Merge pull request #57 from charslab/development

Update master to PTB 21.10

Author: carloalbertobarbano

.coverage

@@ -0,0 +1,41 @@
+name: DockerBuildAndPush
+
+on:
+  push:
+    branches:
+      - master
+      - developement
+      - ptb-async
+
+env:
+  IMAGE_NAME: transcriberbot
+
+jobs:
+  push:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push'
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Login to ghcr registry
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u $ --password-stdin
+
+      - name: Build image
+        run: docker build . --file Dockerfile --tag $IMAGE_NAME
+
+      - name: Push image
+        run: |
+          IMAGE_ID=ghcr.io/${{ github.repository_owner }}/$IMAGE_NAME
+          # Change all uppercase to lowercase
+          IMAGE_ID=$(echo $IMAGE_ID | tr '[A-Z]' '[a-z]')
+          # Strip git ref prefix from version
+          VERSION=$(echo "${{ github.ref }}" | sed -e 's,.*/\(.*\),\1,')
+          # Strip "v" prefix from tag name
+          [[ "${{ github.ref }}" == "refs/tags/"* ]] && VERSION=$(echo $VERSION | sed -e 's/^v//')
+          # Use Docker `latest` tag convention
+          [ "$VERSION" == "master" ] && VERSION=latest
+          echo IMAGE_ID=$IMAGE_ID
+          echo VERSION=$VERSION
+          docker tag $IMAGE_NAME $IMAGE_ID:$VERSION
+          docker push $IMAGE_ID:$VERSION

.github/workflows/build_image.yml

@@ -1,5 +1,4 @@
 # TranscriberBot-specific ignores
-config/
 media/
 
 # Generic data-related ignores

.gitignore

@@ -0,0 +1 @@
+transcriber-bot-wonda

.python-version

@@ -1,4 +1,4 @@
-FROM python:3.9-slim
+FROM python:3.12.0-slim
 
 # Set global configs
 WORKDIR /

.travis.yml

@@ -9,88 +9,73 @@
 
 2. Edit the file **config/telegram.json**
 
-   `{
+   ```json
+   {
    	  "username": "BOT USERNAME",
    	  "token": "BOT TOKEN",
    	  "admins": [ "YOUR TELEGRAM ID" ]
-   }`
+   }
+   ```
 
 3. Create your own Wit token on [Wit website](https://wit.ai/docs/quickstart)
 
 4. Edit the file **config/wit.json** (for example with italian token)
 
-   `{
+   ```json
+   {
    	"it-IT": "WIT TOKEN FOR Italian"
-   }`
+   }
+   ```
 
    You can repeat the points 3 and 4 for support multiple languages.
 
-   You can test if your token is working by running:
-
-   `
-   $ python src/audiotools/speech.py wit_api_key some_file.mp3 transcription.txt
-   `
+   You can test if your token is working by running: `python src/audiotools/speech.py wit_api_key some_file.mp3 transcription.txt`
 
 5. Create your own Yandex translate token on [Yandex website](https://tech.yandex.com/translate/)
 
 6. Edit the file **config/yandex.json**
 
-   `{
+   ```json
+   {
    	"translate_key": "YOUR YANDEX TOKEN"
-   }`
-
-
-
-## Installation with virtualenv
-
-1. Install virtualenv and setuptools package
-
-   `$ python3 -m pip install --upgrade pip`
-   `$ pip3 install virtualenv setuptools`
-
-2. Make a note of the full file path to the custom version of Python you just installed
-
-   `$ which python3 `
+   }
+   ```
 
-3. Create the virtual environment while you specify the version of Python you wish to use
+## Running with Docker
 
-   `$ virtualenv -p /usr/bin/python3 venv`
+We provide prebuilt images on [ghcr.io](https://github.com/charslab/TranscriberBot/pkgs/container/transcriberbot).
+See **[run.sh](https://github.com/charslab/TranscriberBot/blob/developement/run.sh)** to start a docker container with the latest release.
 
-4. Activate the new virtual environment
+Altenratevely, you can build the image from the Dockerfile with **[build.sh](https://github.com/charslab/TranscriberBot/blob/developement/build.sh)** 
 
-   `$ source venv/bin/activate`
+In **[run.sh](https://github.com/charslab/TranscriberBot/blob/developement/run.sh)**, the docker directories **config**, **data** and **values** are binding with the repository directory.
+If you want to edit the files in the configuration directories you can do this simply by stopping the container.
+As soon as you finish editing the files, just restart the container to make them active.
 
-5. Install the requirement packages
 
-   `(venv) $ pip3 install -r requirements.txt`
+## Running with virtualenv
 
-6. Run the bot
+Tested with: `python 3.12.0`
 
-   `(venv) $ python3 src/main.py`
+First, install the required dependencies (Ubuntu):
 
-## Installation with Docker
+```bash
+sudo apt install tesseract-ocr libtesseract-dev libleptonica-dev libpython3-dev libzbar-dev
+```
+Create a virtual environment and install the required packages:
 
-You can install easily with Docker.
+```bash
+python3 -m venv transcriber-bot
+source transcriber-bot/bin/activate
+pip install -r requirements.txt
+```
+Run the bot:
 
-1. Run the script **dockerBuild.sh** to generate the docker image from the Dockerfile.
+```
+cd src
+python3 main.py
+```
 
-2. Run the script **dockerRun.sh** to create and start the docker container.
 
-   In the run script, the docker directories **config**, **data** and **values** are binding with the repository directory.
-   If you want to edit the files in the configuration directories you can do this simply by stopping the container.
-   As soon as you finish editing the files, just restart the container to make them active.
 
-## TODO
 
-- [x] Voice Messages
-- [x] Audio Files
-- [x] Video notes
-- [x] Pictures
-- [x] Multithreading
-- [x] Stop callback
-- [ ] Stats
-- [x] Admin commands only in groups
-- [x] Antiflood
-- [x] Translations
-- [ ] Voice ask
-- [x] Channels support

Dockerfile

@@ -49,12 +49,24 @@
     "webm"
   ],
 
+  "ocr": {
+    "tesseract_path": "/usr/share/tesseract-ocr/5/tessdata/"
+  },
+
   "antiflood": {
     "age_threshold": 10,
     "flood_ratio": 2,
     "max_flood_ratio": 6,
     "time_threshold_warning": 4,
     "time_threshold_flood": 5,
     "timeout": 10
+  },
+
+  "whisper": {
+    "api_endpoint": "http://127.0.0.1:8000"
+  },
+
+  "logging": {
+    "level": "APP"
   }
 }

README.md

@@ -0,0 +1,3 @@
+{
+  "dsn": "xxx"
+}