rosetta-cli 3.0.0__tar.gz → 3.0.2__tar.gz

{rosetta_cli-3.0.0/rosetta_cli.egg-info → rosetta_cli-3.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rosetta-cli
-Version: 3.0.0
+Version: 3.0.2
 Summary: Rosetta CLI for publishing knowledge base content to RAGFlow
 Author-email: Rosetta Team <rosetta-support@griddynamics.com>
 License-Expression: Apache-2.0

{rosetta_cli-3.0.0 → rosetta_cli-3.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rosetta-cli"
-version = "3.0.0"
+version = "3.0.2"
 description = "Rosetta CLI for publishing knowledge base content to RAGFlow"
 readme = "README.md"
 requires-python = ">=3.12"

{rosetta_cli-3.0.0 → rosetta_cli-3.0.2}/rosetta_cli/commands/cleanup_command.py

@@ -94,13 +94,13 @@ class CleanupCommand(BaseCommand):
             # Filter by tags (metadata condition)
             tags_list = self._parse_tags(args.tags)
             filtered_documents = document_service.filter_documents_by_tags(
-                dataset, tags_list
+                dataset, tags_list, limit=self.config.page_size
             )
             print(f"\nFiltered {len(filtered_documents)} document(s) with tags: {', '.join(tags_list)}\n")
         elif args.prefix:
             # Filter by prefix
             filtered_documents = document_service.filter_documents_by_prefix(
-                dataset, args.prefix
+                dataset, args.prefix, limit=self.config.page_size
             )
             print(f"\nFiltered {len(filtered_documents)} document(s) matching prefix '{args.prefix}'\n")
         else:

{rosetta_cli-3.0.0 → rosetta_cli-3.0.2}/rosetta_cli/commands/parse_command.py

@@ -115,6 +115,7 @@ class ParseCommand(BaseCommand):
             print(f"Found {len(documents)} document(s) (force mode - parsing all)\n")
             
             for document in documents:
+                status = self._count_parse_status(status_counts, document)
                 doc_id = getattr(document, 'id', None)
                 if doc_id:
                     docs_to_parse.append({
@@ -122,7 +123,7 @@ class ParseCommand(BaseCommand):
                         "name": getattr(document, 'name', 'Untitled'),
                         "dataset_id": dataset.id,
                         "folder": ".",
-                        "status": getattr(document, 'run', 'UNSTART')
+                        "status": status
                     })
         else:
             # Default mode: filter by status (need parsing)
@@ -131,10 +132,17 @@ class ParseCommand(BaseCommand):
                 statuses=["FAIL", "UNSTART", "CANCEL"],
                 limit=self.config.page_size
             )
+
+            # Tally skipped documents from the full list so the summary reflects
+            # what this run will not re-trigger.
+            all_documents = dataset.list_documents(page_size=self.config.page_size)
+            for document in all_documents:
+                self._count_parse_status(status_counts, document)
             
             print(f"Found {len(documents_needing_parse)} document(s) needing parsing\n")
             
             for document in documents_needing_parse:
+                status = self._count_parse_status(status_counts, document)
                 doc_id = getattr(document, 'id', None)
                 if doc_id:
                     docs_to_parse.append({
@@ -142,10 +150,19 @@ class ParseCommand(BaseCommand):
                         "name": getattr(document, 'name', 'Untitled'),
                         "dataset_id": dataset.id,
                         "folder": ".",
-                        "status": getattr(document, 'run', 'UNSTART')
+                        "status": status
                     })
         
         return docs_to_parse, status_counts
+
+    def _count_parse_status(self, status_counts: dict[str, int], document: object) -> str:
+        """Tally a document's parse status and return it."""
+        status = getattr(document, 'run', 'UNSTART')
+        if status == 'DONE':
+            status_counts['done'] += 1
+        elif status == 'RUNNING':
+            status_counts['running'] += 1
+        return status
     
     def _print_parse_status(self, docs_to_parse: list[JsonDict], status_counts: dict[str, int], args: CommandArgs) -> None:
         """Print parsing status."""

{rosetta_cli-3.0.0 → rosetta_cli-3.0.2/rosetta_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rosetta-cli
-Version: 3.0.0
+Version: 3.0.2
 Summary: Rosetta CLI for publishing knowledge base content to RAGFlow
 Author-email: Rosetta Team <rosetta-support@griddynamics.com>
 License-Expression: Apache-2.0