pelias-openstreetmap 8.4.2 → 8.5.2

package/.github/workflows/_test.yml

@@ -7,7 +7,7 @@ jobs:
       matrix:
         os:
           - ubuntu-24.04
-        node-version: [ 20.x, 22.x, 24.x ]
+        node-version: [ 20.x, 22.x, 24.x, 26.x ]
     steps:
       - uses: actions/checkout@v6
       - name: 'Install node.js ${{ matrix.node-version }}'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pelias-openstreetmap",
-  "version": "8.4.2",
+  "version": "8.5.2",
   "engines": {
     "node": ">=10.0.0"
   },
@@ -14,6 +14,7 @@
     "coverage": "node_modules/.bin/istanbul cover test/run.js",
     "end-to-end": "export NODE_ENV=test && node test/end-to-end.js;",
     "lint": "jshint .",
+    "languages": "node scripts/generate_languages.js",
     "start": "./bin/start",
     "taginfo": "node scripts/generate_taginfo.js",
     "prepublishOnly": "npm run taginfo",
@@ -49,7 +50,7 @@
     "pelias-dbclient": "^3.1.0",
     "pelias-logger": "^1.6.0",
     "pelias-model": "^10.6.0",
-    "pelias-wof-admin-lookup": "^7.17.0",
+    "pelias-wof-admin-lookup": "^7.19.0",
     "through2": "^3.0.0",
     "through2-sink": "^1.0.0"
   },

package/scripts/generate_languages.js

@@ -0,0 +1,43 @@
+#!/usr/bin/env node
+'use strict';
+
+/**
+ * Generates scripts/languages.json: a snapshot of the ISO-639-1 codes we accept
+ * as name:<lang> suffixes, mapped to their English language names.
+ *
+ * The snapshot exists so generate_taginfo.js can run with no node_modules — the
+ * npm-publish CI job runs semantic-release without an `npm install`, and both
+ * iso-639-3 and config/localized_name_keys (which needs lodash) are unavailable there.
+ *
+ * Run after upgrading iso-639-3; test/scripts/languages.js fails if it drifts.
+ */
+
+const fs      = require('fs');
+const path    = require('path');
+const iso6393 = require('iso-639-3');
+
+const localizedKeys = require('../config/localized_name_keys');
+
+function build() {
+  const names = iso6393.reduce((acc, lang) => {
+    if (lang.iso6391) {
+      // iso-639-3 qualifies some names, eg 'Occitan (post 1500)', 'Malay (macrolanguage)'
+      acc[lang.iso6391] = lang.name.replace(/\s*\(.*\)\s*$/, '');
+    }
+    return acc;
+  }, {});
+
+  return localizedKeys.reduce((acc, code) => {
+    acc[code] = names[code] || code;
+    return acc;
+  }, {});
+}
+
+const outPath = path.join(__dirname, 'languages.json');
+
+if (require.main === module) {
+  fs.writeFileSync(outPath, JSON.stringify(build(), null, 2) + '\n');
+  console.log(`languages.json written (${Object.keys(build()).length} languages)`);
+}
+
+module.exports = build;

package/scripts/generate_taginfo.js

@@ -8,12 +8,15 @@
  *   - config/features.js          (venue detection tags, address filter keys)
  *   - config/addendum_whitelist.js (metadata tags stored in the OSM addendum)
  *   - schema/name_osm.js           (name/alias tags)
+ *   - scripts/languages.json      (name:<lang> codes, snapshot of localized_name_keys)
  *   - schema/address_*.js          (address tags)
  *
  * Published to npm and served by jsDelivr:
  *   https://cdn.jsdelivr.net/npm/pelias-openstreetmap/taginfo.json
  */
 
+// note: this script runs during `npm publish` in a checkout with no node_modules,
+// so it must only require core modules and local files (see scripts/languages.json)
 const fs   = require('fs');
 const path = require('path');
 
@@ -25,6 +28,7 @@ const osmAddr      = require('../schema/address_osm');
 const tiger        = require('../schema/address_tiger');
 const naptan       = require('../schema/address_naptan');
 const addendumKeys = require('../config/addendum_whitelist');
+const languages    = require('./languages.json');
 
 const OBJECT_TYPES = ['node', 'way', 'relation'];
 
@@ -97,7 +101,7 @@ const addressTags = [...addressKeys].map(k =>
 
 // ---------------------------------------------------------------------------
 // Name tags — derived from schema/name_osm.js
-// Localized name tags (name:en, name:fr, …) are read dynamically via iso-639-3
+// Localized name tags (name:en, name:fr, …) come from scripts/languages.json
 // ---------------------------------------------------------------------------
 const nameDescriptions = {
   name:       'Primary display name; the main search term for a record',
@@ -106,12 +110,18 @@ const nameDescriptions = {
   short_name: 'Short name; indexed as an alias',
 };
 
+// taginfo has no wildcard syntax — 'name:*' would be read as a literal asterisk —
+// so every localized key we accept is listed individually. scripts/languages.json is
+// a snapshot of config/localized_name_keys; a unit test fails if the two diverge.
+const localizedNameTags = Object.keys(languages).map(code =>
+  entry(`name:${code}`, `Name in ${languages[code]}, indexed as a localized alias`)
+);
+
 const nameTags = [
   ...Object.keys(nameSchema).map(k =>
     entry(k, nameDescriptions[k] || 'Name variant indexed as an alias')
   ),
-  // Localised names are resolved at import time from iso-639-3 (e.g. name:en, name:fr)
-  entry('name:*', 'Language-specific names (e.g. name:en, name:fr) are indexed as localized aliases'),
+  ...localizedNameTags,
 ];
 
 // ---------------------------------------------------------------------------

package/scripts/languages.json

@@ -0,0 +1,186 @@
+{
+  "aa": "Afar",
+  "ab": "Abkhazian",
+  "af": "Afrikaans",
+  "ak": "Akan",
+  "am": "Amharic",
+  "ar": "Arabic",
+  "an": "Aragonese",
+  "as": "Assamese",
+  "av": "Avaric",
+  "ae": "Avestan",
+  "ay": "Aymara",
+  "az": "Azerbaijani",
+  "ba": "Bashkir",
+  "bm": "Bambara",
+  "be": "Belarusian",
+  "bn": "Bengali",
+  "bi": "Bislama",
+  "bo": "Tibetan",
+  "bs": "Bosnian",
+  "br": "Breton",
+  "bg": "Bulgarian",
+  "ca": "Catalan",
+  "cs": "Czech",
+  "ch": "Chamorro",
+  "ce": "Chechen",
+  "cu": "Church Slavic",
+  "cv": "Chuvash",
+  "kw": "Cornish",
+  "co": "Corsican",
+  "cr": "Cree",
+  "cy": "Welsh",
+  "da": "Danish",
+  "de": "German",
+  "dv": "Dhivehi",
+  "dz": "Dzongkha",
+  "el": "Modern Greek",
+  "en": "English",
+  "eo": "Esperanto",
+  "et": "Estonian",
+  "eu": "Basque",
+  "ee": "Ewe",
+  "fo": "Faroese",
+  "fa": "Persian",
+  "fj": "Fijian",
+  "fi": "Finnish",
+  "fr": "French",
+  "fy": "Western Frisian",
+  "ff": "Fulah",
+  "gd": "Scottish Gaelic",
+  "ga": "Irish",
+  "gl": "Galician",
+  "gv": "Manx",
+  "gn": "Guarani",
+  "gu": "Gujarati",
+  "ht": "Haitian",
+  "ha": "Hausa",
+  "sh": "Serbo-Croatian",
+  "he": "Hebrew",
+  "hz": "Herero",
+  "hi": "Hindi",
+  "ho": "Hiri Motu",
+  "hr": "Croatian",
+  "hu": "Hungarian",
+  "hy": "Armenian",
+  "ig": "Igbo",
+  "io": "Ido",
+  "ii": "Sichuan Yi",
+  "iu": "Inuktitut",
+  "ie": "Interlingue",
+  "ia": "Interlingua",
+  "id": "Indonesian",
+  "ik": "Inupiaq",
+  "is": "Icelandic",
+  "it": "Italian",
+  "jv": "Javanese",
+  "ja": "Japanese",
+  "kl": "Kalaallisut",
+  "kn": "Kannada",
+  "ks": "Kashmiri",
+  "ka": "Georgian",
+  "kr": "Kanuri",
+  "kk": "Kazakh",
+  "km": "Khmer",
+  "ki": "Kikuyu",
+  "rw": "Kinyarwanda",
+  "ky": "Kirghiz",
+  "kv": "Komi",
+  "kg": "Kongo",
+  "ko": "Korean",
+  "kj": "Kuanyama",
+  "ku": "Kurdish",
+  "lo": "Lao",
+  "la": "Latin",
+  "lv": "Latvian",
+  "li": "Limburgan",
+  "ln": "Lingala",
+  "lt": "Lithuanian",
+  "lb": "Luxembourgish",
+  "lu": "Luba-Katanga",
+  "lg": "Ganda",
+  "mh": "Marshallese",
+  "ml": "Malayalam",
+  "mr": "Marathi",
+  "mk": "Macedonian",
+  "mg": "Malagasy",
+  "mt": "Maltese",
+  "mn": "Mongolian",
+  "mi": "Maori",
+  "ms": "Malay",
+  "my": "Burmese",
+  "na": "Nauru",
+  "nv": "Navajo",
+  "nr": "South Ndebele",
+  "nd": "North Ndebele",
+  "ng": "Ndonga",
+  "ne": "Nepali",
+  "nl": "Dutch",
+  "nn": "Norwegian Nynorsk",
+  "nb": "Norwegian Bokmål",
+  "no": "Norwegian",
+  "ny": "Nyanja",
+  "oc": "Occitan",
+  "oj": "Ojibwa",
+  "or": "Oriya",
+  "om": "Oromo",
+  "os": "Ossetian",
+  "pa": "Panjabi",
+  "pi": "Pali",
+  "pl": "Polish",
+  "pt": "Portuguese",
+  "ps": "Pushto",
+  "qu": "Quechua",
+  "rm": "Romansh",
+  "ro": "Romanian",
+  "rn": "Rundi",
+  "ru": "Russian",
+  "sg": "Sango",
+  "sa": "Sanskrit",
+  "si": "Sinhala",
+  "sk": "Slovak",
+  "sl": "Slovenian",
+  "se": "Northern Sami",
+  "sm": "Samoan",
+  "sn": "Shona",
+  "sd": "Sindhi",
+  "so": "Somali",
+  "st": "Southern Sotho",
+  "es": "Spanish",
+  "sq": "Albanian",
+  "sc": "Sardinian",
+  "sr": "Serbian",
+  "ss": "Swati",
+  "su": "Sundanese",
+  "sw": "Swahili",
+  "sv": "Swedish",
+  "ty": "Tahitian",
+  "ta": "Tamil",
+  "tt": "Tatar",
+  "te": "Telugu",
+  "tg": "Tajik",
+  "tl": "Tagalog",
+  "th": "Thai",
+  "ti": "Tigrinya",
+  "to": "Tonga",
+  "tn": "Tswana",
+  "ts": "Tsonga",
+  "tk": "Turkmen",
+  "tr": "Turkish",
+  "tw": "Twi",
+  "ug": "Uighur",
+  "uk": "Ukrainian",
+  "ur": "Urdu",
+  "uz": "Uzbek",
+  "ve": "Venda",
+  "vi": "Vietnamese",
+  "vo": "Volapük",
+  "wa": "Walloon",
+  "wo": "Wolof",
+  "xh": "Xhosa",
+  "yi": "Yiddish",
+  "yo": "Yoruba",
+  "za": "Zhuang",
+  "zh": "Chinese",
+  "zu": "Zulu"
+}