@finbheara/domain 0.60.1 → 0.62.0

package/dist/school.js

@@ -1,1118 +1,51 @@
 import {
-  SHARED_ROW_SENTINELS2,
-  sentinelIn2
+  SHARED_ROW_SENTINELS2
 } from "./chunks/place-tcgfvemw.js";
 import {
   NEVER_NAME,
-  printZones,
-  opensLocation,
+  printZones2,
+  opensLocation2,
   place2,
   isPlaceToken2,
   countryCodeOf2,
   areAllPlaceTokens2,
   placeRelation2,
   sameReading2
-} from "./chunks/place-yvcn0ngm.js";
+} from "./chunks/place-c5g25pym.js";
+import {
+  SCHOOL_CELL_OWN_SENTINELS2,
+  SCHOOL_CELL_SENTINELS2,
+  schoolCellSentinelOf2,
+  SCHOOL_NAME_EXCEPTIONS2,
+  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
+} from "./chunks/place-1mpcshk8.js";
 import {
   validity
 } from "./chunks/place-q9kwsmzd.js";
 
-import { normalizeApostrophes as normalizeApostrophes2 } from "@finbheara/names/lexicon";
+import { normalizeApostrophes } from "@finbheara/names/lexicon";
 import { SURNAME_SEPARATOR, lexiconKey, titleCaseNamePart } from "@finbheara/names/normalize";
 import { personName } from "@finbheara/names/normalize";
-
-var SCHOOL_CELL_OWN_SENTINELS = [
-  {
-    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_SENTINELS = [
-  ...SHARED_ROW_SENTINELS2,
-  ...SCHOOL_CELL_OWN_SENTINELS
-];
-var schoolCellSentinelOf = sentinelIn2(SCHOOL_CELL_SENTINELS);
-
-var SCHOOL_NAME_EXCEPTIONS = [
-  {
-    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_EXCEPTIONS
-].sort((a, b) => b.phrase.length - a.phrase.length);
-var NOT_A_SCHOOL = [
-  {
-    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 notASchoolIn(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 = schoolCellSentinelOf(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 isFluffWord(token) {
-  return schoolFluff(token)?.kind === "word";
-}
-function isTruncatedFluff(token) {
-  const t = token.toLocaleLowerCase();
-  if (t === "")
-    return false;
-  for (const entry of SCHOOL_FLUFF_VOCABULARY.values()) {
-    if (entry.kind !== "word" || !entry.truncatable)
-      continue;
-    if (entry.canonical.length > t.length && entry.canonical.startsWith(t))
-      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 trailingFluffRun(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 (!isFluffWord(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 joinedPrefix(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));
-}
-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_PHRASES = [...SCHOOL_INSTITUTION_VOCABULARY].filter(([, v]) => v.kind === "phrase").map(([k]) => k).sort();
-var GLUED_INSTITUTION_SUFFIXES = [...SCHOOL_INSTITUTION_VOCABULARY].filter(([, v]) => v.glued).map(([k]) => k).sort();
-function truncatedInstitution(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 hasSpecificToken(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) {
-  for (const w of SCHOOL_FLUFF_WORDS) {
-    if (w.length > token.length && w.startsWith(token))
-      return true;
-  }
-  return false;
-}
-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 foldSchoolName(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 : joinedPrefix(prev, word);
-    if (joined === undefined)
-      words.push(word);
-    else
-      words[words.length - 1] = joined.toLowerCase().replace(/'/g, "");
-  }
-  return words.join(" ");
-}
-function schoolKeyTokens(raw) {
-  const folded = foldSchoolName(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 (!hasSpecificToken(distinctiveTokens(folded.slice(0, end - 1))))
-      break;
-    end -= 1;
-  }
-  return [...new Set(distinctiveTokens(folded.slice(0, end)))];
-}
-
 var SCHOOL_REFUSED = "!!!NOTASCHOOL";
 var TITLE_CASE_STATE_CODES = new Set(["Nsw", "Qld", "Vic", "Tas"]);
 function schoolInitials(name) {
@@ -1161,10 +94,10 @@ var REAL_WORDS = new WeakMap;
 var DEFAULT_SCHOOL_NAME_CAPACITY = 16384;
 function createSchoolNameReader(options = {}) {
   const lexicon = options.lexicon;
-  const EXCEPTIONS_BY_LENGTH = exceptionsByLength(options.exceptions ?? SCHOOL_NAME_EXCEPTIONS);
-  const notASchool = notASchoolIn([
+  const EXCEPTIONS_BY_LENGTH = exceptionsByLength(options.exceptions ?? SCHOOL_NAME_EXCEPTIONS2);
+  const notASchool = notASchoolIn2([
     ...options.garbage ?? [],
-    ...options.refusals ?? NOT_A_SCHOOL
+    ...options.refusals ?? NOT_A_SCHOOL2
   ]);
   const SPACING_ACUTE_AFTER_VOWEL = /((?<=\p{L})[AEIOUaeiou]|[AEIUaeiu])[´ˊ](?![sS]\b)/gu;
   const SPACING_ACUTE = /[´ˊ]/gu;
@@ -1173,7 +106,7 @@ function createSchoolNameReader(options = {}) {
   }
   const INJECTED_LINK = /(?<=^|[\s([])(?:https?:\/\/|www\.)[^\s)\]]+/giu;
   function renderSn1(print) {
-    return normalizeApostrophes2(readSpacingAcute(repairSchoolMojibake(print)).normalize("NFKC")).replace(/\p{Cf}+/gu, "").replace(/\p{Cc}+/gu, " ").replace(INJECTED_LINK, " ").replace(/\s+/gu, " ").trim();
+    return normalizeApostrophes(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",
@@ -1205,7 +138,7 @@ function createSchoolNameReader(options = {}) {
       if (text === "")
         continue;
       const prev = out[out.length - 1];
-      const joined = prev === undefined ? undefined : joinedPrefix(prev.printed, text);
+      const joined = prev === undefined ? undefined : joinedPrefix2(prev.printed, text);
       if (prev !== undefined && joined !== undefined) {
         prev.printed = joined;
         continue;
@@ -1257,7 +190,7 @@ function createSchoolNameReader(options = {}) {
       const token = tokens[i];
       if (token === undefined || token.cls !== null)
         continue;
-      const suffix = GLUED_INSTITUTION_SUFFIXES.find((s) => token.text.length > s.length + 2 && token.text.endsWith(s));
+      const suffix = GLUED_INSTITUTION_SUFFIXES2.find((s) => token.text.length > s.length + 2 && token.text.endsWith(s));
       if (suffix === undefined)
         continue;
       const word = token.words[0];
@@ -1282,7 +215,7 @@ function createSchoolNameReader(options = {}) {
     }
   }
   function applyInstitutionPhrases(tokens) {
-    for (const phrase of INSTITUTION_PHRASES) {
+    for (const phrase of INSTITUTION_PHRASES2) {
       const words = phrase.split(" ");
       for (;; ) {
         const at = runAt(tokens, words);
@@ -1300,12 +233,16 @@ function createSchoolNameReader(options = {}) {
     }
   }
   function applyPlaces(tokens, at, sn1) {
+    let failedOpen = -1;
     for (let i = 1;i < tokens.length; i++) {
       const token = tokens[i];
       if (token.cls !== null)
         continue;
-      if (!opensLocation(token.text, at, token.words[0]?.at))
+      if (!opensLocation2(token.text, at, token.words[0]?.at))
         continue;
+      const before = tokens[i - 1];
+      const after = failedOpen === i - 1 && spaceJoined(sn1, before, token) && declaredQualifier(sn1, before.words[0]?.at);
+      failedOpen = i;
       const tail = tokens.slice(i);
       if (tail.some((t) => t.cls !== null))
         continue;
@@ -1329,6 +266,8 @@ function createSchoolNameReader(options = {}) {
         continue;
       if (read.truncated && nameBeatsACut(printed))
         continue;
+      if (read.truncated && after)
+        continue;
       if (read.truncated && !survivesWithout(tokens, i, tail.length))
         continue;
       for (const t of tail) {
@@ -1340,6 +279,13 @@ function createSchoolNameReader(options = {}) {
     }
     return null;
   }
+  function spaceJoined(sn1, before, token) {
+    const last = before.words[before.words.length - 1];
+    const first = token.words[0];
+    if (last === undefined || first === undefined)
+      return false;
+    return /^\s+$/u.test(sn1.slice(last.at + last.printed.length, first.at));
+  }
   function punctuatedTail(sn1, tail) {
     const first = tail[0]?.words[0];
     const lastToken = tail[tail.length - 1];
@@ -1347,7 +293,7 @@ function createSchoolNameReader(options = {}) {
     if (first === undefined || last === undefined)
       return null;
     const raw = sn1.slice(first.at, last.at + last.printed.length);
-    if (!/[,/;]/.test(raw) || /[()[\]]/.test(raw))
+    if (!/[,/;&+]/.test(raw) || /[()[\]]/.test(raw))
       return null;
     return raw;
   }
@@ -1434,9 +380,9 @@ function createSchoolNameReader(options = {}) {
       return false;
     if (schoolInstitution(token.text) !== undefined)
       return false;
-    if (truncatedInstitution(token.text) !== undefined)
+    if (truncatedInstitution2(token.text) !== undefined)
       return false;
-    if (isFluffWord(token.text))
+    if (isFluffWord2(token.text))
       return false;
     const flags = flagsOf(token.words.map((w) => w.printed).join(" "));
     if (flags === null || !flags.place)
@@ -1464,9 +410,9 @@ function createSchoolNameReader(options = {}) {
       return false;
     if (schoolInstitution(text) !== undefined)
       return false;
-    if (truncatedInstitution(text) !== undefined)
+    if (truncatedInstitution2(text) !== undefined)
       return false;
-    return !isFluffWord(text);
+    return !isFluffWord2(text);
   }
   function survivesWithout(tokens, at, width = 1) {
     const off = (i) => i >= at && i < at + width;
@@ -1510,7 +456,7 @@ function createSchoolNameReader(options = {}) {
         token.institution = inst.canonical;
         continue;
       }
-      if (isFluffWord(token.text)) {
+      if (isFluffWord2(token.text)) {
         token.cls = "FLUFF";
         continue;
       }
@@ -1532,7 +478,7 @@ function createSchoolNameReader(options = {}) {
       if (tokens.slice(i + 1).some((t) => t.cls === "NAME_PART"))
         continue;
       token.institution = undefined;
-      if (isFluffWord(token.text))
+      if (isFluffWord2(token.text))
         token.cls = "FLUFF";
       else if (token.text.length <= 2) {
         token.cls = "FLUFF";
@@ -1554,12 +500,12 @@ function createSchoolNameReader(options = {}) {
       if (tokens.slice(0, i).some(named) && !tokens.slice(i + 1).some(named))
         continue;
       const back = token.words.map((w) => ({
-        text: token.words.length === 1 ? token.text : foldSchoolName(w.printed),
+        text: token.words.length === 1 ? token.text : foldSchoolName2(w.printed),
         words: [w],
         cls: null
       }));
       for (const t of back) {
-        if (isFluffWord(t.text))
+        if (isFluffWord2(t.text))
           t.cls = "FLUFF";
         else if (t.text.length <= 2) {
           t.cls = "FLUFF";
@@ -1574,12 +520,12 @@ function createSchoolNameReader(options = {}) {
   function eatTruncatedTail(tokens) {
     let ate = false;
     const names = new Set(tokens.filter((t) => t.cls === "NAME_PART").map((t) => t.text));
-    const start = trailingFluffRun(tokens.map((t) => t.text), (text) => names.has(text));
+    const start = trailingFluffRun2(tokens.map((t) => t.text), (text) => names.has(text));
     for (let i = start;i < tokens.length; i++) {
       const token = tokens[i];
       if (token === undefined || token.cls !== "NAME_PART")
         continue;
-      const entry = truncatedInstitution(token.text);
+      const entry = truncatedInstitution2(token.text);
       if (entry !== undefined) {
         token.cls = "INSTITUTION_TYPE";
         token.institution = entry.canonical;
@@ -1596,7 +542,7 @@ function createSchoolNameReader(options = {}) {
         continue;
       if (token.cls !== "NAME_PART")
         break;
-      const entry = truncatedInstitution(token.text);
+      const entry = truncatedInstitution2(token.text);
       if (entry === undefined)
         break;
       if (!tokens.slice(0, end - 1).some((t) => t.cls === "NAME_PART"))
@@ -1610,7 +556,7 @@ function createSchoolNameReader(options = {}) {
   }
   const CONNECTORS = new Set(["of", "and", "the", "na", "an", "a", "do", "de", "du", "la", "le"]);
   function initialsOfWords(words) {
-    const folded = words.map((w) => foldSchoolName(w.printed)).filter((w) => /^[a-z]/.test(w));
+    const folded = words.map((w) => foldSchoolName2(w.printed)).filter((w) => /^[a-z]/.test(w));
     const all = folded.map((w) => w[0]).join("");
     const named = folded.filter((w) => !CONNECTORS.has(w)).map((w) => w[0]).join("");
     return [...new Set([all, named])].filter((i) => i.length >= 3).map((i) => i.toUpperCase());
@@ -1751,7 +697,7 @@ function createSchoolNameReader(options = {}) {
     return `${core}${type}${at === "" ? "" : ` (${at})`}`;
   }
   function nameWord(printed, first) {
-    const folded = foldSchoolName(printed);
+    const folded = foldSchoolName2(printed);
     if (!first && schoolFluff(folded)?.lowerInside === true && printed !== printed.toLocaleUpperCase())
       return printed.toLocaleLowerCase();
     return titleCaseNamePart(printed);
@@ -1759,7 +705,7 @@ function createSchoolNameReader(options = {}) {
   function renderException(token, first) {
     const printed = token.words.map((w) => w.printed).join(" ");
     const canonical = EXCEPTION_PHRASE.get(token.text);
-    const text = canonical !== undefined && foldSchoolName(printed) !== canonical ? canonical : printed;
+    const text = canonical !== undefined && foldSchoolName2(printed) !== canonical ? canonical : printed;
     return text.split(" ").map((w, i) => nameWord(w, first && i === 0)).join(" ");
   }
   function renderPart(part, first) {
@@ -1885,7 +831,7 @@ function createSchoolNameReader(options = {}) {
     }
     const tokens = [];
     for (const word of printedWords(sn1)) {
-      const text = foldSchoolName(word.printed);
+      const text = foldSchoolName2(word.printed);
       if (text === "")
         continue;
       tokens.push({ text, words: [word], cls: null });
@@ -1895,7 +841,7 @@ function createSchoolNameReader(options = {}) {
     deglueInstitutions(tokens);
     applyPhraseExceptions(tokens);
     applyInstitutionPhrases(tokens);
-    const positions = printZones(sn1);
+    const positions = printZones2(sn1);
     const tail = applyPlaces(tokens, positions, sn1);
     const read = tail?.read ?? null;
     const cutPlace = read?.truncated === true;
@@ -2235,7 +1181,7 @@ function schoolEncoder(options = {}) {
     levels: SCHOOL_LEVEL_COLUMNS,
     indexed: [...SCHOOL_LEVEL_COLUMNS, "matchKey"],
     encode(x) {
-      const key = foldSchoolName(x.sn0);
+      const key = foldSchoolName2(x.sn0);
       return { [printCol]: x.sn0, ...schoolColumns(x), matchKey: key === "" ? null : key };
     },
     key: (x, level) => schoolColumns(x)[level],
@@ -2280,34 +1226,41 @@ function compareSchools(a, b) {
     return { verdict: "CANDIDATE", reason: "truncated-print", sharesNameParts };
   return { verdict: "CANDIDATE", reason: "same-name-and-type", sharesNameParts };
 }
+function isSchoolVocabularyWord(token) {
+  return isPlaceToken2(token) || isInstitutionWord2(token) || isFluffWord2(token.toLowerCase());
+}
 export {
   DEFAULT_SCHOOL_NAME_CAPACITY,
   DEFAULT_SCHOOL_NAME_READER,
-  NOT_A_SCHOOL,
-  SCHOOL_CELL_OWN_SENTINELS,
-  SCHOOL_CELL_SENTINELS,
+  NOT_A_SCHOOL2 as NOT_A_SCHOOL,
+  SCHOOL_CELL_OWN_SENTINELS2 as SCHOOL_CELL_OWN_SENTINELS,
+  SCHOOL_CELL_SENTINELS2 as SCHOOL_CELL_SENTINELS,
   SCHOOL_LEVEL_COLUMNS,
-  SCHOOL_NAME_EXCEPTIONS,
+  SCHOOL_NAME_EXCEPTIONS2 as SCHOOL_NAME_EXCEPTIONS,
   SHARED_ROW_SENTINELS2 as SHARED_ROW_SENTINELS,
   compareSchoolNames,
   compareSchools,
   createSchoolNameReader,
-  foldSchoolName,
-  hasSpecificToken,
+  foldSchoolName2 as foldSchoolName,
+  hasSpecificToken2 as hasSpecificToken,
   isColumnCutOf,
+  isFluffOrFragment2 as isFluffOrFragment,
   isInitialismOf,
   isLadderLevel,
+  isSchoolVocabularyWord,
   mapOfSchools,
+  namesInstitution2 as namesInstitution,
+  notASchoolIn2 as notASchoolIn,
   probablySameSchool,
   realWords,
   realWordsInPrintOrder,
   sameInEveryPart,
-  schoolCellSentinelOf,
+  schoolCellSentinelOf2 as schoolCellSentinelOf,
   schoolColumns,
   schoolCompare,
   schoolEncoder,
   schoolInitials,
-  schoolKeyTokens,
+  schoolKeyTokens2 as schoolKeyTokens,
   schoolPrintSplit,
   schoolTokensAt,
   setOfSchools