Added Docker build (#126)

* Added Docker build

* Bugfix Build and push Docker image

* Bugfix actions

* Bugfix github actions

* Bugfix actions

* Bugfix actions

* Added push on Docker Hub

* Bugfix actions

* Bugfix actions

* Test

* Bugfix actions

* Bugfix actions

* Fixed build docker  GitHub Container Registry

* Added publish to PyPI

* Improved cli code

* Fixed tests and minor refactoring

* Minor changes

Author: fedelemantuano

.github/workflows/main.yml

@@ -1,4 +1,4 @@
-name: Python application
+name: Python application and Docker image CI
 
 on:
   push:
@@ -65,3 +65,96 @@ jobs:
           path: |
             dist/mail-parser-*.tar.gz
             dist/mail_parser-*.whl
+
+      - name: Publish to PyPI
+        if: matrix.python-version == '3.10' && startsWith(github.ref, 'refs/tags/')
+        uses: pypa/gh-action-pypi-publish@v1.5.1
+        with:
+          user: ${{ secrets.PYPI_USERNAME }}
+          password: ${{ secrets.PYPI_PASSWORD }}
+
+  docker:
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: docker.io
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract branch or tag name
+        id: extract_ref
+        run: |
+          if [ -n "${GITHUB_HEAD_REF}" ]; then
+            REF_NAME=${GITHUB_HEAD_REF}
+          else
+            REF_NAME=$(git describe --tags --exact-match 2>/dev/null || git rev-parse --abbrev-ref HEAD)
+          fi
+          echo "REF_NAME=${REF_NAME,,}" >> $GITHUB_ENV
+
+      - name: Debug REF_NAME
+        run: echo "REF_NAME=${{ env.REF_NAME }}"
+
+      - name: Build and push Docker image on GitHub Container Registry
+        run: |
+          cd docker
+          IMAGE_NAME=ghcr.io/ghcr.io/spamscope/mail-parser/mailparser
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+            TAG=${GITHUB_REF#refs/tags/}
+            docker build \
+              --label "org.opencontainers.image.source=${{ github.repositoryUrl }}" \
+              --label "org.opencontainers.image.description=Easy way to pass from raw mail to Python object" \
+              --label "org.opencontainers.image.licenses=Apache-2.0" \
+              --build-arg BRANCH=$TAG \
+              -t $IMAGE_NAME:$TAG \
+              -t $IMAGE_NAME:latest .
+            docker push $IMAGE_NAME:$TAG
+            docker push $IMAGE_NAME:latest
+          else
+            docker build \
+              --label "org.opencontainers.image.source=${{ github.repositoryUrl }}" \
+              --label "org.opencontainers.image.description=Easy way to pass from raw mail to Python object" \
+              --label "org.opencontainers.image.licenses=Apache-2.0" \
+              --build-arg BRANCH=${{ env.REF_NAME }} \
+              -t $IMAGE_NAME:develop .
+            docker push $IMAGE_NAME:develop
+          fi
+
+      - name: Build and push Docker image on Docker Hub
+        run: |
+          cd docker
+          IMAGE_NAME=docker.io/${{ secrets.DOCKER_USERNAME }}/spamscope-mail-parser
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+            TAG=${GITHUB_REF#refs/tags/}
+            docker build \
+              --label "org.opencontainers.image.source=${{ github.repositoryUrl }}" \
+              --label "org.opencontainers.image.description=Easy way to pass from raw mail to Python object" \
+              --label "org.opencontainers.image.licenses=Apache-2.0" \
+              --build-arg BRANCH=$TAG \
+              -t $IMAGE_NAME:$TAG \
+              -t $IMAGE_NAME:latest .
+            docker push $IMAGE_NAME:$TAG
+            docker push $IMAGE_NAME:latest
+          else
+            docker build \
+              --label "org.opencontainers.image.source=${{ github.repositoryUrl }}" \
+              --label "org.opencontainers.image.description=Easy way to pass from raw mail to Python object" \
+              --label "org.opencontainers.image.licenses=Apache-2.0" \
+              --build-arg BRANCH=${{ env.REF_NAME }} \
+              -t $IMAGE_NAME:develop .
+            docker push $IMAGE_NAME:develop
+          fi

Makefile

@@ -45,7 +45,7 @@ clean-tests: ## remove test and coverage artifacts
 
 clean-all: clean-tests clean-build  ## remove all tests and build files
 
-test: clean-tests ## run tests quickly with the default Python
+unittest: clean-tests ## run tests quickly with the default Python
 	pytest
 
 pre-commit:  ## run pre-commit on all files

docker/Dockerfile

@@ -1,11 +1,12 @@
-FROM python
+FROM python:3.10-slim-bullseye
 ENV MAIL_PARSER_PATH=/tmp/mailparser
 ARG BRANCH=develop
-RUN apt-get -yqq update; \
-    apt-get -yqq --no-install-recommends install libemail-outlook-message-perl; \
-    apt-get clean; \
-    rm -rf /var/lib/apt/lists/*; \
-    git clone -b $BRANCH --single-branch https://github.com/SpamScope/mail-parser.git $MAIL_PARSER_PATH; \
-    cd $MAIL_PARSER_PATH && python setup.py install
-ENTRYPOINT ["mailparser"]
+RUN apt-get -yqq update && \
+    apt-get -yqq --no-install-recommends install libemail-outlook-message-perl git && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* && \
+    git clone -b ${BRANCH} --single-branch https://github.com/SpamScope/mail-parser.git ${MAIL_PARSER_PATH} && \
+    cd ${MAIL_PARSER_PATH} && \
+    python setup.py install
+ENTRYPOINT ["mail-parser"]
 CMD ["-h"]

docker/README.md

@@ -1,33 +1,33 @@
-[![Build Status](https://travis-ci.org/SpamScope/mail-parser.svg?branch=develop)](https://travis-ci.org/SpamScope/mail-parser)
-[![](https://images.microbadger.com/badges/image/fmantuano/spamscope-mail-parser.svg)](https://microbadger.com/images/fmantuano/spamscope-mail-parser "Get your own image badge on microbadger.com")
+[![PyPI - Version](https://img.shields.io/pypi/v/mail-parser)](https://pypi.org/project/mail-parser/)
+[![Coverage Status](https://coveralls.io/repos/github/SpamScope/mail-parser/badge.svg?branch=develop)](https://coveralls.io/github/SpamScope/mail-parser?branch=develop)
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/mail-parser?color=blue)](https://pypistats.org/packages/mail-parser)
 
 ![SpamScope](https://raw.githubusercontent.com/SpamScope/spamscope/develop/docs/logo/spamscope.png)
 
 # fmantuano/spamscope-mail-parser
-
-This Dockerfile represents a Docker image that encapsulates mail-parser. The [official image](https://hub.docker.com/r/fmantuano/spamscope-mail-parser/) is on Docker Hub.
+This Dockerfile represents a Docker image that encapsulates `mail-parser`. The [official image](https://hub.docker.com/r/fmantuano/spamscope-mail-parser/) is on Docker Hub.
 
 To run this image after installing Docker, use a command like this:
 
-```
+```shell
 sudo docker run -i -t --rm -v ~/mails:/mails fmantuano/spamscope-mail-parser
 ```
 
-This command runs mail-parser help as default, but you can use all others options.
+This command runs `mail-parser` help as default, but you can use all others options.
 
 To share the "mails" directory between your host and the container, create a "mails" directory on your host.
 
 There also is an example of `docker-compose`
 
 From the `docker-compose.yml` directory, run:
 
-```
+```shell
 $ sudo docker-compose up
 ```
 
-The provided ```docker-compose.yml``` file is configured to:
+The provided `docker-compose.yml` file is configured to:
 
  - Mount your host's `~/mails/` folder from your source tree inside the container at `/mails/` (read-only).
  - A command line test example.
 
-See the ```docker-compose.yml``` to view and tweak the launch parameters.
+See the `docker-compose.yml` to view and tweak the launch parameters.

report/.gitkeep

@@ -18,8 +18,7 @@
 """
 
 import argparse
-import os
-import runpy
+import logging
 import sys
 
 import mailparser
@@ -31,14 +30,18 @@
     safe_print,
     write_attachments,
 )
+from mailparser.version import __version__
 
 
-current = os.path.realpath(os.path.dirname(__file__))
-
-__version__ = runpy.run_path(os.path.join(current, "version.py"))["__version__"]
+log = logging.getLogger("mailparser")
 
 
 def get_args():
+    """
+    Get arguments from command line.
+    :return: argparse.ArgumentParser
+    :rtype: argparse.ArgumentParser
+    """
     parser = argparse.ArgumentParser(
         description="Wrapper for email Python Standard Library",
         epilog="It takes as input a raw mail and generates a parsed object.",
@@ -189,22 +192,80 @@ def get_args():
 
 
 def main():
+    """
+    Main function.
+    """
     args = get_args().parse_args()
-    log = custom_log(level=args.log_level)
-
+    log = custom_log(level=args.log_level, name="mailparser")
+
+    try:
+        parser = get_parser(args)
+        process_output(args, parser)
+    except Exception as e:
+        log.error(f"An error occurred: {e}")
+        sys.exit(1)
+
+
+def get_parser(args):
+    """
+    Get the correct parser based on the input source.
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    :return: MailParser
+    :rtype: mailparser.core.MailParser
+    """
     if args.file:
-        if args.outlook:
-            log.debug("Analysis Outlook mail")
-            parser = mailparser.parse_from_file_msg(args.file)
-        else:
-            parser = mailparser.parse_from_file(args.file)
+        return parse_file(args)
     elif args.string:
-        parser = mailparser.parse_from_string(args.string)
+        log.debug("Start analysis by string mail")
+        return mailparser.parse_from_string(args.string)
     elif args.stdin:
-        if args.outlook:
-            raise MailParserOutlookError("You can't use stdin with msg Outlook")
-        parser = mailparser.parse_from_file_obj(sys.stdin)
-
+        return parse_stdin(args)
+    else:
+        raise ValueError("No input source provided")
+
+
+def parse_file(args):
+    """
+    Parse the file based on the arguments provided.
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    :return: MailParser
+    :rtype: mailparser.core.MailParser
+    """
+    log.debug("Start analysis by file mail")
+    if args.outlook:
+        log.debug("Start analysis by Outlook msg")
+        return mailparser.parse_from_file_msg(args.file)
+    else:
+        log.debug("Start analysis by raw mail")
+        return mailparser.parse_from_file(args.file)
+
+
+def parse_stdin(args):
+    """
+    Parse the stdin based on the arguments provided.
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    :return: MailParser
+    :rtype: mailparser.core.MailParser
+    """
+    log.debug("Start analysis by stdin mail")
+    if args.outlook:
+        raise MailParserOutlookError("You can't use stdin with msg Outlook")
+    return mailparser.parse_from_file_obj(sys.stdin)
+
+
+def process_output(args, parser):
+    """
+    Process the output based on the arguments provided.
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    :param parser: MailParser
+    :type parser: mailparser.core.MailParser
+    :param log: logger
+    :type log: logging.Logger
+    """
     if args.json:
         safe_print(parser.mail_json)
 
@@ -230,21 +291,13 @@ def main():
         safe_print(parser.received_json)
 
     if args.defects:
-        log.debug("Printing defects")
-        for i in parser.defects_categories:
-            safe_print(i)
+        print_defects(parser)
 
     if args.senderip:
-        log.debug("Printing sender IP")
-        r = parser.get_server_ipaddress(args.senderip)
-        if r:
-            safe_print(r)
-        else:
-            safe_print("Not Found")
+        print_sender_ip(parser, args)
 
     if args.attachments or args.attachments_hash:
-        log.debug("Printing attachments details")
-        print_attachments(parser.attachments, args.attachments_hash)
+        print_attachments_details(parser, args)
 
     if args.mail_hash:
         log.debug("Printing also mail fingerprints")
@@ -255,5 +308,41 @@ def main():
         write_attachments(parser.attachments, args.attachments_path)
 
 
-if __name__ == "__main__":
+def print_defects(parser):
+    """
+    Print email defects.
+    :param parser: MailParser
+    :type parser: mailparser.core.MailParser
+    """
+    log.debug("Printing defects")
+    for defect in parser.defects_categories:
+        safe_print(defect)
+
+
+def print_sender_ip(parser, args):
+    """
+    Print sender IP address.
+    :param parser: MailParser
+    :type parser: mailparser.core.MailParser
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    """
+    log.debug("Printing sender IP")
+    sender_ip = parser.get_server_ipaddress(args.senderip)
+    safe_print(sender_ip if sender_ip else "Not Found")
+
+
+def print_attachments_details(parser, args):
+    """
+    Print attachments details.
+    :param parser: MailParser
+    :type parser: mailparser.core.MailParser
+    :param args: argparse.Namespace
+    :type args: argparse.Namespace
+    """
+    log.debug("Printing attachments details")
+    print_attachments(parser.attachments, args.attachments_hash)
+
+
+if __name__ == "__main__":  # pragma: no cover
     main()