chaffjs 0.19.0 → 0.21.0

package/dist/detectors/mark-shape.js

@@ -0,0 +1,160 @@
+import { escapeRegExp } from "../orthography.js";
+import { minorityReport } from "../spacing-minority.js";
+import { isWithinAny, quotedSpans } from "../quoted-span.js";
+/** The letters a mark must touch to count as part of the document's text, by language. */
+const SCRIPT = {
+    ja: /[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}ー々]/u,
+    en: /\p{Script=Latin}/u,
+};
+/**
+ * The two ways of writing each kind of mark, from the lexicon: pattern is one way, instead_of the other, group the kind.
+ * Two patterns may share one instead_of (“ and ” both against "), so the other way of a shared mark is both patterns.
+ */
+export const formsOf = (lexicon) => {
+    const forms = new Map();
+    lexicon.forEach((entry) => {
+        const kind = entry.group ?? entry.pattern;
+        const shared = entry.instead_of ?? "";
+        forms.set(entry.pattern, { kind, side: true, other: shared });
+        const known = forms.get(shared);
+        forms.set(shared, { kind, side: false, other: `${known?.side === false ? known.other : ""}${entry.pattern}` });
+    });
+    return forms;
+};
+/** Punctuation that may stand between a closing or opening mark and the word it belongs to ("draft." and “draft”.). */
+const BETWEEN = /[.,;:!?。、]/u;
+/** The letter beside a mark on one side (step -1 or 1), past one punctuation mark. */
+const besideLetter = (text, at, step, script) => {
+    const next = text.charAt(at + step);
+    return script.test(next) || (BETWEEN.test(next) && script.test(text.charAt(at + step * 2)));
+};
+const touchesScript = (text, at, script) => besideLetter(text, at, -1, script) || besideLetter(text, at, 1, script);
+/** The marks in a sentence that touch a letter of the document's script, outside 「」『』 quotations. spaced is the lexicon's pattern side. */
+export const marksIn = (sentence, forms, script) => {
+    const quoted = quotedSpans(sentence.text);
+    return sentence.text.split("").flatMap((char, at) => {
+        const form = forms.get(char);
+        if (form === undefined || !touchesScript(sentence.text, at, script))
+            return [];
+        if (isWithinAny(quoted, { start: at, end: at }))
+            return [];
+        return [{ sentence, char, form, offset: sentence.span.start + at, spaced: form.side }];
+    });
+};
+const sidedFinding = (item, values, variant) => ({
+    rule: "",
+    severity: "info",
+    line: 0,
+    column: 0,
+    quote: item.sentence.text.trim(),
+    ...(variant === undefined ? {} : { variant }),
+    values: { ...values, offset: item.offset },
+});
+/** The less common way, one finding each, or one finding for a document written both ways (spacing-minority.ts). */
+const minorityFindings = (items, limit, valuesOf) => {
+    const report = minorityReport(items, limit);
+    if (report === undefined)
+        return [];
+    if (report.mode === "mixed") {
+        const { first, odd, spaced, touching } = report;
+        return [sidedFinding(first, { ...valuesOf(first), spaced, touching, count: odd, of: items.length, limit }, "mixed")];
+    }
+    return report.odd.map((item) => sidedFinding(item, { ...valuesOf(item), count: report.odd.length, of: items.length, limit }));
+};
+/** Sentences written in the document's own language; a quoted sentence in another language follows its own marks. */
+const ownSentences = (doc) => doc.sentences.filter((sentence) => sentence.embeddedLanguage === undefined);
+/**
+ * A mark written two ways in one document (（ and (, “ and "), the less common way reported. The two ways come from the
+ * lexicon; neither is called right. Only marks next to a letter of the document's script count, so a bracket in code-like
+ * text (f(x)) or an English aside in a Japanese document does not.
+ */
+export const markConsistency = (doc, options) => {
+    const script = SCRIPT[doc.language];
+    if (script === undefined)
+        return [];
+    const forms = formsOf(options.lexicon ?? []);
+    const marks = ownSentences(doc).flatMap((sentence) => marksIn(sentence, forms, script));
+    const kinds = [...new Set(marks.map((mark) => mark.form.kind))];
+    return kinds.flatMap((kind) => minorityFindings(marks.filter((mark) => mark.form.kind === kind), options.limit, (mark) => ({ mark: mark.char, usual: mark.form.other })));
+};
+/**
+ * A sentence that surely ends: a lower-case word of two letters or more, then the mark. A number ("11.1."), an abbreviation
+ * ("Req.", "e.g.") or a capital ("U.S.") may be a split the adapter made inside a sentence, where one space is usual.
+ */
+const SENTENCE_END = /(?<![\p{L}\d.])\p{Ll}{2,}[.!?]["'”’)\]]?$/u;
+/** The next sentence starts with a capital, past an opening quote: not a citation ("[ISO99]") or an aside in brackets. */
+const SENTENCE_START = /^["'“‘]?\p{Lu}/u;
+const ONE_SPACE = " ";
+const TWO_SPACES = "  ";
+/** The space between two sentences on one line, when the first ends with a period, question or exclamation mark. spaced is two spaces. */
+export const sentenceGaps = (doc) => ownSentences(doc).flatMap((sentence, at, sentences) => {
+    const next = sentences[at + 1];
+    if (next === undefined || !SENTENCE_END.test(sentence.text) || !SENTENCE_START.test(next.text))
+        return [];
+    const gap = doc.source.slice(sentence.span.end, next.span.start);
+    if (gap !== ONE_SPACE && gap !== TWO_SPACES)
+        return [];
+    return [{ sentence: next, spaced: gap === TWO_SPACES, offset: sentence.span.end }];
+});
+/** One space between sentences and two, mixed in one document: the less common is reported. */
+export const sentenceSpacing = (doc, options) => minorityFindings(sentenceGaps(doc), options.limit, (gap) => ({
+    spaces: gap.spaced ? TWO_SPACES.length : ONE_SPACE.length,
+    usual: gap.spaced ? ONE_SPACE.length : TWO_SPACES.length,
+}));
+const hitFinding = (hit, count, limit) => ({
+    rule: "",
+    severity: "info",
+    line: 0,
+    column: 0,
+    quote: hit.sentence.text.trim(),
+    values: { matched: hit.matched, count, limit, offset: hit.offset },
+});
+const hitsOf = (sentences, pattern) => sentences.flatMap((sentence) => [...sentence.text.matchAll(pattern)].map((match) => ({ sentence, matched: match[0].trim(), offset: sentence.span.start + match.index })));
+const reportFrom = (hits, limit) => (hits.length < limit ? [] : hits.map((hit) => hitFinding(hit, hits.length, limit)));
+/** A spaced hyphen or a double hyphen between words, standing for a dash ("late - very late", "late--very late"). */
+const HYPHEN_DASH = /(?<=[\p{L},;)]) -{1,2} (?=[\p{L}(])|(?<=\p{L})--(?=\p{L})/gu;
+export const hyphenDash = (doc, options) => reportFrom(hitsOf(ownSentences(doc), HYPHEN_DASH), options.limit);
+/** Every way of writing an abbreviation with some of its periods dropped but not all (e.g. → e.g, eg.). */
+export const partialForms = (abbreviation) => {
+    const dots = [...abbreviation].flatMap((char, at) => (char === "." ? [at] : []));
+    const subsets = Array.from({ length: 2 ** dots.length }, (_unused, mask) => dots.filter((_dot, bit) => (mask >> bit) % 2 === 1));
+    return subsets
+        .filter((dropped) => dropped.length > 0 && dropped.length < dots.length)
+        .map((dropped) => [...abbreviation].filter((_char, at) => !dropped.includes(at)).join(""));
+};
+/** One partial form as a pattern: its first letter in either case, not inside a word, not followed by a period or letter. */
+const partialPattern = (form) => `(?<![\\p{L}.])[${form.charAt(0).toLowerCase()}${form.charAt(0).toUpperCase()}]${escapeRegExp(form.slice(1))}(?![\\p{L}.])`;
+/** Latin abbreviations from the lexicon (e.g., i.e.) written with only some of their periods (e.g, eg.). */
+export const latinAbbreviation = (doc, options) => {
+    const forms = (options.lexicon ?? []).flatMap((entry) => partialForms(entry.pattern));
+    if (forms.length === 0)
+        return [];
+    const pattern = new RegExp(forms.map(partialPattern).join("|"), "gu");
+    return reportFrom(hitsOf(ownSentences(doc), pattern), options.limit);
+};
+/** How many all-capital words in a row read as shouting rather than a run of acronyms. */
+const SHOUT_WORDS = 3;
+const CAPS_RUN = new RegExp(`\\b[A-Z][A-Z']*(?:,? [A-Z][A-Z']*){${String(SHOUT_WORDS - 1)},}\\b`, "gu");
+/** One-letter words (I, A) may sit in a run, but a run of them alone ("A B C") is a list of labels. */
+const MIN_LONG_WORDS = 2;
+const LATIN_WORD = /[A-Za-z][A-Za-z']*/gu;
+/** The words a source writes at least once not wholly in capitals (do, Do), in lower case: words, not acronyms. */
+export const lowerCaseWords = (source) => new Set((source.match(LATIN_WORD) ?? []).filter((word) => word !== word.toUpperCase()).map((word) => word.toLowerCase()));
+/**
+ * Whether more than half the words of a capital run are also written elsewhere in lower case. Words the lexicon lists as
+ * written in capitals by convention (MUST NOT in a specification) count like acronyms.
+ */
+export const isShouting = (run, known, conventional) => {
+    const words = run.split(/,? /u);
+    const ordinary = words.filter((word) => !conventional.has(word) && known.has(word.toLowerCase()));
+    const long = words.filter((word) => word.length > 1);
+    return long.length >= MIN_LONG_WORDS && ordinary.length * 2 > words.length;
+};
+/** Runs of three or more all-capital words that are ordinary words, not acronyms ("DO NOT DELETE THIS"). */
+export const capsShouting = (doc, options) => {
+    const known = lowerCaseWords(doc.prose ?? doc.source);
+    const conventional = new Set((options.lexicon ?? []).map((entry) => entry.pattern));
+    const hits = hitsOf(ownSentences(doc), CAPS_RUN).filter((hit) => isShouting(hit.matched, known, conventional));
+    return reportFrom(hits, options.limit);
+};
+//# sourceMappingURL=mark-shape.js.map

package/dist/detectors/mark-shape.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"mark-shape.js","sourceRoot":"","sources":["../../src/detectors/mark-shape.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,YAAY,EAAE,MAAM,mBAAmB,CAAC;AACjD,OAAO,EAAE,cAAc,EAAE,MAAM,wBAAwB,CAAC;AACxD,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAE7D,0FAA0F;AAC1F,MAAM,MAAM,GAAqC;IAC/C,EAAE,EAAE,2DAA2D;IAC/D,EAAE,EAAE,mBAAmB;CACxB,CAAC;AAKF;;;GAGG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,CAAC,OAAgB,EAA6B,EAAE;IACrE,MAAM,KAAK,GAAG,IAAI,GAAG,EAAgB,CAAC;IACtC,OAAO,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE;QACxB,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,IAAI,KAAK,CAAC,OAAO,CAAC;QAC1C,MAAM,MAAM,GAAG,KAAK,CAAC,UAAU,IAAI,EAAE,CAAC;QACtC,KAAK,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;QAC9D,MAAM,KAAK,GAAG,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;QAChC,KAAK,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,GAAG,KAAK,EAAE,IAAI,KAAK,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,GAAG,KAAK,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;IACjH,CAAC,CAAC,CAAC;IACH,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAIF,uHAAuH;AACvH,MAAM,OAAO,GAAG,aAAa,CAAC;AAE9B,sFAAsF;AACtF,MAAM,YAAY,GAAG,CAAC,IAAY,EAAE,EAAU,EAAE,IAAY,EAAE,MAAc,EAAW,EAAE;IACvF,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,CAAC,EAAE,GAAG,IAAI,CAAC,CAAC;IACpC,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;AAC9F,CAAC,CAAC;AAEF,MAAM,aAAa,GAAG,CAAC,IAAY,EAAE,EAAU,EAAE,MAAc,EAAW,EAAE,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,YAAY,CAAC,IAAI,EAAE,EAAE,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC;AAErJ,2IAA2I;AAC3I,MAAM,CAAC,MAAM,OAAO,GAAG,CAAC,QAAkB,EAAE,KAAgC,EAAE,MAAc,EAAU,EAAE;IACtG,MAAM,MAAM,GAAG,WAAW,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;IAC1C,OAAO,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,EAAE;QAClD,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QAC7B,IAAI,IAAI,KAAK,SAAS,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,EAAE,MAAM,CAAC;YAAE,OAAO,EAAE,CAAC;QAC/E,IAAI,WAAW,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE,CAAC;YAAE,OAAO,EAAE,CAAC;QAC3D,OAAO,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,CAAC,IAAI,CAAC,KAAK,GAAG,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;IACzF,CAAC,CAAC,CAAC;AACL,CAAC,CAAC;AAKF,MAAM,YAAY,GAAG,CAAC,IAAW,EAAE,MAAyB,EAAE,OAAgB,EAAW,EAAE,CAAC,CAAC;IAC3F,IAAI,EAAE,EAAE;IACR,QAAQ,EAAE,MAAM;IAChB,IAAI,EAAE,CAAC;IACP,MAAM,EAAE,CAAC;IACT,KAAK,EAAE,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,EAAE;IAChC,GAAG,CAAC,OAAO,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC;IAC7C,MAAM,EAAE,EAAE,GAAG,MAAM,EAAE,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE;CAC3C,CAAC,CAAC;AAEH,oHAAoH;AACpH,MAAM,gBAAgB,GAAG,CAAkB,KAAmB,EAAE,KAAa,EAAE,QAAwC,EAAa,EAAE;IACpI,MAAM,MAAM,GAAG,cAAc,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;IAC5C,IAAI,MAAM,KAAK,SAAS;QAAE,OAAO,EAAE,CAAC;IACpC,IAAI,MAAM,CAAC,IAAI,KAAK,OAAO,EAAE,CAAC;QAC5B,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,MAAM,CAAC;QAChD,OAAO,CAAC,YAAY,CAAC,KAAK,EAAE,EAAE,GAAG,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,EAAE,QAAQ,EAAE,KAAK,EAAE,GAAG,EAAE,EAAE,EAAE,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,OAAO,CAAC,CAAC,CAAC;IACvH,CAAC;IACD,OAAO,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,GAAG,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE,EAAE,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;AAChI,CAAC,CAAC;AAEF,qHAAqH;AACrH,MAAM,YAAY,GAAG,CAAC,GAAkB,EAAuB,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,QAAQ,CAAC,gBAAgB,KAAK,SAAS,CAAC,CAAC;AAE9I;;;;GAIG;AACH,MAAM,CAAC,MAAM,eAAe,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IACnE,MAAM,MAAM,GAAG,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;IACpC,IAAI,MAAM,KAAK,SAAS;QAAE,OAAO,EAAE,CAAC;IACpC,MAAM,KAAK,GAAG,OAAO,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC;IAC7C,MAAM,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,OAAO,CAAC,QAAQ,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC;IACxF,MAAM,KAAK,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IAChE,OAAO,KAAK,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CAC5B,gBAAgB,CACd,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,KAAK,IAAI,CAAC,EAC/C,OAAO,CAAC,KAAK,EACb,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC,CACxD,CACF,CAAC;AACJ,CAAC,CAAC;AAEF;;;GAGG;AACH,MAAM,YAAY,GAAG,4CAA4C,CAAC;AAClE,0HAA0H;AAC1H,MAAM,cAAc,GAAG,iBAAiB,CAAC;AACzC,MAAM,SAAS,GAAG,GAAG,CAAC;AACtB,MAAM,UAAU,GAAG,IAAI,CAAC;AAExB,0IAA0I;AAC1I,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,GAAkB,EAAW,EAAE,CAC1D,YAAY,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE,EAAE,SAAS,EAAE,EAAE;IACpD,MAAM,IAAI,GAAG,SAAS,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;IAC/B,IAAI,IAAI,KAAK,SAAS,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,EAAE,CAAC;IAC1G,MAAM,GAAG,GAAG,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACjE,IAAI,GAAG,KAAK,SAAS,IAAI,GAAG,KAAK,UAAU;QAAE,OAAO,EAAE,CAAC;IACvD,OAAO,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,KAAK,UAAU,EAAE,MAAM,EAAE,QAAQ,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC;AACrF,CAAC,CAAC,CAAC;AAEL,+FAA+F;AAC/F,MAAM,CAAC,MAAM,eAAe,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE,CACnE,gBAAgB,CAAC,YAAY,CAAC,GAAG,CAAC,EAAE,OAAO,CAAC,KAAK,EAAE,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;IAC3D,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,MAAM;IACzD,KAAK,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,CAAC,UAAU,CAAC,MAAM;CACzD,CAAC,CAAC,CAAC;AAIN,MAAM,UAAU,GAAG,CAAC,GAAQ,EAAE,KAAa,EAAE,KAAa,EAAW,EAAE,CAAC,CAAC;IACvE,IAAI,EAAE,EAAE;IACR,QAAQ,EAAE,MAAM;IAChB,IAAI,EAAE,CAAC;IACP,MAAM,EAAE,CAAC;IACT,KAAK,EAAE,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,EAAE;IAC/B,MAAM,EAAE,EAAE,OAAO,EAAE,GAAG,CAAC,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,CAAC,MAAM,EAAE;CACnE,CAAC,CAAC;AAEH,MAAM,MAAM,GAAG,CAAC,SAA8B,EAAE,OAAe,EAAS,EAAE,CACxE,SAAS,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE,CAC7B,CAAC,GAAG,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,EAAE,QAAQ,EAAE,OAAO,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,MAAM,EAAE,QAAQ,CAAC,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,KAAK,EAAE,CAAC,CAAC,CACzI,CAAC;AAEJ,MAAM,UAAU,GAAG,CAAC,IAAoB,EAAE,KAAa,EAAa,EAAE,CAAC,CAAC,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC;AAE3J,qHAAqH;AACrH,MAAM,WAAW,GAAG,6DAA6D,CAAC;AAElF,MAAM,CAAC,MAAM,UAAU,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE,CAAC,UAAU,CAAC,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,EAAE,WAAW,CAAC,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC;AAEnI,2GAA2G;AAC3G,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,YAAoB,EAAY,EAAE;IAC7D,MAAM,IAAI,GAAG,CAAC,GAAG,YAAY,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,IAAI,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IACjF,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC,IAAI,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC,OAAO,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,GAAG,EAAE,EAAE,CAAC,CAAC,IAAI,IAAI,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IACjI,OAAO,OAAO;SACX,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,OAAO,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC;SACvE,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,GAAG,YAAY,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;AAC/F,CAAC,CAAC;AAEF,6HAA6H;AAC7H,MAAM,cAAc,GAAG,CAAC,IAAY,EAAU,EAAE,CAC9C,kBAAkB,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,IAAI,YAAY,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,eAAe,CAAC;AAE9H,4GAA4G;AAC5G,MAAM,CAAC,MAAM,iBAAiB,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IACrE,MAAM,KAAK,GAAG,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC;IACtF,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IAClC,MAAM,OAAO,GAAG,IAAI,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IACtE,OAAO,UAAU,CAAC,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,EAAE,OAAO,CAAC,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC;AACvE,CAAC,CAAC;AAEF,0FAA0F;AAC1F,MAAM,WAAW,GAAG,CAAC,CAAC;AACtB,MAAM,QAAQ,GAAG,IAAI,MAAM,CAAC,sCAAsC,MAAM,CAAC,WAAW,GAAG,CAAC,CAAC,OAAO,EAAE,IAAI,CAAC,CAAC;AACxG,uGAAuG;AACvG,MAAM,cAAc,GAAG,CAAC,CAAC;AAEzB,MAAM,UAAU,GAAG,sBAAsB,CAAC;AAE1C,mHAAmH;AACnH,MAAM,CAAC,MAAM,cAAc,GAAG,CAAC,MAAc,EAAuB,EAAE,CACpE,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC;AAE5H;;;GAGG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG,CAAC,GAAW,EAAE,KAA0B,EAAE,YAAiC,EAAW,EAAE;IAChH,MAAM,KAAK,GAAG,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;IAChC,MAAM,QAAQ,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC;IAClG,MAAM,IAAI,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IACrD,OAAO,IAAI,CAAC,MAAM,IAAI,cAAc,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,GAAG,KAAK,CAAC,MAAM,CAAC;AAC7E,CAAC,CAAC;AAEF,4GAA4G;AAC5G,MAAM,CAAC,MAAM,YAAY,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IAChE,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,CAAC,KAAK,IAAI,GAAG,CAAC,MAAM,CAAC,CAAC;IACtD,MAAM,YAAY,GAAG,IAAI,GAAG,CAAC,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC;IACpF,MAAM,IAAI,GAAG,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,EAAE,QAAQ,CAAC,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,OAAO,EAAE,KAAK,EAAE,YAAY,CAAC,CAAC,CAAC;IAC/G,OAAO,UAAU,CAAC,IAAI,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC;AACzC,CAAC,CAAC"}

package/dist/detectors/misuse-match.d.ts

@@ -0,0 +1,7 @@
+import type { Detector } from "../plugin.ts";
+/**
+ * A phrase from a lexicon of established misuses, each entry carrying its correct form in `rewrite`. The message names
+ * both, so the writer does not have to look the right form up. One finding per sentence, for its first listed misuse.
+ */
+export declare const misuseMatch: Detector;
+//# sourceMappingURL=misuse-match.d.ts.map

package/dist/detectors/misuse-match.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"misuse-match.d.ts","sourceRoot":"","sources":["../../src/detectors/misuse-match.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAA4C,MAAM,cAAc,CAAC;AAmBvF;;;GAGG;AACH,eAAO,MAAM,WAAW,EAAE,QAIzB,CAAC"}

package/dist/detectors/misuse-match.js

@@ -0,0 +1,23 @@
+import { entryIn } from "./lexicon-match.js";
+const misuseIn = (sentence, lexicon) => {
+    const entry = lexicon.find((candidate) => entryIn(sentence, candidate));
+    return entry === undefined ? undefined : { sentence, entry };
+};
+const findingOf = (misuse, limit) => ({
+    rule: "",
+    severity: "warning",
+    line: 0,
+    column: 0,
+    quote: misuse.sentence.text.trim(),
+    values: { matched: misuse.entry.pattern, correct: misuse.entry.rewrite ?? "", limit, offset: misuse.sentence.span.start },
+});
+/**
+ * A phrase from a lexicon of established misuses, each entry carrying its correct form in `rewrite`. The message names
+ * both, so the writer does not have to look the right form up. One finding per sentence, for its first listed misuse.
+ */
+export const misuseMatch = (doc, options) => {
+    const lexicon = options.lexicon ?? [];
+    const misuses = doc.sentences.flatMap((sentence) => misuseIn(sentence, lexicon) ?? []);
+    return misuses.length < options.limit ? [] : misuses.map((misuse) => findingOf(misuse, options.limit));
+};
+//# sourceMappingURL=misuse-match.js.map

package/dist/detectors/misuse-match.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"misuse-match.js","sourceRoot":"","sources":["../../src/detectors/misuse-match.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,OAAO,EAAE,MAAM,oBAAoB,CAAC;AAI7C,MAAM,QAAQ,GAAG,CAAC,QAAkB,EAAE,OAAgB,EAAsB,EAAE;IAC5E,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC,CAAC;IACxE,OAAO,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,QAAQ,EAAE,KAAK,EAAE,CAAC;AAC/D,CAAC,CAAC;AAEF,MAAM,SAAS,GAAG,CAAC,MAAc,EAAE,KAAa,EAAW,EAAE,CAAC,CAAC;IAC7D,IAAI,EAAE,EAAE;IACR,QAAQ,EAAE,SAAS;IACnB,IAAI,EAAE,CAAC;IACP,MAAM,EAAE,CAAC;IACT,KAAK,EAAE,MAAM,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,EAAE;IAClC,MAAM,EAAE,EAAE,OAAO,EAAE,MAAM,CAAC,KAAK,CAAC,OAAO,EAAE,OAAO,EAAE,MAAM,CAAC,KAAK,CAAC,OAAO,IAAI,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,CAAC,QAAQ,CAAC,IAAI,CAAC,KAAK,EAAE;CAC1H,CAAC,CAAC;AAEH;;;GAGG;AACH,MAAM,CAAC,MAAM,WAAW,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IAC/D,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC;IACtC,MAAM,OAAO,GAAG,GAAG,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;IACvF,OAAO,OAAO,CAAC,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,SAAS,CAAC,MAAM,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC;AACzG,CAAC,CAAC"}

package/dist/detectors/modal-conflict.d.ts

@@ -1,4 +1,6 @@
-import type { Detector } from "../plugin.ts";
+import type { Detector, StructureNode } from "../plugin.ts";
+import { type Obligation } from "../structure/modal-conflict.ts";
+export declare const obligationsOf: (tree: StructureNode) => Obligation[];
 /** 同じ主語と行為に、前の文と逆の様相（しなければならない と してはならない、may と must not）を書いた文。 */
 export declare const modalConflict: Detector;
 //# sourceMappingURL=modal-conflict.d.ts.map

package/dist/detectors/modal-conflict.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"modal-conflict.d.ts","sourceRoot":"","sources":["../../src/detectors/modal-conflict.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAA0B,MAAM,cAAc,CAAC;AAarE,kEAAkE;AAClE,eAAO,MAAM,aAAa,EAAE,QAW3B,CAAC"}
+{"version":3,"file":"modal-conflict.d.ts","sourceRoot":"","sources":["../../src/detectors/modal-conflict.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAAW,aAAa,EAAE,MAAM,cAAc,CAAC;AAErE,OAAO,EAAmC,KAAK,UAAU,EAAE,MAAM,gCAAgC,CAAC;AAIlG,eAAO,MAAM,aAAa,GAAI,MAAM,aAAa,KAAG,UAAU,EAK3D,CAAC;AAEJ,kEAAkE;AAClE,eAAO,MAAM,aAAa,EAAE,QAW3B,CAAC"}

package/dist/detectors/modal-conflict.js

@@ -2,7 +2,7 @@ import { inDocumentOrder } from "../structure/issues.js";
 import { modalConflicts, modalStatements } from "../structure/modal-conflict.js";
 import { linesOf, lineNumberAt } from "../structure/lines.js";
 import { quoteAt } from "./structure-tree.js";
-const obligationsOf = (tree) => inDocumentOrder(tree).flatMap((node) => node.kind === "obligation"
+export const obligationsOf = (tree) => inDocumentOrder(tree).flatMap((node) => node.kind === "obligation"
     ? [{ start: node.span.start, end: node.span.end, type: String(node.attrs["type"] ?? ""), marker: String(node.attrs["marker"] ?? "") }]
     : []);
 /** 同じ主語と行為に、前の文と逆の様相（しなければならない と してはならない、may と must not）を書いた文。 */

package/dist/detectors/modal-conflict.js.map

@@ -1 +1 @@
-{"version":3,"file":"modal-conflict.js","sourceRoot":"","sources":["../../src/detectors/modal-conflict.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAC;AACzD,OAAO,EAAE,cAAc,EAAE,eAAe,EAAmB,MAAM,gCAAgC,CAAC;AAClG,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAC9D,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAE9C,MAAM,aAAa,GAAG,CAAC,IAAmB,EAAgB,EAAE,CAC1D,eAAe,CAAC,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CACrC,IAAI,CAAC,IAAI,KAAK,YAAY;IACxB,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,EAAE,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;IACtI,CAAC,CAAC,EAAE,CACP,CAAC;AAEJ,kEAAkE;AAClE,MAAM,CAAC,MAAM,aAAa,GAAa,CAAC,GAAG,EAAa,EAAE;IACxD,IAAI,GAAG,CAAC,SAAS,KAAK,SAAS;QAAE,OAAO,EAAE,CAAC;IAC3C,MAAM,KAAK,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;IAClC,OAAO,cAAc,CAAC,eAAe,CAAC,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,GAAG,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,SAAS,EAAE,OAAO,EAAE,EAAE,EAAE,CAAC,CAAC;QACnH,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,CAAC;QACP,MAAM,EAAE,CAAC;QACT,KAAK,EAAE,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,SAAS,CAAC,MAAM,CAAC;QAC5C,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,CAAC,MAAM,EAAE,KAAK,EAAE,OAAO,CAAC,MAAM,EAAE,SAAS,EAAE,YAAY,CAAC,KAAK,EAAE,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,SAAS,CAAC,MAAM,EAAE;KAC3I,CAAC,CAAC,CAAC;AACN,CAAC,CAAC"}
+{"version":3,"file":"modal-conflict.js","sourceRoot":"","sources":["../../src/detectors/modal-conflict.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAC;AACzD,OAAO,EAAE,cAAc,EAAE,eAAe,EAAmB,MAAM,gCAAgC,CAAC;AAClG,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAC9D,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAE9C,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,IAAmB,EAAgB,EAAE,CACjE,eAAe,CAAC,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CACrC,IAAI,CAAC,IAAI,KAAK,YAAY;IACxB,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,EAAE,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;IACtI,CAAC,CAAC,EAAE,CACP,CAAC;AAEJ,kEAAkE;AAClE,MAAM,CAAC,MAAM,aAAa,GAAa,CAAC,GAAG,EAAa,EAAE;IACxD,IAAI,GAAG,CAAC,SAAS,KAAK,SAAS;QAAE,OAAO,EAAE,CAAC;IAC3C,MAAM,KAAK,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;IAClC,OAAO,cAAc,CAAC,eAAe,CAAC,aAAa,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,GAAG,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,SAAS,EAAE,OAAO,EAAE,EAAE,EAAE,CAAC,CAAC;QACnH,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,CAAC;QACP,MAAM,EAAE,CAAC;QACT,KAAK,EAAE,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,SAAS,CAAC,MAAM,CAAC;QAC5C,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,CAAC,MAAM,EAAE,KAAK,EAAE,OAAO,CAAC,MAAM,EAAE,SAAS,EAAE,YAAY,CAAC,KAAK,EAAE,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,SAAS,CAAC,MAAM,EAAE;KAC3I,CAAC,CAAC,CAAC;AACN,CAAC,CAAC"}

package/dist/detectors/next-word.d.ts

@@ -0,0 +1,22 @@
+import type { Detector, Lexicon } from "../plugin.ts";
+/** The sound knowledge of lexicon article-sound, by group. */
+export type ArticleSounds = {
+    readonly vowelLetters: ReadonlySet<string>;
+    readonly vowelLetterNames: ReadonlySet<string>;
+    readonly eitherLetterNames: ReadonlySet<string>;
+    readonly consonant: readonly string[];
+    readonly vowel: readonly string[];
+    readonly word: ReadonlySet<string>;
+    readonly either: readonly string[];
+};
+export declare const articleSoundsOf: (lexicon: Lexicon) => ArticleSounds;
+/**
+ * Whether a word starts with a vowel sound. Capitals are read as the lexicon says (a NASA probe), else letter by letter when
+ * surely spelled out (an MBA). undefined when the word may be said both ways (a SQL, an SQL; a or an HTTP) or nothing says how.
+ */
+export declare const startsWithVowelSound: (word: string, sounds: ArticleSounds) => boolean | undefined;
+/** "a" before a vowel sound or "an" before a consonant sound (a apple, an user), by the sound knowledge in the lexicon. */
+export declare const articleSound: Detector;
+/** "very" + adjective, dense for the document's length: each one leans on "very" instead of a stronger word. */
+export declare const intensifiedAdjective: Detector;
+//# sourceMappingURL=next-word.d.ts.map

package/dist/detectors/next-word.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"next-word.d.ts","sourceRoot":"","sources":["../../src/detectors/next-word.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAAW,OAAO,EAAmB,MAAM,cAAc,CAAC;AAiBhF,8DAA8D;AAC9D,MAAM,MAAM,aAAa,GAAG;IAC1B,QAAQ,CAAC,YAAY,EAAE,WAAW,CAAC,MAAM,CAAC,CAAC;IAC3C,QAAQ,CAAC,gBAAgB,EAAE,WAAW,CAAC,MAAM,CAAC,CAAC;IAC/C,QAAQ,CAAC,iBAAiB,EAAE,WAAW,CAAC,MAAM,CAAC,CAAC;IAChD,QAAQ,CAAC,SAAS,EAAE,SAAS,MAAM,EAAE,CAAC;IACtC,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAClC,QAAQ,CAAC,IAAI,EAAE,WAAW,CAAC,MAAM,CAAC,CAAC;IACnC,QAAQ,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC;CACpC,CAAC;AAIF,eAAO,MAAM,eAAe,GAAI,SAAS,OAAO,KAAG,aAQjD,CAAC;AAoBH;;;GAGG;AACH,eAAO,MAAM,oBAAoB,GAAI,MAAM,MAAM,EAAE,QAAQ,aAAa,KAAG,OAAO,GAAG,SAMpF,CAAC;AA4CF,2HAA2H;AAC3H,eAAO,MAAM,YAAY,EAAE,QAU1B,CAAC;AAqBF,gHAAgH;AAChH,eAAO,MAAM,oBAAoB,EAAE,QAUlC,CAAC"}

package/dist/detectors/next-word.js

@@ -0,0 +1,125 @@
+import { densityFindings } from "./ai-phrasing.js";
+/**
+ * The word kinds an article can stand before. A conjunction, a preposition or a verb after "a" is the letter a ("option A
+ * or B", "a is the length").
+ */
+const CONTENT = new Set(["NOUN", "PROPN", "ADJ", "ADV", "NUM"]);
+const LETTER_START = /^\p{L}/u;
+const HAS_LOWER = /\p{Ll}/u;
+/** A lower-case letter before capitals (mRNA, pH is not): the first letter is said by its name. */
+const LETTER_BEFORE_CAPITALS = /^\p{Ll}\p{Lu}{2}/u;
+/** Two tokens with nothing but whitespace between them in the source. Code and markup are hidden from the tokens. */
+const adjacent = (source, left, right) => source.slice(left.span.end, right.span.start).trim() === "";
+const ofGroup = (lexicon, group) => lexicon.filter((entry) => entry.group === group).map((entry) => entry.pattern);
+export const articleSoundsOf = (lexicon) => ({
+    vowelLetters: new Set(ofGroup(lexicon, "vowel-letter")),
+    vowelLetterNames: new Set(ofGroup(lexicon, "letter-name-vowel")),
+    eitherLetterNames: new Set(ofGroup(lexicon, "letter-name-either")),
+    consonant: ofGroup(lexicon, "consonant"),
+    vowel: ofGroup(lexicon, "vowel"),
+    word: new Set(ofGroup(lexicon, "word")),
+    either: ofGroup(lexicon, "either"),
+});
+const startsWithAny = (word, starts) => starts.some((start) => word.startsWith(start));
+/** Whether a word in lower or mixed case starts with a vowel sound; undefined when it is said both ways. */
+const wordSound = (word, sounds) => {
+    const lower = word.toLowerCase();
+    if (startsWithAny(lower, sounds.either))
+        return undefined;
+    if (startsWithAny(lower, sounds.vowel))
+        return true;
+    if (startsWithAny(lower, sounds.consonant))
+        return false;
+    return sounds.vowelLetters.has(lower.charAt(0));
+};
+/** Capitals longer than this that hold a vowel may be said as a word (SALT, GIF), so only the lexicon decides them. */
+const SPELLED_OUT_LENGTH = 3;
+/** Whether capitals not in the lexicon are surely said letter by letter: short (MBA), or with no vowel to say (HTTP). */
+const isSpelledOut = (word, sounds) => word.length <= SPELLED_OUT_LENGTH || ![...word.toLowerCase()].some((letter) => sounds.vowelLetters.has(letter));
+/**
+ * Whether a word starts with a vowel sound. Capitals are read as the lexicon says (a NASA probe), else letter by letter when
+ * surely spelled out (an MBA). undefined when the word may be said both ways (a SQL, an SQL; a or an HTTP) or nothing says how.
+ */
+export const startsWithVowelSound = (word, sounds) => {
+    if (LETTER_BEFORE_CAPITALS.test(word))
+        return sounds.vowelLetterNames.has(word.charAt(0).toUpperCase());
+    if (HAS_LOWER.test(word))
+        return wordSound(word, sounds);
+    if (sounds.either.includes(word) || sounds.eitherLetterNames.has(word.charAt(0)))
+        return undefined;
+    if (sounds.word.has(word))
+        return wordSound(word, sounds);
+    return isSpelledOut(word, sounds) ? sounds.vowelLetterNames.has(word.charAt(0)) : undefined;
+};
+const ARTICLES = { a: false, an: true };
+/** The article the next word takes, written in the case of the one written ("A apple" → "An"). */
+const fitting = (written, vowel) => {
+    const article = vowel ? "an" : "a";
+    return written.charAt(0) === written.charAt(0).toUpperCase() ? `${article.charAt(0).toUpperCase()}${article.slice(1)}` : article;
+};
+/** An article that does not fit the sound of the word after it. */
+const WORD = /\p{L}/u;
+/**
+ * Whether a token is the article "a" or "an": lower case, or capitalised as the first word of the sentence. A capital A
+ * inside a sentence is a letter ("grade A eggs", "vitamin A intake").
+ */
+const isArticle = (token, at, tokens) => {
+    const first = tokens.findIndex((candidate) => WORD.test(candidate.surface));
+    return token.surface === token.surface.toLowerCase() || at === first;
+};
+const slipAt = (source, tokens, at, sounds) => {
+    const article = tokens[at];
+    const next = tokens[at + 1];
+    const takesAn = ARTICLES[article?.surface.toLowerCase() ?? ""];
+    if (article === undefined || next === undefined || takesAn === undefined || !isArticle(article, at, tokens))
+        return undefined;
+    if (!CONTENT.has(next.pos) || !LETTER_START.test(next.surface))
+        return undefined;
+    if (!adjacent(source, article, next))
+        return undefined;
+    const vowel = startsWithVowelSound(next.surface, sounds);
+    return vowel === undefined || vowel === takesAn ? undefined : { article, next, fits: fitting(article.surface, vowel) };
+};
+const slipFinding = (sentence, slip) => ({
+    rule: "",
+    severity: "warning",
+    line: 0,
+    column: 0,
+    quote: sentence.text.trim(),
+    values: { matched: `${slip.article.surface} ${slip.next.surface}`, article: slip.fits, offset: slip.article.span.start },
+});
+/** "a" before a vowel sound or "an" before a consonant sound (a apple, an user), by the sound knowledge in the lexicon. */
+export const articleSound = (doc, options) => {
+    const sounds = articleSoundsOf(options.lexicon ?? []);
+    const findings = doc.sentences.flatMap((sentence) => {
+        const tokens = sentence.tokens ?? [];
+        return tokens.flatMap((_token, at) => {
+            const slip = slipAt(doc.source, tokens, at, sounds);
+            return slip === undefined ? [] : [slipFinding(sentence, slip)];
+        });
+    });
+    return findings.length < options.limit ? [] : findings;
+};
+const ADJECTIVE = "ADJ";
+/** The lexicon's intensifier right before an adjective ("very important"), not before an excepted word ("the very first"). */
+const intensifiedIn = (source, sentence, words) => {
+    const tokens = sentence.tokens ?? [];
+    return tokens.flatMap((token, at) => {
+        const next = tokens[at + 1];
+        if (next === undefined || !words.intensifiers.has(token.surface.toLowerCase()) || next.pos !== ADJECTIVE)
+            return [];
+        if (!adjacent(source, token, next))
+            return [];
+        return words.exceptions.has(next.surface.toLowerCase()) ? [] : [{ sentence, matched: `${token.surface} ${next.surface}`, offset: token.span.start }];
+    });
+};
+const EXCEPTIONS = "very-exception";
+/** "very" + adjective, dense for the document's length: each one leans on "very" instead of a stronger word. */
+export const intensifiedAdjective = (doc, options) => {
+    const words = {
+        intensifiers: new Set((options.lexicon ?? []).map((entry) => entry.pattern)),
+        exceptions: new Set((doc.lexicons[EXCEPTIONS] ?? []).map((entry) => entry.pattern)),
+    };
+    return densityFindings(doc, doc.sentences.flatMap((sentence) => intensifiedIn(doc.source, sentence, words)), options.limit);
+};
+//# sourceMappingURL=next-word.js.map

package/dist/detectors/next-word.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"next-word.js","sourceRoot":"","sources":["../../src/detectors/next-word.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAEnD;;;GAGG;AACH,MAAM,OAAO,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,CAAC,CAAC;AAEhE,MAAM,YAAY,GAAG,SAAS,CAAC;AAC/B,MAAM,SAAS,GAAG,SAAS,CAAC;AAC5B,mGAAmG;AACnG,MAAM,sBAAsB,GAAG,mBAAmB,CAAC;AAEnD,qHAAqH;AACrH,MAAM,QAAQ,GAAG,CAAC,MAAc,EAAE,IAAW,EAAE,KAAY,EAAW,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,CAAC;AAarI,MAAM,OAAO,GAAG,CAAC,OAAgB,EAAE,KAAa,EAAY,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,KAAK,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;AAE9I,MAAM,CAAC,MAAM,eAAe,GAAG,CAAC,OAAgB,EAAiB,EAAE,CAAC,CAAC;IACnE,YAAY,EAAE,IAAI,GAAG,CAAC,OAAO,CAAC,OAAO,EAAE,cAAc,CAAC,CAAC;IACvD,gBAAgB,EAAE,IAAI,GAAG,CAAC,OAAO,CAAC,OAAO,EAAE,mBAAmB,CAAC,CAAC;IAChE,iBAAiB,EAAE,IAAI,GAAG,CAAC,OAAO,CAAC,OAAO,EAAE,oBAAoB,CAAC,CAAC;IAClE,SAAS,EAAE,OAAO,CAAC,OAAO,EAAE,WAAW,CAAC;IACxC,KAAK,EAAE,OAAO,CAAC,OAAO,EAAE,OAAO,CAAC;IAChC,IAAI,EAAE,IAAI,GAAG,CAAC,OAAO,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;IACvC,MAAM,EAAE,OAAO,CAAC,OAAO,EAAE,QAAQ,CAAC;CACnC,CAAC,CAAC;AAEH,MAAM,aAAa,GAAG,CAAC,IAAY,EAAE,MAAyB,EAAW,EAAE,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC;AAE3H,4GAA4G;AAC5G,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,MAAqB,EAAuB,EAAE;IAC7E,MAAM,KAAK,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC;IACjC,IAAI,aAAa,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,CAAC;QAAE,OAAO,SAAS,CAAC;IAC1D,IAAI,aAAa,CAAC,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC;QAAE,OAAO,IAAI,CAAC;IACpD,IAAI,aAAa,CAAC,KAAK,EAAE,MAAM,CAAC,SAAS,CAAC;QAAE,OAAO,KAAK,CAAC;IACzD,OAAO,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;AAClD,CAAC,CAAC;AAEF,uHAAuH;AACvH,MAAM,kBAAkB,GAAG,CAAC,CAAC;AAE7B,yHAAyH;AACzH,MAAM,YAAY,GAAG,CAAC,IAAY,EAAE,MAAqB,EAAW,EAAE,CACpE,IAAI,CAAC,MAAM,IAAI,kBAAkB,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC;AAElH;;;GAGG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,CAAC,IAAY,EAAE,MAAqB,EAAuB,EAAE;IAC/F,IAAI,sBAAsB,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,MAAM,CAAC,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC;IACxG,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,SAAS,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;IACzD,IAAI,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,MAAM,CAAC,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC;QAAE,OAAO,SAAS,CAAC;IACnG,IAAI,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;QAAE,OAAO,SAAS,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;IAC1D,OAAO,YAAY,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;AAC9F,CAAC,CAAC;AAEF,MAAM,QAAQ,GAAsC,EAAE,CAAC,EAAE,KAAK,EAAE,EAAE,EAAE,IAAI,EAAE,CAAC;AAE3E,kGAAkG;AAClG,MAAM,OAAO,GAAG,CAAC,OAAe,EAAE,KAAc,EAAU,EAAE;IAC1D,MAAM,OAAO,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC;IACnC,OAAO,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,KAAK,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC;AACnI,CAAC,CAAC;AAIF,mEAAmE;AACnE,MAAM,IAAI,GAAG,QAAQ,CAAC;AAEtB;;;GAGG;AACH,MAAM,SAAS,GAAG,CAAC,KAAY,EAAE,EAAU,EAAE,MAAwB,EAAW,EAAE;IAChF,MAAM,KAAK,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,CAAC;IAC5E,OAAO,KAAK,CAAC,OAAO,KAAK,KAAK,CAAC,OAAO,CAAC,WAAW,EAAE,IAAI,EAAE,KAAK,KAAK,CAAC;AACvE,CAAC,CAAC;AAEF,MAAM,MAAM,GAAG,CAAC,MAAc,EAAE,MAAwB,EAAE,EAAU,EAAE,MAAqB,EAAoB,EAAE;IAC/G,MAAM,OAAO,GAAG,MAAM,CAAC,EAAE,CAAC,CAAC;IAC3B,MAAM,IAAI,GAAG,MAAM,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;IAC5B,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,EAAE,OAAO,CAAC,WAAW,EAAE,IAAI,EAAE,CAAC,CAAC;IAC/D,IAAI,OAAO,KAAK,SAAS,IAAI,IAAI,KAAK,SAAS,IAAI,OAAO,KAAK,SAAS,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,EAAE,EAAE,MAAM,CAAC;QAAE,OAAO,SAAS,CAAC;IAC9H,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,SAAS,CAAC;IACjF,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,OAAO,EAAE,IAAI,CAAC;QAAE,OAAO,SAAS,CAAC;IACvD,MAAM,KAAK,GAAG,oBAAoB,CAAC,IAAI,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;IACzD,OAAO,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,EAAE,CAAC;AACzH,CAAC,CAAC;AAEF,MAAM,WAAW,GAAG,CAAC,QAAkB,EAAE,IAAU,EAAW,EAAE,CAAC,CAAC;IAChE,IAAI,EAAE,EAAE;IACR,QAAQ,EAAE,SAAS;IACnB,IAAI,EAAE,CAAC;IACP,MAAM,EAAE,CAAC;IACT,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,IAAI,EAAE;IAC3B,MAAM,EAAE,EAAE,OAAO,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,EAAE,OAAO,EAAE,IAAI,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,EAAE;CACzH,CAAC,CAAC;AAEH,2HAA2H;AAC3H,MAAM,CAAC,MAAM,YAAY,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IAChE,MAAM,MAAM,GAAG,eAAe,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC;IACtD,MAAM,QAAQ,GAAG,GAAG,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE;QAClD,MAAM,MAAM,GAAG,QAAQ,CAAC,MAAM,IAAI,EAAE,CAAC;QACrC,OAAO,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE;YACnC,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,CAAC,CAAC;YACpD,OAAO,IAAI,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,QAAQ,EAAE,IAAI,CAAC,CAAC,CAAC;QACjE,CAAC,CAAC,CAAC;IACL,CAAC,CAAC,CAAC;IACH,OAAO,QAAQ,CAAC,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC;AACzD,CAAC,CAAC;AAEF,MAAM,SAAS,GAAG,KAAK,CAAC;AAMxB,8HAA8H;AAC9H,MAAM,aAAa,GAAG,CAAC,MAAc,EAAE,QAAkB,EAAE,KAAuB,EAAiB,EAAE;IACnG,MAAM,MAAM,GAAG,QAAQ,CAAC,MAAM,IAAI,EAAE,CAAC;IACrC,OAAO,MAAM,CAAC,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,EAAE,EAAE;QAClC,MAAM,IAAI,GAAG,MAAM,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC;QAC5B,IAAI,IAAI,KAAK,SAAS,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,IAAI,IAAI,CAAC,GAAG,KAAK,SAAS;YAAE,OAAO,EAAE,CAAC;QACpH,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,KAAK,EAAE,IAAI,CAAC;YAAE,OAAO,EAAE,CAAC;QAC9C,OAAO,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,QAAQ,EAAE,OAAO,EAAE,GAAG,KAAK,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,EAAE,EAAE,MAAM,EAAE,KAAK,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC;IACvJ,CAAC,CAAC,CAAC;AACL,CAAC,CAAC;AAEF,MAAM,UAAU,GAAG,gBAAgB,CAAC;AAEpC,gHAAgH;AAChH,MAAM,CAAC,MAAM,oBAAoB,GAAa,CAAC,GAAG,EAAE,OAAO,EAAa,EAAE;IACxE,MAAM,KAAK,GAAG;QACZ,YAAY,EAAE,IAAI,GAAG,CAAC,CAAC,OAAO,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;QAC5E,UAAU,EAAE,IAAI,GAAG,CAAC,CAAC,GAAG,CAAC,QAAQ,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;KACpF,CAAC;IACF,OAAO,eAAe,CACpB,GAAG,EACH,GAAG,CAAC,SAAS,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,aAAa,CAAC,GAAG,CAAC,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CAAC,EAC/E,OAAO,CAAC,KAAK,CACd,CAAC;AACJ,CAAC,CAAC"}

package/dist/detectors/number-style.d.ts

@@ -0,0 +1,31 @@
+import type { Detector, Sentence } from "../plugin.ts";
+export type NumberKind = "count" | "grouping" | "percent" | "count-small" | "count-large";
+/** One number as written: its kind, the style it is written in, the text, and where it starts in the document. */
+export type NumberMark = {
+    readonly kind: NumberKind;
+    readonly style: string;
+    readonly written: string;
+    readonly offset: number;
+};
+/** The language's words for numbers. countWords is in order from one (the position is the value). */
+export type NumberWords = {
+    readonly counters: readonly string[];
+    readonly kanji: readonly string[];
+    readonly percentUnits: readonly string[];
+    readonly countWords: readonly string[];
+    /** Plural nouns of measure (days, miles) that take figures in every style: a number before one is not a count. */
+    readonly figureNouns: readonly string[];
+};
+/** Every number mark in a sentence, less those inside a quotation. */
+export declare const numberMarksIn: (sentence: Sentence, words: NumberWords, language: string, source: string) => NumberMark[];
+/**
+ * The marks not in the document's usual style, when they are few enough to be slips: at most limitPercent of the kind.
+ * The usual style is the most common one; on a tie, the one the document used first.
+ */
+export declare const minorityStyles: (marks: readonly NumberMark[], limitPercent: number) => {
+    readonly odd: NumberMark[];
+    readonly usual: NumberMark | undefined;
+};
+/** For each kind of number, the marks written in the document's less common style. */
+export declare const numberStyleConsistency: Detector;
+//# sourceMappingURL=number-style.d.ts.map

package/dist/detectors/number-style.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"number-style.d.ts","sourceRoot":"","sources":["../../src/detectors/number-style.ts"],"names":[],"mappings":"AAMA,OAAO,KAAK,EAAE,QAAQ,EAA0B,QAAQ,EAAe,MAAM,cAAc,CAAC;AAE5F,MAAM,MAAM,UAAU,GAAG,OAAO,GAAG,UAAU,GAAG,SAAS,GAAG,aAAa,GAAG,aAAa,CAAC;AAE1F,kHAAkH;AAClH,MAAM,MAAM,UAAU,GAAG;IAAE,QAAQ,CAAC,IAAI,EAAE,UAAU,CAAC;IAAC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC;AAElI,qGAAqG;AACrG,MAAM,MAAM,WAAW,GAAG;IACxB,QAAQ,CAAC,QAAQ,EAAE,SAAS,MAAM,EAAE,CAAC;IACrC,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAClC,QAAQ,CAAC,YAAY,EAAE,SAAS,MAAM,EAAE,CAAC;IACzC,QAAQ,CAAC,UAAU,EAAE,SAAS,MAAM,EAAE,CAAC;IACvC,kHAAkH;IAClH,QAAQ,CAAC,WAAW,EAAE,SAAS,MAAM,EAAE,CAAC;CACzC,CAAC;AAiJF,sEAAsE;AACtE,eAAO,MAAM,aAAa,GAAI,UAAU,QAAQ,EAAE,OAAO,WAAW,EAAE,UAAU,MAAM,EAAE,QAAQ,MAAM,KAAG,UAAU,EAUlH,CAAC;AAIF;;;GAGG;AACH,eAAO,MAAM,cAAc,GAAI,OAAO,SAAS,UAAU,EAAE,EAAE,cAAc,MAAM,KAAG;IAAE,QAAQ,CAAC,GAAG,EAAE,UAAU,EAAE,CAAC;IAAC,QAAQ,CAAC,KAAK,EAAE,UAAU,GAAG,SAAS,CAAA;CAQvJ,CAAC;AAyBF,sFAAsF;AACtF,eAAO,MAAM,sBAAsB,EAAE,QAUpC,CAAC"}