publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-13 04:04:18 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix docker

Browse source
This commit is contained in:
ericiwamoto 2024-12-23 08:05:18 -08:00 • committed by Carlos Felix
commit 682b2d34a7
10 changed files with 111 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

51
data/data-pipeline/Dockerfile
View file

@ -1,4 +1,4 @@
FROM ubuntu:20.04
FROM ubuntu:22.04
ENV TZ=America/Los_Angeles
@ -10,13 +10,13 @@ RUN apt-get update && TZ=America/Los_Angeles DEBIAN_FRONTEND=noninteractive apt-
git \
unzip \
wget \
python3-dev \
python3-pip \
gdal-bin
software-properties-common \
libsqlite3-dev \
zlib1g-dev
# tippeanoe
# tippecanoe
RUN apt-get update
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
RUN apt-get install -y software-properties-common libsqlite3-dev zlib1g-dev
RUN apt-add-repository -y ppa:git-core/ppa
RUN mkdir -p /tmp/tippecanoe-src && git clone https://github.com/mapbox/tippecanoe.git /tmp/tippecanoe-src
WORKDIR /tmp/tippecanoe-src
@ -24,26 +24,35 @@ RUN /bin/sh -c make && make install
## gdal
RUN add-apt-repository ppa:ubuntugis/ppa
RUN apt-get -y install gdal-bin
RUN apt-get -y install gdal-bin libgdal-dev
# Install python3.10
RUN add-apt-repository ppa:deadsnakes/ppa
RUN apt install -y python3.10-dev
RUN apt install -y python3-pip
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
RUN update-alternatives --config python3
# Copy all project files into the container
COPY . /data-pipeline
WORKDIR /data-pipeline
# Python package installation using poetry. See:
# https://stackoverflow.com/questions/53835198/integrating-python-poetry-with-docker
ENV PYTHONFAULTHANDLER=1 \
PYTHONUNBUFFERED=1 \
PYTHONHASHSEED=random \
PIP_NO_CACHE_DIR=off \
PIP_DISABLE_PIP_VERSION_CHECK=on \
PIP_DEFAULT_TIMEOUT=100 \
POETRY_VERSION=1.1.12
WORKDIR /data-pipeline
COPY . /data-pipeline
PYTHONUNBUFFERED=1 \
PYTHONHASHSEED=random \
PIP_NO_CACHE_DIR=off \
PIP_DISABLE_PIP_VERSION_CHECK=on \
PIP_DEFAULT_TIMEOUT=100 \
POETRY_VERSION=1.8.4
RUN pip install "poetry==$POETRY_VERSION"
RUN poetry config virtualenvs.create false \
&& poetry config virtualenvs.in-project false \
&& poetry install --no-dev --no-interaction --no-ansi
&& poetry config virtualenvs.in-project false \
&& poetry install --only main --no-interaction --no-ansi
RUN pip install openpyxl
# Copy all project files into the container
CMD python3 -m data_pipeline.application data-full-run --check -s aws
# Default behavior is to output the options for "full-run". This prevents the entire pipeline from running unintentionally.
ENTRYPOINT [ "poetry", "run", "python3", "-m", "data_pipeline.application"]
CMD ["full-run", "--help"]