@finbheara/domain 0.9.0 → 0.10.0

package/dist/chunks/{place-h7tvdfyp.js → place-tv86hmps.js}

@@ -199,14 +199,16 @@ var PLACE_NODES = [
     geo: "USA",
     admin: "IDTANA",
     prints: [
+      "idtama",
       "lar mheiricea",
       "mid america",
       "mid america region",
       "mid america region usa",
+      "mid american region",
       "reigiun lar meiricea",
       "usa mid america region"
     ],
-    codes: ["MAO"],
+    codes: ["IDTAMA", "MAO"],
     truncations: ["mid am"],
     oireachtas: "MAO"
   },
@@ -243,6 +245,7 @@ var PLACE_NODES = [
     geo: "USA",
     admin: "IDTANA",
     prints: [
+      "idtana sr",
       "reigiun an deiscirt",
       "s usa",
       "so usa",
@@ -4994,6 +4997,15 @@ var PLACE_NODES = [
     prints: ["essex"],
     codes: []
   },
+  {
+    id: "GBR-ENG/surrey",
+    kind: "city",
+    name: "Surrey",
+    geo: "GBR-ENG",
+    admin: "ENG_SOUTH",
+    prints: ["surrey"],
+    codes: []
+  },
   {
     id: "GBR-ENG/leeds",
     kind: "city",
@@ -6800,7 +6812,7 @@ function createPlaceReader2(options = {}) {
     return s.normalize("NFD").replace(/\p{M}+/gu, "").toLowerCase().replace(/[^\p{L}\p{N}]+/gu, " ").trim();
   }
   function repair(print) {
-    const s = print.normalize("NFC").replace(/\s+/g, " ").trim();
+    const s = print.normalize("NFC").replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(/\s+/g, " ").trim();
     const opens = (s.match(/[([{]/g) ?? []).length;
     const closes = (s.match(/[)\]}]/g) ?? []).length;
     if (opens === closes)
@@ -7407,6 +7419,41 @@ function createPlaceReader2(options = {}) {
     const found = (idx().byRunPrint.get(fold(piece)) ?? []).filter((n) => subs.some((s) => n.id !== s.id && isAncestor(s, n)));
     return found.length === 1 ? found[0] : undefined;
   }
+  function continentOf(n) {
+    const seen = new Set;
+    for (let at = n;at !== undefined && !seen.has(at.id); ) {
+      if (at.kind === "continent")
+        return at;
+      seen.add(at.id);
+      at = at.geo === null ? undefined : idx().byId.get(at.geo);
+    }
+    return;
+  }
+  const POSTAL_COUNTRIES = new Set(["USA", "CAN"]);
+  function qualifierAlone(left, right) {
+    if (left.length === 0 || right.length === 0)
+      return;
+    if (left.some((l) => right.some((r) => relates(l, r))))
+      return;
+    const postal = right.filter((r) => r.kind === "subdivision" && POSTAL_COUNTRIES.has(countryOf(r)?.id ?? ""));
+    if (postal.length > 0) {
+      const theirs = new Set(postal.map((r) => countryOf(r)?.id));
+      const fits = left.every((l) => l.kind === "city" || (l.kind === "country" || l.kind === "subdivision") && !theirs.has(countryOf(l)?.id));
+      return fits ? postal : undefined;
+    }
+    if (!right.every((r) => r.kind === "country" || r.kind === "subdivision"))
+      return;
+    const continents = new Set(right.map((r) => continentOf(r)?.id));
+    if (continents.has(undefined))
+      return;
+    const abroad = left.every((l) => {
+      if (l.kind !== "city")
+        return false;
+      const c = continentOf(l)?.id;
+      return c !== undefined && !continents.has(c);
+    });
+    return abroad ? right : undefined;
+  }
   function read(print, declared = false, smushed = true) {
     const core = unbracket(repair(print));
     if (fold(core) === "")
@@ -7432,6 +7479,7 @@ function createPlaceReader2(options = {}) {
     const seen = new Set;
     for (const split of subsets) {
       const parts = [];
+      const before = [null];
       let space = tokens[0] ?? "";
       let conj = space;
       for (let i = 0;i < seps.length; i++) {
@@ -7439,6 +7487,7 @@ function createPlaceReader2(options = {}) {
         const next = tokens[i + 1] ?? "";
         if (split.includes(k)) {
           parts.push({ space, conj });
+          before.push(k);
           space = next;
           conj = next;
         } else {
@@ -7466,6 +7515,21 @@ function createPlaceReader2(options = {}) {
             refusal: null
           };
       }
+      const qualified = (k) => k === "comma" || k === "space";
+      const settled = reads.map((r, n) => {
+        const prev = reads[n - 1];
+        if (prev === undefined || !qualified(before[n]) || r.truncated)
+          return;
+        if (n - 1 > 0 && (qualified(before[n - 1]) || !qualified(before[n - 2])))
+          return;
+        return qualifierAlone(prev.heads, r.heads);
+      });
+      settled.forEach((heads, n) => {
+        if (heads === undefined)
+          return;
+        reads[n - 1] = { ...reads[n - 1], heads };
+        reads[n] = { ...reads[n], heads };
+      });
       if (reads.some((r) => r.heads.length === 0 || r.refusal !== null))
         continue;
       const together = combine(reads);

package/dist/place.js

@@ -15,7 +15,7 @@ import {
   placesRelation2,
   probablySamePlace2,
   sameReading2
-} from "./chunks/place-h7tvdfyp.js";
+} from "./chunks/place-tv86hmps.js";
 export {
   DEFAULT_PLACE_CAPACITY2 as DEFAULT_PLACE_CAPACITY,
   DEFAULT_PLACE_READER2 as DEFAULT_PLACE_READER,

package/dist/school.js

@@ -8,12 +8,12 @@ import {
   areAllPlaceTokens2,
   placeRelation2,
   sameReading2
-} from "./chunks/place-h7tvdfyp.js";
+} from "./chunks/place-tv86hmps.js";
 import {
   validity
 } from "./chunks/place-q9kwsmzd.js";
 
-import { normalizeApostrophes } from "@finbheara/names/lexicon";
+import { normalizeApostrophes as normalizeApostrophes2 } from "@finbheara/names/lexicon";
 import { SURNAME_SEPARATOR, lexiconKey, titleCaseNamePart } from "@finbheara/names/normalize";
 import { personName } from "@finbheara/names/normalize";
 
@@ -873,6 +873,7 @@ function truncatedInstitution(tail) {
   return found;
 }
 
+import { normalizeApostrophes } from "@finbheara/names/lexicon";
 var SCHOOL_FLUFF_WORDS = new Set([
   "academy",
   "irish",
@@ -929,12 +930,11 @@ function isDiscardedAnyway(token) {
 function distinctiveTokens(tokens) {
   return tokens.filter((t) => t.length > 2 && !SCHOOL_FLUFF_WORDS.has(t));
 }
-var APOSTROPHE_VARIANTS = /['`´‘’“”’]/g;
 function foldSchoolName(raw) {
   let s = raw.toLowerCase();
   s = s.normalize("NFD").replace(/[̀-ͯ]/g, "");
   s = s.replace(/ß/g, "ss").replace(/æ/g, "ae").replace(/œ/g, "oe").replace(/ø/g, "o");
-  s = s.replace(APOSTROPHE_VARIANTS, "'");
+  s = normalizeApostrophes(s);
   s = s.replace(/'/g, "");
   const words = [];
   for (const word of s.split(/[^a-z0-9]+/)) {
@@ -1057,7 +1057,7 @@ function createSchoolNameReader(options = {}) {
     return print.replace(SPACING_ACUTE_AFTER_VOWEL, "$1́").replace(SPACING_ACUTE, "'");
   }
   function renderSn1(print) {
-    return normalizeApostrophes(readSpacingAcute(repairMojibake(print)).normalize("NFKC")).replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(/\s+/gu, " ").trim();
+    return normalizeApostrophes2(readSpacingAcute(repairMojibake(print)).normalize("NFKC")).replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(/\s+/gu, " ").trim();
   }
   const COMPOUND_OPENERS = new Set([
     "hyphen",

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@finbheara/domain",
-	"version": "0.9.0",
+	"version": "0.10.0",
 	"description": "Places, CLRG regions, school names, ages and dances as they are printed: read, compared and told apart",
 	"keywords": [
 		"places",