text_detector 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a7d68797d530b617238813bcadb52cf8649d13f6
-  data.tar.gz: f615523b8676171aebb035c2d4432a3c596f2126
+  metadata.gz: 315dfa048ec3b6dd195976900bb573407cbfdfc9
+  data.tar.gz: 2441e251ec922dc7900907fab919a068f1dbd614
 SHA512:
-  metadata.gz: 1b0263082fe4138421f104844389afdf78aef50b864d6dbd7c2021176296da7f8ec86e41241bc4a80ff4d461de0fb38c8dcc5bfc3ff6ca8dc6eaae885c8bd274
-  data.tar.gz: 0c542dde4eff06e4a5a80be840acbde7e9ac3b061e03e84aea633a4b28fb032fa1c1e056d1b84d45f02ddaab79640408b820ddbfc532571de306f3f3923785cc
+  metadata.gz: e31c2fe0028629483e7dc6079c16314217ef15c471289b9ffedc8030c3ea807db09fc55905080eec18f196de2009f1b9615c0e7770e9e946bd802d4ea7b38d18
+  data.tar.gz: f1134bc00b6cd5261d566b545c0ea9b2c108f6c36c1b76c860f2ecab935f5e1d4aaf384db662d9deb65149b09781a50709e60bbdaa231bf608a0d37ace52a547

data/README.md

@@ -3,9 +3,7 @@
 
 # TextDetector
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/text_detector`. To experiment with that code, run `bin/console` for an interactive prompt.
-
-TODO: Delete this and the text above, and describe your gem
+This is an experimental implementation for detecting text from document.
 
 ## Installation
 
@@ -25,7 +23,23 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+See also `bin/benchmark` and `examples/`.
+
+### Regexp
+
+```ruby
+require 'text_detector'
+regexp_detector = TextDetector.factory(:regexp, open('dictionary.txt'))
+regexp_detector.detect('The detector detects NG word from this document. The dictionary has many NG words.')
+```
+
+### Like Boyer-Moore String Search Algorithm
+
+```ruby
+require 'text_detector'
+simple_detector = TextDetector.factory(:simple, open('dictionary.txt'))
+simple_detector.detect('The detector detects NG word from this document. The dictionary has many NG words.')
+```
 
 ## Development
 

data/examples/regexp.rb

@@ -0,0 +1,15 @@
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+
+require 'stringio'
+require 'text_detector'
+
+dictionary = StringIO.new(<<EOF)
+NG_A
+NG_B
+NG_C
+EOF
+
+regexp_detector = TextDetector.factory(:regexp, dictionary)
+
+p regexp_detector.detect('This document not include NG words.')
+p regexp_detector.detect('This document include NG words: NG_A')

data/examples/simple.rb

@@ -0,0 +1,15 @@
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+
+require 'stringio'
+require 'text_detector'
+
+dictionary = StringIO.new(<<EOF)
+NG_A
+NG_B
+NG_C
+EOF
+
+simple_detector = TextDetector.factory(:simple, dictionary)
+
+p simple_detector.detect('This document not include NG words.')
+p simple_detector.detect('This document include NG words: NG_A')

data/lib/text_detector/dictionary/file.rb

@@ -20,15 +20,14 @@ module TextDetector
         @dictionary = Set.new
         @depth = []
 
-        open(dictionary) do |input|
-          input.each_line do |line|
-            text = TextDetector.normalize(line.chomp)
-            next if text.size == 0
-
-            @dictionary << text
-            @depth << text.size
-          end
+        dictionary.each_line do |line|
+          text = TextDetector.normalize(line.chomp)
+          next if text.size == 0
+
+          @dictionary << text
+          @depth << text.size
         end
+
         @depth = @depth.sort.uniq
       end
     end

data/lib/text_detector/dictionary.rb

@@ -1,10 +1,11 @@
+require 'stringio'
 require_relative 'dictionary/file'
 
 module TextDetector
   module Dictionary
     def self.factory(dictionary)
       case dictionary
-      when ::File
+      when ::IO, ::StringIO
         TextDetector::Dictionary::File.new(dictionary)
       end
     end

data/lib/text_detector/version.rb

@@ -1,3 +1,3 @@
 module TextDetector
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

data/text_detector.gemspec

@@ -9,8 +9,8 @@ Gem::Specification.new do |spec|
   spec.authors       = ["koshigoe"]
   spec.email         = ["koshigoeb@gmail.com"]
 
-  spec.summary       = %q{Text detector.}
-  spec.description   = %q{Text detector}
+  spec.summary       = %q{This is an experimental implementation for detecting text from document.}
+  spec.description   = %q{This is an experimental implementation for detecting text from document.}
   spec.homepage      = "https://github.com/koshigoe/text_detector"
   spec.license       = "MIT"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: text_detector
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - koshigoe
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-03-26 00:00:00.000000000 Z
+date: 2015-03-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,7 +52,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Text detector
+description: This is an experimental implementation for detecting text from document.
 email:
 - koshigoeb@gmail.com
 executables: []
@@ -68,6 +68,8 @@ files:
 - bin/benchmark
 - bin/console
 - bin/setup
+- examples/regexp.rb
+- examples/simple.rb
 - lib/text_detector.rb
 - lib/text_detector/detector.rb
 - lib/text_detector/detector/base.rb
@@ -102,5 +104,5 @@ rubyforge_project:
 rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
-summary: Text detector.
+summary: This is an experimental implementation for detecting text from document.
 test_files: []