LanguageMachines/ucto-v0.20.zip
LanguageMachines-ucto-9652619
.gitignore
1.7 kB
.travis.yml
2.7 kB
AUTHORS
68 Bytes
COPYING
35.1 kB
Makefile.am
281 Bytes
NEWS
14.3 kB
README
42 Bytes
README.md
5.7 kB
TODO
84 Bytes
bootstrap.sh
2.7 kB
codemeta.json
3.6 kB
config
Makefile.am
361 Bytes
textcat.cfg
738 Bytes
textcat_alt.cfg.in
707 Bytes
textcat_normal.cfg.in
648 Bytes
configure.ac
3.3 kB
docs
Makefile.am
60 Bytes
Makefile.sphinx
592 Bytes
source
_static
DUMMY
0 Bytes
_templates
DUMMY
0 Bytes
conf.py
5.4 kB
index.rst
32.2 kB
todo
73 Bytes
ucto.1
3.7 kB
ucto_manual.bib
277 Bytes
ucto_manual.pdf
197.6 kB
ucto_manual.rst
22.1 kB
ucto_manual.tex
23.9 kB
include
Makefile.am
46 Bytes
ucto
Makefile.am
55 Bytes
my_textcat.h
1.6 kB
setting.h
3.6 kB
tokenize.h
14.7 kB
logo.svg
6.1 kB
m4
Makefile.am
29 Bytes
ac_check_old_textcat.m4
1.5 kB
ac_osx_pkg.m4
2.1 kB
ac_search_lm.m4
2.0 kB
ax_icu_check.m4
2.5 kB
src
Makefile.am
375 Bytes
my_textcat.cxx
3.5 kB
setting.cxx
22.7 kB
tokenize.cxx
76.9 kB
tst.sh
117 Bytes
ucto.cxx
18.9 kB
tests
Makefile.am
37 Bytes
UTF16BE.nl
188 Bytes
W1258.nl
193 Bytes
abbreviations.nl.tok.V
1.3 kB
abbreviations.nl.txt
390 Bytes
bracket.nl.tok.V
361 Bytes
bracket.nl.txt
73 Bytes
bug0048.nl.tok.V
203 Bytes
bug0048.nl.txt
32 Bytes
bug0051.nl.tok.V
289 Bytes
bug0051.nl.txt
35 Bytes
bug0052.nl.tok.V
1.3 kB
bug0052.nl.txt
297 Bytes
bug0054.nl.tok.V
181 Bytes
bug0054.nl.txt
35 Bytes
bug0063.nl.tok.V
186 Bytes
bug0063.nl.txt
52 Bytes
bug0065.nl.tok.V
687 Bytes
bug0065.nl.txt
211 Bytes
bug0065b.nl.tok.V
734 Bytes
bug0065b.nl.txt
207 Bytes
bug0065c.nl.tok.V
638 Bytes
bug0065c.nl.txt
205 Bytes
bug0067.nl.tok.V
105 Bytes
bug0067.nl.txt
22 Bytes
bug0075.nl.tok.V
120 Bytes
bug0075.nl.txt
23 Bytes
bug0083.nl.tok.V
13.2 kB
bug0083.nl.txt
4.9 kB
bug0094.nl.tok.V
147 Bytes
bug0094.nl.txt
14 Bytes
cell.xml
524 Bytes
datetime.nl.tok.V
711 Bytes
datetime.nl.txt
178 Bytes
dimin.nl.tok.V
413 Bytes
dimin.nl.txt
96 Bytes
empty.xml
570 Bytes
empty_line.txt
46 Bytes
encoding.nl.tok.V
589 Bytes
encoding.nl.txt
166 Bytes
encoding2.nl
873 Bytes
eos.txt
109 Bytes
filter.xml
375 Bytes
folia-lang-2.xml
759 Bytes
folia-lang.xml
865 Bytes
folia.txt
114 Bytes
folia1.xml
663 Bytes
folia2.txt
887 Bytes
folia2.xml
588 Bytes
folia3.xml
531 Bytes
folia4.xml
580 Bytes
folia5.xml
500 Bytes
folia6.xml
534 Bytes
folia7.xml
392 Bytes
folia8.xml
411 Bytes
folia9a.xml
450 Bytes
folia9b.xml
450 Bytes
genitive.nl.tok.V
352 Bytes
genitive.nl.txt
108 Bytes
invoer.rule
30 Bytes
issue01.nl.tok.V
1.1 kB
issue01.nl.txt
284 Bytes
issue03.nl.tok.V
507 Bytes
issue03.nl.txt
101 Bytes
issue04.nl.tok.V
539 Bytes
issue04.nl.txt.FAILS
133 Bytes
issue046.nl.tok.V
2.3 kB
issue046.nl.txt
442 Bytes
issue048.nl.tok.V
300 Bytes
issue048.nl.txt
111 Bytes
issue051.nl.tok.V
881 Bytes
issue051.nl.txt
113 Bytes
issue064a.xml
741 Bytes
issue064b.xml
572 Bytes
issue064c.xml
655 Bytes
issue066.xml
414 Bytes
issue70.xml
1.1 kB
issue70_b.xml
1.2 kB
issue70_c.xml
1.1 kB
issue71_b.xml
3.4 kB
issue71_c.xml
2.6 kB
issue71_d.xml
1.1 kB
issue71_e.xml
3.4 kB
ligaturen.nl.tok.V
906 Bytes
ligaturen.nl.txt
221 Bytes
multilang.txt
989 Bytes
multilang2.txt
265 Bytes
multisentenceoneline.nl.tok.V
430 Bytes
multisentenceoneline.nl.txt
115 Bytes
munten.nl.tok.V
0 Bytes
munten.nl.txt.disabled
47 Bytes
nbsp.xml
635 Bytes
normalisation.nl.tok.V
414 Bytes
normalisation.nl.txt
105 Bytes
normalisationUTF16.nl.tok.V
414 Bytes
normalisationUTF16.nl.txt
188 Bytes
nu.nl.tok.V
14.0 kB
nu.nl.txt
4.9 kB
ocr.nl.tok.V
5.5 kB
ocr.nl.txt
1.6 kB
onesentencemultiline.nl.tok.V
298 Bytes
onesentencemultiline.nl.txt
104 Bytes
parentheses.nl.tok.V
607 Bytes
parentheses.nl.txt
187 Bytes
partest.nl.tok
240 Bytes
partest.nl.txt
195 Bytes
partest2.nl.tok
150 Bytes
partest2.nl.txt
127 Bytes
partest2_folia.nl.txt
127 Bytes
partest2_folia.nl.xml
4.2 kB
partest_crlf.nl.tok.V
396 Bytes
partest_crlf.nl.txt
69 Bytes
partest_folia.nl.txt
195 Bytes
partest_folia.nl.xml
5.9 kB
passthru.txt
42 Bytes
passthru2.txt
135 Bytes
qtest.nl
353 Bytes
qtest.nl.tok
256 Bytes
qtest.nl.tok.V
1.2 kB
qtest.spec
263 Bytes
qtest.spec.tok
338 Bytes
qtest.spec.tok.V
1.5 kB
quoteproblem.txt
3.2 kB
quotetest_folgert.nl.tok.V
601 Bytes
quotetest_folgert.nl.txt
103 Bytes
quotetest_folgert2.nl.tok.V
1.6 kB
quotetest_folgert2.nl.txt
248 Bytes
quotetest_folgert3.nl.tok.V
1.5 kB
quotetest_folgert3.nl.txt
384 Bytes
quotetest_folgert4.nl.tok.V
820 Bytes
quotetest_folgert4.nl.txt
155 Bytes
quotetest_folgert5.nl.tok.V
930 Bytes
quotetest_folgert5.nl.txt
225 Bytes
quotetest_folgert6.nl.tok.V
2.1 kB
quotetest_folgert6.nl.txt
542 Bytes
quotetest_folgert7.nl.tok.V
687 Bytes
quotetest_folgert7.nl.txt
131 Bytes
quotetest_folgert8.nl.tok.V
1.6 kB
quotetest_folgert8.nl.txt.disabled
340 Bytes
quotetest_multiline.nl.tok.V
368 Bytes
quotetest_multiline.nl.txt
69 Bytes
quotetest_multisentence.nl.tok.V
816 Bytes
quotetest_multisentence.nl.txt
130 Bytes
quotetest_nested.nl.tok.V
380 Bytes
quotetest_nested.nl.txt
85 Bytes
quotetest_nested2.nl.tok.V
1.8 kB
quotetest_nested2.nl.txt
586 Bytes
quotetest_nosentence.nl.tok.V
422 Bytes
quotetest_nosentence.nl.txt
54 Bytes
quotetest_onesentence.nl.tok.V
582 Bytes
quotetest_onesentence.nl.txt
74 Bytes
reverse-smiley.nl.tok.V
482 Bytes
reverse-smiley.nl.txt
109 Bytes
slashes.xml
912 Bytes
small-tokconfig-nld
147 Bytes
small.cfg
147 Bytes
small.txt
18 Bytes
smileys.nl.tok.V
861 Bytes
smileys.nl.txt
202 Bytes
stuk1.cfg
133 Bytes
stuk2.cfg
114 Bytes
suffix.nl.tok.V
3.5 kB
suffix.nl.txt
829 Bytes
test.de.tok.V
3.2 kB
test.de.txt
892 Bytes
test.en.tok.V
4.1 kB
test.en.txt
1.1 kB
test.es.tok.V
3.0 kB
test.es.txt
766 Bytes
test.fr.tok.V
4.6 kB
test.fr.txt
1.3 kB
test.nl.tok
1.9 kB
test.nl.tok.V
8.4 kB
test.nl.txt
2.4 kB
test.pt.txt.disabled
923 Bytes
test.py
4.8 kB
testall
1.1 kB
testclassnormalization
214 Bytes
testclassnormalization.ok
2.3 kB
testconf1
62 Bytes
testconf1.ok
0 Bytes
testconf2
62 Bytes
testconf2.ok
0 Bytes
testencoding2
247 Bytes
testencoding2.ok
10.8 kB
testfiles1
78 Bytes
testfiles1.ok
0 Bytes
testfiles2
73 Bytes
testfiles2.ok
0 Bytes
testfolia
112 Bytes
testfolia.ok
10.0 kB
testfolia2
197 Bytes
testfolia2.ok
57.9 kB
testfoliain
785 Bytes
testfoliain.ok
48.6 kB
testinclude
72 Bytes
testinclude.ok
25 Bytes
testissue64
555 Bytes
testissue64.ok
6.2 kB
testissue66
53 Bytes
testissue66.ok
1.6 kB
testissue70
128 Bytes
testissue70.ok
10.3 kB
testissue71
255 Bytes
testissue71.ok
24.0 kB
testissue72
663 Bytes
testissue72.ok
10.8 kB
testlang
345 Bytes
testlang.ok
48.9 kB
testlanguage
53 Bytes
testlanguage.ok
0 Bytes
testmac
796 Bytes
testnbsp
108 Bytes
testnbsp.ok
1.8 kB
testnormalisation
479 Bytes
testnormalisation.ok
1.3 kB
testone
1.3 kB
testoption-P
170 Bytes
testoption-P.ok
878 Bytes
testoption-s
200 Bytes
testoption-s.ok
214 Bytes
testoption-split
212 Bytes
testoption-split.ok
1.1 kB
testoption1
61 Bytes
testoption1.ok
0 Bytes
testoption2
71 Bytes
testoption2.ok
0 Bytes
testpassthru
246 Bytes
testpassthru.ok
3.1 kB
testpunctfilter
193 Bytes
testpunctfilter.ok
698 Bytes
testpunctuation
180 Bytes
testpunctuation.ok
820 Bytes
testpunctuation.txt
667 Bytes
testquotes
98 Bytes
testquotes.ok
3.7 kB
testquotes2
199 Bytes
testquotes2.ok
3.3 kB
testslash
69 Bytes
testslash.ok
4.1 kB
testtext
69 Bytes
testtext.ok
1.0 kB
testtokens
100 Bytes
testtokens.ok
1.3 kB
testtwitter
80 Bytes
testtwitter.ok
48 Bytes
testusage
50 Bytes
testusage.ok
0 Bytes
testutt
72 Bytes
testutt.ok
15.1 kB
textproblem.xml
620 Bytes
tokens
35 Bytes
tokens.txt
127 Bytes
tst.cfg
76 Bytes
tst.ok
43 Bytes
tst.txt
35 Bytes
twitter.txt
35 Bytes
units.nl.tok.V
0 Bytes
units.nl.txt.disabled
30 Bytes
urls.nl.tok.V
1.4 kB
urls.nl.txt
519 Bytes
utf16bom.nl
92 Bytes
utf8bom.nl
52 Bytes
utt.txt
109 Bytes
utt.xml
1.3 kB
utt2.xml
760 Bytes
windows_cr_lf_utf16.czech
16.4 kB
ucto-icu.pc.in
267 Bytes
ucto.pc.in
214 Bytes