lingo 1.8.1 → 1.8.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/ChangeLog +23 -5
- data/README +1 -1
- data/Rakefile +5 -7
- data/TODO +2 -0
- data/bin/lingo +5 -1
- data/de.lang +1 -1
- data/en/lingo-syn.txt +0 -0
- data/en.lang +2 -1
- data/lib/lingo/attendee/abbreviator.rb +8 -9
- data/lib/lingo/attendee/debugger.rb +5 -4
- data/lib/lingo/attendee/decomposer.rb +8 -3
- data/lib/lingo/attendee/dehyphenizer.rb +19 -63
- data/lib/lingo/attendee/formatter.rb +1 -1
- data/lib/lingo/attendee/multi_worder.rb +67 -155
- data/lib/lingo/attendee/noneword_filter.rb +16 -9
- data/lib/lingo/attendee/object_filter.rb +1 -1
- data/lib/lingo/attendee/sequencer.rb +32 -63
- data/lib/lingo/attendee/stemmer/porter.rb +343 -0
- data/{info/gpl-hdr.txt → lib/lingo/attendee/stemmer.rb} +33 -0
- data/lib/lingo/attendee/synonymer.rb +10 -9
- data/lib/lingo/attendee/text_reader.rb +102 -76
- data/lib/lingo/attendee/text_writer.rb +23 -26
- data/lib/lingo/attendee/tokenizer.rb +13 -27
- data/lib/lingo/attendee/variator.rb +26 -66
- data/lib/lingo/attendee/vector_filter.rb +42 -43
- data/lib/lingo/attendee/word_searcher.rb +6 -7
- data/lib/lingo/attendee.rb +25 -7
- data/lib/lingo/buffered_attendee.rb +36 -10
- data/lib/lingo/cachable.rb +8 -8
- data/lib/lingo/config.rb +5 -6
- data/lib/lingo/ctl.rb +2 -3
- data/lib/lingo/database/crypter.rb +9 -26
- data/lib/lingo/database/gdbm_store.rb +3 -5
- data/lib/lingo/database/libcdb_store.rb +4 -6
- data/lib/lingo/database/sdbm_store.rb +11 -6
- data/lib/lingo/database/show_progress.rb +3 -43
- data/lib/lingo/database/source/key_value.rb +2 -6
- data/lib/lingo/database/source/multi_key.rb +3 -5
- data/lib/lingo/database/source/multi_value.rb +2 -6
- data/lib/lingo/database/source/single_word.rb +4 -6
- data/lib/lingo/database/source/word_class.rb +4 -10
- data/lib/lingo/database/source.rb +20 -18
- data/lib/lingo/database.rb +84 -59
- data/lib/lingo/error.rb +57 -1
- data/lib/lingo/language/dictionary.rb +21 -18
- data/lib/lingo/language/grammar.rb +40 -49
- data/lib/lingo/language/lexical.rb +6 -6
- data/lib/lingo/language/lexical_hash.rb +6 -0
- data/lib/lingo/language/word.rb +32 -15
- data/lib/lingo/language/word_form.rb +1 -1
- data/lib/lingo/language.rb +14 -25
- data/lib/lingo/reportable.rb +12 -10
- data/lib/lingo/show_progress.rb +81 -0
- data/lib/lingo/version.rb +1 -1
- data/lib/lingo.rb +63 -24
- data/lingo-call.cfg +6 -10
- data/lingo.cfg +60 -44
- data/lir.cfg +42 -41
- data/test/attendee/ts_abbreviator.rb +3 -5
- data/test/attendee/ts_decomposer.rb +3 -5
- data/test/attendee/ts_multi_worder.rb +87 -145
- data/test/attendee/ts_noneword_filter.rb +5 -3
- data/test/attendee/ts_object_filter.rb +5 -3
- data/test/attendee/ts_sequencer.rb +3 -5
- data/test/attendee/ts_stemmer.rb +309 -0
- data/test/attendee/ts_synonymer.rb +15 -11
- data/test/attendee/ts_text_reader.rb +12 -15
- data/test/attendee/ts_text_writer.rb +24 -29
- data/test/attendee/ts_tokenizer.rb +9 -7
- data/test/attendee/ts_variator.rb +4 -4
- data/test/attendee/ts_vector_filter.rb +24 -16
- data/test/attendee/ts_word_searcher.rb +20 -36
- data/test/{lir.csv → lir.vec} +0 -0
- data/test/ref/artikel.vec +943 -943
- data/test/ref/artikel.ven +943 -943
- data/test/ref/lir.non +201 -201
- data/test/ref/lir.seq +178 -178
- data/test/ref/lir.syn +49 -49
- data/test/ref/lir.vec +329 -0
- data/test/test_helper.rb +20 -36
- data/test/ts_database.rb +10 -10
- data/test/ts_language.rb +279 -319
- metadata +93 -104
- data/info/Objekte.png +0 -0
- data/info/Typen.png +0 -0
- data/info/database.png +0 -0
- data/info/db_small.png +0 -0
- data/info/download.png +0 -0
- data/info/kerze.png +0 -0
- data/info/language.png +0 -0
- data/info/lingo.png +0 -0
- data/info/logo.png +0 -0
- data/info/meeting.png +0 -0
- data/info/types.png +0 -0
- data/lingo-all.cfg +0 -89
- data/porter/stem.cfg +0 -311
- data/porter/stem.rb +0 -150
- data/test/ref/lir.csv +0 -329
- data/test.cfg +0 -79
data/test/ts_database.rb
CHANGED
|
@@ -3,10 +3,13 @@
|
|
|
3
3
|
require_relative 'test_helper'
|
|
4
4
|
|
|
5
5
|
class Lingo::Database
|
|
6
|
+
|
|
6
7
|
alias_method :original_convert, :convert
|
|
8
|
+
|
|
7
9
|
def convert(verbose = false)
|
|
8
10
|
original_convert(verbose)
|
|
9
11
|
end
|
|
12
|
+
|
|
10
13
|
end
|
|
11
14
|
|
|
12
15
|
class TestDatabase < LingoTestCase
|
|
@@ -176,11 +179,11 @@ Wort2=
|
|
|
176
179
|
'separator' => '*',
|
|
177
180
|
'def-wc' => 's'
|
|
178
181
|
}, @keyvalue, {
|
|
179
|
-
'wort1'=>'projektion1#s|projektion4#s|projektion5#s',
|
|
180
|
-
'wort2'=>'projektion2#s',
|
|
181
|
-
'wort3'=>'projektion3#s',
|
|
182
|
-
'mehr wort satz'=>'pro jeck zion 1#s|pro jeck zion 2#s',
|
|
183
|
-
'albert einstein'=>'einstein, albert#s'
|
|
182
|
+
'wort1' => 'projektion1#s|projektion4#s|projektion5#s',
|
|
183
|
+
'wort2' => 'projektion2#s',
|
|
184
|
+
'wort3' => 'projektion3#s',
|
|
185
|
+
'mehr wort satz' => 'pro jeck zion 1#s|pro jeck zion 2#s',
|
|
186
|
+
'albert einstein' => 'einstein, albert#s'
|
|
184
187
|
})
|
|
185
188
|
end
|
|
186
189
|
|
|
@@ -253,10 +256,7 @@ Wort2=
|
|
|
253
256
|
if block_given?
|
|
254
257
|
yield db
|
|
255
258
|
else
|
|
256
|
-
|
|
257
|
-
store.delete(Lingo::Database::SYS_KEY)
|
|
258
|
-
|
|
259
|
-
assert_equal(output, store)
|
|
259
|
+
assert_equal(output, db.to_h.tap { |store| store.delete(Lingo::Database::SYS_KEY) })
|
|
260
260
|
end
|
|
261
261
|
}
|
|
262
262
|
ensure
|
|
@@ -264,7 +264,7 @@ Wort2=
|
|
|
264
264
|
end
|
|
265
265
|
|
|
266
266
|
def set_config(id, config)
|
|
267
|
-
"_test_#{id}_".tap { |
|
|
267
|
+
"_test_#{id}_".tap { |i| @lingo.config["language/dictionary/databases/#{i}"] = config }
|
|
268
268
|
end
|
|
269
269
|
|
|
270
270
|
end
|