mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 22:01:09 +02:00
feat(geocoding): auto-categorize places via Pelias taxonomy
Pelias hides the 'category' field from API responses unless the caller filters by categories=... explicitly — a default intended for keyword search that strips category metadata from address queries. Patch the Pelias API's geojsonify_place_details.js so the category array is returned on every feature (food, retail, transport, …), mounted into the container as a read-only volume override. Rewrite category-map.ts to map Pelias' OSM taxonomy to our 7 PlaceCategories using a priority-ordered list so a restaurant tagged ['food','retail','nightlife'] resolves to 'food' (the most specific), not 'shopping'. Verified with Konstanz test queries: Konzil Restaurant → food Bahnhof Konstanz → transit Physiotherapie-Schule → work MX-Park → leisure Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Till JS
parent
1293756bbf
commit
e82b5c1449
5 changed files with 195 additions and 156 deletions
|
|
@ -21,6 +21,14 @@ services:
|
|||
PORT: 4000
|
||||
volumes:
|
||||
- ./pelias.json:/code/pelias.json:ro
|
||||
# Patch: always return the `category` field in API responses, not only
|
||||
# when a `categories=...` filter is present. Pelias' default
|
||||
# `checkCategoryParam` hides category from results unless the caller
|
||||
# filters by it, but we want the OSM taxonomy (food, retail, transport, …)
|
||||
# on every venue so our Places UI can auto-map it to a PlaceCategory.
|
||||
# The patched file is generated from the upstream one with
|
||||
# `sed "s|condition: checkCategoryParam|condition: () => true|"`
|
||||
- ./geojsonify_place_details.js:/code/pelias/api/helper/geojsonify_place_details.js:ro
|
||||
depends_on:
|
||||
elasticsearch:
|
||||
condition: service_healthy
|
||||
|
|
|
|||
123
services/mana-geocoding/pelias/geojsonify_place_details.js
Normal file
123
services/mana-geocoding/pelias/geojsonify_place_details.js
Normal file
|
|
@ -0,0 +1,123 @@
|
|||
const _ = require('lodash');
|
||||
const field = require('./fieldValue');
|
||||
|
||||
// Properties to be copied
|
||||
// If a property is identified as a single string, assume it should be presented as a string in response
|
||||
// If something other than string is desired, use the following structure: { name: 'category', type: 'array' }
|
||||
const DETAILS_PROPS = [
|
||||
{ name: 'unit', type: 'string' },
|
||||
{ name: 'housenumber', type: 'string' },
|
||||
{ name: 'street', type: 'string' },
|
||||
{ name: 'postalcode', type: 'string' },
|
||||
{ name: 'postalcode_gid', type: 'string' },
|
||||
{ name: 'confidence', type: 'default' },
|
||||
{ name: 'match_type', type: 'string' },
|
||||
{ name: 'distance', type: 'default' },
|
||||
{ name: 'accuracy', type: 'string' },
|
||||
{ name: 'country', type: 'string' },
|
||||
{ name: 'country_gid', type: 'string' },
|
||||
{ name: 'country_a', type: 'string' },
|
||||
{ name: 'dependency', type: 'string' },
|
||||
{ name: 'dependency_gid', type: 'string' },
|
||||
{ name: 'dependency_a', type: 'string' },
|
||||
{ name: 'macroregion', type: 'string' },
|
||||
{ name: 'macroregion_gid', type: 'string' },
|
||||
{ name: 'macroregion_a', type: 'string' },
|
||||
{ name: 'region', type: 'string' },
|
||||
{ name: 'region_gid', type: 'string' },
|
||||
{ name: 'region_a', type: 'string' },
|
||||
{ name: 'macrocounty', type: 'string' },
|
||||
{ name: 'macrocounty_gid', type: 'string' },
|
||||
{ name: 'macrocounty_a', type: 'string' },
|
||||
{ name: 'county', type: 'string' },
|
||||
{ name: 'county_gid', type: 'string' },
|
||||
{ name: 'county_a', type: 'string' },
|
||||
{ name: 'localadmin', type: 'string' },
|
||||
{ name: 'localadmin_gid', type: 'string' },
|
||||
{ name: 'localadmin_a', type: 'string' },
|
||||
{ name: 'locality', type: 'string' },
|
||||
{ name: 'locality_gid', type: 'string' },
|
||||
{ name: 'locality_a', type: 'string' },
|
||||
{ name: 'borough', type: 'string' },
|
||||
{ name: 'borough_gid', type: 'string' },
|
||||
{ name: 'borough_a', type: 'string' },
|
||||
{ name: 'neighbourhood', type: 'string' },
|
||||
{ name: 'neighbourhood_gid', type: 'string' },
|
||||
{ name: 'continent', type: 'string' },
|
||||
{ name: 'continent_gid', type: 'string' },
|
||||
{ name: 'continent_a', type: 'string' },
|
||||
{ name: 'empire', type: 'string', condition: _.negate(hasCountry) },
|
||||
{ name: 'empire_gid', type: 'string', condition: _.negate(hasCountry) },
|
||||
{ name: 'empire_a', type: 'string', condition: _.negate(hasCountry) },
|
||||
{ name: 'ocean', type: 'string' },
|
||||
{ name: 'ocean_gid', type: 'string' },
|
||||
{ name: 'ocean_a', type: 'string' },
|
||||
{ name: 'marinearea', type: 'string' },
|
||||
{ name: 'marinearea_gid', type: 'string' },
|
||||
{ name: 'marinearea_a', type: 'string' },
|
||||
{ name: 'bounding_box', type: 'default' },
|
||||
{ name: 'label', type: 'string' },
|
||||
{ name: 'category', type: 'array', condition: () => true },
|
||||
];
|
||||
|
||||
const EXTENDED_PROPS = DETAILS_PROPS.concat([
|
||||
{ name: 'population', type: 'default' },
|
||||
{ name: 'popularity', type: 'default' },
|
||||
]);
|
||||
|
||||
// returns true IFF source a country_gid property
|
||||
function hasCountry(params, source) {
|
||||
return source.hasOwnProperty('country_gid');
|
||||
}
|
||||
|
||||
function checkCategoryParam(params) {
|
||||
return _.isObject(params) && params.hasOwnProperty('categories');
|
||||
}
|
||||
|
||||
/**
|
||||
* Collect the specified properties from source into an object and return it
|
||||
* Ignore missing properties.
|
||||
*
|
||||
* @param {object} params clean query params
|
||||
* @param {object} source
|
||||
* @param {object} dst
|
||||
*/
|
||||
function collectProperties(params, source) {
|
||||
let props = DETAILS_PROPS;
|
||||
|
||||
// extended properties when debugging mode is enabled
|
||||
if (params.enableDebug === true) {
|
||||
props = EXTENDED_PROPS;
|
||||
}
|
||||
|
||||
return props.reduce((result, prop) => {
|
||||
// if condition isn't met, don't set the property
|
||||
if (_.isFunction(prop.condition) && !prop.condition(params, source)) {
|
||||
return result;
|
||||
}
|
||||
|
||||
if (source.hasOwnProperty(prop.name)) {
|
||||
let value = null;
|
||||
|
||||
switch (prop.type) {
|
||||
case 'string':
|
||||
value = field.getStringValue(source[prop.name]);
|
||||
break;
|
||||
case 'array':
|
||||
value = field.getArrayValue(source[prop.name]);
|
||||
break;
|
||||
// default behavior is to copy property exactly as is
|
||||
default:
|
||||
value = source[prop.name];
|
||||
}
|
||||
|
||||
if (_.isNumber(value) || (value && !_.isEmpty(value))) {
|
||||
result[prop.name] = value;
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}, {});
|
||||
}
|
||||
|
||||
module.exports = collectProperties;
|
||||
|
|
@ -1,156 +1,75 @@
|
|||
/**
|
||||
* Maps Pelias/OSM categories to our 7 Places categories.
|
||||
* Maps Pelias categories (OSM taxonomy) to our 7 Places categories.
|
||||
*
|
||||
* Pelias returns results with `addendum.osm.category` and `addendum.osm.type`
|
||||
* fields that correspond to OSM key/value pairs. We map these to our simple
|
||||
* category enum: home, work, food, shopping, transit, leisure, other.
|
||||
* Pelias' openstreetmap importer tags venues with categories from its
|
||||
* built-in taxonomy (food, retail, transport, health, education, …).
|
||||
* We collapse those into the simpler Places enum:
|
||||
*
|
||||
* home · work · food · shopping · transit · leisure · other
|
||||
*
|
||||
* A venue can have multiple Pelias categories (e.g. a restaurant is
|
||||
* tagged `['food', 'retail', 'nightlife']`). We pick the most specific
|
||||
* one in priority order rather than the first — a restaurant should be
|
||||
* "food" even though "retail" also matches.
|
||||
*/
|
||||
|
||||
export type PlaceCategory = 'home' | 'work' | 'food' | 'shopping' | 'transit' | 'leisure' | 'other';
|
||||
|
||||
/**
|
||||
* OSM key → PlaceCategory mapping.
|
||||
* The key is the OSM tag key (e.g. "amenity", "shop"), the value maps
|
||||
* specific OSM values to our categories. A `_default` entry covers
|
||||
* any value not explicitly listed.
|
||||
* Priority-ordered: first matching category wins. Earlier entries are
|
||||
* more specific, so "food" beats "retail", "transport" beats "professional".
|
||||
*/
|
||||
const OSM_CATEGORY_MAP: Record<
|
||||
string,
|
||||
Record<string, PlaceCategory> & { _default?: PlaceCategory }
|
||||
> = {
|
||||
amenity: {
|
||||
_default: 'other',
|
||||
restaurant: 'food',
|
||||
cafe: 'food',
|
||||
fast_food: 'food',
|
||||
bar: 'food',
|
||||
pub: 'food',
|
||||
biergarten: 'food',
|
||||
food_court: 'food',
|
||||
ice_cream: 'food',
|
||||
bakery: 'food',
|
||||
school: 'work',
|
||||
university: 'work',
|
||||
college: 'work',
|
||||
library: 'work',
|
||||
coworking_space: 'work',
|
||||
office: 'work',
|
||||
bus_station: 'transit',
|
||||
ferry_terminal: 'transit',
|
||||
taxi: 'transit',
|
||||
parking: 'transit',
|
||||
fuel: 'transit',
|
||||
bicycle_parking: 'transit',
|
||||
charging_station: 'transit',
|
||||
cinema: 'leisure',
|
||||
theatre: 'leisure',
|
||||
nightclub: 'leisure',
|
||||
community_centre: 'leisure',
|
||||
swimming_pool: 'leisure',
|
||||
marketplace: 'shopping',
|
||||
},
|
||||
shop: {
|
||||
_default: 'shopping',
|
||||
supermarket: 'shopping',
|
||||
bakery: 'food',
|
||||
butcher: 'food',
|
||||
deli: 'food',
|
||||
greengrocer: 'food',
|
||||
seafood: 'food',
|
||||
pastry: 'food',
|
||||
cheese: 'food',
|
||||
coffee: 'food',
|
||||
},
|
||||
tourism: {
|
||||
_default: 'leisure',
|
||||
hotel: 'other',
|
||||
hostel: 'other',
|
||||
guest_house: 'other',
|
||||
motel: 'other',
|
||||
apartment: 'home',
|
||||
},
|
||||
leisure: {
|
||||
_default: 'leisure',
|
||||
park: 'leisure',
|
||||
playground: 'leisure',
|
||||
sports_centre: 'leisure',
|
||||
fitness_centre: 'leisure',
|
||||
stadium: 'leisure',
|
||||
swimming_pool: 'leisure',
|
||||
garden: 'leisure',
|
||||
nature_reserve: 'leisure',
|
||||
beach_resort: 'leisure',
|
||||
marina: 'leisure',
|
||||
},
|
||||
railway: {
|
||||
_default: 'transit',
|
||||
station: 'transit',
|
||||
halt: 'transit',
|
||||
tram_stop: 'transit',
|
||||
},
|
||||
aeroway: {
|
||||
_default: 'transit',
|
||||
aerodrome: 'transit',
|
||||
terminal: 'transit',
|
||||
},
|
||||
highway: {
|
||||
_default: 'transit',
|
||||
bus_stop: 'transit',
|
||||
},
|
||||
building: {
|
||||
_default: 'other',
|
||||
residential: 'home',
|
||||
house: 'home',
|
||||
apartments: 'home',
|
||||
detached: 'home',
|
||||
commercial: 'work',
|
||||
office: 'work',
|
||||
industrial: 'work',
|
||||
retail: 'shopping',
|
||||
supermarket: 'shopping',
|
||||
church: 'leisure',
|
||||
cathedral: 'leisure',
|
||||
stadium: 'leisure',
|
||||
school: 'work',
|
||||
university: 'work',
|
||||
hospital: 'other',
|
||||
},
|
||||
office: {
|
||||
_default: 'work',
|
||||
},
|
||||
sport: {
|
||||
_default: 'leisure',
|
||||
},
|
||||
};
|
||||
const PELIAS_PRIORITY: Array<[string, PlaceCategory]> = [
|
||||
// Food is strongest signal — a restaurant is food, not retail
|
||||
['food', 'food'],
|
||||
|
||||
// Transit/transport
|
||||
['transport:public', 'transit'],
|
||||
['transport:air', 'transit'],
|
||||
['transport:sea', 'transit'],
|
||||
['transport:bus', 'transit'],
|
||||
['transport:taxi', 'transit'],
|
||||
['transport', 'transit'],
|
||||
|
||||
// Shopping — explicit retail markers
|
||||
['retail', 'shopping'],
|
||||
|
||||
// Leisure / entertainment / recreation
|
||||
['entertainment', 'leisure'],
|
||||
['nightlife', 'leisure'],
|
||||
['recreation', 'leisure'],
|
||||
|
||||
// Work-ish
|
||||
['education', 'work'],
|
||||
['professional', 'work'],
|
||||
['government', 'work'],
|
||||
['finance', 'work'],
|
||||
|
||||
// Health/religion fall through to other
|
||||
['health', 'other'],
|
||||
['religion', 'other'],
|
||||
];
|
||||
|
||||
/**
|
||||
* Derive a PlaceCategory from a Pelias result's OSM metadata.
|
||||
* Derive a PlaceCategory from a Pelias feature's category array.
|
||||
*
|
||||
* Pelias provides category info in several fields depending on the data source.
|
||||
* We check them in order of specificity.
|
||||
* @param categories The `category` array from a Pelias feature's properties
|
||||
* @param peliasLayer The Pelias layer (venue, address, street, …) — used as fallback hint
|
||||
*/
|
||||
export function mapOsmToPlaceCategory(
|
||||
osmCategory?: string,
|
||||
osmType?: string,
|
||||
export function mapPeliasToPlaceCategory(
|
||||
categories?: string[] | null,
|
||||
peliasLayer?: string
|
||||
): PlaceCategory {
|
||||
// Try direct OSM key/value mapping first
|
||||
if (osmCategory && osmType) {
|
||||
const categoryMap = OSM_CATEGORY_MAP[osmCategory];
|
||||
if (categoryMap) {
|
||||
return categoryMap[osmType] ?? categoryMap._default ?? 'other';
|
||||
if (Array.isArray(categories) && categories.length > 0) {
|
||||
// Walk our priority list and pick the first match
|
||||
for (const [peliasCat, placeCat] of PELIAS_PRIORITY) {
|
||||
if (categories.includes(peliasCat)) return placeCat;
|
||||
}
|
||||
}
|
||||
|
||||
// Try just the OSM key as a category
|
||||
if (osmCategory) {
|
||||
const categoryMap = OSM_CATEGORY_MAP[osmCategory];
|
||||
if (categoryMap?._default) {
|
||||
return categoryMap._default;
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback: use Pelias layer as a hint
|
||||
// Fallback: use Pelias layer as a hint. Addresses/streets/regions
|
||||
// all land in "other" since they aren't really "places" in the
|
||||
// categorical sense.
|
||||
if (peliasLayer) {
|
||||
switch (peliasLayer) {
|
||||
case 'venue':
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@
|
|||
import { Hono } from 'hono';
|
||||
import type { Config } from '../config';
|
||||
import { LRUCache } from '../lib/cache';
|
||||
import { mapOsmToPlaceCategory, type PlaceCategory } from '../lib/category-map';
|
||||
import { mapPeliasToPlaceCategory, type PlaceCategory } from '../lib/category-map';
|
||||
|
||||
/** Normalized result returned to the client */
|
||||
export interface GeocodingResult {
|
||||
|
|
@ -29,12 +29,10 @@ export interface GeocodingResult {
|
|||
state?: string;
|
||||
country?: string;
|
||||
};
|
||||
/** Our Places category, derived from OSM tags */
|
||||
/** Our Places category, derived from Pelias taxonomy */
|
||||
category: PlaceCategory;
|
||||
/** Raw OSM category key (e.g. "amenity") */
|
||||
osmCategory?: string;
|
||||
/** Raw OSM type value (e.g. "restaurant") */
|
||||
osmType?: string;
|
||||
/** Raw Pelias categories (food, retail, transport, …) */
|
||||
peliasCategories?: string[];
|
||||
/** Pelias confidence score 0-1 */
|
||||
confidence: number;
|
||||
}
|
||||
|
|
@ -174,12 +172,7 @@ interface PeliasFeature {
|
|||
locality?: string;
|
||||
region?: string;
|
||||
country?: string;
|
||||
addendum?: {
|
||||
osm?: {
|
||||
category?: string;
|
||||
type?: string;
|
||||
};
|
||||
};
|
||||
category?: string[];
|
||||
};
|
||||
}
|
||||
|
||||
|
|
@ -187,9 +180,6 @@ function normalizePeliasFeature(feature: PeliasFeature): GeocodingResult {
|
|||
const props = feature.properties;
|
||||
const [lon, lat] = feature.geometry.coordinates;
|
||||
|
||||
const osmCategory = props.addendum?.osm?.category;
|
||||
const osmType = props.addendum?.osm?.type;
|
||||
|
||||
return {
|
||||
label: props.label || props.name || '',
|
||||
name: props.name || '',
|
||||
|
|
@ -203,9 +193,8 @@ function normalizePeliasFeature(feature: PeliasFeature): GeocodingResult {
|
|||
state: props.region,
|
||||
country: props.country,
|
||||
},
|
||||
category: mapOsmToPlaceCategory(osmCategory, osmType, props.layer),
|
||||
osmCategory,
|
||||
osmType,
|
||||
category: mapPeliasToPlaceCategory(props.category, props.layer),
|
||||
peliasCategories: props.category,
|
||||
confidence: props.confidence ?? 0,
|
||||
};
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue