xls-codec 1.0.2 → 2.0.1

package/dist/workbook/sheet.cjs

@@ -1,11 +1,13 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
 require("../biff/record-types.cjs");
 const require_biff_records = require("../biff/records.cjs");
+const require_units = require("../units.cjs");
+const require_biff_print_setup = require("../biff/print-setup.cjs");
 const require_biff_cursor = require("../biff/cursor.cjs");
 const require_biff_strings = require("../biff/strings.cjs");
 const require_biff_errors = require("../biff/errors.cjs");
+const require_biff_ptg = require("../biff/ptg.cjs");
 const require_biff_rk = require("../biff/rk.cjs");
-const require_units = require("../units.cjs");
 //#region src/workbook/sheet.ts
 /** Row record flag bits, in the 32-bit field following unused1 ([MS-XLS] 2.4.221). */
 const ROW_FLAG_HIDDEN = 32;
@@ -24,13 +26,25 @@ const FORMULA_VALUE_BLANK = 3;
 const MUL_FIXED_BYTES = 6;
 const MULRK_ENTRY_BYTES = 6;
 const MULBLANK_ENTRY_BYTES = 2;
+/** No sheets and no resolvable 3D references -- the default a caller with nothing formula-relevant to offer (every existing test fixture that predates formula-text recovery) gets, so a 3D reference simply fails to resolve rather than throwing on an absent context. */
+const EMPTY_FORMULA_SHEET_CONTEXT = {
+	sheets: [],
+	sheetRanges: []
+};
 /** Reads one worksheet substream's records. */
-function readSheetRecords(records, sharedStrings) {
+function readSheetRecords(records, sharedStrings, formulaSheets = EMPTY_FORMULA_SHEET_CONTEXT) {
 	const cells = [];
 	const rows = [];
 	const columns = [];
 	const merges = [];
 	let usedRange;
+	const marginsPt = {};
+	const rowBreaks = [];
+	const columnBreaks = [];
+	let setup;
+	let printGridlines;
+	let printHeaders;
+	let fitToPage;
 	for (let index = 0; index < records.length; index += 1) {
 		const record = records[index];
 		if (record === void 0) continue;
@@ -73,22 +87,108 @@ function readSheetRecords(records, sharedStrings) {
 			case 516:
 				cells.push(readLabel(record));
 				break;
-			case 6: cells.push(readFormula(record, stringResultAfter(records, index)));
+			case 6:
+				cells.push(readFormula(record, stringResultAfter(records, index), formulaSheets));
+				break;
+			case 161:
+				setup = readSetup(record);
+				break;
+			case 38:
+				marginsPt.left = readMargin(record);
+				break;
+			case 39:
+				marginsPt.right = readMargin(record);
+				break;
+			case 40:
+				marginsPt.top = readMargin(record);
+				break;
+			case 41:
+				marginsPt.bottom = readMargin(record);
+				break;
+			case 43:
+				printGridlines = readGridlineBooleanRecord(record);
+				break;
+			case 42:
+				printHeaders = readBooleanRecord(record);
+				break;
+			case 129:
+				fitToPage = (new require_biff_cursor.BlockCursor(record.blocks).u16() & 256) !== 0;
+				break;
+			case 27:
+				rowBreaks.push(...readPageBreaks(record));
+				break;
+			case 26: columnBreaks.push(...readPageBreaks(record));
 		}
 	}
+	const print = {
+		marginsPt,
+		rowBreaks: ascendingDistinct(rowBreaks),
+		columnBreaks: ascendingDistinct(columnBreaks),
+		...setup === void 0 ? {} : { setup },
+		...printGridlines === void 0 ? {} : { printGridlines },
+		...printHeaders === void 0 ? {} : { printHeaders },
+		...fitToPage === void 0 ? {} : { fitToPage }
+	};
 	return usedRange === void 0 ? {
 		cells,
 		rows,
 		columns,
-		merges
+		merges,
+		print
 	} : {
 		cells,
 		rows,
 		columns,
 		merges,
-		usedRange
+		usedRange,
+		print
+	};
+}
+/** Setup ([MS-XLS] 2.4.257): iPaperSize, iScale, iPageStart, iFitWidth, iFitHeight, a flags word, iRes, iVRes, an eight-byte header margin, an eight-byte footer margin, and iCopies. The starting page number, the two print resolutions, the header/footer margins, and the copy count are read past: ContentSheetPrintSettings has no field for any of them, and Margins models only the four page edges. */
+function readSetup(record) {
+	const cursor = new require_biff_cursor.BlockCursor(record.blocks);
+	const paperCode = cursor.u16();
+	const scalePercent = cursor.u16();
+	cursor.skip(2);
+	return {
+		paperCode,
+		scalePercent,
+		fitWidth: cursor.u16(),
+		fitHeight: cursor.u16(),
+		...require_biff_print_setup.unpackSetupFlags(cursor.u16())
 	};
 }
+/** Any of the four margin records ([MS-XLS] 2.4.151, 2.4.219, 2.4.328, 2.4.27): a single Xnum stating that margin in inches. All four share the identical one-field layout, so one reader serves them all. */
+function readMargin(record) {
+	return require_units.inchesToPoints(new require_biff_cursor.BlockCursor(record.blocks).f64());
+}
+/** PrintRowCol ([MS-XLS] 2.4.203): a single 16-bit `Boolean` field (2.5.14), whose whole word is the value. [MS-XLS] 2.4.203's own value table states both 0x0000 and 0x0001 as "Row and column headers are not printed", which is a typo in that table rather than two spellings of one meaning -- the record exists precisely to distinguish them, and every real producer writes 1 for printed (confirmed against LibreOffice-written BIFF8, where a sheet with header printing enabled carries 0x0001 and one without carries 0x0000). */
+function readBooleanRecord(record) {
+	return new require_biff_cursor.BlockCursor(record.blocks).u16() !== 0;
+}
+/** PrintGrid ([MS-XLS] 2.4.202): unlike PrintRowCol above, its 16-bit field is only ONE bit wide (`fPrintGrid`) with the remaining 15 "Undefined, and MUST be ignored" -- so a producer leaving anything in those bits would read as gridlines-on under a bare `!== 0` test. No real producer does (LibreOffice writes 0x0000/0x0001, confirmed against its own BIFF8 output), but masking to the one bit the spec actually defines is what the field's own layout says to do. */
+function readGridlineBooleanRecord(record) {
+	return (new require_biff_cursor.BlockCursor(record.blocks).u16() & 1) !== 0;
+}
+/**
+* HorizontalPageBreaks ([MS-XLS] 2.4.142) and VerticalPageBreaks ([MS-XLS] 2.4.343): a count then that many six-byte structures, each an index on the break's own axis followed by the start and end of the break's extent on the other one.
+*
+* Only the index is taken. HorzBrk's colStart/colEnd and VertBrk's rowStart/rowEnd say how far along the perpendicular axis the break runs -- a BIFF8 page break can be partial -- and ContentSheetPrintSettings.manualBreaks models a break as a whole-axis index with no extent, so a partial break is carried as a full one rather than dropped. Both structures have the identical three-field shape, so one reader serves both.
+*/
+function readPageBreaks(record) {
+	const cursor = new require_biff_cursor.BlockCursor(record.blocks);
+	const count = cursor.u16();
+	const indices = [];
+	for (let index = 0; index < count; index += 1) {
+		indices.push(cursor.u16());
+		cursor.skip(4);
+	}
+	return indices;
+}
+/** Page-break indices, ascending and with duplicates collapsed: two records naming the same row are one page break as far as the schema's own index-only model of a break can express. */
+function ascendingDistinct(values) {
+	return [...new Set(values)].sort((a, b) => a - b);
+}
 /**
 * Finds the String record carrying a Formula's cached string result, if it has one.
 *
@@ -314,28 +414,36 @@ function readLabel(record) {
 		fromFormula: false
 	};
 }
+/** The Formula record's own flags field ([MS-XLS] 2.4.127) and calculation cache, between the cached value and the compiled expression -- neither read for its own content; see the two-byte and four-byte skips in readFormula. */
+const FORMULA_FLAGS_BYTES = 2;
+const FORMULA_CALC_CACHE_BYTES = 4;
 /**
-* Formula ([MS-XLS] 2.4.127): a Cell, an eight-byte FormulaValue, flags, a calculation cache, then the compiled expression.
+* Formula ([MS-XLS] 2.4.127): a Cell, an eight-byte FormulaValue, flags, a calculation cache, then a CellParsedFormula -- a two-byte cce followed by exactly that many bytes of compiled Ptg tokens ([MS-XLS] 2.5.198.3).
 *
-* Only the cached VALUE is read. The expression is a CellParsedFormula -- a compiled Ptg token stream rather than text -- and turning one back into a formula string means implementing the whole Ptg vocabulary plus shared-formula and external-reference resolution, which is its own substantial piece of work. So the cell's displayed value is correct and its `formula` field stays absent, rather than a plausible-looking expression being invented for it.
+* Both the cached value and the expression are read: the value from the FormulaValue exactly as before, and the expression by handing the token bytes to biff/ptg.ts's parseFormulaText, which resolves the whole Ptg vocabulary this reader supports and returns undefined for the constructs it does not (a shared formula, an array formula, a defined name, a natural-language reference, a genuinely external 3D reference -- see that module's own boundary). `formula` is attached only when it resolves; a cell it does not resolve for keeps exactly the behaviour this reader always had, its cached value present and `formula` absent.
 */
-function readFormula(record, next) {
+function readFormula(record, next, formulaSheets) {
 	const cursor = new require_biff_cursor.BlockCursor(record.blocks);
 	const header = readCellHeader(cursor);
 	const bytes = cursor.take(8);
 	const view = new DataView(bytes.buffer, bytes.byteOffset, bytes.byteLength);
-	if (!(view.getUint16(6, true) === FORMULA_VALUE_TAGGED)) return {
-		...header,
-		value: {
-			kind: "number",
-			value: view.getFloat64(0, true)
-		},
-		fromFormula: true
+	const value = view.getUint16(6, true) === FORMULA_VALUE_TAGGED ? taggedFormulaValue(view, next) : {
+		kind: "number",
+		value: view.getFloat64(0, true)
 	};
-	return {
+	cursor.skip(FORMULA_FLAGS_BYTES);
+	cursor.skip(FORMULA_CALC_CACHE_BYTES);
+	const cce = cursor.u16();
+	const formula = require_biff_ptg.parseFormulaText(cursor.take(cce), formulaSheets);
+	return formula === void 0 ? {
 		...header,
-		value: taggedFormulaValue(view, next),
+		value,
 		fromFormula: true
+	} : {
+		...header,
+		value,
+		fromFormula: true,
+		formula
 	};
 }
 /** The non-numeric readings of a FormulaValue ([MS-XLS] 2.5.133), selected by its first byte. */

package/dist/workbook/sheet.d.cts

@@ -1,4 +1,6 @@
-import { RecordGroup } from "../biff/substreams.cjs";
+import { n as SetupFields } from "../print-setup-B_ihDvm5.cjs";
+import { t as FormulaSheetContext } from "../ptg-B2K8t3js.cjs";
+import { t as RecordGroup } from "../substreams-Ddtvn_Vr.cjs";
 //#region src/workbook/sheet.d.ts
 /** A cell's value as its own record carries it, before number-format classification decides whether a number is really a date, a percentage, or an amount of money. */
 type RawCellValue = {
@@ -23,8 +25,10 @@ interface RawCell {
   /** The cell's own ixfe ([MS-XLS] 2.5.168): an index into the globals substream's XF table. */
   readonly xfIndex: number;
   readonly value: RawCellValue;
-  /** True when the value is a Formula record's CACHED result rather than a literal. The formula expression itself is not read: BIFF8 stores it as a compiled Ptg token stream, not as text. */
+  /** True when the value is a Formula record's CACHED result rather than a literal. */
   readonly fromFormula: boolean;
+  /** The formula's own text, recovered from its compiled Ptg token stream ([MS-XLS] 2.5.198), when every token in it is one this reader resolves -- absent for a shared-formula member, an array formula, a defined-name or natural-language reference, or a 3D reference into a genuinely external workbook (see biff/ptg.ts). */
+  readonly formula?: string;
 }
 interface RawRow {
   readonly index: number;
@@ -43,6 +47,34 @@ interface RawRange {
   readonly endRow: number;
   readonly endColumn: number;
 }
+/**
+ * The page-setup half of a sheet's print settings, as the worksheet substream's own records carry them.
+ *
+ * Every field is optional because every record behind it is: [MS-XLS] 2.1.7.20.6's PAGESETUP production makes each of the four margins and Setup itself optional, and a sheet that never had its page setup touched carries none of them. An absent field is therefore "this file states nothing here", which is a different fact from "this file states the default", and content.ts is where the distinction is resolved into the required ContentSheetPrintSettings fields.
+ *
+ * The other half -- the print range and the repeated header bands -- is not here at all, because BIFF8 does not put it in the worksheet substream; see workbook/print-names.ts.
+ */
+interface RawPrintSettings {
+  /** The Setup record's own fields ([MS-XLS] 2.4.257). */
+  readonly setup?: SetupFields;
+  /** Each page margin in points, from its own record ([MS-XLS] 2.4.151, 2.4.219, 2.4.328, 2.4.27), which states it in inches. */
+  readonly marginsPt: {
+    readonly left?: number;
+    readonly right?: number;
+    readonly top?: number;
+    readonly bottom?: number;
+  };
+  /** PrintGrid's fPrintGrid ([MS-XLS] 2.4.202). */
+  readonly printGridlines?: boolean;
+  /** PrintRowCol's printRwCol ([MS-XLS] 2.4.203): whether the row and column headers print. */
+  readonly printHeaders?: boolean;
+  /** WsBool's fFitToPage ([MS-XLS] 2.4.351), which decides whether Setup's iScale or its iFitWidth/iFitHeight pair is the live one. */
+  readonly fitToPage?: boolean;
+  /** Zero-based row indices an explicit page break falls immediately above ([MS-XLS] 2.4.142), ascending and deduplicated. */
+  readonly rowBreaks: readonly number[];
+  /** Zero-based column indices an explicit page break falls immediately to the left of ([MS-XLS] 2.4.343). */
+  readonly columnBreaks: readonly number[];
+}
 /** One worksheet's records, read but not yet mapped onto the shared schema. */
 interface RawSheet {
   readonly cells: readonly RawCell[];
@@ -51,8 +83,10 @@ interface RawSheet {
   readonly merges: readonly RawRange[];
   /** The used range from the Dimensions record ([MS-XLS] 2.4.90), when the sheet declared one. */
   readonly usedRange?: RawRange;
+  /** The sheet's own page setup, as far as its records state it. */
+  readonly print: RawPrintSettings;
 }
 /** Reads one worksheet substream's records. */
-declare function readSheetRecords(records: readonly RecordGroup[], sharedStrings: readonly string[]): RawSheet;
+declare function readSheetRecords(records: readonly RecordGroup[], sharedStrings: readonly string[], formulaSheets?: FormulaSheetContext): RawSheet;
 //#endregion
-export { RawCell, RawCellValue, RawColumn, RawRange, RawRow, RawSheet, readSheetRecords };
+export { RawCell, RawCellValue, RawColumn, RawPrintSettings, RawRange, RawRow, RawSheet, readSheetRecords };

package/dist/workbook/sheet.d.ts

@@ -1,4 +1,6 @@
-import { RecordGroup } from "../biff/substreams.js";
+import { n as SetupFields } from "../print-setup-B_ihDvm5.js";
+import { t as FormulaSheetContext } from "../ptg-B2K8t3js.js";
+import { t as RecordGroup } from "../substreams-D7dQiJbp.js";
 //#region src/workbook/sheet.d.ts
 /** A cell's value as its own record carries it, before number-format classification decides whether a number is really a date, a percentage, or an amount of money. */
 type RawCellValue = {
@@ -23,8 +25,10 @@ interface RawCell {
   /** The cell's own ixfe ([MS-XLS] 2.5.168): an index into the globals substream's XF table. */
   readonly xfIndex: number;
   readonly value: RawCellValue;
-  /** True when the value is a Formula record's CACHED result rather than a literal. The formula expression itself is not read: BIFF8 stores it as a compiled Ptg token stream, not as text. */
+  /** True when the value is a Formula record's CACHED result rather than a literal. */
   readonly fromFormula: boolean;
+  /** The formula's own text, recovered from its compiled Ptg token stream ([MS-XLS] 2.5.198), when every token in it is one this reader resolves -- absent for a shared-formula member, an array formula, a defined-name or natural-language reference, or a 3D reference into a genuinely external workbook (see biff/ptg.ts). */
+  readonly formula?: string;
 }
 interface RawRow {
   readonly index: number;
@@ -43,6 +47,34 @@ interface RawRange {
   readonly endRow: number;
   readonly endColumn: number;
 }
+/**
+ * The page-setup half of a sheet's print settings, as the worksheet substream's own records carry them.
+ *
+ * Every field is optional because every record behind it is: [MS-XLS] 2.1.7.20.6's PAGESETUP production makes each of the four margins and Setup itself optional, and a sheet that never had its page setup touched carries none of them. An absent field is therefore "this file states nothing here", which is a different fact from "this file states the default", and content.ts is where the distinction is resolved into the required ContentSheetPrintSettings fields.
+ *
+ * The other half -- the print range and the repeated header bands -- is not here at all, because BIFF8 does not put it in the worksheet substream; see workbook/print-names.ts.
+ */
+interface RawPrintSettings {
+  /** The Setup record's own fields ([MS-XLS] 2.4.257). */
+  readonly setup?: SetupFields;
+  /** Each page margin in points, from its own record ([MS-XLS] 2.4.151, 2.4.219, 2.4.328, 2.4.27), which states it in inches. */
+  readonly marginsPt: {
+    readonly left?: number;
+    readonly right?: number;
+    readonly top?: number;
+    readonly bottom?: number;
+  };
+  /** PrintGrid's fPrintGrid ([MS-XLS] 2.4.202). */
+  readonly printGridlines?: boolean;
+  /** PrintRowCol's printRwCol ([MS-XLS] 2.4.203): whether the row and column headers print. */
+  readonly printHeaders?: boolean;
+  /** WsBool's fFitToPage ([MS-XLS] 2.4.351), which decides whether Setup's iScale or its iFitWidth/iFitHeight pair is the live one. */
+  readonly fitToPage?: boolean;
+  /** Zero-based row indices an explicit page break falls immediately above ([MS-XLS] 2.4.142), ascending and deduplicated. */
+  readonly rowBreaks: readonly number[];
+  /** Zero-based column indices an explicit page break falls immediately to the left of ([MS-XLS] 2.4.343). */
+  readonly columnBreaks: readonly number[];
+}
 /** One worksheet's records, read but not yet mapped onto the shared schema. */
 interface RawSheet {
   readonly cells: readonly RawCell[];
@@ -51,8 +83,10 @@ interface RawSheet {
   readonly merges: readonly RawRange[];
   /** The used range from the Dimensions record ([MS-XLS] 2.4.90), when the sheet declared one. */
   readonly usedRange?: RawRange;
+  /** The sheet's own page setup, as far as its records state it. */
+  readonly print: RawPrintSettings;
 }
 /** Reads one worksheet substream's records. */
-declare function readSheetRecords(records: readonly RecordGroup[], sharedStrings: readonly string[]): RawSheet;
+declare function readSheetRecords(records: readonly RecordGroup[], sharedStrings: readonly string[], formulaSheets?: FormulaSheetContext): RawSheet;
 //#endregion
-export { RawCell, RawCellValue, RawColumn, RawRange, RawRow, RawSheet, readSheetRecords };
+export { RawCell, RawCellValue, RawColumn, RawPrintSettings, RawRange, RawRow, RawSheet, readSheetRecords };

package/dist/workbook/sheet.js

@@ -1,10 +1,12 @@
 import "../biff/record-types.js";
 import { BiffFormatError } from "../biff/records.js";
+import { columnWidthToPoints, inchesToPoints, twipsToPoints } from "../units.js";
+import { unpackSetupFlags } from "../biff/print-setup.js";
 import { BlockCursor } from "../biff/cursor.js";
 import { readXLUnicodeString } from "../biff/strings.js";
 import { errorTextOf } from "../biff/errors.js";
+import { parseFormulaText } from "../biff/ptg.js";
 import { decodeRkNumber } from "../biff/rk.js";
-import { columnWidthToPoints, twipsToPoints } from "../units.js";
 //#region src/workbook/sheet.ts
 /** Row record flag bits, in the 32-bit field following unused1 ([MS-XLS] 2.4.221). */
 const ROW_FLAG_HIDDEN = 32;
@@ -23,13 +25,25 @@ const FORMULA_VALUE_BLANK = 3;
 const MUL_FIXED_BYTES = 6;
 const MULRK_ENTRY_BYTES = 6;
 const MULBLANK_ENTRY_BYTES = 2;
+/** No sheets and no resolvable 3D references -- the default a caller with nothing formula-relevant to offer (every existing test fixture that predates formula-text recovery) gets, so a 3D reference simply fails to resolve rather than throwing on an absent context. */
+const EMPTY_FORMULA_SHEET_CONTEXT = {
+	sheets: [],
+	sheetRanges: []
+};
 /** Reads one worksheet substream's records. */
-function readSheetRecords(records, sharedStrings) {
+function readSheetRecords(records, sharedStrings, formulaSheets = EMPTY_FORMULA_SHEET_CONTEXT) {
 	const cells = [];
 	const rows = [];
 	const columns = [];
 	const merges = [];
 	let usedRange;
+	const marginsPt = {};
+	const rowBreaks = [];
+	const columnBreaks = [];
+	let setup;
+	let printGridlines;
+	let printHeaders;
+	let fitToPage;
 	for (let index = 0; index < records.length; index += 1) {
 		const record = records[index];
 		if (record === void 0) continue;
@@ -72,22 +86,108 @@ function readSheetRecords(records, sharedStrings) {
 			case 516:
 				cells.push(readLabel(record));
 				break;
-			case 6: cells.push(readFormula(record, stringResultAfter(records, index)));
+			case 6:
+				cells.push(readFormula(record, stringResultAfter(records, index), formulaSheets));
+				break;
+			case 161:
+				setup = readSetup(record);
+				break;
+			case 38:
+				marginsPt.left = readMargin(record);
+				break;
+			case 39:
+				marginsPt.right = readMargin(record);
+				break;
+			case 40:
+				marginsPt.top = readMargin(record);
+				break;
+			case 41:
+				marginsPt.bottom = readMargin(record);
+				break;
+			case 43:
+				printGridlines = readGridlineBooleanRecord(record);
+				break;
+			case 42:
+				printHeaders = readBooleanRecord(record);
+				break;
+			case 129:
+				fitToPage = (new BlockCursor(record.blocks).u16() & 256) !== 0;
+				break;
+			case 27:
+				rowBreaks.push(...readPageBreaks(record));
+				break;
+			case 26: columnBreaks.push(...readPageBreaks(record));
 		}
 	}
+	const print = {
+		marginsPt,
+		rowBreaks: ascendingDistinct(rowBreaks),
+		columnBreaks: ascendingDistinct(columnBreaks),
+		...setup === void 0 ? {} : { setup },
+		...printGridlines === void 0 ? {} : { printGridlines },
+		...printHeaders === void 0 ? {} : { printHeaders },
+		...fitToPage === void 0 ? {} : { fitToPage }
+	};
 	return usedRange === void 0 ? {
 		cells,
 		rows,
 		columns,
-		merges
+		merges,
+		print
 	} : {
 		cells,
 		rows,
 		columns,
 		merges,
-		usedRange
+		usedRange,
+		print
 	};
 }
+/** Setup ([MS-XLS] 2.4.257): iPaperSize, iScale, iPageStart, iFitWidth, iFitHeight, a flags word, iRes, iVRes, an eight-byte header margin, an eight-byte footer margin, and iCopies. The starting page number, the two print resolutions, the header/footer margins, and the copy count are read past: ContentSheetPrintSettings has no field for any of them, and Margins models only the four page edges. */
+function readSetup(record) {
+	const cursor = new BlockCursor(record.blocks);
+	const paperCode = cursor.u16();
+	const scalePercent = cursor.u16();
+	cursor.skip(2);
+	return {
+		paperCode,
+		scalePercent,
+		fitWidth: cursor.u16(),
+		fitHeight: cursor.u16(),
+		...unpackSetupFlags(cursor.u16())
+	};
+}
+/** Any of the four margin records ([MS-XLS] 2.4.151, 2.4.219, 2.4.328, 2.4.27): a single Xnum stating that margin in inches. All four share the identical one-field layout, so one reader serves them all. */
+function readMargin(record) {
+	return inchesToPoints(new BlockCursor(record.blocks).f64());
+}
+/** PrintRowCol ([MS-XLS] 2.4.203): a single 16-bit `Boolean` field (2.5.14), whose whole word is the value. [MS-XLS] 2.4.203's own value table states both 0x0000 and 0x0001 as "Row and column headers are not printed", which is a typo in that table rather than two spellings of one meaning -- the record exists precisely to distinguish them, and every real producer writes 1 for printed (confirmed against LibreOffice-written BIFF8, where a sheet with header printing enabled carries 0x0001 and one without carries 0x0000). */
+function readBooleanRecord(record) {
+	return new BlockCursor(record.blocks).u16() !== 0;
+}
+/** PrintGrid ([MS-XLS] 2.4.202): unlike PrintRowCol above, its 16-bit field is only ONE bit wide (`fPrintGrid`) with the remaining 15 "Undefined, and MUST be ignored" -- so a producer leaving anything in those bits would read as gridlines-on under a bare `!== 0` test. No real producer does (LibreOffice writes 0x0000/0x0001, confirmed against its own BIFF8 output), but masking to the one bit the spec actually defines is what the field's own layout says to do. */
+function readGridlineBooleanRecord(record) {
+	return (new BlockCursor(record.blocks).u16() & 1) !== 0;
+}
+/**
+* HorizontalPageBreaks ([MS-XLS] 2.4.142) and VerticalPageBreaks ([MS-XLS] 2.4.343): a count then that many six-byte structures, each an index on the break's own axis followed by the start and end of the break's extent on the other one.
+*
+* Only the index is taken. HorzBrk's colStart/colEnd and VertBrk's rowStart/rowEnd say how far along the perpendicular axis the break runs -- a BIFF8 page break can be partial -- and ContentSheetPrintSettings.manualBreaks models a break as a whole-axis index with no extent, so a partial break is carried as a full one rather than dropped. Both structures have the identical three-field shape, so one reader serves both.
+*/
+function readPageBreaks(record) {
+	const cursor = new BlockCursor(record.blocks);
+	const count = cursor.u16();
+	const indices = [];
+	for (let index = 0; index < count; index += 1) {
+		indices.push(cursor.u16());
+		cursor.skip(4);
+	}
+	return indices;
+}
+/** Page-break indices, ascending and with duplicates collapsed: two records naming the same row are one page break as far as the schema's own index-only model of a break can express. */
+function ascendingDistinct(values) {
+	return [...new Set(values)].sort((a, b) => a - b);
+}
 /**
 * Finds the String record carrying a Formula's cached string result, if it has one.
 *
@@ -313,28 +413,36 @@ function readLabel(record) {
 		fromFormula: false
 	};
 }
+/** The Formula record's own flags field ([MS-XLS] 2.4.127) and calculation cache, between the cached value and the compiled expression -- neither read for its own content; see the two-byte and four-byte skips in readFormula. */
+const FORMULA_FLAGS_BYTES = 2;
+const FORMULA_CALC_CACHE_BYTES = 4;
 /**
-* Formula ([MS-XLS] 2.4.127): a Cell, an eight-byte FormulaValue, flags, a calculation cache, then the compiled expression.
+* Formula ([MS-XLS] 2.4.127): a Cell, an eight-byte FormulaValue, flags, a calculation cache, then a CellParsedFormula -- a two-byte cce followed by exactly that many bytes of compiled Ptg tokens ([MS-XLS] 2.5.198.3).
 *
-* Only the cached VALUE is read. The expression is a CellParsedFormula -- a compiled Ptg token stream rather than text -- and turning one back into a formula string means implementing the whole Ptg vocabulary plus shared-formula and external-reference resolution, which is its own substantial piece of work. So the cell's displayed value is correct and its `formula` field stays absent, rather than a plausible-looking expression being invented for it.
+* Both the cached value and the expression are read: the value from the FormulaValue exactly as before, and the expression by handing the token bytes to biff/ptg.ts's parseFormulaText, which resolves the whole Ptg vocabulary this reader supports and returns undefined for the constructs it does not (a shared formula, an array formula, a defined name, a natural-language reference, a genuinely external 3D reference -- see that module's own boundary). `formula` is attached only when it resolves; a cell it does not resolve for keeps exactly the behaviour this reader always had, its cached value present and `formula` absent.
 */
-function readFormula(record, next) {
+function readFormula(record, next, formulaSheets) {
 	const cursor = new BlockCursor(record.blocks);
 	const header = readCellHeader(cursor);
 	const bytes = cursor.take(8);
 	const view = new DataView(bytes.buffer, bytes.byteOffset, bytes.byteLength);
-	if (!(view.getUint16(6, true) === FORMULA_VALUE_TAGGED)) return {
-		...header,
-		value: {
-			kind: "number",
-			value: view.getFloat64(0, true)
-		},
-		fromFormula: true
+	const value = view.getUint16(6, true) === FORMULA_VALUE_TAGGED ? taggedFormulaValue(view, next) : {
+		kind: "number",
+		value: view.getFloat64(0, true)
 	};
-	return {
+	cursor.skip(FORMULA_FLAGS_BYTES);
+	cursor.skip(FORMULA_CALC_CACHE_BYTES);
+	const cce = cursor.u16();
+	const formula = parseFormulaText(cursor.take(cce), formulaSheets);
+	return formula === void 0 ? {
 		...header,
-		value: taggedFormulaValue(view, next),
+		value,
 		fromFormula: true
+	} : {
+		...header,
+		value,
+		fromFormula: true,
+		formula
 	};
 }
 /** The non-numeric readings of a FormulaValue ([MS-XLS] 2.5.133), selected by its first byte. */