lemmatizer 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3962f3411b45a381c605ddd975f34bfad4055d8bc63bfdf385ed9341f395f5c4
-  data.tar.gz: 7dd90d196fda8c109f5847a7fafb0917f99c6f508dd0488cc33d60ced2c435e6
+  metadata.gz: 9ffb812c39d3601bb86da6d6e44c8375cc8078bfb88089a8357c14c92473209a
+  data.tar.gz: fe6a030e331e8138231dfaf48b136bf5dc7e4e8be40a8457664bdd8bf2b8f6b5
 SHA512:
-  metadata.gz: eef23c892d9d9544637196fa61dde985fe440308157fd05f0202511723f3c84585b294cea6d827b4652a1473ff89f2b1f7a4b242aed17ae97c1700ffdee302e6
-  data.tar.gz: 1e95bb9907884803e9413251df611bd999d698baf2a6c709e5eb8f4ccbe9b272894ce179931c3609fa50e37fcac08f444cc10e05602312362b72f99fb871c77f
+  metadata.gz: f2505986c5b0919c7691fbec86afc814df9567e23024f68e9c7f1daa0afd1485534fcd700aa131146d12f8d7dbfb95fbcbce798fc37e4408afd7976d077d750f
+  data.tar.gz: 3e9e7f6289d906b2e4f984ccf285e24024de933b7aa9065f99559f057392299a69696ab82706624781f780d925eb6f1565f629462ec9a1f98fadfc3bea8810ba

data/README.md

@@ -41,25 +41,33 @@ p lem.lemma("MacBooks", :noun) # => "MacBooks"
 p lem.lemma("higher", :adj) # => "higher" not "high"!
 
 # The above has to happen because "higher" is itself an entry word listed in dict/index.adj .
-# Modify dict/index.{noun|verb|adj|adv} if necessary.
+# To fix this, modify the original dict directly (lib/dict/index.{noun|verb|adj|adv}) 
+# or supply with custom dict files (recommended).
 ```
 
 Supplying with user dict
 -----------
 ```ruby
-# You can supply files with additional dict data consisting of lines in the format of <pos>\s+<form>\s+<lemma>.
-# The data in user supplied files overrides the preset data
+# You can supply custom dict files consisting of lines in the format of <pos>\s+<form>\s+<lemma>.
+# The data in user supplied files overrides the preset data. Here's the sample. 
 
------- sample.dict.txt -----
-adj   higher   high
-adj   highest  high
-noun  MacBooks MacBook
-----------------------------
+# --- sample.dict.txt (don't include hash symbol on the left) ---
+# adj   higher   high
+# adj   highest  high
+# noun  MacBooks MacBook
+# ---------------------------------------------------------------
 
 lem = Lemmatizer.new("sample.dict.txt")
-p lem.lemma("higher", :adj)    # => "high"
-p lem.lemma("highest", :adj)   # => "high"
-p lem.lemma("MacBooks", :noun  # => "MacBook"
+# => 3 lexical items added from dict file provided
+
+p lem.lemma("higher", :adj)     # => "high"
+p lem.lemma("highest", :adj)    # => "high"
+p lem.lemma("MacBooks", :noun)  # => "MacBook"
+
+# The argument to Lemmatizer.new can be either of the following:
+# 1) a path string to a dict file (e.g. "/path/to/dict.txt")
+# 2) an array of paths to dict files (e.g. ["./dict/noun.txt", "./dict/verb.txt"])
+
 ```
 
 Author

data/lib/lemmatizer/lemmatizer.rb

@@ -68,7 +68,11 @@ module Lemmatizer
         load_wordnet_files(pos, pair[0], pair[1])
       end
 
-      load_provided_dict(dict) if dict
+      if dict
+        [dict].flatten.each do |d|
+          load_provided_dict(d)
+        end
+      end
     end
 
     def lemma(form, pos = nil)
@@ -182,7 +186,7 @@ module Lemmatizer
           end
         end
       end
-      puts "#{num_lex_added} lexical items added from dict file provided"
+      puts "#{num_lex_added} items added from #{File.basename dict}"
     end
   end
 end

data/lib/lemmatizer/version.rb

@@ -1,3 +1,3 @@
 module Lemmatizer
-  VERSION = '0.2.0'
+  VERSION = '0.2.1'
 end

data/spec/lemmatizer_spec.rb

@@ -5,8 +5,10 @@ describe 'Lemmatizer' do
 
   before(:all) do
     @lemmatizer = Lemmatizer.new
-    user_data = File.join(File.dirname(__FILE__), "user.dict.txt")
-    @lemmatizer_with_userdata = Lemmatizer.new(user_data)
+    user_data1 = File.join(File.dirname(__FILE__), "user.dict1.txt")
+    user_data2 = File.join(File.dirname(__FILE__), "user.dict2.txt")
+    @lemmatizer_single_userdict = Lemmatizer.new(user_data1)
+    @lemmatizer_multiple_userdicts = Lemmatizer.new([user_data1, user_data2])
   end
 
   describe '#lemma' do
@@ -75,19 +77,27 @@ describe 'Lemmatizer' do
       expect(result_n2).not_to eq('MacBook')
     end
 
-    it 'can load user dict that overrides presets' do
+    it 'can load a user dict that overrides presets' do
       # 'MacBooks' -> 'MacBook'
-      result_u1 = @lemmatizer_with_userdata.lemma('MacBooks', :noun)
+      result_u1 = @lemmatizer_single_userdict.lemma('MacBooks', :noun)
       expect(result_u1).to eq('MacBook')
+      result_u2 = @lemmatizer_single_userdict.lemma('crying', :verb)
+      expect(result_u2).to eq('cry')
+    end
+
+    it 'can load uder dicts that override presets' do
+      # 'MacBooks' -> 'MacBook'
+      result_ud1 = @lemmatizer_multiple_userdicts.lemma('MacBooks', :noun)
+      expect(result_ud1).to eq('MacBook')
       # 'higher' -> 'high'
-      result_u2 = @lemmatizer_with_userdata.lemma('higher', :adj)
-      expect(result_u2).to eq('high')
+      result_ud2 = @lemmatizer_multiple_userdicts.lemma('higher', :adj)
+      expect(result_ud2).to eq('high')
       # 'highest' -> 'high'
-      result_u3 = @lemmatizer_with_userdata.lemma('higher')
-      expect(result_u3).to eq('high')
+      result_ud3 = @lemmatizer_multiple_userdicts.lemma('higher')
+      expect(result_ud3).to eq('high')
       # check if (unoverridden) preset data is kept intact
-      result_u4 = @lemmatizer_with_userdata.lemma('crying', :verb)
-      expect(result_u4).to eq('cry')
+      result_ud4 = @lemmatizer_multiple_userdicts.lemma('crying', :verb)
+      expect(result_ud4).to eq('cry')
     end
   end
 end

data/spec/user.dict1.txt

@@ -0,0 +1,3 @@
+noun MacBooks MacBook
+noun iPhones  iPhone
+noun iPads    iPad

data/spec/user.dict2.txt

@@ -0,0 +1,2 @@
+adj higher  high
+adj highest high

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lemmatizer
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Yoichiro Hasebe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-02-15 00:00:00.000000000 Z
+date: 2019-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -53,7 +53,8 @@ files:
 - lib/lemmatizer/version.rb
 - spec/lemmatizer_spec.rb
 - spec/spec_helper.rb
-- spec/user.dict.txt
+- spec/user.dict1.txt
+- spec/user.dict2.txt
 homepage: http://github.com/yohasebe/lemmatizer
 licenses:
 - MIT
@@ -80,4 +81,5 @@ summary: Englsh lemmatizer in Ruby
 test_files:
 - spec/lemmatizer_spec.rb
 - spec/spec_helper.rb
-- spec/user.dict.txt
+- spec/user.dict1.txt
+- spec/user.dict2.txt

data/spec/user.dict.txt

@@ -1,5 +0,0 @@
-n MacBooks MacBook
-n iPhones iPhone
-n iPads iPad
-adj higher high
-adj highest high