GitHub - john-root/natbakke: IIIF and Entity extraction toolset

john-root / natbakke Public

forked from mattmcgrattan/natbakke

Notifications You must be signed in to change notification settings
Fork 0
Star 0

IIIF and Entity extraction toolset

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 271 Commits
tests		tests
.gitignore		.gitignore
GB.txt		GB.txt
GeoNames.htm		GeoNames.htm
README.txt		README.txt
__init__.py		__init__.py
anno_handler.py		anno_handler.py
basics.py		basics.py
canvas_processor.py		canvas_processor.py
canvas_worker.conf		canvas_worker.conf
canvas_worker.ini		canvas_worker.ini
csv_stats.py		csv_stats.py
flask_manifester.py		flask_manifester.py
gazetteer_update.py		gazetteer_update.py
gb.zip		gb.zip
gb_gaz.zip		gb_gaz.zip
geonames_import.py		geonames_import.py
input.html		input.html
lod_test.py		lod_test.py
lod_test_new.py		lod_test_new.py
manifest_enqueue.py		manifest_enqueue.py
master.csv		master.csv
matcher_load.py		matcher_load.py
matcher_test.py		matcher_test.py
new_mexico.json		new_mexico.json
ocr_basics.py		ocr_basics.py
output.csv		output.csv
output_master.csv		output_master.csv
output_tribes.csv		output_tribes.csv
parser_basics.py		parser_basics.py
processor.py		processor.py
queue_processor.py		queue_processor.py
queue_receiver.py		queue_receiver.py
req.txt		req.txt
requirements.txt		requirements.txt
schmentities.py		schmentities.py
schmentities_ocr.py		schmentities_ocr.py
schmentities_ocr2.py		schmentities_ocr2.py
schmentities_refactor.py		schmentities_refactor.py
schmentities_tribes.py		schmentities_tribes.py
spacy_basics.py		spacy_basics.py
stats.csv		stats.csv
stats_master.json		stats_master.json
stats_master_tribes.json		stats_master_tribes.json
test_a.json		test_a.json
test_b.json		test_b.json
tribe_list2.txt		tribe_list2.txt
tribes.py		tribes.py
tribes_import.py		tribes_import.py
usa.json.zip		usa.json.zip
usa_gazetteer.json.zip		usa_gazetteer.json.zip

Repository files navigation

To Do:

Better handling of segmented text.
Better OCR handling.
More accurate registration of hOCR and OCR'd text with annos.
Additional sources of linked open data.
Validate that custom matchers are working.
Box joining.



Sample OCR text:



Manual add of individual example e.g. Toadlena as an entity works, but the bulk add does not seem to be working.

Source of data for enrichment:

names.mongabay.com/data/indians.html