filter for most recent file (#321)

* filter for most recent file * Added test
Hochfrequenz · May 21, 2024 · 6f162a7 · 6f162a7
1 parent 73e4e0c
commit 6f162a7
Show file tree

Hide file tree

Showing 2 changed files with 49 additions and 6 deletions.
diff --git a/src/kohlrahbi/docxfilefinder.py b/src/kohlrahbi/docxfilefinder.py
@@ -112,14 +112,20 @@ def filter_latest_version(groups: dict[str, list[Path]]) -> list[Path]:
             if len(group_items) == 1:
                 result.append(group_items[0])
             else:
-                for path in group_items:
-                    if (
-                        "KonsolidierteLesefassungmitFehlerkorrekturen" in path.name
+                most_recent_file = max(
+                    (
+                        path
+                        for path in group_items
+                        if "KonsolidierteLesefassungmitFehlerkorrekturen" in path.name
                         or "AußerordentlicheVeröffentlichung" in path.name
-                    ):
-                        result.append(path)
-                    else:
+                    ),
+                    key=lambda path: (int(path.stem.split("_")[-1])),
+                )
+                for path in group_items:
+                    if path != most_recent_file:
                         logger.debug("Ignoring file %s", path.name)
+                    else:
+                        result.append(most_recent_file)
         return result
 
     def filter_for_latest_mig_and_ahb_docx_files(self) -> None:

diff --git a/unittests/test_docx_extensions.py b/unittests/test_docx_extensions.py
@@ -2,6 +2,7 @@
 tests all the features the kohlrahbi package provides to process Docx files (by using the docx package)
 """
 
+from pathlib import Path
 from typing import Generator
 
 import pytest
@@ -11,6 +12,7 @@
 from docx.table import Table
 from docx.text.paragraph import Paragraph
 
+from kohlrahbi.docxfilefinder import DocxFileFinder
 from kohlrahbi.read_functions import get_all_paragraphs_and_tables
 
 
@@ -40,3 +42,38 @@ def test_get_all_paragraphs_and_tables(self, create_docx_from_filename: Document
         actual = list(get_all_paragraphs_and_tables(create_docx_from_filename))
         assert len(actual) == expected_length
         assert all([isinstance(x, Table) or isinstance(x, Paragraph) for x in actual]) is True
+
+    @pytest.mark.parametrize(
+        "all_file_paths, filtered_file_paths",
+        [
+            pytest.param(
+                [Path("IFTSTAAHB-informatorischeLesefassung2.0e_99991231_20231001.docx")],
+                [Path("IFTSTAAHB-informatorischeLesefassung2.0e_99991231_20231001.docx")],
+                id="One file",
+            ),
+            pytest.param(
+                [
+                    Path("IFTSTAAHB-informatorischeLesefassung2.0e_99991231_20231001.docx"),
+                    Path(
+                        "IFTSTAAHB-informatorischeLesefassung2.0e-AußerordentlicheVeröffentlichung_20231211_20231001.docx"
+                    ),
+                    Path(
+                        "IFTSTAAHB-informatorischeLesefassung2.0eKonsolidierteLesefassungmitFehlerkorrekturenStand11.03.2024_99991231_20240311.docx"
+                    ),
+                    Path(
+                        "IFTSTAAHB-informatorischeLesefassung2.0eKonsolidierteLesefassungmitFehlerkorrekturenStand12.12.2023_20240310_20231212.docx"
+                    ),
+                ],
+                [
+                    Path(
+                        "IFTSTAAHB-informatorischeLesefassung2.0eKonsolidierteLesefassungmitFehlerkorrekturenStand11.03.2024_99991231_20240311.docx"
+                    )
+                ],
+                id="Several files",
+            ),
+        ],
+    )
+    def test_filter_lastest_version(self, all_file_paths, filtered_file_paths):
+        input_file_dict = {"FORMAT": all_file_paths}
+        actual = DocxFileFinder.filter_latest_version(input_file_dict)
+        assert actual == filtered_file_paths