another
+option is by passing in an list of column numbers or header names, so
+only those get written, e.g.
+
+```
+    t.write_file('test1a.csv', columns: [0,1,2,4,6,8])
+    t.write_file('test1b.csv', columns: ["AJ","B6","Axb1","Axb4","AXB13","Axb15","Axb19"] )
+```
+
+other options are available for excluding row names (rownames: false), etc.
+
+To sort a table file, the current routine is to load the file in
+memory and sort according to table columns. In the near future we aim
+to have a low-memory version, by reading only the sorting columns in
+memory, and indexing them before writing output. That means reading a
+file twice, but being able to handle much larger data.
+
+### Loading a numerical matrix
+
+Coming soon
+
+### More...
+
+The API doc is online. For more code examples see the test files in
+the source tree.
+
+       
+## Project home page
+
+Information on the source tree, documentation, examples, issues and
+how to contribute, see
+
+  http://github.com/pjotrp/bioruby-table
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+## Cite
+
+If you use this software, please cite one of
+  
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+## Biogems.info
+
+This Biogem is published at [#bio-table](http://biogems.info/index.html)
+
+## Copyright
+
+Copyright (c) 2012 Pjotr Prins. See LICENSE.txt for further details.
+

data/Rakefile

@@ -0,0 +1,55 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "bio-table"
+  gem.homepage = "http://github.com/pjotrp/bioruby-table"
+  gem.license = "MIT"
+  gem.summary = %Q{Transforming/filtering tab/csv files}
+  gem.description = %Q{Functions and tools for tranforming and changing tab delimited and comma separated table files - useful for Excel sheets and SQL/RDF output}
+  gem.email = "pjotr.public01@thebird.nl"
+  gem.authors = ["Pjotr Prins"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+require 'cucumber/rake/task'
+Cucumber::Rake::Task.new do |features|
+end
+
+task :test => [ :cucumber ] 
+
+task :default => :test
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "bio-table #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.1

data/bin/bio-table

@@ -0,0 +1,141 @@
+#!/usr/bin/env ruby
+#
+# BioRuby bio-table Plugin BioTable
+# Author:: Pjotr Prins
+# Copyright:: 2012
+
+rootpath = File.dirname(File.dirname(__FILE__))
+$: << File.join(rootpath,'lib')
+
+_VERSION = File.new(File.join(rootpath,'VERSION')).read.chomp
+
+$stderr.print "bio-table "+_VERSION+" Copyright (C) 2012 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
+
+USAGE =<<EOU
+
+bio-table transforms, filters and reorders table files (CSV, tab-delimited).
+
+EOU
+
+if ARGV.size == 0
+  print USAGE
+end
+
+require 'bio-table'
+require 'optparse'
+require 'bio-logger'
+
+log = Bio::Log::LoggerPlus.new 'bio-table'
+# log.outputters = Bio::Log::Outputter.stderr
+
+Bio::Log::CLI.logger('stderr')
+Bio::Log::CLI.trace('info')
+
+options = {show_help: false, write_header: true}
+options[:show_help] = true if ARGV.size == 0
+opts = OptionParser.new do |o|
+  o.banner = "Usage: #{File.basename($0)} [options] filename\n\n"
+
+  o.on('--in-format [tab,csv]', [:tab, :csv], 'Input format (default tab)') do |par|
+    options[:in_format] = par.to_sym
+  end
+
+  o.on('--format [tab,csv]', [:tab, :csv], 'Output format (default tab)') do |par|
+    options[:format] = par.to_sym
+  end
+  
+  o.on('--num-filter func', 'Numeric filtering function') do |par|
+    options[:num_filter] = par
+  end
+
+  o.on('--columns list', Array, 'List of column names or indices') do |l|
+    options[:columns] = l
+  end
+
+  o.on('--diff list',Array,'Diff two input files on columns') do |l|
+    options[:diff] = l
+  end
+
+  o.on('--overlap list',Array,'Find overlap of two input files on columns)') do |l|
+    options[:overlap] = l
+  end
+  
+  
+  # o.on('--with-header','Include the header element in filtering etc.') do
+  #   options[:with_header] = true
+  # end
+  
+  o.on('--with-rownames','Include the rownames in filtering etc.') do
+    options[:with_rownames] = true
+  end
+  
+  o.separator ""
+
+  o.on("--logger filename",String,"Log to file (default stderr)") do | name |
+    Bio::Log::CLI.logger(name)
+  end
+  
+  o.on("--trace options",String,"Set log level (default INFO, see bio-logger)") do | s |
+    Bio::Log::CLI.trace(s)
+  end
+  
+  o.on("-q", "--quiet", "Run quietly") do |q|
+    Bio::Log::CLI.trace('error')
+  end
+  
+  o.on("-v", "--verbose", "Run verbosely") do |v|
+    Bio::Log::CLI.trace('info')
+  end
+  
+  o.on("--debug", "Show debug messages") do |v|
+    Bio::Log::CLI.trace('debug')
+  end
+
+  o.separator ""
+
+  o.on_tail('-h', '--help', 'Display this help and exit') do
+    options[:show_help] = true
+  end
+end
+
+begin
+  opts.parse!(ARGV)
+
+  if options[:show_help] 
+    print opts
+    print USAGE
+  end
+
+  # TODO: your code here
+  # use options for your logic
+rescue OptionParser::InvalidOption => e
+  options[:invalid_argument] = e.message
+end
+
+Bio::Log::CLI.configure('bio-table')
+logger = Bio::Log::LoggerPlus['bio-table']
+logger.info [options, ARGV]
+
+include BioTable
+
+if options[:diff]
+  logger.warn "Column settings are ignored for --diff" if options[:columns]
+  logger.warn "Ignoring extraneaousfiles" if ARGV.size>2
+  t1 = TableReader::read_file(ARGV[0], options)
+  t2 = TableReader::read_file(ARGV[1], options)
+  t = Diff::diff_tables(t1,t2, options)
+  t.write(options)
+  exit
+end
+
+if options[:overlap]
+  logger.warn "Column settings are ignored for --overlap" if options[:columns]
+  exit
+end
+
+
+ARGV.each do | fn |
+  t = TableReader::read_file(fn, options)
+  t.write(options)
+  options[:write_header] = false  # don't write the header for chained files
+end