UTF-8 do IL2redia odstranit poznámky v závorkách:$ cd /corp/CZESL/BARE-redia/in-il2 $ for ff in *; do echo $ff; perl -i -pe 's/([^\ ])\([^\ ]+\)\ /$1 /g' $ff; done
$ cd /corp/CZESL/BARE-corr/in-il2 $ for ff in *; do echo $ff; perl -i -pe 's/\ ([\,\.\!\?\:\;])/$1/g' $ff; done
$ for ff in *; do echo $ff; perl -i -pe 's/\|.//g' $ff; done
$ make-corp.sh -t vert-morg -v -p8
vert-rules-frazrl-rulh1-tag:$ make-corp.sh -s vert-morg -t vert-rules -g -o wide_vertical -v -p8 $ make-whole-corp.sh -t frazrl -T tag -v -p8
vert-tag vert-tag-rules-frazrl-rulh1-tagvert-morf:$ cd .../vert-morf $ for ff in *; do echo $ff; sed -i -e '1i\ ' $ff; done
vert-tag-guess$ cd .../vert-tag $ for ff in *; do echo $ff; paste $ff ../vert-morf/$ff \ | perl -pe 's/[1-9\-](\t[^\t]+\t[^\ ]+\ X\@)/\@$1/' \ | cut -f1-2 | perl -pe 's/^\t$//' > ../vert-tag-guess/$ff; done
vert-rules-frazrl-rulh1-tag-guess a vytvořit v něm soubory podle předchozího bodu$ cd ~/PROJEKTY/CZESL/KORPUS/romove/xml
$ for ff in *.a.xml; do echo $ff; \
saxon $ff ../../../XSL/vertikala.xsl speaker=$(basename $(cd ..; pwd)) \
| grep -v "xml version" \
| grep . \
| perl -pe 's/^[ ]*//' \
| perl -pe 's/xmlns[^\ ]+ //' \
| perl -pe 's/id="[^\"]+\-([^\"]+)"/id="$1"/' > ../vert/${ff%.a.xml}.vert; done
$ for ff in *; do echo $ff; norm-utf8 $ff | simple-http-ent.pl |\
recode UTF8..l2 > ../in-il2/${ff%.txt1}; done
vert.$ cd /array/czesl/ames-korpus/4CzeSL_kvalifikacni_prace $ mkdir vert-vert $ cd vert $ for ff in *; do echo $ff; \ echo "<doc name=\"$ff\" group=\"kval\">" > ../vert-vert/$ff; \ simple-amper.pl < $ff | simple-corp.pl >> ../vert-vert/$ff; \ echo "</doc>" >> ../vert-vert/$ff; done
for ff in *; do echo $ff; perl -i -pe 's/&/&/' $ff; done
$ cd .../vert $ for ff in *; do echo $ff; \ entity < $ff |\ entity2 |\ recode l2..UTF8 |\ simple-http-utf8.pl > ../vert-utf8/$ff; done
$ cd orig
$ for ff in *.plain; do echo $ff; \
dos2unix < $ff |\
simple-uvoz.pl |\
recode UTF8..l2 |\
grep -v '&dt:' |\
simple-dot-l2.pl |\
cat -s |\
awk '/^$/ && !f{f=1;next}1' > ../vert/${ff%.plain}; done
mkdir vert-vert.$ cd ../vert-vert $ for ff in *; do echo $ff; perl -i -pe 's:</doc>:</s>\n</doc>:' $ff; done $ for ff in *; do echo $ff; perl -i -pe 's/&priv:(.*)/&priv;/' $ff; done $ for ff in *; do echo $ff; perl -i -pe 's/&unclear/&unclear;/' $ff; done $ for ff in *; do echo $ff; perl -i -pe 's/^&$/&/' $ff; done
$ cd .../vert-utf8 $ for ff in *; do echo $ff; \ devert.pl < $ff |\ ~/PROJEKTY/CZESL/Korektor/korektor ~/PROJEKTY/CZESL/Korektor/spellchecking_h2mor.conf |\ perl -pe 's/(spelling|grammar) original/$1_original/g' |\ perl -pe 's/" suggestions/"_suggestions/g' |\ perl -pe 's/ /\n/g' > ../vert-corr-med/$ff; done $ cd ../vert-corr-med $ for ff in *; do echo $ff; \ rekorekt.pl < $ff > ../vert-corr/$ff; done
$ cd .../vert-corr $ for ff in *; do echo $ff; \ cstocs --fillstring='_' utf8 il2 < $ff |\ cut -f1 > ../tag-corr/vert/$ff; done
$ cd .../vert-corr $ for ff in *; do echo $ff; \ cstocs --fillstring='_' utf8 il2 < $ff |\ perl -pe 's/.*\t(.*)\t.*/$1/' > ../tag-ori/vert/$ff; done
Slouží jako dočasná náhražka AMESu.
Adresářová struktura:
/store/czesl/kontrolori/k_oprave/cesi
/neslovani
/romove
/slovani
/ke_konverzi/...
/konvertovane/...
/anotatori/cesi/brtnova/download
/upload
/komrskova/download
/upload
/kukrechtova/...
/poncarova/...
/prchlikova/...
/vokacova/...
/neslovani/hanova/...
/havlikova/...
/karvaiova/...
/kristufkova/...
/moldova/...
/nenutil/...
/pliskova/...
/stechova/...
/svak/...
/vavrickova/...
/zudova/...
/romove/cerna/...
/dvorakova/...
/frnochovaad/...
/hubena/...
/churanova/...
/maresova/...
/simek/...
/svarcova/...
/zima/...
/zitova/...
/slovani/frnochovaan/...
/hrabalova/...
/hajkova/...
/halbichova/...
/kominova/...
/novakova/...
/rybczynska/...
/simunkova/...
/tesar/...
/vlasak/...
/zakova/...
Přístupová práva:
czesl# lla total 20 drwxr-xr-x 5 root root 4096 2011-06-03 15:43 ./ drwxr-xr-x 3 root root 4096 2011-06-03 17:08 ../ drwxr-xr-x 6 root root 4096 2011-06-03 14:47 anotatori/ drwxr-xr-x 5 root root 4096 2011-06-03 14:40 kontrolori/
kontrolori# lla total 20 drwxr-xr-x 5 root root 4096 2011-06-03 14:40 ./ drwxr-xr-x 5 root root 4096 2011-06-03 15:43 ../ drwxrwxr-x 6 root kontrolor 4096 2011-05-25 15:39 k_oprave/ drwxrwxr-x 6 root kontrolor 4096 2011-05-25 15:38 ke_konverzi/ drwxrwxr-x 6 root kontrolor 4096 2011-05-25 15:38 konvertovane/ konvertovane# lla total 24 drwxrwxr-x 6 root kontrolor 4096 2011-05-25 15:38 ./ drwxr-xr-x 5 root root 4096 2011-06-03 14:40 ../ drwxrwxr-x 2 root kontrolor 4096 2011-06-03 19:35 cesi/ drwxrwxr-x 2 root kontrolor 4096 2011-05-25 15:38 neslovani/ drwxrwxr-x 2 root kontrolor 4096 2011-05-25 15:38 romove/ drwxrwxr-x 2 root kontrolor 4096 2011-05-25 15:38 slovani/
anotatori# lla total 24 drwxr-xr-x 6 root root 4096 2011-06-03 14:47 ./ drwxr-xr-x 5 root root 4096 2011-06-03 15:43 ../ drwxr-xr-x 9 root root 4096 2011-06-03 19:00 cesi/ drwxr-xr-x 2 root root 4096 2011-06-03 14:47 neslovani/ drwxr-xr-x 2 root root 4096 2011-06-03 14:47 romove/ drwxr-xr-x 2 root root 4096 2011-06-03 14:47 slovani/ cesi# lla total 36 drwxr-xr-x 9 root root 4096 2011-06-03 19:00 ./ drwxr-xr-x 6 root root 4096 2011-06-03 14:47 ../ drwxrwx--- 2 root www-data 4096 2011-06-03 19:46 .files/ drwxr-xr-x 4 root root 4096 2011-06-03 14:30 Brtnova/ drwxr-xr-x 4 root root 4096 2011-06-03 18:59 Komrskova/ drwxr-xr-x 4 root root 4096 2011-06-03 18:59 Kukrechtova/ drwxr-xr-x 4 root root 4096 2011-06-03 18:59 Poncarova/ drwxr-xr-x 4 root root 4096 2011-06-03 18:59 Prchlikova/ drwxr-xr-x 4 root root 4096 2011-06-03 18:59 Vokacova/ Brtnova# lla total 16 drwxr-xr-x 4 root root 4096 2011-06-03 14:30 ./ drwxr-xr-x 9 root root 4096 2011-06-03 19:00 ../ drwxrwxr-x 2 root www-data 4096 2011-06-03 19:46 download/ drwxr-xr-x 2 brtnova anotator 4096 2011-06-03 19:45 upload/
kontrolor:x:10000:jhana anotator:x:10002:
hrdlickova:x:10001:10000:Tereza Hrdlickova:/store/czesl:/usr/bin/scponly
stindlova:x:10002:10002:Barbora Stindlova:/store/czesl/anotatori/neslovani:/usr/bin/scponly pierscieniak:x:10003:10002:Piotr Pawel Pierscieniak:/store/czesl/anotatori/slovani:/usr/bin/scponly bedrichova:x:10004:10002:Zuzanna Bedrichova:/store/czesl/anotatori/romove:/usr/bin/scponly hlavackova:x:10005:10002:Eva Hlavackova:/store/czesl/anotatori/cesi:/usr/bin/scponly
Vytvoření uživatele:
useradd -d /store/czesl/anotatori/neslovani -c "Barbora Stindlova" -g 10002 \ -M -s /usr/bin/scponly -u 10002 stindlova
Uživatel webu:
$ lla /var/www/html/anotatori/.files -rw-rw-r-- 1 skoumal apache 91 Jun 1 11:14 .skoumal $ cat /var/www/html/anotatori/.files/.skoumal 2a5a166d5d7fe042bd0d2e0f78ab9488:hana.skoumalova@ff.cuni.cz:/store/czesl/kontrolori/konvertovane/cesi