From 2d9bce014f88e6c58cc57af5661808e83328d083 Mon Sep 17 00:00:00 2001
From: Dierk <dierk.lenz@dl-cons.de>
Date: Wed, 13 May 2026 11:48:03 +0200
Subject: [PATCH] Add ODF (.ods) support via odfpy

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 README.md              | 10 +++++++++-
 excel_import/reader.py | 13 +++++++++++--
 pyproject.toml         |  1 +
 tests/test_reader.py   | 12 ++++++++++++
 4 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 6dedb6f..aae8c1f 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,14 @@
 # excel-import
 
-Generisches Kommandozeilen-Tool zum Import von Excel-Dateien (`.xls` und `.xlsx`) in Oracle- und PostgreSQL-Datenbanken.
+Generisches Kommandozeilen-Tool zum Import von Tabellendateien in Oracle- und PostgreSQL-Datenbanken.
+
+Unterstützte Formate:
+
+| Format | Endung | Paket |
+|--------|--------|-------|
+| Excel 97–2003 | `.xls` | `xlrd` |
+| Excel 2007+ | `.xlsx`, `.xlsm`, `.xlsb` | `openpyxl` |
+| OpenDocument (LibreOffice) | `.ods` | `odfpy` |
 
 ## Voraussetzungen
 
diff --git a/excel_import/reader.py b/excel_import/reader.py
index 05d7619..8ecd690 100644
--- a/excel_import/reader.py
+++ b/excel_import/reader.py
@@ -5,8 +5,17 @@ import pandas as pd
 from .config import SheetConfig
 
 
+_ENGINES = {
+    ".xls": "xlrd",
+    ".xlsx": "openpyxl",
+    ".xlsm": "openpyxl",
+    ".xlsb": "openpyxl",
+    ".ods": "odf",
+}
+
+
 def _engine_for(path: Path) -> str:
-    return "xlrd" if path.suffix.lower() == ".xls" else "openpyxl"
+    return _ENGINES[path.suffix.lower()]
 
 
 class ExcelReader:
@@ -14,7 +23,7 @@ class ExcelReader:
         self.path = Path(path)
         if not self.path.exists():
             raise FileNotFoundError(f"Excel file not found: {self.path}")
-        if self.path.suffix.lower() not in {".xls", ".xlsx", ".xlsm", ".xlsb"}:
+        if self.path.suffix.lower() not in _ENGINES:
             raise ValueError(f"Unsupported file type: {self.path.suffix}")
 
     def sheet_names(self) -> list[str]:
diff --git a/pyproject.toml b/pyproject.toml
index 28cae8b..ce72029 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,6 +10,7 @@ dependencies = [
     "pandas>=2.0",
     "openpyxl>=3.1",
     "xlrd>=2.0",
+    "odfpy>=1.4",
     "sqlalchemy>=2.0",
     "psycopg2-binary>=2.9",
     "oracledb>=2.0",
diff --git a/tests/test_reader.py b/tests/test_reader.py
index 416698a..4c644db 100644
--- a/tests/test_reader.py
+++ b/tests/test_reader.py
@@ -72,6 +72,18 @@ def test_read_column_skip(xlsx_file: Path):
     assert "Preis" not in df.columns
 
 
+def test_read_ods(tmp_path: Path):
+    pytest.importorskip("odf")
+    path = tmp_path / "test.ods"
+    df = pd.DataFrame({"Name": ["Alice", "Bob"], "Wert": [1, 2]})
+    df.to_excel(path, index=False, engine="odf")
+
+    reader = ExcelReader(path)
+    result = reader.read(SheetConfig(sheet=0, target_table="t"))
+    assert len(result) == 2
+    assert list(result.columns) == ["Name", "Wert"]
+
+
 def test_file_not_found():
     with pytest.raises(FileNotFoundError):
         ExcelReader("/nonexistent/path/file.xlsx")