Crosspoint/docs/file-formats.md

# File Formats

These formats describe the SD-card cache files under `/.crosspoint/epub_<hash>/`.
All POD fields are written in the ESP32 little-endian representation used by
`Serialization.h`; strings are length-prefixed UTF-8.

## `book.bin`

### Version 7

`book.bin` stores EPUB metadata plus lookup tables for spine and TOC entries.
The current firmware writes this version from `BookMetadataCache`.

ImHex pattern:

```c++
import std.mem;
import std.string;
import std.core;

#define EXPECTED_VERSION 7
#define MAX_STRING_LENGTH 65535

struct String {
    u32 length [[hidden, comment("String byte length")]];
    if (length > MAX_STRING_LENGTH) {
        std::warning(std::format("Unusually large string length: {} bytes", length));
    }
    char data[length] [[comment("UTF-8 string data")]];
} [[sealed, format("format_string"), comment("Length-prefixed UTF-8 string")]];

fn format_string(String s) {
    return s.data;
};

struct Metadata {
    String title [[comment("Book title")]];
    String author [[comment("Book author")]];
    String language [[comment("Book language code")]];
    String coverItemHref [[comment("Path to cover image")]];
    String textReferenceHref [[comment("Path to guided first text reference")]];
};

struct SpineEntry {
    String href [[comment("Resource path")]];
    u32 cumulativeSize [[comment("Cumulative uncompressed spine size through this entry")]];
    s16 tocIndex [[comment("Index into TOC, or inherited/previous TOC index when no direct entry exists")]];
};

struct TocEntry {
    String title [[comment("Chapter/section title")]];
    String href [[comment("Resource path")]];
    String anchor [[comment("Fragment identifier")]];
    u8 level [[comment("Nesting level")]];
    s16 spineIndex [[comment("Index into spine (-1 if none)")]];
};

struct BookBin {
    u8 version;
    if (version != EXPECTED_VERSION) {
        std::error(std::format("Unsupported version: {} (expected {})", version, EXPECTED_VERSION));
    }

    u32 lutOffset [[comment("Offset to lookup tables")]];
    u16 spineCount;
    u16 tocCount;

    Metadata metadata;

    u32 currentOffset = $;
    if (currentOffset != lutOffset) {
        std::warning(std::format("LUT offset mismatch: expected 0x{:X}, got 0x{:X}", lutOffset, currentOffset));
    }

    u32 spineLut[spineCount] [[comment("Spine entry offsets")]];
    u32 tocLut[tocCount] [[comment("TOC entry offsets")]];

    SpineEntry spines[spineCount];
    TocEntry toc[tocCount];
};

BookBin book @ 0x00;

u32 fileSize = std::mem::size();
u32 parsedSize = $;
if (parsedSize != fileSize) {
    std::warning(std::format("Unparsed data detected: {} bytes remaining at offset 0x{:X}", fileSize - parsedSize, parsedSize));
}
```

## `section.bin`

### Version 28

Each file in `sections/*.bin` stores one laid-out spine section. The header is
also the cache-busting key: if any layout-affecting setting differs from the
current reader settings, the section is discarded and rebuilt.

Version 28 includes:

- cache-busting fields for paragraph alignment, hyphenation, embedded CSS,
  image rendering mode, and Focus Reading
- page offset LUT
- anchor-to-page map for fragment and footnote navigation
- paragraph and list-item LUTs used by KOReader sync page refinement
- optional per-word Focus Reading split metadata
- per-page footnote entries
- serialized word style bits for underline, strikethrough, superscript, and
  subscript

ImHex pattern:

```c++
import std.mem;
import std.string;
import std.core;

#define EXPECTED_VERSION 28
#define MAX_STRING_LENGTH 65535
#define FOOTNOTE_NUMBER_LEN 32
#define FOOTNOTE_HREF_LEN 96

struct String {
    u32 length [[hidden, comment("String byte length")]];
    if (length > MAX_STRING_LENGTH) {
        std::warning(std::format("Unusually large string length: {} bytes", length));
    }
    char data[length] [[comment("UTF-8 string data")]];
} [[sealed, format("format_string"), comment("Length-prefixed UTF-8 string")]];

fn format_string(String s) {
    return s.data;
};

enum PageElementTag : u8 {
    TAG_PageLine = 1,
    TAG_PageImage = 2,
    TAG_PageHorizontalRule = 3
};

enum WordStyle : u8 {
    REGULAR = 0,
    BOLD = 1,
    ITALIC = 2,
    BOLD_ITALIC = 3,
    UNDERLINE = 4,
    STRIKETHROUGH = 8,
    SUP = 16,
    SUB = 32
};

enum TextAlign : u8 {
    JUSTIFIED = 0,
    LEFT_ALIGN = 1,
    CENTER_ALIGN = 2,
    RIGHT_ALIGN = 3,
    NONE = 4
};

struct BlockStyle {
    TextAlign alignment;
    bool textAlignDefined;
    s16 marginTop;
    s16 marginBottom;
    s16 marginLeft;
    s16 marginRight;
    s16 paddingTop;
    s16 paddingBottom;
    s16 paddingLeft;
    s16 paddingRight;
    s16 textIndent;
    bool textIndentDefined;
    bool isRtl;
    bool directionDefined;
};

struct TextBlock {
    u16 wordCount;
    String words[wordCount];
    s16 wordXPos[wordCount];
    WordStyle wordStyle[wordCount];

    u8 hasFocus;
    if (hasFocus != 0) {
        u8 wordFocusBoundary[wordCount] [[comment("UTF-8 byte boundary between bold prefix and suffix")]];
        u16 wordFocusSuffixX[wordCount] [[comment("Suffix x offset from word start")]];
    }

    BlockStyle blockStyle;
};

struct ImageBlock {
    String imagePath;
    s16 width;
    s16 height;
};

struct PageLine {
    s16 xPos;
    s16 yPos;
    TextBlock block;
};

struct PageImage {
    s16 xPos;
    s16 yPos;
    ImageBlock image;
};

struct PageHorizontalRule {
    s16 xPos;
    s16 yPos;
    u16 width;
    u8 thickness;
};

struct PageElement {
    PageElementTag pageElementType;
    if (pageElementType == TAG_PageLine) {
        PageLine pageLine [[inline]];
    } else if (pageElementType == TAG_PageImage) {
        PageImage pageImage [[inline]];
    } else if (pageElementType == TAG_PageHorizontalRule) {
        PageHorizontalRule horizontalRule [[inline]];
    } else {
        std::error(std::format("Unknown page element type: {}", pageElementType));
    }
};

struct FootnoteEntry {
    char number[FOOTNOTE_NUMBER_LEN];
    char href[FOOTNOTE_HREF_LEN];
};

struct Page {
    u16 elementCount;
    PageElement elements[elementCount] [[inline]];

    u16 footnoteCount;
    FootnoteEntry footnotes[footnoteCount];
};

struct AnchorEntry {
    String anchor;
    u16 page;
};

struct AnchorMap {
    u16 count;
    AnchorEntry entries[count];
};

struct ParagraphLut {
    u16 count;
    u16 paragraphIndex[count];
};

struct SectionBin {
    u8 version;
    if (version != EXPECTED_VERSION) {
        std::error(std::format("Unsupported version: {} (expected {})", version, EXPECTED_VERSION));
    }

    s32 fontId;
    float lineCompression;
    bool extraParagraphSpacing;
    u8 paragraphAlignment;
    u16 viewportWidth;
    u16 viewportHeight;
    bool hyphenationEnabled;
    bool embeddedStyle;
    u8 imageRendering;
    bool focusReadingEnabled;

    u16 pageCount;
    u32 pageLutOffset;
    u32 anchorMapOffset;
    u32 paragraphLutOffset;
    u32 listItemLutOffset;

    Page pages[pageCount];

    u32 currentOffset = $;
    if (currentOffset != pageLutOffset) {
        std::warning(std::format("Page LUT offset mismatch: expected 0x{:X}, got 0x{:X}", pageLutOffset, currentOffset));
    }

    u32 pageLut[pageCount] [[comment("Page data offsets")]];

    if (anchorMapOffset != 0) {
        AnchorMap anchorMap @ anchorMapOffset;
    }

    if (paragraphLutOffset != 0) {
        ParagraphLut paragraphLut @ paragraphLutOffset;
    }

    if (listItemLutOffset != 0 && paragraphLutOffset != 0) {
        u16 listItemIndex[paragraphLut.count] @ listItemLutOffset;
    }
};

SectionBin section @ 0x00;

u32 fileSize = std::mem::size();
u32 parsedSize = $;
if (parsedSize != fileSize) {
    std::warning(std::format("Unparsed data detected: {} bytes remaining at offset 0x{:X}", fileSize - parsedSize, parsedSize));
}
```