[ferlanero@ferlanero-imac okb-engine-master]$ db/build.sh es
Building for languages:  es
~/okb-engine-master/ngrams ~/okb-engine-master/db
running build
running build_ext
running build
running build_ext
~/okb-engine-master/db
~/okb-engine-master/cluster ~/okb-engine-master/db
make: No se hace nada para 'first'.
~/okb-engine-master/db
«/home/ferlanero/okb-engine-master/db/lang-en.cf» -> «/home/ferlanero/okboard/langs/lang-en.cf»
«/home/ferlanero/okb-engine-master/db/lang-es.cf» -> «/home/ferlanero/okboard/langs/lang-es.cf»
«/home/ferlanero/okb-engine-master/db/lang-fr.cf» -> «/home/ferlanero/okboard/langs/lang-fr.cf»
«/home/ferlanero/okb-engine-master/db/lang-nl.cf» -> «/home/ferlanero/okboard/langs/lang-nl.cf»
«/home/ferlanero/okb-engine-master/db/add-words-fr.txt» -> «/home/ferlanero/okboard/langs/add-words-fr.txt»
«/home/ferlanero/okb-engine-master/db/db.version» -> «/home/ferlanero/okboard/langs/db.version»
make: '.depend-es' está actualizado.
( [ -f "add-words-es.txt" ] && cat "add-words-es.txt" ; aspell -l es dump master ) | sort | uniq > es-full.dict
lbzip2 -d < /home/ferlanero/okboard/langs/corpus-es.txt.bz2 | /home/ferlanero/okb-engine-master/db/../tools/corpus-splitter.pl 200 50 es-learn.tmp.bz2 es-test.tmp.bz2
mv -vf es-learn.tmp.bz2 es-learn.txt.bz2
«es-learn.tmp.bz2» -> «es-learn.txt.bz2»
mv -vf es-test.tmp.bz2 es-test.txt.bz2
«es-test.tmp.bz2» -> «es-test.txt.bz2»
set -o pipefail ; lbzip2 -d < es-learn.txt.bz2 | /home/ferlanero/okb-engine-master/db/../tools/import_corpus.py es-full.dict | sort -rn | lbzip2 -9 > grams-es-full.csv.bz2.tmp
mv -f grams-es-full.csv.bz2.tmp grams-es-full.csv.bz2
set -o pipefail ; lbzip2 -d < grams-es-full.csv.bz2 | grep ';#NA;#NA;' | cut -f '1,4' -d';' \
 | grep -v '#TOTAL' | sort -rn | cut -d';' -f 2 | egrep -v '^(i)$' | tee words-es.txt \
         | sed -n "1,30000 p" > es-predict.dict.tmp  # ok i've re-implemented "head" with sed to avoid ugly sigpipes (which hurt with -o pipefail)
mv -f es-predict.dict.tmp es-predict.dict
set -o pipefail	; lbzip2 -d < es-learn.txt.bz2 | /home/ferlanero/okb-engine-master/db/../tools/import_corpus.py es-predict.dict | lbzip2 -9 > grams-es-learn.csv.bz2.tmp
/home/ferlanero/okb-engine-master/db/../tools/loadkb.py es-full.tre < es-full.dict
set -o pipefail ; lbzip2 -d < es-test.txt.bz2 | /home/ferlanero/okb-engine-master/db/../tools/import_corpus.py es-predict.dict | lbzip2 -9 > grams-es-test.csv.bz2.tmp
mv -f grams-es-learn.csv.bz2.tmp grams-es-learn.csv.bz2
Computing clusters for language es. Please make some coffee ...
 (logs can be found in clusters-es.log)
set -o pipefail ; lbzip2 -d < grams-es-learn.csv.bz2 | sort -rn | sed -n "1,13500000 p" \
 | /home/ferlanero/okb-engine-master/db/../tools/cluster -n 10 -o clusters-es.tmp > clusters-es.log 2>&1
mv -f clusters-es.tmp clusters-es.txt
mv -f grams-es-test.csv.bz2.tmp grams-es-test.csv.bz2
1000
set -o pipefail ; lbzip2 -d < grams-es-learn.csv.bz2 \
 | /home/ferlanero/okb-engine-master/db/../tools/clusterize.py -l 8 -w 200000 -c 500000 clusters-es.txt \
 | tee predict-es.txt \
 | /home/ferlanero/okb-engine-master/db/../tools/load_cdb_fslm.py predict-es-tmp.db
Import CSV corpus data ...
Dumping compressed ngram file ...
Dumping words to database ...
2000
lbzip2 -9fv predict-es.txt
lbzip2: compressing "predict-es.txt" to "predict-es.txt.bz2"
lbzip2: "predict-es.txt": compression ratio is 1:2.274, space savings is 56.02%
/home/ferlanero/okb-engine-master/db/../tools/db_param.py predict-es-tmp.db version 11
lbzip2 -9f predict-es-tmp.rpt
mv -f predict-es-tmp.db predict-es.db
mv -f predict-es-tmp.ng predict-es.ng
mv -f predict-es-tmp.rpt.bz2 predict-es.rpt.bz2
3000
4000
5000
6000
7000
8000
9000
10000
11000
12000
13000
14000
15000
16000
17000
18000
19000
20000
21000
22000
23000
24000
25000
26000
27000
28000
29000
30000
31000
32000
33000
34000
35000
36000
37000
38000
39000
40000
41000
42000
43000
44000
45000
46000
47000
48000
49000
50000
51000
52000
53000
54000
55000
56000
/home/ferlanero/okb-engine-master/db/../tools/loadkb.py es.tre < words-es.txt  # all word seens in learn corpus (smaller than full directory, but bigger than prediction learning dictionary)
OK es
sending incremental file list
es-full.tre
es.tre
predict-es.db
predict-es.ng
predict-es.rpt.bz2

sent 2,423,995 bytes  received 111 bytes  4,848,212.00 bytes/sec
total size is 2,423,052  speedup is 1.00