@finbheara/domain 0.60.0 → 0.62.0

package/dist/chunks/place-1mpcshk8.js

@@ -0,0 +1,1105 @@
+import {
+  SHARED_ROW_SENTINELS2,
+  sentinelIn2
+} from "./place-tcgfvemw.js";
+
+var SCHOOL_CELL_OWN_SENTINELS2 = [
+  {
+    print: "no school",
+    authority: "`No School`: 76 school cells, the dancer entered with no school"
+  },
+  {
+    print: "independent",
+    authority: "`Independent`, `independent`, `Independent?`: 5 school cells, no school by the dancer's own description"
+  },
+  {
+    print: "independent dancer",
+    authority: "`Independent Dancer`, `Independent dancer`, `Independent Dancer?`: 8 school cells"
+  },
+  {
+    print: "non dancing",
+    authority: "`Non-dancing`: 107 school cells, an entry form's option for a non-dancer"
+  },
+  {
+    print: "school not selected",
+    match: "prefix",
+    authority: "`SCHOOL NOT SELECTED - update your ... profile`: 45 school cells, an entry form's instruction"
+  },
+  {
+    print: "choose one",
+    authority: "`-- Choose One --`: 41 school cells, an entry form's unchosen option"
+  },
+  {
+    print: "no school selected",
+    match: "prefix",
+    authority: "`NO SCHOOL SELECTED - Please change your profile`: 16 school cells, an entry form's instruction"
+  },
+  {
+    print: "no school associations",
+    authority: "`No School Associations`: 13 school cells"
+  },
+  { print: "no lessons yet", authority: "`No lessons yet`: 5 school cells" },
+  { print: "non dancer", authority: "`Non-dancer`: 4 school cells" },
+  { print: "non dance competitions", authority: "`Non-Dance Competitions`: 3 school cells" },
+  {
+    print: "not listed",
+    match: "prefix",
+    authority: "`--Not Listed--`: 2 school cells, an entry form's option"
+  },
+  { print: "other", authority: "`Other`: 2 school cells, an entry form's option" },
+  { print: "not certified", authority: "`Not Certified`: 1 school cell" },
+  { print: "n e e d", authority: "`(n e e d ) ____`: 1 school cell, keyboard filler" },
+  { print: "none", authority: "`None`: 1 school cell" },
+  {
+    print: "unknown irish dancing school",
+    authority: "`Unknown Irish Dancing School`: 1 school cell"
+  },
+  { print: "none inactive dancer", authority: "`None - Inactive Dancer`: 1 school cell" },
+  {
+    print: "school hidden",
+    authority: "`(School Hidden)`: 1,221 school cells of 8 registrant lists, the entry platform's print for a competitor who asked not to be published"
+  },
+  { print: "not applicable", authority: "`Not applicable`: a school print, no school entered" },
+  {
+    print: "no school judge",
+    authority: "`No School - Judge`: an entry form's option for an adjudicator"
+  },
+  { print: "no dance school", authority: "`No Dance School`: an entry form's option" },
+  { print: "unknown music school", authority: "`Unknown Music School`: an entry form's option" },
+  { print: "school deleted", authority: "`---SCHOOL DELETED`: an entry form's option" },
+  { print: "select school", authority: "`--Select School--`: an entry form's unchosen option" },
+  { print: "school other", authority: "`School Other`: an entry form's option" },
+  { print: "non", authority: "`Non`: an entry form's option, the truncation of `Non-dancer`" },
+  {
+    print: "x closed select new school",
+    authority: "`X - CLOSED - Select New School`: an entry form's option for a closed school"
+  },
+  {
+    print: "x school closed please select another school",
+    authority: "`X -SCHOOL CLOSED - Please select another school`: an entry form's option"
+  },
+  { print: "default school", authority: "`Default School`: an entry form's default" },
+  {
+    print: "my school of irish dance",
+    authority: "`My School of Irish Dance`: an entry form's example text"
+  }
+];
+var SCHOOL_CELL_SENTINELS2 = [
+  ...SHARED_ROW_SENTINELS2,
+  ...SCHOOL_CELL_OWN_SENTINELS2
+];
+var schoolCellSentinelOf2 = sentinelIn2(SCHOOL_CELL_SENTINELS2);
+
+var SCHOOL_NAME_EXCEPTIONS2 = [
+  {
+    phrase: "the academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "theacademy"
+  },
+  {
+    phrase: "the academy irish dance co",
+    scope: "label",
+    as: "NAME_PART",
+    token: "theacademy"
+  },
+  {
+    phrase: "rhythm of ireland",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "rhythmofireland"
+  },
+  {
+    phrase: "irish dance center",
+    scope: "label",
+    as: "NAME_PART",
+    token: "irishdancecenter"
+  },
+  {
+    phrase: "the irish dance center",
+    scope: "label",
+    as: "NAME_PART",
+    token: "irishdancecenter"
+  },
+  {
+    phrase: "the irish dance academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "theirishdanceacademy"
+  },
+  {
+    phrase: "irish dance academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "theirishdanceacademy"
+  },
+  {
+    phrase: "the irish dance company",
+    scope: "label",
+    as: "NAME_PART",
+    token: "theirishdancecompany"
+  },
+  {
+    phrase: "gra na rince",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "granarince"
+  },
+  {
+    phrase: "clann na cara",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "clannnacara"
+  },
+  {
+    phrase: "rince academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "rinceacademy"
+  },
+  {
+    phrase: "i d a s",
+    scope: "label",
+    as: "NAME_PART",
+    token: "idas"
+  },
+  {
+    phrase: "ml dance academy",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "mldanceacademy"
+  },
+  {
+    phrase: "cm dance",
+    scope: "label",
+    as: "NAME_PART",
+    token: "cmdance"
+  },
+  {
+    phrase: "traditional irish dance academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "traditionalirishdanceacademy"
+  },
+  {
+    phrase: "irish dance centre",
+    scope: "label",
+    as: "NAME_PART",
+    token: "irishdancecenter"
+  },
+  {
+    phrase: "tj academy",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "tjacademy"
+  },
+  {
+    phrase: "m d l academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "mdlacademy"
+  },
+  {
+    phrase: "wa academy",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "waacademy"
+  },
+  {
+    phrase: "fd academy",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "fdacademy"
+  },
+  {
+    phrase: "em academy",
+    scope: "label",
+    as: "NAME_PART",
+    token: "emacademy"
+  },
+  {
+    phrase: "aoibhneas an rince",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "aoibhneasanrince"
+  },
+  {
+    phrase: "an rince mor",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "anrincemor"
+  },
+  {
+    phrase: "clan rince",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "clanrince"
+  },
+  {
+    phrase: "acadamh rince",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "acadamhrince"
+  },
+  {
+    phrase: "spreagadh na rince",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "spreagadhnarince"
+  },
+  {
+    phrase: "clann na rince",
+    scope: "label",
+    as: "NAME_PART",
+    token: "clannnarince"
+  },
+  {
+    phrase: "mise eire",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "miseeire"
+  },
+  {
+    phrase: "reel eire",
+    scope: "phrase",
+    as: "NAME_PART",
+    token: "reeleire"
+  }
+];
+var EXCEPTIONS_BY_LENGTH = [
+  ...SCHOOL_NAME_EXCEPTIONS2
+].sort((a, b) => b.phrase.length - a.phrase.length);
+var NOT_A_SCHOOL2 = [
+  {
+    pattern: "north west regional council",
+    kind: "exact",
+    reason: "organization"
+  },
+  {
+    pattern: "^#\\s*\\d+$",
+    kind: "regex",
+    reason: "placeholder"
+  },
+  {
+    pattern: "cce other",
+    kind: "exact",
+    reason: "placeholder"
+  },
+  {
+    pattern: "^x{4,}$",
+    kind: "regex",
+    reason: "placeholder"
+  },
+  {
+    pattern: "^.+['’]s team$",
+    kind: "regex",
+    reason: "not-a-name"
+  },
+  {
+    pattern: "^\\d+(st|nd|rd|th) team up$",
+    kind: "regex",
+    reason: "not-a-name"
+  },
+  {
+    pattern: "^[abc] team$",
+    kind: "regex",
+    reason: "not-a-name"
+  },
+  {
+    pattern: "^[^\\p{L}]*$",
+    kind: "regex",
+    reason: "not-a-name"
+  }
+];
+var INVISIBLE = /[​‌‍ ]/g;
+var COMBINING = /[̀-ͯ]/g;
+function normalizeForRefusal(print) {
+  return print.replace(INVISIBLE, " ").normalize("NFD").replace(COMBINING, "").toLowerCase().replace(/\s+/g, " ").trim();
+}
+var PLACEHOLDER_ROWS = new Map;
+function placeholderRow(p) {
+  let row = PLACEHOLDER_ROWS.get(p);
+  if (row === undefined)
+    PLACEHOLDER_ROWS.set(p, row = { pattern: p.print, kind: p.match ?? "exact", reason: "placeholder" });
+  return row;
+}
+function notASchoolIn2(rows) {
+  const regexes = new Map(rows.filter((row) => row.kind === "regex").map((row) => [row, new RegExp(row.pattern, "iu")]));
+  return (print) => {
+    const text = normalizeForRefusal(print);
+    if (text === "")
+      return;
+    const placeholder = schoolCellSentinelOf2(text);
+    if (placeholder !== undefined)
+      return placeholderRow(placeholder);
+    for (const row of rows) {
+      if (row.kind === "exact" && text === row.pattern)
+        return row;
+      if (row.kind === "prefix" && text.startsWith(row.pattern))
+        return row;
+      if (row.kind === "regex" && regexes.get(row)?.test(text))
+        return row;
+    }
+    return;
+  };
+}
+function exceptionsByLength(rows) {
+  return [...rows].sort((a, b) => b.phrase.length - a.phrase.length);
+}
+
+var SCHOOL_FLUFF_VOCABULARY = new Map([
+  [
+    "irish",
+    {
+      canonical: "irish",
+      kind: "word",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: true
+    }
+  ],
+  [
+    "dance",
+    {
+      canonical: "dance",
+      kind: "word",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: true
+    }
+  ],
+  [
+    "dancing",
+    {
+      canonical: "dancing",
+      kind: "word",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: true
+    }
+  ],
+  [
+    "dancers",
+    {
+      canonical: "dancers",
+      kind: "word",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: true
+    }
+  ],
+  [
+    "traditional",
+    {
+      canonical: "traditional",
+      kind: "word",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: true
+    }
+  ],
+  [
+    "the",
+    {
+      canonical: "the",
+      kind: "word",
+      lowerInside: true,
+      descriptor: true,
+      truncatable: false,
+      tokenFluff: true
+    }
+  ],
+  [
+    "of",
+    {
+      canonical: "of",
+      kind: "word",
+      lowerInside: true,
+      descriptor: true,
+      truncatable: false,
+      tokenFluff: true
+    }
+  ],
+  [
+    "and",
+    {
+      canonical: "and",
+      kind: "word",
+      lowerInside: true,
+      descriptor: true,
+      truncatable: false,
+      tokenFluff: true
+    }
+  ],
+  [
+    "na",
+    {
+      canonical: "na",
+      kind: "word",
+      lowerInside: true,
+      descriptor: false,
+      truncatable: false,
+      tokenFluff: true
+    }
+  ],
+  [
+    "an",
+    {
+      canonical: "an",
+      kind: "word",
+      lowerInside: true,
+      descriptor: false,
+      truncatable: false,
+      tokenFluff: true
+    }
+  ],
+  [
+    "a",
+    {
+      canonical: "a",
+      kind: "word",
+      lowerInside: true,
+      descriptor: false,
+      truncatable: false,
+      tokenFluff: false
+    }
+  ],
+  [
+    "do",
+    {
+      canonical: "do",
+      kind: "word",
+      lowerInside: true,
+      descriptor: false,
+      truncatable: false,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish dance",
+    {
+      canonical: "irish dance",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish dancing",
+    {
+      canonical: "irish dancing",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "of irish dance",
+    {
+      canonical: "of irish dance",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "of irish dancing",
+    {
+      canonical: "of irish dancing",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "school of irish dance",
+    {
+      canonical: "school of irish dance",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "school of irish dancing",
+    {
+      canonical: "school of irish dancing",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "school of dance",
+    {
+      canonical: "school of dance",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "school of dancing",
+    {
+      canonical: "school of dancing",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish dance school",
+    {
+      canonical: "irish dance school",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish dancing school",
+    {
+      canonical: "irish dancing school",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish dance academy",
+    {
+      canonical: "irish dance academy",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "dance academy",
+    {
+      canonical: "dance academy",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish step dance",
+    {
+      canonical: "irish step dance",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ],
+  [
+    "irish step dancing",
+    {
+      canonical: "irish step dancing",
+      kind: "phrase",
+      lowerInside: false,
+      descriptor: true,
+      truncatable: true,
+      tokenFluff: false
+    }
+  ]
+]);
+function schoolFluff(text) {
+  return SCHOOL_FLUFF_VOCABULARY.get(text.toLocaleLowerCase());
+}
+function isFluffWord2(token) {
+  return schoolFluff(token)?.kind === "word";
+}
+var TRUNCATABLE_FLUFF_WORDS = [...SCHOOL_FLUFF_VOCABULARY.values()].filter((entry) => entry.kind === "word" && entry.truncatable).map((entry) => entry.canonical);
+function isTruncatedFluff(token) {
+  const t = token.toLocaleLowerCase();
+  return t !== "" && isProperPrefixOfAny(t, TRUNCATABLE_FLUFF_WORDS);
+}
+function isProperPrefixOfAny(token, words) {
+  for (const w of words)
+    if (w.length > token.length && w.startsWith(token))
+      return true;
+  return false;
+}
+var FLUFF_PHRASES = [...SCHOOL_FLUFF_VOCABULARY.values()].filter((entry) => entry.kind === "phrase").map((entry) => entry.canonical).sort((a, b) => b.length - a.length || a.localeCompare(b));
+function isFluffPhrasePrefix(text) {
+  const t = text.toLocaleLowerCase();
+  if (t === "")
+    return false;
+  return FLUFF_PHRASES.some((phrase) => phrase.startsWith(t));
+}
+function trailingFluffRun2(tokens, distinctive) {
+  let start = tokens.length;
+  for (let i = tokens.length - 1;i >= 0; i -= 1) {
+    if (!isFluffPhrasePrefix(tokens.slice(i).join(" ")))
+      continue;
+    if (!tokens.slice(0, i).some(distinctive))
+      continue;
+    start = i;
+  }
+  while (start > 0) {
+    const token = tokens[start - 1] ?? "";
+    if (!isFluffWord2(token) && !isTruncatedFluff(token) && distinctive(token))
+      break;
+    if (!tokens.slice(0, start - 1).some(distinctive))
+      break;
+    start -= 1;
+  }
+  return start;
+}
+
+import { nameParticle } from "@finbheara/names/particles";
+var FUSED_PREFIXES = new Set(["O", "Mc", "Mac"]);
+function joinedPrefix2(printed, next) {
+  if (!/^\p{L}{2}/u.test(next))
+    return;
+  const particle = nameParticle(printed);
+  if (particle === undefined || !particle.standalone)
+    return;
+  if (!FUSED_PREFIXES.has(particle.canonical))
+    return;
+  return particle.join === "apostrophe" ? `${particle.canonical}'${next}` : `${particle.canonical}${next}`;
+}
+
+var SCHOOL_INSTITUTION_VOCABULARY = new Map([
+  [
+    "academy",
+    {
+      canonical: "academy",
+      label: "Academy",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: true,
+      matchKey: true
+    }
+  ],
+  [
+    "acadamy",
+    {
+      canonical: "academy",
+      label: "Academy",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "acadamh",
+    {
+      canonical: "academy",
+      label: "Academy",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "accademia",
+    {
+      canonical: "academy",
+      label: "Academy",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "school",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: true,
+      matchKey: true
+    }
+  ],
+  [
+    "schools",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "sd",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "s d",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "phrase",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "ecole",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "word",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "escuela",
+    {
+      canonical: "school",
+      label: "School",
+      kind: "word",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "scoil",
+    {
+      canonical: "scoilrince",
+      label: "S.R.",
+      kind: "word",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "scoil rince",
+    {
+      canonical: "scoilrince",
+      label: "S.R.",
+      kind: "phrase",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "s r",
+    {
+      canonical: "scoilrince",
+      label: "S.R.",
+      kind: "phrase",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "sr",
+    {
+      canonical: "scoilrince",
+      label: "S.R.",
+      kind: "word",
+      position: "prefix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "studio",
+    {
+      canonical: "studio",
+      label: "Studio",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "studios",
+    {
+      canonical: "studio",
+      label: "Studio",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ],
+  [
+    "company",
+    {
+      canonical: "company",
+      label: "Company",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "institute",
+    {
+      canonical: "institute",
+      label: "Institute",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "center",
+    {
+      canonical: "center",
+      label: "Center",
+      kind: "word",
+      position: "suffix",
+      truncatable: true,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "centre",
+    {
+      canonical: "center",
+      label: "Center",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: true
+    }
+  ],
+  [
+    "club",
+    {
+      canonical: "club",
+      label: "Club",
+      kind: "word",
+      position: "suffix",
+      truncatable: false,
+      glued: false,
+      matchKey: false
+    }
+  ]
+]);
+function foldText(text) {
+  return text.toLocaleLowerCase().normalize("NFD").replace(/\p{M}/gu, "").replace(/[^a-z0-9]+/g, " ").trim();
+}
+function schoolInstitution(text) {
+  return SCHOOL_INSTITUTION_VOCABULARY.get(foldText(text));
+}
+function isInstitutionWord2(text) {
+  return schoolInstitution(text) !== undefined;
+}
+function namesInstitution2(text) {
+  for (const m of text.matchAll(/[\p{L}\p{N}.'’]+/gu))
+    if (isInstitutionWord2(m[0]))
+      return true;
+  return false;
+}
+var LABEL_BY_TYPE = new Map([...SCHOOL_INSTITUTION_VOCABULARY.values()].map((v) => [v.canonical, v.label]));
+function institutionLabel(type) {
+  return LABEL_BY_TYPE.get(type);
+}
+var INSTITUTION_TYPES = [...LABEL_BY_TYPE.keys()].sort();
+var INSTITUTION_PHRASES2 = [...SCHOOL_INSTITUTION_VOCABULARY].filter(([, v]) => v.kind === "phrase").map(([k]) => k).sort();
+var GLUED_INSTITUTION_SUFFIXES2 = [...SCHOOL_INSTITUTION_VOCABULARY].filter(([, v]) => v.glued).map(([k]) => k).sort();
+function truncatedInstitution2(tail) {
+  const folded = foldText(tail);
+  if (folded === "")
+    return;
+  let found;
+  for (const [key, entry] of SCHOOL_INSTITUTION_VOCABULARY) {
+    if (!entry.truncatable)
+      continue;
+    if (key.length <= folded.length || !key.startsWith(folded))
+      continue;
+    if (found !== undefined && found.canonical !== entry.canonical)
+      return;
+    found ??= entry;
+  }
+  return found;
+}
+var MATCH_KEY_INSTITUTION_WORDS = [
+  ...new Set([...SCHOOL_INSTITUTION_VOCABULARY].filter(([, v]) => v.matchKey).flatMap(([k]) => k.split(" ")))
+].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
+]);
+var SCHOOL_GENERIC_NAME_PARTS = new Set(["celtic", "clann"]);
+function hasSpecificToken2(tokens) {
+  for (const t of tokens)
+    if (!SCHOOL_GENERIC_NAME_PARTS.has(t))
+      return true;
+  return false;
+}
+var GLUED_FLUFF_SUFFIXES = ["academy", "school"];
+function deglueToken(token) {
+  let t = token;
+  let changed = true;
+  while (changed) {
+    changed = false;
+    for (const suf of GLUED_FLUFF_SUFFIXES) {
+      if (t.length > suf.length + 2 && t.endsWith(suf)) {
+        t = t.slice(0, -suf.length);
+        changed = true;
+      }
+    }
+  }
+  return t;
+}
+function isTruncatedFluff2(token) {
+  return isProperPrefixOfAny(token, SCHOOL_FLUFF_WORDS);
+}
+function isFluffOrFragment2(token) {
+  return SCHOOL_FLUFF_WORDS.has(token) || isTruncatedFluff2(token);
+}
+function isDiscardedAnyway(token) {
+  return token.length <= 2 || SCHOOL_FLUFF_WORDS.has(token);
+}
+function distinctiveTokens(tokens) {
+  return tokens.filter((t) => t.length > 2 && !SCHOOL_FLUFF_WORDS.has(t));
+}
+function foldSchoolName2(raw) {
+  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);
+  s = s.replace(/'/g, "");
+  const words = [];
+  for (const word of s.split(/[^a-z0-9]+/)) {
+    if (word === "")
+      continue;
+    const prev = words[words.length - 1];
+    const joined = prev === undefined ? undefined : joinedPrefix2(prev, word);
+    if (joined === undefined)
+      words.push(word);
+    else
+      words[words.length - 1] = joined.toLowerCase().replace(/'/g, "");
+  }
+  return words.join(" ");
+}
+function schoolKeyTokens2(raw) {
+  const folded = foldSchoolName2(raw).split(" ").filter((t) => t !== "").map(deglueToken);
+  let end = folded.length;
+  while (end > 0) {
+    const last = folded[end - 1];
+    if (!isTruncatedFluff2(last) && !isDiscardedAnyway(last))
+      break;
+    if (!hasSpecificToken2(distinctiveTokens(folded.slice(0, end - 1))))
+      break;
+    end -= 1;
+  }
+  return [...new Set(distinctiveTokens(folded.slice(0, end)))];
+}
+
+export { SCHOOL_CELL_OWN_SENTINELS2, SCHOOL_CELL_SENTINELS2, schoolCellSentinelOf2, SCHOOL_NAME_EXCEPTIONS2, EXCEPTIONS_BY_LENGTH, NOT_A_SCHOOL2, notASchoolIn2, exceptionsByLength, SCHOOL_FLUFF_VOCABULARY, schoolFluff, isFluffWord2, trailingFluffRun2, joinedPrefix2, SCHOOL_INSTITUTION_VOCABULARY, schoolInstitution, isInstitutionWord2, namesInstitution2, institutionLabel, INSTITUTION_PHRASES2, GLUED_INSTITUTION_SUFFIXES2, truncatedInstitution2, repairSchoolMojibake, hasSpecificToken2, isFluffOrFragment2, foldSchoolName2, schoolKeyTokens2 };