corpus aligner

This commit is contained in:
Rafał Jaworski 2019-05-30 14:43:37 +02:00
parent 1b4d0de022
commit 285c742c65
4 changed files with 65 additions and 1 deletions

View File

@ -8,6 +8,14 @@ ENV LANG pl_PL.UTF-8
ENV LANGUAGE pl_PL:pl
ENV LC_ALL pl_PL.UTF-8
RUN apt-get install -y git mono-complete
RUN apt-get install -y git libfcgi-dev libpq-dev python3-psycopg2 nginx php apache2 libapache2-mod-php spawn-fcgi cmake g++ libboost-dev libboost-serialization-dev libboost-test-dev libboost-filesystem-dev libboost-system-dev libboost-program-options-dev libboost-iostreams-dev libboost-regex-dev libboost-locale-dev liblog4cpp5-dev libconfig++-dev libconfig-dev libpcre3-dev mono-complete python3-requests
RUN git clone https://git.code.sf.net/p/tmconcordia/code
RUN cd code && mkdir build && cd build && ../cmake.sh && make && make install && ldconfig
RUN git clone https://git.wmi.amu.edu.pl/rjawor/concordia-server.git
RUN cd concordia-server && mkdir index && mkdir build && cd build && ../cmake.sh && make
COPY fcgi_concordia /etc/nginx/sites-available
RUN rm /etc/nginx/sites-enabled/default
RUN ln -s /etc/nginx/sites-available/fcgi_concordia /etc/nginx/sites-enabled/fcgi_concordia
#CMD /usr/sbin/nginx -g "daemon on;" && sleep 4 && sh concordia-server/scripts/backgroundstart.sh && cd concordia-server/fast-aligner/ && make SRC_LANG=pl TRG_LANG=en CORPUS_NAME=opensubtitles_sample

3
align_corpus.sh Executable file
View File

@ -0,0 +1,3 @@
#!/bin/sh
docker run -it --rm --mount src="$(pwd)"/corpora,target=/concordia-server/fast-aligner/corpora,type=bind concordia-aligner:Dockerfile

50
fcgi_concordia Normal file
View File

@ -0,0 +1,50 @@
server {
listen 8800 default_server;
listen [::]:8800 default_server;
# SSL configuration
#
# listen 443 ssl default_server;
# listen [::]:443 ssl default_server;
#
# Note: You should disable gzip for SSL traffic.
# See: https://bugs.debian.org/773332
#
# Read up on ssl_ciphers to ensure a secure configuration.
# See: https://bugs.debian.org/765782
#
# Self signed certs generated by the ssl-cert package
# Don't use them in a production server!
#
# include snippets/snakeoil.conf;
root /var/www/html;
# Add index.php to the list if you are using PHP
index index.html index.htm index.nginx-debian.html;
server_name _;
location / {
fastcgi_pass 127.0.0.1:8000;
fastcgi_param GATEWAY_INTERFACE CGI/1.1;
fastcgi_param SERVER_SOFTWARE nginx;
fastcgi_param QUERY_STRING $query_string;
fastcgi_param REQUEST_METHOD $request_method;
fastcgi_param CONTENT_TYPE $content_type;
fastcgi_param CONTENT_LENGTH $content_length;
fastcgi_param SCRIPT_FILENAME $document_root$fastcgi_script_name;
fastcgi_param SCRIPT_NAME $fastcgi_script_name;
fastcgi_param REQUEST_URI $request_uri;
fastcgi_param DOCUMENT_URI $document_uri;
fastcgi_param DOCUMENT_ROOT $document_root;
fastcgi_param SERVER_PROTOCOL $server_protocol;
fastcgi_param REMOTE_ADDR $remote_addr;
fastcgi_param REMOTE_PORT $remote_port;
fastcgi_param SERVER_ADDR $server_addr;
fastcgi_param SERVER_PORT $server_port;
fastcgi_param SERVER_NAME $server_name;
}
}

3
setup.sh Executable file
View File

@ -0,0 +1,3 @@
#!/bin/sh
docker build --tag="concordia-aligner:Dockerfile" .