metadata-crawler 2510.0.0__tar.gz → 2510.0.2__tar.gz

{metadata_crawler-2510.0.0 → metadata_crawler-2510.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metadata-crawler
-Version: 2510.0.0
+Version: 2510.0.2
 Summary: Crawl, extract and push climate metadata for indexing.
 Author-email: "DKRZ, Clint" <freva@dkrz.de>
 Requires-Python: >=3.11

{metadata_crawler-2510.0.0 → metadata_crawler-2510.0.2}/docs/source/whatsnew.rst

@@ -3,6 +3,15 @@ What's new
 
 This document highlights major changes and additions across releases.
 
+v2510.0.2
+---------
+* Allow any type of additional keys.
+
+
+v2510.0.1
+---------
+* Bug fixing
+
 v2510.0.0
 ---------
 * Restructure solr ingest.

{metadata_crawler-2510.0.0 → metadata_crawler-2510.0.2}/drs_config.toml

@@ -1,11 +1,13 @@
 [nextgems_cat]
 root_path = "test_intake.json"
+solr_server = ["foo"]
 drs_format = "nextgems"
 fs_type = "intake"
 
 [nextgems_cycle3]
 root_path = "data/intake/work/bm1235"
 drs_format = "nextgems_cycle3"
+solr_server = ["foo"]
 fs_type = "posix"
 [nextgems_cycle3.defaults]
 project = "nextgems"

metadata_crawler-2510.0.2/src/metadata_crawler/_version.py

@@ -0,0 +1 @@
+__version__ = "2510.0.2"

{metadata_crawler-2510.0.0 → metadata_crawler-2510.0.2}/src/metadata_crawler/api/config.py

@@ -264,8 +264,15 @@ class PathSpecs(BaseModel):
         self, data: Dict[str, Any], rel_path: Path
     ) -> None:
         dir_parts = rel_path.parent.parts
+
         if self.dir_parts and len(dir_parts) == len(self.dir_parts):
-            _parts = dict(zip(self.dir_parts, dir_parts))
+            data.update(
+                {
+                    k: v
+                    for (k, v) in zip(self.dir_parts, dir_parts)
+                    if k not in data
+                }
+            )
         elif self.dir_parts:
             raise MetadataCrawlerException(
                 (
@@ -273,7 +280,6 @@ class PathSpecs(BaseModel):
                     f"- needs: {len(self.dir_parts)} has: {len(dir_parts)}"
                 )
             ) from None
-        data.update({k: v for (k, v) in _parts.items() if k not in data})
 
     def _get_metadata_from_filename(
         self, data: Dict[str, Any], rel_path: Path
@@ -281,6 +287,7 @@ class PathSpecs(BaseModel):
         if self.file_parts is None:
             return
         file_parts = rel_path.name.split(self.file_sep)
+        _parts: Dict[str, str] = {}
         if len(file_parts) == len(self.file_parts):
             _parts = dict(zip(self.file_parts, file_parts))
         elif (
@@ -413,7 +420,7 @@ class DataSpecs(BaseModel):
 class Datasets(BaseModel):
     """Definition of datasets that should be crawled."""
 
-    __pydantic_extra__: Dict[str, str] = Field(init=False)
+    __pydantic_extra__: Dict[str, Any] = Field(init=False)
     model_config = ConfigDict(extra="allow")
     root_path: str | Path
     drs_format: str = "freva"

metadata_crawler-2510.0.0/src/metadata_crawler/_version.py

@@ -1 +0,0 @@
-__version__ = "2510.0.0"