sporada/file-setup
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/file-setup.git synced 2024-12-25 19:04:18 +00:00
Code Issues Projects Releases Wiki Activity

Update Pipeline structure

Browse Source
This commit is contained in:
Patrick Jentsch 2022-01-18 12:58:42 +01:00
parent 3c9a800886
commit cdb4f1889c
5 changed files with 175 additions and 180 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
Dockerfile
View File

@ -9,38 +9,32 @@ ENV LANG=C.UTF-8
RUN apt-get update \
&& apt-get install --no-install-recommends --yes \
wget
imagemagick \
procps \
wget \
&& mv /etc/ImageMagick-6/policy.xml /etc/ImageMagick-6/policy.xml.bak
# Install the NLP pipeline and it's dependencies #
# Install the File setup pipeline and it's dependencies #
## Install pyFlow ##
ENV PYFLOW_VERSION=1.1.20
RUN wget --no-check-certificate --quiet \
"https://github.com/Illumina/pyflow/releases/download/v${PYFLOW_VERSION}/pyflow-${PYFLOW_VERSION}.tar.gz" \
&& tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
&& cd "pyflow-${PYFLOW_VERSION}" \
&& apt-get install --no-install-recommends --yes \
python2.7 \
&& python2.7 setup.py build install \
&& cd .. \
&& rm -r "pyflow-${PYFLOW_VERSION}" "pyflow-${PYFLOW_VERSION}.tar.gz"
&& tar -xzf "pyflow-${PYFLOW_VERSION}.tar.gz" \
&& cd "pyflow-${PYFLOW_VERSION}" \
&& apt-get install --no-install-recommends --yes \
python2.7 \
&& python2.7 setup.py build install \
&& cd - > /dev/null \
&& rm -r "pyflow-${PYFLOW_VERSION}" "pyflow-${PYFLOW_VERSION}.tar.gz"
## Further dependencies ##
RUN apt-get install --no-install-recommends --yes \
imagemagick \
procps \
python3.7 \
zip \
&& mv /etc/ImageMagick-6/policy.xml /etc/ImageMagick-6/policy.xml.bak
RUN rm -r /var/lib/apt/lists/*
## Install Pipeline ##
COPY file-setup /usr/local/bin
RUN rm -r /var/lib/apt/lists/*
ENTRYPOINT ["file-setup"]
CMD ["--help"]

21
LICENSE Normal file
View File

@ -0,0 +1,21 @@
MIT License
Copyright (c) 2021 Bielefeld University - CRC 1288 - INF
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

46
README.md
View File

@ -1,37 +1,37 @@
# File setup
This software implements a parallelized pipeline to setup image files. It is used for nopaque's File setup service but you can also use it standalone, for that purpose a convenient wrapper script is provided.
This software implements a parallelized pipeline to setup image files. It is used for nopaque's File setup service but you can also use it standalone, for that purpose a convenient wrapper script is provided. The pipeline is designed to run on Linux operating systems, but with some tweaks it should also run on Windows with WSL installed.
## Software used in this pipeline implementation
- Official Debian Docker image (buster-slim) and programs from its free repositories: https://hub.docker.com/_/debian
- Official Debian Docker image (buster-slim): https://hub.docker.com/_/debian
- Software from Debian Buster's free repositories
## Use this image
## Installation
1. Create input and output directories for the pipeline.
``` bash
mkdir -p /<my_data_location>/input /<my_data_location>/output
1. Install Docker and Python 3.
2. Clone this repository: `git clone https://gitlab.ub.uni-bielefeld.de/sfb1288inf/file-setup.git`
2. Build the Docker image: `docker build -t gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/file-setup:v0.1.0 file-setup`
3. Add the wrapper script (`wrapper/filesetup` relative to this README file) to your `${PATH}`.
4. Create working directories for the pipeline: `mkdir -p /<my_data_location>/{input,output}`.
## Use the Pipeline
1. Place your images files inside a subdirectory in `/<my_data_location>/input`. It should look similar to this:
```
.
|-- input
| |-- alice_in_wonderland
| |-- page-1.png
| |-- page-2.png
| |-- ...
| `-- page-x.png
`-- output
```
2. Place your images files inside a directory in `/<my_data_location>/input`.
3. Start the pipeline process. Check the pipeline help (`file-setup --help`) for more details.
```
# Option one: Use the wrapper script
## Install the wrapper script (only on first run). Get it from https://gitlab.ub.uni-bielefeld.de/sfb1288inf/file-setup/-/raw/1.0.0/wrapper/file-setup, make it executeable and add it to your ${PATH}
```bash
cd /<my_data_location>
file-setup -i input -o output
# Option two: Classic Docker style
docker run \
--rm \
-it \
-u $(id -u $USER):$(id -g $USER) \
-v /<my_data_location>/input:/input \
-v /<my_data_location>/output:/output \
gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/file-setup:1.0.0 \
-i /input \
-o /output
```
4. Check your results in the `/<my_data_location>/output` directory.

246
file-setup
View File

@ -1,29 +1,28 @@
#!/usr/bin/env python2.7
# coding=utf-8
"""A file setup pipeline for image file merging."""
__author__ = 'Patrick Jentsch <p.jentsch@uni-bielefeld.de>,' \
'Stephan Porada <porada@posteo.de>'
__version__ = '1.0.0'
''' File setup pipeline for image file merging. '''
__version__ = '0.1.0'
from argparse import ArgumentParser
from pyflow import WorkflowRunner
import json
import multiprocessing
import os
import sys
class FileSetupPipelineJob:
"""An file setup pipeline job class
class PipelineJob:
'''
File setup pipeline job class.
Each image containing input directory of the pipeline is represented as an
file setup pipeline job, which holds all necessary information for the
pipeline to process it.
Each input directory containing images is represented here together with
all necessary information for the pipeline to process it.
Arguments:
dir -- Path to the directory
output_dir -- Path to a directory, where job results a stored
"""
output_dir -- Path to a directory, where job results are stored
'''
def __init__(self, dir, output_dir):
self.dir = dir
@ -31,134 +30,118 @@ class FileSetupPipelineJob:
self.output_dir = output_dir
class FileSetupPipeline(WorkflowRunner):
def __init__(self, input_dir, output_dir, zip):
class CreatePDFWorkflow(WorkflowRunner):
def __init__(self, job):
self.job = job
def workflow(self):
'''
' ##################################################
' # convert #
' ##################################################
'''
n_cores = min(2, self.getNCores())
mem_mb = min(n_cores * 256, self.getMemMb())
cmd = 'ls -dv "{}/"* > "{}"'.format(
os.path.join(self.job.dir),
os.path.join(self.job.output_dir, 'inputs.txt')
)
cmd += ' && '
cmd += 'convert "@{}" "{}"'.format(
os.path.join(self.job.output_dir, 'inputs.txt'),
os.path.join(self.job.output_dir, '{}.pdf'.format(self.job.name))
)
cmd += ' && '
cmd += 'rm "{}"'.format(os.path.join(self.job.output_dir, 'inputs.txt')) # noqa
self.addTask(
'convert',
command=cmd,
memMb=mem_mb,
nCores=n_cores
)
class MainWorkflow(WorkflowRunner):
def __init__(self, input_dir, output_dir):
self.input_dir = input_dir
self.output_dir = output_dir
self.zip = zip
self.jobs = collect_jobs(self.input_dir, self.output_dir)
self.jobs = []
self.collect_jobs()
def collect_jobs(self):
for dir in os.listdir(self.input_dir):
if not os.path.isdir(os.path.join(self.input_dir, dir)):
continue
if not os.listdir(os.path.join(self.input_dir, dir)):
continue
# TODO: Filter for file types within the directory
job = PipelineJob(
os.path.join(self.input_dir, dir),
os.path.join(self.output_dir, dir)
)
self.jobs.append(job)
def workflow(self):
if not self.jobs:
return
# Create output and temporary directories
for job in self.jobs:
os.mkdir(job.output_dir)
'''
' ##################################################
' # setup output directory #
' # create-pdf #
' ##################################################
'''
setup_output_directory_tasks = []
create_pdf_tasks = []
for i, job in enumerate(self.jobs):
cmd = 'mkdir -p "{}"'.format(job.output_dir)
lbl = 'setup_output_directory_-_{}'.format(i)
task = self.addTask(command=cmd, label=lbl)
setup_output_directory_tasks.append(task)
task = self.addWorkflowTask(
'create_pdf_-_{}'.format(i),
CreatePDFWorkflow(job)
)
create_pdf_tasks.append(task)
'''
' ##################################################
' # pre file setup #
' ##################################################
'''
pre_file_setup_tasks = []
for i, job in enumerate(self.jobs):
input_file = os.path.join(job.output_dir, 'file_setup_input_files.txt') # noqa
cmd = 'ls -dQv "{}/"* >> "{}"'.format(job.dir, input_file)
deps = 'setup_output_directory_-_{}'.format(i)
lbl = 'pre_file_setup_-_{}'.format(i)
task = self.addTask(command=cmd, dependencies=deps, label=lbl)
pre_file_setup_tasks.append(task)
'''
' ##################################################
' # file setup #
' ##################################################
'''
file_setup_tasks = []
n_cores = max(1, int(self.getNCores() / len(self.jobs)))
for i, job in enumerate(self.jobs):
input_file = os.path.join(job.output_dir, 'file_setup_input_files.txt') # noqa
output_file = os.path.join(job.output_dir, '{}.pdf'.format(job.name)) # noqa
cmd = 'convert "@{}" "{}"'.format(input_file, output_file)
deps = 'pre_file_setup_-_{}'.format(i)
lbl = 'file_setup_-_{}'.format(i)
task = self.addTask(command=cmd, dependencies=deps, label=lbl,
nCores=n_cores)
file_setup_tasks.append(task)
'''
' ##################################################
' # post file setup #
' ##################################################
'''
post_file_setup_tasks = []
for i, job in enumerate(self.jobs):
input_file = os.path.join(job.output_dir, 'file_setup_input_files.txt') # noqa
cmd = 'rm "{}"'.format(input_file)
deps = 'file_setup_-_{}'.format(i)
lbl = 'post_file_setup_-_{}'.format(i)
task = self.addTask(command=cmd, dependencies=deps, label=lbl)
post_file_setup_tasks.append(task)
'''
' ##################################################
' # zip creation #
' ##################################################
'''
zip_creation_tasks = []
if self.zip is not None:
cmd = 'cd "{}"'.format(self.output_dir)
cmd += ' && '
cmd += 'zip'
cmd += ' -r'
cmd += ' "{}.zip" .'.format(self.zip)
cmd += ' -x "pyflow.data*"'
cmd += ' -i "*.pdf"'
cmd += ' && '
cmd += 'cd -'
deps = file_setup_tasks
lbl = 'zip_creation'
task = self.addTask(command=cmd, dependencies=deps, label=lbl)
zip_creation_tasks.append(task)
def collect_jobs(input_dir, output_dir):
jobs = []
for dir in os.listdir(input_dir):
if not os.path.isdir(os.path.join(input_dir, dir)):
continue
# TODO: Filter for file types
if not os.listdir(os.path.join(input_dir, dir)):
continue
job = FileSetupPipelineJob(os.path.join(input_dir, dir),
os.path.join(output_dir, dir))
jobs.append(job)
return jobs
self.waitForTasks()
for job in self.jobs:
# Track output files
relative_output_dir = os.path.relpath(job.output_dir, start=self.output_dir) # noqa
self.output_files.append(
{
'description': 'PDF file without text layer.',
'file': os.path.join(relative_output_dir, '{}.pdf'.format(job.name)), # noqa
'mimetype': 'application/pdf'
}
)
with open(os.path.join(self.output_dir, 'output_records.json'), 'w') as f: # noqa
json.dump(self.output_files, f, indent=4)
def parse_args():
parser = ArgumentParser(description='A file setup pipeline for image file merging', # noqa
prog='File setup pipeline')
parser.add_argument('-i', '--input-dir',
help='Input directory',
required=True)
parser.add_argument('-o', '--output-dir',
help='Output directory',
required=True)
parser.add_argument('--log-dir',
help='Logging directory')
parser.add_argument('--mem-mb',
help='Amount of system memory to be used (Default: min(--n-cores * 2048, available system memory))', # noqa
type=int)
parser.add_argument('--n-cores',
default=1,
help='Number of CPU threads to be used (Default: 1)',
type=int)
parser.add_argument('--zip',
help='Create one zip file per filetype')
parser.add_argument('-v', '--version',
action='version',
help='Returns the current version of the file setup pipeline', # noqa
version='%(prog)s {}'.format(__version__))
parser = ArgumentParser(description='Pipeline for merging images')
parser.add_argument(
'-i', '--input-dir', help='Input directory', required=True)
parser.add_argument(
'-o', '--output-dir', help='Output directory', required=True)
parser.add_argument(
'--log-dir', help='Logging directory (Default: --output-dir)')
parser.add_argument(
'--mem-mb',
help='Amount of system memory to be used (Default: min(--n-cores * 256, available system memory))', # noqa
type=int
)
parser.add_argument(
'--n-cores',
default=min(2, multiprocessing.cpu_count()),
help='Number of CPU threads to be used (Default: min(2, CPU count))',
type=int
)
parser.add_argument(
'-v', '--version',
action='version',
help='Returns the current version of the file setup pipeline',
version='%(prog)s {}'.format(__version__)
)
args = parser.parse_args()
# Set some tricky default values and check for insufficient input
@ -168,20 +151,17 @@ def parse_args():
raise Exception('--n-cores must be greater or equal 1')
if args.mem_mb is None:
max_mem_mb = int(os.popen('free -t -m').readlines()[-1].split()[1:][0])
args.mem_mb = min(args.n_cores * 2048, max_mem_mb)
if args.mem_mb < 2048:
raise Exception('--mem-mb must be greater or equal 2048')
if args.zip is not None and args.zip.lower().endswith('.zip'):
# Remove .zip file extension if provided
args.zip = args.zip[:-4]
args.zip = args.zip if args.zip else 'output'
args.mem_mb = min(args.n_cores * 256, max_mem_mb)
if args.mem_mb < 256:
raise Exception('--mem-mb must be greater or equal 256')
return args
def main():
args = parse_args()
file_setup_pipeline = FileSetupPipeline(args.input_dir, args.output_dir, args.zip) # noqa
retval = file_setup_pipeline.run(dataDirRoot=args.log_dir, memMb=args.mem_mb, nCores=args.n_cores) # noqa
main_workflow = MainWorkflow(args.input_dir, args.output_dir)
retval = main_workflow.run(
dataDirRoot=args.log_dir, memMb=args.mem_mb, nCores=args.n_cores) # noqa
sys.exit(retval)

10
wrapper/file-setup
View File

@ -6,7 +6,7 @@ import os
import subprocess
import sys
CONTAINER_IMAGE = 'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/file-setup:1.0.0'
CONTAINER_IMAGE = 'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/file-setup:v0.1.0' # noqa
CONTAINER_INPUT_DIR = '/input'
CONTAINER_OUTPUT_DIR = '/output'
CONTAINER_LOG_DIR = '/logs'
@ -19,17 +19,17 @@ parser.add_argument('-o', '--output-dir')
parser.add_argument('--log-dir')
args, remaining_args = parser.parse_known_args()
cmd = ['docker', 'run', '--rm', '-it', '-u', '{}:{}'.format(UID, GID)]
cmd = ['docker', 'run', '--rm', '-it', '-u', f'{UID}:{GID}']
if args.input_dir is not None:
mapping = os.path.abspath(args.input_dir) + ':' + CONTAINER_INPUT_DIR
mapping = f'{os.path.abspath(args.input_dir)}:{CONTAINER_INPUT_DIR}'
cmd += ['-v', mapping]
remaining_args += ['-i', CONTAINER_INPUT_DIR]
if args.output_dir is not None:
mapping = os.path.abspath(args.output_dir) + ':' + CONTAINER_OUTPUT_DIR
mapping = f'{os.path.abspath(args.output_dir)}:{CONTAINER_OUTPUT_DIR}'
cmd += ['-v', mapping]
remaining_args += ['-o', CONTAINER_OUTPUT_DIR]
if args.log_dir is not None:
mapping = os.path.abspath(args.log_dir) + ':' + CONTAINER_LOG_DIR
mapping = '{os.path.abspath(args.log_dir)}:{CONTAINER_LOG_DIR}'
cmd += ['-v', mapping]
remaining_args += ['--log-dir', CONTAINER_LOG_DIR]
cmd.append(CONTAINER_IMAGE)