Homogenizes loader API.

Author: aaronstevenwhite

README.md

@@ -36,8 +36,9 @@ Then start using the data:
 ```python
 from glazing.search import UnifiedSearch
 
+# Automatically uses default data directory after 'glazing init'
 search = UnifiedSearch()
-results = search.search_by_query("give")
+results = search.search("give")
 
 for result in results[:5]:
     print(f"{result.dataset}: {result.name} - {result.description}")
@@ -65,31 +66,36 @@ Load and work with individual datasets:
 ```python
 from glazing.framenet.loader import FrameNetLoader
 from glazing.verbnet.loader import VerbNetLoader
-from pathlib import Path
 
-# Load datasets
-data_dir = Path.home() / ".local/share/glazing/converted"
-
-fn_loader = FrameNetLoader()
-frames = fn_loader.load_frames(data_dir / "framenet.jsonl")
+# Loaders automatically use default paths and load data after 'glazing init'
+fn_loader = FrameNetLoader()  # Data is already loaded
+frames = fn_loader.frames
 
-vn_loader = VerbNetLoader()
-verb_classes = vn_loader.load_verb_classes(data_dir / "verbnet.jsonl")
+vn_loader = VerbNetLoader()  # Data is already loaded
+verb_classes = list(vn_loader.classes.values())
 ```
 
 Cross-reference resolution:
 
 ```python
-from glazing.references.resolver import ReferenceResolver
 from glazing.references.extractor import ReferenceExtractor
+from glazing.verbnet.loader import VerbNetLoader
+from glazing.propbank.loader import PropBankLoader
 
-# Extract and resolve references
-extractor = ReferenceExtractor()
-references = extractor.extract_from_datasets(data_dir)
+# Load datasets
+vn_loader = VerbNetLoader()
+pb_loader = PropBankLoader()
 
-resolver = ReferenceResolver(references)
-related = resolver.resolve("give.01", source="propbank")
-print(f"VerbNet classes: {related.verbnet_classes}")
+# Extract references
+extractor = ReferenceExtractor()
+extractor.extract_verbnet_references(list(vn_loader.classes.values()))
+extractor.extract_propbank_references(list(pb_loader.framesets.values()))
+
+# Access PropBank cross-references
+if "give.01" in extractor.propbank_refs:
+    refs = extractor.propbank_refs["give.01"]
+    vn_classes = refs.get_verbnet_classes()
+    print(f"VerbNet classes for give.01: {vn_classes}")
 ```
 
 ## Supported Datasets
@@ -142,3 +148,7 @@ MIT License - see [LICENSE](LICENSE) file for details.
 - [PyPI Package](https://pypi.org/project/glazing/)
 - [Documentation](https://glazing.readthedocs.io)
 - [Issue Tracker](https://github.com/aaronstevenwhite/glazing/issues)
+
+## Acknowledgments
+
+This project was funded by a [National Science Foundation](https://www.nsf.gov/) ([BCS-2040831](https://www.nsf.gov/awardsearch/showAward?AWD_ID=2040831)) and builds upon the foundational work of the FrameNet, PropBank, VerbNet, and WordNet teams.

docs/api/index.md

@@ -74,8 +74,8 @@ from glazing.references.resolver import ReferenceResolver
 from pathlib import Path
 from glazing.verbnet.loader import VerbNetLoader
 
-loader = VerbNetLoader()
-verb_classes = loader.load_verb_classes(Path("data/verbnet.jsonl"))
+loader = VerbNetLoader(Path("data/verbnet.jsonl"))
+verb_classes = loader.load_verb_classes()
 ```
 
 ### Searching
@@ -84,7 +84,7 @@ verb_classes = loader.load_verb_classes(Path("data/verbnet.jsonl"))
 from glazing.search import UnifiedSearch
 
 search = UnifiedSearch()
-results = search.search_by_query("abandon")
+results = search.search("abandon")
 ```
 
 ## Type Safety

docs/index.md

@@ -48,11 +48,12 @@ After initialization, you can immediately start exploring the data:
 
 ```python
 from glazing.search import UnifiedSearch
-from pathlib import Path
 
-# Search across all datasets
+# Automatically uses default data directory after 'glazing init'
 search = UnifiedSearch()
-results = search.search_by_query("give")
+
+# Search across all datasets
+results = search.search("give")
 
 for result in results[:5]:
     print(f"{result.dataset}: {result.name} - {result.description}")
@@ -95,7 +96,7 @@ Glazing is actively maintained and welcomes contributions. The project follows s
 
 ## License
 
-MIT License - see [LICENSE](https://github.com/aaronstevenwhite/glazing/blob/main/LICENSE) file for details.
+This package is licensed under an MIT License. See [LICENSE](https://github.com/aaronstevenwhite/glazing/blob/main/LICENSE) file for details.
 
 ## Citation
 
@@ -109,3 +110,7 @@ If you use Glazing in your research, please cite:
   url = {https://github.com/aaronstevenwhite/glazing}
 }
 ```
+
+## Acknowledgments
+
+This project was funded by a [National Science Foundation](https://www.nsf.gov/) ([BCS-2040831](https://www.nsf.gov/awardsearch/showAward?AWD_ID=2040831)) and builds upon the foundational work of the FrameNet, PropBank, VerbNet, and WordNet teams.

docs/quick-start.md

@@ -19,14 +19,14 @@ This one-time setup downloads ~120MB of data and prepares it for use.
 Find entries across all datasets:
 
 ```bash
-# Search for "give" in all datasets
-glazing search query "give" --data-dir ~/.local/share/glazing/converted
+# Search for "give" in all datasets (uses default data directory)
+glazing search query "give"
 
 # Search only in VerbNet
-glazing search query "give" --dataset verbnet --data-dir ~/.local/share/glazing/converted
+glazing search query "give" --dataset verbnet
 
 # Get JSON output
-glazing search query "give" --json --data-dir ~/.local/share/glazing/converted
+glazing search query "give" --json
 ```
 
 ### Find Cross-References
@@ -35,8 +35,7 @@ Discover connections between datasets:
 
 ```bash
 # Find VerbNet classes for a PropBank roleset
-glazing search cross-ref --source propbank --target verbnet --id "give.01" \
-    --data-dir ~/.local/share/glazing/converted
+glazing search cross-ref --source propbank --target verbnet --id "give.01"
 ```
 
 ### Get Dataset Information
@@ -57,13 +56,12 @@ glazing download info verbnet
 
 ```python
 from glazing.search import UnifiedSearch
-from pathlib import Path
 
-# Initialize search with default data directory
+# Initialize search (automatically uses default paths)
 search = UnifiedSearch()
 
 # Search across all datasets
-results = search.search_by_query("abandon")
+results = search.search("abandon")
 
 for result in results[:5]:
     print(f"{result.dataset}: {result.name}")
@@ -77,32 +75,27 @@ for result in results[:5]:
 ```python
 from glazing.framenet.loader import FrameNetLoader
 from glazing.verbnet.loader import VerbNetLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
-
-# Load FrameNet
-fn_loader = FrameNetLoader()
-frames = fn_loader.load_frames(data_dir / "framenet.jsonl")
+# Loaders automatically use default paths and load data after 'glazing init'
+fn_loader = FrameNetLoader()  # Data is already loaded
+frames = fn_loader.frames
 print(f"Loaded {len(frames)} frames")
 
-# Load VerbNet
-vn_loader = VerbNetLoader()
-verb_classes = vn_loader.load_verb_classes(data_dir / "verbnet.jsonl")
+vn_loader = VerbNetLoader()  # Data is already loaded
+verb_classes = list(vn_loader.classes.values())
 print(f"Loaded {len(verb_classes)} verb classes")
 ```
 
 ### Work with VerbNet Classes
 
 ```python
 from glazing.verbnet.loader import VerbNetLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Loader automatically uses default path and loads data
 loader = VerbNetLoader()
 
-# Load all verb classes
-classes = loader.load_verb_classes(data_dir / "verbnet.jsonl")
+# Access already loaded verb classes
+classes = list(loader.classes.values())
 
 # Find a specific class
 give_class = next(
@@ -125,13 +118,12 @@ if give_class:
 
 ```python
 from glazing.propbank.loader import PropBankLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Loader automatically uses default path and loads data
 loader = PropBankLoader()
 
-# Load framesets
-framesets = loader.load_framesets(data_dir / "propbank.jsonl")
+# Access already loaded framesets
+framesets = list(loader.framesets.values())
 
 # Find rolesets for "give"
 give_framesets = [fs for fs in framesets if fs.lemma == "give"]
@@ -149,16 +141,20 @@ for frameset in give_framesets:
 ```python
 from glazing.references.extractor import ReferenceExtractor
 from glazing.references.resolver import ReferenceResolver
-from pathlib import Path
+from glazing.verbnet.loader import VerbNetLoader
+from glazing.propbank.loader import PropBankLoader
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Load datasets
+vn_loader = VerbNetLoader()  # Automatically loads data
+pb_loader = PropBankLoader()  # Automatically loads data
 
-# Extract all references
+# Extract references
 extractor = ReferenceExtractor()
-references = extractor.extract_from_datasets(data_dir)
+extractor.extract_verbnet_references(list(vn_loader.classes.values()))
+extractor.extract_propbank_references(list(pb_loader.framesets.values()))
 
 # Resolve references for a PropBank roleset
-resolver = ReferenceResolver(references)
+resolver = ReferenceResolver(extractor.mapping_index)
 related = resolver.resolve("give.01", source="propbank")
 
 print(f"PropBank roleset: give.01")
@@ -171,13 +167,10 @@ print(f"WordNet senses: {related.wordnet_senses}")
 
 ```python
 from glazing.wordnet.loader import WordNetLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Loader automatically uses default path and loads data
 loader = WordNetLoader()
-
-# Load synsets
-synsets = loader.load_synsets(data_dir / "wordnet.jsonl")
+synsets = list(loader.synsets.values())  # Already loaded
 
 # Find synsets for "dog"
 dog_synsets = [s for s in synsets if any(
@@ -203,13 +196,12 @@ For memory-efficient processing:
 
 ```python
 from glazing.verbnet.loader import VerbNetLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
-loader = VerbNetLoader()
+# For memory-efficient streaming, use lazy loading
+loader = VerbNetLoader(lazy=True, autoload=False)
 
 # Stream verb classes one at a time
-for verb_class in loader.stream_verb_classes(data_dir / "verbnet.jsonl"):
+for verb_class in loader.iter_verb_classes():
     # Process each class without loading all into memory
     if "run" in [m.name for m in verb_class.members]:
         print(f"Found 'run' in class: {verb_class.id}")
@@ -222,10 +214,11 @@ for verb_class in loader.stream_verb_classes(data_dir / "verbnet.jsonl"):
 
 ```python
 from glazing.verbnet.search import VerbNetSearch
-from pathlib import Path
+from glazing.verbnet.loader import VerbNetLoader
 
-data_dir = Path.home() / ".local/share/glazing/converted"
-search = VerbNetSearch(data_dir / "verbnet.jsonl")
+# Loader automatically loads data
+loader = VerbNetLoader()
+search = VerbNetSearch(list(loader.classes.values()))
 
 # Find all classes with an Agent role
 agent_classes = []
@@ -241,13 +234,10 @@ print(f"Classes with Agent role: {len(agent_classes)}")
 ```python
 import json
 from glazing.framenet.loader import FrameNetLoader
-from pathlib import Path
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Loader automatically uses default path and loads data
 loader = FrameNetLoader()
-
-# Load frames
-frames = loader.load_frames(data_dir / "framenet.jsonl")
+frames = loader.frames  # Already loaded
 
 # Export as simple JSON
 simple_frames = []

docs/user-guide/cli.md

@@ -98,11 +98,11 @@ Common Options:
 # 1. Initialize everything
 glazing init
 
-# 2. Search for a concept
-glazing search query "give" --data-dir ~/.local/share/glazing/converted
+# 2. Search for a concept (uses default data directory)
+glazing search query "give"
 
 # 3. Find cross-references
-glazing search cross-ref --source propbank --id "give.01"     --target verbnet --data-dir ~/.local/share/glazing/converted
+glazing search cross-ref --source propbank --id "give.01" --target verbnet
 ```
 
 ### Custom Data Directory
@@ -122,13 +122,13 @@ glazing search query "run"
 
 ```bash
 # Download only VerbNet
-glazing download dataset --dataset verbnet --output-dir raw/
+glazing download dataset --dataset verbnet
 
 # Convert it
-glazing convert dataset --dataset verbnet     --input-dir raw/verbnet-3.4 --output-dir converted/
+glazing convert dataset --dataset verbnet
 
-# Search it
-glazing search query "run" --dataset verbnet --data-dir converted/
+# Search it (uses default converted directory)
+glazing search query "run" --dataset verbnet
 ```
 
 ## Output Formats

docs/user-guide/cross-references.md

@@ -51,16 +51,20 @@ glazing search cross-ref --source propbank --id "give.01" \
 ```python
 from glazing.references.extractor import ReferenceExtractor
 from glazing.references.resolver import ReferenceResolver
-from pathlib import Path
+from glazing.verbnet.loader import VerbNetLoader
+from glazing.propbank.loader import PropBankLoader
 
-data_dir = Path.home() / ".local/share/glazing/converted"
+# Load datasets
+vn_loader = VerbNetLoader()  # Automatically loads data
+pb_loader = PropBankLoader()  # Automatically loads data
 
-# Extract all references
+# Extract references
 extractor = ReferenceExtractor()
-references = extractor.extract_from_datasets(data_dir)
+extractor.extract_verbnet_references(list(vn_loader.classes.values()))
+extractor.extract_propbank_references(list(pb_loader.framesets.values()))
 
 # Resolve for specific item
-resolver = ReferenceResolver(references)
+resolver = ReferenceResolver(extractor.mapping_index)
 related = resolver.resolve("give.01", source="propbank")
 
 print(f"VerbNet: {related.verbnet_classes}")
@@ -74,14 +78,19 @@ print(f"FrameNet: {related.framenet_frames}")
 
 ```python
 from glazing.references.extractor import ReferenceExtractor
+from glazing.verbnet.loader import VerbNetLoader
 
-extractor = ReferenceExtractor()
+# Load dataset
+vn_loader = VerbNetLoader()
 
-# Extract from all datasets
-all_refs = extractor.extract_from_datasets(data_dir)
+# Extract references
+extractor = ReferenceExtractor()
 
 # Extract from specific dataset
-vn_refs = extractor.extract_from_verbnet(verb_classes)
+extractor.extract_verbnet_references(list(vn_loader.classes.values()))
+
+# Access extracted references
+vn_refs = extractor.verbnet_refs
 ```
 
 ### Manual Mapping