Fix train state and modification time for unfinished project training

annif/backend/backend.py

@@ -51,15 +51,26 @@ def params(self) -> dict[str, Any]:
         params.update(self.config_params)
         return params
 
+    @property
+    def _model_file_paths(self) -> list:
+        all_paths = glob(os.path.join(self.datadir, "*"))
+        ignore_patterns = ("*-train*", "tmp-*", "vectorizer")
+        ignore_paths = [
+            path
+            for igp in ignore_patterns
+            for path in glob(os.path.join(self.datadir, igp))
+        ]
+        return list(set(all_paths) - set(ignore_paths))
+
     @property
     def is_trained(self) -> bool:
-        return bool(glob(os.path.join(self.datadir, "*")))
+        return bool(self._model_file_paths)
 
     @property
     def modification_time(self) -> datetime | None:
         mtimes = [
             datetime.utcfromtimestamp(os.path.getmtime(p))
-            for p in glob(os.path.join(self.datadir, "*"))
+            for p in self._model_file_paths
         ]
         most_recent = max(mtimes, default=None)
         if most_recent is None:

annif/util.py

@@ -35,6 +35,7 @@ def atomic_save(
     final name."""
 
     prefix, suffix = os.path.splitext(filename)
+    prefix = "tmp-" + prefix
     tempfd, tempfilename = tempfile.mkstemp(prefix=prefix, suffix=suffix, dir=dirname)
     os.close(tempfd)
     logger.debug("saving %s to temporary file %s", str(obj)[:90], tempfilename)

tests/test_project.py

@@ -152,6 +152,20 @@ def test_project_tfidf_is_not_trained(registry):
     assert not project.is_trained
 
 
+def test_project_tfidf_is_not_trained_prepared_only(registry, testdatadir):
+    testdatadir.join("projects/tfidf-fi").ensure("vectorizer")
+    testdatadir.join("projects/tfidf-fi").ensure("dummy-tfidf-train.txt")
+    project = registry.get_project("tfidf-fi")
+    assert not project.is_trained
+
+
+def test_project_tfidf_modification_time_prepared_only(registry, testdatadir):
+    testdatadir.join("projects/tfidf-fi").ensure("vectorizer")
+    testdatadir.join("projects/tfidf-fi").ensure("dummy-tfidf-train.txt")
+    project = registry.get_project("tfidf-fi")
+    assert project.modification_time is None
+
+
 def test_project_train_tfidf(registry, document_corpus, testdatadir):
     project = registry.get_project("tfidf-fi")
     project.train(document_corpus)