Skip unchanged Excel report uploads

README.md

@@ -64,7 +64,9 @@ damit interne Dokumentdaten nicht unbeabsichtigt über einen Proxy laufen.
 SHA-256-Prüfsummen und SQLite verhindern, dass erfolgreich verarbeitete Inhalte
 erneut verarbeitet werden. Bestehende Zieldateien werden nicht überschrieben; bei
 Kollisionen wird `_02`, `_03` usw. ergänzt. Eine Prozesssperre verhindert parallele
-Läufe auf derselben Installation.
+Läufe auf derselben Installation. Entsteht während eines Laufs kein neuer
+Protokolleintrag, wird `protokoll.xlsx` weder lokal neu erzeugt noch erneut zu
+Nextcloud hochgeladen.
 
 ## Installation auf einer Linux-VM
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "orc-renaming"
-version = "0.4.0"
+version = "0.4.1"
 description = "Lokale, datenschutzfreundliche Benennung gescannter PDF-Dokumente"
 readme = "README.md"
 requires-python = ">=3.11"

src/orc_renaming/__init__.py

@@ -1,3 +1,3 @@
 """Lokale Dokumentklassifikation und PDF-Benennung."""
 
-__version__ = "0.4.0"
+__version__ = "0.4.1"

src/orc_renaming/ledger.py

@@ -91,6 +91,12 @@ class Ledger:
         ).fetchone()
         return row is not None
 
+    def entry_count(self) -> int:
+        row = self.connection.execute(
+            "SELECT COUNT(*) AS count FROM processing_log"
+        ).fetchone()
+        return int(row["count"])
+
     def add(self, record: ProcessingRecord) -> None:
         values = record.model_dump(mode="json")
         values["evidence"] = json.dumps(

src/orc_renaming/pipeline.py

@@ -301,6 +301,7 @@ class Pipeline:
         return status
 
     def run(self) -> dict[str, int]:
+        entries_before_run = self.ledger.entry_count()
         upload_report = (
             not self.config.processing.dry_run
             or self.config.processing.upload_excel_in_dry_run
@@ -342,6 +343,12 @@ class Pipeline:
                     status = "error"
                 counters[status] = counters.get(status, 0) + 1
 
+        if self.ledger.entry_count() == entries_before_run:
+            LOGGER.info(
+                "Protokoll unverändert; Excel-Export und Nextcloud-Upload übersprungen"
+            )
+            return counters
+
         excel_path = (
             self.config.processing.state_directory
             / self.config.processing.excel_filename

tests/test_pipeline.py

@@ -4,7 +4,12 @@ from datetime import date
 from pathlib import Path
 
 import orc_renaming.pipeline as pipeline_module
-from orc_renaming.models import DocumentScope, DocumentType, ExtractionResult
+from orc_renaming.models import (
+    DocumentScope,
+    DocumentType,
+    ExtractionResult,
+    ProcessingRecord,
+)
 from orc_renaming.normalize import result_is_complete
 from orc_renaming.pipeline import Pipeline
 from orc_renaming.webdav import RemoteFile
@@ -111,6 +116,44 @@ def test_live_run_uploads_pdf_report_and_archives(config, monkeypatch) -> None:
     assert config.nextcloud.review_folder in folders
 
 
+def test_empty_run_does_not_write_or_upload_report(config, monkeypatch) -> None:
+    _prepare(monkeypatch)
+
+    with Pipeline(config) as pipeline:
+        pipeline.webdav.list_pdfs = lambda _folder: []
+        counters = pipeline.run()
+        uploads = list(pipeline.webdav.uploads)
+
+    assert counters == {}
+    assert uploads == []
+    assert not (config.processing.state_directory / "protokoll.xlsx").exists()
+
+
+def test_skipped_files_do_not_rewrite_report(config, monkeypatch) -> None:
+    _prepare(monkeypatch)
+    report_path = config.processing.state_directory / "protokoll.xlsx"
+
+    with Pipeline(config) as pipeline:
+        pipeline.ledger.add(
+            ProcessingRecord(
+                remote_path="/Scanner/Eingang/scan001.pdf",
+                original_name="scan001.pdf",
+                checksum="abc123",
+                status="success",
+            )
+        )
+        pipeline.ledger.export_xlsx(report_path)
+        report_before = report_path.read_bytes()
+
+        counters = pipeline.run()
+        uploads = list(pipeline.webdav.uploads)
+        report_after = report_path.read_bytes()
+
+    assert counters == {"skipped": 1}
+    assert uploads == []
+    assert report_after == report_before
+
+
 def test_ollama_fallback_is_only_used_after_incomplete_primary(
     config, monkeypatch
 ) -> None: