ivanvc-dictionary 0.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +2 -0
- data/README.rdoc +13 -0
- data/Rakefile +45 -0
- data/VERSION +1 -0
- data/bin/anagram_extractor +10 -0
- data/extras/3k_english.txt +3000 -0
- data/extras/capitalized_english.txt +7 -0
- data/extras/english.txt +7 -0
- data/lib/dictionary/anagram_extractor.rb +98 -0
- data/lib/dictionary/error.rb +25 -0
- data/lib/dictionary.rb +26 -0
- data/spec/anagram_extactor_spec.rb +94 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- metadata +90 -0
data/extras/english.txt
ADDED
@@ -0,0 +1,98 @@
|
|
1
|
+
module Dictionary
|
2
|
+
# The class AnagramExtactor, contains the implementation to get all the anagrams
|
3
|
+
# from a dictionary provided text file.
|
4
|
+
#
|
5
|
+
# @example Example Usage
|
6
|
+
# extractor = AnagramExtractor.new('my_dictionary.txt')
|
7
|
+
# extractor.extract!
|
8
|
+
# extractor.export('anagrams.txt')
|
9
|
+
class AnagramExtractor
|
10
|
+
# Holds the dictionary file.
|
11
|
+
attr_reader :file
|
12
|
+
# Holds the anagrams extracted.
|
13
|
+
attr_reader :anagrams
|
14
|
+
|
15
|
+
# An AnagramExtactor instance should be initialized with the location of the file to scan.
|
16
|
+
#
|
17
|
+
# @raise [Dictionary::Error::FileNotFoundError] if the provided file is not found.
|
18
|
+
# @param [String, Pathname] file the location of the file.
|
19
|
+
def initialize(file=nil)
|
20
|
+
self.file = file if file
|
21
|
+
end
|
22
|
+
|
23
|
+
# Replaces the dictionary file. Also resets the dictionary and the extracted anagrams.
|
24
|
+
#
|
25
|
+
# @raise [Dictionary::Error::FileNotFoundError] if the provided file is not found.
|
26
|
+
# @param [String, Pathname] file the location of the file.
|
27
|
+
def file=(file)
|
28
|
+
reset_dictionaries
|
29
|
+
@file = get_full_location file
|
30
|
+
raise Error::FileNotFoundError unless File.exists?(@file)
|
31
|
+
end
|
32
|
+
|
33
|
+
# Extracts the anagrams from the provided file.
|
34
|
+
#
|
35
|
+
# @return [Array] the anagram list.
|
36
|
+
def extract!
|
37
|
+
reset_dictionaries
|
38
|
+
File.read(@file).each_line do |word|
|
39
|
+
word = word.strip
|
40
|
+
has_an_anagram = anagram_for? word
|
41
|
+
@anagrams += [word, has_an_anagram] if has_an_anagram
|
42
|
+
@dictionary << word
|
43
|
+
end
|
44
|
+
@anagrams
|
45
|
+
end
|
46
|
+
|
47
|
+
# Saves the anagram dictionary to a provided file.
|
48
|
+
#
|
49
|
+
# @param [String, Pathname] location the location of the file to write.
|
50
|
+
# @raise [Dictionary::Error::FileAlreadyExistsError] if the file already exists.
|
51
|
+
# @raise [Dictionary::Error::PathNotFoundError] if the export path does not exists.
|
52
|
+
# @return [String] the full path to the exported file.
|
53
|
+
def export(location)
|
54
|
+
location = get_full_location location
|
55
|
+
@anagrams ||= []
|
56
|
+
|
57
|
+
raise Dictionary::Error::FileAlreadyExistsError if File.exists? location
|
58
|
+
unless File.directory? File.dirname(location)
|
59
|
+
raise Dictionary::Error::PathNotFoundError
|
60
|
+
end
|
61
|
+
File.open(location, 'w') { |file| file.puts @anagrams.join("\n") }
|
62
|
+
location
|
63
|
+
end
|
64
|
+
|
65
|
+
private
|
66
|
+
# Will return if a word has an anagram in the currently extracted dictionary.
|
67
|
+
#
|
68
|
+
# @private
|
69
|
+
# @param [String] word the word to check
|
70
|
+
# @return [nil, String] nil if the dictionary is empty or, there are no anagrams for
|
71
|
+
# this word. Else, the matching word.
|
72
|
+
def anagram_for?(word)
|
73
|
+
word_letters = word.downcase.scan(/\w/).sort
|
74
|
+
@dictionary.find do |test_word|
|
75
|
+
test_word_letters = test_word.downcase.scan(/\w/)
|
76
|
+
test_word_letters.size == word_letters.size &&
|
77
|
+
test_word_letters.sort == word_letters
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
# Resets the dictionary and the anagrams.
|
82
|
+
#
|
83
|
+
# @return [nil]
|
84
|
+
def reset_dictionaries
|
85
|
+
@dictionary = []
|
86
|
+
@anagrams = []
|
87
|
+
end
|
88
|
+
|
89
|
+
# Standardizes the location of the passed file.
|
90
|
+
#
|
91
|
+
# @param [String, Pathname] file the file to scan.
|
92
|
+
# @return [String] the standardized location.
|
93
|
+
def get_full_location(file)
|
94
|
+
file = "#{Dir.pwd}/#{file}" unless Pathname.new(file).absolute?
|
95
|
+
File.expand_path(file)
|
96
|
+
end
|
97
|
+
end
|
98
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# Module for Exceptions from the Dictionary Module.
|
2
|
+
module Dictionary::Error
|
3
|
+
# A FileNotFoundError may be raised by an AnagramExtactor class if the source file is not
|
4
|
+
# found.
|
5
|
+
#
|
6
|
+
# @see Dictionary::AnagramExtractor#initialize
|
7
|
+
# @see Dictionary::AnagramExtractor#file=
|
8
|
+
class FileNotFoundError < StandardError
|
9
|
+
end
|
10
|
+
|
11
|
+
# A PathNotFoundError may be raised by an AnagramExtactor class if the path to a file is not
|
12
|
+
# found.
|
13
|
+
#
|
14
|
+
# @see Dictionary::AnagramExtractor#export
|
15
|
+
# @see Dictionary::AnagramExtractor#file=
|
16
|
+
class PathNotFoundError < StandardError
|
17
|
+
end
|
18
|
+
|
19
|
+
# A FileAlreadyExistsError may be raised by an AnagramExtactor class if the file already exists.
|
20
|
+
#
|
21
|
+
# @see Dictionary::AnagramExtractor#export
|
22
|
+
# @see Dictionary::AnagramExtractor#file=
|
23
|
+
class FileAlreadyExistsError < StandardError
|
24
|
+
end
|
25
|
+
end
|
data/lib/dictionary.rb
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'pathname'
|
2
|
+
|
3
|
+
# Module that contains the AnagramExtractor.
|
4
|
+
module Dictionary
|
5
|
+
base_dir = File.expand_path(File.dirname(__FILE__) + '/dictionary') + '/'
|
6
|
+
autoload :AnagramExtractor, base_dir + 'anagram_extractor.rb'
|
7
|
+
autoload :Error, base_dir + 'error.rb'
|
8
|
+
|
9
|
+
# Extracts the anagrams from a file, and exports the results.
|
10
|
+
#
|
11
|
+
# @param [String, Pathname] file the location of the dictionary
|
12
|
+
# @param [String, Pathname] export_location the export location for the results.
|
13
|
+
# @return [String] The result of the extraction.
|
14
|
+
def self.extract_anagrams(file, export_location)
|
15
|
+
extractor = AnagramExtractor.new(file)
|
16
|
+
extractor.extract!
|
17
|
+
extractor.export(export_location)
|
18
|
+
"Exported anagram list to #{export_location}."
|
19
|
+
rescue Error::FileNotFoundError
|
20
|
+
"The source file seems to be missing."
|
21
|
+
rescue Error::PathNotFoundError
|
22
|
+
"The export path does not exist."
|
23
|
+
rescue Error::FileAlreadyExistsError
|
24
|
+
"The export file already exists."
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,94 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
|
3
|
+
describe Dictionary::AnagramExtractor do
|
4
|
+
|
5
|
+
before(:each) do
|
6
|
+
@extractor = Dictionary::AnagramExtractor.new
|
7
|
+
end
|
8
|
+
|
9
|
+
describe ".file=" do
|
10
|
+
|
11
|
+
it "should raise an error if file not found" do
|
12
|
+
lambda { @extractor.file = 'extras/notfound.txt' }.should\
|
13
|
+
raise_error(Dictionary::Error::FileNotFoundError)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should set it to the absolute path" do
|
17
|
+
@extractor.file = 'extras/english.txt'
|
18
|
+
Pathname.new(@extractor.file).should be_absolute
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should clear the anagram list" do
|
22
|
+
@extractor.file = 'extras/english.txt'
|
23
|
+
@extractor.extract!
|
24
|
+
|
25
|
+
lambda { @extractor.file = 'extras/english.txt' }.should change(@extractor, :anagrams)
|
26
|
+
@extractor.anagrams.should be_empty
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
|
31
|
+
describe ".extract!" do
|
32
|
+
|
33
|
+
before(:each) do
|
34
|
+
@extractor.file = 'extras/english.txt'
|
35
|
+
end
|
36
|
+
|
37
|
+
it "should return an Array" do
|
38
|
+
@extractor.extract!.should be_an_instance_of(Array)
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should return four matches" do
|
42
|
+
@extractor.extract!.size.should == 4
|
43
|
+
end
|
44
|
+
|
45
|
+
it "should return four matches even if words are capitalized" do
|
46
|
+
@extractor.file = 'extras/capitalized_english.txt'
|
47
|
+
@extractor.extract!.size.should == 4
|
48
|
+
end
|
49
|
+
|
50
|
+
it "should contain mary and army as anagrams" do
|
51
|
+
@extractor.extract!.should include('mary', 'army')
|
52
|
+
end
|
53
|
+
|
54
|
+
end
|
55
|
+
|
56
|
+
describe "export" do
|
57
|
+
before(:each) do
|
58
|
+
@location = "#{Dir.pwd}/example.txt"
|
59
|
+
end
|
60
|
+
|
61
|
+
after(:each) do
|
62
|
+
FileUtils.rm_rf @location
|
63
|
+
end
|
64
|
+
|
65
|
+
it "should raise an error if the output file already exists" do
|
66
|
+
lambda { @extractor.export 'extras/english.txt' }.should\
|
67
|
+
raise_error(Dictionary::Error::FileAlreadyExistsError)
|
68
|
+
end
|
69
|
+
|
70
|
+
it "should raise an error if the path of the file does not exist" do
|
71
|
+
lambda { @extractor.export 'chunky/bacon.txt' }.should\
|
72
|
+
raise_error(Dictionary::Error::PathNotFoundError)
|
73
|
+
end
|
74
|
+
|
75
|
+
it "should return the location of the output" do
|
76
|
+
@extractor.export('example.txt').should == @location
|
77
|
+
end
|
78
|
+
|
79
|
+
it "should write a file" do
|
80
|
+
@extractor.export 'example.txt'
|
81
|
+
File.exists?(@location).should be_true
|
82
|
+
end
|
83
|
+
|
84
|
+
it "should contain all the lines in @anagrams" do
|
85
|
+
@extractor.file = 'extras/english.txt'
|
86
|
+
@extractor.extract!
|
87
|
+
@extractor.export 'example.txt'
|
88
|
+
|
89
|
+
File.read(@location).split("\n").size.should == 4
|
90
|
+
end
|
91
|
+
|
92
|
+
end
|
93
|
+
|
94
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,90 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ivanvc-dictionary
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
version: 0.0.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- "Iv\xC3\xA1n Vald\xC3\xA9s (@ivanvc)"
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-07-09 00:00:00 -05:00
|
18
|
+
default_executable: anagram_extractor
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rspec
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 1
|
29
|
+
- 2
|
30
|
+
- 9
|
31
|
+
version: 1.2.9
|
32
|
+
type: :development
|
33
|
+
version_requirements: *id001
|
34
|
+
description: Dictionary
|
35
|
+
email: iv@nvald.es
|
36
|
+
executables:
|
37
|
+
- anagram_extractor
|
38
|
+
extensions: []
|
39
|
+
|
40
|
+
extra_rdoc_files:
|
41
|
+
- README.rdoc
|
42
|
+
files:
|
43
|
+
- .document
|
44
|
+
- .gitignore
|
45
|
+
- README.rdoc
|
46
|
+
- Rakefile
|
47
|
+
- VERSION
|
48
|
+
- bin/anagram_extractor
|
49
|
+
- extras/3k_english.txt
|
50
|
+
- extras/capitalized_english.txt
|
51
|
+
- extras/english.txt
|
52
|
+
- lib/dictionary.rb
|
53
|
+
- lib/dictionary/anagram_extractor.rb
|
54
|
+
- lib/dictionary/error.rb
|
55
|
+
- spec/anagram_extactor_spec.rb
|
56
|
+
- spec/spec.opts
|
57
|
+
- spec/spec_helper.rb
|
58
|
+
has_rdoc: true
|
59
|
+
homepage: http://github.com/ivanvc/dictionary
|
60
|
+
licenses: []
|
61
|
+
|
62
|
+
post_install_message:
|
63
|
+
rdoc_options:
|
64
|
+
- --charset=UTF-8
|
65
|
+
require_paths:
|
66
|
+
- lib
|
67
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - ">="
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
segments:
|
72
|
+
- 0
|
73
|
+
version: "0"
|
74
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
75
|
+
requirements:
|
76
|
+
- - ">="
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
segments:
|
79
|
+
- 0
|
80
|
+
version: "0"
|
81
|
+
requirements: []
|
82
|
+
|
83
|
+
rubyforge_project:
|
84
|
+
rubygems_version: 1.3.6
|
85
|
+
signing_key:
|
86
|
+
specification_version: 3
|
87
|
+
summary: Dictionary
|
88
|
+
test_files:
|
89
|
+
- spec/anagram_extactor_spec.rb
|
90
|
+
- spec/spec_helper.rb
|