add extractor properties to registry

Author: jat255

docs/extractors.md

@@ -521,9 +521,42 @@ See {doc}`writing_extractor_plugins` for instructions on how to write a new extr
 
 ## API Reference
 
+### Extractor Registry Properties
+
+The {py:class}`nexusLIMS.extractors.registry.ExtractorRegistry` class provides convenient properties for querying registered extractors:
+
+**`extractors` Property**
+: Returns a dictionary mapping file extensions to lists of extractor classes, sorted by priority (descending). This property automatically triggers plugin discovery if not already performed.
+
+```python
+from nexusLIMS.extractors.registry import get_registry
+
+registry = get_registry()
+extractors_by_ext = registry.extractors
+# Returns: {
+#   'dm3': [<class digital_micrograph.DM3Extractor'>], 
+#   'dm4': [<class 'digital_micrograph.DM3Extractor'>], 
+#   'msa': [<class 'edax.MsaExtractor'>], 
+#   'spc': [<class 'edax.SpcExtractor'>], 
+#   ... 
+# }
+```
+
+**`extractor_names` Property**
+: Returns a deduplicated, alphabetically-sorted list of all registered extractor class names. Includes both extension-specific and wildcard extractors. This property also triggers auto-discovery if needed.
+
+```python
+registry = get_registry()
+names = registry.extractor_names
+# Returns: ["BasicFileInfoExtractor", "DM3Extractor", ..., "TescanTiffExtractor"]
+```
+
+### Extractor Modules
+
 For complete API documentation of the extractor modules, see:
 
 - {py:mod}`nexusLIMS.extractors` - Main extractor module
+- {py:mod}`nexusLIMS.extractors.registry` - Extractor registry and auto-discovery
 - {py:mod}`nexusLIMS.extractors.plugins.digital_micrograph` - DM3/DM4 file extractor
 - {py:mod}`nexusLIMS.extractors.plugins.quanta_tif` - FEI/Thermo TIF file extractor
 - {py:mod}`nexusLIMS.extractors.plugins.orion_HIM_tif` - Zeiss Orion / Fibics HIM TIF file extractor

nexusLIMS/extractors/registry.py

@@ -99,6 +99,67 @@ def __init__(self):
 
         logger.debug("Initialized ExtractorRegistry")
 
+    @property
+    def extractors(self) -> dict[str, list[type[BaseExtractor]]]:
+        """
+        Get the extractor list.
+
+        Returns a dictionary mapping file extensions to lists of extractor classes,
+        sorted by priority (descending).
+
+        Auto-discovers plugins if not already discovered.
+
+        Returns
+        -------
+        dict[str, list[type[BaseExtractor]]]
+            Maps extension (without dot) to list of extractor classes
+
+        Examples
+        --------
+            >>> registry = get_registry()
+            >>> extractors_by_ext = registry.extractors
+            >>> print(extractors_by_ext.get("dm3", []))
+        """
+        if not self._discovered:
+            self.discover_plugins()
+        return dict(self._extractors)
+
+    @property
+    def extractor_names(self) -> list[str]:
+        """
+        Get a deduplicated list of extractor names.
+
+        Returns extractor names sorted alphabetically, with duplicates removed.
+
+        Auto-discovers plugins if not already discovered.
+
+        Returns
+        -------
+        list[str]
+            Sorted list of unique extractor names
+
+        Examples
+        --------
+            >>> registry = get_registry()
+            >>> names = registry.extractor_names
+            >>> print(names)
+            ['BasicFileInfoExtractor', 'DM3Extractor', 'QuantaTiffExtractor', ...]
+        """
+        if not self._discovered:
+            self.discover_plugins()
+
+        # Collect all extractor names
+        extractor_names_set = set()
+        for extractor_classes in self._extractors.values():
+            for extractor_class in extractor_classes:
+                extractor_names_set.add(extractor_class.__name__)
+
+        # Also add wildcard extractors
+        for extractor_class in self._wildcard_extractors:
+            extractor_names_set.add(extractor_class.__name__)
+
+        return sorted(extractor_names_set)
+
     def discover_plugins(self) -> None:
         """
         Auto-discover extractor plugins by walking the plugins directory.