p-spore 0.1.3 → 0.1.42

package/dist/documents/extract.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"extract.js","sourceRoot":"","sources":["../../src/documents/extract.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AAElD,OAAO,EAAE,wBAAwB,EAAE,MAAM,aAAa,CAAC;AACvD,OAAO,EAAE,gBAAgB,EAAE,aAAa,EAAE,MAAM,oBAAoB,CAAC;AACrE,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,UAAU,CAAC;AACrD,OAAO,EAAE,eAAe,EAAE,YAAY,EAAE,MAAM,YAAY,CAAC;AAC3D,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,UAAU,CAAC;AACpD,OAAO,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,iBAAiB,CAAC;AAC5D,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,UAAU,CAAC;AAEpD,OAAO,EAAE,wBAAwB,EAAE,MAAM,aAAa,CAAC;AAmCvD,MAAM,CAAC,MAAM,0BAA0B,GAAG,EAAE,GAAG,IAAI,GAAG,IAAI,CAAC;AAC3D,MAAM,CAAC,MAAM,kBAAkB,GAAG,OAAO,CAAC;AAE1C,MAAM,aAAa,GAA6C;IAC9D,IAAI,EAAE,SAAS;IACf,IAAI,EAAE,WAAW;IACjB,IAAI,EAAE,iBAAiB;IACvB,GAAG,EAAE,iBAAiB;IACtB,GAAG,EAAE,mBAAmB;IACxB,GAAG,EAAE,yBAAyB;IAC9B,GAAG,EAAE,QAAQ;IACb,IAAI,EAAE,KAAK;CACZ,CAAC;AAEF,MAAM,CAAC,KAAK,UAAU,eAAe,CAAC,IAAY,EAAE,UAA0B,EAAE;IAC9E,MAAM,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,0BAA0B,CAAC;IAChE,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,IAAI,kBAAkB,CAAC;IAElD,MAAM,KAAK,GAAG,MAAM,IAAI,CAAC,IAAI,CAAC,CAAC;IAC/B,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE;QAAE,MAAM,IAAI,wBAAwB,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC;IAC3E,IAAI,KAAK,CAAC,IAAI,GAAG,QAAQ,EAAE,CAAC;QAC1B,MAAM,IAAI,wBAAwB,CAAC,QAAQ,QAAQ,aAAa,IAAI,EAAE,CAAC,CAAC;IAC1E,CAAC;IACD,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,IAAI,CAAC,CAAC;IACpC,MAAM,SAAS,GAAG,MAAM,aAAa,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;IACpD,OAAO,UAAU,CAAC,EAAE,GAAG,SAAS,EAAE,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,EAAE,KAAK,CAAC,CAAC;AACnE,CAAC;AAED,KAAK,UAAU,aAAa,CAAC,MAAc,EAAE,IAAY;IACvD,IAAI,YAAY,CAAC,MAAM,CAAC,EAAE,CAAC;QACzB,MAAM,OAAO,GAAG,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACxC,MAAM,IAAI,GAAG,eAAe,CAAC,OAAO,CAAC,CAAC;QACtC,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,MAAM,IAAI,wBAAwB,CAChC,GAAG,IAAI,8CAA8C,OAAO,CAAC,KAAK,EAAE,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAC/F,CAAC;QACJ,CAAC;QACD,MAAM,QAAQ,GAAG,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,CAAC;QAC7C,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,WAAW,EAAE,aAAa,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,QAAQ,CAAC,IAAI,EAAE,QAAQ,EAAE,QAAQ,CAAC,QAAQ,EAAE,CAAC;IACpH,CAAC;IAED,IAAI,YAAY,CAAC,MAAM,CAAC,EAAE,CAAC;QACzB,MAAM,QAAQ,GAAG,WAAW,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QAC1C,MAAM,IAAI,GAAG,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QACxC,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,qEAAqE;YACrE,kDAAkD;YAClD,MAAM,IAAI,wBAAwB,CAChC,GAAG,IAAI,6CAA6C,QAAQ,CAAC,KAAK,EAAE,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI;kBAC7F,iDAAiD,CACpD,CAAC;QACJ,CAAC;QACD,MAAM,SAAS,GAAG,aAAa,CAAC,QAAQ,EAAE,IAAI,CAAC,CAAC;QAChD,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,WAAW,EAAE,aAAa,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,SAAS,CAAC,IAAI,EAAE,QAAQ,EAAE,SAAS,CAAC,QAAQ,EAAE,CAAC;IACtH,CAAC;IAED,IAAI,YAAY,CAAC,MAAM,CAAC,EAAE,CAAC;QACzB,MAAM,QAAQ,GAAG,MAAM,UAAU,CAAC,MAAM,CAAC,CAAC;QAC1C,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,WAAW,EAAE,aAAa,CAAC,GAAG,EAAE,IAAI,EAAE,QAAQ,CAAC,IAAI,EAAE,QAAQ,EAAE,QAAQ,CAAC,QAAQ,EAAE,CAAC;IACnH,CAAC;IAED,IAAI,aAAa,CAAC,MAAM,CAAC,EAAE,CAAC;QAC1B,MAAM,OAAO,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC;QACnC,OAAO;YACL,IAAI;YACJ,MAAM,EAAE,MAAM;YACd,WAAW,EAAE,aAAa,CAAC,IAAI;YAC/B,IAAI,EAAE,OAAO,CAAC,IAAI;YAClB,QAAQ,EAAE,EAAE;YACZ,QAAQ,EAAE,OAAO,CAAC,QAAQ;SAC3B,CAAC;IACJ,CAAC;IAED,MAAM,IAAI,wBAAwB,CAChC,eAAe,IAAI,WAAW,CAAC,GAAG,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CACxH,CAAC;AACJ,CAAC;AAED;;;;;GAKG;AACH,SAAS,UAAU,CAAC,QAA2B,EAAE,KAAa;IAC5D,IAAI,QAAQ,CAAC,IAAI,CAAC,MAAM,IAAI,KAAK;QAAE,OAAO,QAAQ,CAAC;IACnD,OAAO;QACL,GAAG,QAAQ;QACX,IAAI,EAAE,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC;QACnC,QAAQ,EAAE,EAAE;QACZ,aAAa,EAAE,QAAQ,CAAC,IAAI,CAAC,MAAM;KACpC,CAAC;AACJ,CAAC"}

package/dist/documents/legacy-office.d.ts

@@ -0,0 +1,23 @@
+import { OleDocument } from "./ole.js";
+/**
+ * Text out of the pre-2007 binary Office formats.
+ *
+ * Each of the three keeps its text somewhere different inside the compound
+ * document, and none of them stores it as a contiguous run, so the shape of
+ * every function here follows the format rather than a shared abstraction.
+ * The goal throughout is the words on the page: layout, styling and revision
+ * history are deliberately dropped.
+ */
+export type LegacyKind = "doc" | "xls" | "ppt";
+export interface LegacyDocument {
+    kind: LegacyKind;
+    text: string;
+    sections: readonly {
+        name: string;
+        text: string;
+    }[];
+}
+/** Which legacy format a compound document holds, decided by its streams. */
+export declare function detectLegacyKind(document: OleDocument): LegacyKind | undefined;
+export declare function extractLegacy(document: OleDocument, kind: LegacyKind): LegacyDocument;
+//# sourceMappingURL=legacy-office.d.ts.map

package/dist/documents/legacy-office.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"legacy-office.d.ts","sourceRoot":"","sources":["../../src/documents/legacy-office.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,UAAU,CAAC;AAEvC;;;;;;;;GAQG;AAEH,MAAM,MAAM,UAAU,GAAG,KAAK,GAAG,KAAK,GAAG,KAAK,CAAC;AAE/C,MAAM,WAAW,cAAc;IAC7B,IAAI,EAAE,UAAU,CAAC;IACjB,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,SAAS;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;CACrD;AAED,6EAA6E;AAC7E,wBAAgB,gBAAgB,CAAC,QAAQ,EAAE,WAAW,GAAG,UAAU,GAAG,SAAS,CAK9E;AAED,wBAAgB,aAAa,CAAC,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,UAAU,GAAG,cAAc,CAIrF"}

package/dist/documents/legacy-office.js

@@ -0,0 +1,439 @@
+import { OleDocument } from "./ole.js";
+/** Which legacy format a compound document holds, decided by its streams. */
+export function detectLegacyKind(document) {
+    if (document.has("WordDocument"))
+        return "doc";
+    if (document.has("Workbook") || document.has("Book"))
+        return "xls";
+    if (document.has("PowerPoint Document"))
+        return "ppt";
+    return undefined;
+}
+export function extractLegacy(document, kind) {
+    if (kind === "doc")
+        return { kind, text: extractWord(document), sections: [] };
+    if (kind === "xls")
+        return extractWorkbook(document);
+    return extractPresentation(document);
+}
+// ---------------------------------------------------------------------------
+// Word 97-2003
+// ---------------------------------------------------------------------------
+/** Offsets into the File Information Block, which is fixed for Word 97 onwards. */
+const FIB_FLAGS = 0x000a;
+const FIB_CCP_TEXT = 0x004c;
+const FIB_FC_CLX = 0x01a2;
+const FIB_LCB_CLX = 0x01a6;
+/** Bit 9 of the FIB flags picks which of the two table streams is in use. */
+const FIB_WHICH_TABLE_STREAM = 0x0200;
+/**
+ * Word does not store its text in reading order. The document is a sequence of
+ * pieces, and the piece table in the table stream says where each one lives and
+ * whether it was written as 8-bit or 16-bit characters. Reading the text stream
+ * directly returns the pieces in whatever order editing left them.
+ */
+function extractWord(document) {
+    const main = document.read("WordDocument");
+    if (!main || main.length < FIB_LCB_CLX + 4)
+        throw new Error("Word document has no readable FIB");
+    const useOneTable = (main.readUInt16LE(FIB_FLAGS) & FIB_WHICH_TABLE_STREAM) !== 0;
+    const table = document.read(useOneTable ? "1Table" : "0Table") ?? document.read("1Table") ?? document.read("0Table");
+    const characterCount = main.readUInt32LE(FIB_CCP_TEXT);
+    if (!table) {
+        // A document written by a very old release keeps its text contiguously from
+        // the start of the text stream, with no piece table to consult.
+        return collapse(decodeWordRun(main.subarray(0x0800, 0x0800 + characterCount), true));
+    }
+    const clxOffset = main.readUInt32LE(FIB_FC_CLX);
+    const clxLength = main.readUInt32LE(FIB_LCB_CLX);
+    const pieces = readPieceTable(table.subarray(clxOffset, clxOffset + clxLength), characterCount);
+    let text = "";
+    for (const piece of pieces) {
+        text += decodeWordRun(main.subarray(piece.offset, piece.offset + piece.byteLength), piece.compressed);
+    }
+    return collapse(text);
+}
+/**
+ * Walks the CLX to its piece table. The CLX is a list of property runs, each
+ * introduced by 0x01, followed by the piece table introduced by 0x02, so the
+ * property runs have to be stepped over rather than searched past.
+ */
+function readPieceTable(clx, characterCount) {
+    let cursor = 0;
+    while (cursor < clx.length && clx[cursor] === 0x01) {
+        if (cursor + 3 > clx.length)
+            return [];
+        cursor += 3 + clx.readUInt16LE(cursor + 1);
+    }
+    if (cursor >= clx.length || clx[cursor] !== 0x02 || cursor + 5 > clx.length)
+        return [];
+    const length = clx.readUInt32LE(cursor + 1);
+    const table = clx.subarray(cursor + 5, cursor + 5 + length);
+    // The table is (n + 1) character positions followed by n 8-byte descriptors,
+    // which is what fixes n for a given length.
+    const count = Math.floor((table.length - 4) / 12);
+    const pieces = [];
+    for (let index = 0; index < count; index += 1) {
+        const start = table.readUInt32LE(index * 4);
+        const end = table.readUInt32LE((index + 1) * 4);
+        if (end <= start || start > characterCount)
+            continue;
+        const descriptor = (count + 1) * 4 + index * 8;
+        if (descriptor + 8 > table.length)
+            break;
+        const fc = table.readUInt32LE(descriptor + 2);
+        // Bit 30 marks a piece written one byte per character; clearing it and
+        // halving the remainder gives the byte offset of a compressed piece.
+        const compressed = (fc & 0x40000000) !== 0;
+        const offset = compressed ? (fc & 0x3fffffff) >>> 1 : fc & 0x3fffffff;
+        const characters = end - start;
+        pieces.push({ offset, byteLength: compressed ? characters : characters * 2, compressed });
+    }
+    return pieces;
+}
+/**
+ * Word's control characters, mapped to what they mean to a reader. Everything
+ * below a space that is not listed marks a field or an anchor and is dropped.
+ */
+function decodeWordRun(run, compressed) {
+    const decoded = compressed
+        // A compressed piece is Windows-1252 with a handful of remapped positions;
+        // for the CJK documents this exists to read, those pieces are pure ASCII.
+        ? new TextDecoder("windows-1252").decode(run)
+        : new TextDecoder("utf-16le").decode(run);
+    let text = "";
+    for (const character of decoded) {
+        const code = character.codePointAt(0) ?? 0;
+        if (code === 0x0d || code === 0x07)
+            text += "\n";
+        else if (code === 0x0b)
+            text += "\n";
+        else if (code === 0x09)
+            text += "\t";
+        else if (code === 0x0c)
+            text += "\n\n";
+        else if (code === 0x1e)
+            text += "-";
+        else if (code === 0x1f)
+            text += "";
+        else if (code >= 0x20 || code === 0x0a)
+            text += character;
+    }
+    return text;
+}
+// ---------------------------------------------------------------------------
+// Excel 97-2003
+// ---------------------------------------------------------------------------
+const RECORD_FORMULA = 0x0006;
+const RECORD_EOF = 0x000a;
+const RECORD_CONTINUE = 0x003c;
+const RECORD_BOUNDSHEET = 0x0085;
+const RECORD_SST = 0x00fc;
+const RECORD_LABELSST = 0x00fd;
+const RECORD_MULRK = 0x00bd;
+const RECORD_BOF = 0x0809;
+const RECORD_RK = 0x027e;
+const RECORD_LABEL = 0x0204;
+const RECORD_NUMBER = 0x0203;
+const RECORD_STRING = 0x0207;
+const RECORD_BOOLERR = 0x0205;
+/**
+ * Excel writes one flat record stream for the whole workbook: a global section
+ * holding the shared string table and the sheet directory, then one section per
+ * sheet. Cells reference strings by index, so the table has to be read first.
+ */
+function extractWorkbook(document) {
+    const stream = document.read("Workbook") ?? document.read("Book");
+    if (!stream)
+        throw new Error("Workbook stream is missing");
+    const records = readBiffRecords(stream);
+    const sharedStrings = readSharedStringTable(records);
+    const sheets = records
+        .filter((record) => record.id === RECORD_BOUNDSHEET && record.body.length >= 8)
+        .map((record) => ({
+        offset: record.body.readUInt32LE(0),
+        name: readShortBiffString(record.body, 6),
+    }));
+    const sections = sheets.map((sheet, index) => ({
+        name: sheet.name || `工作表 ${index + 1}`,
+        text: readSheetCells(stream, sheet.offset, sharedStrings),
+    }));
+    return { kind: "xls", sections, text: joinSections(sections) };
+}
+function readBiffRecords(stream, from = 0, stopAtEof = false) {
+    const records = [];
+    let cursor = from;
+    while (cursor + 4 <= stream.length) {
+        const id = stream.readUInt16LE(cursor);
+        const length = stream.readUInt16LE(cursor + 2);
+        if (cursor + 4 + length > stream.length)
+            break;
+        const body = stream.subarray(cursor + 4, cursor + 4 + length);
+        cursor += 4 + length;
+        if (id === RECORD_CONTINUE) {
+            // A CONTINUE belongs to whatever record came before it; on its own it has
+            // no meaning, and dropping it would truncate long strings.
+            records.at(-1)?.continuations.push(body);
+            continue;
+        }
+        records.push({ id, body, continuations: [] });
+        if (stopAtEof && id === RECORD_EOF)
+            break;
+    }
+    return records;
+}
+/**
+ * The shared string table can outgrow one record, and a string may straddle the
+ * boundary. Each continuation restarts with its own flags byte saying whether
+ * the remainder is 8- or 16-bit, so the pieces cannot simply be concatenated.
+ */
+function readSharedStringTable(records) {
+    const record = records.find((candidate) => candidate.id === RECORD_SST);
+    if (!record || record.body.length < 8)
+        return [];
+    const chunks = [record.body, ...record.continuations];
+    const uniqueCount = record.body.readUInt32LE(4);
+    const strings = [];
+    let chunk = 0;
+    let cursor = 8;
+    const advance = () => {
+        while (chunk < chunks.length && cursor >= (chunks[chunk]?.length ?? 0)) {
+            chunk += 1;
+            cursor = 0;
+        }
+        return chunk < chunks.length;
+    };
+    for (let index = 0; index < uniqueCount; index += 1) {
+        if (!advance())
+            break;
+        const current = chunks[chunk];
+        if (cursor + 3 > current.length)
+            break;
+        const characters = current.readUInt16LE(cursor);
+        let flags = current.readUInt8(cursor + 2);
+        cursor += 3;
+        // Rich-text runs and East Asian phonetic guides are sized here and skipped
+        // after the characters; both are formatting, not content.
+        let runCount = 0;
+        let phoneticBytes = 0;
+        if ((flags & 0x08) !== 0) {
+            runCount = current.readUInt16LE(cursor);
+            cursor += 2;
+        }
+        if ((flags & 0x04) !== 0) {
+            phoneticBytes = current.readUInt32LE(cursor);
+            cursor += 4;
+        }
+        let text = "";
+        let remaining = characters;
+        while (remaining > 0) {
+            if (!advance())
+                break;
+            const buffer = chunks[chunk];
+            const wide = (flags & 0x01) !== 0;
+            const available = buffer.length - cursor;
+            const take = Math.min(remaining, wide ? Math.floor(available / 2) : available);
+            if (take <= 0) {
+                // The value continues in the next record, which restates its own width.
+                chunk += 1;
+                cursor = 0;
+                if (chunk >= chunks.length)
+                    break;
+                flags = chunks[chunk].readUInt8(0);
+                cursor = 1;
+                continue;
+            }
+            const bytes = wide ? take * 2 : take;
+            text += wide
+                ? new TextDecoder("utf-16le").decode(buffer.subarray(cursor, cursor + bytes))
+                : new TextDecoder("windows-1252").decode(buffer.subarray(cursor, cursor + bytes));
+            cursor += bytes;
+            remaining -= take;
+        }
+        strings.push(text);
+        cursor += runCount * 4 + phoneticBytes;
+    }
+    return strings;
+}
+function readSheetCells(stream, offset, sharedStrings) {
+    if (offset <= 0 || offset >= stream.length || stream.readUInt16LE(offset) !== RECORD_BOF)
+        return "";
+    const rows = new Map();
+    const put = (row, column, value) => {
+        if (value === "")
+            return;
+        const line = rows.get(row) ?? new Map();
+        line.set(column, value);
+        rows.set(row, line);
+    };
+    const records = readBiffRecords(stream, offset, true);
+    for (const [index, record] of records.entries()) {
+        const body = record.body;
+        if (body.length < 4)
+            continue;
+        const row = body.readUInt16LE(0);
+        const column = body.readUInt16LE(2);
+        switch (record.id) {
+            case RECORD_LABELSST:
+                if (body.length >= 10)
+                    put(row, column, sharedStrings[body.readUInt32LE(6)] ?? "");
+                break;
+            case RECORD_LABEL:
+                put(row, column, readShortBiffString(body, 6));
+                break;
+            case RECORD_NUMBER:
+                if (body.length >= 14)
+                    put(row, column, formatNumber(body.readDoubleLE(6)));
+                break;
+            case RECORD_RK:
+                if (body.length >= 10)
+                    put(row, column, formatNumber(decodeRk(body.readUInt32LE(6))));
+                break;
+            case RECORD_MULRK:
+                // One record carrying a run of numbers across consecutive columns.
+                for (let cell = 0; cell + 6 <= body.length - 2; cell += 6) {
+                    put(row, column + cell / 6, formatNumber(decodeRk(body.readUInt32LE(4 + cell + 2))));
+                }
+                break;
+            case RECORD_BOOLERR:
+                if (body.length >= 8)
+                    put(row, column, body.readUInt8(7) === 0 ? (body.readUInt8(6) ? "TRUE" : "FALSE") : "#ERR");
+                break;
+            case RECORD_FORMULA: {
+                // A formula that evaluated to text is followed by the text itself; one
+                // that evaluated to a number carries the result in its own body.
+                const next = records[index + 1];
+                if (next?.id === RECORD_STRING)
+                    put(row, column, readBiffString(next.body));
+                else if (body.length >= 14 && body.readUInt16LE(12) !== 0xffff)
+                    put(row, column, formatNumber(body.readDoubleLE(6)));
+                break;
+            }
+            default:
+                break;
+        }
+    }
+    return [...rows.entries()]
+        .sort(([left], [right]) => left - right)
+        .map(([, line]) => [...line.entries()].sort(([left], [right]) => left - right).map(([, value]) => value).join("\t"))
+        .join("\n");
+}
+/** A BIFF string whose character count is one byte, as used for sheet names. */
+function readShortBiffString(body, offset) {
+    if (offset >= body.length)
+        return "";
+    const characters = body.readUInt8(offset);
+    const wide = offset + 1 < body.length && (body.readUInt8(offset + 1) & 0x01) !== 0;
+    const start = offset + 2;
+    return wide
+        ? new TextDecoder("utf-16le").decode(body.subarray(start, start + characters * 2))
+        : new TextDecoder("windows-1252").decode(body.subarray(start, start + characters));
+}
+/** A BIFF string whose character count is two bytes, as used for cell values. */
+function readBiffString(body) {
+    if (body.length < 3)
+        return "";
+    const characters = body.readUInt16LE(0);
+    const wide = (body.readUInt8(2) & 0x01) !== 0;
+    return wide
+        ? new TextDecoder("utf-16le").decode(body.subarray(3, 3 + characters * 2))
+        : new TextDecoder("windows-1252").decode(body.subarray(3, 3 + characters));
+}
+/**
+ * RK packs a number into 32 bits: the low two bits say whether the value was
+ * stored as a truncated double or a 30-bit integer, and whether it was scaled.
+ */
+function decodeRk(value) {
+    const isInteger = (value & 0x02) !== 0;
+    let number;
+    if (isInteger) {
+        // Arithmetic shift: the 30-bit payload is signed.
+        number = value >> 2;
+    }
+    else {
+        const buffer = Buffer.alloc(8);
+        buffer.writeUInt32LE(value & 0xfffffffc, 4);
+        number = buffer.readDoubleLE(0);
+    }
+    return (value & 0x01) !== 0 ? number / 100 : number;
+}
+function formatNumber(value) {
+    if (!Number.isFinite(value))
+        return "";
+    // Excel stores everything as a double; integers should not read as "3.0", and
+    // the rest should not carry the noise of binary rounding.
+    return Number.isInteger(value) ? String(value) : String(Number(value.toPrecision(15)));
+}
+// ---------------------------------------------------------------------------
+// PowerPoint 97-2003
+// ---------------------------------------------------------------------------
+const ATOM_TEXT_CHARS = 0x0fa0;
+const ATOM_TEXT_BYTES = 0x0fa8;
+const ATOM_SLIDE_PERSIST = 0x03f3;
+/**
+ * PowerPoint stores its text as atoms scattered through a record tree. Walking
+ * the tree in order recovers the text in slide order without having to model
+ * the drawing hierarchy the atoms hang off.
+ */
+function extractPresentation(document) {
+    const stream = document.read("PowerPoint Document");
+    if (!stream)
+        throw new Error("PowerPoint Document stream is missing");
+    const slides = [];
+    let current = [];
+    walkPptRecords(stream, 0, stream.length, (type, body) => {
+        if (type === ATOM_SLIDE_PERSIST && current.length > 0) {
+            slides.push(current);
+            current = [];
+            return;
+        }
+        const text = type === ATOM_TEXT_CHARS
+            ? new TextDecoder("utf-16le").decode(body)
+            : type === ATOM_TEXT_BYTES
+                ? new TextDecoder("windows-1252").decode(body)
+                : undefined;
+        // Vertical tab is a soft line break and carriage return ends a paragraph.
+        if (text !== undefined && text.trim() !== "")
+            current.push(text.replace(/[\v\r]/g, "\n").trim());
+    });
+    if (current.length > 0)
+        slides.push(current);
+    const sections = slides.map((lines, index) => ({
+        name: `幻灯片 ${index + 1}`,
+        text: lines.join("\n"),
+    }));
+    return { kind: "ppt", sections, text: joinSections(sections) };
+}
+/**
+ * Records nest: the low nibble of the first field is 0xF on a container, whose
+ * body is more records rather than data.
+ */
+function walkPptRecords(stream, from, to, visit, depth = 0) {
+    if (depth > 32)
+        return;
+    let cursor = from;
+    while (cursor + 8 <= to) {
+        const version = stream.readUInt16LE(cursor) & 0x000f;
+        const type = stream.readUInt16LE(cursor + 2);
+        const length = stream.readUInt32LE(cursor + 4);
+        const start = cursor + 8;
+        const end = start + length;
+        if (length < 0 || end > to)
+            break;
+        if (version === 0x0f)
+            walkPptRecords(stream, start, end, visit, depth + 1);
+        else
+            visit(type, stream.subarray(start, end));
+        cursor = end;
+    }
+}
+function joinSections(sections) {
+    return sections
+        .filter((section) => section.text.trim() !== "")
+        .map((section) => `## ${section.name}\n${section.text}`)
+        .join("\n\n");
+}
+function collapse(value) {
+    return value.replace(/\n{3,}/g, "\n\n").trim();
+}
+//# sourceMappingURL=legacy-office.js.map

package/dist/documents/legacy-office.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"legacy-office.js","sourceRoot":"","sources":["../../src/documents/legacy-office.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,UAAU,CAAC;AAoBvC,6EAA6E;AAC7E,MAAM,UAAU,gBAAgB,CAAC,QAAqB;IACpD,IAAI,QAAQ,CAAC,GAAG,CAAC,cAAc,CAAC;QAAE,OAAO,KAAK,CAAC;IAC/C,IAAI,QAAQ,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC;QAAE,OAAO,KAAK,CAAC;IACnE,IAAI,QAAQ,CAAC,GAAG,CAAC,qBAAqB,CAAC;QAAE,OAAO,KAAK,CAAC;IACtD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,QAAqB,EAAE,IAAgB;IACnE,IAAI,IAAI,KAAK,KAAK;QAAE,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,WAAW,CAAC,QAAQ,CAAC,EAAE,QAAQ,EAAE,EAAE,EAAE,CAAC;IAC/E,IAAI,IAAI,KAAK,KAAK;QAAE,OAAO,eAAe,CAAC,QAAQ,CAAC,CAAC;IACrD,OAAO,mBAAmB,CAAC,QAAQ,CAAC,CAAC;AACvC,CAAC;AAED,8EAA8E;AAC9E,eAAe;AACf,8EAA8E;AAE9E,mFAAmF;AACnF,MAAM,SAAS,GAAG,MAAM,CAAC;AACzB,MAAM,YAAY,GAAG,MAAM,CAAC;AAC5B,MAAM,UAAU,GAAG,MAAM,CAAC;AAC1B,MAAM,WAAW,GAAG,MAAM,CAAC;AAE3B,6EAA6E;AAC7E,MAAM,sBAAsB,GAAG,MAAM,CAAC;AAEtC;;;;;GAKG;AACH,SAAS,WAAW,CAAC,QAAqB;IACxC,MAAM,IAAI,GAAG,QAAQ,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC;IAC3C,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,GAAG,WAAW,GAAG,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,mCAAmC,CAAC,CAAC;IAEjG,MAAM,WAAW,GAAG,CAAC,IAAI,CAAC,YAAY,CAAC,SAAS,CAAC,GAAG,sBAAsB,CAAC,KAAK,CAAC,CAAC;IAClF,MAAM,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;IACrH,MAAM,cAAc,GAAG,IAAI,CAAC,YAAY,CAAC,YAAY,CAAC,CAAC;IACvD,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,4EAA4E;QAC5E,gEAAgE;QAChE,OAAO,QAAQ,CAAC,aAAa,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,cAAc,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC;IACvF,CAAC;IAED,MAAM,SAAS,GAAG,IAAI,CAAC,YAAY,CAAC,UAAU,CAAC,CAAC;IAChD,MAAM,SAAS,GAAG,IAAI,CAAC,YAAY,CAAC,WAAW,CAAC,CAAC;IACjD,MAAM,MAAM,GAAG,cAAc,CAAC,KAAK,CAAC,QAAQ,CAAC,SAAS,EAAE,SAAS,GAAG,SAAS,CAAC,EAAE,cAAc,CAAC,CAAC;IAChG,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC3B,IAAI,IAAI,aAAa,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,MAAM,EAAE,KAAK,CAAC,MAAM,GAAG,KAAK,CAAC,UAAU,CAAC,EAAE,KAAK,CAAC,UAAU,CAAC,CAAC;IACxG,CAAC;IACD,OAAO,QAAQ,CAAC,IAAI,CAAC,CAAC;AACxB,CAAC;AAQD;;;;GAIG;AACH,SAAS,cAAc,CAAC,GAAW,EAAE,cAAsB;IACzD,IAAI,MAAM,GAAG,CAAC,CAAC;IACf,OAAO,MAAM,GAAG,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,CAAC;QACnD,IAAI,MAAM,GAAG,CAAC,GAAG,GAAG,CAAC,MAAM;YAAE,OAAO,EAAE,CAAC;QACvC,MAAM,IAAI,CAAC,GAAG,GAAG,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAC7C,CAAC;IACD,IAAI,MAAM,IAAI,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,KAAK,IAAI,IAAI,MAAM,GAAG,CAAC,GAAG,GAAG,CAAC,MAAM;QAAE,OAAO,EAAE,CAAC;IACvF,MAAM,MAAM,GAAG,GAAG,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAC5C,MAAM,KAAK,GAAG,GAAG,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,MAAM,GAAG,CAAC,GAAG,MAAM,CAAC,CAAC;IAE5D,6EAA6E;IAC7E,4CAA4C;IAC5C,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC;IAClD,MAAM,MAAM,GAAgB,EAAE,CAAC;IAC/B,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;QAC9C,MAAM,KAAK,GAAG,KAAK,CAAC,YAAY,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;QAC5C,MAAM,GAAG,GAAG,KAAK,CAAC,YAAY,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAChD,IAAI,GAAG,IAAI,KAAK,IAAI,KAAK,GAAG,cAAc;YAAE,SAAS;QACrD,MAAM,UAAU,GAAG,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,KAAK,GAAG,CAAC,CAAC;QAC/C,IAAI,UAAU,GAAG,CAAC,GAAG,KAAK,CAAC,MAAM;YAAE,MAAM;QACzC,MAAM,EAAE,GAAG,KAAK,CAAC,YAAY,CAAC,UAAU,GAAG,CAAC,CAAC,CAAC;QAC9C,uEAAuE;QACvE,qEAAqE;QACrE,MAAM,UAAU,GAAG,CAAC,EAAE,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC;QAC3C,MAAM,MAAM,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,EAAE,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,GAAG,UAAU,CAAC;QACtE,MAAM,UAAU,GAAG,GAAG,GAAG,KAAK,CAAC;QAC/B,MAAM,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,UAAU,EAAE,UAAU,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,UAAU,GAAG,CAAC,EAAE,UAAU,EAAE,CAAC,CAAC;IAC5F,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;;GAGG;AACH,SAAS,aAAa,CAAC,GAAW,EAAE,UAAmB;IACrD,MAAM,OAAO,GAAG,UAAU;QACxB,2EAA2E;QAC3E,0EAA0E;QAC1E,CAAC,CAAC,IAAI,WAAW,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC;QAC7C,CAAC,CAAC,IAAI,WAAW,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;IAC5C,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,KAAK,MAAM,SAAS,IAAI,OAAO,EAAE,CAAC;QAChC,MAAM,IAAI,GAAG,SAAS,CAAC,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC;QAC3C,IAAI,IAAI,KAAK,IAAI,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,IAAI,CAAC;aAC5C,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,IAAI,CAAC;aAChC,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,IAAI,CAAC;aAChC,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,MAAM,CAAC;aAClC,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,GAAG,CAAC;aAC/B,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,EAAE,CAAC;aAC9B,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,IAAI;YAAE,IAAI,IAAI,SAAS,CAAC;IAC5D,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED,8EAA8E;AAC9E,gBAAgB;AAChB,8EAA8E;AAE9E,MAAM,cAAc,GAAG,MAAM,CAAC;AAC9B,MAAM,UAAU,GAAG,MAAM,CAAC;AAC1B,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,iBAAiB,GAAG,MAAM,CAAC;AACjC,MAAM,UAAU,GAAG,MAAM,CAAC;AAC1B,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,YAAY,GAAG,MAAM,CAAC;AAC5B,MAAM,UAAU,GAAG,MAAM,CAAC;AAC1B,MAAM,SAAS,GAAG,MAAM,CAAC;AACzB,MAAM,YAAY,GAAG,MAAM,CAAC;AAC5B,MAAM,aAAa,GAAG,MAAM,CAAC;AAC7B,MAAM,aAAa,GAAG,MAAM,CAAC;AAC7B,MAAM,cAAc,GAAG,MAAM,CAAC;AAS9B;;;;GAIG;AACH,SAAS,eAAe,CAAC,QAAqB;IAC5C,MAAM,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IAClE,IAAI,CAAC,MAAM;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,CAAC,CAAC;IAC3D,MAAM,OAAO,GAAG,eAAe,CAAC,MAAM,CAAC,CAAC;IAExC,MAAM,aAAa,GAAG,qBAAqB,CAAC,OAAO,CAAC,CAAC;IACrD,MAAM,MAAM,GAAG,OAAO;SACnB,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,EAAE,KAAK,iBAAiB,IAAI,MAAM,CAAC,IAAI,CAAC,MAAM,IAAI,CAAC,CAAC;SAC9E,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;QAChB,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC;QACnC,IAAI,EAAE,mBAAmB,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC;KAC1C,CAAC,CAAC,CAAC;IAEN,MAAM,QAAQ,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;QAC7C,IAAI,EAAE,KAAK,CAAC,IAAI,IAAI,OAAO,KAAK,GAAG,CAAC,EAAE;QACtC,IAAI,EAAE,cAAc,CAAC,MAAM,EAAE,KAAK,CAAC,MAAM,EAAE,aAAa,CAAC;KAC1D,CAAC,CAAC,CAAC;IACJ,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,YAAY,CAAC,QAAQ,CAAC,EAAE,CAAC;AACjE,CAAC;AAED,SAAS,eAAe,CAAC,MAAc,EAAE,IAAI,GAAG,CAAC,EAAE,SAAS,GAAG,KAAK;IAClE,MAAM,OAAO,GAAiB,EAAE,CAAC;IACjC,IAAI,MAAM,GAAG,IAAI,CAAC;IAClB,OAAO,MAAM,GAAG,CAAC,IAAI,MAAM,CAAC,MAAM,EAAE,CAAC;QACnC,MAAM,EAAE,GAAG,MAAM,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;QACvC,MAAM,MAAM,GAAG,MAAM,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAC/C,IAAI,MAAM,GAAG,CAAC,GAAG,MAAM,GAAG,MAAM,CAAC,MAAM;YAAE,MAAM;QAC/C,MAAM,IAAI,GAAG,MAAM,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,MAAM,GAAG,CAAC,GAAG,MAAM,CAAC,CAAC;QAC9D,MAAM,IAAI,CAAC,GAAG,MAAM,CAAC;QACrB,IAAI,EAAE,KAAK,eAAe,EAAE,CAAC;YAC3B,0EAA0E;YAC1E,2DAA2D;YAC3D,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACzC,SAAS;QACX,CAAC;QACD,OAAO,CAAC,IAAI,CAAC,EAAE,EAAE,EAAE,IAAI,EAAE,aAAa,EAAE,EAAE,EAAE,CAAC,CAAC;QAC9C,IAAI,SAAS,IAAI,EAAE,KAAK,UAAU;YAAE,MAAM;IAC5C,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;;;GAIG;AACH,SAAS,qBAAqB,CAAC,OAA8B;IAC3D,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC,SAAS,CAAC,EAAE,KAAK,UAAU,CAAC,CAAC;IACxE,IAAI,CAAC,MAAM,IAAI,MAAM,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAC;IACjD,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,IAAI,EAAE,GAAG,MAAM,CAAC,aAAa,CAAC,CAAC;IACtD,MAAM,WAAW,GAAG,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;IAEhD,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,MAAM,GAAG,CAAC,CAAC;IACf,MAAM,OAAO,GAAG,GAAY,EAAE;QAC5B,OAAO,KAAK,GAAG,MAAM,CAAC,MAAM,IAAI,MAAM,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,MAAM,IAAI,CAAC,CAAC,EAAE,CAAC;YACvE,KAAK,IAAI,CAAC,CAAC;YACX,MAAM,GAAG,CAAC,CAAC;QACb,CAAC;QACD,OAAO,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC;IAC/B,CAAC,CAAC;IAEF,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,WAAW,EAAE,KAAK,IAAI,CAAC,EAAE,CAAC;QACpD,IAAI,CAAC,OAAO,EAAE;YAAE,MAAM;QACtB,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAW,CAAC;QACxC,IAAI,MAAM,GAAG,CAAC,GAAG,OAAO,CAAC,MAAM;YAAE,MAAM;QACvC,MAAM,UAAU,GAAG,OAAO,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;QAChD,IAAI,KAAK,GAAG,OAAO,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAC1C,MAAM,IAAI,CAAC,CAAC;QACZ,2EAA2E;QAC3E,0DAA0D;QAC1D,IAAI,QAAQ,GAAG,CAAC,CAAC;QACjB,IAAI,aAAa,GAAG,CAAC,CAAC;QACtB,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YACzB,QAAQ,GAAG,OAAO,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;YACxC,MAAM,IAAI,CAAC,CAAC;QACd,CAAC;QACD,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YACzB,aAAa,GAAG,OAAO,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;YAC7C,MAAM,IAAI,CAAC,CAAC;QACd,CAAC;QAED,IAAI,IAAI,GAAG,EAAE,CAAC;QACd,IAAI,SAAS,GAAG,UAAU,CAAC;QAC3B,OAAO,SAAS,GAAG,CAAC,EAAE,CAAC;YACrB,IAAI,CAAC,OAAO,EAAE;gBAAE,MAAM;YACtB,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAW,CAAC;YACvC,MAAM,IAAI,GAAG,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;YAClC,MAAM,SAAS,GAAG,MAAM,CAAC,MAAM,GAAG,MAAM,CAAC;YACzC,MAAM,IAAI,GAAG,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;YAC/E,IAAI,IAAI,IAAI,CAAC,EAAE,CAAC;gBACd,wEAAwE;gBACxE,KAAK,IAAI,CAAC,CAAC;gBACX,MAAM,GAAG,CAAC,CAAC;gBACX,IAAI,KAAK,IAAI,MAAM,CAAC,MAAM;oBAAE,MAAM;gBAClC,KAAK,GAAI,MAAM,CAAC,KAAK,CAAY,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;gBAC/C,MAAM,GAAG,CAAC,CAAC;gBACX,SAAS;YACX,CAAC;YACD,MAAM,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;YACrC,IAAI,IAAI,IAAI;gBACV,CAAC,CAAC,IAAI,WAAW,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,KAAK,CAAC,CAAC;gBAC7E,CAAC,CAAC,IAAI,WAAW,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC;YACpF,MAAM,IAAI,KAAK,CAAC;YAChB,SAAS,IAAI,IAAI,CAAC;QACpB,CAAC;QACD,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACnB,MAAM,IAAI,QAAQ,GAAG,CAAC,GAAG,aAAa,CAAC;IACzC,CAAC;IACD,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,cAAc,CAAC,MAAc,EAAE,MAAc,EAAE,aAAgC;IACtF,IAAI,MAAM,IAAI,CAAC,IAAI,MAAM,IAAI,MAAM,CAAC,MAAM,IAAI,MAAM,CAAC,YAAY,CAAC,MAAM,CAAC,KAAK,UAAU;QAAE,OAAO,EAAE,CAAC;IACpG,MAAM,IAAI,GAAG,IAAI,GAAG,EAA+B,CAAC;IACpD,MAAM,GAAG,GAAG,CAAC,GAAW,EAAE,MAAc,EAAE,KAAa,EAAQ,EAAE;QAC/D,IAAI,KAAK,KAAK,EAAE;YAAE,OAAO;QACzB,MAAM,IAAI,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,IAAI,GAAG,EAAkB,CAAC;QACxD,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;QACxB,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC;IACtB,CAAC,CAAC;IAEF,MAAM,OAAO,GAAG,eAAe,CAAC,MAAM,EAAE,MAAM,EAAE,IAAI,CAAC,CAAC;IACtD,KAAK,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,IAAI,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC;QAChD,MAAM,IAAI,GAAG,MAAM,CAAC,IAAI,CAAC;QACzB,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC;YAAE,SAAS;QAC9B,MAAM,GAAG,GAAG,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;QACjC,MAAM,MAAM,GAAG,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;QACpC,QAAQ,MAAM,CAAC,EAAE,EAAE,CAAC;YAClB,KAAK,eAAe;gBAClB,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,aAAa,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;gBACnF,MAAM;YACR,KAAK,YAAY;gBACf,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,mBAAmB,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;gBAC/C,MAAM;YACR,KAAK,aAAa;gBAChB,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,YAAY,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBAC5E,MAAM;YACR,KAAK,SAAS;gBACZ,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,YAAY,CAAC,QAAQ,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACtF,MAAM;YACR,KAAK,YAAY;gBACf,mEAAmE;gBACnE,KAAK,IAAI,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,CAAC,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;oBAC1D,GAAG,CAAC,GAAG,EAAE,MAAM,GAAG,IAAI,GAAG,CAAC,EAAE,YAAY,CAAC,QAAQ,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACvF,CAAC;gBACD,MAAM;YACR,KAAK,cAAc;gBACjB,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;gBAClH,MAAM;YACR,KAAK,cAAc,CAAC,CAAC,CAAC;gBACpB,uEAAuE;gBACvE,iEAAiE;gBACjE,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;gBAChC,IAAI,IAAI,EAAE,EAAE,KAAK,aAAa;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;qBACvE,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE,IAAI,IAAI,CAAC,YAAY,CAAC,EAAE,CAAC,KAAK,MAAM;oBAAE,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,YAAY,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACrH,MAAM;YACR,CAAC;YACD;gBACE,MAAM;QACV,CAAC;IACH,CAAC;IAED,OAAO,CAAC,GAAG,IAAI,CAAC,OAAO,EAAE,CAAC;SACvB,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,IAAI,GAAG,KAAK,CAAC;SACvC,GAAG,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,IAAI,CAAC,OAAO,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,IAAI,GAAG,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;SACnH,IAAI,CAAC,IAAI,CAAC,CAAC;AAChB,CAAC;AAED,gFAAgF;AAChF,SAAS,mBAAmB,CAAC,IAAY,EAAE,MAAc;IACvD,IAAI,MAAM,IAAI,IAAI,CAAC,MAAM;QAAE,OAAO,EAAE,CAAC;IACrC,MAAM,UAAU,GAAG,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC;IAC1C,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,GAAG,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,MAAM,GAAG,CAAC,CAAC;IACzB,OAAO,IAAI;QACT,CAAC,CAAC,IAAI,WAAW,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,EAAE,KAAK,GAAG,UAAU,GAAG,CAAC,CAAC,CAAC;QAClF,CAAC,CAAC,IAAI,WAAW,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,EAAE,KAAK,GAAG,UAAU,CAAC,CAAC,CAAC;AACvF,CAAC;AAED,iFAAiF;AACjF,SAAS,cAAc,CAAC,IAAY;IAClC,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAC;IAC/B,MAAM,UAAU,GAAG,IAAI,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;IACxC,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;IAC9C,OAAO,IAAI;QACT,CAAC,CAAC,IAAI,WAAW,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,GAAG,UAAU,GAAG,CAAC,CAAC,CAAC;QAC1E,CAAC,CAAC,IAAI,WAAW,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,GAAG,UAAU,CAAC,CAAC,CAAC;AAC/E,CAAC;AAED;;;GAGG;AACH,SAAS,QAAQ,CAAC,KAAa;IAC7B,MAAM,SAAS,GAAG,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;IACvC,IAAI,MAAc,CAAC;IACnB,IAAI,SAAS,EAAE,CAAC;QACd,kDAAkD;QAClD,MAAM,GAAG,KAAK,IAAI,CAAC,CAAC;IACtB,CAAC;SAAM,CAAC;QACN,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;QAC/B,MAAM,CAAC,aAAa,CAAC,KAAK,GAAG,UAAU,EAAE,CAAC,CAAC,CAAC;QAC5C,MAAM,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;IAClC,CAAC;IACD,OAAO,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC;AACtD,CAAC;AAED,SAAS,YAAY,CAAC,KAAa;IACjC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC;QAAE,OAAO,EAAE,CAAC;IACvC,8EAA8E;IAC9E,0DAA0D;IAC1D,OAAO,MAAM,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,WAAW,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;AACzF,CAAC;AAED,8EAA8E;AAC9E,qBAAqB;AACrB,8EAA8E;AAE9E,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,eAAe,GAAG,MAAM,CAAC;AAC/B,MAAM,kBAAkB,GAAG,MAAM,CAAC;AAElC;;;;GAIG;AACH,SAAS,mBAAmB,CAAC,QAAqB;IAChD,MAAM,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,qBAAqB,CAAC,CAAC;IACpD,IAAI,CAAC,MAAM;QAAE,MAAM,IAAI,KAAK,CAAC,uCAAuC,CAAC,CAAC;IAEtE,MAAM,MAAM,GAAe,EAAE,CAAC;IAC9B,IAAI,OAAO,GAAa,EAAE,CAAC;IAC3B,cAAc,CAAC,MAAM,EAAE,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,EAAE;QACtD,IAAI,IAAI,KAAK,kBAAkB,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACtD,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YACrB,OAAO,GAAG,EAAE,CAAC;YACb,OAAO;QACT,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,KAAK,eAAe;YACnC,CAAC,CAAC,IAAI,WAAW,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC;YAC1C,CAAC,CAAC,IAAI,KAAK,eAAe;gBACxB,CAAC,CAAC,IAAI,WAAW,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC;gBAC9C,CAAC,CAAC,SAAS,CAAC;QAChB,0EAA0E;QAC1E,IAAI,IAAI,KAAK,SAAS,IAAI,IAAI,CAAC,IAAI,EAAE,KAAK,EAAE;YAAE,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;IACnG,CAAC,CAAC,CAAC;IACH,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC;QAAE,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAE7C,MAAM,QAAQ,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;QAC7C,IAAI,EAAE,OAAO,KAAK,GAAG,CAAC,EAAE;QACxB,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC;KACvB,CAAC,CAAC,CAAC;IACJ,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,YAAY,CAAC,QAAQ,CAAC,EAAE,CAAC;AACjE,CAAC;AAED;;;GAGG;AACH,SAAS,cAAc,CACrB,MAAc,EACd,IAAY,EACZ,EAAU,EACV,KAA2C,EAC3C,KAAK,GAAG,CAAC;IAET,IAAI,KAAK,GAAG,EAAE;QAAE,OAAO;IACvB,IAAI,MAAM,GAAG,IAAI,CAAC;IAClB,OAAO,MAAM,GAAG,CAAC,IAAI,EAAE,EAAE,CAAC;QACxB,MAAM,OAAO,GAAG,MAAM,CAAC,YAAY,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC;QACrD,MAAM,IAAI,GAAG,MAAM,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAC7C,MAAM,MAAM,GAAG,MAAM,CAAC,YAAY,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAC/C,MAAM,KAAK,GAAG,MAAM,GAAG,CAAC,CAAC;QACzB,MAAM,GAAG,GAAG,KAAK,GAAG,MAAM,CAAC;QAC3B,IAAI,MAAM,GAAG,CAAC,IAAI,GAAG,GAAG,EAAE;YAAE,MAAM;QAClC,IAAI,OAAO,KAAK,IAAI;YAAE,cAAc,CAAC,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,KAAK,EAAE,KAAK,GAAG,CAAC,CAAC,CAAC;;YACtE,KAAK,CAAC,IAAI,EAAE,MAAM,CAAC,QAAQ,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC,CAAC;QAC9C,MAAM,GAAG,GAAG,CAAC;IACf,CAAC;AACH,CAAC;AAED,SAAS,YAAY,CAAC,QAAmD;IACvE,OAAO,QAAQ;SACZ,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,EAAE,KAAK,EAAE,CAAC;SAC/C,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,MAAM,OAAO,CAAC,IAAI,KAAK,OAAO,CAAC,IAAI,EAAE,CAAC;SACvD,IAAI,CAAC,MAAM,CAAC,CAAC;AAClB,CAAC;AAED,SAAS,QAAQ,CAAC,KAAa;IAC7B,OAAO,KAAK,CAAC,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC;AACjD,CAAC"}

package/dist/documents/ole.d.ts

@@ -0,0 +1,20 @@
+/**
+ * The container every pre-2007 Office file is written in.
+ *
+ * A `.doc`, `.xls` or `.ppt` is a Compound File Binary document: a FAT-style
+ * filesystem inside one file, whose named streams hold the actual format. The
+ * reader is here so the three legacy parsers share one implementation of the
+ * container and only differ in how they read their own stream.
+ */
+export declare class OleDocument {
+    #private;
+    private constructor();
+    static open(buffer: Buffer): OleDocument;
+    /** Stream names present in the document, for diagnostics and format sniffing. */
+    names(): string[];
+    has(name: string): boolean;
+    /** Reads a whole named stream, or undefined when the document has no such stream. */
+    read(name: string): Buffer | undefined;
+}
+export declare function looksLikeOle(buffer: Buffer): boolean;
+//# sourceMappingURL=ole.d.ts.map

package/dist/documents/ole.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"ole.d.ts","sourceRoot":"","sources":["../../src/documents/ole.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAqBH,qBAAa,WAAW;;IAUtB,OAAO;IAeP,MAAM,CAAC,IAAI,CAAC,MAAM,EAAE,MAAM,GAAG,WAAW;IAKxC,iFAAiF;IACjF,KAAK,IAAI,MAAM,EAAE;IAIjB,GAAG,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO;IAI1B,qFAAqF;IACrF,IAAI,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS;CA4HvC;AAED,wBAAgB,YAAY,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAEpD"}