getting paperless-ng ready for the first release.

This commit is contained in:
Jonas Winkler
2020-11-14 12:10:38 +01:00
parent a0479d33b5
commit 12b70a13be
13 changed files with 150 additions and 23 deletions

View File

@@ -1,94 +0,0 @@
#!/bin/bash
set -e
# Source: https://github.com/sameersbn/docker-gitlab/
map_uidgid() {
USERMAP_ORIG_UID=$(id -u paperless)
USERMAP_ORIG_GID=$(id -g paperless)
USERMAP_NEW_UID=${USERMAP_UID:-$USERMAP_ORIG_UID}
USERMAP_NEW_GID=${USERMAP_GID:-${USERMAP_ORIG_GID:-$USERMAP_NEW_UID}}
if [[ ${USERMAP_NEW_UID} != "${USERMAP_ORIG_UID}" || ${USERMAP_NEW_GID} != "${USERMAP_ORIG_GID}" ]]; then
echo "Mapping UID and GID for paperless:paperless to $USERMAP_NEW_UID:$USERMAP_NEW_GID"
usermod -u "${USERMAP_NEW_UID}" paperless
groupmod -o -g "${USERMAP_NEW_GID}" paperless
fi
}
migrations() {
(
# flock is in place to prevent multiple containers from doing migrations
# simultaneously. This also ensures that the db is ready when the command
# of the current container starts.
flock 200
sudo -HEu paperless python3 manage.py migrate
) 200>/usr/src/paperless/data/migration_lock
}
initialize() {
map_uidgid
for dir in export data data/index media media/documents media/documents/originals media/documents/thumbnails; do
if [[ ! -d "../$dir" ]]
then
echo "creating directory ../$dir"
mkdir ../$dir
fi
done
chown -R paperless:paperless ../
migrations
}
install_languages() {
local langs="$1"
read -ra langs <<<"$langs"
# Check that it is not empty
if [ ${#langs[@]} -eq 0 ]; then
return
fi
apt-get update
for lang in "${langs[@]}"; do
pkg="tesseract-ocr-$lang"
# English is installed by default
#if [[ "$lang" == "eng" ]]; then
# continue
#fi
if dpkg -s $pkg &> /dev/null; then
echo "package $pkg already installed!"
continue
fi
if ! apt-cache show $pkg &> /dev/null; then
echo "package $pkg not found! :("
continue
fi
echo "Installing package $pkg..."
if ! apt-get -y install "$pkg" &> /dev/null; then
echo "Could not install $pkg"
exit 1
fi
done
}
initialize
# Install additional languages if specified
if [[ ! -z "$PAPERLESS_OCR_LANGUAGES" ]]; then
install_languages "$PAPERLESS_OCR_LANGUAGES"
fi
if [[ "$1" != "/"* ]]; then
exec sudo -HEu paperless python3 manage.py "$@"
else
exec "$@"
fi

View File

@@ -1,48 +0,0 @@
bind = '127.0.0.1:8000'
backlog = 2048
workers = 3
worker_class = 'sync'
worker_connections = 1000
timeout = 20
keepalive = 2
spew = False
daemon = False
pidfile = None
umask = 0
user = None
group = None
tmp_upload_dir = None
loglevel = 'info'
errorlog = '-'
accesslog = '-'
proc_name = None
def pre_fork(server, worker):
pass
def pre_exec(server):
server.log.info("Forked child, re-executing.")
def when_ready(server):
server.log.info("Server is ready. Spawning workers")
def worker_int(worker):
worker.log.info("worker received INT or QUIT signal")
## get traceback info
import threading, sys, traceback
id2name = dict([(th.ident, th.name) for th in threading.enumerate()])
code = []
for threadId, stack in sys._current_frames().items():
code.append("\n# Thread: %s(%d)" % (id2name.get(threadId,""),
threadId))
for filename, lineno, name, line in traceback.extract_stack(stack):
code.append('File: "%s", line %d, in %s' % (filename,
lineno, name))
if line:
code.append(" %s" % (line.strip()))
worker.log.debug("\n".join(code))
def worker_abort(worker):
worker.log.info("worker received SIGABRT signal")

View File

@@ -1,96 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE policymap [
<!ELEMENT policymap (policy)+>
<!ATTLIST policymap xmlns CDATA #FIXED ''>
<!ELEMENT policy EMPTY>
<!ATTLIST policy xmlns CDATA #FIXED '' domain NMTOKEN #REQUIRED
name NMTOKEN #IMPLIED pattern CDATA #IMPLIED rights NMTOKEN #IMPLIED
stealth NMTOKEN #IMPLIED value CDATA #IMPLIED>
]>
<!--
Configure ImageMagick policies.
Domains include system, delegate, coder, filter, path, or resource.
Rights include none, read, write, execute and all. Use | to combine them,
for example: "read | write" to permit read from, or write to, a path.
Use a glob expression as a pattern.
Suppose we do not want users to process MPEG video images:
<policy domain="delegate" rights="none" pattern="mpeg:decode" />
Here we do not want users reading images from HTTP:
<policy domain="coder" rights="none" pattern="HTTP" />
The /repository file system is restricted to read only. We use a glob
expression to match all paths that start with /repository:
<policy domain="path" rights="read" pattern="/repository/*" />
Lets prevent users from executing any image filters:
<policy domain="filter" rights="none" pattern="*" />
Any large image is cached to disk rather than memory:
<policy domain="resource" name="area" value="1GP"/>
Define arguments for the memory, map, area, width, height and disk resources
with SI prefixes (.e.g 100MB). In addition, resource policies are maximums
for each instance of ImageMagick (e.g. policy memory limit 1GB, -limit 2GB
exceeds policy maximum so memory limit is 1GB).
Rules are processed in order. Here we want to restrict ImageMagick to only
read or write a small subset of proven web-safe image types:
<policy domain="delegate" rights="none" pattern="*" />
<policy domain="filter" rights="none" pattern="*" />
<policy domain="coder" rights="none" pattern="*" />
<policy domain="coder" rights="read|write" pattern="{GIF,JPEG,PNG,WEBP}" />
-->
<policymap>
<!-- <policy domain="system" name="shred" value="2"/> -->
<!-- <policy domain="system" name="precision" value="6"/> -->
<!-- <policy domain="system" name="memory-map" value="anonymous"/> -->
<!-- <policy domain="system" name="max-memory-request" value="256MiB"/> -->
<!-- <policy domain="resource" name="temporary-path" value="/tmp"/> -->
<policy domain="resource" name="memory" value="256MiB"/>
<policy domain="resource" name="map" value="512MiB"/>
<policy domain="resource" name="width" value="16KP"/>
<policy domain="resource" name="height" value="16KP"/>
<!-- <policy domain="resource" name="list-length" value="128"/> -->
<policy domain="resource" name="area" value="128MB"/>
<policy domain="resource" name="disk" value="1GiB"/>
<!-- <policy domain="resource" name="file" value="768"/> -->
<!-- <policy domain="resource" name="thread" value="4"/> -->
<!-- <policy domain="resource" name="throttle" value="0"/> -->
<!-- <policy domain="resource" name="time" value="3600"/> -->
<!-- <policy domain="coder" rights="none" pattern="MVG" /> -->
<!-- <policy domain="module" rights="none" pattern="{PS,PDF,XPS}" /> -->
<!-- <policy domain="delegate" rights="none" pattern="HTTPS" /> -->
<!-- <policy domain="path" rights="none" pattern="@*" /> -->
<!-- <policy domain="cache" name="memory-map" value="anonymous"/> -->
<!-- <policy domain="cache" name="synchronize" value="True"/> -->
<!-- <policy domain="cache" name="shared-secret" value="passphrase" stealth="true"/> -->
<!-- <policy domain="system" name="pixel-cache-memory" value="anonymous"/> -->
<!-- <policy domain="system" name="shred" value="2"/> -->
<!-- <policy domain="system" name="precision" value="6"/> -->
<!-- not needed due to the need to use explicitly by mvg: -->
<!-- <policy domain="delegate" rights="none" pattern="MVG" /> -->
<!-- use curl -->
<policy domain="delegate" rights="none" pattern="URL" />
<policy domain="delegate" rights="none" pattern="HTTPS" />
<policy domain="delegate" rights="none" pattern="HTTP" />
<!-- in order to avoid to get image with password text -->
<policy domain="path" rights="none" pattern="@*"/>
<!-- disable ghostscript format types -->
<policy domain="coder" rights="none" pattern="PS" />
<policy domain="coder" rights="none" pattern="PS2" />
<policy domain="coder" rights="none" pattern="PS3" />
<policy domain="coder" rights="none" pattern="EPS" />
<policy domain="coder" rights="read|write" pattern="PDF" />
<policy domain="coder" rights="none" pattern="XPS" />
</policymap>

View File

@@ -1,35 +0,0 @@
[supervisord]
nodaemon=true ; start in foreground if true; default false
logfile=/var/log/supervisord/supervisord.log ; main log file; default $CWD/supervisord.log
pidfile=/var/run/supervisord/supervisord.pid ; supervisord pidfile; default supervisord.pid
logfile_maxbytes=50MB ; max main logfile bytes b4 rotation; default 50MB
logfile_backups=10 ; # of main logfile backups; 0 means none, default 10
loglevel=info ; log level; default info; others: debug,warn,trace
user=root
[program:gunicorn]
command=gunicorn -c /usr/src/paperless/gunicorn.conf.py -b 0.0.0.0:8000 paperless.wsgi
user=paperless
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:consumer]
command=python3 manage.py document_consumer
user=paperless
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:scheduler]
command=python3 manage.py qcluster
user=paperless
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0