test: 6 parallel agents — +40 test files across core, agent, translate, services, API routes, dataset_review. core 100%, agent 100%, services 100%, translate plugin mostly done. Pending: ~10 minor failures to fix

backend/tests/test_agent/test_document_parser.py

@@ -8,6 +8,8 @@ sys.path.append(str(Path(__file__).parent.parent.parent / "src"))
 
 import os
 import tempfile
+from unittest.mock import MagicMock, patch
+
 import pytest
 
 from src.agent.document_parser import parse_pdf, parse_xlsx, parse_upload, ParseError
@@ -188,5 +190,114 @@ def test_parse_upload_dict():
         assert "Dict test" in result
     finally:
         os.unlink(tmp_path)
+
+
+def test_parse_upload_file_path_fallback():
+    """parse_upload falls back to file_path key if path is missing."""
+    with tempfile.NamedTemporaryFile(suffix=".txt", mode="w", delete=False) as f:
+        f.write("Fallback key test")
+        tmp_path = f.name
+
+    try:
+        result = parse_upload({"name": "test.txt", "file_path": tmp_path})
+        assert "Fallback" in result
+    finally:
+        os.unlink(tmp_path)
 # #endregion TestAgentChat.DocumentParser.ParseUpload
+
+
+# #region TestAgentChat.DocumentParser.ImportErrors [C:2] [TYPE Function] [SEMANTICS test,parser,import,error]
+# @BRIEF Test ImportError paths in parse_pdf and parse_xlsx.
+
+def test_parse_pdf_import_error():
+    """pdfplumber import fails → ParseError."""
+    import builtins
+    real_import = builtins.__import__
+
+    def raise_on_pdfplumber(name, globals=None, locals=None, fromlist=(), level=0):
+        if name == 'pdfplumber':
+            raise ImportError(f"No module named pdfplumber", name=name)
+        return real_import(name, globals, locals, fromlist, level)
+
+    with patch('builtins.__import__', side_effect=raise_on_pdfplumber):
+        with pytest.raises(ParseError, match="pdfplumber not installed"):
+            parse_pdf("/tmp/dummy.pdf")
+
+
+def test_parse_xlsx_import_error():
+    """openpyxl import fails → ParseError."""
+    import builtins
+    real_import = builtins.__import__
+
+    def raise_on_openpyxl(name, globals=None, locals=None, fromlist=(), level=0):
+        if name == 'openpyxl':
+            raise ImportError(f"No module named openpyxl", name=name)
+        return real_import(name, globals, locals, fromlist, level)
+
+    with patch('builtins.__import__', side_effect=raise_on_openpyxl):
+        with pytest.raises(ParseError, match="openpyxl not installed"):
+            parse_xlsx("/tmp/dummy.xlsx")
+# #endregion TestAgentChat.DocumentParser.ImportErrors
+
+
+# #region TestAgentChat.DocumentParser.PyPDF2Fallback [C:2] [TYPE Function] [SEMANTICS test,parser,pypdf2,fallback]
+# @BRIEF When pdfplumber fails, PyPDF2 is used as fallback path.
+
+def test_parse_pdf_pypdf2_fallback():
+    """pdfplumber failure triggers PyPDF2 fallback."""
+    # Build mock PyPDF2 module in sys.modules
+    mock_pypdf2 = MagicMock()
+    mock_reader = MagicMock()
+    mock_page = MagicMock()
+    mock_page.extract_text.return_value = "Fallback PyPDF2 text"
+    mock_reader.pages = [mock_page]
+    mock_pypdf2.PdfReader = MagicMock(return_value=mock_reader)
+
+    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
+        f.write(b"dummy pdf content")
+        tmp_path = f.name
+
+    try:
+        # Patch pdfplumber.open directly (the real module) — NOT document_parser.pdfplumber
+        # because pdfplumber is imported inside the function body, not at module level.
+        with patch('pdfplumber.open', side_effect=Exception("pdfplumber error")), \
+             patch.dict('sys.modules', {'PyPDF2': mock_pypdf2}):
+            result = parse_pdf(tmp_path)
+            assert isinstance(result, str)
+            assert "PyPDF2" in result
+            mock_pypdf2.PdfReader.assert_called_once()
+    finally:
+        os.unlink(tmp_path)
+# #endregion TestAgentChat.DocumentParser.PyPDF2Fallback
+
+
+# #region TestAgentChat.DocumentParser.ParseUploadBranches [C:2] [TYPE Function] [SEMANTICS test,parser,upload,branches]
+# @BRIEF Test parse_upload dispatches to correct parser for PDF, XLSX, XLS.
+
+def test_parse_upload_pdf_branch():
+    """parse_upload with .pdf dispatches to parse_pdf."""
+    import src.agent.document_parser as dp
+    with patch.object(dp, 'parse_pdf', return_value="pdf result") as mock_parse:
+        result = parse_upload({"name": "report.pdf", "path": "/tmp/report.pdf"})
+        assert result == "pdf result"
+        mock_parse.assert_called_once_with("/tmp/report.pdf")
+
+
+def test_parse_upload_xlsx_branch():
+    """parse_upload with .xlsx dispatches to parse_xlsx."""
+    import src.agent.document_parser as dp
+    with patch.object(dp, 'parse_xlsx', return_value="xlsx result") as mock_parse:
+        result = parse_upload({"name": "data.xlsx", "path": "/tmp/data.xlsx"})
+        assert result == "xlsx result"
+        mock_parse.assert_called_once_with("/tmp/data.xlsx")
+
+
+def test_parse_upload_xls_branch():
+    """parse_upload with .xls (legacy) also dispatches to parse_xlsx."""
+    import src.agent.document_parser as dp
+    with patch.object(dp, 'parse_xlsx', return_value="xls result") as mock_parse:
+        result = parse_upload({"name": "legacy.xls", "path": "/tmp/legacy.xls"})
+        assert result == "xls result"
+        mock_parse.assert_called_once_with("/tmp/legacy.xls")
+# #endregion TestAgentChat.DocumentParser.ParseUploadBranches
 # #endregion TestAgentChat.DocumentParser