dictionaries 0.3.81
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +354 -0
- data/bin/dictionaries +7 -0
- data/bin/unique_words_in_this_file +7 -0
- data/dictionaries.gemspec +84 -0
- data/doc/README.gen +292 -0
- data/doc/todo/todo.md +8 -0
- data/lib/dictionaries/ask_english_word.rb +141 -0
- data/lib/dictionaries/ask_italian_word.rb +84 -0
- data/lib/dictionaries/base/base.rb +78 -0
- data/lib/dictionaries/class/class.rb +903 -0
- data/lib/dictionaries/commandline/parse_commandline.rb +85 -0
- data/lib/dictionaries/constants/constants.rb +134 -0
- data/lib/dictionaries/gui/tk/README.md +2 -0
- data/lib/dictionaries/gui/tk/dictionary.rb +85 -0
- data/lib/dictionaries/gui/universal_widgets/dictionary/dictionary.rb +516 -0
- data/lib/dictionaries/helper_module/helper_module.rb +60 -0
- data/lib/dictionaries/project/project.rb +36 -0
- data/lib/dictionaries/require_project/require_project.rb +14 -0
- data/lib/dictionaries/sinatra/app.rb +123 -0
- data/lib/dictionaries/sinatra/english_to_german.rb +84 -0
- data/lib/dictionaries/spell_checker/README.md +5 -0
- data/lib/dictionaries/spell_checker/spell_checker.rb +133 -0
- data/lib/dictionaries/statistics/statistics.rb +59 -0
- data/lib/dictionaries/toplevel_methods/e.rb +16 -0
- data/lib/dictionaries/toplevel_methods/english_to_german.rb +31 -0
- data/lib/dictionaries/toplevel_methods/has_key.rb +32 -0
- data/lib/dictionaries/toplevel_methods/is_on_roebe.rb +16 -0
- data/lib/dictionaries/toplevel_methods/main_file.rb +88 -0
- data/lib/dictionaries/toplevel_methods/misc.rb +231 -0
- data/lib/dictionaries/toplevel_methods/module_methods.rb +9 -0
- data/lib/dictionaries/toplevel_methods/show_help.rb +31 -0
- data/lib/dictionaries/version/version.rb +19 -0
- data/lib/dictionaries/yaml/chinese.yml +25 -0
- data/lib/dictionaries/yaml/danish.yml +4 -0
- data/lib/dictionaries/yaml/deutsche_fremdw/303/266rter.yml +1 -0
- data/lib/dictionaries/yaml/dutch.yml +3 -0
- data/lib/dictionaries/yaml/english.yml +3263 -0
- data/lib/dictionaries/yaml/farsi.yml +8 -0
- data/lib/dictionaries/yaml/finnish.yml +2 -0
- data/lib/dictionaries/yaml/italian.yml +532 -0
- data/lib/dictionaries/yaml/japanese.yml +15 -0
- data/lib/dictionaries/yaml/norwegian.yml +26 -0
- data/lib/dictionaries/yaml/polish.yml +2 -0
- data/lib/dictionaries/yaml/portugese.yml +41 -0
- data/lib/dictionaries/yaml/russian.yml +10 -0
- data/lib/dictionaries/yaml/spanish.yml +147 -0
- data/lib/dictionaries/yaml/swedish.yml +104 -0
- data/lib/dictionaries.rb +1 -0
- data/test/translation_example.html +2758 -0
- metadata +211 -0
@@ -0,0 +1,231 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'dictionaries/toplevel_methods/misc.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
module Dictionaries
|
8
|
+
|
9
|
+
require 'yaml'
|
10
|
+
|
11
|
+
begin
|
12
|
+
require 'save_file/module'
|
13
|
+
rescue LoadError; end
|
14
|
+
|
15
|
+
require 'dictionaries/constants/constants.rb'
|
16
|
+
require 'dictionaries/toplevel_methods/main_file.rb'
|
17
|
+
require 'dictionaries/toplevel_methods/has_key.rb'
|
18
|
+
|
19
|
+
# ========================================================================= #
|
20
|
+
# === Dictionaries.english_key_values?
|
21
|
+
# ========================================================================= #
|
22
|
+
def self.english_key_values?(
|
23
|
+
this_file = Dictionaries.main_file?
|
24
|
+
)
|
25
|
+
dataset = YAML.load_file(this_file)
|
26
|
+
return dataset
|
27
|
+
end
|
28
|
+
|
29
|
+
# ========================================================================= #
|
30
|
+
# === Dictionaries.create_javascript_file
|
31
|
+
#
|
32
|
+
# This method will create a .js file, into the current working directory.
|
33
|
+
#
|
34
|
+
# Invocation example:
|
35
|
+
#
|
36
|
+
# require 'dictionaries'; result = Dictionaries.create_javascript_file
|
37
|
+
#
|
38
|
+
# ========================================================================= #
|
39
|
+
def self.create_javascript_file(
|
40
|
+
into = File.absolute_path('dictionary.js'),
|
41
|
+
dataset = english_key_values?
|
42
|
+
)
|
43
|
+
what = <<-EOF
|
44
|
+
function return_english_dictionary() {
|
45
|
+
|
46
|
+
var dictionary = {};
|
47
|
+
|
48
|
+
EOF
|
49
|
+
what = what.dup
|
50
|
+
dataset.each {|key, value|
|
51
|
+
value = value.gsub(/"/,'\"') if value.include?('"')
|
52
|
+
what << " dictionary[\"#{key}\"] = \"#{value}\";\n"
|
53
|
+
}
|
54
|
+
what << " return dictionary;\n"
|
55
|
+
what << "}\n"
|
56
|
+
SaveFile.write_what_into(what, into)
|
57
|
+
return into
|
58
|
+
end
|
59
|
+
|
60
|
+
# ========================================================================= #
|
61
|
+
# === Dictionaries.generate_pdf_file
|
62
|
+
#
|
63
|
+
# This method can be used to generate a .pdf file.
|
64
|
+
# ========================================================================= #
|
65
|
+
def self.generate_pdf_file(
|
66
|
+
use_this_font = 'Courier', # Helvetica-Bold' # #'Times-Roman'
|
67
|
+
use_this_font_size = 12
|
68
|
+
)
|
69
|
+
require 'prawn'
|
70
|
+
::Prawn::Fonts::AFM.hide_m17n_warning = true
|
71
|
+
right_arrow = ' -> '.dup.encode(
|
72
|
+
'Windows-1252', invalid: :replace, undef: :replace, replace: ''
|
73
|
+
)
|
74
|
+
dataset = YAML.load_file(Dictionaries.file_english)
|
75
|
+
into = File.absolute_path('english_to_german_dictionary.pdf')
|
76
|
+
Prawn::Document.generate(into) {
|
77
|
+
font use_this_font
|
78
|
+
font_size use_this_font_size
|
79
|
+
text(
|
80
|
+
"English to German dictionary: "\
|
81
|
+
"#{dataset.keys.size.to_s} translated words\n\n"
|
82
|
+
)
|
83
|
+
# ===================================================================== #
|
84
|
+
# Iterate over our exam dataset next.
|
85
|
+
# ===================================================================== #
|
86
|
+
dataset.each_pair {|key, value|
|
87
|
+
indent(8) {
|
88
|
+
key = key.dup if key.frozen?
|
89
|
+
value = value.dup if value.frozen?
|
90
|
+
result = key.encode(
|
91
|
+
'Windows-1252', invalid: :replace, undef: :replace, replace: ''
|
92
|
+
)+
|
93
|
+
right_arrow+
|
94
|
+
value.encode(
|
95
|
+
'Windows-1252', invalid: :replace, undef: :replace, replace: ''
|
96
|
+
)
|
97
|
+
text(result, {size: 10})
|
98
|
+
}
|
99
|
+
}
|
100
|
+
}
|
101
|
+
e 'Stored into `'+into+'`.'
|
102
|
+
end
|
103
|
+
|
104
|
+
# ========================================================================= #
|
105
|
+
# === Dictionaries.return_array_of_translated_words_from_online_leo
|
106
|
+
#
|
107
|
+
# This method can be used to query the online dictionary from leo.
|
108
|
+
#
|
109
|
+
# It will then return an Array of translations.
|
110
|
+
#
|
111
|
+
# Note that this currently only works for the translation from english
|
112
|
+
# to german, not the other way around, even though that is not too
|
113
|
+
# hard to implement either.
|
114
|
+
# ========================================================================= #
|
115
|
+
def self.return_array_of_translated_words_from_online_leo(this_word)
|
116
|
+
if this_word.is_a? Array
|
117
|
+
this_word = this_word.join(' ').strip
|
118
|
+
end
|
119
|
+
require 'open-uri'
|
120
|
+
remote_url = "https://dict.leo.org/german-english/#{this_word}"
|
121
|
+
remote_dataset = URI.open(remote_url).read
|
122
|
+
# ======================================================================= #
|
123
|
+
# See: https://rubular.com/r/OOXwAc6PVqjU5Q
|
124
|
+
# ======================================================================= #
|
125
|
+
use_this_regex =
|
126
|
+
/<words><word>([a-zA-Z\s]+)\<\/word><\/words>/
|
127
|
+
scanned_results = remote_dataset.scan(use_this_regex).flatten
|
128
|
+
# ======================================================================= #
|
129
|
+
# This result may look like so:
|
130
|
+
# [["cat"], ["die Katze"]
|
131
|
+
# We have to sanitize it still.
|
132
|
+
# ======================================================================= #
|
133
|
+
scanned_results.reject! {|entry| entry.start_with?(this_word) }
|
134
|
+
return scanned_results # Note that the full Array is returned.
|
135
|
+
end
|
136
|
+
|
137
|
+
# ========================================================================= #
|
138
|
+
# === Dictionaries.return_unique_words_from_this_file
|
139
|
+
#
|
140
|
+
# This method will read in the words from an existing local file.
|
141
|
+
#
|
142
|
+
# Some files may be huge, though, and then this method becomes
|
143
|
+
# quite useless, so we really should discard a lot of data after a
|
144
|
+
# certain threshold, to keep memory usage low.
|
145
|
+
# ========================================================================= #
|
146
|
+
def self.return_unique_words_from_this_file(
|
147
|
+
this_file,
|
148
|
+
optional_arguments = :english,
|
149
|
+
remove_html_tags = false
|
150
|
+
)
|
151
|
+
case remove_html_tags
|
152
|
+
# ======================================================================= #
|
153
|
+
# === :remove_HTML_tags
|
154
|
+
# ======================================================================= #
|
155
|
+
when :remove_HTML_tags
|
156
|
+
remove_html_tags = true
|
157
|
+
end
|
158
|
+
dataset = nil
|
159
|
+
if this_file.is_a? Array
|
160
|
+
this_file = this_file.join(' ').strip
|
161
|
+
end
|
162
|
+
if this_file and File.file?(this_file)
|
163
|
+
dataset = File.read(this_file)
|
164
|
+
if remove_html_tags
|
165
|
+
require 'cyberweb/toplevel_methods/toplevel_methods.rb'
|
166
|
+
dataset = ::Cyberweb.remove_html(dataset)
|
167
|
+
end
|
168
|
+
end
|
169
|
+
result = [] # ← This variable will store the unique words found in the file.
|
170
|
+
case optional_arguments
|
171
|
+
# ======================================================================= #
|
172
|
+
# === :english
|
173
|
+
# ======================================================================= #
|
174
|
+
when :english,
|
175
|
+
:default
|
176
|
+
# ===================================================================== #
|
177
|
+
# Query unknown words in english. We will compare the words to the
|
178
|
+
# available variants.
|
179
|
+
# ===================================================================== #
|
180
|
+
result = dataset.scan(/\w+/).map {|entry| entry.downcase } # ← Obtain all words here.
|
181
|
+
# ===================================================================== #
|
182
|
+
# Next, reject those that are registered:
|
183
|
+
# ===================================================================== #
|
184
|
+
result.reject! {|this_word|
|
185
|
+
::Dictionaries.has_key?(this_word)
|
186
|
+
}
|
187
|
+
end if dataset
|
188
|
+
return result.uniq.sort
|
189
|
+
end
|
190
|
+
|
191
|
+
# ========================================================================= #
|
192
|
+
# === Dictionaries[]
|
193
|
+
#
|
194
|
+
# Currently this method will always reload the main file. In the future
|
195
|
+
# we may change this approach, but for now this has to suffice (May 2019).
|
196
|
+
#
|
197
|
+
# The method will return either the translated string - or nil. Nil
|
198
|
+
# indicates that the main Hash does not include that key; in other words,
|
199
|
+
# that the word is not registered.
|
200
|
+
# ========================================================================= #
|
201
|
+
def self.[](i = ARGV)
|
202
|
+
i = i.join.strip if i.is_a? Array
|
203
|
+
this_file = Dictionaries.main_file?
|
204
|
+
if this_file.nil?
|
205
|
+
Dictionaries.set_main_file(:default) # Must initialize it in this case.
|
206
|
+
this_file = Dictionaries.main_file?
|
207
|
+
end
|
208
|
+
if this_file
|
209
|
+
dataset = YAML.load_file(this_file)
|
210
|
+
dataset[i] # Return the result here.
|
211
|
+
else
|
212
|
+
nil
|
213
|
+
end
|
214
|
+
end
|
215
|
+
|
216
|
+
end
|
217
|
+
|
218
|
+
if __FILE__ == $PROGRAM_NAME
|
219
|
+
alias e puts
|
220
|
+
#puts Dictionaries[ARGV]
|
221
|
+
e 'Possible words for cat:'
|
222
|
+
pp Dictionaries.return_array_of_translated_words_from_online_leo('cat')
|
223
|
+
# ========================================================================= #
|
224
|
+
# The next chunk of code is to test reading unique words from a given
|
225
|
+
# local file.
|
226
|
+
# ========================================================================= #
|
227
|
+
puts '-'*80
|
228
|
+
_ = Dictionaries.return_unique_words_from_this_file('/Depot/j/foobar.md')
|
229
|
+
pp _
|
230
|
+
pp _.size
|
231
|
+
end # rb misc.rb cat
|
@@ -0,0 +1,9 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# Just bundle together some requires through this file here.
|
6
|
+
# =========================================================================== #
|
7
|
+
require 'dictionaries/commandline/parse_commandline.rb'
|
8
|
+
require 'dictionaries/toplevel_methods/e.rb'
|
9
|
+
require 'dictionaries/toplevel_methods/show_help.rb'
|
@@ -0,0 +1,31 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'dictionaries/toplevel_methods/show_help.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
require 'dictionaries/toplevel_methods/e.rb'
|
8
|
+
|
9
|
+
module Dictionaries
|
10
|
+
|
11
|
+
# ========================================================================= #
|
12
|
+
# === Dictionaries.show_help
|
13
|
+
#
|
14
|
+
# To invoke this, try:
|
15
|
+
#
|
16
|
+
# dictionaries --help
|
17
|
+
#
|
18
|
+
# ========================================================================= #
|
19
|
+
def self.show_help
|
20
|
+
help_string = <<EOF
|
21
|
+
These options are currently available:
|
22
|
+
|
23
|
+
--n_words? # Show how many words are available
|
24
|
+
--gui # Start the GTK GUI; aliases exist to this, such as --gtk
|
25
|
+
--read=www.nytimes.com.html # Read from a specific file, to find unique words
|
26
|
+
|
27
|
+
EOF
|
28
|
+
e help_string
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'dictionaries/version/version.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
module Dictionaries
|
8
|
+
|
9
|
+
# ========================================================================= #
|
10
|
+
# === VERSION
|
11
|
+
# ========================================================================= #
|
12
|
+
VERSION = '0.3.81'
|
13
|
+
|
14
|
+
# ========================================================================= #
|
15
|
+
# === LAST_UPDATE
|
16
|
+
# ========================================================================= #
|
17
|
+
LAST_UPDATE = '31.01.2024'
|
18
|
+
|
19
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# =========================================================================== #
|
2
|
+
# === chinese.yml
|
3
|
+
#
|
4
|
+
# CHINESE or MANDARIN - Singlish,Singaporean Slang TAG
|
5
|
+
# rf dict chinese
|
6
|
+
# =========================================================================== #
|
7
|
+
|
8
|
+
'nie hau': hallo
|
9
|
+
'hao': 'ja/gut'
|
10
|
+
ganbao: gewonnen
|
11
|
+
shije: schwester
|
12
|
+
wobazaju: I dont care
|
13
|
+
budumo: dont touch it
|
14
|
+
buyaotawo: |
|
15
|
+
"Dont hit me." bu yao ta wo
|
16
|
+
sian: boring
|
17
|
+
dao: Weg
|
18
|
+
chai: Tee
|
19
|
+
wei: "hallo"
|
20
|
+
shue: ja
|
21
|
+
|
22
|
+
'shü-she': '~ja, in ordnung. Danke'
|
23
|
+
yang: Sonne
|
24
|
+
sei tschien: auf wiedersehen
|
25
|
+
|
@@ -0,0 +1 @@
|
|
1
|
+
elegisch: klagend # added 19.10.2003
|