Skip to content

chore(lexicon): describe every lexicon category #915

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jirhiker wants to merge 1 commit into
base: staging
Choose a base branch
from
+237 −67
Open

chore(lexicon): describe every lexicon category #915

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions core/initializers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
from pathlib import Path

from fastapi_pagination import add_pagination
from sqlalchemy import text, select
from sqlalchemy import text, select, func
from sqlalchemy.dialects.postgresql import insert
from sqlalchemy.exc import DatabaseError

Expand Down Expand Up @@ -105,13 +105,22 @@ def init_lexicon(path: str = None) -> None:
category_rows = [
{"name": category["name"], "description": category["description"]}
for category in categories
if category["name"] not in existing_categories
]
if category_rows:
# Insert every category, not just the missing ones, so that a
# category seeded before it had a description gets backfilled.
# coalesce keeps a description already in the database, so an
# edit made through /lexicon survives re-running the seed.
stmt = insert(LexiconCategory).values(category_rows)
session.execute(
insert(LexiconCategory)
.values(category_rows)
.on_conflict_do_nothing(index_elements=["name"])
stmt.on_conflict_do_update(
index_elements=["name"],
set_={
"description": func.coalesce(
LexiconCategory.description, stmt.excluded.description
)
},
)
)
session.commit()
existing_categories = dict(
Expand Down
122 changes: 61 additions & 61 deletions core/lexicon.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,247 +2,247 @@
"categories": [
{
"name": "activity_type",
"description": null
"description": "Kinds of field activity recorded under a field event: well inventory, groundwater level, water chemistry. Determines which activity-specific tables a visit populates."
},
{
"name": "address_type",
"description": null
"description": "Role an address plays for a contact (Primary, Work, Mailing, Physical). Describes the address's use, not its format."
},
{
"name": "analysis_method_type",
"description": null
"description": "Broad class of analysis behind a result: laboratory, field procedure, or calculation. Coarser than the named method itself."
},
{
"name": "aquifer_type",
"description": null
"description": "Confinement and saturation state of the aquifer a well or spring taps, e.g. confined, unconfined, perched, aquitard."
},
{
"name": "casing_material",
"description": null
"description": "Material a well's casing is made of. Paired with screen_type, which records the same materials for the screened interval."
},
{
"name": "collection_method",
"description": null
"description": "Method used to collect a value recorded on data_provenance. Union of the legacy NM_Aquifer LU_AltitudeMethod and LU_CoordinateMethod lookups, so it spans both elevation and horizontal position."
},
{
"name": "well_construction_method",
"description": null
"description": "Drilling or excavation technique used to construct a well, e.g. air-rotary, cable-tool, bored or augered."
},
{
"name": "contact_type",
"description": null
"description": "Role a contact holds for a record: primary, secondary, or field event participant."
},
{
"name": "coordinate_method",
"description": null
"description": "Method used to determine a horizontal position. Legacy NM_Aquifer LU_CoordinateMethod; its terms also feed the broader collection_method category."
},
{
"name": "country",
"description": null
"description": "Country names used in addresses and geographic references. No terms are seeded; populated as needed."
},
{
"name": "county",
"description": null
"description": "County names used in addresses and location references. No terms are seeded; populated as needed."
},
{
"name": "data_quality",
"description": null
"description": "Accuracy statement for a groundwater level measurement, mostly the USGS accuracy levels (nearest foot, tenth, hundredth). Records precision, not review state; see data_maturity for that."
},
{
"name": "data_reliability",
"description": null
"description": "Whether a legacy record was field checked and by whom, e.g. checked by the reporting agency, or not field checked but considered reliable."
},
{
"name": "data_source",
"description": null
"description": "Who supplied a value in the legacy NM_Aquifer record (driller's log, well owner, NMBGMR staff). Legacy LU_DataSource; its terms also feed origin_type."
},
{
"name": "depth_completion_source",
"description": null
"description": "Source of a reported well depth or completion detail. Legacy NM_Aquifer LU_Depth_CompletionSource; its terms also feed origin_type."
},
{
"name": "discharge_source",
"description": null
"description": "Who supplied a surface-water discharge value, e.g. another agency, a published report, a Bureau scientist."
},
{
"name": "drilling_fluid",
"description": null
"description": "Fluid circulated while drilling a well."
},
{
"name": "elevation_method",
"description": null
"description": "Method used to determine a land-surface or measuring-point elevation. Legacy NM_Aquifer LU_AltitudeMethod; its terms also feed collection_method."
},
{
"name": "email_type",
"description": null
"description": "Role an email address plays for a contact: primary, work, or personal."
},
{
"name": "participant_role",
"description": null
"description": "Role a contact played at a field event: lead, participant, observer, or visitor."
},
{
"name": "geochronology",
"description": null
"description": "Radiometric dating systems used to report a geologic age, e.g. Ar/Ar, K/Ar, U/Pb."
},
{
"name": "geographic_scale",
"description": null
"description": "Extent of an aquifer system: major, regional, local, or minor."
},
{
"name": "groundwater_level_reason",
"description": null
"description": "USGS-style condition codes explaining why a water level reads as it does or could not be measured, e.g. site dry, frozen, flowing, obstructed, or being pumped."
},
{
"name": "group_type",
"description": null
"description": "What a group of things represents: a monitoring plan, a geographic area, or a historical grouping. Not a provenance marker."
},
{
"name": "horizontal_datum",
"description": null
"description": "Datum a horizontal coordinate was reported against (WGS84, NAD83, NAD27). Stored geometry is always WGS84 / SRID 4326 regardless."
},
{
"name": "level_status",
"description": null
"description": "Trend of a water level over time: stable, rising, or falling."
},
{
"name": "limit_type",
"description": null
"description": "Kind of regulatory or analytical threshold a limit value represents, e.g. MCL, SMCL, GWQS, MDL, PQL, RL."
},
{
"name": "measurement_method",
"description": null
"description": "Method used to take a measurement where no more specific method category applies."
},
{
"name": "monitoring_frequency",
"description": null
"description": "How often a site is scheduled to be visited or measured, from monthly through decadal, plus event-based."
},
{
"name": "note_type",
"description": null
"description": "Subject of a free-text note attached to a record, e.g. access, directions, construction, water quality."
},
{
"name": "parameter_name",
"description": null
"description": "Names of measured or analyzed parameters, e.g. groundwater level, pH, calcium. Backs the parameter table; every observation points at one of these."
},
{
"name": "organization",
"description": null
"description": "Agencies, companies, water associations, ranches and other organizations named as owners, drillers, or data sources."
},
{
"name": "parameter_type",
"description": null
"description": "Broad class a parameter falls into: field parameter, metal, radionuclide, major or minor element, physical property."
},
{
"name": "phone_type",
"description": null
"description": "Role a phone number plays for a contact: primary, work, home, or mobile."
},
{
"name": "publication_type",
"description": null
"description": "Form a bibliography entry takes, e.g. map, report, dataset, thesis, webpage."
},
{
"name": "qc_type",
"description": null
"description": "Quality-control role of a collected sample: normal, duplicate, split, or one of the blank types."
},
{
"name": "quality_flag",
"description": null
"description": "Judgement of an individual result: good, questionable, estimated, or rejected."
},
{
"name": "relation",
"description": null
"description": "Predicates used by lexicon triples and by cross-system identifier links, e.g. same_as, OSEWellTagID, OSEPOD, PLSS."
},
{
"name": "release_status",
"description": null
"description": "Release level of a record, i.e. who may see it. Also holds historical review-state terms (provisional, final) kept for old rows; new code puts review state in data_maturity."
},
{
"name": "review_status",
"description": null
"description": "Two-state review marker on transducer records: approved or not reviewed."
},
{
"name": "role",
"description": null
"description": "Role a person or organization plays for a well or project, e.g. owner, driller, hydrologist, principal investigator."
},
{
"name": "sample_matrix",
"description": null
"description": "Physical medium a sample was collected from: water, groundwater, or soil."
},
{
"name": "sample_method",
"description": null
"description": "Technique used to obtain a measurement or sample, e.g. transducer, airline measurement, pressure gage, sonic water level meter."
},
{
"name": "sample_type",
"description": null
"description": "Purpose a collected sample serves, e.g. standard field sample, background, repeat, or one of the blank and duplicate types."
},
{
"name": "screen_type",
"description": null
"description": "Material of a well's screened interval. Same term set as casing_material, which covers the casing instead."
},
{
"name": "sensor_type",
"description": null
"description": "Kind of instrument deployed at a site, e.g. pressure transducer, barometer, tipping bucket, weather station."
},
{
"name": "sensor_status",
"description": null
"description": "Service state of a deployed sensor: in service, in repair, retired, or lost."
},
{
"name": "spring_type",
"description": null
"description": "Character of a spring, e.g. artesian, ephemeral, perennial, thermal, mineral."
},
{
"name": "state",
"description": null
"description": "State or province names used in addresses and location references. No terms are seeded; populated as needed."
},
{
"name": "status",
"description": null
"description": "Generic status category, currently holding only 'Unknown'. Status tracked over time uses status_type and status_value on status_history instead."
},
{
"name": "thing_type",
"description": null
"description": "Kind of monitoring point a thing is, e.g. observation well, piezometer, production well, spring, stream."
},
{
"name": "unit",
"description": null
"description": "Units of measure for observations and accuracy values, e.g. ft, ftbgs, mg/L, deg C."
},
{
"name": "vertical_datum",
"description": null
"description": "Datum a vertical coordinate or elevation is referenced to: NAVD88, NGVD29, or WGS84."
},
{
"name": "well_purpose",
"description": null
"description": "Use a well is put to, e.g. domestic, irrigation, livestock, public supply, observation."
},
{
"name": "status_type",
"description": null
"description": "Which status axis a status_history entry tracks, e.g. well status, monitoring status, access status, datalogger suitability status."
},
{
"name": "status_value",
"description": null
"description": "Values a status_history entry may take across the status_type axes, e.g. open, closed, abandoned, currently monitored."
},
{
"name": "origin_type",
"description": null
"description": "Where a value recorded on data_provenance came from. Union of the legacy NM_Aquifer LU_DataSource and LU_Depth_CompletionSource lookups."
},
{
"name": "well_pump_type",
"description": null
"description": "Kind of pump installed in a well: submersible, jet, line shaft, hand, or windmill."
},
{
"name": "permission_type",
"description": null
"description": "Activity a landowner has consented to at a site: water level sampling, water chemistry sampling, or datalogger installation. Site-access consent, not authorization."
},
{
"name": "formation_code",
"description": null
"description": "Short codes identifying geologic formations, e.g. '120ELRT'. Used as the controlled vocabulary for geologic_formation.formation_code."
},
{
"name": "lithology",
"description": null
"description": "Rock and sediment types recorded in drill and formation logs, e.g. alluvium, basalt, clay, caliche, conglomerate."
},
{
"name": "data_maturity",
Expand Down
Loading
Loading