lingo 1.8.1 → 1.8.2
Sign up to get free protection for your applications and to get access to all the features.
- 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
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: lingo
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.8.
|
4
|
+
version: 1.8.2
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -10,11 +10,11 @@ authors:
|
|
10
10
|
autorequire:
|
11
11
|
bindir: bin
|
12
12
|
cert_chain: []
|
13
|
-
date: 2012-
|
13
|
+
date: 2012-04-19 00:00:00.000000000 Z
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: ruby-nuggets
|
17
|
-
requirement: &
|
17
|
+
requirement: &12303700 !ruby/object:Gem::Requirement
|
18
18
|
none: false
|
19
19
|
requirements:
|
20
20
|
- - ! '>='
|
@@ -22,10 +22,10 @@ dependencies:
|
|
22
22
|
version: 0.8.5
|
23
23
|
type: :runtime
|
24
24
|
prerelease: false
|
25
|
-
version_requirements: *
|
25
|
+
version_requirements: *12303700
|
26
26
|
- !ruby/object:Gem::Dependency
|
27
27
|
name: unicode
|
28
|
-
requirement: &
|
28
|
+
requirement: &12302600 !ruby/object:Gem::Requirement
|
29
29
|
none: false
|
30
30
|
requirements:
|
31
31
|
- - ! '>='
|
@@ -33,10 +33,10 @@ dependencies:
|
|
33
33
|
version: '0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
|
-
version_requirements: *
|
36
|
+
version_requirements: *12302600
|
37
37
|
- !ruby/object:Gem::Dependency
|
38
38
|
name: highline
|
39
|
-
requirement: &
|
39
|
+
requirement: &12317680 !ruby/object:Gem::Requirement
|
40
40
|
none: false
|
41
41
|
requirements:
|
42
42
|
- - ! '>='
|
@@ -44,10 +44,10 @@ dependencies:
|
|
44
44
|
version: '0'
|
45
45
|
type: :runtime
|
46
46
|
prerelease: false
|
47
|
-
version_requirements: *
|
47
|
+
version_requirements: *12317680
|
48
48
|
- !ruby/object:Gem::Dependency
|
49
49
|
name: diff-lcs
|
50
|
-
requirement: &
|
50
|
+
requirement: &12315360 !ruby/object:Gem::Requirement
|
51
51
|
none: false
|
52
52
|
requirements:
|
53
53
|
- - ! '>='
|
@@ -55,10 +55,10 @@ dependencies:
|
|
55
55
|
version: 1.1.3
|
56
56
|
type: :development
|
57
57
|
prerelease: false
|
58
|
-
version_requirements: *
|
58
|
+
version_requirements: *12315360
|
59
59
|
- !ruby/object:Gem::Dependency
|
60
60
|
name: open4
|
61
|
-
requirement: &
|
61
|
+
requirement: &12314340 !ruby/object:Gem::Requirement
|
62
62
|
none: false
|
63
63
|
requirements:
|
64
64
|
- - ! '>='
|
@@ -66,7 +66,7 @@ dependencies:
|
|
66
66
|
version: '0'
|
67
67
|
type: :development
|
68
68
|
prerelease: false
|
69
|
-
version_requirements: *
|
69
|
+
version_requirements: *12314340
|
70
70
|
description: ! "Lingo is an open source indexing system for research and teachings.\nThe
|
71
71
|
main functions of Lingo are:\n\n* identification of (i.e. reduction to) basic word
|
72
72
|
form by means of\n dictionaries and suffix lists\n* algorithmic decomposition\n*
|
@@ -76,144 +76,133 @@ email:
|
|
76
76
|
- lingo@vorhauer.de
|
77
77
|
- jens.wille@uni-koeln.de
|
78
78
|
executables:
|
79
|
-
- lingo
|
80
79
|
- lingoctl
|
80
|
+
- lingo
|
81
81
|
extensions: []
|
82
82
|
extra_rdoc_files:
|
83
83
|
- README
|
84
84
|
- COPYING
|
85
85
|
- ChangeLog
|
86
86
|
files:
|
87
|
-
- lib/lingo
|
87
|
+
- lib/lingo.rb
|
88
|
+
- lib/lingo/show_progress.rb
|
89
|
+
- lib/lingo/config.rb
|
88
90
|
- lib/lingo/database.rb
|
89
|
-
- lib/lingo/
|
90
|
-
- lib/lingo/
|
91
|
-
- lib/lingo/
|
92
|
-
- lib/lingo/
|
93
|
-
- lib/lingo/
|
94
|
-
- lib/lingo/
|
95
|
-
- lib/lingo/
|
96
|
-
- lib/lingo/
|
97
|
-
- lib/lingo/
|
98
|
-
- lib/lingo/
|
99
|
-
- lib/lingo/database/source/word_class.rb
|
100
|
-
- lib/lingo/database/source/multi_value.rb
|
101
|
-
- lib/lingo/database/gdbm_store.rb
|
102
|
-
- lib/lingo/database/hash_store.rb
|
103
|
-
- lib/lingo/cli.rb
|
104
|
-
- lib/lingo/cachable.rb
|
105
|
-
- lib/lingo/attendee/variator.rb
|
106
|
-
- lib/lingo/attendee/debugger.rb
|
91
|
+
- lib/lingo/language/dictionary.rb
|
92
|
+
- lib/lingo/language/word_form.rb
|
93
|
+
- lib/lingo/language/lexical.rb
|
94
|
+
- lib/lingo/language/grammar.rb
|
95
|
+
- lib/lingo/language/lexical_hash.rb
|
96
|
+
- lib/lingo/language/token.rb
|
97
|
+
- lib/lingo/language/word.rb
|
98
|
+
- lib/lingo/attendee/stemmer/porter.rb
|
99
|
+
- lib/lingo/attendee/vector_filter.rb
|
100
|
+
- lib/lingo/attendee/noneword_filter.rb
|
107
101
|
- lib/lingo/attendee/object_filter.rb
|
108
|
-
- lib/lingo/attendee/
|
109
|
-
- lib/lingo/attendee/text_writer.rb
|
102
|
+
- lib/lingo/attendee/variator.rb
|
110
103
|
- lib/lingo/attendee/multi_worder.rb
|
111
104
|
- lib/lingo/attendee/text_reader.rb
|
105
|
+
- lib/lingo/attendee/synonymer.rb
|
106
|
+
- lib/lingo/attendee/word_searcher.rb
|
112
107
|
- lib/lingo/attendee/dehyphenizer.rb
|
108
|
+
- lib/lingo/attendee/sequencer.rb
|
109
|
+
- lib/lingo/attendee/debugger.rb
|
110
|
+
- lib/lingo/attendee/text_writer.rb
|
111
|
+
- lib/lingo/attendee/stemmer.rb
|
113
112
|
- lib/lingo/attendee/tokenizer.rb
|
114
113
|
- lib/lingo/attendee/abbreviator.rb
|
115
|
-
- lib/lingo/attendee/formatter.rb
|
116
|
-
- lib/lingo/attendee/noneword_filter.rb
|
117
|
-
- lib/lingo/attendee/sequencer.rb
|
118
114
|
- lib/lingo/attendee/decomposer.rb
|
119
|
-
- lib/lingo/attendee/
|
120
|
-
- lib/lingo/
|
121
|
-
- lib/lingo/
|
115
|
+
- lib/lingo/attendee/formatter.rb
|
116
|
+
- lib/lingo/database/hash_store.rb
|
117
|
+
- lib/lingo/database/show_progress.rb
|
118
|
+
- lib/lingo/database/sdbm_store.rb
|
119
|
+
- lib/lingo/database/source.rb
|
120
|
+
- lib/lingo/database/crypter.rb
|
121
|
+
- lib/lingo/database/source/multi_value.rb
|
122
|
+
- lib/lingo/database/source/word_class.rb
|
123
|
+
- lib/lingo/database/source/key_value.rb
|
124
|
+
- lib/lingo/database/source/multi_key.rb
|
125
|
+
- lib/lingo/database/source/single_word.rb
|
126
|
+
- lib/lingo/database/gdbm_store.rb
|
127
|
+
- lib/lingo/database/libcdb_store.rb
|
128
|
+
- lib/lingo/call.rb
|
129
|
+
- lib/lingo/attendee.rb
|
130
|
+
- lib/lingo/version.rb
|
131
|
+
- lib/lingo/ctl.rb
|
132
|
+
- lib/lingo/cli.rb
|
122
133
|
- lib/lingo/core_ext.rb
|
123
|
-
- lib/lingo/agenda_item.rb
|
124
134
|
- lib/lingo/buffered_attendee.rb
|
125
|
-
- lib/lingo/
|
135
|
+
- lib/lingo/agenda_item.rb
|
136
|
+
- lib/lingo/cachable.rb
|
126
137
|
- lib/lingo/language.rb
|
127
|
-
- lib/lingo/
|
128
|
-
- lib/lingo/
|
129
|
-
- lib/lingo/language/lexical.rb
|
130
|
-
- lib/lingo/language/word_form.rb
|
131
|
-
- lib/lingo/language/token.rb
|
132
|
-
- lib/lingo/language/grammar.rb
|
133
|
-
- lib/lingo/language/lexical_hash.rb
|
134
|
-
- lib/lingo/attendee.rb
|
135
|
-
- lib/lingo/call.rb
|
136
|
-
- lib/lingo.rb
|
137
|
-
- bin/lingo
|
138
|
+
- lib/lingo/error.rb
|
139
|
+
- lib/lingo/reportable.rb
|
138
140
|
- bin/lingoctl
|
141
|
+
- bin/lingo
|
139
142
|
- lingo.rb
|
140
143
|
- lingo.cfg
|
141
|
-
- lingo-all.cfg
|
142
144
|
- lingo-call.cfg
|
145
|
+
- lir.cfg
|
143
146
|
- de.lang
|
144
147
|
- en.lang
|
145
|
-
- de/lingo-syn.txt
|
146
|
-
- de/lingo-abk.txt
|
147
148
|
- de/lingo-dic.txt
|
149
|
+
- de/lingo-abk.txt
|
150
|
+
- de/lingo-syn.txt
|
148
151
|
- de/lingo-mul.txt
|
149
152
|
- de/user-dic.txt
|
153
|
+
- de/test_syn.txt
|
154
|
+
- de/test_dic.txt
|
155
|
+
- de/test_syn2.txt
|
156
|
+
- de/test_singleword.txt
|
157
|
+
- de/test_mul.txt
|
158
|
+
- de/test_mul2.txt
|
150
159
|
- en/lingo-dic.txt
|
160
|
+
- en/lingo-syn.txt
|
151
161
|
- en/lingo-mul.txt
|
152
162
|
- en/user-dic.txt
|
153
163
|
- txt/artikel.txt
|
154
164
|
- txt/artikel-en.txt
|
155
|
-
- info/gpl-hdr.txt
|
156
|
-
- info/kerze.png
|
157
|
-
- info/meeting.png
|
158
|
-
- info/lingo.png
|
159
|
-
- info/types.png
|
160
|
-
- info/logo.png
|
161
|
-
- info/language.png
|
162
|
-
- info/Typen.png
|
163
|
-
- info/Objekte.png
|
164
|
-
- info/download.png
|
165
|
-
- info/database.png
|
166
|
-
- info/db_small.png
|
167
|
-
- lir.cfg
|
168
165
|
- txt/lir.txt
|
169
|
-
- porter/stem.rb
|
170
|
-
- porter/stem.cfg
|
171
|
-
- test.cfg
|
172
|
-
- de/test_mul.txt
|
173
|
-
- de/test_singleword.txt
|
174
|
-
- de/test_mul2.txt
|
175
|
-
- de/test_syn.txt
|
176
|
-
- de/test_dic.txt
|
177
|
-
- de/test_syn2.txt
|
178
|
-
- TODO
|
179
|
-
- README
|
180
166
|
- ChangeLog
|
181
167
|
- COPYING
|
168
|
+
- README
|
182
169
|
- Rakefile
|
170
|
+
- TODO
|
183
171
|
- spec/spec_helper.rb
|
184
172
|
- .rspec
|
185
|
-
- test/lir.csv
|
186
|
-
- test/attendee/ts_abbreviator.rb
|
187
|
-
- test/attendee/ts_noneword_filter.rb
|
188
|
-
- test/attendee/ts_word_searcher.rb
|
189
|
-
- test/attendee/ts_object_filter.rb
|
190
|
-
- test/attendee/ts_vector_filter.rb
|
191
|
-
- test/attendee/ts_text_writer.rb
|
192
|
-
- test/attendee/ts_decomposer.rb
|
193
|
-
- test/attendee/ts_sequencer.rb
|
194
|
-
- test/attendee/ts_synonymer.rb
|
195
|
-
- test/attendee/ts_tokenizer.rb
|
196
|
-
- test/attendee/ts_variator.rb
|
197
|
-
- test/attendee/ts_text_reader.rb
|
198
|
-
- test/attendee/ts_multi_worder.rb
|
199
|
-
- test/mul.txt
|
200
|
-
- test/test_helper.rb
|
201
173
|
- test/ref/artikel.ven
|
202
|
-
- test/ref/lir.csv
|
203
|
-
- test/ref/artikel.vec
|
204
174
|
- test/ref/lir.mul
|
205
|
-
- test/ref/
|
175
|
+
- test/ref/lir.vec
|
176
|
+
- test/ref/artikel.vec
|
206
177
|
- test/ref/lir.syn
|
207
178
|
- test/ref/artikel.mul
|
179
|
+
- test/ref/artikel.syn
|
208
180
|
- test/ref/artikel.seq
|
209
|
-
- test/ref/lir.seq
|
210
181
|
- test/ref/artikel.non
|
211
|
-
- test/ref/artikel.ver
|
212
182
|
- test/ref/lir.non
|
183
|
+
- test/ref/lir.seq
|
184
|
+
- test/ref/artikel.ver
|
185
|
+
- test/ts_language.rb
|
213
186
|
- test/lir2.txt
|
214
|
-
- test/
|
187
|
+
- test/attendee/ts_noneword_filter.rb
|
188
|
+
- test/attendee/ts_text_writer.rb
|
189
|
+
- test/attendee/ts_sequencer.rb
|
190
|
+
- test/attendee/ts_object_filter.rb
|
191
|
+
- test/attendee/ts_text_reader.rb
|
192
|
+
- test/attendee/ts_multi_worder.rb
|
193
|
+
- test/attendee/ts_variator.rb
|
194
|
+
- test/attendee/ts_decomposer.rb
|
195
|
+
- test/attendee/ts_abbreviator.rb
|
196
|
+
- test/attendee/ts_stemmer.rb
|
197
|
+
- test/attendee/ts_tokenizer.rb
|
198
|
+
- test/attendee/ts_vector_filter.rb
|
199
|
+
- test/attendee/ts_word_searcher.rb
|
200
|
+
- test/attendee/ts_synonymer.rb
|
201
|
+
- test/lir.vec
|
202
|
+
- test/test_helper.rb
|
215
203
|
- test/lir.txt
|
216
|
-
- test/
|
204
|
+
- test/mul.txt
|
205
|
+
- test/ts_database.rb
|
217
206
|
homepage: http://lex-lingo.de
|
218
207
|
licenses: []
|
219
208
|
post_install_message:
|
@@ -223,7 +212,7 @@ rdoc_options:
|
|
223
212
|
- --line-numbers
|
224
213
|
- --all
|
225
214
|
- --title
|
226
|
-
- lingo Application documentation (v1.8.
|
215
|
+
- lingo Application documentation (v1.8.2)
|
227
216
|
- --main
|
228
217
|
- README
|
229
218
|
require_paths:
|
data/info/Objekte.png
DELETED
Binary file
|
data/info/Typen.png
DELETED
Binary file
|
data/info/database.png
DELETED
Binary file
|
data/info/db_small.png
DELETED
Binary file
|
data/info/download.png
DELETED
Binary file
|
data/info/kerze.png
DELETED
Binary file
|
data/info/language.png
DELETED
Binary file
|
data/info/lingo.png
DELETED
Binary file
|
data/info/logo.png
DELETED
Binary file
|
data/info/meeting.png
DELETED
Binary file
|
data/info/types.png
DELETED
Binary file
|
data/lingo-all.cfg
DELETED
@@ -1,89 +0,0 @@
|
|
1
|
-
#
|
2
|
-
# Lingo-Konfiguration
|
3
|
-
#
|
4
|
-
---
|
5
|
-
meeting:
|
6
|
-
|
7
|
-
attendees:
|
8
|
-
|
9
|
-
########################################
|
10
|
-
# Text bereitstellen
|
11
|
-
#
|
12
|
-
|
13
|
-
# Angegebene Datei zeilenweise einlesen und verarbeitet
|
14
|
-
- text_reader: { files: '$(files)' }
|
15
|
-
|
16
|
-
|
17
|
-
########################################
|
18
|
-
# Inhalte verarbeiten
|
19
|
-
#
|
20
|
-
|
21
|
-
# Zeile in einzelnen Sinnbestandteile (Token) zerlegen
|
22
|
-
- tokenizer: { }
|
23
|
-
|
24
|
-
# Abkürzungen erkennen und auflösen
|
25
|
-
# - abbreviator: { source: 'sys-abk' }
|
26
|
-
|
27
|
-
# Verbleibende Token im Wörterbuch suchen
|
28
|
-
- word_searcher: { source: 'sys-dic', mode: 'first' }
|
29
|
-
|
30
|
-
# Schreibweisen variieren und erneut suchen
|
31
|
-
# - variator: { source: 'sys-dic' }
|
32
|
-
|
33
|
-
# Bindestrichergänzungen rekonstruieren
|
34
|
-
# - dehyphenizer: { source: 'sys-dic' }
|
35
|
-
|
36
|
-
# Nicht erkannte Wörter auf Kompositum testen
|
37
|
-
# - decomposer: { source: 'sys-dic' }
|
38
|
-
|
39
|
-
# Mehrwortgruppen im Strom erkennen
|
40
|
-
# - multi_worder: { stopper: 'PUNC,OTHR', source: 'sys-mul' }
|
41
|
-
|
42
|
-
# Wortsequenzen anhand von Regeln identifizieren
|
43
|
-
# - sequencer: { stopper: 'PUNC,OTHR' }
|
44
|
-
|
45
|
-
# Relationierungen einfügen
|
46
|
-
# - synonymer: { skip: '?,t', source: 'sys-syn', out: syn }
|
47
|
-
|
48
|
-
|
49
|
-
########################################
|
50
|
-
# Datenstrom anzeigen
|
51
|
-
#
|
52
|
-
- debugger: { eval: 'true', ceval: 'cmd!="EOL"', prompt: 'lex:) ' }
|
53
|
-
|
54
|
-
|
55
|
-
########################################
|
56
|
-
# Ergebnisse ausgeben
|
57
|
-
#
|
58
|
-
|
59
|
-
# Erstelle Datei mit Endung .log für Datenstrom
|
60
|
-
# - vector_filter: { in: syn, debug: 'true', prompt: 'lex:) ' }
|
61
|
-
# - text_writer: { ext: log, sep: "\n" }
|
62
|
-
|
63
|
-
# Erstelle Datei mit Endung .non für nicht erkannte Wörter
|
64
|
-
# - noneword_filter: { in: syn }
|
65
|
-
# - text_writer: { ext: non, sep: "\n" }
|
66
|
-
|
67
|
-
# Erstelle Datei mit Endung .vec für erkannte Indexterme
|
68
|
-
# - vector_filter: { in: syn, lexicals: '^[ksavem]$' }
|
69
|
-
# - text_writer: { ext: vec, sep: "\n" }
|
70
|
-
|
71
|
-
# Erstelle Datei mit Endung .ven für erkannte Indexterme mit absoluter Häufigkeit
|
72
|
-
# - vector_filter: { in: syn, lexicals: '^[ksavem]$', sort: 'term_abs' }
|
73
|
-
# - text_writer: { ext: ven, sep: "\n" }
|
74
|
-
|
75
|
-
# Erstelle Datei mit Endung .ver für erkannte Indexterme mit relativer Häufigkeit
|
76
|
-
# - vector_filter: { in: syn, lexicals: '^[ksavem]$', sort: 'term_rel' }
|
77
|
-
# - text_writer: { ext: ver, sep: "\n" }
|
78
|
-
|
79
|
-
# Erstelle Datei mit Endung .mul für erkannte Mehrwortgruppen
|
80
|
-
# - vector_filter: { in: syn, lexicals: m }
|
81
|
-
# - text_writer: { ext: mul, sep: "\n" }
|
82
|
-
|
83
|
-
# Erstelle Datei mit Endung .seq für erkannte Wortsequenzen
|
84
|
-
# - vector_filter: { in: syn, lexicals: q, sort: 'term_abs' }
|
85
|
-
# - text_writer: { ext: seq, sep: "\n" }
|
86
|
-
|
87
|
-
# Erstelle Datei mit Endung .syn für erkannte Synonyme
|
88
|
-
# - vector_filter: { in: syn, lexicals: y, sort: 'term_abs' }
|
89
|
-
# - text_writer: { ext: syn, sep: "\n" }
|