chore: more tests

tests/parser/file/test_docs_parser.py

@@ -1,117 +1,187 @@
-import pytest
+"""Comprehensive tests for application/parser/file/docs_parser.py
+
+Covers: PDFParser (init, parse with pypdf, parse as image, import error),
+DocxParser (init, parse, import error).
+"""
+
 from pathlib import Path
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch, mock_open
+
+import pytest
 
 from application.parser.file.docs_parser import PDFParser, DocxParser
 
 
-@pytest.fixture
-def pdf_parser():
-    return PDFParser()
+# =====================================================================
+# PDFParser - Init
+# =====================================================================
 
 
-@pytest.fixture
-def docx_parser():
-    return DocxParser()
+@pytest.mark.unit
+class TestPDFParserInit:
+
+    def test_init_parser(self):
+        parser = PDFParser()
+        result = parser._init_parser()
+        assert isinstance(result, dict)
+        assert result == {}
+
+    def test_parser_config_not_set_initially(self):
+        parser = PDFParser()
+        assert not parser.parser_config_set
+
+    def test_parser_config_set_after_init(self):
+        parser = PDFParser()
+        parser.init_parser()
+        assert parser.parser_config_set
 
 
-def test_pdf_init_parser():
-    parser = PDFParser()
-    assert isinstance(parser._init_parser(), dict)
-    assert not parser.parser_config_set
-    parser.init_parser()
-    assert parser.parser_config_set
+# =====================================================================
+# PDFParser - Parse File
+# =====================================================================
 
 
-def test_docx_init_parser():
-    parser = DocxParser()
-    assert isinstance(parser._init_parser(), dict)
-    assert not parser.parser_config_set
-    parser.init_parser()
-    assert parser.parser_config_set
+@pytest.mark.unit
+class TestPDFParserParse:
+
+    @patch("application.parser.file.docs_parser.settings")
+    def test_parse_with_pypdf(self, mock_settings):
+        mock_settings.PARSE_PDF_AS_IMAGE = False
+
+        parser = PDFParser()
+
+        mock_page1 = MagicMock()
+        mock_page1.extract_text.return_value = "Page 1 content"
+        mock_page2 = MagicMock()
+        mock_page2.extract_text.return_value = "Page 2 content"
+
+        mock_reader = MagicMock()
+        mock_reader.pages = [mock_page1, mock_page2]
+
+        with patch("application.parser.file.docs_parser.PdfReader",
+                   create=True), \
+             patch("builtins.open", mock_open()):
+            # Need to patch the import inside the function
+            import sys
+            mock_pypdf = MagicMock()
+            mock_pypdf.PdfReader = MagicMock(return_value=mock_reader)
+            sys.modules["pypdf"] = mock_pypdf
+
+            try:
+                result = parser.parse_file(Path("test.pdf"))
+                assert "Page 1 content" in result
+                assert "Page 2 content" in result
+            finally:
+                del sys.modules["pypdf"]
+
+    @patch("application.parser.file.docs_parser.settings")
+    @patch("application.parser.file.docs_parser.requests")
+    def test_parse_as_image(self, mock_requests, mock_settings):
+        mock_settings.PARSE_PDF_AS_IMAGE = True
+
+        mock_response = MagicMock()
+        mock_response.json.return_value = {"markdown": "# OCR Result"}
+        mock_requests.post.return_value = mock_response
+
+        parser = PDFParser()
+
+        with patch("builtins.open", mock_open(read_data=b"fake pdf")):
+            result = parser.parse_file(Path("test.pdf"))
+            assert result == "# OCR Result"
+
+    @patch("application.parser.file.docs_parser.settings")
+    def test_parse_raises_on_missing_pypdf(self, mock_settings):
+        mock_settings.PARSE_PDF_AS_IMAGE = False
+
+        parser = PDFParser()
+
+        # Simulate the import error path
+        original = parser.parse_file
+
+        def mock_parse(*args, **kwargs):
+            raise ValueError("pypdf is required to read PDF files.")
+
+        parser.parse_file = mock_parse
+
+        try:
+            with pytest.raises(ValueError, match="pypdf is required"):
+                parser.parse_file(Path("test.pdf"))
+        finally:
+            parser.parse_file = original
 
 
-@patch("application.parser.file.docs_parser.settings")
-def test_parse_pdf_with_pypdf(mock_settings, pdf_parser):
-    mock_settings.PARSE_PDF_AS_IMAGE = False
-
-    # Create mock pages with text content
-    mock_page1 = MagicMock()
-    mock_page1.extract_text.return_value = "Test PDF content page 1"
-    mock_page2 = MagicMock()
-    mock_page2.extract_text.return_value = "Test PDF content page 2"
-
-    mock_reader_instance = MagicMock()
-    mock_reader_instance.pages = [mock_page1, mock_page2]
-
-    original_parse_file = pdf_parser.parse_file
-
-    def mock_parse_file(*args, **kwargs):
-        _ = args, kwargs
-        text_list = []
-        num_pages = len(mock_reader_instance.pages)
-        for page_index in range(num_pages):
-            page = mock_reader_instance.pages[page_index]
-            page_text = page.extract_text()
-            text_list.append(page_text)
-        text = "\n".join(text_list)
-        return text
-
-    pdf_parser.parse_file = mock_parse_file
-
-    try:
-        result = pdf_parser.parse_file(Path("test.pdf"))
-        assert result == "Test PDF content page 1\nTest PDF content page 2"
-    finally:
-        pdf_parser.parse_file = original_parse_file
+# =====================================================================
+# DocxParser - Init
+# =====================================================================
 
 
-@patch("application.parser.file.docs_parser.settings")
-def test_parse_pdf_pypdf_import_error(mock_settings, pdf_parser):
-    mock_settings.PARSE_PDF_AS_IMAGE = False
+@pytest.mark.unit
+class TestDocxParserInit:
 
-    original_parse_file = pdf_parser.parse_file
+    def test_init_parser(self):
+        parser = DocxParser()
+        result = parser._init_parser()
+        assert isinstance(result, dict)
+        assert result == {}
 
-    def mock_parse_file(*args, **kwargs):
-        _ = args, kwargs
-        raise ValueError("pypdf is required to read PDF files.")
+    def test_parser_config_not_set_initially(self):
+        parser = DocxParser()
+        assert not parser.parser_config_set
 
-    pdf_parser.parse_file = mock_parse_file
-
-    try:
-        with pytest.raises(ValueError, match="pypdf is required to read PDF files"):
-            pdf_parser.parse_file(Path("test.pdf"))
-    finally:
-        pdf_parser.parse_file = original_parse_file
+    def test_parser_config_set_after_init(self):
+        parser = DocxParser()
+        parser.init_parser()
+        assert parser.parser_config_set
 
 
-def test_parse_docx(docx_parser):
-    original_parse_file = docx_parser.parse_file
-
-    def mock_parse_file(*args, **kwargs):
-        _ = args, kwargs
-        return "Test DOCX content"
-
-    docx_parser.parse_file = mock_parse_file
-
-    try:
-        result = docx_parser.parse_file(Path("test.docx"))
-        assert result == "Test DOCX content"
-    finally:
-        docx_parser.parse_file = original_parse_file
+# =====================================================================
+# DocxParser - Parse File
+# =====================================================================
 
 
-def test_parse_docx_import_error(docx_parser):
-    original_parse_file = docx_parser.parse_file
+@pytest.mark.unit
+class TestDocxParserParse:
 
-    def mock_parse_file(*args, **kwargs):
-        _ = args, kwargs
-        raise ValueError("docx2txt is required to read Microsoft Word files.")
+    def test_parse_file_success(self):
+        parser = DocxParser()
 
-    docx_parser.parse_file = mock_parse_file
+        import sys
+        mock_docx2txt = MagicMock()
+        mock_docx2txt.process.return_value = "DOCX content here"
+        sys.modules["docx2txt"] = mock_docx2txt
 
-    try:
-        with pytest.raises(ValueError, match="docx2txt is required to read Microsoft Word files"):
-            docx_parser.parse_file(Path("test.docx"))
-    finally:
-        docx_parser.parse_file = original_parse_file
+        try:
+            result = parser.parse_file(Path("test.docx"))
+            assert result == "DOCX content here"
+        finally:
+            del sys.modules["docx2txt"]
+
+    def test_parse_raises_on_missing_docx2txt(self):
+        parser = DocxParser()
+
+        original = parser.parse_file
+
+        def mock_parse(*args, **kwargs):
+            raise ValueError("docx2txt is required to read Microsoft Word files.")
+
+        parser.parse_file = mock_parse
+
+        try:
+            with pytest.raises(ValueError, match="docx2txt is required"):
+                parser.parse_file(Path("test.docx"))
+        finally:
+            parser.parse_file = original
+
+
+# =====================================================================
+# BaseParser properties
+# =====================================================================
+
+
+@pytest.mark.unit
+class TestBaseParserProperties:
+
+    def test_get_file_metadata_default(self):
+        parser = PDFParser()
+        meta = parser.get_file_metadata(Path("test.pdf"))
+        assert meta == {}