chaffjs 0.28.0 → 0.30.0

package/dist/inline-count.js

@@ -0,0 +1,109 @@
+import { escapeRegExp } from "./orthography.js";
+import { alternation, valueOf } from "./announced-count.js";
+const MAX_LABEL_CHARS = 30;
+const MAX_MEMBER_CHARS = 40;
+const MIN_MEMBERS = 2;
+/** 一行に並べる名前の数として読む上限。括弧の年（Holland (1993): ...）を数に読まない。 */
+const MAX_ANNOUNCED = 99;
+/**
+ * 行頭（箇条書きの印の後ろでもよい）のラベル、括弧の中の数（数える語は付いても付かなくてもよい）、コロン。
+ * 括弧の中に数以外の語があるもの（約6名、6名以上、5名ほか）は形が合わず、ここで外れる。
+ */
+const headPattern = (words) => {
+    const numbers = words.numbers.length === 0 ? "\\p{Nd}+" : `\\p{Nd}+|${alternation(words.numbers)}`;
+    const counter = words.counters.length === 0 ? "" : `(?:[ \\t]?(?<counter>${alternation(words.counters)})(?![A-Za-z]))?`;
+    const label = `(?<label>[^\\s\\p{Nd}(（:：|>#*+-][^(（:：\\n]{0,${MAX_LABEL_CHARS}})`;
+    const listMark = String.raw `(?:(?:[-*+]|\d{1,9}[.)])[ \t]+)?`;
+    return new RegExp(`^[ \\t]*${listMark}${label}[(（][ \\t]*(?<phrase>(?<number>${numbers})${counter})[ \\t]*[)）][ \\t]*[:：][ \\t]*`, "diu");
+};
+const LATIN_LETTER = /[A-Za-z]/u;
+/** 英語の語は語の切れ目で照らす（and が Anderson に当たらない）。日本語の語は字面どおり。atEnd なら末尾の語だけ。 */
+const wordPattern = (word, atEnd = false) => {
+    const before = LATIN_LETTER.test(word[0] ?? "") ? "(?<![A-Za-z])" : "";
+    const after = LATIN_LETTER.test(word.at(-1) ?? "") ? "(?![A-Za-z])" : "";
+    return new RegExp(`${before}${escapeRegExp(word)}${after}${atEnd ? "\\s*$" : ""}`, "iu");
+};
+const BRACKETED = /\([^()（）]*\)|（[^()（）]*）|「[^「」]*」|\[[^[\]]*\]/gu;
+const BRACKET = /[()（）「」[\]]/u;
+/** 並びの途中で文が切れる、別のラベルが始まる。名前の並びでなく文なので数えない。 */
+const NOT_A_NAME_LIST = /[。．.:：;；]/u;
+const TRAILING_END = /[。．.]\s*$/u;
+/** 括弧の中の注記（議長）を除いた並び。括弧が閉じていなければ undefined。 */
+const withoutNotes = (members) => {
+    const stripped = members.replace(BRACKETED, "");
+    return BRACKET.test(stripped) ? undefined : stripped;
+};
+const hasAny = (text, words) => words.some((word) => wordPattern(word).test(text));
+/** 閉じていないことを言う語は名前の後ろに付く（田中ほか、etc）。名前の中の字（等々力）は数える。 */
+const endsOpen = (member, open) => open.some((word) => wordPattern(word, true).test(member));
+/** 最後の名前の前のつなぐ語（, and Ito）は並びの終わりの印で、名前の一部ではない。 */
+const withoutLeadingJoiner = (member, joiners) => {
+    const leading = joiners.find((joiner) => new RegExp(`^${escapeRegExp(joiner)}\\s+`, "iu").test(member));
+    return leading === undefined ? member : member.slice(leading.length).trimStart();
+};
+const splitMembers = (text, separators) => text.split(new RegExp(separators.map(escapeRegExp).join("|"), "u")).map((part) => part.trim());
+const withLastJoinerOff = (parts, joiners) => {
+    const last = parts.at(-1);
+    return last === undefined ? [...parts] : [...parts.slice(0, -1), withoutLeadingJoiner(last, joiners)];
+};
+const isNameLike = (member, words) => member !== "" && member.length <= MAX_MEMBER_CHARS && !hasAny(member, words.joiners);
+/** 区切って並べた名前の数。並びとして読めないときは undefined。 */
+export const memberCount = (members, words) => {
+    if (words.separators.length === 0)
+        return undefined;
+    const notes = withoutNotes(members.trim().replace(TRAILING_END, ""));
+    if (notes === undefined || NOT_A_NAME_LIST.test(notes))
+        return undefined;
+    const parts = splitMembers(notes, words.separators);
+    if (parts.some((part) => endsOpen(part, words.open)))
+        return undefined;
+    const names = withLastJoinerOff(parts, words.joiners);
+    return names.length >= MIN_MEMBERS && names.every((name) => isNameLike(name, words)) ? names.length : undefined;
+};
+/** 次の行に並びが続いてよい行。空行、箇条書き、見出し、引用、表の行は別のもの。 */
+const CONTINUATION = /^[ \t]*[^\s\-*+#>|]/u;
+const endsWithSeparator = (text, words) => words.separators.some((separator) => text.trimEnd().endsWith(separator));
+/** 区切りで終わる行は、次の行に並びが続く。 */
+const membersFrom = (lines, next, soFar, words) => {
+    const line = lines[next] ?? "";
+    return endsWithSeparator(soFar, words) && CONTINUATION.test(line) ? membersFrom(lines, next + 1, soFar + line, words) : soFar;
+};
+/**
+ * ラベルは短い名前（出席者、Attendees）。区切りを含むもの（Dunn, G.E. (1960):）は文献の著者で、番号で終わるもの（Step 2 (3):）は
+ * 番号の付いた項目。どちらも括弧の数は並べた名前の数ではない。
+ */
+const isLabel = (label, members) => !/\p{Nd}\s*$/u.test(label) && !members.separators.some((separator) => label.includes(separator));
+/** 数える語の無い数（Attendees (6)）は、ラベル自身が数えるもの（attendees、items）を言うときだけ数。Appendix (3) は番号。 */
+const labelCounts = (label, counters) => counters.some((counter) => wordPattern(counter, true).test(label));
+const linesOf = (text) => {
+    const starts = [0, ...[...text.matchAll(/\n/gu)].map((match) => match.index + 1)];
+    return text.split("\n").map((line, index) => ({ text: line, start: starts[index] ?? 0 }));
+};
+/** 数える語が数に付いているか、ラベルが数えるものを言っている（Attendees (6)）ときだけ、括弧の数を名前の数に読む。 */
+const isCount = (announced, counter, label, words) => (counter !== undefined || labelCounts(label, words.counters)) && announced >= 1 && announced <= MAX_ANNOUNCED;
+const headOf = (text, head, words, members) => {
+    const match = head.exec(text);
+    const groups = match?.groups;
+    const phraseAt = match?.indices?.groups?.["phrase"]?.[0];
+    const label = groups?.["label"] ?? "";
+    if (match === null || groups === undefined || phraseAt === undefined || !isLabel(label, members))
+        return undefined;
+    const announced = valueOf(groups["number"] ?? "", words.numbers);
+    if (!isCount(announced, groups["counter"], label, words))
+        return undefined;
+    return { phrase: (groups["phrase"] ?? "").trim(), phraseAt, announced, rest: text.slice(match[0].length) };
+};
+/** 本文（コードや強調の印を空白で覆ったもの）の、一行に並べた名前の予告で、数が合わないもの。 */
+export const inlineCountMismatches = (text, words, members) => {
+    const head = headPattern(words);
+    const lines = linesOf(text);
+    const texts = lines.map((line) => line.text);
+    return lines.flatMap((line, index) => {
+        const found = headOf(line.text, head, words, members);
+        const listed = found === undefined ? undefined : memberCount(membersFrom(texts, index + 1, found.rest, members), members);
+        if (found === undefined || listed === undefined || listed === found.announced)
+            return [];
+        return [{ offset: line.start + found.phraseAt, phrase: found.phrase, announced: found.announced, listed }];
+    });
+};
+//# sourceMappingURL=inline-count.js.map

package/dist/inline-count.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"inline-count.js","sourceRoot":"","sources":["../src/inline-count.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,kBAAkB,CAAC;AAChD,OAAO,EAAE,WAAW,EAAE,OAAO,EAAuC,MAAM,sBAAsB,CAAC;AAgBjG,MAAM,eAAe,GAAG,EAAE,CAAC;AAC3B,MAAM,gBAAgB,GAAG,EAAE,CAAC;AAC5B,MAAM,WAAW,GAAG,CAAC,CAAC;AACtB,0DAA0D;AAC1D,MAAM,aAAa,GAAG,EAAE,CAAC;AAEzB;;;GAGG;AACH,MAAM,WAAW,GAAG,CAAC,KAAiB,EAAU,EAAE;IAChD,MAAM,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,YAAY,WAAW,CAAC,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;IACnG,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,wBAAwB,WAAW,CAAC,KAAK,CAAC,QAAQ,CAAC,iBAAiB,CAAC;IACxH,MAAM,KAAK,GAAG,gDAAgD,eAAe,IAAI,CAAC;IAClF,MAAM,QAAQ,GAAG,MAAM,CAAC,GAAG,CAAA,kCAAkC,CAAC;IAC9D,OAAO,IAAI,MAAM,CAAC,WAAW,QAAQ,GAAG,KAAK,kCAAkC,OAAO,IAAI,OAAO,gCAAgC,EAAE,KAAK,CAAC,CAAC;AAC5I,CAAC,CAAC;AAEF,MAAM,YAAY,GAAG,WAAW,CAAC;AAEjC,wEAAwE;AACxE,MAAM,WAAW,GAAG,CAAC,IAAY,EAAE,KAAK,GAAG,KAAK,EAAU,EAAE;IAC1D,MAAM,MAAM,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,EAAE,CAAC;IACvE,MAAM,KAAK,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;IACzE,OAAO,IAAI,MAAM,CAAC,GAAG,MAAM,GAAG,YAAY,CAAC,IAAI,CAAC,GAAG,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,IAAI,CAAC,CAAC;AAC3F,CAAC,CAAC;AAEF,MAAM,SAAS,GAAG,gDAAgD,CAAC;AACnE,MAAM,OAAO,GAAG,cAAc,CAAC;AAC/B,8CAA8C;AAC9C,MAAM,eAAe,GAAG,YAAY,CAAC;AACrC,MAAM,YAAY,GAAG,YAAY,CAAC;AAElC,+CAA+C;AAC/C,MAAM,YAAY,GAAG,CAAC,OAAe,EAAsB,EAAE;IAC3D,MAAM,QAAQ,GAAG,OAAO,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;IAChD,OAAO,OAAO,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC;AACvD,CAAC,CAAC;AAEF,MAAM,MAAM,GAAG,CAAC,IAAY,EAAE,KAAwB,EAAW,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;AAEvH,uDAAuD;AACvD,MAAM,QAAQ,GAAG,CAAC,MAAc,EAAE,IAAuB,EAAW,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,WAAW,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;AAEjI,mDAAmD;AACnD,MAAM,oBAAoB,GAAG,CAAC,MAAc,EAAE,OAA0B,EAAU,EAAE;IAClF,MAAM,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,IAAI,MAAM,CAAC,IAAI,YAAY,CAAC,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;IACxG,OAAO,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,SAAS,EAAE,CAAC;AACnF,CAAC,CAAC;AAEF,MAAM,YAAY,GAAG,CAAC,IAAY,EAAE,UAA6B,EAAY,EAAE,CAC7E,IAAI,CAAC,KAAK,CAAC,IAAI,MAAM,CAAC,UAAU,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;AAEjG,MAAM,iBAAiB,GAAG,CAAC,KAAwB,EAAE,OAA0B,EAAY,EAAE;IAC3F,MAAM,IAAI,GAAG,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAC1B,OAAO,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,oBAAoB,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,CAAC;AACxG,CAAC,CAAC;AAEF,MAAM,UAAU,GAAG,CAAC,MAAc,EAAE,KAAkB,EAAW,EAAE,CAAC,MAAM,KAAK,EAAE,IAAI,MAAM,CAAC,MAAM,IAAI,gBAAgB,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;AAEzJ,0CAA0C;AAC1C,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC,OAAe,EAAE,KAAkB,EAAsB,EAAE;IACrF,IAAI,KAAK,CAAC,UAAU,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,SAAS,CAAC;IACpD,MAAM,KAAK,GAAG,YAAY,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,OAAO,CAAC,YAAY,EAAE,EAAE,CAAC,CAAC,CAAC;IACrE,IAAI,KAAK,KAAK,SAAS,IAAI,eAAe,CAAC,IAAI,CAAC,KAAK,CAAC;QAAE,OAAO,SAAS,CAAC;IACzE,MAAM,KAAK,GAAG,YAAY,CAAC,KAAK,EAAE,KAAK,CAAC,UAAU,CAAC,CAAC;IACpD,IAAI,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,QAAQ,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IACvE,MAAM,KAAK,GAAG,iBAAiB,CAAC,KAAK,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;IACtD,OAAO,KAAK,CAAC,MAAM,IAAI,WAAW,IAAI,KAAK,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC;AAClH,CAAC,CAAC;AAEF,6CAA6C;AAC7C,MAAM,YAAY,GAAG,sBAAsB,CAAC;AAE5C,MAAM,iBAAiB,GAAG,CAAC,IAAY,EAAE,KAAkB,EAAW,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC,CAAC;AAElJ,2BAA2B;AAC3B,MAAM,WAAW,GAAG,CAAC,KAAwB,EAAE,IAAY,EAAE,KAAa,EAAE,KAAkB,EAAU,EAAE;IACxG,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;IAC/B,OAAO,iBAAiB,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,KAAK,EAAE,IAAI,GAAG,CAAC,EAAE,KAAK,GAAG,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC;AAChI,CAAC,CAAC;AAEF;;;GAGG;AACH,MAAM,OAAO,GAAG,CAAC,KAAa,EAAE,OAAoB,EAAW,EAAE,CAC/D,CAAC,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC,CAAC;AAEnG,sFAAsF;AACtF,MAAM,WAAW,GAAG,CAAC,KAAa,EAAE,QAA2B,EAAW,EAAE,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,WAAW,CAAC,OAAO,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC;AAIhJ,MAAM,OAAO,GAAG,CAAC,IAAY,EAAU,EAAE;IACvC,MAAM,MAAM,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC;IAClF,OAAO,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;AAC5F,CAAC,CAAC;AAKF,qEAAqE;AACrE,MAAM,OAAO,GAAG,CAAC,SAAiB,EAAE,OAA2B,EAAE,KAAa,EAAE,KAAiB,EAAW,EAAE,CAC5G,CAAC,OAAO,KAAK,SAAS,IAAI,WAAW,CAAC,KAAK,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,SAAS,IAAI,CAAC,IAAI,SAAS,IAAI,aAAa,CAAC;AAEhH,MAAM,MAAM,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,KAAiB,EAAE,OAAoB,EAAoB,EAAE;IACvG,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC9B,MAAM,MAAM,GAAG,KAAK,EAAE,MAAM,CAAC;IAC7B,MAAM,QAAQ,GAAG,KAAK,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACzD,MAAM,KAAK,GAAG,MAAM,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;IACtC,IAAI,KAAK,KAAK,IAAI,IAAI,MAAM,KAAK,SAAS,IAAI,QAAQ,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC;QAAE,OAAO,SAAS,CAAC;IACnH,MAAM,SAAS,GAAG,OAAO,CAAC,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;IACjE,IAAI,CAAC,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC,SAAS,CAAC,EAAE,KAAK,EAAE,KAAK,CAAC;QAAE,OAAO,SAAS,CAAC;IAC3E,OAAO,EAAE,MAAM,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC;AAC7G,CAAC,CAAC;AAEF,oDAAoD;AACpD,MAAM,CAAC,MAAM,qBAAqB,GAAG,CAAC,IAAY,EAAE,KAAiB,EAAE,OAAoB,EAAmB,EAAE;IAC9G,MAAM,IAAI,GAAG,WAAW,CAAC,KAAK,CAAC,CAAC;IAChC,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAC5B,MAAM,KAAK,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC7C,OAAO,KAAK,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE;QACnC,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,OAAO,CAAC,CAAC;QACtD,MAAM,MAAM,GAAG,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,WAAW,CAAC,WAAW,CAAC,KAAK,EAAE,KAAK,GAAG,CAAC,EAAE,KAAK,CAAC,IAAI,EAAE,OAAO,CAAC,EAAE,OAAO,CAAC,CAAC;QAC1H,IAAI,KAAK,KAAK,SAAS,IAAI,MAAM,KAAK,SAAS,IAAI,MAAM,KAAK,KAAK,CAAC,SAAS;YAAE,OAAO,EAAE,CAAC;QACzF,OAAO,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,QAAQ,EAAE,MAAM,EAAE,KAAK,CAAC,MAAM,EAAE,SAAS,EAAE,KAAK,CAAC,SAAS,EAAE,MAAM,EAAE,CAAC,CAAC;IAC7G,CAAC,CAAC,CAAC;AACL,CAAC,CAAC"}

package/dist/kana-spelling.d.ts

@@ -3,6 +3,11 @@ export declare const toKatakana: (text: string) => string;
 export declare const isKanaOnly: (text: string) => boolean;
 /** The kanji of a spelling, in order: 引越 for both 引っ越し and 引越し, nothing for できる. */
 export declare const kanjiSkeleton: (text: string) => string;
+/**
+ * Whether a spelling is the kanji alone of a word the others spell with okurigana: 取扱 beside 取扱い, 締切 beside 締切り. Official
+ * Japanese drops okurigana at the head of a compound (取扱事業者) and keeps it on the word alone, so the two are one convention.
+ */
+export declare const dropsOkurigana: (spelling: string, spellings: readonly string[]) => boolean;
 /**
  * The reading of the dictionary form, from the reading of the written form: 下さい (クダサイ) with lemma 下さる reads クダサル.
  * The written form and the lemma differ only in their kana ending, so that ending is swapped in the reading. When the ending is

package/dist/kana-spelling.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"kana-spelling.d.ts","sourceRoot":"","sources":["../src/kana-spelling.ts"],"names":[],"mappings":"AASA,6DAA6D;AAC7D,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,KAAG,MAAmH,CAAC;AAE9J,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,KAAG,OAA+B,CAAC;AAE1E,oFAAoF;AACpF,eAAO,MAAM,aAAa,GAAI,MAAM,MAAM,KAAG,MAAqE,CAAC;AAUnH;;;;GAIG;AACH,eAAO,MAAM,YAAY,GAAI,SAAS,MAAM,EAAE,OAAO,MAAM,EAAE,SAAS,MAAM,KAAG,MAAM,GAAG,SAOvF,CAAC;AAKF,oHAAoH;AACpH,eAAO,MAAM,WAAW,GAAI,SAAS,MAAM,KAAG,MAKrB,CAAC"}
+{"version":3,"file":"kana-spelling.d.ts","sourceRoot":"","sources":["../src/kana-spelling.ts"],"names":[],"mappings":"AASA,6DAA6D;AAC7D,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,KAAG,MAAmH,CAAC;AAE9J,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,KAAG,OAA+B,CAAC;AAE1E,oFAAoF;AACpF,eAAO,MAAM,aAAa,GAAI,MAAM,MAAM,KAAG,MAAqE,CAAC;AAEnH;;;GAGG;AACH,eAAO,MAAM,cAAc,GAAI,UAAU,MAAM,EAAE,WAAW,SAAS,MAAM,EAAE,KAAG,OAC+D,CAAC;AAUhJ;;;;GAIG;AACH,eAAO,MAAM,YAAY,GAAI,SAAS,MAAM,EAAE,OAAO,MAAM,EAAE,SAAS,MAAM,KAAG,MAAM,GAAG,SAOvF,CAAC;AAKF,oHAAoH;AACpH,eAAO,MAAM,WAAW,GAAI,SAAS,MAAM,KAAG,MAKrB,CAAC"}

package/dist/kana-spelling.js

@@ -10,6 +10,11 @@ export const toKatakana = (text) => text.replace(HIRAGANA, (char) => String.from
 export const isKanaOnly = (text) => KANA_ONLY.test(text);
 /** The kanji of a spelling, in order: 引越 for both 引っ越し and 引越し, nothing for できる. */
 export const kanjiSkeleton = (text) => [...text.matchAll(KANJI)].map((match) => match[0]).join("");
+/**
+ * Whether a spelling is the kanji alone of a word the others spell with okurigana: 取扱 beside 取扱い, 締切 beside 締切り. Official
+ * Japanese drops okurigana at the head of a compound (取扱事業者) and keeps it on the word alone, so the two are one convention.
+ */
+export const dropsOkurigana = (spelling, spellings) => spelling !== "" && kanjiSkeleton(spelling) === spelling && spellings.some((other) => other !== spelling && kanjiSkeleton(other) === spelling);
 /** The length, in UTF-16 units, of the start both strings share, compared character by character (𠮟 is one character, two units). */
 const sharedPrefixLength = (left, right) => {
     const [leftChars, rightChars] = [[...left], [...right]];

package/dist/kana-spelling.js.map

@@ -1 +1 @@
-{"version":3,"file":"kana-spelling.js","sourceRoot":"","sources":["../src/kana-spelling.ts"],"names":[],"mappings":"AAAA,yHAAyH;AACzH,mHAAmH;AACnH,yEAAyE;AAEzE,MAAM,oBAAoB,GAAG,IAAI,CAAC;AAClC,MAAM,QAAQ,GAAG,SAAS,CAAC;AAC3B,MAAM,SAAS,GAAG,eAAe,CAAC;AAClC,MAAM,KAAK,GAAG,qBAAqB,CAAC;AAEpC,6DAA6D;AAC7D,MAAM,CAAC,MAAM,UAAU,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,oBAAoB,CAAC,CAAC,CAAC;AAE9J,MAAM,CAAC,MAAM,UAAU,GAAG,CAAC,IAAY,EAAW,EAAE,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAE1E,oFAAoF;AACpF,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;AAEnH,sIAAsI;AACtI,MAAM,kBAAkB,GAAG,CAAC,IAAY,EAAE,KAAa,EAAU,EAAE;IACjE,MAAM,CAAC,SAAS,EAAE,UAAU,CAAC,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC;IACxD,MAAM,OAAO,GAAG,SAAS,CAAC,SAAS,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,EAAE,CAAC,UAAU,CAAC,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC;IAC3E,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,CAAC;IACpG,OAAO,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,MAAM,CAAC;AAChC,CAAC,CAAC;AAEF;;;;GAIG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,OAAe,EAAE,KAAa,EAAE,OAAe,EAAsB,EAAE;IAClG,MAAM,MAAM,GAAG,kBAAkB,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;IAClD,MAAM,CAAC,UAAU,EAAE,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC;IAC5E,IAAI,CAAC,UAAU,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,QAAQ,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IACnH,MAAM,MAAM,GAAG,UAAU,CAAC,UAAU,CAAC,CAAC;IACtC,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;QAAE,OAAO,SAAS,CAAC;IAChD,OAAO,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,GAAG,UAAU,CAAC,QAAQ,CAAC,CAAC;AACjF,CAAC,CAAC;AAEF,MAAM,cAAc,GAAqC,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC;AAC5H,MAAM,EAAE,GAAqC,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC;AAE5F,oHAAoH;AACpH,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC,OAAe,EAAU,EAAE,CACrD,OAAO;KACJ,OAAO,CAAC,YAAY,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,EAAE,CAAC,KAAK,CAAC,IAAI,KAAK,CAAC;KACpD,OAAO,CAAC,cAAc,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,cAAc,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC;KAC/D,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC;KAClB,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC"}
+{"version":3,"file":"kana-spelling.js","sourceRoot":"","sources":["../src/kana-spelling.ts"],"names":[],"mappings":"AAAA,yHAAyH;AACzH,mHAAmH;AACnH,yEAAyE;AAEzE,MAAM,oBAAoB,GAAG,IAAI,CAAC;AAClC,MAAM,QAAQ,GAAG,SAAS,CAAC;AAC3B,MAAM,SAAS,GAAG,eAAe,CAAC;AAClC,MAAM,KAAK,GAAG,qBAAqB,CAAC;AAEpC,6DAA6D;AAC7D,MAAM,CAAC,MAAM,UAAU,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,oBAAoB,CAAC,CAAC,CAAC;AAE9J,MAAM,CAAC,MAAM,UAAU,GAAG,CAAC,IAAY,EAAW,EAAE,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAE1E,oFAAoF;AACpF,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;AAEnH;;;GAGG;AACH,MAAM,CAAC,MAAM,cAAc,GAAG,CAAC,QAAgB,EAAE,SAA4B,EAAW,EAAE,CACxF,QAAQ,KAAK,EAAE,IAAI,aAAa,CAAC,QAAQ,CAAC,KAAK,QAAQ,IAAI,SAAS,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,KAAK,QAAQ,IAAI,aAAa,CAAC,KAAK,CAAC,KAAK,QAAQ,CAAC,CAAC;AAEhJ,sIAAsI;AACtI,MAAM,kBAAkB,GAAG,CAAC,IAAY,EAAE,KAAa,EAAU,EAAE;IACjE,MAAM,CAAC,SAAS,EAAE,UAAU,CAAC,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC;IACxD,MAAM,OAAO,GAAG,SAAS,CAAC,SAAS,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,EAAE,CAAC,UAAU,CAAC,EAAE,CAAC,KAAK,IAAI,CAAC,CAAC;IAC3E,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,CAAC;IACpG,OAAO,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,MAAM,CAAC;AAChC,CAAC,CAAC;AAEF;;;;GAIG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,OAAe,EAAE,KAAa,EAAE,OAAe,EAAsB,EAAE;IAClG,MAAM,MAAM,GAAG,kBAAkB,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;IAClD,MAAM,CAAC,UAAU,EAAE,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC;IAC5E,IAAI,CAAC,UAAU,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,QAAQ,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IACnH,MAAM,MAAM,GAAG,UAAU,CAAC,UAAU,CAAC,CAAC;IACtC,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;QAAE,OAAO,SAAS,CAAC;IAChD,OAAO,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,GAAG,UAAU,CAAC,QAAQ,CAAC,CAAC;AACjF,CAAC,CAAC;AAEF,MAAM,cAAc,GAAqC,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC;AAC5H,MAAM,EAAE,GAAqC,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,GAAG,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC;AAE5F,oHAAoH;AACpH,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC,OAAe,EAAU,EAAE,CACrD,OAAO;KACJ,OAAO,CAAC,YAAY,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,EAAE,CAAC,KAAK,CAAC,IAAI,KAAK,CAAC;KACpD,OAAO,CAAC,cAAc,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,cAAc,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC;KAC/D,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC;KAClB,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC"}

package/dist/location-part.d.ts

@@ -0,0 +1,13 @@
+import type { Span, Token } from "./plugin.ts";
+/** units は階・部屋の番号の単位（語彙表 floor-unit）、levels は番号の前に書いて階の名前の一部になる語（語彙表 floor-level）。 */
+export type FloorWords = {
+    readonly units: ReadonlySet<string>;
+    readonly levels: ReadonlySet<string>;
+};
+/**
+ * 「本社 5階 第2会議室」「研究所 3階 セミナー室」のように、名前の語の後ろに空白で区切って書いた階・部屋の番号。
+ * その前の空白は所在の組を分ける区切りで、日本語と数字のあいだの空け方の好みではない。「地下 1階」「地上 5階」の空白は階の名前の中の空け方なので、区切りと読まない。
+ * 番号は数字だけで、単位の後ろで組が閉じる（空白・読点・文末・英字が続く）ものだけ。tokens は文書全体の座標で、base は text の先頭の位置。
+ */
+export declare const isSpacedLocationPart: (text: string, run: Span, tokens: readonly Token[] | undefined, base: number, words: FloorWords) => boolean;
+//# sourceMappingURL=location-part.d.ts.map

package/dist/location-part.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"location-part.d.ts","sourceRoot":"","sources":["../src/location-part.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,aAAa,CAAC;AAU/C,sFAAsF;AACtF,MAAM,MAAM,UAAU,GAAG;IAAE,QAAQ,CAAC,KAAK,EAAE,WAAW,CAAC,MAAM,CAAC,CAAC;IAAC,QAAQ,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,CAAC,CAAA;CAAE,CAAC;AAMvG;;;;GAIG;AACH,eAAO,MAAM,oBAAoB,GAAI,MAAM,MAAM,EAAE,KAAK,IAAI,EAAE,QAAQ,SAAS,KAAK,EAAE,GAAG,SAAS,EAAE,MAAM,MAAM,EAAE,OAAO,UAAU,KAAG,OAOrI,CAAC"}

package/dist/location-part.js

@@ -0,0 +1,24 @@
+/** 空白の前の、建物や場所の名前になる語の品詞。助詞の後ろ（「会場は 5階」）は名前の区切りではない。 */
+const NAME_POS = new Set(["NOUN", "PROPN"]);
+/** 階・部屋の番号の後ろに続けば、番号が語の一部（5階建て、5階です）で、所在の組を閉じていない字。 */
+const WORD_CHAR = /[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}]/u;
+const SPACES = new Set([" ", "　"]);
+/** run のすぐ後ろに書いた、units のうち最も長い語。無ければ undefined。 */
+const unitAfter = (text, run, units) => [...units].filter((unit) => text.startsWith(unit, run.end)).toSorted((left, right) => right.length - left.length)[0];
+/**
+ * 「本社 5階 第2会議室」「研究所 3階 セミナー室」のように、名前の語の後ろに空白で区切って書いた階・部屋の番号。
+ * その前の空白は所在の組を分ける区切りで、日本語と数字のあいだの空け方の好みではない。「地下 1階」「地上 5階」の空白は階の名前の中の空け方なので、区切りと読まない。
+ * 番号は数字だけで、単位の後ろで組が閉じる（空白・読点・文末・英字が続く）ものだけ。tokens は文書全体の座標で、base は text の先頭の位置。
+ */
+export const isSpacedLocationPart = (text, run, tokens, base, words) => {
+    if (tokens === undefined || !SPACES.has(text[run.start - 1] ?? ""))
+        return false;
+    if (!/^\d+$/u.test(text.slice(run.start, run.end)))
+        return false;
+    const unit = unitAfter(text, run, words.units);
+    if (unit === undefined || WORD_CHAR.test(text[run.end + unit.length] ?? ""))
+        return false;
+    const named = tokens.find((token) => token.span.end === base + run.start - 1);
+    return named !== undefined && NAME_POS.has(named.pos) && !words.levels.has(named.surface);
+};
+//# sourceMappingURL=location-part.js.map

package/dist/location-part.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"location-part.js","sourceRoot":"","sources":["../src/location-part.ts"],"names":[],"mappings":"AAEA,wDAAwD;AACxD,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;AAE5C,uDAAuD;AACvD,MAAM,SAAS,GAAG,yDAAyD,CAAC;AAE5E,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAKnC,mDAAmD;AACnD,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,GAAS,EAAE,KAA0B,EAAsB,EAAE,CAC5F,CAAC,GAAG,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;AAEvH;;;;GAIG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,CAAC,IAAY,EAAE,GAAS,EAAE,MAAoC,EAAE,IAAY,EAAE,KAAiB,EAAW,EAAE;IAC9I,IAAI,MAAM,KAAK,SAAS,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;QAAE,OAAO,KAAK,CAAC;IACjF,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,CAAC,CAAC;QAAE,OAAO,KAAK,CAAC;IACjE,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,EAAE,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;IAC/C,IAAI,IAAI,KAAK,SAAS,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC;QAAE,OAAO,KAAK,CAAC;IAC1F,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,KAAK,IAAI,GAAG,GAAG,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;IAC9E,OAAO,KAAK,KAAK,SAAS,IAAI,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;AAC5F,CAAC,CAAC"}

package/dist/nado-closed-list.d.ts

@@ -0,0 +1,20 @@
+import type { LexiconEntry, Token } from "./plugin.ts";
+export type ClosedListWords = {
+    readonly open: readonly string[];
+    /** A limit right after the open word (等に限り, etc. only). */
+    readonly limitsAfter: readonly string[];
+    /** A limit before the list it governs (only A, B, etc.). */
+    readonly limitsBefore: readonly string[];
+    /** A phrase holding a limit's letters that closes nothing (に限らず, not only). */
+    readonly notLimits: readonly string[];
+};
+/** An open word on a closed list: where it is in the sentence, the word and the limit. */
+export type OpenOnClosed = {
+    readonly offset: number;
+    readonly open: string;
+    readonly limit: string;
+};
+export declare const closedListWordsOf: (entries: readonly LexiconEntry[]) => ClosedListWords;
+/** The open words of one sentence that a limit closes, by their offset in the sentence. */
+export declare const openWordsOnClosedLists: (text: string, tokens: readonly Token[], words: ClosedListWords) => OpenOnClosed[];
+//# sourceMappingURL=nado-closed-list.d.ts.map

package/dist/nado-closed-list.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"nado-closed-list.d.ts","sourceRoot":"","sources":["../src/nado-closed-list.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,MAAM,aAAa,CAAC;AAGvD,MAAM,MAAM,eAAe,GAAG;IAC5B,QAAQ,CAAC,IAAI,EAAE,SAAS,MAAM,EAAE,CAAC;IACjC,2DAA2D;IAC3D,QAAQ,CAAC,WAAW,EAAE,SAAS,MAAM,EAAE,CAAC;IACxC,4DAA4D;IAC5D,QAAQ,CAAC,YAAY,EAAE,SAAS,MAAM,EAAE,CAAC;IACzC,+EAA+E;IAC/E,QAAQ,CAAC,SAAS,EAAE,SAAS,MAAM,EAAE,CAAC;CACvC,CAAC;AAEF,0FAA0F;AAC1F,MAAM,MAAM,YAAY,GAAG;IAAE,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAA;CAAE,CAAC;AAKtG,eAAO,MAAM,iBAAiB,GAAI,SAAS,SAAS,YAAY,EAAE,KAAG,eAKnE,CAAC;AAoEH,2FAA2F;AAC3F,eAAO,MAAM,sBAAsB,GAAI,MAAM,MAAM,EAAE,QAAQ,SAAS,KAAK,EAAE,EAAE,OAAO,eAAe,KAAG,YAAY,EAS3C,CAAC"}

package/dist/nado-closed-list.js

@@ -0,0 +1,72 @@
+import { escapeRegExp } from "./orthography.js";
+const patternsOf = (entries, group, position) => entries.filter((entry) => entry.group === group && (position === undefined || entry.position === position)).map((entry) => entry.pattern);
+export const closedListWordsOf = (entries) => ({
+    open: patternsOf(entries, "open"),
+    limitsAfter: patternsOf(entries, "limit", "after"),
+    limitsBefore: patternsOf(entries, "limit", "before"),
+    notLimits: patternsOf(entries, "not-limit"),
+});
+const LATIN_START = /^[A-Za-z]/u;
+const LETTER = /\p{L}/u;
+/** What may stand between an open word and a limit right after it: spaces, a comma, a closing bracket. */
+const BETWEEN_OPEN_AND_LIMIT = /^[\s,、)）」』]*/u;
+/** A word that is a counter or a class (1等, 2等), not an open word, by the tagger's features. */
+const CLASS_NOUN = "Class";
+/** What makes the words between a limit and an open word a clause of their own, not the list it governs. */
+const CLAUSE_POS = new Set(["AUX", "VERB"]);
+/** A verb form that modifies a noun inside a list (a driving licence, used cars). */
+const NOUN_MODIFYING_FORMS = new Set(["Ger", "Part"]);
+const LIST_SEPARATOR = /[,、]/u;
+/** Where a word occurs in a text; a Latin word only as whole words, any case. */
+const placesOf = (text, word) => {
+    const latin = LATIN_START.test(word);
+    const matches = [...text.matchAll(new RegExp(escapeRegExp(word), latin ? "giu" : "gu"))].map((match) => match.index);
+    if (!latin)
+        return matches;
+    return matches.filter((at) => !LETTER.test(text[at - 1] ?? "") && !LETTER.test(text[at + word.length] ?? ""));
+};
+const startsWithWord = (text, word) => placesOf(text.slice(0, word.length + 1), word).includes(0);
+/**
+ * The open word stands as a word of its own: a token starts there, is no longer than the word (等しい, 同等 are other
+ * words), and is not a counter (1等). Token spans are the sentence's own offsets. Without tokens only a Latin word is read.
+ */
+const standsAsOpenWord = (tokens, at, open) => {
+    if (tokens.length === 0)
+        return LATIN_START.test(open);
+    const token = tokens.find((candidate) => candidate.span.start === at);
+    return token !== undefined && open.toLowerCase().startsWith(token.surface.toLowerCase()) && token.features?.NounType !== CLASS_NOUN;
+};
+const limitRightAfter = (rest, words) => {
+    const after = rest.slice(BETWEEN_OPEN_AND_LIMIT.exec(rest)?.[0].length ?? 0);
+    if (words.notLimits.some((phrase) => startsWithWord(after, phrase)))
+        return undefined;
+    return longestFirst(words.limitsAfter).find((limit) => startsWithWord(after, limit));
+};
+const longestFirst = (words) => [...words].sort((a, b) => b.length - a.length);
+const insideNotLimit = (text, at, notLimits) => notLimits.some((phrase) => placesOf(text, phrase).some((start) => start <= at && at < start + phrase.length));
+const OPEN_BRACKETS = /[(（]/gu;
+const CLOSE_BRACKETS = /[)）]/gu;
+/** A bracket opened and not closed between the limit and the list: the list explains a word the limit governs. */
+const opensBracket = (between) => (between.match(OPEN_BRACKETS)?.length ?? 0) > (between.match(CLOSE_BRACKETS)?.length ?? 0);
+/** The words between a limit and the open word are a list it governs: separated by commas, with no clause of their own. */
+const governsList = (text, tokens, from, to) => LIST_SEPARATOR.test(text.slice(from, to)) &&
+    !opensBracket(text.slice(from, to)) &&
+    !tokens.some((token) => token.span.start >= from && token.span.end <= to && CLAUSE_POS.has(token.pos) && !NOUN_MODIFYING_FORMS.has(token.features?.VerbForm ?? ""));
+const limitBefore = (text, tokens, at, words) => {
+    const limits = words.limitsBefore.flatMap((limit) => placesOf(text.slice(0, at), limit).map((start) => ({ limit, start, end: start + limit.length, negated: insideNotLimit(text, start, words.notLimits) })));
+    const nearest = limits.toSorted((a, b) => b.start - a.start)[0];
+    if (nearest === undefined || nearest.negated)
+        return undefined;
+    return governsList(text, tokens, nearest.end, at) ? nearest.limit : undefined;
+};
+/** The open words of one sentence that a limit closes, by their offset in the sentence. */
+export const openWordsOnClosedLists = (text, tokens, words) => words.open
+    .flatMap((open) => placesOf(text, open).map((at) => ({ open, at })))
+    .filter(({ open, at }) => standsAsOpenWord(tokens, at, open))
+    .flatMap(({ open, at }) => {
+    const limit = limitRightAfter(text.slice(at + open.length), words) ?? limitBefore(text, tokens, at, words);
+    return limit === undefined ? [] : [{ offset: at, open, limit }];
+})
+    .sort((a, b) => a.offset - b.offset || b.open.length - a.open.length)
+    .filter((hit, index, hits) => hits[index - 1]?.offset !== hit.offset);
+//# sourceMappingURL=nado-closed-list.js.map

package/dist/nado-closed-list.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"nado-closed-list.js","sourceRoot":"","sources":["../src/nado-closed-list.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,YAAY,EAAE,MAAM,kBAAkB,CAAC;AAehD,MAAM,UAAU,GAAG,CAAC,OAAgC,EAAE,KAAa,EAAE,QAA6B,EAAY,EAAE,CAC9G,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,KAAK,KAAK,IAAI,CAAC,QAAQ,KAAK,SAAS,IAAI,KAAK,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;AAE5I,MAAM,CAAC,MAAM,iBAAiB,GAAG,CAAC,OAAgC,EAAmB,EAAE,CAAC,CAAC;IACvF,IAAI,EAAE,UAAU,CAAC,OAAO,EAAE,MAAM,CAAC;IACjC,WAAW,EAAE,UAAU,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC;IAClD,YAAY,EAAE,UAAU,CAAC,OAAO,EAAE,OAAO,EAAE,QAAQ,CAAC;IACpD,SAAS,EAAE,UAAU,CAAC,OAAO,EAAE,WAAW,CAAC;CAC5C,CAAC,CAAC;AAEH,MAAM,WAAW,GAAG,YAAY,CAAC;AACjC,MAAM,MAAM,GAAG,QAAQ,CAAC;AACxB,0GAA0G;AAC1G,MAAM,sBAAsB,GAAG,eAAe,CAAC;AAC/C,gGAAgG;AAChG,MAAM,UAAU,GAAG,OAAO,CAAC;AAC3B,4GAA4G;AAC5G,MAAM,UAAU,GAAwB,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC;AACjE,qFAAqF;AACrF,MAAM,oBAAoB,GAAwB,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC;AAC3E,MAAM,cAAc,GAAG,OAAO,CAAC;AAE/B,iFAAiF;AACjF,MAAM,QAAQ,GAAG,CAAC,IAAY,EAAE,IAAY,EAAY,EAAE;IACxD,MAAM,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACrC,MAAM,OAAO,GAAG,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,IAAI,MAAM,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;IACrH,IAAI,CAAC,KAAK;QAAE,OAAO,OAAO,CAAC;IAC3B,OAAO,OAAO,CAAC,MAAM,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;AAChH,CAAC,CAAC;AAEF,MAAM,cAAc,GAAG,CAAC,IAAY,EAAE,IAAY,EAAW,EAAE,CAAC,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;AAE3H;;;GAGG;AACH,MAAM,gBAAgB,GAAG,CAAC,MAAwB,EAAE,EAAU,EAAE,IAAY,EAAW,EAAE;IACvF,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACvD,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,IAAI,CAAC,KAAK,KAAK,EAAE,CAAC,CAAC;IACtE,OAAO,KAAK,KAAK,SAAS,IAAI,IAAI,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,KAAK,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,IAAI,KAAK,CAAC,QAAQ,EAAE,QAAQ,KAAK,UAAU,CAAC;AACtI,CAAC,CAAC;AAEF,MAAM,eAAe,GAAG,CAAC,IAAY,EAAE,KAAsB,EAAsB,EAAE;IACnF,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,sBAAsB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC;IAC7E,IAAI,KAAK,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,cAAc,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IACtF,OAAO,YAAY,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,cAAc,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC,CAAC;AACvF,CAAC,CAAC;AAEF,MAAM,YAAY,GAAG,CAAC,KAAwB,EAAY,EAAE,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC;AAE5G,MAAM,cAAc,GAAG,CAAC,IAAY,EAAE,EAAU,EAAE,SAA4B,EAAW,EAAE,CACzF,SAAS,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,IAAI,EAAE,GAAG,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC;AAEhH,MAAM,aAAa,GAAG,QAAQ,CAAC;AAC/B,MAAM,cAAc,GAAG,QAAQ,CAAC;AAEhC,kHAAkH;AAClH,MAAM,YAAY,GAAG,CAAC,OAAe,EAAW,EAAE,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,aAAa,CAAC,EAAE,MAAM,IAAI,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,cAAc,CAAC,EAAE,MAAM,IAAI,CAAC,CAAC,CAAC;AAE9I,2HAA2H;AAC3H,MAAM,WAAW,GAAG,CAAC,IAAY,EAAE,MAAwB,EAAE,IAAY,EAAE,EAAU,EAAW,EAAE,CAChG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;IACzC,CAAC,YAAY,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;IACnC,CAAC,MAAM,CAAC,IAAI,CACV,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,IAAI,IAAI,IAAI,KAAK,CAAC,IAAI,CAAC,GAAG,IAAI,EAAE,IAAI,UAAU,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,oBAAoB,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,QAAQ,IAAI,EAAE,CAAC,CACtJ,CAAC;AAEJ,MAAM,WAAW,GAAG,CAAC,IAAY,EAAE,MAAwB,EAAE,EAAU,EAAE,KAAsB,EAAsB,EAAE;IACrH,MAAM,MAAM,GAAG,KAAK,CAAC,YAAY,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,CAClD,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,GAAG,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,cAAc,CAAC,IAAI,EAAE,KAAK,EAAE,KAAK,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC,CACxJ,CAAC;IACF,MAAM,OAAO,GAAG,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;IAChE,IAAI,OAAO,KAAK,SAAS,IAAI,OAAO,CAAC,OAAO;QAAE,OAAO,SAAS,CAAC;IAC/D,OAAO,WAAW,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC;AAChF,CAAC,CAAC;AAEF,2FAA2F;AAC3F,MAAM,CAAC,MAAM,sBAAsB,GAAG,CAAC,IAAY,EAAE,MAAwB,EAAE,KAAsB,EAAkB,EAAE,CACvH,KAAK,CAAC,IAAI;KACP,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,QAAQ,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC;KACnE,MAAM,CAAC,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,EAAE,EAAE,CAAC,gBAAgB,CAAC,MAAM,EAAE,EAAE,EAAE,IAAI,CAAC,CAAC;KAC5D,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,EAAE,EAAE;IACxB,MAAM,KAAK,GAAG,eAAe,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,EAAE,KAAK,CAAC,IAAI,WAAW,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,KAAK,CAAC,CAAC;IAC3G,OAAO,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC,CAAC;AAClE,CAAC,CAAC;KACD,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC;KACpE,MAAM,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,GAAG,CAAC,CAAC,EAAE,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,CAAC"}

package/dist/name-cue.d.ts

@@ -0,0 +1,17 @@
+/** 人を指す前置き（担当の、私、）、敬称（様、さん）、名前のすぐ後ろに来る語（です、まで）。語彙表から。 */
+export type NameCues = {
+    readonly leads: readonly string[];
+    readonly suffixes: readonly string[];
+    readonly particles: readonly string[];
+};
+/**
+ * person: 人の名前と言える（前に「担当の」、後ろに敬称）。slot: 名前の来る場所（後ろに「です」「まで」）。bare: どちらでもない。
+ * 名前の形でないもの（字数が違う、漢字以外を含む、長い漢字の連なりの一部）は undefined。
+ */
+export type NameCue = "person" | "slot" | "bare";
+/**
+ * offset から書いた surface を、前後の語で読む。名前は 2〜4 字の漢字で、前後に漢字が続かない（鹿嶋市、株式会社髙橋は地名や会社の名前の
+ * 一部）。敬称だけは漢字（様、氏）でも名前のすぐ後ろに続いてよい。
+ */
+export declare const nameCueAt: (text: string, offset: number, surface: string, cues: NameCues) => NameCue | undefined;
+//# sourceMappingURL=name-cue.d.ts.map

package/dist/name-cue.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"name-cue.d.ts","sourceRoot":"","sources":["../src/name-cue.ts"],"names":[],"mappings":"AAEA,yDAAyD;AACzD,MAAM,MAAM,QAAQ,GAAG;IAAE,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAAC,QAAQ,CAAC,QAAQ,EAAE,SAAS,MAAM,EAAE,CAAC;IAAC,QAAQ,CAAC,SAAS,EAAE,SAAS,MAAM,EAAE,CAAA;CAAE,CAAC;AAE1I;;;GAGG;AACH,MAAM,MAAM,OAAO,GAAG,QAAQ,GAAG,MAAM,GAAG,MAAM,CAAC;AAUjD;;;GAGG;AACH,eAAO,MAAM,SAAS,GAAI,MAAM,MAAM,EAAE,QAAQ,MAAM,EAAE,SAAS,MAAM,EAAE,MAAM,QAAQ,KAAG,OAAO,GAAG,SAWnG,CAAC"}

package/dist/name-cue.js

@@ -0,0 +1,29 @@
+// 敬称も、解析器の人名の印も無い名前（担当の斎藤です、斉藤までご連絡ください）を、前後の語から人の名前と読む。
+const MIN_NAME = 2;
+const MAX_NAME = 4;
+/** 前後の一字を読むのに要る長さ（UTF-16 の単位）。𠮷 は二つ。 */
+const SURROGATE_PAIR = 2;
+const HAN = /^\p{Script=Han}$/u;
+const isHan = (letter) => letter !== undefined && HAN.test(letter);
+/**
+ * offset から書いた surface を、前後の語で読む。名前は 2〜4 字の漢字で、前後に漢字が続かない（鹿嶋市、株式会社髙橋は地名や会社の名前の
+ * 一部）。敬称だけは漢字（様、氏）でも名前のすぐ後ろに続いてよい。
+ */
+export const nameCueAt = (text, offset, surface, cues) => {
+    const letters = [...surface];
+    if (letters.length < MIN_NAME || letters.length > MAX_NAME || !letters.every((letter) => isHan(letter)))
+        return undefined;
+    const context = Math.max(SURROGATE_PAIR, ...[...cues.leads, ...cues.suffixes, ...cues.particles].map((word) => word.length));
+    const before = text.slice(Math.max(0, offset - context), offset);
+    const after = text.slice(offset + surface.length, offset + surface.length + context);
+    if (isHan([...before].at(-1)))
+        return undefined;
+    if (cues.suffixes.some((suffix) => after.startsWith(suffix)))
+        return "person";
+    if (isHan([...after][0]))
+        return undefined;
+    if (cues.leads.some((lead) => before.endsWith(lead)))
+        return "person";
+    return cues.particles.some((particle) => after.startsWith(particle)) ? "slot" : "bare";
+};
+//# sourceMappingURL=name-cue.js.map

package/dist/name-cue.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"name-cue.js","sourceRoot":"","sources":["../src/name-cue.ts"],"names":[],"mappings":"AAAA,yDAAyD;AAWzD,MAAM,QAAQ,GAAG,CAAC,CAAC;AACnB,MAAM,QAAQ,GAAG,CAAC,CAAC;AACnB,yCAAyC;AACzC,MAAM,cAAc,GAAG,CAAC,CAAC;AACzB,MAAM,GAAG,GAAG,mBAAmB,CAAC;AAEhC,MAAM,KAAK,GAAG,CAAC,MAA0B,EAAW,EAAE,CAAC,MAAM,KAAK,SAAS,IAAI,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;AAEhG;;;GAGG;AACH,MAAM,CAAC,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,MAAc,EAAE,OAAe,EAAE,IAAc,EAAuB,EAAE;IAC9G,MAAM,OAAO,GAAG,CAAC,GAAG,OAAO,CAAC,CAAC;IAC7B,IAAI,OAAO,CAAC,MAAM,GAAG,QAAQ,IAAI,OAAO,CAAC,MAAM,GAAG,QAAQ,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IAC1H,MAAM,OAAO,GAAG,IAAI,CAAC,GAAG,CAAC,cAAc,EAAE,GAAG,CAAC,GAAG,IAAI,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,QAAQ,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC;IAC7H,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,EAAE,MAAM,CAAC,CAAC;IACjE,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,GAAG,OAAO,CAAC,CAAC;IACrF,IAAI,KAAK,CAAC,CAAC,GAAG,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IAChD,IAAI,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC;QAAE,OAAO,QAAQ,CAAC;IAC9E,IAAI,KAAK,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IAC3C,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,QAAQ,CAAC;IACtE,OAAO,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC;AACzF,CAAC,CAAC"}

package/dist/name-variants.d.ts

@@ -1,7 +1,8 @@
 import type { Token } from "./plugin.ts";
+import { type NameCue, type NameCues } from "./name-cue.ts";
 /**
  * words は名前の語（記号を除く）。読みが同じ二つの名前が、どの語で違うかを見るため。person は人の名前と読めるもの（解析器が
- * 人名と読むか、敬称が付く）。
+ * 人名と読むか、敬称が付く）。cue は前後の語から見た名前らしさ（name-cue.ts）。
  */
 export type NameMention = {
     readonly surface: string;
@@ -9,11 +10,12 @@ export type NameMention = {
     readonly reading: string | undefined;
     readonly words: readonly string[];
     readonly person?: boolean;
+    readonly cue?: NameCue;
 };
 export type NameVariant = {
     readonly mention: NameMention;
     readonly usual: string;
-    readonly kind: "spelling" | "reading" | "near" | "character";
+    readonly kind: "spelling" | "reading" | "near" | "surname" | "character";
 };
 /** 字体の違う同じ字（斎・斉・齋）。字から、その組の代表の字へ。 */
 export type VariantChars = ReadonlyMap<string, string>;
@@ -22,15 +24,40 @@ export type VariantChars = ReadonlyMap<string, string>;
  * 大文字だけの名前（ACME INC、NASA）は外す。契約書の署名欄や略語で、ふつうの書き方の別の形ではない。小文字の英字だけの語も外す。
  */
 export declare const mentionsIn: (tokens: readonly Token[], source: string, personSuffixes?: readonly string[]) => NameMention[];
+/**
+ * 解析器が名前の一語を名前と読まなかった所（to Rachel Whitford の Rachel を動詞と読む）。空白一つで隣の語と合わせた形を、ほかの所で
+ * 名前と読めていれば、その形の現れと見る。隣の語がほかの名前の現れに入るなら合わせない。
+ */
+export declare const withKnownNeighbours: (mentions: readonly NameMention[], source: string) => NameMention[];
 /**
  * 解析器が名前と読めなかった、字体の違う字を含む人の名前（髙橋様、𠮷田様、﨑山様）。敬称のすぐ前の漢字の連なりで、語彙表の字を
  * 含み、ほかの名前の現れと重ならないもの。
  */
 export declare const suffixedNamesIn: (source: string, suffixes: readonly string[], chars: VariantChars, taken: readonly NameMention[]) => NameMention[];
+/**
+ * 解析器が名前と読めず、敬称も無いが、前後の語で名前と読める、字体の違う字を含む漢字（担当の髙橋です、髙橋まで）。
+ * ほかの名前の現れと重ならないもの。
+ */
+export declare const cuedNamesIn: (source: string, cues: NameCues, chars: VariantChars, taken: readonly NameMention[]) => NameMention[];
 /** 比べる形。幅（ＡＷＳ と AWS）、大文字小文字、空白と記号は名前を変えない。 */
 export declare const nameKey: (surface: string) => string;
+/**
+ * 名前の現れから言えること。person: 人の名前と読める。named: 人を指す前置きか敬称が付く。nameLike: 名前の来る場所にある（前置き
+ * か敬称、名前のすぐ後ろに来る語）。解析器の人名の印は地名にも付く（鹿嶋へ）ので、nameLike には数えない。
+ */
+export type NameEvidence = {
+    readonly person: boolean;
+    readonly named: boolean;
+    readonly nameLike: boolean;
+};
 /** 二つの語が一字違いか。英字だけの、長さ 5 以上の語で。 */
 export declare const isNearWord: (left: string, right: string) => boolean;
+/**
+ * 字体の違う字で書き分けた二つを、同じ人の名前と見るか。どちらも人の名前と読めるか、片方に人を指す前置きか敬称が付き
+ * （担当の斎藤です）、もう片方が名前の来る場所にある（斉藤まで）。地名にも同じ組がある（鹿島 と 鹿嶋）ので、名前の来る場所どうし
+ * だけでは見ない。
+ */
+export declare const isCharacterPair: (left: NameEvidence, right: NameEvidence) => boolean;
 /**
  * 同じ名前の、少ないほうの書き方。書き方ごとに最初の現れを一つ。同じ現れを二つの見方が言えば、先の見方だけ。chars は字体の
  * 違う同じ字の組（語彙表 name-variant-char）。

package/dist/name-variants.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"name-variants.d.ts","sourceRoot":"","sources":["../src/name-variants.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,aAAa,CAAC;AAOzC;;;GAGG;AACH,MAAM,MAAM,WAAW,GAAG;IACxB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,OAAO,EAAE,MAAM,GAAG,SAAS,CAAC;IACrC,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAClC,QAAQ,CAAC,MAAM,CAAC,EAAE,OAAO,CAAC;CAC3B,CAAC;AAEF,MAAM,MAAM,WAAW,GAAG;IAAE,QAAQ,CAAC,OAAO,EAAE,WAAW,CAAC;IAAC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,IAAI,EAAE,UAAU,GAAG,SAAS,GAAG,MAAM,GAAG,WAAW,CAAA;CAAE,CAAC;AAElJ,qCAAqC;AACrC,MAAM,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;AA0DvD;;;GAGG;AACH,eAAO,MAAM,UAAU,GAAI,QAAQ,SAAS,KAAK,EAAE,EAAE,QAAQ,MAAM,EAAE,iBAAgB,SAAS,MAAM,EAAO,KAAG,WAAW,EAarH,CAAC;AAeL;;;GAGG;AACH,eAAO,MAAM,eAAe,GAAI,QAAQ,MAAM,EAAE,UAAU,SAAS,MAAM,EAAE,EAAE,OAAO,YAAY,EAAE,OAAO,SAAS,WAAW,EAAE,KAAG,WAAW,EAU1I,CAAC;AAEJ,8CAA8C;AAC9C,eAAO,MAAM,OAAO,GAAI,SAAS,MAAM,KAAG,MAIH,CAAC;AAoFxC,mCAAmC;AACnC,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,EAAE,OAAO,MAAM,KAAG,OAKxD,CAAC;AA4DF;;;GAGG;AACH,eAAO,MAAM,YAAY,GAAI,UAAU,SAAS,WAAW,EAAE,EAAE,QAAO,YAAwB,KAAG,WAAW,EAwB3G,CAAC"}
+{"version":3,"file":"name-variants.d.ts","sourceRoot":"","sources":["../src/name-variants.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,aAAa,CAAC;AAEzC,OAAO,EAAa,KAAK,OAAO,EAAE,KAAK,QAAQ,EAAE,MAAM,eAAe,CAAC;AAOvE;;;GAGG;AACH,MAAM,MAAM,WAAW,GAAG;IACxB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,OAAO,EAAE,MAAM,GAAG,SAAS,CAAC;IACrC,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAClC,QAAQ,CAAC,MAAM,CAAC,EAAE,OAAO,CAAC;IAC1B,QAAQ,CAAC,GAAG,CAAC,EAAE,OAAO,CAAC;CACxB,CAAC;AAEF,MAAM,MAAM,WAAW,GAAG;IACxB,QAAQ,CAAC,OAAO,EAAE,WAAW,CAAC;IAC9B,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,IAAI,EAAE,UAAU,GAAG,SAAS,GAAG,MAAM,GAAG,SAAS,GAAG,WAAW,CAAC;CAC1E,CAAC;AAEF,qCAAqC;AACrC,MAAM,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;AA0DvD;;;GAGG;AACH,eAAO,MAAM,UAAU,GAAI,QAAQ,SAAS,KAAK,EAAE,EAAE,QAAQ,MAAM,EAAE,iBAAgB,SAAS,MAAM,EAAO,KAAG,WAAW,EAarH,CAAC;AA8BL;;;GAGG;AACH,eAAO,MAAM,mBAAmB,GAAI,UAAU,SAAS,WAAW,EAAE,EAAE,QAAQ,MAAM,KAAG,WAAW,EAqBjG,CAAC;AAeF;;;GAGG;AACH,eAAO,MAAM,eAAe,GAAI,QAAQ,MAAM,EAAE,UAAU,SAAS,MAAM,EAAE,EAAE,OAAO,YAAY,EAAE,OAAO,SAAS,WAAW,EAAE,KAAG,WAAW,EAU1I,CAAC;AAIJ;;;GAGG;AACH,eAAO,MAAM,WAAW,GAAI,QAAQ,MAAM,EAAE,MAAM,QAAQ,EAAE,OAAO,YAAY,EAAE,OAAO,SAAS,WAAW,EAAE,KAAG,WAAW,EAQxH,CAAC;AAEL,8CAA8C;AAC9C,eAAO,MAAM,OAAO,GAAI,SAAS,MAAM,KAAG,MAIH,CAAC;AAExC;;;GAGG;AACH,MAAM,MAAM,YAAY,GAAG;IAAE,QAAQ,CAAC,MAAM,EAAE,OAAO,CAAC;IAAC,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAC;IAAC,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAA;CAAE,CAAC;AAiG7G,mCAAmC;AACnC,eAAO,MAAM,UAAU,GAAI,MAAM,MAAM,EAAE,OAAO,MAAM,KAAG,OAKxD,CAAC;AA0CF;;;;GAIG;AACH,eAAO,MAAM,eAAe,GAAI,MAAM,YAAY,EAAE,OAAO,YAAY,KAAG,OACyB,CAAC;AAmCpG;;;GAGG;AACH,eAAO,MAAM,YAAY,GAAI,UAAU,SAAS,WAAW,EAAE,EAAE,QAAO,YAAwB,KAAG,WAAW,EAyB3G,CAAC"}