Initial commit: SharePoint connector and ToothFairyAI integration

test_document_parser.py

@@ -0,0 +1,145 @@
+"""
+Unit tests for document_parser.py
+"""
+import pytest
+from document_parser import DocumentParser, get_file_info
+
+
+class TestDocumentParser:
+    """Test DocumentParser class."""
+
+    def setup_method(self):
+        """Set up test fixtures."""
+        self.parser = DocumentParser()
+
+    def test_can_parse_supported_extensions(self):
+        """Test can_parse returns True for supported file types."""
+        supported_files = [
+            'document.txt', 'readme.md', 'data.csv', 'config.json',
+            'report.pdf', 'document.docx', 'spreadsheet.xlsx', 'slides.pptx',
+            'script.py', 'code.java', 'style.css', 'index.html'
+        ]
+
+        for filename in supported_files:
+            assert self.parser.can_parse(filename), f"Should parse {filename}"
+
+    def test_can_parse_unsupported_extensions(self):
+        """Test can_parse returns False for unsupported file types."""
+        unsupported_files = [
+            'image.png', 'video.mp4', 'audio.mp3', 'archive.zip',
+            'binary.exe', 'document.doc'
+        ]
+
+        for filename in unsupported_files:
+            assert not self.parser.can_parse(filename), f"Should not parse {filename}"
+
+    def test_get_extension(self):
+        """Test _get_extension method."""
+        assert self.parser._get_extension('file.txt') == '.txt'
+        assert self.parser._get_extension('FILE.TXT') == '.txt'
+        assert self.parser._get_extension('archive.tar.gz') == '.gz'
+        assert self.parser._get_extension('noextension') == ''
+
+    def test_parse_text_utf8(self):
+        """Test parsing UTF-8 text files."""
+        content = "Hello World\nThis is a test".encode('utf-8')
+        result = self.parser.parse(content, 'test.txt')
+        assert result == "Hello World\nThis is a test"
+
+    def test_parse_text_multiple_encodings(self):
+        """Test parsing text with different encodings."""
+        content = "Test content"
+
+        # UTF-8
+        result = self.parser._parse_text(content.encode('utf-8'))
+        assert result == "Test content"
+
+        # Latin-1
+        result = self.parser._parse_text(content.encode('latin-1'))
+        assert result == "Test content"
+
+    def test_parse_unsupported_file_raises_error(self):
+        """Test parsing unsupported file type raises ValueError."""
+        with pytest.raises(ValueError, match="Unsupported file type"):
+            self.parser.parse(b"content", "file.exe")
+
+    def test_parse_json(self):
+        """Test parsing JSON files."""
+        content = '{"key": "value", "number": 123}'.encode('utf-8')
+        result = self.parser.parse(content, 'data.json')
+        assert '"key": "value"' in result
+        assert '"number": 123' in result
+
+    def test_parse_csv(self):
+        """Test parsing CSV files."""
+        content = "name,age,city\nAlice,30,NYC\nBob,25,LA".encode('utf-8')
+        result = self.parser.parse(content, 'data.csv')
+        assert "Alice" in result
+        assert "30" in result
+        assert "NYC" in result
+
+
+class TestGetFileInfo:
+    """Test get_file_info function."""
+
+    def test_document_category(self):
+        """Test document file type categorization."""
+        info = get_file_info('report.pdf', 1024)
+        assert info['category'] == 'document'
+        assert info['extension'] == '.pdf'
+
+    def test_spreadsheet_category(self):
+        """Test spreadsheet file type categorization."""
+        info = get_file_info('data.xlsx', 2048)
+        assert info['category'] == 'spreadsheet'
+        assert info['extension'] == '.xlsx'
+
+    def test_presentation_category(self):
+        """Test presentation file type categorization."""
+        info = get_file_info('slides.pptx', 4096)
+        assert info['category'] == 'presentation'
+
+    def test_code_category(self):
+        """Test code file type categorization."""
+        info = get_file_info('script.py', 512)
+        assert info['category'] == 'code'
+
+    def test_image_category(self):
+        """Test image file type categorization."""
+        info = get_file_info('photo.jpg', 8192)
+        assert info['category'] == 'image'
+
+    def test_file_size_bytes(self):
+        """Test file size formatting in bytes."""
+        info = get_file_info('small.txt', 512)
+        assert info['size_formatted'] == '512 B'
+        assert info['size_bytes'] == 512
+
+    def test_file_size_kilobytes(self):
+        """Test file size formatting in KB."""
+        info = get_file_info('medium.txt', 2048)
+        assert 'KB' in info['size_formatted']
+        assert info['size_bytes'] == 2048
+
+    def test_file_size_megabytes(self):
+        """Test file size formatting in MB."""
+        info = get_file_info('large.pdf', 5 * 1024 * 1024)
+        assert 'MB' in info['size_formatted']
+        assert '5.0' in info['size_formatted']
+
+    def test_file_size_gigabytes(self):
+        """Test file size formatting in GB."""
+        info = get_file_info('huge.zip', 2 * 1024 * 1024 * 1024)
+        assert 'GB' in info['size_formatted']
+        assert '2.0' in info['size_formatted']
+
+    def test_unknown_extension(self):
+        """Test unknown file extension."""
+        info = get_file_info('file.xyz', 1024)
+        assert info['category'] == 'file'
+        assert info['extension'] == '.xyz'
+
+    def test_no_extension(self):
+        """Test file with no extension."""
+        info = get_file_info('README', 1024)
+        assert info['extension'] == ''