chaffjs 0.35.0 → 0.36.0

package/rules/vague-word-density.yaml

@@ -53,8 +53,8 @@ example:
       Report an incident within 30 minutes and notify the affected teams. Record it in the incident log and fix the cause by the next working day.
 
 not_flagged:
-  ja: 文書の長さに対して少ないものは指しません。短すぎる文書も測りません。指すのは語のある文ごとに一度で、長い言い方の中の語（in a timely manner の timely）は一つと数えます。英語の法務の文書では、法律や慣行が意味を決めている言い方（reasonable、best efforts、from time to time）の中の語は数えません。要求の文の中の「可能な限り」「必要に応じて」は、要求の書き方として requirement-smell も見ます。
-  en: 'A few vague words for the document''s length are not reported, and very short documents are not measured. Each sentence is reported once, and a word inside a longer phrase ("timely" in "in a timely manner") counts once. In legal documents, a word inside a term that law and practice define ("reasonable", "best efforts", "from time to time") is not counted. Inside a requirement, requirement-smell also reads "where possible" and "as needed".'
+  ja: 文書の長さに対して少ないものは指しません。短すぎる文書も測りません。指すのは語のある文ごとに一度で、長い言い方の中の語（in a timely manner の timely）は一つと数えます。英語の法務の文書では、法律や慣行が意味を決めている言い方（reasonable、best efforts、from time to time）の中の語は数えません。要求の文の中の「可能な限り」「必要に応じて」は、要求の書き方として requirement-smell も見ます。すぐ後ろの括弧で中身を書いた語（一定の事項（請求書に書く事項））も数えません。括弧が名前を付けるだけ（以下「本措置」という。）なら数えます。
+  en: 'A few vague words for the document''s length are not reported, and very short documents are not measured. Each sentence is reported once, and a word inside a longer phrase ("timely" in "in a timely manner") counts once. In legal documents, a word inside a term that law and practice define ("reasonable", "best efforts", "from time to time") is not counted. Inside a requirement, requirement-smell also reads "where possible" and "as needed". A word that the bracket right after it pins down ("a reasonable fee (USD 50)") is not counted either; a bracket that only names it ("(hereinafter the ""Fee"")") pins nothing down.'
 level_meaning:
   ja: 1000 字あたりあいまいな語 {limit} 個まで
   en: up to {limit} vague words per 1000 words

package/skills/chaff/SKILL.md

@@ -31,7 +31,9 @@ read. A contract checked as a blog post gets wrong findings, so choose the genre
    guessed or default genre shows no guide, and `--no-guide` leaves it out.
 
 A rule the genre turns off is listed under "did not run" with the genre as the reason. That is the preset's
-choice, not a gap; turn it back on (`rules:` in `chaff.yaml`) only when the person asks.
+choice, not a gap; turn it back on (`rules:` in `chaff.yaml`) only when the person asks. Some of these are off
+because chaff measured them to be mostly wrong for that kind of document on real, judged documents
+([isamu/chaff-corpus](https://github.com/isamu/chaff-corpus)); turning one back on brings those false findings back.
 
 ## Run it
 
@@ -75,6 +77,10 @@ calls nothing. Ask the person before a real run; the passages leave the machine.
 `npx chaffjs explain <rule-id>` shows why a rule exists, its levels and the current one. Read it before
 relaxing a rule.
 
+When a finding is wrong for a reason that is not about this team (chaff misread the text), tell the person and offer
+`npx chaffjs feedback <file> --rule <rule-id> --line <n>`: it drafts a report and sends nothing. A document the
+person may share can go to isamu/chaff-corpus, where wrong findings become test cases and rule fixes.
+
 ## When numbers or dates disagree
 
 The group "Facts that disagree" in `npx chaffjs rules` checks what a sum or a calendar can settle. Among them:

package/src/announced-count.ts

@@ -20,6 +20,8 @@ export type CountWords = {
   readonly hedgesBefore: readonly string[];
   /** 数か数える語のすぐ後ろにあると予告でなくなる語（以上、目、or more）。 */
   readonly hedgesAfter: readonly string[];
+  /** 数と合わせて、その一行だけで下の並びの数を言う見出しの語（3行要約、three-line summary）。 */
+  readonly titles: readonly string[];
 };
 
 export type CountMismatch = { readonly offset: number; readonly phrase: string; readonly announced: number; readonly listed: number };
@@ -101,7 +103,17 @@ const numberPattern = (words: CountWords): RegExp => {
   return new RegExp(latin.length === 0 ? digits : `${digits}|(?<![A-Za-z])(?:${alternation(latin)})(?![A-Za-z])`, "iu");
 };
 
-type Patterns = { readonly phrase: RegExp; readonly number: RegExp };
+/**
+ * 予告の塊が一行で、数と見出しの語だけ（3行要約、**Three-line summary:**）。前後でそろった強調の印と終わりのコロンは許す。
+ * 文の中の「3行要約を書いた」は予告でない。
+ */
+const titlePattern = (words: CountWords): RegExp | undefined => {
+  if (words.titles.length === 0) return undefined;
+  const numbers = words.numbers.length === 0 ? "\\p{Nd}+" : `\\p{Nd}+|${alternation(words.numbers)}`;
+  return new RegExp(`^([ \\t]*(\\*\\*|__|\\*|_)?)((${numbers})[ \\t]?(?:${alternation(words.titles)}))\\2[ \\t]*[:：]?[ \\t]*$`, "iu");
+};
+
+type Patterns = { readonly phrase: RegExp; readonly number: RegExp; readonly title: RegExp | undefined };
 
 /**
  * 数える語の無い数は、先を指す語のすぐ後ろでだけ（the following two:）。「under $75:」の金額を数に読まない。
@@ -181,20 +193,35 @@ const matchesList = (announced: number, source: string, list: BulletList): boole
 
 type Context = { readonly source: string; readonly words: CountWords; readonly patterns: Patterns; readonly neighbours: Neighbours };
 
+/** 予告の塊のどこに、何と書いて、いくつと言ったか。 */
+type Announcement = { readonly start: number; readonly phrase: string; readonly announced: number };
+
+/** 最後の一文の予告（以下の3点）か、塊が見出しの語句だけの予告（3行要約）。 */
+const announcementIn = (lead: string, words: CountWords, patterns: Patterns): Announcement | undefined => {
+  const sentenceStart = lastSentenceStart(lead);
+  const sentence = lead.slice(sentenceStart);
+  const phrase = announcedIn(sentence, words, patterns);
+  if (phrase !== undefined)
+    return { start: sentenceStart + phrase.start, phrase: sentence.slice(phrase.start, phrase.end).trim(), announced: phrase.announced };
+  const title = patterns.title?.exec(lead);
+  const written = title?.[3];
+  if (title === null || title === undefined || written === undefined) return undefined;
+  const announced = valueOf(title[4] ?? "", words.numbers);
+  return announced < 1 ? undefined : { start: (title[1] ?? "").length, phrase: written, announced };
+};
+
 const mismatchOf = ({ source, words, patterns, neighbours }: Context, list: BulletList): CountMismatch[] => {
   if (hasNeighbour(source, list.span, neighbours)) return [];
   const lead = leadBefore(source, list.span.start);
   if (lead === undefined) return [];
-  const sentenceStart = lastSentenceStart(lead.text);
-  const sentence = lead.text.slice(sentenceStart);
-  const phrase = announcedIn(sentence, words, patterns);
-  if (phrase === undefined || matchesList(phrase.announced, source, list)) return [];
-  const offset = lead.start + sentenceStart + phrase.start;
-  return [{ offset, phrase: sentence.slice(phrase.start, phrase.end).trim(), announced: phrase.announced, listed: list.items.length }];
+  const announcement = announcementIn(lead.text, words, patterns);
+  if (announcement === undefined || matchesList(announcement.announced, source, list)) return [];
+  return [{ offset: lead.start + announcement.start, phrase: announcement.phrase, announced: announcement.announced, listed: list.items.length }];
 };
 
 export const announcedCountMismatches = (source: string, lists: readonly BulletList[], words: CountWords): CountMismatch[] => {
   if (words.counters.length === 0) return [];
-  const context = { source, words, patterns: { phrase: phrasePattern(words), number: numberPattern(words) }, neighbours: neighboursOf(source, lists) };
+  const patterns = { phrase: phrasePattern(words), number: numberPattern(words), title: titlePattern(words) };
+  const context = { source, words, patterns, neighbours: neighboursOf(source, lists) };
   return lists.flatMap((list) => mismatchOf(context, list));
 };

package/src/chronology-rows.ts

@@ -0,0 +1,86 @@
+import { calendarUnitsOf, type CalendarUnits } from "./calendar-number.ts";
+import type { ProseDocument, Sentence } from "./plugin.ts";
+
+/**
+ * 年表の行（「1950年4月 設立」「2003年４月大阪証券取引所上場廃止。」）。日付で始まり、すぐに出来事を書く。
+ * 行は名詞で止め、文書の文体とも合わせないのが年表の書き方なので、本文の文として数えない。
+ *
+ * 日付で始まる文が 1 つだけなら本文（「2020年4月当社は…」）。続けて MIN_ROWS 以上並んだときだけ年表と読む。
+ * 行の注記（「当時主要製品は…」）が MAX_GAP 文まで挟まっても同じ年表の続きで、注記も年表の中身として数えない。
+ */
+const MIN_ROWS = 3;
+const MAX_GAP = 4;
+
+/** 日付のすぐ後ろにあれば、日付は文の一部で年表の見出しではない（2020年に、2020年4月、当社は）。 */
+const JOINS_DATE = /^[\p{Script=Hiragana}\p{P}\p{Sm}]/u;
+const DIGITS = /^[0-9０-９]+/u;
+const CALENDAR_YEAR_DIGITS = 4;
+
+type Part = { readonly digits: number; readonly rank: number; readonly end: number };
+
+/** 数（全角も）と、その後ろ（空白 1 つまで）の単位。単位が units.chained に無ければ undefined。 */
+const partAt = (text: string, at: number, units: CalendarUnits): Part | undefined => {
+  const digits = DIGITS.exec(text.slice(at))?.[0];
+  if (digits === undefined) return undefined;
+  const unitAt = text[at + digits.length] === " " ? at + digits.length + 1 : at + digits.length;
+  const rank = units.chained.findIndex((unit) => text.startsWith(unit, unitAt));
+  const unit = units.chained[rank];
+  if (unit === undefined) return undefined;
+  // 「2020年度」は年度という別の語で、年表の日付ではない。
+  if ([...units.year].some((word) => word.length > unit.length && text.startsWith(word, unitAt))) return undefined;
+  return { digits: digits.length, rank, end: unitAt + unit.length };
+};
+
+/** 前より小さい単位（年の後ろの月、月の後ろの日）が続く限り延ばした日付の終わり。 */
+const chainEnd = (text: string, last: Part, units: CalendarUnits): number => {
+  const next = partAt(text, last.end, units);
+  return next !== undefined && next.rank > last.rank ? chainEnd(text, next, units) : last.end;
+};
+
+/** 文の頭の見出しの札（「２【沿革】」）。本文に流し込んだ見出しの後ろから、最初の行が始まる。 */
+const LEADING_LABEL = /^\s*(?:[0-9０-９]+\s*)?【[^】\n]*】\s*/u;
+
+/** 文の頭（空白と見出しの札を除く）の、年から始まる日付（1950年4月、昭和56年11月1日）の終わり。年は 4 桁か元号付き。日付で始まらなければ undefined。 */
+const leadingDateEnd = (text: string, units: CalendarUnits): number | undefined => {
+  const lead = LEADING_LABEL.exec(text)?.[0].length ?? text.length - text.trimStart().length;
+  const era = units.era.find((name) => text.startsWith(name, lead));
+  const year = partAt(text, lead + (era?.length ?? 0), units);
+  if (year === undefined || year.rank !== 0 || (era === undefined && year.digits !== CALENDAR_YEAR_DIGITS)) return undefined;
+  return chainEnd(text, year, units);
+};
+
+/** 年から始まる日付で始まり、助詞も句読点も挟まずに出来事が続く文か。units は日付の単位（年月日の順）と元号。 */
+export const opensWithDateStamp = (text: string, units: CalendarUnits): boolean => {
+  const end = leadingDateEnd(text, units);
+  if (end === undefined) return false;
+  const rest = text.slice(end).trimStart();
+  return rest !== "" && !JOINS_DATE.test(rest);
+};
+
+/** heads[i] が日付で始まる文。年表と読む文の番号（MAX_GAP 文までの間を挟んで MIN_ROWS 以上続く行と、行の間の注記）。 */
+export const chronologyRowIndexes = (heads: readonly boolean[]): ReadonlySet<number> => {
+  const dated = heads.flatMap((head, index) => (head ? [index] : []));
+  const clusters = dated.reduce<number[][]>((acc, index) => {
+    const cluster = acc.at(-1);
+    const previous = cluster?.at(-1);
+    if (cluster !== undefined && previous !== undefined && index - previous - 1 <= MAX_GAP) cluster.push(index);
+    else acc.push([index]);
+    return acc;
+  }, []);
+  return new Set(
+    clusters
+      .filter((cluster) => cluster.length >= MIN_ROWS)
+      .flatMap((cluster) => Array.from({ length: (cluster.at(-1) ?? 0) - (cluster[0] ?? 0) + 1 }, (_, offset) => (cluster[0] ?? 0) + offset)),
+  );
+};
+
+/** 主題の「は」。年表の行は出来事だけを書き、主題を立てない。立てた文（2021年売上高は110億円です。）は日付で始まっても本文。 */
+const TOPIC = "は";
+const hasTopic = (sentence: Sentence): boolean => (sentence.tokens ?? []).some((token) => token.surface === TOPIC && token.pos === "ADP");
+
+/** 文書の中の、年表の行の文。 */
+export const chronologyRows = (doc: ProseDocument): ReadonlySet<Sentence> => {
+  const units = calendarUnitsOf(doc);
+  const rows = chronologyRowIndexes(doc.sentences.map((sentence) => opensWithDateStamp(sentence.text, units) && !hasTopic(sentence)));
+  return new Set(doc.sentences.filter((_, index) => rows.has(index)));
+};

package/src/company-name-run.ts

@@ -0,0 +1,37 @@
+import { escapeRegExp } from "./orthography.ts";
+import type { Span } from "./plugin.ts";
+
+/** 会社の名前に使う字（漢字・片仮名・英数字）の続き。かなや句読点で名前は切れる。 */
+const NAME_RUN = /[\p{Script=Han}ァ-ヺーA-Za-zＡ-Ｚａ-ｚ0-9０-９&＆・]+/gu;
+
+/** 漢字か片仮名を含む形（株式会社、㈱、(株)）。英字だけの形は日本語の名前の目印にならない。 */
+const NOT_LATIN = /[^\p{Script=Latin}\p{P}\s]/u;
+
+const formPattern = (forms: readonly string[]): RegExp =>
+  new RegExp(
+    [...forms]
+      .sort((a, b) => b.length - a.length)
+      .map(escapeRegExp)
+      .join("|"),
+    "gu",
+  );
+
+/** at を含むか、at で接する名前の字の続き。 */
+const runAround = (runs: readonly Span[], at: number): Span | undefined => runs.find((run) => run.start <= at && at <= run.end);
+
+/**
+ * text の中の、日本の会社の形（語彙表 company-form）とその隣の名前の範囲（関東珪曹硝子㈱、株式会社ADEKA）。
+ * 名前は書き手が選べない字で書かれるので、表記のゆれを数える語に入れない。形の前は名前の字が続くかぎり、形の後ろも同じ。
+ * 名前の字の続きを一度だけ求め、形の両端をそれに合わせて伸ばす。
+ */
+export const japaneseCompanyNameSpans = (text: string, forms: readonly string[]): Span[] => {
+  const japanese = forms.filter((form) => NOT_LATIN.test(form));
+  if (japanese.length === 0) return [];
+  const found = [...text.matchAll(formPattern(japanese))];
+  if (found.length === 0) return [];
+  const runs = [...text.matchAll(NAME_RUN)].map((match) => ({ start: match.index, end: match.index + match[0].length }));
+  return found.map((match) => {
+    const end = match.index + match[0].length;
+    return { start: runAround(runs, match.index)?.start ?? match.index, end: runAround(runs, end)?.end ?? end };
+  });
+};

package/src/compound-head.ts

@@ -0,0 +1,25 @@
+import type { Token } from "./plugin.ts";
+
+const OPENING = new Set(["（", "("]);
+const CLOSING = new Set(["）", ")"]);
+
+const isTouching = (left: Token | undefined, right: Token | undefined): boolean =>
+  left !== undefined && right !== undefined && left.span.end === right.span.start;
+
+const isNounBefore = (token: Token, next: Token | undefined, suffixes: ReadonlySet<string>): next is Token =>
+  next?.pos === "NOUN" && isTouching(token, next) && !suffixes.has(next.surface);
+
+/** A noun alone in brackets that close onto a noun (卒業（見込）証明書): the brackets mark it optional inside one compound. */
+const isBracketedInCompound = (token: Token, tokens: readonly Token[], at: number, suffixes: ReadonlySet<string>): boolean => {
+  const [opening, closing] = [tokens[at - 1], tokens[at + 1]];
+  if (opening === undefined || closing === undefined) return false;
+  if (!OPENING.has(opening.surface) || !CLOSING.has(closing.surface) || !isTouching(opening, token) || !isTouching(token, closing)) return false;
+  return isNounBefore(closing, tokens[at + 2], suffixes);
+};
+
+/**
+ * Whether `token`, read at `at` in `tokens`, is a noun written onto the noun after it (取扱事業者), so official Japanese may
+ * drop its okurigana. A listed phrase suffix (割当て等) does not make a compound. `token` may be tokens[at] read as a noun.
+ */
+export const isCompoundHead = (token: Token, tokens: readonly Token[], at: number, suffixes: ReadonlySet<string>): boolean =>
+  token.pos === "NOUN" && (isNounBefore(token, tokens[at + 1], suffixes) || isBracketedInCompound(token, tokens, at, suffixes));

package/src/date-format.ts

@@ -115,9 +115,48 @@ const LINE_HEAD = /(?:^|\|)[\s>*_+-]*(?:\d+[.)]\s+)?$/u;
 /** 日付が行の頭（箇条書きの項目や表の升の頭）にあるか。 */
 export const opensLine = (text: string, offset: number): boolean => LINE_HEAD.test(text.slice(text.lastIndexOf("\n", offset - 1) + 1, offset));
 
+/** 刻印のラベルと日付の間に来る字（更新日：、Last updated: ）。 */
+const STAMP_GAP = /[\s:：]/u;
+/** 末尾の、ラベルと日付の間の字を外した文字列。 */
+const withoutGap = (text: string): string => {
+  const chars = text.split("");
+  return chars.slice(0, chars.findLastIndex((char) => !STAMP_GAP.test(char)) + 1).join("");
+};
+
+/** 刻印のラベルの前に来てよい字。行の頭か、ページの部品を区切る空白と縦線（ページID：0014616 更新日：）。 */
+const STAMP_LEAD = /[\s|｜]/u;
+
+/**
+ * text が刻印のラベル word で終わり、ラベルが行の頭か区切りの後ろから始まる。文の中の語（この日付は公開：、The date:、
+ * 1Updated）は刻印のラベルではない。語彙表に書いたとおりの字で照らす。
+ */
+const endsWithLabel = (text: string, word: string): boolean => {
+  const start = text.length - word.length;
+  if (word === "" || start < 0 || !text.endsWith(word)) return false;
+  return start === 0 || STAMP_LEAD.test(text.charAt(start - 1));
+};
+
+/**
+ * 日付のすぐ前が、ページの更新日・公開日の刻印のラベル（更新日：2026年10月13日、Last updated: 2 October 2026）。
+ * 刻印は CMS が付ける付帯情報で、本文の日付の書き方（令和8年…）とは別の書き方をしてよい。
+ */
+export const stampedDate = (text: string, offset: number, stampLabels: readonly string[]): boolean => {
+  const before = withoutGap(text.slice(text.lastIndexOf("\n", offset - 1) + 1, offset));
+  return stampLabels.some((label) => endsWithLabel(before, label));
+};
+
+type DateGroup = "head" | "body" | "stamp";
+
+const groupOf = (text: string, date: WrittenDate, stampLabels: readonly string[]): DateGroup => {
+  if (stampedDate(text, date.offset, stampLabels)) return "stamp";
+  return opensLine(text, date.offset) ? "head" : "body";
+};
+
+const GROUP_ORDER: readonly DateGroup[] = ["head", "body", "stamp"];
+
 /**
- * 行の頭の日付と、文の中の日付を分ける。予定表を 2026-10-16 で並べ、文では 14 October 2026 と書くのは使い分けで、混ざりではない。
- * 書き方はそれぞれの組の中でだけ比べる。
+ * 行の頭の日付と、文の中の日付と、更新日・公開日の刻印の日付を分ける。予定表を 2026-10-16 で並べ、文では 14 October 2026 と
+ * 書くのは使い分けで、混ざりではない。刻印のラベルは言語パッケージの語彙表（date-stamp-label）が渡す。書き方はそれぞれの組の中でだけ比べる。
  */
-export const dateGroups = (text: string, dates: readonly WrittenDate[]): WrittenDate[][] =>
-  [true, false].map((head) => dates.filter((date) => opensLine(text, date.offset) === head)).filter((group) => group.length > 0);
+export const dateGroups = (text: string, dates: readonly WrittenDate[], stampLabels: readonly string[] = []): WrittenDate[][] =>
+  GROUP_ORDER.map((group) => dates.filter((date) => groupOf(text, date, stampLabels) === group)).filter((group) => group.length > 0);

package/src/derived/count-per-period.ts

@@ -0,0 +1,28 @@
+import type { Span } from "../plugin.ts";
+import { overlapsAny, type SpanIndex } from "../compare/spans.ts";
+import type { DurationUnit } from "./date-arithmetic.ts";
+
+/** A word that names a period (週, 毎月, a week), where it is written beside the count, and the period's unit. */
+export type PeriodWord = { readonly word: string; readonly position: "before" | "after"; readonly unit: DurationUnit };
+
+/** The period words, and the named schedules in the document (週休2日制, 4週8休). */
+export type PerPeriodWords = { readonly periods: readonly PeriodWord[]; readonly schedules: SpanIndex };
+
+const UNIT_ORDER: readonly DurationUnit[] = ["day", "week", "month", "year"];
+
+/** A number or a counter just before the period word: 1年3か月 and 3か月10日 are one length written in two units, not a count per year or month. */
+const COUNTED = /[0-9０-９〇一二三四五六七八九十百千かヵヶカケ箇個]$/u;
+
+const endsWithPeriod = (before: string, word: string): boolean => before.endsWith(word) && !COUNTED.test(before.slice(0, before.length - word.length));
+
+const isBeside = (period: PeriodWord, before: string, after: string): boolean =>
+  period.position === "before" ? endsWithPeriod(before, period.word) : after.startsWith(period.word);
+
+/**
+ * A number with a unit of time that is not a length to add to a date: a count in each period (週3日、月10日、3 days a week) or a
+ * number inside the name of a work schedule (週休2日制の2日、4週8休の4週). A count is in a unit smaller than its period: 毎年1年間 is a
+ * year's length. before and after are the text next to the count, lower-cased.
+ */
+export const isCountPerPeriod = (count: Span & { readonly unit: DurationUnit }, before: string, after: string, words: PerPeriodWords): boolean =>
+  overlapsAny(words.schedules, count) ||
+  words.periods.some((period) => UNIT_ORDER.indexOf(count.unit) < UNIT_ORDER.indexOf(period.unit) && isBeside(period, before, after));

package/src/detectors/acronym-context.ts

@@ -6,7 +6,7 @@ import { loneNumeralSpans, nameNumeralSpans } from "./name-numeral.ts";
 import { placeholderSpans } from "./placeholder.ts";
 import { numeralWordSpans } from "./numeral-word.ts";
 import { seriesLabelSpans } from "./series-label.ts";
-import { oneOf } from "./acronym-name.ts";
+import { nameSpansOf, oneOf } from "./acronym-name.ts";
 
 /**
  * 大文字の語が略語ではなく、決まった書き方の一部として読める所（3:30 PM、1pm ET、USD 1,000、Kansas City, MO 64108、Fort Lauderdale FL 33304）。
@@ -114,3 +114,32 @@ export const notAcronymSpansOf = (words: NotationWords): NotAcronymSpans => {
     ...numeralWordSpans(text),
   ];
 };
+
+/**
+ * 略語として数えない範囲（書き方の範囲と、名前の中の範囲）を、言語パッケージの語彙表から組み立てる。wordsOf は語彙表の id から語を返す。
+ */
+export const lexiconNotationOf = (wordsOf: (id: string) => string[]): NotAcronymSpans => {
+  const notation = notAcronymSpansOf({
+    meridiem: wordsOf("meridiem"),
+    timeZones: wordsOf("time-zone"),
+    currencies: wordsOf("currency-code"),
+    usStates: wordsOf("us-state-code"),
+    emphasis: wordsOf("emphasis-word"),
+    divisions: wordsOf("numbered-division"),
+    abbreviatedLabels: wordsOf("abbreviated-label"),
+    honorifics: wordsOf("honorific"),
+    titles: wordsOf("name-title"),
+    dateTimeUnits: wordsOf("date-time-unit"),
+  });
+  const names = nameSpansOf({
+    legalForms: wordsOf("legal-form"),
+    companyForms: wordsOf("company-form"),
+    determiners: wordsOf("name-determiner"),
+    citationSeries: wordsOf("citation-series"),
+    carriers: wordsOf("carrier-name"),
+    namePrefixes: wordsOf("name-prefix"),
+    streetSuffixes: wordsOf("street-suffix"),
+    capitalPhrases: wordsOf("capital-phrase"),
+  });
+  return (text) => [...notation(text), ...names(text)];
+};

package/src/detectors/acronym-expansion.ts

@@ -13,6 +13,9 @@ import { escapeRegExp } from "../orthography.ts";
  *   人事部（以下「HR」という。）      括弧の中が定義の語と略語だけ
  *   overnight reverse repurchase agreement (ON RRP)  括弧の中が空白で繋いだ略語だけで、前の名前から文字が順に拾える
  *   Partnership On Wide Energy and Resources Resilience Asia (POWERR Asia)  括弧の中が略語と添えた語で、前の名前の頭文字と揃う
+ *   End User Technical Advisory Board (“End User TAB”)  括弧の中が名前の頭の語と略語で、前の名前の頭文字と揃う
+ *   Special Interest Groups, or SIGs  名前の後ろの読点と言い換えの語（語彙表の definition-alternative）の後ろで、名前の頭文字と揃う
+ * 複数形の s を付けた略語（SIGs）の展開は、s の無い略語（SIG）の展開でもある。
  * 括弧と略語の間には、引用符（(“MNDA”)、（「MNDA」））と空白だけを許す。
  */
 const WRAP = String.raw`[\s"“”'‘’「」『』]*`;
@@ -37,11 +40,14 @@ const DEFINITION_REACH = 60;
 /** 定義の語どうし、定義の語と略語の間に来てよいもの（以下、HR）。英字が続けば語の途中（(theSLA)）。 */
 const MARKER_GAP = String.raw`(?![A-Za-z])[\s、,]*`;
 
+/** 複数形の略語の終わりの s（SIGs）。頭文字と比べる文字ではない。 */
+const PLURAL_END = /(?<=[A-Z])s$/u;
+
 /**
  * 角括弧は引用の印にも使う（[IANA]、[1]）。直前の語のうち大文字で始まる語の頭文字が
  * 略語と揃うときだけ展開と見なす。見る語は略語の文字数の 2 倍まで（and や of を挟むため）。
  */
-const lettersOf = (acronym: string): string => acronym.replaceAll(/[&-]/gu, "");
+const lettersOf = (acronym: string): string => acronym.replaceAll(/[&-]/gu, "").replace(PLURAL_END, "");
 
 const initialsOf = (words: readonly string[]): string =>
   words
@@ -92,16 +98,20 @@ const isNamedBeforeAt = (body: string, acronym: string, at: number): boolean =>
   return namesAcronym(named.groups?.["name"] ?? "", acronym);
 };
 
-/** 言語パッケージの語彙表から読む、括弧の中で略語の前に書く語（以下、hereinafter）と後ろに書く語（という）。 */
-export type DefinitionWords = { readonly markers: readonly string[]; readonly verbs: readonly string[] };
+/**
+ * 言語パッケージの語彙表から読む、括弧の中で略語の前に書く語（以下、hereinafter）と後ろに書く語（という）、名前の後ろの読点に続けて
+ * 略語の前に書く言い換えの語（Special Interest Groups, or SIGs の or）。
+ */
+export type DefinitionWords = { readonly markers: readonly string[]; readonly verbs: readonly string[]; readonly alternatives?: readonly string[] };
 
-type DefinitionPatterns = { readonly opened: RegExp; readonly closes: RegExp };
+type DefinitionPatterns = { readonly opened: RegExp; readonly closes: RegExp; readonly alternative: RegExp };
 
 const oneOf = (words: readonly string[]): string => (words.length === 0 ? "(?!)" : words.map(escapeRegExp).join("|"));
 
 const definitionPatterns = (words: DefinitionWords): DefinitionPatterns => ({
   opened: new RegExp(String.raw`[(（]\s*(?<markers>(?:(?:${oneOf(words.markers)})${MARKER_GAP})*)${WRAP}(?<![A-Za-z])$`, "iu"),
   closes: new RegExp(String.raw`^${WRAP}(?<verb>(?:${oneOf(words.verbs)})[。.]?)?${WRAP}[)）]`, "iu"),
+  alternative: new RegExp(String.raw`[,，、]\s*(?:${oneOf(words.alternatives ?? [])})\s*$`, "iu"),
 });
 
 /**
@@ -166,12 +176,39 @@ const isQualifiedAt = (body: string, acronym: string, at: number): boolean => {
   return spellsOut(name.endsWith(words) ? name.slice(0, -words.length) : name, acronym);
 };
 
+/** 括弧の中で略語の前に置いた、大文字で始まる語（(“End User TAB”) の End User）。 */
+const PREFIX = new RegExp(String.raw`[(（]${WRAP}(?<words>(?:[A-Z][a-z]+ )+)$`, "u");
+
+/**
+ * 括弧の中が、前の名前の頭の語と略語だけの形（End User Technical Advisory Board (“End User TAB”)）。添えた語が括弧の前の名前にあり、
+ * 名前の頭文字が略語と揃うときだけ展開と見なす。名前に無い語を添えた括弧（Review Board (“Community CRB”)）は別の名前。
+ */
+const isPrefixedAt = (body: string, acronym: string, at: number): boolean => {
+  const prefix = PREFIX.exec(body.slice(Math.max(0, at - DEFINITION_REACH), at));
+  if (prefix === null || !CLOSES.test(body.slice(at + acronym.length, at + acronym.length + NEAR))) return false;
+  const name = body.slice(0, at - prefix[0].length);
+  const words = (prefix.groups?.["words"] ?? "").trim();
+  return name.slice(-DEFINITION_REACH).includes(words) && spellsOut(name, acronym);
+};
+
+/** 名前の後ろの読点と言い換えの語に続く略語（Special Interest Groups, or SIGs）。名前の頭文字が略語と揃うときだけ。 */
+const isAlternativeAt = (patterns: DefinitionPatterns, body: string, acronym: string, at: number): boolean => {
+  const joined = patterns.alternative.exec(body.slice(Math.max(0, at - DEFINITION_REACH), at));
+  return joined !== null && spellsOut(body.slice(0, at - joined[0].length), acronym);
+};
+
 const isBracketedAt = (body: string, acronym: string, at: number): boolean => {
   const after = body.slice(at + acronym.length, at + acronym.length + NEAR);
   const before = body.slice(Math.max(0, at - NEAR), at);
   if (OPENS.test(after) || (OPENED.test(before) && CLOSES.test(after))) return true;
   if (SQUARE_OPENED.test(before) && SQUARE_CLOSES.test(after) && spellsOut(body.slice(0, at), acronym)) return true;
-  return isSeparatedAt(body, acronym, at) || isNamedBeforeAt(body, acronym, at) || isJointBracketedAt(body, acronym, at) || isQualifiedAt(body, acronym, at);
+  return (
+    isSeparatedAt(body, acronym, at) ||
+    isNamedBeforeAt(body, acronym, at) ||
+    isJointBracketedAt(body, acronym, at) ||
+    isQualifiedAt(body, acronym, at) ||
+    isPrefixedAt(body, acronym, at)
+  );
 };
 
 /**
@@ -358,5 +395,9 @@ export type ExpandedAt = (body: string, acronym: string, at: number) => boolean;
 /** body の at にある略語が、その場で展開・定義されているか。語彙表から一度だけ組み立てて、略語ごとに呼ぶ。 */
 export const expansionAt = (words: DefinitionWords): ExpandedAt => {
   const patterns = definitionPatterns(words);
-  return (body, acronym, at) => isBracketedAt(body, acronym, at) || isDefinedAt(patterns, body, acronym, at) || isEqualsDefinedAt(body, acronym, at);
+  return (body, acronym, at) =>
+    isBracketedAt(body, acronym, at) ||
+    isDefinedAt(patterns, body, acronym, at) ||
+    isAlternativeAt(patterns, body, acronym, at) ||
+    isEqualsDefinedAt(body, acronym, at);
 };

package/src/detectors/acronym-known.ts

@@ -0,0 +1,40 @@
+// Words in capitals that a document itself makes known without spelling them out: a keyword of its code, a cited venue. Pure.
+import { codeFences, codeSpans, withoutCodeBlocks } from "./code-fences.ts";
+
+type Span = { readonly start: number; readonly end: number };
+
+/** A piece of code between spaces and brackets: a hyphen, a dot, a slash or an underscore keeps a name in one piece. */
+const CODE_TOKEN = /[\w./-]+/gu;
+/** A keyword: a token of letters only (select, from), not a name with parts (net-http-sspi, gsa.gov, --yjit, api_key). */
+const KEYWORD = /^[A-Za-z]+$/u;
+/** The text of an inline link ([text](url)) or of a reference link ([text][label]). */
+const LINK_TEXT = /^\[([^\]]*)\][([]/u;
+/** Capitals followed by a year: a venue and when it was held (FOSDEM 2024). */
+const VENUE_YEAR = /(?<![\w&])([A-Z][A-Z\d]+) (?:19|20)\d{2}(?!\d)/gu;
+
+/**
+ * The keywords a document's code (fenced blocks and inline code) writes in lower case, in capitals. Prose that writes a
+ * keyword of that code in capitals (a SELECT, the WHERE clause, with select and where in the code) names the keyword; it is
+ * not an acronym. A word the code too writes in capitals (`TTS`) is the acronym set as code, and gives nothing.
+ */
+export const codeWords = (source: string): Set<string> => {
+  const blocks = codeFences(source).flatMap((fence) => fence.lines);
+  const inline = codeSpans(withoutCodeBlocks(source)).map((span) => span.text);
+  const tokens = [...blocks, ...inline].flatMap((code) => code.match(CODE_TOKEN) ?? []);
+  return new Set(tokens.filter((token) => KEYWORD.test(token) && token !== token.toUpperCase()).map((token) => token.toUpperCase()));
+};
+
+/**
+ * Capitals followed by a year in a link's text (([Jane Roe, FOSDEM 2024, 18:10](https://…))): the venue of a cited talk or
+ * paper, as a reference list names one, and the link leads to it. Outside a link, a year after capitals is not read so.
+ */
+export const citedVenues = (source: string, links: readonly Span[]): Set<string> =>
+  new Set(
+    links.flatMap((link) => {
+      const text = LINK_TEXT.exec(source.slice(link.start, link.end))?.[1] ?? "";
+      return [...text.matchAll(VENUE_YEAR)].flatMap((match) => (match[1] === undefined ? [] : [match[1]]));
+    }),
+  );
+
+/** Both: the capitals a document makes known, which undefined-acronym does not ask to spell out. */
+export const knownByDocument = (source: string, links: readonly Span[]): string[] => [...codeWords(source), ...citedVenues(source, links)];

package/src/detectors/acronym-link.ts

@@ -0,0 +1,37 @@
+/**
+ * 外のページへのリンクを 1 行に 1 つ並べた一覧（参考の一覧、謝辞）の、リンクの文字。リンク先のページの題名
+ * （- [NASA Fprime AI Policy](https://…)、- [User Timing API - Web APIs | MDN](https://…)）で、書き手が展開を書き足せない。
+ * 文の中のリンク（following [NIST SP 800-61](https://…), as …）は書き手の言葉なので、略語をそのまま数える。
+ * 文書の中や手元のファイルへのリンク（[README](./README.md)）も題名ではない。
+ */
+
+type Span = { readonly start: number; readonly end: number };
+
+const EXTERNAL = /^<?https?:\/\//iu;
+const TEXT_END = "](";
+/** リンクの前に書いてよいもの: 行頭の空白と、箇条書きの印。 */
+const LINE_HEAD = /^[ \t]*(?:(?:[-*+]|\d+[.)])[ \t]+)?$/u;
+/** リンクの後ろに書いてよいもの: 行末までの空白と句読点。 */
+const LINE_TAIL = /^[ \t.,;。、]*(?:\n|$)/u;
+
+/** リンクの文字の範囲。[文字](行き先) の形で、行き先が外のページのものだけ。 */
+const externalTextOf = (source: string, link: Span): Span | undefined => {
+  const written = source.slice(link.start, link.end);
+  const end = written.lastIndexOf(TEXT_END);
+  if (!written.startsWith("[") || end === -1 || !EXTERNAL.test(written.slice(end + TEXT_END.length))) return undefined;
+  return { start: link.start + 1, end: link.start + end };
+};
+
+const standsAlone = (source: string, link: Span): boolean => {
+  const lineStart = source.lastIndexOf("\n", link.start - 1) + 1;
+  const lineEnd = source.indexOf("\n", link.end);
+  const tail = lineEnd === -1 ? source.slice(link.end) : source.slice(link.end, lineEnd + 1);
+  return LINE_HEAD.test(source.slice(lineStart, link.start)) && LINE_TAIL.test(tail);
+};
+
+/** 1 行に 1 つ並べた外のページへのリンクの、文字の範囲。位置は source の上。 */
+export const linkTitleSpans = (source: string, links: readonly Span[]): Span[] =>
+  links.flatMap((link) => {
+    const text = externalTextOf(source, link);
+    return text !== undefined && standsAlone(source, link) ? [text] : [];
+  });

package/src/detectors/acronym-name.ts

@@ -12,6 +12,8 @@ type Span = { readonly start: number; readonly end: number };
 export type NameWords = {
   /** 会社名の後ろに大文字で書く法人の形（LLC、INC、SE、PTE、PTY）。 */
   readonly legalForms: readonly string[];
+  /** 日本の会社の形（株式会社、㈱。語彙表 company-form）。すぐ隣の英字の語は会社の名前（㈱ADEKA、DOWAホールディングス㈱）。 */
+  readonly companyForms: readonly string[];
   /** 名詞の前に置く限定の語（the、this、each）。文の頭で大文字になっても（The SE team）名前の語ではない。大小を問わずに照らす。 */
   readonly determiners: readonly string[];
   /** 法令・官報の引用の大文字の部分（45 CFR §164、21 USC §301、94/820/EC）。 */
@@ -52,20 +54,40 @@ const NAME_WORDS_MAX = 5;
 /**
  * 名前の語のすぐ後ろ（読点を挟んでもよい）の法人の形と、その前の名前（JVLS, LLC、CPM Medical Consultants LLC、TRATON SE、
  * GitLab Singapore PTE. LTD.）。名前の語は空白だけで続くものを数え、読点で切れた先（CENTENE CORPORATION, MAYFLOWER …）は入れない。
- * 名前に続けて書いた括弧のすぐ後ろの形（SUNCALL（Guangzhou）CO.,LTD.）も名前の終わり。空白を挟んだ括弧（Section (A) LLC）は名前の一部ではない。形のすぐ前が限定の語なら名前ではない（The SE team）。
+ * 名前に続けて書いた括弧のすぐ後ろの形（SUNCALL（Guangzhou）CO.,LTD.、SUNCALL CO.,（H.K.）LTD.）も名前の終わり。日本語の文の中の「，」も区切り（JCI(THAILAND)CO.，LTD.）。空白を挟んだ括弧（Section (A) LLC）は名前の一部ではない。形のすぐ前が限定の語なら名前ではない（The SE team）。
  */
 export const companyNameSpans = (text: string, forms: readonly string[], determiners: readonly string[]): Span[] => {
   if (forms.length === 0) return [];
   const single = `${oneOf(forms)}${EDGE_AFTER}`;
   // 形を重ねて書く（PTE. LTD.、CO.,LTD.）。
-  const form = String.raw`${single}(?:\.?,?[ \t]*${single})*`;
-  const named = new RegExp(String.raw`${EDGE_BEFORE}(?:${NAME_WORD}[ \t]+){0,${NAME_WORDS_MAX - 1}}(?<last>${NAME_WORD})(?:,[ \t]*|[ \t]+)${form}`, "gu");
-  const bracketed = new RegExp(String.raw`(?<=${NAME_WORD}[(（][\p{L} ]+[)）][ \t]*)${form}`, "gu");
+  const form = String.raw`${single}(?:\.?[,，]?[ \t]*${single})*`;
+  const named = new RegExp(String.raw`${EDGE_BEFORE}(?:${NAME_WORD}[ \t]+){0,${NAME_WORDS_MAX - 1}}(?<last>${NAME_WORD})(?:[,，][ \t]*|[ \t]+)${form}`, "gu");
+  const bracketed = new RegExp(String.raw`(?<=${NAME_WORD}[,，]?[(（][\p{L}. ]+[)）][ \t]*)${form}`, "gu");
   const determiner = new Set(determiners.map((word) => word.toLowerCase()));
   const names = [...text.matchAll(named)].filter((match) => !determiner.has((match.groups?.["last"] ?? "").toLowerCase()));
   return [...names.map((match) => ({ start: match.index, end: match.index + match[0].length })), ...spansOf(text, bracketed)];
 };
 
+/** 日本の会社の名前の英字の語（ADEKA、DOWA）。英字の語と形のあいだに書く名前の続きの片仮名（DOWAホールディングス㈱ の ホールディングス）。 */
+const LATIN_NAME = "[A-Za-zＡ-Ｚａ-ｚ][A-Za-zＡ-Ｚａ-ｚ0-9０-９&＆]*";
+const KATAKANA_TAIL = "[ァ-ヺー・]*";
+
+/** 英字だけの形（英語の Ltd）は英字の語に続けて書かれず、続いて見えれば語の一部。漢字か片仮名を含む形だけを読む。 */
+const NOT_LATIN = /[^\p{Script=Latin}\p{P}\s]/u;
+
+/**
+ * 日本の会社の形のすぐ後ろの英字の語（㈱ADEKA、株式会社ADEKA）と、片仮名を挟んですぐ前の英字の語（ADEKA株式会社、
+ * DOWAホールディングス㈱）。名前の英字で、説明を待つ略語ではない。範囲は英字の語だけ。
+ */
+export const japaneseCompanyNameSpans = (text: string, forms: readonly string[]): Span[] => {
+  const japanese = forms.filter((form) => NOT_LATIN.test(form));
+  if (japanese.length === 0) return [];
+  const form = oneOf(japanese);
+  const after = new RegExp(`(?<=${form})${LATIN_NAME}`, "gu");
+  const before = new RegExp(`(?<![A-Za-zＡ-Ｚａ-ｚ])${LATIN_NAME}(?=${KATAKANA_TAIL}${form})`, "gu");
+  return [...spansOf(text, after), ...spansOf(text, before)];
+};
+
 /** 通貨の記号に付けた大文字（USD$、AU$10、US$ 5）。国や通貨の印で、略語ではない。 */
 const CURRENCY_PREFIX = new RegExp(String.raw`${EDGE_BEFORE}\p{Lu}{1,3}(?=[$€£¥])`, "gu");
 
@@ -108,6 +130,7 @@ export const nameSpansOf =
   (words: NameWords) =>
   (text: string): Span[] => [
     ...companyNameSpans(text, words.legalForms, words.determiners),
+    ...japaneseCompanyNameSpans(text, words.companyForms),
     ...currencySymbolSpans(text),
     ...citationSpans(text, words.citationSeries),
     ...carrierListSpans(text, words.carriers),