feat: Implement PDF to XML conversion using ScienceBeam Parser

.gitignore

@@ -11,6 +11,5 @@ __pycache__/
 dist/
 build/
 .tox/
-venv/
 .vscode/settings.json
 .DS_Store

commands/converters/converter.py

@@ -0,0 +1,9 @@
+from abc import ABC, abstractmethod
+
+from pydantic import FilePath, BaseModel
+
+
+class Converter(ABC, BaseModel):
+    @abstractmethod
+    def convert(self, pdf_path: FilePath) -> str:
+        pass

commands/converters/pdf_converter.py

@@ -0,0 +1,26 @@
+from pydantic import FilePath
+import requests
+
+from commands.converters.converter import Converter
+
+
+class PDFConverter(Converter):
+    sciencebeam_url: str = 'http://localhost:8080/api/convert'
+
+    def convert(self, pdf_path: FilePath):
+        """Convert a PDF file to XML using ScienceBeam Parser.
+
+        Args:
+            pdf_path: Path to the PDF file
+        Returns:
+            XML content as a string
+        """
+        with open(pdf_path, 'rb') as pdf_file:
+            files = {'file': pdf_file}
+            headers = {'Accept': 'application/tei+xml'}
+            response = requests.post(self.sciencebeam_url, files=files, headers=headers)
+
+            if response.status_code == 200:
+                return response.text
+            else:
+                response.raise_for_status()

commands/file_processing.py

@@ -1,6 +1,11 @@
 import click
+import requests
+from pydantic import ValidationError
+
+from commands.converters.pdf_converter import PDFConverter
 from logs.logger import logger
 
+
 @click.command()
 @click.argument('file_path', type=click.Path(exists=True))
 @click.argument('file_id', type=str)
@@ -9,11 +14,21 @@ def pdf_xml(file_path, file_id):
         to XML
 
     Args:
-        file_paht (file path): First parameter
+        file_path (file path): First parameter
         file_id (string): Second parameter
     Returns:
         Creates an XML file in the directory xmls_sciencebeam
     """
+    try:
+        converter = PDFConverter()
+        xml_content = converter.convert(file_path)
+        # Save the converted xml contents
+        with open(f'docs/examples/sciencebeam_xml_outputs/{file_id}.xml', '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 ValidationError as error:
+        logger.error("Validation error:", error)
 
-    # Function Implementation
-    logger.info(f'Converted: {file_path} with ID: {file_id} to XML')
+    except requests.RequestException as error:
+        logger.error("Request error:", error)

osm/cli.py

@@ -1,13 +1,15 @@
 import click
 from commands.file_processing import pdf_xml
 
+
 @click.group()
 def cli():
     """Main command group."""
     pass
 
+
 # Add commands to the main group
 cli.add_command(pdf_xml)
 
 if __name__ == '__main__':
-    cli()
+    cli()

requirements.txt

@@ -1,4 +1,6 @@
 click==8.1.7
 tox==4.15.0
+pydantic==2.7.3
 pytest==8.2.1
 rich==13.7.1
+requests==2.32.3

tests/test_file_processing.py

@@ -1,31 +1,33 @@
-import pytest
+import unittest
 from click.testing import CliRunner
 import os
-import logging
 
-from commands.file_processing import pdf_xml
+from osm.cli import cli
 
-@pytest.mark.usefixtures("caplog")
-class TestFileProcessing:
-    def setup_method(self):
+
+class TestFileProcessing(unittest.TestCase):
+    def setUp(self):
         # Create a temporary PDF file for testing
-        self.pdf_path = 'test_sample.pdf'
-        with open(self.pdf_path, 'wb') as f:
-            f.write(b'%PDF-1.4\n%Test PDF content\n')
+        self.pdfs_folder = 'docs/examples/pdf_inputs'
+        self.file = 'test_sample.pdf'
+        self.file_id = 'test_file_id'
 
-    def teardown_method(self):
-        # Remove the temporary PDF file and any generated XML file
-        if os.path.exists(self.pdf_path):
-            os.remove(self.pdf_path)
-        xml_output = f"{self.pdf_path.replace('.pdf', '')}_test_file.xml"
-        if os.path.exists(xml_output):
-            os.remove(xml_output)
+        self.output_file = f'docs/examples/sciencebeam_xml_outputs/{self.file_id}.xml'
 
-    def test_pdf_xml_command(self, caplog):
-        caplog.set_level(logging.INFO)
+    def tearDown(self):
+        # Remove the generated XML file
+        if os.path.exists(self.output_file):
+            os.remove(self.output_file)
 
+    def test_pdf_xml_command(self):
         runner = CliRunner()
-        result = runner.invoke(pdf_xml, [self.pdf_path, 'test_file'])
+        pdf_path = f'{self.pdfs_folder}/{self.file}'
+        result = runner.invoke(cli, ['pdf-xml', pdf_path, self.file_id])
+
+        # Check that the command executed successfully
+        self.assertEqual(result.exit_code, 0)
+        self.assertTrue(os.path.exists(self.output_file))
+
 
-        assert result.exit_code == 0
-        assert f'Converted: {self.pdf_path}' in caplog.text
+if __name__ == '__main__':
+    unittest.main()