minor docker process tweaks

Dockerfile

@@ -1,9 +1,9 @@
 # This is the Dockerfile for ArchiveBox, it includes the following major pieces:
 #     git, curl, wget, python3, youtube-dl, google-chrome-stable, ArchiveBox
 # Usage:
-#     docker build . -t archivebox:latest
-#     docker run -v=$PWD/data:/data archivebox:latest archivebox init
-#     echo 'https://example.com' | docker run -v=$PWD/data:/data -i archivebox:latest archivebox add
+#     docker build . -t archivebox
+#     docker run -v "$PWD/data":/data archivebox init
+#     docker run -v "$PWD/data":/data archivebox add 'https://example.com'
 # Documentation:
 #     https://github.com/pirate/ArchiveBox/wiki/Docker#docker
 
@@ -43,8 +43,7 @@ RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selectio
        fonts-symbola \
        fonts-noto \
        fonts-freefont-ttf \
-    && rm -rf /var/lib/apt/lists/* \
-    && pip install --upgrade --no-cache-dir pip setuptools
+    && rm -rf /var/lib/apt/lists/*
 
 # Run everything from here on out as non-privileged user
 RUN groupadd --system archivebox \
@@ -54,6 +53,7 @@ ADD . "$CODE_PATH"
 WORKDIR "$CODE_PATH"
 ENV PATH="$VENV_PATH/bin:${PATH}"
 RUN python -m venv --clear --symlinks "$VENV_PATH" \
+    && pip install --upgrade pip setuptools \
     && pip install -e .
 
 VOLUME "$DATA_PATH"
@@ -62,5 +62,7 @@ EXPOSE 8000
 ENV CHROME_BINARY=google-chrome \
     CHROME_SANDBOX=False
 
-ENTRYPOINT ["dumb-init", "--", "/app/bin/entrypoint.sh", "archivebox"]
+RUN env ALLOW_ROOT=True archivebox version
+
+ENTRYPOINT ["dumb-init", "--", "/app/bin/docker_entrypoint.sh", "archivebox"]
 CMD ["server", "0.0.0.0:8000"]

bin/entrypoint.sh → bin/docker_entrypoint.sh

@@ -1,22 +1,24 @@
 #!/usr/bin/env bash
 
-# detect userid:groupid of contents of data folder
+COMMAND="$*"
+
+# Autodetect UID,GID of host user based on ownership of files in the data volume
 DATA_DIR="${DATA_DIR:-/data}"
 ARCHIVEBOX_USER="${ARCHIVEBOX_USER:-archivebox}"
 
-# Autodetect UID and GID of host user based on ownership of files in the volume
 USID=$(stat --format="%u" "$DATA_DIR")
 GRID=$(stat --format="%g" "$DATA_DIR")
-COMMAND="$*"
-
-# run django as the host user's uid:gid so that any files touched have the same permissions as outside the container
-# e.g. ./manage.py runserver
-
-chown "$USID":"$GRID" "$DATA_DIR"
 
+# If user is not root, modify the archivebox user+files to have the same uid,gid
 if [[ "$USID" != 0 && "$GRID" != 0 ]]; then
+    chown "$USID":"$GRID" "$DATA_DIR"
     usermod -u "$USID" "$ARCHIVEBOX_USER"
     groupmod -g "$GRID" "$ARCHIVEBOX_USER"
     chown -R "$USID":"$GRID" "/home/$ARCHIVEBOX_USER"
 fi
+
+# run django as the new archivebox user
+# any files touched will have the same uid,gid
+# inside docker and outside docker on the host
 gosu "$ARCHIVEBOX_USER" bash -c "$COMMAND"
+# e.g. "archivebox server"

bin/lint.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+
+### Bash Environment Setup
+# http://redsymbol.net/articles/unofficial-bash-strict-mode/
+# https://www.gnu.org/software/bash/manual/html_node/The-Set-Builtin.html
+# set -o xtrace
+set -o errexit
+set -o errtrace
+set -o nounset
+set -o pipefail
+IFS=$'\n'
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && cd .. && pwd )"
+
+source "$DIR/.venv/bin/activate"
+
+flake8 archivebox
+mypy archivebox

bin/test.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+
+### Bash Environment Setup
+# http://redsymbol.net/articles/unofficial-bash-strict-mode/
+# https://www.gnu.org/software/bash/manual/html_node/The-Set-Builtin.html
+# set -o xtrace
+set -o errexit
+set -o errtrace
+set -o nounset
+set -o pipefail
+IFS=$'\n'
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && cd .. && pwd )"
+
+source "$DIR/.venv/bin/activate"
+
+pytest