chore: resolve feedback and include docker file

.gitignore

@@ -13,6 +13,5 @@ __pycache__/
 dist/
 build/
 .tox/
-venv/
 .vscode/settings.json
 .DS_Store

Dockerfile

@@ -0,0 +1,35 @@
+# Use the official Debian Docker image as the base
+FROM debian:latest
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies, Python, pip, networking, and debugging tools
+RUN apt-get update && apt-get install -y \
+    git \
+    python3 \
+    python3-pip \
+    python3-venv \
+    curl \
+    iputils-ping \
+    net-tools \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy your project files
+COPY . /app
+
+# Create and activate virtual environment
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Upgrade pip in the virtual environment
+RUN pip install --upgrade pip
+
+# Install the package and its dependencies
+RUN pip install -e .
+
+# Install pre-commit (optional, remove if not needed in the container)
+RUN pip install pre-commit
+
+# Set the command to the osm command
+CMD ["osm", "--help"]

README.md

@@ -1,21 +1,28 @@
 # OpenSciMetrics
+
 OpenSciMetrics (OSM) applies NLP and LLM-based metrics and indicators related to transparency, data sharing, rigor, and open science on biomedical publications.
 
 # How to setup and run the application
+
 - After cloning the repo, navigate into the project's root directory by running `cd osm`
 - Run `python -m venv venv` to create a Virtual Environment
 - Depending on your system, run the approriate command to Activate the Virtual Environment
-Windows: `venv\Scripts\activate`<br>
-macOS and Linux: `source venv/bin/activate`
+  Windows: `venv\Scripts\activate`<br>
+  macOS and Linux: `source venv/bin/activate`
 
 - Next, run `pip install -e .` to install the package with its dependencies.
-- Open a terminal tab and run the image `docker run --rm -p 8082:8070 elifesciences/sciencebeam-parser` and keep it running for the rest of the testing period
-- Go back to terminal(root folder)
-- Finally, run `osm pdf-xml "path_to_file_name.pdf" file_id`
+- Open a terminal tab and run the image `docker run --rm -p 8070:8070 elifesciences/sciencebeam-parser` and keep it running
+
+**Note:** The ScienceBeam image is not supported by all apple silicon chips. You may need to consider using an alternative systems.
+
+- Finally, run `osm pdf-xml-json "path_to_file_name.pdf" output_file_path`
 
 # How to run tests of the application
+
 Run `tox`
+
 # How to run the unit tests
+
 - Navigate to the project's root directory and run `pytest`
 
 # Using pre-commit for commit checks
@@ -27,3 +34,10 @@ pre-commit and its hooks, run the following commands:
 pip install pre-commit
 pre-commit install
 ```
+
+# How to build the Docker image and run the Docker container
+
+- Navigate to the project's root directory and run `docker-compose up --build`
+- When the image is built and the containers are running, open another terminal and start osm container in interactive mode using the command `docker-compose run osm bash`
+- You can do file conversions in the container using this command `osm pdf-xml-json "path_to_file_name.pdf" output_file_path`
+- Or use the command `docker-compose run --rm osm pdf-xml-json "path_to_file_name.pdf" output_file_path` to convert files in non-interactive mode

docker-compose.yml

@@ -0,0 +1,30 @@
+version: '3.8'
+
+services:
+  sciencebeam:
+    image: elifesciences/sciencebeam-parser
+    ports:
+      - "8070:8070"
+    networks:
+      - app-network
+
+  osm:
+    build: 
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "8081:8070"
+    volumes:
+      - .:/app
+    depends_on:
+      - sciencebeam
+    environment:
+      - SCIENCEBEAM_URL=http://sciencebeam:8070
+    tty: true
+    stdin_open: true
+    networks:
+      - app-network
+
+networks:
+  app-network:
+    driver: bridge

osm/cli/main.py

@@ -1,8 +1,7 @@
 import click
-import requests
 
-from osm.logging.logger import logger
-from osm.converters.pdf_converter import PDFConverter
+from osm.converters.converter import convert_pdf_to_xml
+
 
 @click.group()
 def osm():
@@ -12,32 +11,19 @@ def osm():
 
 @osm.command()
 @click.argument("file_path", type=click.Path(exists=True))
-@click.argument("file_id", type=str)
-def pdf_xml(file_path, file_id):
-    """
+@click.argument("output_file", type=str)
+def pdf_xml_json(file_path, output_file):
+    """Converts a PDF file of a biomedical publication to JSON format
     Args:
-        file_path (file path): First parameter
-        file_id (string): Second parameter
+        file_path (string): Path to the input PDF file
+        output_file (string): an output file path
     Returns:
-        Creates an XML file in the directory xmls_sciencebeam
+        Creates an JSON file containing bibliometric
+        indicators and metadata and saves it in the
+        output file path
     """
     try:
-        converter = PDFConverter()
-
-        if not converter.is_docker_running():
-            raise click.ClickException("Please make sure the docker is running")
-
-        if not converter.is_host_ready():
-            raise click.ClickException("The converter server is offline")
-
-        xml_content = converter.convert(file_path)
-        # Save the converted xml contents
-        output_file: str = f"docs/examples/sciencebeam_xml_outputs/{file_id}.xml"
-        with open(output_file, "w", encoding="utf-8") as xml_file:
-            xml_file.write(xml_content)
-            logger.info(f"Converted: {file_path} with ID: {file_id} to XML")
-
-    except requests.RequestException as error:
-        logger.error("Request error:", error)
-
-    logger.info(f"Converted: {file_path} with ID: {file_id} to XML")
+        convert_pdf_to_xml(file_path, output_file)
+    except Exception as e:
+        click.echo(f"Error: {str(e)}", err=True)
+        exit(1)

osm/converters/converter.py

@@ -1,9 +1,87 @@
+import socket
 from abc import ABC, abstractmethod
+from pathlib import Path
 
-from pydantic import BaseModel, FilePath
+import requests
 
+from osm.logging.logger import logger
+from osm.utils.config import config
 
-class Converter(ABC, BaseModel):
+
+class Converter(ABC):
     @abstractmethod
-    def convert(self, pdf_path: FilePath) -> str:
+    def convert(self, pdf_path) -> str:
         pass
+
+    def handle_error(self, error):
+        if isinstance(error, requests.RequestException):
+            logger.error("Request error:", exc_info=error)
+        else:
+            logger.error("An error occurred:", exc_info=error)
+
+        raise error
+
+
+class PDFConverter(Converter):
+    protocol: str = config.PROTOCOL
+    host: str = config.HOST
+    port: int = config.PORT
+
+    def convert(self, pdf_path) -> str:
+        """Convert a PDF file to XML using ScienceBeam Parser.
+
+        Args:
+            pdf_path: Path to the PDF file
+        Returns:
+            XML content as a string
+        """
+        sciencebeam_url: str = f"{self.protocol}://{self.host}:{self.port}/api/convert"
+        with Path(pdf_path).open("rb") as pdf_file:
+            files = {"file": pdf_file}
+            headers = {"Accept": "application/tei+xml"}
+            response = requests.post(sciencebeam_url, files=files, headers=headers)
+
+            if response.status_code == 200:
+                return response.text
+            else:
+                response.raise_for_status()
+
+    def is_host_ready(self, timeout=3) -> bool:
+        """Check if the host is ready to accept requests.
+        Args:
+            timeout: Timeout in seconds
+        Returns:
+            True if the server host is ready, False otherwise
+        """
+        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
+            sock.settimeout(timeout)
+            try:
+                sock.connect((self.host, self.port))
+            except (socket.timeout, socket.error):
+                return False
+            return True
+
+
+def convert_pdf_to_xml(file_path, output_file_path):
+    """Converts a PDF file to XML and saves the output.
+
+    Args:
+        file_path (str): Path to the input PDF file.
+        output_file_path (str): Path to the output XML file.
+    """
+    converter = PDFConverter()
+    try:
+        if not converter.is_host_ready():
+            raise Exception("The converter server is offline")
+
+        xml_content = converter.convert(file_path)
+
+        # Save the converted xml contents
+        Path(output_file_path).write_text(xml_content)
+        logger.info(f"Converted: {file_path} to XML. Output file: {output_file_path}")
+
+    except requests.RequestException as error:
+        converter.handle_error(error)
+
+    except Exception as error:
+        converter.handle_error(error)

osm/utils/config.py

@@ -1,10 +1,7 @@
-from pydantic.v1 import BaseSettings
-
-
-class AppConfig(BaseSettings):
-    PORT: int = 8082
-    HOST: str = "localhost"
-    PROTOCAL: str = "http"
+class AppConfig:
+    PORT: int = 8070
+    HOST: str = "sciencebeam"
+    PROTOCOL: str = "http"
 
 
 config = AppConfig()

pyproject.toml

@@ -14,12 +14,12 @@ dynamic = ["version"]
 dependencies = [
     "click>=8.1.7",
     "rich>=13.7.1",
-    "docker",
-    "pydantic",
+    "requests>=2.32.3",
 ]
 
 [project.optional-dependencies]
 dev = [
+    "pytest-mock>=3.14.0",
     "tox>=4.15.0",
     "pytest>=8.2.1",
     "pytest-cov",