feat: dict based Hyphenation (#305)

## Summary

* Adds (optional) Hyphenation for English, French, German, Russian
languages

## Additional Context

* Included hyphenation dictionaries add approximately 280kb to the flash
usage (German alone takes 200kb)
* Trie encoded dictionaries are adopted from hypher project
(https://github.com/typst/hypher)
* Soft hyphens (and other explicit hyphens) take precedence over
dict-based hyphenation. Overall, the hyphenation rules are quite
aggressive, as I believe it makes more sense on our smaller screen.

---------

Co-authored-by: Dave Allie <dave@daveallie.com>
This commit is contained in:
Arthur Tazhitdinov
2026-01-19 12:56:26 +00:00
committed by GitHub
co-authored by Dave Allie
parent 0beaaaacba
commit 09f8fa84b9
40 changed files with 36465 additions and 52 deletions
+6 -3
View File
@@ -9,7 +9,7 @@
#include "FsHelpers.h"
namespace {
constexpr uint8_t BOOK_CACHE_VERSION = 4;
constexpr uint8_t BOOK_CACHE_VERSION = 5;
constexpr char bookBinFile[] = "/book.bin";
constexpr char tmpSpineBinFile[] = "/spine.bin.tmp";
constexpr char tmpTocBinFile[] = "/toc.bin.tmp";
@@ -87,8 +87,9 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
constexpr uint32_t headerASize =
sizeof(BOOK_CACHE_VERSION) + /* LUT Offset */ sizeof(uint32_t) + sizeof(spineCount) + sizeof(tocCount);
const uint32_t metadataSize = metadata.title.size() + metadata.author.size() + metadata.coverItemHref.size() +
metadata.textReferenceHref.size() + sizeof(uint32_t) * 4;
const uint32_t metadataSize = metadata.title.size() + metadata.author.size() + metadata.language.size() +
metadata.coverItemHref.size() + metadata.textReferenceHref.size() +
sizeof(uint32_t) * 5;
const uint32_t lutSize = sizeof(uint32_t) * spineCount + sizeof(uint32_t) * tocCount;
const uint32_t lutOffset = headerASize + metadataSize;
@@ -100,6 +101,7 @@ bool BookMetadataCache::buildBookBin(const std::string& epubPath, const BookMeta
// Metadata
serialization::writeString(bookFile, metadata.title);
serialization::writeString(bookFile, metadata.author);
serialization::writeString(bookFile, metadata.language);
serialization::writeString(bookFile, metadata.coverItemHref);
serialization::writeString(bookFile, metadata.textReferenceHref);
@@ -289,6 +291,7 @@ bool BookMetadataCache::load() {
serialization::readString(bookFile, coreMetadata.title);
serialization::readString(bookFile, coreMetadata.author);
serialization::readString(bookFile, coreMetadata.language);
serialization::readString(bookFile, coreMetadata.coverItemHref);
serialization::readString(bookFile, coreMetadata.textReferenceHref);