chaffjs 0.16.0 → 0.18.0

package/rules/unbalanced-bracket.yaml

@@ -0,0 +1,56 @@
+id: unbalanced-bracket
+layer: L1
+status: experimental
+how_to_find: unbalanced-bracket
+severity: warning
+
+name:
+  ja: 括弧が組になっていない
+  en: Unbalanced bracket
+
+why:
+  ja: 閉じ忘れた「（」や、開きの無い「」」があると、読み手はどこまでが括弧の中なのか分からなくなります。全角の「（」を半角の「)」で閉じるのも、書き換えの途中で残った印です。見出しで区切った節ごとに、「」『』（）()［］[]【】〔〕〈〉《》“” の組を数えます。詩の連や長い引用は段落をまたぐので、段落を越えて組にします。行の頭や空白の後ろの「1)」「a)」「事例）」のような三文字までの番号の印と数の後ろの「）」、コードと URL は数えません。英語の小説のように、次の段落も同じ開きで始まるなら、閉じない開きは続きとして数えません。
+  en: A "(" never closed, or a ")" never opened, leaves the reader unsure where the aside ends. A full-width "（" closed by a half-width ")" is left over from an edit too. Brackets are paired within each section under a heading ((), [], “”, and the Japanese 「」『』（）［］【】〔〕〈〉《》), across paragraphs, since a stanza or a long quotation may span several. A short label of up to three characters such as "1)", "a)" or "iv)" at the start of a line or after a space, a ")" right after a number, code and URLs are not counted. An opening quotation mark carried into a paragraph that opens with the same mark, as in fiction, is not counted.
+
+message:
+  ja: 「{mark}」が組になっていません
+  en: '"{mark}" has no partner'
+
+messages:
+  unclosed:
+    ja: 「{mark}」が閉じていません
+    en: '"{mark}" is never closed'
+  unopened:
+    ja: 「{mark}」に対応する開きがありません
+    en: '"{mark}" closes nothing that was opened'
+  mismatch:
+    ja: 「{partner}」を「{mark}」で閉じています（全角と半角が違います）
+    en: '"{partner}" is closed by "{mark}" (full-width and half-width differ)'
+
+how_to_fix:
+  ja: 足りない括弧を足すか、余分な括弧を消してください。全角と半角は、開きと閉じをそろえてください。
+  en: Add the missing bracket or remove the extra one. Make the opening and closing marks the same width.
+
+levels: { strict: error, normal: warning, relaxed: info }
+
+use_for: [business, technical, blog, legal, docs, academic, literature, speech]
+
+group: slips
+summary:
+  ja: 閉じ忘れた「（」や開きの無い「」」のように、組になっていない括弧と引用符
+  en: A bracket or quotation mark with no partner, such as a "(" that is never closed
+example:
+  ja:
+    before: |
+      資料（別紙を参照してください。
+    after: |
+      資料（別紙）を参照してください。
+  en:
+    before: |
+      The plan (see below is ready.
+    after: |
+      The plan (see below) is ready.
+
+not_flagged:
+  ja: 行の頭や空白の後ろの「1)」「a)」「事例）」のような三文字までの番号の印、数の後ろの「）」、コードと URL は数えません。段落をまたいで閉じる括弧と、次の段落を同じ引用符で始める台詞も指しません。
+  en: Labels of up to three characters such as "1)" or "a)" at the start of a line or after a space, a ")" right after a number, code and URLs are not counted. A bracket closed in a later paragraph, and a quotation carried into a paragraph that opens with the same mark, are not reported.

package/rules/undefined-acronym.yaml

@@ -13,7 +13,9 @@ extra_word_lists:
     us-state-code,
     emphasis-word,
     numbered-division,
+    abbreviated-label,
     honorific,
+    name-title,
     date-time-unit,
     http-method,
   ]
@@ -39,3 +41,24 @@ how_to_fix:
 levels: { strict: 1, normal: 3, relaxed: 6 }
 
 use_for: [business, technical, legal, docs, academic, literature, speech]
+
+group: readability
+summary:
+  ja: 「KGI」「PMF」のように、説明なしで出てくる略語
+  en: An acronym such as "KGI" or "PMF" used without ever being spelled out
+example:
+  ja:
+    config: { rules: { undefined-acronym: strict } }
+    before: 今期の KGI は、PMF の達成です。
+    after: 今期の最終目標（KGI, Key Goal Indicator）は、製品が市場に受け入れられること（PMF, Product Market Fit）です。
+  en:
+    config: { rules: { undefined-acronym: strict } }
+    before: Our KGI this term is to reach PMF.
+    after: Our key goal indicator (KGI) this term is to reach product-market fit (PMF).
+
+not_flagged:
+  ja: 誰でも知っている略語（URL、PDF など）と、前後の括弧で説明した略語は指しません。
+  en: Common acronyms (URL, PDF) and acronyms spelled out in brackets next to them are not reported.
+level_meaning:
+  ja: 説明のない略語が {limit} 種類あれば指摘
+  en: reported once {limit} different acronyms go unexplained

package/rules/unfilled-placeholder.yaml

@@ -0,0 +1,50 @@
+id: unfilled-placeholder
+layer: L2
+status: experimental
+how_to_find: unfilled-placeholder
+word_list: placeholder-word
+severity: warning
+
+name:
+  ja: 埋め忘れた空欄
+  en: Unfilled placeholder
+
+why:
+  ja: 「【会社名】」「[Your Name]」は、雛形や生成した下書きに残る空欄です。文体の好みではなく、埋め忘れです。例として置いた「○○」は正しい書き方なので数えません。
+  en: '"[Your Name]" and "[Insert Date]" are the blanks a template or a generated draft leaves. This is not a matter of style: the blank was never filled.'
+
+message:
+  ja: 「{matched}」が埋まっていません
+  en: '"{matched}" was never filled in'
+
+how_to_fix:
+  ja: 中身を書いてください。例のつもりなら、例だと分かる書き方（例：山田太郎）にしてください。
+  en: Fill it in. If it is meant as an example, say so ("for example, Jane Smith").
+
+# 指摘に要る空欄の数。
+levels: { strict: 1, normal: 1, relaxed: 2 }
+
+use_for: [blog, business, technical, legal, docs, academic, literature, speech]
+
+group: slips
+summary:
+  ja: 「【会社名】」「[Your Name]」のように、雛形の空欄が埋まらないまま残っている所
+  en: A template blank left unfilled, such as "[Your Name]" or "[Insert Date]"
+example:
+  ja:
+    before: |
+      【会社名】の田中です。見積もりをお送りします。
+    after: |
+      山田商事の田中です。見積もりをお送りします。
+  en:
+    before: |
+      We can meet on [Insert Date] to go through the quote.
+    after: |
+      We can meet on Friday 9 October to go through the quote.
+
+not_flagged:
+  ja: 例として置いた「○○」、Markdown のリンク、脚注の番号、チェック欄、値が続く見出しの札（【氏名】山田）は指しません。
+  en: 'Markdown links and reference definitions, footnote numbers, checkboxes, and a label its value follows ("[Date]: 2024-04-01") are not reported.'
+level_meaning:
+  ja: 空欄が {limit} 箇所あれば指摘
+  en: reported once there are {limit}

package/rules/unqualified-superlative.yaml

@@ -26,3 +26,22 @@ how_to_fix:
 levels: { strict: 1, normal: 2, relaxed: 4 }
 
 use_for: [business, blog, legal, docs, academic, literature, speech]
+
+group: wording
+summary:
+  ja: 「業界最速」「最高の品質」のように、何と比べたのかを書いていない最上級
+  en: A superlative such as "the fastest" with nothing to compare it against
+example:
+  ja:
+    before: 当社の新製品は業界最速で、最高の品質です。圧倒的な使いやすさです。
+    after: 当社の新製品は、従来品より処理が二割速くなりました。
+  en:
+    before: Our new product is the fastest on the market, with unmatched quality and unparalleled ease of use.
+    after: Our new product processes orders a fifth faster than the previous model.
+
+not_flagged:
+  ja: 「当社比」「〜の中で」のように、比べる相手や範囲が同じ文にあれば指しません。
+  en: A superlative with its comparison or scope in the same sentence ("in our range", "than last year") is not reported.
+level_meaning:
+  ja: 比べる相手のない最上級が {limit} 箇所あれば指摘
+  en: reported once there are {limit} such claims

package/rules/unsourced-number.yaml

@@ -38,3 +38,19 @@ levels:
   relaxed: info
 
 use_for: [business]
+
+group: facts
+summary:
+  ja: どこから来たのか確かめようのない数字（AI に読ませる検査）
+  en: A number the reader has no way to check (checked by an AI)
+example:
+  ja:
+    before: 利用者の 9 割が、この機能に満足しています。
+    after: 9 月に利用者 120 人へ聞いたアンケートでは、108 人（9 割）がこの機能に満足と答えました。
+  en:
+    before: Nine in ten users are happy with this feature.
+    after: In a survey of 120 users in September, 108 (nine in ten) said they were happy with this feature.
+
+not_flagged:
+  ja: 機械では決めません。chaff test で、機械が数字を含む文を絞り込み、その文だけを AI が読みます。
+  en: No machine decides this. chaff test narrows the text to sentences with numbers, and an AI reads only those.

package/rules/url-run-on.yaml

@@ -0,0 +1,45 @@
+id: url-run-on
+layer: L1
+status: experimental
+how_to_find: url-run-on
+severity: warning
+
+name:
+  ja: URL のすぐ後ろに字が続いている
+  en: Text runs on after a URL
+
+why:
+  ja: 「https://example.jp/をご覧ください」のように、そのまま書いた URL の直後に空白を置かずに日本語や全角の記号（。」）など）が続くと、GitHub などの自動リンクや多くのメールソフトは空白が来るまでを URL と読みます。押すと存在しないページが開きます。ASCII でない字が続くときだけを指摘します。リンクの記法（[資料](https://…) と <https://…>）で書いたものと、コードの中は数えません。
+  en: When a URL written as plain text is followed straight away by a character outside ASCII ("https://example.com/—see", "https://example.jp/をご覧ください"), GitHub's automatic links and many mail clients read everything up to the next space as the URL, and clicking it opens a page that does not exist. Only a character outside ASCII right after the URL is reported. A URL written with link syntax ([docs](https://…) or <https://…>) and URLs in code are not counted.
+
+message:
+  ja: URL「{url}」の直後に「{next}」が続いています。リンクがそこまで伸びます
+  en: 'The URL "{url}" is followed by "{next}" with no space; the link runs on into it'
+
+how_to_fix:
+  ja: URL の後ろに空白を入れるか、<https://…> または [説明](https://…) の形で書いてください。
+  en: Put a space after the URL, or write it as <https://…> or [text](https://…).
+
+levels: { strict: error, normal: warning, relaxed: info }
+
+use_for: [business, technical, blog, legal, docs, academic, literature, speech]
+
+group: slips
+summary:
+  ja: 「https://example.jp/をご覧ください」のように、URL のすぐ後ろに字が続き、リンクがそこまで伸びる所
+  en: A URL followed straight away by a character outside ASCII, which the link swallows
+example:
+  ja:
+    before: |
+      詳しくは https://example.jp/guideをご覧ください。
+    after: |
+      詳しくは https://example.jp/guide をご覧ください。
+  en:
+    before: |
+      See https://example.com/guide—it has the details.
+    after: |
+      See https://example.com/guide — it has the details.
+
+not_flagged:
+  ja: リンクの記法（[説明](URL) と <URL>）で書いた URL、コードの中、空白や ASCII の記号が続く URL、ゼロ幅の空白のような見えない字は指しません。
+  en: URLs written with link syntax ([text](URL) or <URL>), URLs in code, a URL followed by a space or an ASCII mark, and invisible characters such as a zero-width space are not reported.

package/skills/chaff/SKILL.md

@@ -61,6 +61,7 @@ relaxing a rule.
   existing one is left as it is), and adds `.chaff-cache/` and `.env*` to `.gitignore`.
 - `npx chaffjs rules --json [--genre <genre>]` prints every rule with its levels, the setting in effect (`now`,
   the genre's preset included) and why a rule is off. Read it instead of guessing rule names or limits.
+  `npx chaffjs rules` shows the same as a table, grouped, with the level each rule runs at now.
 - A level is `strict` / `normal` / `relaxed` / `off`; when even `relaxed` is too tight, a positive number is the
   limit itself (`max-sentence-length: 260`).
 - `prefer:` maps spellings to the team's (`e-mail: email`); `preferred-term: normal` turns the rule on.
@@ -68,6 +69,75 @@ relaxing a rule.
 - `genre:` sets the kind of document; `by_path` sets one per folder; `--genre` overrides both for one run.
   `rules:` wins over the genre's preset.
 
+## Turn a team's style note into chaff.yaml
+
+When the person gives house rules ("polite endings, sentences of at most 80 characters"), do not guess rule
+names or numbers:
+
+1. Read `npx chaffjs rules --json`. Each rule has `summary` (what it finds), `level_meaning` (what a level's
+   number means), `levels`, `example`, `not_flagged`, and `genres` (whether it runs in each genre).
+2. Split the note into single requirements; map each to the rule whose `summary` and `level_meaning` fit. A
+   number between levels is written as the number itself (`max-sentence-length: 80`). Spellings go under
+   `prefer`, in-house words under `jargon`, required headings under `required_sections`.
+3. Say plainly what no rule covers. For example, `no-mixed-desumasu` flags a register mixed into a document, but
+   does not require a particular one; a document wholly in the other register is not reported.
+4. Write only what differs from the default, then check before committing: `npx chaffjs explain <rule-id>`, a
+   short sample that breaks each requirement (each must be reported), and `npx chaffjs rules` (the table shows the
+   level each rule now runs at).
+
+## Adding a team rule
+
+Pick the easiest way that can say the requirement:
+
+| Requirement | Use |
+| --- | --- |
+| An existing rule covers it | A level, a number, `prefer`, `jargon` or `required_sections` in `chaff.yaml` |
+| A fixed phrase or pattern, with the team's own message | `custom_rules` of type `words` or `pattern` (coming in the next release) |
+| Decided by part of speech or inflection | `custom_rules` of type `tokens` (coming in the next release) |
+| Counting or comparing that the above cannot express | a Node function, `type: module` (a later release) |
+
+Test a new team rule the same way: `explain`, then a sample it must report and a sample it must not, before
+committing `chaff.yaml`. The guide page "Adding a rule" covers each way and how to add a rule to chaff itself.
+
+## Making AI-sounding text sound human
+
+chaff marks the shapes common in generated text (group "Signs of generated text" in `npx chaffjs rules`: `ai-tell`,
+`contrast-framing`, `stock-transition`, `announcing-opener`, `colon-lead-in` (Japanese only), `assistant-residue`, and the signals
+`ai-generated-composite` reads). Most are experimental: run with `--experimental`. None of them says the text was
+generated. When asked to make a text sound less generated, pick one of two modes and say which.
+
+**Light** (only the flagged spots), when the content and structure are fine:
+
+1. `npx chaffjs <file> --experimental` (or with the genre's `--genre`); collect the AI-shape findings.
+2. Rewrite only those spots. Keep the meaning, numbers, conditions and technical constraints.
+3. Run chaff again. At most two rewrite passes.
+4. Show the rewritten text and a short list of what changed and why.
+
+**Bold** (section by section), when a light pass still leaves it reading as generated:
+
+1. Run chaff with `--experimental` and note the document-level signals: the `ai-generated-composite` inputs,
+   `bold-density`, `contrast-framing`, `stock-transition`, `sentence-rhythm`.
+2. Rewrite each section toward a human voice: less bold; one-line paragraphs and punchlines folded back into
+   paragraphs; no "X ではありません。Y です" / "It's not X. It's Y" frames; lists turned back into sentences where the
+   items connect; fewer em dashes; no announcing openers. Each paragraph carries one claim, joined to the last by a
+   connective, built around the writer's own experience or numbers where the original has them.
+3. Run chaff again and report the same signals before and after, from chaff's output.
+4. Run `npx chaffjs compare <old> <new>` (exit 1 on a dropped or added fact; `--json` to act on it). Restore every
+   dropped fact; for one that is not a fact (a number inside a metaphor, the heading of a section you cut), say why it
+   stays out. `--allow-dropped <kind>` excludes a kind you cut on purpose. Never leave an added fact.
+
+In both modes:
+
+- Never add facts, people, numbers or causes the original does not have.
+- Keep a domain term a word rule trips when it is right in context.
+- Prefer a direct statement over a negated contrast. Say who does what.
+- Never loop just to silence a warning; two passes at most, and list what is left with the reason.
+- Per genre: in a tech article, replace metaphors ("静かに壊れる", "silently fails") with what happens and keep steps
+  and commands as lists; in a business document, put the conclusion and who does what first and keep tables and
+  figures; in an essay, fold punchlines back in and replace big words ("真理", "new possibilities") with the scene.
+
+The guide page "Making AI-sounding text sound human" has a worked example with chaff's output before and after.
+
 ## Structured documents
 
 - `npx chaffjs tree <file>` shows a contract or specification as a tree of addresses (`3.2` for 第3条第2項 or

package/src/announced-count.ts

@@ -0,0 +1,148 @@
+import { escapeRegExp } from "./orthography.ts";
+import type { BulletList, Span } from "./plugin.ts";
+import { joined, linesAbove, type TextBlock } from "./text-above.ts";
+
+/**
+ * 箇条書きのすぐ前の文が予告した数（以下の3点、the following three steps）と、箇条書きのいちばん外側の項目の数。
+ * 予告と読むのは、文の最後の一文に数がちょうど一つあり、先を指す語がその前にあるか文がコロンで終わるときだけ。
+ * 言語の知識（先を指す語、漢数字や数の語、数える語、数を目安や順番にする語）は語彙表から受け取る。
+ */
+export type CountWords = {
+  /** 以下の、次の、following。 */
+  readonly anchors: readonly string[];
+  /** 数を字で書いたもの。一から順に並べる。 */
+  readonly numbers: readonly string[];
+  /** 数のすぐ後ろで並べるものを数える語。点、つ、steps。 */
+  readonly counters: readonly string[];
+  /** 数のすぐ前にあると予告でなくなる語（約、第、at least）。 */
+  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[];
+};
+
+export type CountMismatch = { readonly offset: number; readonly phrase: string; readonly announced: number; readonly listed: number };
+
+/** counted: 数える語が付いている（3点）。付いていない数（the following two:）は、先を指す語のすぐ後ろでだけ予告に読む。 */
+type Phrase = { readonly start: number; readonly numberEnd: number; readonly end: number; readonly announced: number; readonly counted: boolean };
+
+/** 予告の文の外側。見出し、表、引用、コードの囲みの行は、すぐ下の箇条書きを予告する文ではない。 */
+const NOT_A_LEAD = /^[ \t]*(?:#|\||>|```|~~~)/u;
+
+/** 箇条書きのすぐ前の塊。見出し・表・引用・コードの囲みなら undefined。 */
+const leadBefore = (source: string, listStart: number): TextBlock | undefined => {
+  const lines = linesAbove(source, listStart);
+  return lines.some((line) => NOT_A_LEAD.test(line.text)) ? undefined : joined(source, lines);
+};
+
+/** 文の終わり。英語の「.」は後ろが空白のときだけ（3.5 や e.g. の途中で切らない）。 */
+const SENTENCE_END = /[。！？!?]|\.(?=\s)/gu;
+
+/** 塊の最後の一文の始まり（塊の中の位置）。 */
+const lastSentenceStart = (text: string): number => {
+  const body = text.trimEnd();
+  const ends = [...body.matchAll(SENTENCE_END)].map((match) => match.index + match[0].length).filter((end) => end < body.length);
+  return ends.at(-1) ?? 0;
+};
+
+const alternation = (words: readonly string[]): string =>
+  words
+    .toSorted((a, b) => b.length - a.length)
+    .map(escapeRegExp)
+    .join("|");
+
+/**
+ * 数と、それが数えるもの。数の前が数字・英字・数の字なら数の途中（十三、23、eleven の中）。
+ * 英語は数と数える語の間に語を二つまで置ける（three key steps）。数える語が無くても、文がコロンで終わる直前の数（the following two:）は数に読む。
+ */
+const phrasePattern = (words: CountWords): RegExp => {
+  const numberChars = escapeRegExp([...new Set(words.numbers.join(""))].join(""));
+  const numbers = words.numbers.length === 0 ? "\\p{Nd}+" : `\\p{Nd}+|${alternation(words.numbers)}`;
+  const counted = `[ \\t\\u00a0]?(?:\\p{Ll}[\\p{Ll}-]*[ \\t]){0,2}(${alternation(words.counters)})(?![A-Za-z])`;
+  return new RegExp(`(?<![\\p{N}A-Za-z${numberChars}])(${numbers})(?:${counted}|(?=[ \\t]?[:：][ \\t]*$))`, "giu");
+};
+
+const valueOf = (written: string, numbers: readonly string[]): number => {
+  const digits = Number(written.normalize("NFKC"));
+  if (!Number.isNaN(digits)) return digits;
+  return numbers.findIndex((number) => number.toLowerCase() === written.toLowerCase()) + 1;
+};
+
+const LATIN_LETTER = /[A-Za-z]/u;
+const isLatin = (char: string | undefined): boolean => LATIN_LETTER.test(char ?? "");
+
+/** 英語の語は語の切れ目で照らす（over が moreover に当たらない）。日本語の語は字面どおり。 */
+const endsWithWord = (text: string, word: string): boolean => text.endsWith(word) && !(isLatin(word[0]) && isLatin(text.at(-word.length - 1)));
+
+const startsWithWord = (text: string, word: string): boolean => text.startsWith(word) && !(isLatin(word.at(-1)) && isLatin(text[word.length]));
+
+const isHedged = (sentence: string, phrase: Phrase, words: CountWords): boolean => {
+  const before = sentence.slice(0, phrase.start).trimEnd().toLowerCase();
+  const afters = [sentence.slice(phrase.numberEnd), sentence.slice(phrase.end)].map((text) => text.trimStart().toLowerCase());
+  return (
+    words.hedgesBefore.some((hedge) => endsWithWord(before, hedge.toLowerCase())) ||
+    words.hedgesAfter.some((hedge) => afters.some((after) => startsWithWord(after, hedge.toLowerCase())))
+  );
+};
+
+const COLON_END = /[:：][ \t]*$/u;
+
+/** 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。 */
+const pointsAhead = (sentence: string, phrase: Phrase, anchors: readonly string[]): boolean => {
+  const before = sentence.slice(0, phrase.start).toLowerCase();
+  const lowered = anchors.map((anchor) => anchor.toLowerCase());
+  if (!phrase.counted) return lowered.some((anchor) => endsWithWord(before.trimEnd(), anchor));
+  return COLON_END.test(sentence.trimEnd()) || lowered.some((anchor) => before.includes(anchor));
+};
+
+/** 最後の一文の予告。数がちょうど一つで、目安や順番でなく、先を指しているときだけ。 */
+const announcedIn = (sentence: string, words: CountWords, pattern: RegExp): Phrase | undefined => {
+  const phrases = [...sentence.matchAll(pattern)].map((match) => ({
+    start: match.index,
+    numberEnd: match.index + (match[1] ?? "").length,
+    end: match.index + match[0].length,
+    announced: valueOf(match[1] ?? "", words.numbers),
+    counted: match[2] !== undefined,
+  }));
+  const only = phrases.length === 1 ? phrases[0] : undefined;
+  if (only === undefined || only.announced < 1 || isHedged(sentence, only, words)) return undefined;
+  return pointsAhead(sentence, only, words.anchors) ? only : undefined;
+};
+
+/** 位置から空白と改行を読み飛ばした先。 */
+const pastSpace = (source: string, at: number): number => {
+  const filled = /[^ \t\r\n]/gu;
+  filled.lastIndex = at;
+  return filled.exec(source)?.index ?? source.length;
+};
+
+/** 箇条書きの終わり（後ろの空白を読み飛ばした先）と始まり。空白だけを挟んで続く二つの箇条書きは、終わりと始まりが同じ位置になる。 */
+type Neighbours = { readonly ends: ReadonlySet<number>; readonly starts: ReadonlySet<number> };
+
+const neighboursOf = (source: string, lists: readonly BulletList[]): Neighbours => ({
+  ends: new Set(lists.map((list) => pastSpace(source, list.span.end))),
+  starts: new Set(lists.map((list) => list.span.start)),
+});
+
+/** 空白だけを挟んで前か後ろに別の箇条書きが続く。印が変わって二つに割れた一つの並びかもしれず、数を決められない。 */
+const hasNeighbour = (source: string, list: Span, neighbours: Neighbours): boolean =>
+  neighbours.ends.has(list.start) || neighbours.starts.has(pastSpace(source, list.end));
+
+type Context = { readonly source: string; readonly words: CountWords; readonly pattern: RegExp; readonly neighbours: Neighbours };
+
+const mismatchOf = ({ source, words, pattern, 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, pattern);
+  if (phrase === undefined || phrase.announced === list.items.length) 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 }];
+};
+
+export const announcedCountMismatches = (source: string, lists: readonly BulletList[], words: CountWords): CountMismatch[] => {
+  if (words.counters.length === 0) return [];
+  const context = { source, words, pattern: phrasePattern(words), neighbours: neighboursOf(source, lists) };
+  return lists.flatMap((list) => mismatchOf(context, list));
+};

package/src/bare-url.ts

@@ -0,0 +1,35 @@
+import type { Span } from "./plugin.ts";
+
+/**
+ * `https://…` をそのまま書いた URL。GFM の autolink 拡張を入れていないので mdast では
+ * ただのテキストになり、本文として残る。残すと、見出しと URL の中の識別子が一致して
+ * 「見出しの繰り返し」と読まれる。表示される文字も本文ではない。
+ * 空白が来るまでを取るので、URL の直後に続けた日本語（「https://example.jp/をご覧ください」の「をご覧ください」）も入る。
+ */
+export const BARE_URL = /https?:\/\/[^\s)<>"'\]]+/gu;
+
+/** 文の終わりの句読点。URL の最後の字としてはまず書かれず、URL の後ろの文の字。 */
+const PUNCTUATION: ReadonlySet<string> = new Set([".", ",", ";", ":", "!", "?"]);
+
+/**
+ * そのまま書いた URL に続けた文の始まり: ひらがなと全角の句読点・括弧（「…/をご覧ください」「…/。」）。
+ * 漢字やカタカナは道の名前（/東京、/カタログ）にもなるので切らない。
+ */
+const SENTENCE_AFTER = /[\p{Script=Hiragana}\u3000-\u303f\uff01-\uff0f\uff1a-\uff20]/u;
+
+/** URL として読む長さ。続けた文の手前で切り、後ろの句読点を外す。正規表現の `[…]+$` は句読点の長い並びで後戻りが二乗になる。 */
+const urlLength = (written: string): number => {
+  const cut = SENTENCE_AFTER.exec(written)?.index ?? written.length;
+  let end = cut;
+  while (end > 0 && PUNCTUATION.has(written.charAt(end - 1))) end -= 1;
+  return end;
+};
+
+export type BareUrl = Span & { readonly url: string };
+
+/** text の中の、そのまま書いた URL。続けて書いた日本語と文末の句読点は外す。位置は text の先頭を 0 とする。 */
+export const bareUrls = (text: string): BareUrl[] =>
+  [...text.matchAll(BARE_URL)].map((match) => {
+    const url = match[0].slice(0, urlLength(match[0]));
+    return { start: match.index, end: match.index + url.length, url };
+  });

package/src/baseline.ts

@@ -13,6 +13,21 @@ export const fingerprint = (path: string, finding: Finding): string => {
   return createHash("sha256").update(body).digest("hex").slice(0, 16);
 };
 
+/**
+ * findings の fingerprint を順に。一つの文から出た指摘は同じ文を引くので、文と rule の組ごとに一度だけ計算する。
+ * 長い文に指摘が多いと、指摘ごとに文を読み直すのでは指摘数と文の長さの積になる。
+ */
+export const fingerprints = (path: string, findings: readonly Finding[]): string[] => {
+  const known = new Map<string, Map<string, string>>();
+  return findings.map((finding) => {
+    const byRule = known.get(finding.quote) ?? new Map<string, string>();
+    known.set(finding.quote, byRule);
+    const found = byRule.get(finding.rule) ?? fingerprint(path, finding);
+    byRule.set(finding.rule, found);
+    return found;
+  });
+};
+
 export type Baseline = { readonly version: 1; readonly created: string; readonly entries: readonly string[] };
 
 const isBaseline = (value: unknown): value is Baseline =>
@@ -40,7 +55,8 @@ export type Split = { readonly fresh: readonly Finding[]; readonly shelved: numb
 export const splitByBaseline = (path: string, findings: readonly Finding[], baseline: Baseline | undefined): Split => {
   if (baseline === undefined) return { fresh: findings, shelved: 0 };
   const known = new Set(baseline.entries);
-  const fresh = findings.filter((finding) => !known.has(fingerprint(path, finding)));
+  const prints = fingerprints(path, findings);
+  const fresh = findings.filter((_, index) => !known.has(prints[index] ?? ""));
   return { fresh, shelved: findings.length - fresh.length };
 };
 

package/src/body-section.ts

@@ -0,0 +1,7 @@
+import type { Section } from "./plugin.ts";
+
+/**
+ * 本題の始まり: 最初の中見出し（深さ 2 以上）の節。表題（深さ 1）の直後から数えると、表題しか無い文書で全文が前置きになる。
+ * 無ければ、本題の前を測る rule は動けない（rule の requires の headings）。
+ */
+export const bodySectionOf = (sections: readonly Section[]): Section | undefined => sections.find((section) => section.depth >= 2);

package/src/calendar-number.ts

@@ -1,5 +1,5 @@
 import { digitRunAround } from "./number-name.ts";
-import type { Span, Token } from "./plugin.ts";
+import type { ProseDocument, Span, Token } from "./plugin.ts";
 
 /**
  * 日付・時刻として書かれた数（9月、3時、2026年、10月1日、10時5分）。数を詰めて書くのが決まりで、空け方の好みではない。
@@ -8,21 +8,27 @@ import type { Span, Token } from "./plugin.ts";
  * 単位は語彙表から渡す。chained は日付・時刻の単位を大きい順に（年月日時分秒）。大きい単位の後ろに小さい単位を続けて書けば
  * 一つの日付・時刻になる。「2008年 2年連続」のように同じ単位や大きい単位が続けば、別のものの始まり。
  * positional は数の後ろに置くだけで位置を言う単位（月、時）。year は 4 桁の数の後ろで暦の年を言う単位（年、年度）。
+ * era は元号（令和）。元号のすぐ後ろ（空白 1 つまで）の数は、単位が何でも暦の上の位置を言う（令和8年、桁が少なくても年数ではない）。
  * 「5日」「5分」「3年」のように、単位だけでは長さと見分けのつかないものは、位置を言う単位と続けて書いたときだけ日付・時刻と読む。
  */
-export type CalendarUnits = { readonly chained: readonly string[]; readonly positional: ReadonlySet<string>; readonly year: ReadonlySet<string> };
+export type CalendarUnits = {
+  readonly chained: readonly string[];
+  readonly positional: ReadonlySet<string>;
+  readonly year: ReadonlySet<string>;
+  readonly era: readonly string[];
+};
 
-/** 日付・時刻の数の並び。first は日付の頭の数、inner は前の単位に続く数（2026年9月の 9）。 */
-export type CalendarRun = { readonly run: Span; readonly place: "first" | "inner" };
+/** 日付・時刻の数の並び。first は日付の頭の数、inner は前の単位に続く数（2026年9月の 9）。unit は数の後ろの単位（月）。 */
+export type CalendarRun = { readonly run: Span; readonly place: "first" | "inner"; readonly unit: string };
 
 /** 数の並びと、その後ろの単位の終わり（文の中の位置）。rank は chained の中の単位の順（無ければ -1）、anchored は単位だけで日付・時刻と分かるもの。 */
-type Part = { readonly run: Span; readonly unitEnd: number; readonly rank: number; readonly anchored: boolean };
+type Part = { readonly run: Span; readonly unit: string; readonly unitEnd: number; readonly rank: number; readonly anchored: boolean };
 
 const DIGIT = /\d/u;
 const CALENDAR_YEAR = /^\d{4}$/u;
 
 /** text の中の数の並び（数字・小数点・ハイフン）を左から。 */
-const digitRuns = (text: string): Span[] => {
+export const digitRuns = (text: string): Span[] => {
   const runs: Span[] = [];
   let at = 0;
   while (at < text.length) {
@@ -38,15 +44,22 @@ const pastSpace = (text: string, at: number): number => (text[at] === " " ? at +
 
 const isUnit = (surface: string, units: CalendarUnits): boolean => units.chained.includes(surface) || units.positional.has(surface) || units.year.has(surface);
 
-const isAnchor = (digits: string, surface: string, units: CalendarUnits): boolean =>
-  units.positional.has(surface) || (units.year.has(surface) && CALENDAR_YEAR.test(digits));
+/** 数 run のすぐ前（空白 1 つまで）が元号か。 */
+const followsEra = (text: string, run: Span, units: CalendarUnits): boolean => {
+  const before = text.slice(0, run.start);
+  const written = before.endsWith(" ") ? before.slice(0, -1) : before;
+  return units.era.some((era) => written.endsWith(era));
+};
+
+const isAnchor = (text: string, run: Span, surface: string, units: CalendarUnits): boolean =>
+  units.positional.has(surface) || (units.year.has(surface) && CALENDAR_YEAR.test(text.slice(run.start, run.end))) || followsEra(text, run, units);
 
 /** 数のすぐ後ろ（空白 1 つまで）の語が日付・時刻の単位なら、その組。語の切れ目が合わなければ組にしない。 */
 const partOf = (text: string, run: Span, tokens: readonly Token[], base: number, units: CalendarUnits): Part | undefined => {
   const unit = tokens.find((token) => token.span.start === base + pastSpace(text, run.end));
   if (unit === undefined || !isUnit(unit.surface, units)) return undefined;
   const rank = units.chained.indexOf(unit.surface);
-  return { run, unitEnd: unit.span.end - base, rank, anchored: isAnchor(text.slice(run.start, run.end), unit.surface, units) };
+  return { run, unit: unit.surface, unitEnd: unit.span.end - base, rank, anchored: isAnchor(text, run, unit.surface, units) };
 };
 
 /** 前の組の単位のすぐ後ろ（空白 1 つまで）から始まり、単位が前より小さい組か。 */
@@ -71,5 +84,15 @@ export const calendarRuns = (text: string, tokens: readonly Token[] | undefined,
   const parts = digitRuns(text).flatMap((run) => partOf(text, run, tokens, base, units) ?? []);
   return chainsOf(text, parts)
     .filter((chain) => chain.some((part) => part.anchored))
-    .flatMap((chain) => chain.map((part, index): CalendarRun => ({ run: part.run, place: index === 0 ? "first" : "inner" })));
+    .flatMap((chain) => chain.map((part, index): CalendarRun => ({ run: part.run, place: index === 0 ? "first" : "inner", unit: part.unit })));
 };
+
+const patternList = (doc: ProseDocument, id: string): string[] => (doc.lexicons[id] ?? []).map((entry) => entry.pattern);
+
+/** 文書の言語の、日付・時刻の単位の語彙表。表の無い言語では空で、日付・時刻の数は見つからない。 */
+export const calendarUnitsOf = (doc: ProseDocument): CalendarUnits => ({
+  chained: patternList(doc, "date-time-unit"),
+  positional: new Set(patternList(doc, "calendar-unit")),
+  year: new Set(patternList(doc, "calendar-year-unit")),
+  era: patternList(doc, "calendar-era"),
+});

package/src/cli-args.ts

@@ -7,3 +7,9 @@ const VALUE_FLAGS: ReadonlySet<string> = new Set(["--sarif", "--genre", "--rule"
 /** The arguments that name what to check: everything that is neither an option nor an option's value. */
 export const targetsOf = (args: readonly string[]): string[] =>
   args.filter((arg, index) => !arg.startsWith("--") && !(index > 0 && VALUE_FLAGS.has(args[index - 1] ?? "")));
+
+/** The settings with --experimental applied: the command line turns experimental rules on as chaff.yaml can. */
+export const withExperimental = <T extends { readonly experimental: boolean }>(config: T, args: readonly string[]): T => ({
+  ...config,
+  experimental: config.experimental || args.includes("--experimental"),
+});