taxamatch_rb 1.0.1 → 1.1.0

data/Makefile

@@ -1,157 +0,0 @@
-
-SHELL = /bin/sh
-
-#### Start of system configuration section. ####
-
-srcdir = /Users/dimus/.rvm/gems/ruby-1.9.2-p0/bin
-topdir = /Users/dimus/.rvm/rubies/ruby-1.9.2-p0/include/ruby-1.9.1
-hdrdir = /Users/dimus/.rvm/rubies/ruby-1.9.2-p0/include/ruby-1.9.1
-arch_hdrdir = /Users/dimus/.rvm/rubies/ruby-1.9.2-p0/include/ruby-1.9.1/$(arch)
-VPATH = $(srcdir):$(arch_hdrdir)/ruby:$(hdrdir)/ruby
-prefix = $(DESTDIR)/Users/dimus/.rvm/rubies/ruby-1.9.2-p0
-rubylibprefix = $(libdir)/$(RUBY_BASE_NAME)
-exec_prefix = $(prefix)
-vendorhdrdir = $(rubyhdrdir)/vendor_ruby
-sitehdrdir = $(rubyhdrdir)/site_ruby
-rubyhdrdir = $(includedir)/$(RUBY_BASE_NAME)-$(ruby_version)
-vendordir = $(rubylibprefix)/vendor_ruby
-sitedir = $(rubylibprefix)/site_ruby
-ridir = $(datarootdir)/$(RI_BASE_NAME)
-mandir = $(datarootdir)/man
-localedir = $(datarootdir)/locale
-libdir = $(exec_prefix)/lib
-psdir = $(docdir)
-pdfdir = $(docdir)
-dvidir = $(docdir)
-htmldir = $(docdir)
-infodir = $(datarootdir)/info
-docdir = $(datarootdir)/doc/$(PACKAGE)
-oldincludedir = $(DESTDIR)/usr/include
-includedir = $(prefix)/include
-localstatedir = $(prefix)/var
-sharedstatedir = $(prefix)/com
-sysconfdir = $(prefix)/etc
-datadir = $(datarootdir)
-datarootdir = $(prefix)/share
-libexecdir = $(exec_prefix)/libexec
-sbindir = $(exec_prefix)/sbin
-bindir = $(exec_prefix)/bin
-rubylibdir = $(rubylibprefix)/$(ruby_version)
-archdir = $(rubylibdir)/$(arch)
-sitelibdir = $(sitedir)/$(ruby_version)
-sitearchdir = $(sitelibdir)/$(sitearch)
-vendorlibdir = $(vendordir)/$(ruby_version)
-vendorarchdir = $(vendorlibdir)/$(sitearch)
-
-CC = gcc
-CXX = g++
-LIBRUBY = $(LIBRUBY_SO)
-LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
-LIBRUBYARG_SHARED = -l$(RUBY_SO_NAME)
-LIBRUBYARG_STATIC = -l$(RUBY_SO_NAME)-static
-OUTFLAG = -o 
-COUTFLAG = -o 
-
-RUBY_EXTCONF_H = 
-cflags   =  $(optflags) $(debugflags) $(warnflags)
-optflags = -O3
-debugflags = -ggdb
-warnflags = -Wextra -Wno-unused-parameter -Wno-parentheses -Wpointer-arith -Wwrite-strings -Wno-missing-field-initializers -Wshorten-64-to-32 -Wno-long-long
-CFLAGS   = -fno-common $(cflags)  -fno-common -pipe 
-INCFLAGS = -I. -I$(arch_hdrdir) -I$(hdrdir)/ruby/backward -I$(hdrdir) -I$(srcdir)
-DEFS     = 
-CPPFLAGS =  -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE $(DEFS) $(cppflags)
-CXXFLAGS = $(CFLAGS) $(cxxflags)
-ldflags  = -L. 
-dldflags = -Wl,-undefined,dynamic_lookup -Wl,-multiply_defined,suppress -Wl,-flat_namespace
-ARCH_FLAG = 
-DLDFLAGS = $(ldflags) $(dldflags)
-LDSHARED = $(CC) -dynamic -bundle
-LDSHAREDXX = $(CXX) -dynamic -bundle
-AR = ar
-EXEEXT = 
-
-RUBY_BASE_NAME = ruby
-RUBY_INSTALL_NAME = ruby
-RUBY_SO_NAME = ruby.1.9.1
-arch = x86_64-darwin10.3.1
-sitearch = $(arch)
-ruby_version = 1.9.1
-ruby = /Users/dimus/.rvm/rubies/ruby-1.9.2-p0/bin/ruby
-RUBY = $(ruby)
-RM = rm -f
-RM_RF = $(RUBY) -run -e rm -- -rf
-RMDIRS = $(RUBY) -run -e rmdir -- -p
-MAKEDIRS = mkdir -p
-INSTALL = /usr/bin/install -c
-INSTALL_PROG = $(INSTALL) -m 0755
-INSTALL_DATA = $(INSTALL) -m 644
-COPY = cp
-
-#### End of system configuration section. ####
-
-preload = 
-
-libpath = . $(libdir)
-LIBPATH =  -L. -L$(libdir)
-DEFFILE = 
-
-CLEANFILES = mkmf.log
-DISTCLEANFILES = 
-DISTCLEANDIRS = 
-
-extout = 
-extout_prefix = 
-target_prefix = 
-LOCAL_LIBS = 
-LIBS = $(LIBRUBYARG_SHARED)  -lpthread -ldl -lobjc 
-SRCS = 
-OBJS = 
-TARGET = 
-DLLIB = 
-EXTSTATIC = 
-STATIC_LIB = 
-
-BINDIR        = $(bindir)
-RUBYCOMMONDIR = $(sitedir)$(target_prefix)
-RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
-RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
-HDRDIR        = $(rubyhdrdir)/ruby$(target_prefix)
-ARCHHDRDIR    = $(rubyhdrdir)/$(arch)/ruby$(target_prefix)
-
-TARGET_SO     = $(DLLIB)
-CLEANLIBS     = $(TARGET).bundle 
-CLEANOBJS     = *.o  *.bak
-
-all:    Makefile
-static: $(STATIC_LIB)
-.PHONY: all install static install-so install-rb
-.PHONY: clean clean-so clean-rb
-
-clean-rb-default::
-clean-rb::
-clean-so::
-clean: clean-so clean-rb-default clean-rb
-		@-$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES)
-
-distclean-rb-default::
-distclean-rb::
-distclean-so::
-distclean: clean distclean-so distclean-rb-default distclean-rb
-		@-$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
-		@-$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
-		@-$(RMDIRS) $(DISTCLEANDIRS)
-
-realclean: distclean
-install: install-so install-rb
-
-install-so: Makefile
-install-rb: pre-install-rb install-rb-default
-install-rb-default: pre-install-rb-default
-pre-install-rb: Makefile
-pre-install-rb-default: Makefile
-
-site-install: site-install-so site-install-rb
-site-install-so: install-so
-site-install-rb: install-rb
-

data/VERSION

@@ -1 +0,0 @@
-1.0.1

data/spec/spec.opts

@@ -1 +0,0 @@
---colour

data/spec/spec_helper.rb

@@ -1,22 +0,0 @@
-require 'rspec'
-
-$:.unshift(File.dirname(__FILE__) + '/../lib')
-require 'taxamatch_rb'
-
-def read_test_file(file, fields_num)
-  f = open(file)
-  f.each do |line|
-    fields = line.split("|")
-    if line.match(/^\s*#/) == nil && fields.size == fields_num
-      fields[-1] = fields[-1].split('#')[0].strip
-      yield(fields)
-    else
-      yield(nil)
-    end
-  end
-end
-
-def make_taxamatch_hash(string)
-  normalized = Taxamatch::Normalizer.normalize(string)
-  {:string => string, :normalized => normalized, :phonetized => Taxamatch::Phonetizer.near_match(normalized)}
-end

data/spec/taxamatch_rb_spec.rb

@@ -1,406 +0,0 @@
-# encoding: UTF-8
-require 'spec_helper'
-
-describe 'Atomizer' do
-  before(:all) do
-    @parser = Taxamatch::Atomizer.new
-  end
-
-  it 'should parse uninomials' do
-    @parser.parse('Betula').should == { :all_authors => [], :all_years => [],
-      :canonical_form => "Betula", :uninomial => { :string => "Betula",
-      :normalized => 'BETULA', :phonetized => "BITILA", :authors => [],
-      :years => [], :normalized_authors => [] } }
-    @parser.parse('Ærenea Lacordaire, 1872').should == {
-      :all_authors => ["LACORDAIRE"], :all_years => [1872],
-      :canonical_form => "Aerenea", :uninomial => { :string => "Aerenea",
-        :normalized => "AERENEA", :phonetized => "ERINIA",
-        :authors => ["Lacordaire"], :years => [1872],
-        :normalized_authors => ["LACORDAIRE"] } }
-  end
-
-  it 'should parse binomials' do
-    @parser.parse('Leœptura laetifica Dow, 1913').should == {
-      :all_authors => ["DOW"], :all_years => [1913],
-      :canonical_form => "Leoeptura laetifica", :genus => {
-      :string => "Leoeptura", :normalized => "LEOEPTURA",
-      :phonetized => "LIPTIRA", :authors => [], :years => [],
-      :normalized_authors => []}, :species => {
-      :string => "laetifica", :normalized => "LAETIFICA",
-      :phonetized => "LITIFICA", :authors => ["Dow"],
-      :years => [1913], :normalized_authors => ["DOW"] } }
-  end
-
-  it 'should parse trinomials' do
-    @parser.parse('Hydnellum scrobiculatum zonatum ' +
-                  '(Banker) D. Hall et D.E. Stuntz 1972').should ==  {
-      :all_authors => ["BANKER", "D HALL", "D E STUNTZ"], :all_years => [1972],
-      :canonical_form => "Hydnellum scrobiculatum zonatum", :genus=>{
-      :string => "Hydnellum", :normalized => "HYDNELLUM",
-      :phonetized => "HIDNILIM", :authors => [], :years => [],
-      :normalized_authors => [] }, :species => { :string => "scrobiculatum",
-      :normalized => "SCROBICULATUM", :phonetized => "SCRABICILATA",
-      :authors => [], :years => [], :normalized_authors => [] },
-      :infraspecies => [{ :string => "zonatum", :normalized => "ZONATUM",
-      :phonetized => "ZANATA", :authors => ["Banker", "D. Hall", "D.E. Stuntz"],
-      :years => [1972], :normalized_authors => ["BANKER", "D HALL",
-      "D E STUNTZ"] }] }
-  end
-
-  it 'should normalize years to integers' do
-    future_year = Time.now.year + 10
-    @parser.parse("Hydnellum scrobiculatum Kern #{future_year} " +
-                  "zonatum (Banker) D. Hall et D.E. Stuntz 1972?").should == {
-      :all_authors => ["KERN", "BANKER", "D HALL", "D E STUNTZ"],
-      :all_years => [1972],
-      :canonical_form => "Hydnellum scrobiculatum zonatum", :genus => {
-      :string => "Hydnellum", :normalized => "HYDNELLUM",
-      :phonetized => "HIDNILIM", :authors => [], :years => [],
-      :normalized_authors => [] }, :species => { :string => "scrobiculatum",
-      :normalized => "SCROBICULATUM", :phonetized => "SCRABICILATA",
-      :authors => ["Kern"], :years => [], :normalized_authors => ["KERN"] },
-      :infraspecies => [{ :string => "zonatum", :normalized => "ZONATUM",
-      :phonetized => "ZANATA", :authors =>
-      ["Banker", "D. Hall", "D.E. Stuntz"], :years => [1972],
-      :normalized_authors => ["BANKER", "D HALL", "D E STUNTZ"] }] }
-  end
-
-  it 'should normalize names with abbreviated genus after cf.' do
-    @parser.parse('Unio cf. U. alba').should == { :all_authors => [],
-      :all_years => [], :canonical_form => "Unio",
-      :genus => { :string => "Unio", :normalized => "UNIO",
-      :phonetized => "UNIA", :authors => [], :years => [],
-      :normalized_authors => [] } }
-  end
-
-  it 'should parse names which broke it before' do
-    ['Parus caeruleus species complex',
-     'Euxoa nr. idahoensis sp. 1clay',
-     'Cetraria islandica ? islandica',
-     'Buteo borealis ? ventralis'].each do |n|
-      res = @parser.parse(n)
-      res.class.should == Hash
-      res.empty?.should be_false
-    end
-  end
-end
-
-
-describe 'Taxamatch::Normalizer' do
-  it 'should normalize  strings' do
-    Taxamatch::Normalizer.normalize('abcd').should == 'ABCD'
-    Taxamatch::Normalizer.normalize('Leœptura').should == 'LEOEPTURA'
-    Taxamatch::Normalizer.normalize('Ærenea').should == 'AERENEA'
-    Taxamatch::Normalizer.normalize('Fallén').should == 'FALLEN'
-    Taxamatch::Normalizer.normalize('Fallé€n').should == 'FALLE?N'
-    Taxamatch::Normalizer.normalize('Fallén привет').should == 'FALLEN ??????'
-    Taxamatch::Normalizer.normalize('Choriozopella trägårdhi').should ==
-      'CHORIOZOPELLA TRAGARDHI'
-    Taxamatch::Normalizer.normalize('×Zygomena').should == 'xZYGOMENA'
-  end
-
-  it 'should normalize words' do
-    Taxamatch::Normalizer.normalize_word('L-3eœ|pt[ura$').should ==
-      'L-3EOEPTURA'
-  end
-end
-
-describe 'Taxamatch::Base' do
-  before(:all) do
-    @tm = Taxamatch::Base.new
-  end
-
-  it 'should get txt tests' do
-    test_file = File.expand_path(File.dirname(__FILE__)) + '/taxamatch_test.txt'
-    read_test_file(test_file, 4) do |y|
-      if y
-        y[2] = y[2] == 'true' ? true : false
-        res = @tm.taxamatch(y[0], y[1], false)
-        # puts "%s, %s, %s, %s" % [y[0], y[1], y[2], y[3]]
-        res['match'].should == y[2]
-        res['edit_distance'].should == y[3].to_i
-      end
-    end
-  end
-
-  it 'should work with names that cannot be parsed' do
-    res = @tm.taxamatch('Quadraspidiotus ostreaeformis MacGillivray, 1921',
-                        'Quadraspidiotus ostreaeformis Curtis)')
-    res = false
-  end
-
-  it 'should compare genera' do
-    # edit distance 1 always match
-    g1 = make_taxamatch_hash 'Plantago'
-    g2 = make_taxamatch_hash 'Plantagon'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => false,
-      'edit_distance' => 1, 'match' => true }
-    # edit_distance above threshold does not math
-    g1 = make_taxamatch_hash 'Plantago'
-    g2 = make_taxamatch_hash 'This shouldnt match'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => false,
-      'match' => false, 'edit_distance' => 4 }
-    # phonetic_match matches
-    g1 = make_taxamatch_hash 'Plantagi'
-    g2 = make_taxamatch_hash 'Plantagy'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => true,
-      'edit_distance' => 1, 'match' => true }
-    @tm.match_genera(g1, g2, :with_phonetic_match => false).should == {
-      'phonetic_match' => false, 'edit_distance' => 1, 'match' => true }
-    # distance 1 in first letter also matches
-    g1 = make_taxamatch_hash 'Xantheri'
-    g2 = make_taxamatch_hash 'Pantheri'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => false,
-      'edit_distance' => 1, 'match' => true }
-    # phonetic match tramps everything
-    g1 = make_taxamatch_hash 'Xaaaaantheriiiiiiiiiiiiiii'
-    g2 = make_taxamatch_hash 'Zaaaaaaaaaaaantheryyyyyyyy'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => true,
-      'edit_distance' => 4, 'match' => true }
-    @tm.match_genera(g1, g2, :with_phonetic_match => false).should == {
-      'phonetic_match' => false, 'edit_distance' => 4, 'match' => false }
-    # same first letter and distance 2 should match
-    g1 = make_taxamatch_hash 'Xaaaantherii'
-    g2 = make_taxamatch_hash 'Xaaaantherrr'
-    @tm.match_genera(g1, g2).should == { 'phonetic_match' => false,
-      'match' => true, 'edit_distance' => 2 }
-    # First letter is the same and distance is 3 should match, no phonetic match
-    g1 = make_taxamatch_hash 'Xaaaaaaaaaaantheriii'
-    g2 = make_taxamatch_hash 'Xaaaaaaaaaaantherrrr'
-    @tm.match_genera(g1, g2).should ==
-      { 'phonetic_match' => false, 'match' => true, 'edit_distance' => 3 }
-    # Should not match if one of words is shorter than 2x edit
-    # distance and distance is 2 or 3
-    g1 = make_taxamatch_hash 'Xant'
-    g2 = make_taxamatch_hash 'Xanthe'
-    @tm.match_genera(g1, g2).should ==  { 'phonetic_match' => false,
-      'match' => false, 'edit_distance' => 2 }
-    # Should not match if edit distance > 3 and no phonetic match
-    g1 = make_taxamatch_hash 'Xantheriiii'
-    g2 = make_taxamatch_hash 'Xantherrrrr'
-    @tm.match_genera(g1, g2).should ==  { 'phonetic_match' => false,
-      'match' => false, 'edit_distance' => 4 }
-  end
-
-  it 'should compare species' do
-    # Exact match
-    s1 = make_taxamatch_hash 'major'
-    s2 = make_taxamatch_hash 'major'
-    @tm.match_species(s1, s2).should ==  { 'phonetic_match' => true,
-      'match' => true, 'edit_distance' => 0 }
-    @tm.match_species(s1, s2, :with_phonetic_match => false).should == {
-      'phonetic_match' => false, 'match' => true, 'edit_distance' => 0 }
-    # Phonetic match always works
-    s1 = make_taxamatch_hash 'xanteriiieeeeeeeeeeeee'
-    s2 = make_taxamatch_hash 'zantereeeeeeeeeeeeeeee'
-    @tm.match_species(s1, s2).should ==  { 'phonetic_match' => true,
-      'match' => true, 'edit_distance' => 4 }
-    @tm.match_species(s1, s2, :with_phonetic_match => false).should ==
-      { 'phonetic_match' => false, 'match' => false, 'edit_distance' => 4 }
-    # Phonetic match works with different endings
-    s1 = make_taxamatch_hash 'majorum'
-    s2 = make_taxamatch_hash 'majoris'
-    @tm.match_species(s1, s2).should ==  {
-      'phonetic_match' => true, 'match' => true, 'edit_distance' => 2 }
-    @tm.match_species(s1, s2, :with_phonetic_match => false).should ==
-      { 'phonetic_match' => false, 'match' => true, 'edit_distance' => 2 }
-    # Distance 4 matches if first 3 chars are the same
-    s1 = make_taxamatch_hash 'majjjjorrrrr'
-    s2 = make_taxamatch_hash 'majjjjoraaaa'
-    @tm.match_species(s1, s2).should ==
-      { 'phonetic_match' => false, 'match' => true, 'edit_distance' => 4 }
-    # Should not match if Distance 4 matches and first 3 chars are not the same
-    s1 = make_taxamatch_hash 'majorrrrr'
-    s2 = make_taxamatch_hash 'marorraaa'
-    @tm.match_species(s1, s2).should == {
-      'phonetic_match' => false, 'match' => false, 'edit_distance' => 4 }
-    # Distance 2 or 3 matches if first 1 char is the same
-    s1 = make_taxamatch_hash 'moooorrrr'
-    s2 = make_taxamatch_hash 'mooooraaa'
-    @tm.match_species(s1, s2).should == { 'phonetic_match' => false,
-      'match' => true, 'edit_distance' => 3 }
-    # Should not match if Distance 2 or 3 and first 1 char is not the same
-    s1 = make_taxamatch_hash 'morrrr'
-    s2 = make_taxamatch_hash 'torraa'
-    @tm.match_species(s1, s2).should == {
-      'phonetic_match' => false, 'match' => false, 'edit_distance' => 3 }
-    # Distance 1 will match anywhere
-    s1 = make_taxamatch_hash 'major'
-    s2 = make_taxamatch_hash 'rajor'
-    @tm.match_species(s1, s2).should == {
-      'phonetic_match' => false, 'match' => true, 'edit_distance' => 1 }
-    # Will not match if distance 3 and length is less then twice
-    # of the edit distance
-    s1 = make_taxamatch_hash 'marrr'
-    s2 = make_taxamatch_hash 'maaaa'
-    @tm.match_species(s1, s2).should == {
-      'phonetic_match' => false, 'match' => false, 'edit_distance' => 3 }
-  end
-
-  it 'should match matches' do
-    # No trobule case
-    gmatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 1 }
-    smatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 1 }
-    @tm.match_matches(gmatch, smatch).should ==
-      { 'phonetic_match' => true, 'edit_distance' => 2, 'match' => true }
-    # Will not match if either genus or sp. epithet dont match
-    gmatch = { 'match' => false,
-      'phonetic_match' => false, 'edit_distance' => 1 }
-    smatch = { 'match' => true,
-      'phonetic_match' => true, 'edit_distance' => 1 }
-    @tm.match_matches(gmatch, smatch).should == { 'phonetic_match' => false,
-      'edit_distance' => 2, 'match' => false }
-    gmatch = { 'match' => true, 'phonetic_match' => true,
-      'edit_distance' => 1 }
-    smatch = { 'match' => false, 'phonetic_match' => false,
-      'edit_distance' => 1 }
-    @tm.match_matches(gmatch, smatch).should == { 'phonetic_match' => false,
-      'edit_distance' => 2, 'match' => false }
-    # Should not match if binomial edit distance > 4
-    # NOTE: EVEN with full phonetic match
-    gmatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 3 }
-    smatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 2 }
-    @tm.match_matches(gmatch, smatch).should == { 'phonetic_match' => true,
-      'edit_distance' => 5, 'match' => false }
-    # Should not have phonetic match if one of the components
-    # does not match phonetically
-    gmatch = { 'match' => true,
-      'phonetic_match' => false, 'edit_distance' => 1 }
-    smatch = { 'match' => true,
-      'phonetic_match' => true, 'edit_distance' => 1 }
-    @tm.match_matches(gmatch, smatch).should == { 'phonetic_match' => false,
-      'edit_distance' => 2, 'match' => true }
-    gmatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 1 }
-    smatch = { 'match' => true,
-      'phonetic_match' => false, 'edit_distance' => 1 }
-    @tm.match_matches(gmatch, smatch).should == { 'phonetic_match' => false,
-      'edit_distance' => 2, 'match' => true }
-    # edit distance should be equal the sum of of edit distances
-    gmatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 2 }
-    smatch = { 'match' => true, 'phonetic_match' => true, 'edit_distance' => 2 }
-    @tm.match_matches(gmatch, smatch).should == {
-      'phonetic_match'=>true, 'edit_distance'=>4, 'match'=>true }
-  end
-
-  it 'should return only boolean values' do
-    @tm.taxamatch("AJLJljljlj", "sls").should_not be_nil
-    @tm.taxamatch('Olsl','a')
-  end
-
-  it "should not match authors from different parts of name" do
-    parser = Taxamatch::Atomizer.new
-    t = Taxamatch::Base.new
-    n1 = parser.parse "Betula Linnaeus"
-    n2 = parser.parse "Betula alba Linnaeus"
-    n3 = parser.parse "Betula alba alba Linnaeus"
-    n4 = parser.parse "Betula alba L."
-    n5 = parser.parse "Betula alba"
-    n6 = parser.parse "Betula olba"
-    n7 = parser.parse "Betula alba Linnaeus alba"
-    n8 = parser.parse "Betula alba Linnaeus alba Smith"
-    n9 = parser.parse "Betula alba Smith alba L."
-    n10 = parser.parse "Betula Linn."
-    # if one authorship is empty, return 0
-    t.match_authors(n1, n5).should == 0
-    t.match_authors(n5, n1).should == 0
-    t.match_authors(n5, n6).should == 0
-    # if authorship matches on different levels ignore
-    t.match_authors(n7, n3).should == 0
-    t.match_authors(n8, n3).should == -1
-    t.match_authors(n2, n8).should == 0
-    t.match_authors(n1, n2).should == 0
-    # match on infraspecies level
-    t.match_authors(n9, n3).should == 1
-    # match on species level
-    t.match_authors(n2, n4).should == 1
-    # match on uninomial level
-    t.match_authors(n1, n10).should == 1
-  end
-
-
-  describe 'Taxamatch::Authmatch' do
-    before(:all) do
-      @am = Taxamatch::Authmatch
-    end
-
-    it 'should calculate score' do
-      res = @am.authmatch(['Linnaeus', 'Muller'], ['L'], [], [1788])
-      res.should == 90
-      res = @am.authmatch(['Linnaeus'],['Kurtz'], [], [])
-      res.should == 0
-      # found all authors, same year
-      res = @am.authmatch(['Linnaeus', 'Muller'],
-                          ['Muller', 'Linnaeus'], [1766], [1766])
-      res.should == 100
-      # all authors, 1 year diff
-      res = @am.authmatch(['Linnaeus', 'Muller'],
-                          ['Muller', 'Linnaeus'], [1767], [1766])
-      res.should == 54
-      # year is not counted in
-      res = @am.authmatch(['Linnaeus', 'Muller'],
-                          ['Muller', 'Linnaeus'], [1767], [])
-      res.should == 94
-      # found all authors on one side, same year
-      res = @am.authmatch(['Linnaeus', 'Muller', 'Kurtz'],
-                          ['Muller', 'Linnaeus'], [1767], [1767])
-      res.should == 91
-      # found all authors on one side, 1 year diff
-      res = @am.authmatch(['Linnaeus', 'Muller', 'Kurtz'],
-                          ['Muller', 'Linnaeus'], [1766], [1767])
-      res.should == 51
-      # found all authors on one side, year does not count
-      res = @am.authmatch(['Linnaeus', 'Muller'],
-                          ['Muller', 'Linnaeus', 'Kurtz'], [1766], [])
-      res.should == 90
-      # found some authors
-      res = @am.authmatch(['Stepanov', 'Linnaeus', 'Muller'],
-                          ['Muller', 'Kurtz', 'Stepanov'], [1766], [])
-      res.should == 67
-      # if year does not match or not present no match for previous case
-      res = @am.authmatch(['Stepanov', 'Linnaeus', 'Muller'],
-                          ['Muller', 'Kurtz', 'Stepanov'], [1766], [1765])
-      res.should == 0
-    end
-
-    it 'should compare years' do
-      @am.compare_years([1882],[1880]).should == 2
-      @am.compare_years([1882],[]).should == nil
-      @am.compare_years([],[]).should == 0
-      @am.compare_years([1788,1798], [1788,1798]).should be_nil
-    end
-
-    it 'should remove duplicate authors' do
-      # Li submatches Linnaeus and it its size 3 is big enought to remove
-      # Linnaeus Muller is identical
-      res = @am.remove_duplicate_authors(['Lin', 'Muller'],
-                                         ['Linnaeus', 'Muller'])
-      res.should == [[], []]
-      # same in different order
-      res = @am.remove_duplicate_authors(['Linnaeus', 'Muller'],
-                                         ['Linn', 'Muller'])
-      res.should == [[], []]
-      # auth Li submatches Linnaeus, but Li size less then 3
-      # required to remove Linnaeus
-      res = @am.remove_duplicate_authors(['Dem', 'Li'],
-                                         ['Linnaeus', 'Stepanov'])
-      res.should == [["Dem"], ["Linnaeus", "Stepanov"]]
-      # fuzzy match
-      res = @am.remove_duplicate_authors(['Dem', 'Lennaeus'],
-                                         ['Linnaeus', 'Stepanov'])
-      res.should == [["Dem"], ["Stepanov"]]
-      res = @am.remove_duplicate_authors(['Linnaeus', 'Muller'],
-                                         ['L', 'Kenn'])
-      res.should == [['Linnaeus', 'Muller'], ['Kenn']]
-      res = @am.remove_duplicate_authors(['Linnaeus', 'Muller'],
-                                         ['Muller', 'Linnaeus', 'Kurtz'])
-      res.should == [[],['Kurtz']]
-    end
-
-    it 'should fuzzy match authors' do
-      res = @am.fuzzy_match_authors('L', 'Muller')
-      res.should be_false
-    end
-
-  end
-
-end

data/spec/taxamatch_test.txt

@@ -1,46 +0,0 @@
-###
-#
-# Tests for string comparison by taxamatch algorithm
-# name1|name2|match|edit_distance
-#
-##
-# Comparing uninomials
-Pomatomus|Pomatomas|true|1
-Pomatomus L.|Pomatomas Linn.|true|1
-Pomatomus Ber|Pomatomas Linn|false|1
-Pomatomus L. 1758|Pomatomus Linn. 1800|false|0
-Patella|Abbella|false|3
-
-## additional authorship should match
-Puma concolor|Puma concolor L.|true|0
-#
-## one-letter misspeling in species epithet should match
-Puma concolor|Puma cancolor|true|1
-#
-Pomatomus saltatrix|Pomatomus saltratix|true|2
-Pomatomus saltator|Pomatomus saltatrix|false|3 #!!!
-#
-Loligo pealeii|Loligo plei|false|3
-#
-## different authors should not match
-Puma concolor Linnaeus|Puma concolor Kurtz|false|0
-#
-##real life examples
-Biatora borealis|Bactra borealis Diakonoff 1964|false|3
-#
-Homo sapien|Homo sapiens|true|1
-Homo sapiens Linnaeus|Homo sapens (Linn. 1758) |true|1
-Homo sapiens Mozzherin|Homo sapiens Linneaus|false|0
-#
-Quinqueloculina punctata|Quinqueloculina punctata d'Orbigny 1905|true|0
-Pomatomus saltator (Linnaeus, 1766)|Pomatomus saltatrix (Linnaeus, 1766)|true|0|3
-#
-#Trinomial names
-Homo sapiens stupidus|Homo spiens stupidus|true|1
-Pomatomus saltator saltator L. 1758|Pomatomus saltator var. saltatror L. 1758|true|1
-Pomatomus saltator L. 1758|Pomatomus saltator var. saltatror L. 1758|false|5
-Pomatomus saltator saltator saltatorische|Pomatomus saltator soltator|true|1
-
-
-
-