feat(doc-codec): read and write a section's own page size and margins

packages/doc-codec/README.md

@@ -23,11 +23,12 @@ Built and shipped, on the read side:
 - **`isDocBytes`** — distinguishes a `.doc` from the `.xls`, `.ppt` and OLE embeddings that share its container, by looking for a `WordDocument` stream carrying `FibBase.wIdent`.
 - **Document metadata** — `title`/`subject`/`author`/`keywords`/`createdIso`/`modifiedIso` read from a `"\x05SummaryInformation"` stream when one is present (see [Metadata](#metadata)); `comments` and `lastPrintedIso` remain unread, since `LayoutMetadata` has no field for either.
 - **Numbering definitions** — `readDocContent`'s own `numbering` field: every list's glyph/format, level-text template, and start-at value, resolved from `PlfLst`/`PlfLfo` and keyed by the same `listId` a paragraph's `ContentParagraph.list.numId` already carries. Read-only; see [Numbering definitions](#numbering-definitions).
+- **The one section's own page size and margins** — `prop/sep.ts`'s `readSectionProperties` resolves `PlcfSed`/`Sepx` (`sprmSXaPage`/`sprmSYaPage`/`sprmSDxaLeft`/`sprmSDxaRight`/`sprmSDyaTop`/`sprmSDyaBottom`) into `ContentSection.pageSize`/`.margins`, falling back field by field to Word's own new-document default (US Letter, one-inch margins) for a document carrying no `PlcfSed` at all, or for any one sprm it leaves unstated. This reader only ever resolves the section spanning the whole main document — the "Section boundaries" row below states what "one section" still means.
 
 Built and shipped, on the write side — see [Writing](#writing) for the full scope statement:
 
-- **`writeDocContent`** — a `'wordprocessing'` `ContentDocument` (one section, paragraphs of runs and tables) to genuine [MS-DOC] bytes: a real piece table, real `ChpxFkp`/`PapxFkp` pages (splitting across as many as a document's own formatting needs, not just the common one-page case), a spec-conformant empty style sheet, a font table when a run names one, and a `"\x05SummaryInformation"` stream when the input's metadata carries anything that stream can hold (see [Metadata](#metadata)) — wrapped in a real [MS-CFB] compound file via `archive-codec`'s `writeCompoundFile`. A `ContentTable` block is expanded by `table/write.ts`'s `flattenSectionBlocks` into the same flat paragraph sequence every other block already is (see [Tables](#tables)), so table paragraphs flow through the identical `ChpxFkp`/`PapxFkp` paging as every other paragraph rather than a separate table-only path. Each cell's own `background` and `borders` ride along into the row's TAP (see [Cell decoration](#cell-decoration)).
-- Every property `writeDocContent` writes is verified by reading it back through this package's own `readDocContent` (`src/write.test.ts`), and additionally against a real, independent [MS-DOC] implementation: LibreOffice opened, rendered, and re-exported a `writeDocContent` sample without error or content loss, including bold/italic/underline/strike/size/colour/font-family runs, paragraph alignment and indentation, non-Latin-1 and non-BMP text (accented Latin, CJK, an emoji surrogate pair), and a table — recognised as a genuine `table:table`, its row/column/cell structure and both horizontal and vertical merges intact, matching real `table:number-columns-spanned`/`table:number-rows-spanned` attributes and `table:covered-table-cell` elements, and each cell's own background fill and per-side borders recovered with their exact colours, exactly as [Tables](#tables) confirms in full.
+- **`writeDocContent`** — a `'wordprocessing'` `ContentDocument` (one section, paragraphs of runs and tables) to genuine [MS-DOC] bytes: a real piece table, real `ChpxFkp`/`PapxFkp` pages (splitting across as many as a document's own formatting needs, not just the common one-page case), a spec-conformant empty style sheet, a font table when a run names one, a real `PlcfSed`/`Sepx` stating the one section's own page size and margins, and a `"\x05SummaryInformation"` stream when the input's metadata carries anything that stream can hold (see [Metadata](#metadata)) — wrapped in a real [MS-CFB] compound file via `archive-codec`'s `writeCompoundFile`. A `ContentTable` block is expanded by `table/write.ts`'s `flattenSectionBlocks` into the same flat paragraph sequence every other block already is (see [Tables](#tables)), so table paragraphs flow through the identical `ChpxFkp`/`PapxFkp` paging as every other paragraph rather than a separate table-only path. Each cell's own `background` and `borders` ride along into the row's TAP (see [Cell decoration](#cell-decoration)).
+- Every property `writeDocContent` writes is verified by reading it back through this package's own `readDocContent` (`src/write.test.ts`), and additionally against a real, independent [MS-DOC] implementation: LibreOffice opened, rendered, and re-exported a `writeDocContent` sample without error or content loss, including bold/italic/underline/strike/size/colour/font-family runs, paragraph alignment and indentation, non-Latin-1 and non-BMP text (accented Latin, CJK, an emoji surrogate pair), a section's own page size and all four margins (a non-default 600x800pt page with a 90/54/45/36pt left/right/top/bottom margin, confirmed against LibreOffice's own `fo:page-width`/`fo:page-height`/`fo:margin-*` export to the exact point), and a table — recognised as a genuine `table:table`, its row/column/cell structure and both horizontal and vertical merges intact, matching real `table:number-columns-spanned`/`table:number-rows-spanned` attributes and `table:covered-table-cell` elements, and each cell's own background fill and per-side borders recovered with their exact colours, exactly as [Tables](#tables) confirms in full.
 
 **Not built, and not approximated, on either side.** Each of these is a genuine layer of [MS-DOC] that this package does not implement; none is silently faked, and a document using one reads (or fails to write) as though it did not:
 
@@ -38,7 +39,7 @@ Built and shipped, on the write side — see [Writing](#writing) for the full sc
 | **Images and drawn objects**                                    | The anchor characters (`U+0001`, `U+0008`) are dropped rather than emitted as control characters. No picture data is read. `writeDocContent` refuses an image block.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | **Style-inherited formatting**                                  | A style's own property sets live in the `STD`'s `grLPUpxSw` and are not read, so a paragraph's formatting is the document defaults plus its own direct exceptions. A `Heading 1` paragraph reports its `styleId` and `headingLevel` but not the boldness or size its style would supply. `writeDocContent` writes no paragraph styles at all (every paragraph is `istd` 0) and does not round-trip `styleId`/`headingLevel`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
 | **Subdocuments**                                                | Only the main document (character positions 0 to `ccpText`) is converted. Footnotes, endnotes, headers, footers, comments and text boxes are not, in either direction.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| **Section properties**                                          | Section boundaries are not read, so the whole document is one section, and its page size and margins are a US Letter placeholder rather than the document's own. `writeDocContent` refuses a `ContentDocument` with more than one section, rather than silently merging their content into what would read back as one.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| **Section boundaries**                                          | Section boundaries themselves are not read — the whole document is always treated as one section, spanning the entire main document — so a multi-section `.doc`'s later sections' own page size and margins are never consulted, only the first's (see the read-side page-size/margins bullet above for what is now read of that one section). `writeDocContent` refuses a `ContentDocument` with more than one section, rather than silently merging their content into what would read back as one.                                                                                                                                                                                                                                                                                                                                                                                                                 |
 | **Extended and user-defined document properties**               | `title`/`subject`/`author`/`keywords`/`createdIso`/`modifiedIso` are read from and written to a `"\x05SummaryInformation"` stream when present (see [Metadata](#metadata)); the sibling `"\x05DocumentSummaryInformation"` stream (company, manager, and custom user-defined properties) is not read or written at all.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | **Encryption**                                                  | An encrypted or XOR-obfuscated document is refused with a `DocUnsupportedError` rather than read as plaintext. `writeDocContent` never encrypts.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
 | **`sprmPHugePapx` / `sprmPTableProps`**                         | Paragraph properties stored indirectly in the Data stream are not followed, so such a paragraph reads with fewer properties than it states. [MS-DOC] 2.4.3's own Overview of Tables text names `sprmPTableProps` as a real, legal alternative to `sprmTDefTable` some applications process — but a real producer's row mark is not shown to prefer it: a genuine LibreOffice-authored `.doc` table's own row mark states its TAP through the identical direct `sprmTDefTable` this package's reader and writer already use (confirmed by parsing a LibreOffice 26.2.5.2-authored table's raw `PapxFkp` bytes; see [ExaDev/documents.js#892](https://github.com/ExaDev/documents.js/issues/892)), matching 2.4.3's own compatibility guidance ("An application SHOULD use sprmTDefTable to define table cells for applications that do not process sprmPTableProps"). `writeDocContent` never writes an indirect Papx. |

packages/doc-codec/src/fib/fib.ts

@@ -41,6 +41,9 @@ export interface Fib {
   readonly fcClx: number;
   readonly lcbClx: number;
 
+  readonly fcPlcfSed: number;
+  readonly lcbPlcfSed: number;
+
   readonly fcSttbfFfn: number;
   readonly lcbSttbfFfn: number;
 
@@ -119,6 +122,8 @@ export function parseFib(wordDocument: Uint8Array): Fib {
     lcbPlcfBtePapx: fcLcb(FC_LCB_VALUE_INDEX.lcbPlcfBtePapx),
     fcClx: fcLcb(FC_LCB_VALUE_INDEX.fcClx),
     lcbClx: fcLcb(FC_LCB_VALUE_INDEX.lcbClx),
+    fcPlcfSed: fcLcb(FC_LCB_VALUE_INDEX.fcPlcfSed),
+    lcbPlcfSed: fcLcb(FC_LCB_VALUE_INDEX.lcbPlcfSed),
     fcSttbfFfn: fcLcb(FC_LCB_VALUE_INDEX.fcSttbfFfn),
     lcbSttbfFfn: fcLcb(FC_LCB_VALUE_INDEX.lcbSttbfFfn),
     fcPlfLst: fcLcb(FC_LCB_VALUE_INDEX.fcPlfLst),

packages/doc-codec/src/fib/offsets.ts

@@ -42,6 +42,9 @@ export const LW_OFFSET = {
 export const FC_LCB_VALUE_INDEX = {
   fcStshf: 2,
   lcbStshf: 3,
+  // Pair 6, counted the same way as the fcSttbfFfn comment below counts pair 15: fcStshfOrig(0), fcStshf(1), fcPlcffndRef(2), fcPlcffndTxt(3), fcPlcfandRef(4), fcPlcfandTxt(5), fcPlcfSed(6).
+  fcPlcfSed: 12,
+  lcbPlcfSed: 13,
   fcPlcfBteChpx: 24,
   lcbPlcfBteChpx: 25,
   fcPlcfBtePapx: 26,

packages/doc-codec/src/fib/write.ts

@@ -31,6 +31,8 @@ export interface FibWriteSpec {
   readonly cbMac: number;
   readonly fcClx: number;
   readonly lcbClx: number;
+  readonly fcPlcfSed: number;
+  readonly lcbPlcfSed: number;
   readonly fcPlcfBteChpx: number;
   readonly lcbPlcfBteChpx: number;
   readonly fcPlcfBtePapx: number;
@@ -83,6 +85,7 @@ export function buildFib(spec: FibWriteSpec): Uint8Array<ArrayBuffer> {
   );
   pair(FC_LCB_VALUE_INDEX.fcSttbfFfn, spec.fcSttbfFfn, spec.lcbSttbfFfn);
   pair(FC_LCB_VALUE_INDEX.fcClx, spec.fcClx, spec.lcbClx);
+  pair(FC_LCB_VALUE_INDEX.fcPlcfSed, spec.fcPlcfSed, spec.lcbPlcfSed);
   // cswNew (the 2 bytes at FIB_FC_LCB_BLOB_OFFSET + blobBytes) stays 0, which [MS-DOC] mandates for nFib 0x00C1 and which correctly leaves fibRgCswNew absent.
 
   if (readUint16LE(bytes, 0) !== FIB_W_IDENT) {

packages/doc-codec/src/index.ts

@@ -18,6 +18,8 @@ export * from "./prop/chp";
 export * from "./prop/chp-write";
 export * from "./prop/pap";
 export * from "./prop/pap-write";
+export * from "./prop/sep";
+export * from "./prop/sep-write";
 export * from "./style/stsh";
 export * from "./style/fonts";
 export * from "./list/numbering";