fixed merge conflict

.envrc

@@ -0,0 +1,2 @@
+source ~/.venvs/z_env/bin/activate
+

.githooks/pre-commit

@@ -1,7 +1,8 @@
 #!/bin/sh
 
 DIR="$(cd "$(dirname "$0")" && pwd)"
-
+echo $DIR
 for rule_name in $DIR/rules; do
-	$DIR/rules/routes_should_not_end_in_slash 
+	cd "$DIR/rules"
+	./routes_should_not_end_in_slash
 done

.github/workflows/publish_docker_image.yml

@@ -0,0 +1,36 @@
+name: Publish Docker Image
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v4
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+        with:
+          images: zeeguu/api
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@3b5e8027fcad23fda98b2e3ac259d8d67585f671
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+

.github/workflows/render-architectural-diff.yml

@@ -0,0 +1,15 @@
+name: Render ARchitectural Diff with ArchLens
+
+jobs:
+  render-diff-and-upload-comment:
+    permissions: write-all
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - id: run_archlens
+        uses: archlens/render-diff-on-pr@main
+        with:
+          config-path: "archlens.json"
+          render-diff: "true"
+          BRANCH_NAME: "_archlens_diff"

.github/workflows/test.yml

@@ -1,6 +1,10 @@
-name: Python package
+name: Unit Testing
 
-on: [push]
+on: 
+    pull_request:
+        branches:
+            - master
+    push:
 
 jobs:
   build:

.gitignore

@@ -2,6 +2,7 @@ instance
 dev_data_folder*
 .idea/
 .cache/
+data/
 
 *.pyc
 *.egg-info

Dockerfile

@@ -0,0 +1,111 @@
+FROM python:3.12.3
+
+RUN apt-get clean all
+RUN apt-get update
+RUN apt-get upgrade -y
+RUN apt-get dist-upgrade -y
+
+# Git
+# ---
+# required by github dependencies in requirements.txt
+RUN apt-get -y install git
+
+
+# mysql CL client
+# -------------------------
+# - good for debugging sometimes
+RUN apt-get install -y mysql\*
+
+
+# libmysqlclient
+# --------------
+# - required to be able to install mysqlclient with pip
+#   https://stackoverflow.com/questions/5178292/pip-install-mysql-python-fails-with-environmenterror-mysql-config-not-found
+RUN apt-get install -y default-libmysqlclient-dev
+
+# Zeeguu-Api
+# ----------
+
+# Declare that this will be mounted from a volume
+VOLUME /Zeeguu-API
+
+# We need to copy the requirements file it in order to be able to install it
+# However, we're not copying the whole folder, such that in case we make a change in the folder
+# (e.g. to this build file) the whole cache is not invalidated and the build process does
+# not have to start from scratch
+RUN mkdir /Zeeguu-API
+COPY ./requirements.txt /Zeeguu-API/requirements.txt
+COPY ./setup.py /Zeeguu-API/setup.py
+
+# Install requirements and setup
+WORKDIR /Zeeguu-API
+
+RUN python -m pip install -r requirements.txt
+RUN python setup.py develop
+
+# Copy the rest of the files 
+# (this is done after the requirements are installed, so that the cache is not invalidated)
+WORKDIR /Zeeguu-API
+COPY . /Zeeguu-API
+
+ENV ZEEGUU_CONFIG=/Zeeguu-API/default_docker.cfg
+
+VOLUME /zeeguu-data
+
+
+# mysql CL client
+# -------------------------
+# - good for debugging sometimes
+RUN apt-get install -y mysql\*
+
+
+# libmysqlclient
+# --------------
+# - required to be able to install mysqlclient with pip
+#   https://stackoverflow.com/questions/5178292/pip-install-mysql-python-fails-with-environmenterror-mysql-config-not-found
+RUN apt-get install -y default-libmysqlclient-dev
+
+
+# Apache
+# ------
+RUN apt-get install -y \
+    apache2 \
+    apache2-dev \
+    vim
+
+
+# mod_wsgi
+# --------
+RUN pip install mod_wsgi
+
+RUN /bin/bash -c 'mod_wsgi-express install-module | tee /etc/apache2/mods-available/wsgi.{load,conf}'
+RUN a2enmod wsgi
+RUN a2enmod headers
+
+# ML: maybe better to map this file from outside?
+RUN echo '\n\
+<VirtualHost *:8080>\n\
+    WSGIDaemonProcess zeeguu_api home=/zeeguu-data/ python-path=/Zeeguu-API/\n\
+    WSGIScriptAlias / /Zeeguu-API/zeeguu_api.wsgi\n\
+    <Location />\n\
+        WSGIProcessGroup zeeguu_api\n\
+	    WSGIApplicationGroup %{GLOBAL}\n\
+    </Location>\n\
+    <Directory "/Zeeguu-API">\n\
+        <Files "zeeguu_api.wsgi">\n\
+            Require all granted\n\
+        </Files>\n\
+    </Directory>\n\
+    ErrorLog ${APACHE_LOG_DIR}/error.log\n\
+    LogLevel info\n\
+    CustomLog ${APACHE_LOG_DIR}/access.log combined\n\
+</VirtualHost>' > /etc/apache2/sites-available/zeeguu-api.conf
+
+RUN a2dissite 000-default.conf
+RUN a2ensite zeeguu-api
+
+RUN chown -R www-data:www-data /var/www
+
+
+# have apache listen on port 8080
+RUN sed -i "s,Listen 80,Listen 8080,g" /etc/apache2/ports.conf

archlens.json

@@ -10,15 +10,15 @@
     "views": {
 
         "top-level-view-depth-1": {
-            "packages": [
+              "packages": [
                 {
-                    "packagePath":"",
-                    "depth":1
+                  "path": "*",
+                  "depth": 1
                 }
-            ],
+              ],
 
             "ignorePackages": []
         }
 
     }
-}
+}

docker-compose.yml

@@ -2,7 +2,7 @@ version: "3.8"
 
 services:
   dev_server:
-    image: zeeguu_api_dev
+    image: zeeguu/api
     environment:
       ZEEGUU_CONFIG: /Zeeguu-API/default_docker.cfg
       ZEEGUU_ES_CONN_STRING: "elasticsearch:9200"
@@ -15,12 +15,19 @@ services:
     volumes:
       - .:/Zeeguu-API
       - ./data/zeeguu:/zeeguu-data
-    entrypoint: "python /Zeeguu-API/dev.py"
+    entrypoint: "python /Zeeguu-API/start.py"
     networks:
       - zeeguu_backend
     depends_on:
       - elasticsearch
 
+  readability_server:
+    image: zeeguu/readability_server
+    ports:
+      - 3456:3456
+    networks:
+      - zeeguu_backend
+    restart: unless-stopped
 
   elasticsearch:
     image: elasticsearch:7.6.2
@@ -40,7 +47,7 @@ services:
 
 
   dev_play:
-    image: zeeguu_api_dev
+    image: zeeguu/api
     environment:
       ZEEGUU_CONFIG: /Zeeguu-API/default_docker.cfg
 
@@ -53,7 +60,7 @@ services:
 
   # docker-compose run --rm dev_bash
   dev_bash:
-    image: zeeguu_api_dev
+    image: zeeguu/api
     stdin_open: true # docker run -i
     tty: true # docker run -t
 
@@ -68,7 +75,7 @@ services:
       - zeeguu_backend
 
   dev_test:
-    image: zeeguu_api_dev
+    image: zeeguu/api
     environment:
       ZEEGUU_CONFIG: /Zeeguu-API/default_docker.cfg
 
@@ -80,7 +87,7 @@ services:
       - zeeguu_backend
 
   dev_init_es:
-    image: zeeguu_api_dev
+    image: zeeguu/api
     environment:
       ZEEGUU_CONFIG: /Zeeguu-API/default_docker.cfg
       ZEEGUU_ES_CONN_STRING: "elasticsearch:9200"

requirements.txt

@@ -43,8 +43,14 @@ en_core_web_md @ https://github.com/explosion/spacy-models/releases/download/en_
 de_core_news_md @ https://github.com/explosion/spacy-models/releases/download/de_core_news_md-3.7.0/de_core_news_md-3.7.0-py3-none-any.whl
 da_core_news_md @ https://github.com/explosion/spacy-models/releases/download/da_core_news_md-3.7.0/da_core_news_md-3.7.0-py3-none-any.whl
 rapidfuzz==3.0.0
-scipy==1.10.1
+scipy==1.13.0
 git+https://github.com/zeeguu/confusionwords.git@main#egg=confusionwords
-readabilipy
 scikit-learn==1.4.0
-flask_monitoringdashboard
+flask_monitoringdashboard
+
+# the following two were required when deploying the API on Mac OS with Python 3.12.1
+cryptography
+lxml_html_clean 
+
+# spacy sometimes pulls an older version of pydantic that breaks stuff; adding the following line to prevent this
+pydantic>=1.10.8

dev.py → start.py

@@ -1,4 +1,4 @@
-#!/bin/env python
+#!python3
 import logging
 
 # this is needed since when run as wsgi this script

tools/_playground.py

@@ -1,19 +1,10 @@
-from zeeguu.core.model import User
-from zeeguu.core.user_statistics.activity import exercises_duration_by_day
+from zeeguu.core.content_retriever.parse_with_readability_server import download_and_parse
 
 from zeeguu.api.app import create_app
 
 app = create_app()
 app.app_context().push()
 
-print("before the for")
-for id in User.all_recent_user_ids(150):
-    u = User.find_by_id(id)
-    print(u.name)
-    duration_old = exercises_duration_by_day(u, True)
-    duration_new = exercises_duration_by_day(u)
-    if duration_new != duration_old:
-        print("old way")
-        print(duration_old)
-        print("new way")
-        print(duration_new)
+na = download_and_parse(
+    "https://www.dr.dk/stories/1288510966/allerede-inden-oscar-showets-start-lurer-en-ny-skandale-i-kulissen")
+print(na)

tools/add_feed.py

@@ -10,13 +10,7 @@
 
 def create_and_test_feed(url: str, feed_type: int):
     feed = Feed.from_url(url, feed_type=feed_type)
-
-    feed_items = feed.feed_items()
-    if not feed_items:
-        print("Feed seems broken. No items found.")
-    else:
-        count = len(feed_items)
-        print(f"Feed seems healthy: {count} items found. ")
+    print(feed.feed_health_info())
 
     return feed
 
@@ -34,8 +28,8 @@ def main():
     print(f"= {icon_name}")
 
     description = (
-        input(f"Description (Enter for: {test_feed.description}): ")
-        or test_feed.description
+            input(f"Description (Enter for: {test_feed.description}): ")
+            or test_feed.description
     )
     print(f"= {description}")