@kensio/pinyinjs 1.9.9 → 1.10.1

package/dist/sources/moe-workbook.js

@@ -0,0 +1,89 @@
+/**
+ * Taking the readings out of a 教育部 dictionary's workbook.
+ *
+ * The workbook has seventeen columns, and only the headword, the order of its
+ * readings, its 漢語拼音 and its variant reading are read. Definitions,
+ * examples, synonyms and the rest are never parsed. See `moe.ts` for what is
+ * done with the readings.
+ */
+import { HEADER_ROW, readRows, readSharedStrings } from "./xlsx.js";
+/**
+ * The columns this package reads, by the name the header row gives them.
+ *
+ * Found by name rather than by letter, because the two dictionaries lay their
+ * columns out differently: 《重編國語辭典修訂本》 has 漢語拼音 in column L and
+ * 《國語辭典簡編本》 in column J. A release that drops one fails the build
+ * rather than reading the wrong column.
+ */
+const HEADERS = {
+    word: "字詞名",
+    order: "多音排序",
+    pinyin: "漢語拼音",
+    variantKind: "變體類型",
+    variant: "變體漢語拼音",
+};
+/**
+ * The kinds of variant reading that are readings of the word itself.
+ */
+const VARIANT_KINDS = new Set(["又音", "語音", "讀音", "或讀"]);
+/**
+ * Turn a dictionary's worksheet into a table of headword, order and reading.
+ *
+ * Done once, when the download is cached, so the build reads a small table and
+ * never the 125 MB of XML the spreadsheet is made of. The output is one
+ * tab-separated line per reading, with a fourth column where the entry gives
+ * a variant reading, and the header row is dropped.
+ */
+export function tabulateMoeWorkbook(sharedStringsXml, sheetXml) {
+    const strings = readSharedStrings(sharedStringsXml);
+    const header = readRows(HEADER_ROW.exec(sheetXml)?.[0] ?? "", strings).get(1);
+    // 變體類型 carries its legend in the header, and the two dictionaries'
+    // legends differ, so a header is matched on how it starts.
+    const columnOf = (name) => {
+        const found = [...(header ?? [])].find(([, text]) => text.startsWith(name))?.[0];
+        if (found === undefined) {
+            throw new Error(`教育部 dictionary has no ${name} column`);
+        }
+        return found;
+    };
+    const columns = {
+        word: columnOf(HEADERS.word),
+        order: columnOf(HEADERS.order),
+        pinyin: columnOf(HEADERS.pinyin),
+        variantKind: columnOf(HEADERS.variantKind),
+        variant: columnOf(HEADERS.variant),
+    };
+    const rows = readRows(sheetXml, strings, new Set(Object.values(columns)));
+    const lines = [];
+    for (const [row, cells] of rows) {
+        const word = cells.get(columns.word) ?? "";
+        const pinyin = cells.get(columns.pinyin) ?? "";
+        if (row === 1 || word === "" || pinyin === "") {
+            continue;
+        }
+        const kind = cells.get(columns.variantKind) ?? "";
+        const variant = VARIANT_KINDS.has(kind)
+            ? (cells.get(columns.variant) ?? "")
+            : "";
+        lines.push([
+            word,
+            orderOf(cells.get(columns.order)),
+            spaced(pinyin),
+            ...(variant === "" ? [] : [spaced(variant)]),
+        ].join("\t"));
+    }
+    return `${lines.join("\n")}\n`;
+}
+/**
+ * A headword's 多音排序, which is blank for a headword with one reading.
+ */
+function orderOf(order) {
+    return order === undefined || order === "" ? "0" : order;
+}
+/**
+ * A reading with its syllables separated by single spaces.
+ */
+function spaced(pinyin) {
+    return pinyin.replaceAll(/\s+/gu, " ");
+}
+//# sourceMappingURL=moe-workbook.js.map

package/dist/sources/moe-workbook.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"moe-workbook.js","sourceRoot":"","sources":["../../src/sources/moe-workbook.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,iBAAiB,EAAE,MAAM,WAAW,CAAC;AAEpE;;;;;;;GAOG;AACH,MAAM,OAAO,GAAG;IACd,IAAI,EAAE,KAAK;IACX,KAAK,EAAE,MAAM;IACb,MAAM,EAAE,MAAM;IACd,WAAW,EAAE,MAAM;IACnB,OAAO,EAAE,QAAQ;CACT,CAAC;AAEX;;GAEG;AACH,MAAM,aAAa,GAAG,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC;AAExD;;;;;;;GAOG;AACH,MAAM,UAAU,mBAAmB,CACjC,gBAAwB,EACxB,QAAgB;IAEhB,MAAM,OAAO,GAAG,iBAAiB,CAAC,gBAAgB,CAAC,CAAC;IACpD,MAAM,MAAM,GAAG,QAAQ,CAAC,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;IAC9E,mEAAmE;IACnE,2DAA2D;IAC3D,MAAM,QAAQ,GAAG,CAAC,IAAY,EAAU,EAAE;QACxC,MAAM,KAAK,GAAG,CAAC,GAAG,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,EAAE,EAAE,CAClD,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,CACtB,EAAE,CAAC,CAAC,CAAC,CAAC;QACP,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,yBAAyB,IAAI,SAAS,CAAC,CAAC;QAC1D,CAAC;QACD,OAAO,KAAK,CAAC;IACf,CAAC,CAAC;IACF,MAAM,OAAO,GAAG;QACd,IAAI,EAAE,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC;QAC5B,KAAK,EAAE,QAAQ,CAAC,OAAO,CAAC,KAAK,CAAC;QAC9B,MAAM,EAAE,QAAQ,CAAC,OAAO,CAAC,MAAM,CAAC;QAChC,WAAW,EAAE,QAAQ,CAAC,OAAO,CAAC,WAAW,CAAC;QAC1C,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,OAAO,CAAC;KACnC,CAAC;IACF,MAAM,IAAI,GAAG,QAAQ,CAAC,QAAQ,EAAE,OAAO,EAAE,IAAI,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;IAE1E,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,IAAI,EAAE,CAAC;QAChC,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;QAC3C,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC;QAC/C,IAAI,GAAG,KAAK,CAAC,IAAI,IAAI,KAAK,EAAE,IAAI,MAAM,KAAK,EAAE,EAAE,CAAC;YAC9C,SAAS;QACX,CAAC;QACD,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC;QAClD,MAAM,OAAO,GAAG,aAAa,CAAC,GAAG,CAAC,IAAI,CAAC;YACrC,CAAC,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;YACpC,CAAC,CAAC,EAAE,CAAC;QACP,KAAK,CAAC,IAAI,CACR;YACE,IAAI;YACJ,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;YACjC,MAAM,CAAC,MAAM,CAAC;YACd,GAAG,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC;SAC7C,CAAC,IAAI,CAAC,IAAI,CAAC,CACb,CAAC;IACJ,CAAC;IACD,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC;AACjC,CAAC;AAED;;GAEG;AACH,SAAS,OAAO,CAAC,KAAyB;IACxC,OAAO,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC;AAC3D,CAAC;AAED;;GAEG;AACH,SAAS,MAAM,CAAC,MAAc;IAC5B,OAAO,MAAM,CAAC,UAAU,CAAC,OAAO,EAAE,GAAG,CAAC,CAAC;AACzC,CAAC"}

package/dist/sources/moe.d.ts

@@ -0,0 +1,58 @@
+/**
+ * Which of 教育部's two dictionaries a reading comes from.
+ *
+ * `concise` is 《國語辭典簡編本》, which describes current usage, and
+ * `revised` is 《重編國語辭典修訂本》, which adds the literary and historical.
+ */
+export type MoeDictionary = "concise" | "revised";
+/**
+ * One reading 教育部 gives a headword.
+ */
+export interface MoeReading {
+    readonly dictionary: MoeDictionary;
+    /**
+     * Where the reading stands among the headword's readings.
+     *
+     * 0 for a headword with one reading. A headword with several numbers them
+     * from 1, and 1 is the reading the dictionary lists first: 和 is `hé` at 1
+     * and `hàn` at 5, 期 `qí` at 1 and `qī` at 2.
+     */
+    readonly order: number;
+    /**
+     * The reading as tokens {@link import("../dictionary/reading.js").readAlignedReading}
+     * accepts, one per syllable, with 儿化 split off as its own `r5` token.
+     */
+    readonly readings: readonly string[];
+    /**
+     * A second reading the dictionary gives the same entry, where it gives one.
+     *
+     * Only the kinds that are readings of the word: 又音, an alternative, and
+     * the 語音 and 讀音 pair of colloquial and literary readings. 變, which
+     * records a tone change in connected speech such as 一 before a fourth tone,
+     * is left out, since the merge stores tones before sandhi.
+     */
+    readonly variant?: readonly string[];
+}
+/**
+ * Read the table {@link tabulateMoeWorkbook} writes, keyed by headword.
+ *
+ * Headwords are 繁體, as Taiwan writes them. A headword's readings come back
+ * in the dictionary's own order.
+ */
+export declare function parseMoeReadings(text: string, dictionary: MoeDictionary): ReadonlyMap<string, readonly MoeReading[]>;
+/**
+ * Two dictionaries' readings as one.
+ *
+ * 《國語辭典簡編本》 is the one that describes current usage, and for a word
+ * both list it wins. 《重編國語辭典修訂本》 is four times its size and records
+ * the literary and historical readings too, so where the two list a word it is
+ * often the older one that the larger dictionary leads with: 玩 is `wàn` there
+ * before `wán`, 鹽 `yàn` before `yán`, and 它們 is `tuō men`. Only the words
+ * the concise dictionary leaves out are taken from it.
+ *
+ * A character keeps the readings of both, the concise dictionary's first.
+ * The merge only ever asks whether a character's reading is listed, and the
+ * concise dictionary leaves out some current ones: it has no 差 `chà`.
+ */
+export declare function preferReadings(first: ReadonlyMap<string, readonly MoeReading[]>, second: ReadonlyMap<string, readonly MoeReading[]>): ReadonlyMap<string, readonly MoeReading[]>;
+//# sourceMappingURL=moe.d.ts.map

package/dist/sources/moe.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"moe.d.ts","sourceRoot":"","sources":["../../src/sources/moe.ts"],"names":[],"mappings":"AAaA;;;;;GAKG;AACH,MAAM,MAAM,aAAa,GAAG,SAAS,GAAG,SAAS,CAAC;AAElD;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,UAAU,EAAE,aAAa,CAAC;IACnC;;;;;;OAMG;IACH,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB;;;OAGG;IACH,QAAQ,CAAC,QAAQ,EAAE,SAAS,MAAM,EAAE,CAAC;IACrC;;;;;;;OAOG;IACH,QAAQ,CAAC,OAAO,CAAC,EAAE,SAAS,MAAM,EAAE,CAAC;CACtC;AAqBD;;;;;GAKG;AACH,wBAAgB,gBAAgB,CAC9B,IAAI,EAAE,MAAM,EACZ,UAAU,EAAE,aAAa,GACxB,WAAW,CAAC,MAAM,EAAE,SAAS,UAAU,EAAE,CAAC,CAqB5C;AAED;;;;;;;;;;;;;GAaG;AACH,wBAAgB,cAAc,CAC5B,KAAK,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,UAAU,EAAE,CAAC,EACjD,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,UAAU,EAAE,CAAC,GACjD,WAAW,CAAC,MAAM,EAAE,SAAS,UAAU,EAAE,CAAC,CAO5C"}

package/dist/sources/moe.js

@@ -0,0 +1,79 @@
+/**
+ * The readings of 教育部's two dictionaries of the 國語 standard,
+ * 《國語辭典簡編本》 and 《重編國語辭典修訂本》.
+ *
+ * Read from the table `moe-workbook.ts` takes out of each download, which holds
+ * a headword, the order of its readings, its 漢語拼音 and any variant reading,
+ * and nothing of the dictionaries' own text. See docs/dictionaries for why the
+ * readings alone are taken and what the licence says about them.
+ */
+import { isSingleCharacter } from "../script/characters.js";
+import { readSyllable } from "../syllable/syllable.js";
+import { ERHUA_TOKEN } from "../dictionary/reading.js";
+/**
+ * Split a reading into the tokens the merge aligns against a headword.
+ *
+ * 教育部 writes 儿化 on the syllable, as `yī huǐr` for 一會兒, where the merge
+ * expects CC-CEDICT's shape of a syllable followed by `r5`. A syllable that
+ * reads as 儿化 is split back into that shape, which leaves 兒 with a token to
+ * account for it; `ér` and `èr` are syllables of their own and stay whole.
+ */
+function tokensOf(pinyin) {
+    return pinyin
+        .split(" ")
+        .filter((token) => token !== "")
+        .flatMap((token) => readSyllable(token)?.erhua === true
+        ? [token.slice(0, -1), ERHUA_TOKEN]
+        : [token]);
+}
+/**
+ * Read the table {@link tabulateMoeWorkbook} writes, keyed by headword.
+ *
+ * Headwords are 繁體, as Taiwan writes them. A headword's readings come back
+ * in the dictionary's own order.
+ */
+export function parseMoeReadings(text, dictionary) {
+    const readings = new Map();
+    for (const line of text.split("\n")) {
+        const [word = "", order = "", pinyin = "", variant = ""] = line.split("\t");
+        if (word === "" || pinyin === "") {
+            continue;
+        }
+        const headword = word.normalize("NFC");
+        const listed = readings.get(headword) ?? [];
+        listed.push({
+            dictionary,
+            order: Number(order) || 0,
+            readings: tokensOf(pinyin),
+            ...(variant !== "" && { variant: tokensOf(variant) }),
+        });
+        readings.set(headword, listed);
+    }
+    for (const listed of readings.values()) {
+        listed.sort((left, right) => left.order - right.order);
+    }
+    return readings;
+}
+/**
+ * Two dictionaries' readings as one.
+ *
+ * 《國語辭典簡編本》 is the one that describes current usage, and for a word
+ * both list it wins. 《重編國語辭典修訂本》 is four times its size and records
+ * the literary and historical readings too, so where the two list a word it is
+ * often the older one that the larger dictionary leads with: 玩 is `wàn` there
+ * before `wán`, 鹽 `yàn` before `yán`, and 它們 is `tuō men`. Only the words
+ * the concise dictionary leaves out are taken from it.
+ *
+ * A character keeps the readings of both, the concise dictionary's first.
+ * The merge only ever asks whether a character's reading is listed, and the
+ * concise dictionary leaves out some current ones: it has no 差 `chà`.
+ */
+export function preferReadings(first, second) {
+    const merged = new Map(second);
+    for (const [word, readings] of first) {
+        const extra = isSingleCharacter(word) ? (second.get(word) ?? []) : [];
+        merged.set(word, [...readings, ...extra]);
+    }
+    return merged;
+}
+//# sourceMappingURL=moe.js.map

package/dist/sources/moe.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"moe.js","sourceRoot":"","sources":["../../src/sources/moe.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AACvD,OAAO,EAAE,WAAW,EAAE,MAAM,0BAA0B,CAAC;AAuCvD;;;;;;;GAOG;AACH,SAAS,QAAQ,CAAC,MAAc;IAC9B,OAAO,MAAM;SACV,KAAK,CAAC,GAAG,CAAC;SACV,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,KAAK,EAAE,CAAC;SAC/B,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE,CACjB,YAAY,CAAC,KAAK,CAAC,EAAE,KAAK,KAAK,IAAI;QACjC,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,WAAW,CAAC;QACnC,CAAC,CAAC,CAAC,KAAK,CAAC,CACZ,CAAC;AACN,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,gBAAgB,CAC9B,IAAY,EACZ,UAAyB;IAEzB,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAwB,CAAC;IACjD,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,MAAM,CAAC,IAAI,GAAG,EAAE,EAAE,KAAK,GAAG,EAAE,EAAE,MAAM,GAAG,EAAE,EAAE,OAAO,GAAG,EAAE,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC5E,IAAI,IAAI,KAAK,EAAE,IAAI,MAAM,KAAK,EAAE,EAAE,CAAC;YACjC,SAAS;QACX,CAAC;QACD,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;QACvC,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC;QAC5C,MAAM,CAAC,IAAI,CAAC;YACV,UAAU;YACV,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC;YACzB,QAAQ,EAAE,QAAQ,CAAC,MAAM,CAAC;YAC1B,GAAG,CAAC,OAAO,KAAK,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;SACtD,CAAC,CAAC;QACH,QAAQ,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;IACjC,CAAC;IACD,KAAK,MAAM,MAAM,IAAI,QAAQ,CAAC,MAAM,EAAE,EAAE,CAAC;QACvC,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC;IACzD,CAAC;IACD,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;;;;;;;;;;;;GAaG;AACH,MAAM,UAAU,cAAc,CAC5B,KAAiD,EACjD,MAAkD;IAElD,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,MAAM,CAAC,CAAC;IAC/B,KAAK,MAAM,CAAC,IAAI,EAAE,QAAQ,CAAC,IAAI,KAAK,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QACtE,MAAM,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,GAAG,QAAQ,EAAE,GAAG,KAAK,CAAC,CAAC,CAAC;IAC5C,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC"}

package/dist/sources/xlsx.d.ts

@@ -0,0 +1,20 @@
+/**
+ * Reading cells out of a spreadsheet's XML, as an `.xlsx` workbook stores
+ * them: a worksheet of cells, and a table of the strings they share.
+ *
+ * Only as much of the format as 教育部's downloads use. Formulas, styles and
+ * the other sheets of a workbook are never read.
+ */
+/**
+ * The header row of a worksheet.
+ */
+export declare const HEADER_ROW: RegExp;
+/**
+ * Read the workbook's shared string table.
+ */
+export declare function readSharedStrings(xml: string): readonly string[];
+/**
+ * Read a worksheet's cells into rows, keeping only the columns asked for.
+ */
+export declare function readRows(sheetXml: string, strings: readonly string[], wanted?: ReadonlySet<string>): Map<number, Map<string, string>>;
+//# sourceMappingURL=xlsx.d.ts.map

package/dist/sources/xlsx.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"xlsx.d.ts","sourceRoot":"","sources":["../../src/sources/xlsx.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH;;GAEG;AACH,eAAO,MAAM,UAAU,QAA+B,CAAC;AAsCvD;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,GAAG,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,CAIhE;AAED;;GAEG;AACH,wBAAgB,QAAQ,CACtB,QAAQ,EAAE,MAAM,EAChB,OAAO,EAAE,SAAS,MAAM,EAAE,EAC1B,MAAM,CAAC,EAAE,WAAW,CAAC,MAAM,CAAC,GAC3B,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CA0BlC"}

package/dist/sources/xlsx.js

@@ -0,0 +1,78 @@
+/**
+ * Reading cells out of a spreadsheet's XML, as an `.xlsx` workbook stores
+ * them: a worksheet of cells, and a table of the strings they share.
+ *
+ * Only as much of the format as 教育部's downloads use. Formulas, styles and
+ * the other sheets of a workbook are never read.
+ */
+/**
+ * The header row of a worksheet.
+ */
+export const HEADER_ROW = /<row r="1"[\s\S]*?<\/row>/u;
+/**
+ * One cell of a worksheet: its attributes and whatever is inside it.
+ */
+const CELL = /<c ([^>]*?)(?:\/>|>([\s\S]*?)<\/c>)/gu;
+/**
+ * One entry of the shared string table.
+ */
+const SHARED_STRING = /<si>([\s\S]*?)<\/si>/gu;
+/**
+ * The text runs of a string, which rich text splits into several.
+ */
+const TEXT_RUN = /<t(?: [^>]*)?>([^<]*)<\/t>/gu;
+/**
+ * Undo the escaping XML applies to text.
+ */
+function unescapeXml(text) {
+    return text
+        .replaceAll("&lt;", "<")
+        .replaceAll("&gt;", ">")
+        .replaceAll("&quot;", '"')
+        .replaceAll("&apos;", "'")
+        .replaceAll("&amp;", "&");
+}
+/**
+ * The text of a cell's string, joining its runs.
+ */
+function textOf(xml) {
+    return unescapeXml([...xml.matchAll(TEXT_RUN)].map((run) => run[1] ?? "").join(""));
+}
+/**
+ * Read the workbook's shared string table.
+ */
+export function readSharedStrings(xml) {
+    return [...xml.matchAll(SHARED_STRING)].map((entry) => textOf(entry[1] ?? ""));
+}
+/**
+ * Read a worksheet's cells into rows, keeping only the columns asked for.
+ */
+export function readRows(sheetXml, strings, wanted) {
+    const rows = new Map();
+    for (const cell of sheetXml.matchAll(CELL)) {
+        const attributes = cell[1] ?? "";
+        const reference = /\br="([A-Z]+)(\d+)"/u.exec(attributes);
+        const column = reference?.[1];
+        if (column === undefined || wanted?.has(column) === false) {
+            continue;
+        }
+        const body = cell[2] ?? "";
+        const value = /<v>([^<]*)<\/v>/u.exec(body)?.[1];
+        let text;
+        if (/\bt="s"/u.test(attributes)) {
+            text = strings[Number(value)] ?? "";
+        }
+        else if (value === undefined) {
+            text = textOf(body);
+        }
+        else {
+            text = unescapeXml(value);
+        }
+        const row = Number(reference?.[2]);
+        const cells = rows.get(row) ?? new Map();
+        cells.set(column, text.trim());
+        rows.set(row, cells);
+    }
+    return rows;
+}
+//# sourceMappingURL=xlsx.js.map

package/dist/sources/xlsx.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"xlsx.js","sourceRoot":"","sources":["../../src/sources/xlsx.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG,4BAA4B,CAAC;AAEvD;;GAEG;AACH,MAAM,IAAI,GAAG,uCAAuC,CAAC;AAErD;;GAEG;AACH,MAAM,aAAa,GAAG,wBAAwB,CAAC;AAE/C;;GAEG;AACH,MAAM,QAAQ,GAAG,8BAA8B,CAAC;AAEhD;;GAEG;AACH,SAAS,WAAW,CAAC,IAAY;IAC/B,OAAO,IAAI;SACR,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC;SACvB,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC;SACvB,UAAU,CAAC,QAAQ,EAAE,GAAG,CAAC;SACzB,UAAU,CAAC,QAAQ,EAAE,GAAG,CAAC;SACzB,UAAU,CAAC,OAAO,EAAE,GAAG,CAAC,CAAC;AAC9B,CAAC;AAED;;GAEG;AACH,SAAS,MAAM,CAAC,GAAW;IACzB,OAAO,WAAW,CAChB,CAAC,GAAG,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAChE,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,iBAAiB,CAAC,GAAW;IAC3C,OAAO,CAAC,GAAG,GAAG,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CACpD,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CACvB,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,QAAQ,CACtB,QAAgB,EAChB,OAA0B,EAC1B,MAA4B;IAE5B,MAAM,IAAI,GAAG,IAAI,GAAG,EAA+B,CAAC;IACpD,KAAK,MAAM,IAAI,IAAI,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;QAC3C,MAAM,UAAU,GAAG,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QACjC,MAAM,SAAS,GAAG,sBAAsB,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;QAC1D,MAAM,MAAM,GAAG,SAAS,EAAE,CAAC,CAAC,CAAC,CAAC;QAC9B,IAAI,MAAM,KAAK,SAAS,IAAI,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,KAAK,KAAK,EAAE,CAAC;YAC1D,SAAS;QACX,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QAC3B,MAAM,KAAK,GAAG,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;QACjD,IAAI,IAAY,CAAC;QACjB,IAAI,UAAU,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;YAChC,IAAI,GAAG,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAC;QACtC,CAAC;aAAM,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YAC/B,IAAI,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC;QACtB,CAAC;aAAM,CAAC;YACN,IAAI,GAAG,WAAW,CAAC,KAAK,CAAC,CAAC;QAC5B,CAAC;QACD,MAAM,GAAG,GAAG,MAAM,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QACnC,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,EAAkB,CAAC;QACzD,KAAK,CAAC,GAAG,CAAC,MAAM,EAAE,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;QAC/B,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,KAAK,CAAC,CAAC;IACvB,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kensio/pinyinjs",
-  "version": "1.9.9",
+  "version": "1.10.1",
   "description": "Chinese hanzi to pinyin conversion",
   "repository": "https://github.com/KensioSoftware/pinyinjs",
   "homepage": "https://pinyinjs.dev",