genelastic 0.9.0__tar.gz → 0.10.0__tar.gz

{genelastic-0.9.0 → genelastic-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: genelastic
-Version: 0.9.0
+Version: 0.10.0
 Summary: Generate and store genetic data into an Elasticsearch database.
 Keywords: CNRGH,genelastic,generation,storage,elasticsearch,database
 Author: CNRGH, Pierrick ROGER, Maxime BLANCHON

{genelastic-0.9.0 → genelastic-0.10.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "genelastic"
-version = "0.9.0"
+version = "0.10.0"
 requires-python = ">= 3.11"
 authors = [
     { name = "CNRGH" },

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/common/cli.py

@@ -66,17 +66,10 @@ def add_es_connection_args(parser: argparse.ArgumentParser) -> None:
     Arguments are added to the parser by using its reference.
     """
     parser.add_argument(
-        "--es-host",
-        dest="es_host",
-        default="localhost",
-        help="Address of Elasticsearch host.",
-    )
-    parser.add_argument(
-        "--es-port",
-        type=int,
-        default=9200,
-        dest="es_port",
-        help="Elasticsearch port.",
+        "--es-url",
+        dest="es_url",
+        default="https://localhost:9200/",
+        help="URL of the Elasticsearch host.",
     )
     parser.add_argument(
         "--es-usr", dest="es_usr", default="elastic", help="Elasticsearch user."

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/cli/cli_check.py

@@ -96,13 +96,12 @@ def main() -> None:
     configure_logging(args.verbose)
 
     logger.info(
-        "Connecting to Elasticsearch at https://%s:%s ...",
-        args.es_host,
-        args.es_port,
+        "Connecting to Elasticsearch at %s...",
+        args.es_url,
     )
 
     es = ElasticQueryConn(
-        f"https://{args.es_host}:{args.es_port}",
+        args.es_url,
         args.es_cert_fp,
         args.es_index_prefix,
         basic_auth=(args.es_usr, args.es_pwd),

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/cli/import_data.py

@@ -234,10 +234,9 @@ def main() -> None:
     logger.debug("LOGGERS: %s", logging.root.manager.loggerDict)
 
     # Open connection to ES
-    addr = f"https://{args.es_host}:{args.es_port}"
-    logger.info("Connecting to Elasticsearch at %s...", addr)
+    logger.info("Connecting to Elasticsearch at %s...", args.es_url)
     es_import_conn = ElasticImportConn(
-        addr,
+        args.es_url,
         args.es_cert_fp,
         args.es_index_prefix,
         args.dryrun,

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/cli/info.py

@@ -209,10 +209,9 @@ def main() -> None:
     configure_logging(args.verbose)
     logger.debug("Arguments: %s", args)
 
-    addr = f"https://{args.es_host}:{args.es_port}"
-    logger.info("Connecting to Elasticsearch at %s...", addr)
+    logger.info("Connecting to Elasticsearch at %s...", args.es_url)
     es_query_conn = ElasticQueryConn(
-        addr,
+        args.es_url,
         args.es_cert_fp,
         args.es_index_prefix,
         basic_auth=(args.es_usr, args.es_pwd),

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/cli/integrity.py

@@ -366,10 +366,9 @@ def main() -> None:
     wet_processes_index = f"{args.es_index_prefix}-wet_processes"
     bi_processes_index = f"{args.es_index_prefix}-bi_processes"
 
-    addr = f"https://{args.es_host}:{args.es_port}"
-    logger.info("Connecting to Elasticsearch at %s...", addr)
+    logger.info("Connecting to Elasticsearch at %s...", args.es_url)
     es_query_conn = ElasticQueryConn(
-        addr,
+        args.es_url,
         args.es_cert_fp,
         args.es_index_prefix,
         args.dryrun,

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/importers/importer_base.py

@@ -72,7 +72,12 @@ class BaseImporter(ABC, Generic[T]):
         """Load and parse raw data from the file."""
 
     def _validate(self, data: T) -> None:
-        """Validate the data structure (optional)."""
+        """Validate the data structure (optional).
+
+        Note: Do not implement for streaming-based importers (generators).
+        Generators should not be consumed here; validate per-record in
+        ``_transform`` if needed.
+        """
 
     @abstractmethod
     def _transform(self, data: T) -> Iterable[dict[str, Any]]:

{genelastic-0.9.0 → genelastic-0.10.0}/src/genelastic/import_data/importers/importer_types.py

@@ -77,15 +77,26 @@ class VCFImporter(BaseImporter[Iterable[_Record]]):
         :raises ImporterError: If the file could not be opened, decoded or is empty.
         """
         try:
-            yield from vcf.Reader(
+            # StopIteration can come from two sources:
+            # 1. vcf.Reader() constructor if file is empty
+            # (unhandled in header parsing)
+            # 2. next() if file has valid headers but no variant records
+            reader = vcf.Reader(
                 filename=str(self._data_file.path), encoding="utf-8"
             )
+            first_record = next(reader)
         except StopIteration:
-            msg = f"VCF file '{self._data_file.path}' is empty."
+            msg = (
+                f"VCF file '{self._data_file.path}' is empty or "
+                f"contains no variant records."
+            )
             raise ImporterError(msg) from None
         except (OSError, UnicodeDecodeError) as e:
             raise ImporterError(e) from None
 
+        yield first_record
+        yield from reader
+
     def _transform(self, data: Iterable[_Record]) -> Iterable[dict[str, Any]]:
         """Transform each VCF file record into a JSON document."""
         for record in data: