taxonifi 0.2.0 → 0.3.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 7df9c89aa9370f5b09c35f4164eb9238be2b8a0d
+  data.tar.gz: 78c4de112c6e40cdf1e2197402f8f47e9dea6fa0
+SHA512:
+  metadata.gz: 6de2acff969064aad7a34e73759298630e3640430dff1c8ad3e189c373e0c5fe22c84cb8d56b71910d4711cf5446f344048a8bc4cbcb5c8ea8faec78a1cb8ac4
+  data.tar.gz: ff6a30b825545b759819540d468d37c68ffe700a531023875ed3e5a917dff6cd14859838da84081c87aefa36962d1398ffb6472c9662a47803d03a78d2144152

data/.gitignore

@@ -0,0 +1,59 @@
+
+# ignore in development script work
+sf
+
+vendor
+
+*.xlsx
+
+# rcov generated
+coverage
+coverage.data
+
+# rdoc generated
+rdoc
+
+# yard generated
+doc
+.yardoc
+
+# bundler
+.bundle
+
+# jeweler generated
+pkg
+
+# Have editor/IDE/OS specific files you need to ignore? Consider using a global gitignore: 
+#
+# * Create a file at ~/.gitignore
+# * Include files you want ignored
+# * Run: git config --global core.excludesfile ~/.gitignore
+#
+# After doing this, these files will be ignored in all your git projects,
+# saving you from having to 'pollute' every project you touch with them
+#
+# Not sure what to needs to be ignored for particular editors/OSes? Here's some ideas to get you started. (Remember, remove the leading # of the line)
+#
+# For MacOS:
+#
+.DS_Store
+
+.swo
+
+# For TextMate
+#*.tmproj
+#tmtags
+
+# For emacs:
+*~
+#\#*
+#.\#*
+
+# For vim:
+*.swp
+
+# For redcar:
+#.redcar
+
+# For rubinius:
+#*.rbc

data/.travis.yml

@@ -0,0 +1,11 @@
+language: ruby
+rvm:
+  - 2.1.5
+bundler_args: --without development
+before_install: ./travis/before_install.sh
+branches:
+  only:
+      - master
+  email:
+    - diapriid@gmail.com 
+  on_failure: change

data/Gemfile

@@ -1,19 +1,7 @@
-source "http://rubygems.org"
-# Add dependencies required to use your gem here.
-# Example:
-#   gem "activesupport", ">= 2.3.5"
 
-#  gem 'geokit'
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in gemspec
+gemspec
+
 
-# Add dependencies to develop your gem here.
-# Include everything needed to run rake, tests, features, etc.
-group :development do
-#  gem "shoulda", ">= 0"
-  gem "rdoc", "~> 3.12"
-  gem "bundler", "> 1.0.0"
-  gem "jeweler", "~> 1.8.3"
-  gem "activerecord", "3.2.8"
-  gem "debugger"
-#  gem "ruby-debug19"
-#  gem "simplecov", ">= 0"
-end

data/Gemfile.lock

@@ -1,47 +1,29 @@
+PATH
+  remote: .
+  specs:
+    taxonifi (0.3.2)
+      rake (~> 10.4)
+
 GEM
-  remote: http://rubygems.org/
+  remote: https://rubygems.org/
   specs:
-    activemodel (3.2.8)
-      activesupport (= 3.2.8)
-      builder (~> 3.0.0)
-    activerecord (3.2.8)
-      activemodel (= 3.2.8)
-      activesupport (= 3.2.8)
-      arel (~> 3.0.2)
-      tzinfo (~> 0.3.29)
-    activesupport (3.2.8)
-      i18n (~> 0.6)
-      multi_json (~> 1.0)
-    arel (3.0.2)
-    builder (3.0.0)
-    columnize (0.3.6)
-    debugger (1.2.0)
-      columnize (>= 0.3.1)
-      debugger-linecache (~> 1.1.1)
-      debugger-ruby_core_source (~> 1.1.3)
-    debugger-linecache (1.1.2)
-      debugger-ruby_core_source (>= 1.1.1)
-    debugger-ruby_core_source (1.1.3)
-    git (1.2.5)
-    i18n (0.6.1)
-    jeweler (1.8.4)
-      bundler (~> 1.0)
-      git (>= 1.2.5)
-      rake
-      rdoc
-    json (1.7.5)
-    multi_json (1.3.6)
-    rake (0.9.2.2)
-    rdoc (3.12)
-      json (~> 1.4)
-    tzinfo (0.3.33)
+    awesome_print (1.6.1)
+    builder (3.2.2)
+    byebug (4.0.5)
+      columnize (= 0.9.0)
+    columnize (0.9.0)
+    did_you_mean (0.9.8)
+      interception
+    interception (0.5)
+    rake (10.4.2)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  activerecord (= 3.2.8)
-  bundler (> 1.0.0)
-  debugger
-  jeweler (~> 1.8.3)
-  rdoc (~> 3.12)
+  awesome_print (~> 1.6)
+  builder (~> 3.2)
+  bundler (~> 1.9)
+  byebug (~> 4.0)
+  did_you_mean (~> 0.9)
+  taxonifi!

data/README.md

@@ -0,0 +1,192 @@
+
+[![Continuous Integration Status][1]][2]
+[![Dependency Status][7]][8]
+
+
+taxonifi
+========
+There will always be "legacy" taxonomic data that needs shuffling around. The taxonifi gem is a suite of general purpose tools that act as a middle layer for data-conversion purposes (e.g. migrating legacy taxonomic databases).  It's first application was to convert DwC-style data downloaded from EoL into a Species File.  The code is well documented in unit tests, poke around to see if it might be useful.  In particular, if you've considered building a collection of regular expressions particular to biodiversity data look at the Tokens code and related tests. 
+
+Overall, the goal is to provide well documented (and unit-tested) coded that is broadly useful, and vanilla enough to encourage other to fork and hack on their own.
+
+Source
+------
+Source is available at https://github.com/SpeciesFile/taxonifi .  The rdoc API is also viewable at http://taxonifi.speciesfile.org , (though those docs may lag behind commits to github).
+
+What's next?
+------------
+
+Before you jump on board you should also check out similar code from the Global Names team at https://github.com/GlobalNamesArchitecture. Future integration and merging of shared functionality is planned.  Code will be released in an "early-and-often" approach.
+
+Taxonifi is presently coded for convience, not speed (though it's not necessarily slow). It assumes that conversion processes are typically one-offs that can afford to run over a longer period of time (read minutes rather than seconds). Reading, and fully parsing into objects, around 25k rows of nomenclature (class to species, inc. author year, = ~45k names) in to memory as Taxonifi objects benchmarks at around 2 minutes. Faster indexing is planned as needed, likely using Redis (see GNA link above).
+
+Getting started
+---------------
+taxonifi is coded for Ruby 1.9.3, it has not been tested on earlier versions (though it will certainly not work with 1.8.7). 
+Using Ruby Version Manager (RVM, https://rvm.io/ ) is highly recommend. You can test your version of Ruby by doinging "ruby -v" in your terminal.
+
+To install:
+
+```
+gem install taxonifi
+```
+
+In your script:
+
+```
+require 'taxonifi'
+```
+
+Use
+===
+
+Quick start
+-----------
+
+Write some code:
+
+```
+require 'taxonifi'
+
+headers = ["a", "B", "c"]
+csv_string = CSV.generate() do |csv|
+  csv <<  @headers
+  csv << %w{a b c}
+end
+
+csv = CSV.parse(csv_string, {headers: true, header_converters: :downcase})
+
+# Taxonifi can create generic hierachical collections based on column headers
+c = Taxonifi::Lumper.create_hierarchical_collection(csv, %w{a b c})    # => a Taxonifi::Model::Collection 
+c.collection.first               # => Taxonifi::Model::GenericObject
+c.collection.first.name          # => "a" 
+c.collection.last.name           # => "c" 
+c.collection.last.parent.name    # => "b" 
+c.collection.first.row_number    # => 0
+c.collection.first.rank          # => "a"
+
+# Header order is important:
+c = Taxonifi::Lumper.create_hierarchical_collection(csv, %w{c a b})    # => a Taxonifi::Model::Collection 
+c.collection.first.name          # => "c" 
+c.collection.last.rank           # => "c" 
+c.collection.last.name           # => "b" 
+c.collection.last.parent.name    # => "a" 
+
+# Collections of GenericObjects (and some other Taxonifi::Collection based objects like TaxonifiNameCollection) only include
+# unique names, i.e. if a name has a shared parent lineage only the name itself is created, not its parents. 
+# For example, for:
+#  a b   c 
+#  a d   nil
+#  b nil d
+# The collection consists of objects with names a,b,c,d,b,d respectively.
+# This makes it very useful for handling not only nomenclatural but other nested data as well.
+```
+
+There are collections of specific types (e.g. taxonomic names, geographic names):
+
+```
+string = CSV.generate() do |csv|
+  csv << %w{family genus species author_year}
+  csv << ["Fooidae", "Foo", "bar", "Smith, 1854"]
+  csv << ["Fooidae", "Foo", "foo", "(Smith, 1854)"]
+end
+
+csv = CSV.parse(string, {headers: true})
+
+nc = Taxonifi::Lumper.create_name_collection(:csv => csv)  # => Taxonifi::Model::NameCollection
+
+nc.collection.first                                # => Taxonifi::Model::Name 
+nc.collection.first.name                           # => "Fooidae"
+nc.collection.first.rank                           # => "family" 
+nc.collection.first.year                           # =>  nil
+nc.collection.first.author                         # => []
+nc.collection.last.rank                            # => "species" 
+nc.collection.last.name                            # => "foo" 
+nc.collection.last.author.first.last_name          # =>  "Smith"
+nc.collection.last.year                            # =>  "1854"
+```
+
+Parent/child style nomenclature is also parseable.
+
+There are *lots* more examples of code use in the test suite.
+
+Export/conversion
+-----------------
+
+The following is an example that translates a DwC style input format as exported by EOL into tables importable to SpeciesFile.  The input file is has id, parent, child, vernacular, synonym columns.  Data are exported by default to a the users home folder in a taxonifi directory.  The export creates 6 tables that can be imported into Species File directly.
+
+```
+require 'taxonifi'
+file = File.expand_path(File.join(File.dirname(__FILE__), 'file_fixtures/Lygaeoidea-csv.tsv'))
+
+csv = CSV.read(file, { 
+  headers: true,
+  col_sep: "\t",
+  header_converters: :downcase
+} ) 
+
+nc = Taxonifi::Lumper::Lumps::ParentChildNameCollection.name_collection(csv)
+e = Taxonifi::Export::SpeciesFile.new(:nc => nc, :authorized_user_id => 1)
+e.export
+```
+
+You should be able to relativley quickly use the export framework to code new output formats.
+
+Reading files 
+-------------
+
+taxonifi feeds on Ruby's CSV. read your files with header true, and downcased, e.g.:
+
+```
+csv = CSV.read('input/my_data.tab',  { 
+              headers: true,
+              header_converters: :downcase,
+              col_sep: "\t"  } ) 
+```
+
+Code organization
+-----------------
+
+```
+test                # unit tests, quite a few of them
+lib                 # the main libraries
+lib/assessor        # libraries to assess the properties of incoming data
+lib/export          # export wrappers 
+lib/export/format   # one module for each export type
+lib/lumper          # code that builds Taxonifi objects 
+lib/model           # Taxonifi objects
+lib/splitter        # a parser/lexer/token suite for breaking down data 
+```
+
+Contributing to taxonifi
+------------------------
+
+(this is generic)
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Write unit test for your code.  Changes are good, just as long as tests run clean.  
+* All pull requests should test clean.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+About
+-----
+
+taxonifi is coded by Matt Yoder in consultation with the Species File Group at University of Illinois.
+
+Copyright
+---------
+
+Copyright (c) 2012 Illinois Natural History Survey. See LICENSE.txt for
+further details.
+
+
+[1]: https://secure.travis-ci.org/SpeciesFileGroup/taxonifi.png?branch=master
+[2]: http://travis-ci.org/SpeciesFileGroup/taxonifi?branch=master
+[7]: https://gemnasium.com/SpeciesFileGroup/taxonifi.png?branch=master
+[8]: https://gemnasium.com/SpeciesFileGroup/taxonifi?branch=master
+
+

data/Rakefile

@@ -1,31 +1,38 @@
-# encodang: 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
+#!/usr/bin/env rake
+
+require 'bundler/gem_tasks'
 require 'rake'
+require 'rake/testtask'
+require 'taxonifi/version'
+
+# 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 'jeweler'
+
+# Jeweler::Tasks.new do |gem|
+#   # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+#   gem.name = "taxonifi"
+#   gem.homepage = "http://github.com/SpeciesFile/taxonifi"
+#   gem.license = "MIT"
+#   gem.summary = %Q{A general purpose framework for scripted handling of taxonomic names}
+#   gem.description = %Q{Taxonifi contains simple models and utilties of use in for parsing lists of taxonomic name (life) related metadata}
+#   gem.email = "diapriid@gmail.com"
+#   gem.authors = ["mjy"]
+#   # dependencies defined in Gemfile
+# end
+
+# Jeweler::RubygemsDotOrgTasks.new
 
-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 = "taxonifi"
-  gem.homepage = "http://github.com/SpeciesFile/taxonifi"
-  gem.license = "MIT"
-  gem.summary = %Q{A general purpose framework for scripted handling of taxonomic names}
-  gem.description = %Q{Taxonifi contains simple models and utilties of use in for parsing lists of taxonomic name (life) related metadata}
-  gem.email = "diapriid@gmail.com"
-  gem.authors = ["mjy"]
-  # dependencies defined in Gemfile
-end
-Jeweler::RubygemsDotOrgTasks.new
 
-require 'rake/testtask'
 Rake::TestTask.new(:test) do |test|
   test.libs << 'lib' << 'test'
   test.pattern = 'test/**/test_*.rb'
@@ -43,11 +50,13 @@ end
 task :default => :test
 
 require 'rdoc/task'
+
 Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+ version = Taxonifi::VERSION 
 
  rdoc.rdoc_dir = 'rdoc'
  rdoc.title = "taxonifi #{version}"
  rdoc.rdoc_files.include('README*')
  rdoc.rdoc_files.include('lib/**/*.rb')
+
 end

data/lib/export/format/base.rb

@@ -7,7 +7,7 @@ module Taxonifi::Export
     # See https://phenoscape.svn.sourceforge.net/svnroot/phenoscape/trunk/vocab/taxonomic_rank.obo
     # Site: https://www.phenoscape.org/wiki/Taxonomic_Rank_Vocabulary
     # Values of -1 have no correspondance in that ontology. 
-    # Nt all values are supported. Not all values are included.
+    # Not all values are supported. Not all values are included.
     TAXRANKS = {
       'taxonomic_rank' =>          0,
       'variety'        =>          16,