@finbheara/domain 0.58.0 → 0.59.0

package/dist/age.js

@@ -40,7 +40,7 @@ import {
   youngFloor2,
   tooYoungForMajor2,
   tooYoungForFeis2
-} from "./chunks/place-w6d4xfzc.js";
+} from "./chunks/place-mbtx4htf.js";
 export {
   ADULT_FLOOR2 as ADULT_FLOOR,
   AVERAGE_AGE_DECIMALS2 as AVERAGE_AGE_DECIMALS,

package/dist/chunks/{place-dn6qk21g.js → place-00sx835a.js}

@@ -1,7 +1,7 @@
 import {
   Age2,
   ageRelation2
-} from "./place-w6d4xfzc.js";
+} from "./place-mbtx4htf.js";
 import {
   validity
 } from "./place-q9kwsmzd.js";

package/dist/chunks/{place-w6d4xfzc.js → place-mbtx4htf.js}

@@ -44,6 +44,7 @@ var AND_UNDER_RANGE = /(?<![a-z0-9])(\d{1,2})\s*(?:&|\band\b)\s*under\s*(\d{1,2}
 var AND_RANGE = /(?<![a-z0-9])(?<!\b(?:under|und|over|faoi|cionn|u|o)\.?\s*)(?<!\d\s*,\s*)(?<!\(\s*)(\d{1,2})\s*(?:&|\band\b)\s*(\d{1,2})(?![a-z0-9])(?!\s*-?\s*hand)(?!\s*(?:&|\+|\/|,|\)|\band\b|\bor\b))/i;
 var SLASH_RANGE = /(?<![a-z0-9/])(\d{1,2})\s*\/\s*(\d{1,2})(?=\s*(?:years?|yrs?|boys?|girls?|ladies|men)\b)/i;
 var AGE_N = /(?<!\b(?:under|over)\s*)\bage\s*(\d{1,2})(?![a-z0-9])(?!\s*-?\s*hand)/i;
+var AGE_RANGE = /(?<!\b(?:under|over)\s*)\bage\s*(\d{1,2})\s+(\d{1,2})(?![a-z0-9])(?!\s*-?\s*hand)/i;
 var YEARS = /(?<![a-z0-9])(?<!\d\s*(?:&|\/|\band\b|[-\u0096–—]|\bto\b)\s*)(\d{1,2})\s*(?:years?|yrs?)(?![a-z0-9])(?!\s*(?:&|\+|\/|\band\b|\bor\b|old))/i;
 var RANGE_DASH = String.raw`(?:\u00c2?[-\u0096–—]|\bto\b)`;
 var RANGE = new RegExp(String.raw`(?<![0-9])(?<![0-9][a-z]*)(?<!(?:^|[^a-z0-9])[a-z])(?:u\s*)?(\d{1,2})\s*${RANGE_DASH}\s*(\d{1,2})(?![a-z0-9])`, "i");
@@ -126,6 +127,9 @@ function readAnchored(title, s, offset, adultWord, aside = false) {
   const r = RANGE.exec(stripped);
   if (r?.[1] !== undefined && r[2] !== undefined && inFence(r[1], r[2]))
     return at(title, offset + shift, r.index, r.index + r[0].length, `${Number(r[1])}-${Number(r[2])}`);
+  const ar = AGE_RANGE.exec(s);
+  if (ar?.[1] !== undefined && ar[2] !== undefined && inFence(ar[1], ar[2]))
+    return at(title, offset, ar.index, ar.index + ar[0].length, `${Number(ar[1])}-${Number(ar[2])}`);
   const au = AND_UNDER.exec(s);
   if (au?.[1] !== undefined)
     return at(title, offset, au.index, au.index + au[0].length, `u${Number(au[1]) + 1}`);

package/dist/code.js

@@ -1,10 +1,10 @@
 import {
   Age2
-} from "./chunks/place-w6d4xfzc.js";
+} from "./chunks/place-mbtx4htf.js";
 import {
   populationIn2,
   compTitle2
-} from "./chunks/place-dn6qk21g.js";
+} from "./chunks/place-00sx835a.js";
 import {
   validity
 } from "./chunks/place-q9kwsmzd.js";

package/dist/schedule.js

@@ -1,8 +1,8 @@
-import"./chunks/place-w6d4xfzc.js";
+import"./chunks/place-mbtx4htf.js";
 import {
   compTitle2,
   matchTitle2
-} from "./chunks/place-dn6qk21g.js";
+} from "./chunks/place-00sx835a.js";
 
 function hallKey(hall) {
   return hall.normalize("NFKD").replace(/\p{M}/gu, "").toLowerCase().replace(/[^a-z0-9]+/g, " ").trim();

package/dist/school.js

@@ -999,6 +999,48 @@ var MATCH_KEY_INSTITUTION_WORDS = [
 ].sort();
 
 import { normalizeApostrophes } from "@finbheara/names/lexicon";
+
+var CP1252_HIGH = "€‚ƒ„…†‡ˆ‰Š‹Œ" + "Ž‘’“”•–—˜™š›" + "œžŸ";
+var BYTE_OF_CP1252 = new Map([...CP1252_HIGH].map((ch, i) => [ch.codePointAt(0), 128 + i]));
+var MOJIBAKE = /[Â-ßà-ï][€-¿‚-›ŒŠŽ]/u;
+var MOJIBAKE_ALL = new RegExp(MOJIBAKE.source, "gu");
+var FLATTENED_NBSP = /(?<=\S)[Â-Å] /u;
+function isNbspLead(code) {
+  return code >= 194 && code <= 197;
+}
+var NON_LATIN_LETTER = /(?!\p{Script=Latin})\p{L}/u;
+function isRepair(before, after) {
+  if (!NON_LATIN_LETTER.test(after))
+    return true;
+  return (before.match(MOJIBAKE_ALL)?.length ?? 0) >= 2;
+}
+function undoMojibake(s) {
+  const bytes = new Uint8Array(s.length);
+  for (let i = 0;i < s.length; i++) {
+    const code = s.charCodeAt(i);
+    const flattened = code === 32 && i > 1 && isNbspLead(s.charCodeAt(i - 1)) && /\S/u.test(s[i - 2]);
+    const byte = flattened ? 160 : BYTE_OF_CP1252.get(code) ?? code;
+    if (byte > 255)
+      return;
+    bytes[i] = byte;
+  }
+  try {
+    return new TextDecoder("utf-8", { fatal: true }).decode(bytes);
+  } catch {
+    return;
+  }
+}
+function repairSchoolMojibake(print) {
+  let s = print;
+  for (let round = 0;round < 3 && (MOJIBAKE.test(s) || FLATTENED_NBSP.test(s)); round++) {
+    const undone = undoMojibake(s);
+    if (undone === undefined || undone === s || !isRepair(s, undone))
+      return s;
+    s = undone;
+  }
+  return s;
+}
+
 var SCHOOL_FLUFF_WORDS = new Set([
   ...[...SCHOOL_FLUFF_VOCABULARY.values()].filter((entry) => entry.tokenFluff).map((entry) => entry.canonical),
   ...MATCH_KEY_INSTITUTION_WORDS
@@ -1039,7 +1081,7 @@ function distinctiveTokens(tokens) {
   return tokens.filter((t) => t.length > 2 && !SCHOOL_FLUFF_WORDS.has(t));
 }
 function foldSchoolName(raw) {
-  let s = raw.toLowerCase();
+  let s = repairSchoolMojibake(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 = normalizeApostrophes(s);
@@ -1124,41 +1166,6 @@ function createSchoolNameReader(options = {}) {
     ...options.garbage ?? [],
     ...options.refusals ?? NOT_A_SCHOOL
   ]);
-  const CP1252_HIGH = "€‚ƒ„…†‡ˆ‰Š‹Œ" + "Ž‘’“”•–—˜™š›" + "œžŸ";
-  const BYTE_OF_CP1252 = new Map([...CP1252_HIGH].map((ch, i) => [ch.codePointAt(0), 128 + i]));
-  const MOJIBAKE = /[Â-ßà-ï][€-¿‚-›ŒŠŽ]/u;
-  const MOJIBAKE_ALL = new RegExp(MOJIBAKE.source, "gu");
-  const NON_LATIN_LETTER = /(?!\p{Script=Latin})\p{L}/u;
-  function isRepair(before, after) {
-    if (!NON_LATIN_LETTER.test(after))
-      return true;
-    return (before.match(MOJIBAKE_ALL)?.length ?? 0) >= 2;
-  }
-  function undoMojibake(s) {
-    const bytes = new Uint8Array(s.length);
-    for (let i = 0;i < s.length; i++) {
-      const code = s.charCodeAt(i);
-      const byte = BYTE_OF_CP1252.get(code) ?? code;
-      if (byte > 255)
-        return;
-      bytes[i] = byte;
-    }
-    try {
-      return new TextDecoder("utf-8", { fatal: true }).decode(bytes);
-    } catch {
-      return;
-    }
-  }
-  function repairMojibake(print) {
-    let s = print;
-    for (let round = 0;round < 3 && MOJIBAKE.test(s); round++) {
-      const undone = undoMojibake(s);
-      if (undone === undefined || undone === s || !isRepair(s, undone))
-        return s;
-      s = undone;
-    }
-    return s;
-  }
   const SPACING_ACUTE_AFTER_VOWEL = /((?<=\p{L})[AEIOUaeiou]|[AEIUaeiu])[´ˊ](?![sS]\b)/gu;
   const SPACING_ACUTE = /[´ˊ]/gu;
   function readSpacingAcute(print) {
@@ -1166,7 +1173,7 @@ function createSchoolNameReader(options = {}) {
   }
   const INJECTED_LINK = /(?<=^|[\s([])(?:https?:\/\/|www\.)[^\s)\]]+/giu;
   function renderSn1(print) {
-    return normalizeApostrophes2(readSpacingAcute(repairMojibake(print)).normalize("NFKC")).replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(INJECTED_LINK, " ").replace(/\s+/gu, " ").trim();
+    return normalizeApostrophes2(readSpacingAcute(repairSchoolMojibake(print)).normalize("NFKC")).replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(INJECTED_LINK, " ").replace(/\s+/gu, " ").trim();
   }
   const COMPOUND_OPENERS = new Set([
     "hyphen",

package/dist/title.js

@@ -9,8 +9,8 @@ import {
   titleRelation2,
   ladderOf2,
   matchTitle2
-} from "./chunks/place-dn6qk21g.js";
-import"./chunks/place-w6d4xfzc.js";
+} from "./chunks/place-00sx835a.js";
+import"./chunks/place-mbtx4htf.js";
 export {
   codePopulation2 as codePopulation,
   compTitle2 as compTitle,

package/dist/types/school-mojibake.d.ts

@@ -0,0 +1 @@
+export declare function repairSchoolMojibake(print: string): string;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@finbheara/domain",
-	"version": "0.58.0",
+	"version": "0.59.0",
 	"description": "Places, CLRG regions and events, school names and the links between schools, ages, dances, competition titles, codes and schedules, and a person's print in its role, as they are printed: read, compared and told apart",
 	"keywords": [
 		"places",