diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index faa846a53c..2cbb858aea 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -27,7 +27,7 @@ repos: # Formatters: hooks that re-write Python & documentation files #################################################################################### - repo: https://github.com/astral-sh/ruff-pre-commit - rev: v0.0.287 + rev: v0.0.288 hooks: - id: ruff args: [--fix, --exit-non-zero-on-fix] diff --git a/src/pudl/metadata/constants.py b/src/pudl/metadata/constants.py index aae9a830db..6505c5e409 100644 --- a/src/pudl/metadata/constants.py +++ b/src/pudl/metadata/constants.py @@ -259,6 +259,39 @@ "government", "federal", ], + "msha": [ + "msha", + "mshamines", + "mine safety and health administration", + "mines", + "mining", + "coal", + "metal", + "department of labor", + ], + "phmsa": [ + "phmsa", + "phmsagas", + "pipelines and hazardous materials safety administration", + "pipelines", + "natural gas", + "transmission", + "distribution", + "gathering", + "liquified natural gas", + "lng", + "underground natural gas storage", + "department of transportation", + "us dot", + ], + "eia_water": [ + "eia thermoelectric cooling water", + "eia waterthermoelectric", + "cooling water", + "water usage", + "water energy nexus", + "energy water nexus", + ], } XBRL_TABLES = [ diff --git a/src/pudl/metadata/sources.py b/src/pudl/metadata/sources.py index 69937dc444..87f2382510 100644 --- a/src/pudl/metadata/sources.py +++ b/src/pudl/metadata/sources.py @@ -50,11 +50,10 @@ [ "eia176", "form 176", + "natural gas", ] + KEYWORDS["eia"] + KEYWORDS["us_govt"] - + KEYWORDS["fuels"] - + KEYWORDS["environment"] ) ), "license_raw": LICENSES["us-govt"], @@ -262,6 +261,9 @@ "Monthly cooling water usage by generator and boiler. Data " "collected in conjunction with the EIA-860 and EIA-923." ), + "keywords": sorted( + set(KEYWORDS["eia"] + KEYWORDS["us_govt"] + KEYWORDS["eia_water"]) + ), "license_raw": LICENSES["us-govt"], "license_pudl": LICENSES["cc-by-4.0"], }, @@ -523,6 +525,17 @@ "as well as transaction information for short-term and long-term " "market-based power sales and cost-based power sales." ), + "keywords": sorted( + set( + [ + "ferceqr", + "electric quarterly report", + ] + + KEYWORDS["ferc"] + + KEYWORDS["us_govt"] + + KEYWORDS["electricity"] + ) + ), "license_raw": LICENSES["us-govt"], "license_pudl": LICENSES["cc-by-4.0"], }, @@ -535,6 +548,7 @@ "mine (Active, Abandoned, NonProducing, etc.), the current owner and " "operating company, commodity codes and physical attributes of the mine." ), + "keywords": sorted(set(KEYWORDS["msha"] + KEYWORDS["us_govt"])), "license_raw": LICENSES["us-govt"], "license_pudl": LICENSES["cc-by-4.0"], }, @@ -548,6 +562,7 @@ "pipeline mileage, facilities, commodities transported, miles by material, " "and installation dates." ), + "keywords": sorted(set(KEYWORDS["phmsa"] + KEYWORDS["us_govt"])), "license_raw": LICENSES["us-govt"], "license_pudl": LICENSES["cc-by-4.0"], },