Xteink-X4-crosspoint-reader/lib/Epub/Epub/hyphenation/Hyphenator.cpp
Arthur Tazhitdinov 8824c87490
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>
2026-01-19 12:56:26 +00:00

98 lines
3.2 KiB
C++

#include "Hyphenator.h"
#include <vector>
#include "HyphenationCommon.h"
#include "LanguageRegistry.h"
const LanguageHyphenator* Hyphenator::cachedHyphenator_ = nullptr;
namespace {
// Maps a BCP-47 language tag to a language-specific hyphenator.
const LanguageHyphenator* hyphenatorForLanguage(const std::string& langTag) {
if (langTag.empty()) return nullptr;
// Extract primary subtag and normalize to lowercase (e.g., "en-US" -> "en").
std::string primary;
primary.reserve(langTag.size());
for (char c : langTag) {
if (c == '-' || c == '_') break;
if (c >= 'A' && c <= 'Z') c = static_cast<char>(c - 'A' + 'a');
primary.push_back(c);
}
if (primary.empty()) return nullptr;
return getLanguageHyphenatorForPrimaryTag(primary);
}
// Maps a codepoint index back to its byte offset inside the source word.
size_t byteOffsetForIndex(const std::vector<CodepointInfo>& cps, const size_t index) {
return (index < cps.size()) ? cps[index].byteOffset : (cps.empty() ? 0 : cps.back().byteOffset);
}
// Builds a vector of break information from explicit hyphen markers in the given codepoints.
std::vector<Hyphenator::BreakInfo> buildExplicitBreakInfos(const std::vector<CodepointInfo>& cps) {
std::vector<Hyphenator::BreakInfo> breaks;
// Scan every codepoint looking for explicit/soft hyphen markers that are surrounded by letters.
for (size_t i = 1; i + 1 < cps.size(); ++i) {
const uint32_t cp = cps[i].value;
if (!isExplicitHyphen(cp) || !isAlphabetic(cps[i - 1].value) || !isAlphabetic(cps[i + 1].value)) {
continue;
}
// Offset points to the next codepoint so rendering starts after the hyphen marker.
breaks.push_back({cps[i + 1].byteOffset, isSoftHyphen(cp)});
}
return breaks;
}
} // namespace
std::vector<Hyphenator::BreakInfo> Hyphenator::breakOffsets(const std::string& word, const bool includeFallback) {
if (word.empty()) {
return {};
}
// Convert to codepoints and normalize word boundaries.
auto cps = collectCodepoints(word);
trimSurroundingPunctuationAndFootnote(cps);
const auto* hyphenator = cachedHyphenator_;
// Explicit hyphen markers (soft or hard) take precedence over language breaks.
auto explicitBreakInfos = buildExplicitBreakInfos(cps);
if (!explicitBreakInfos.empty()) {
return explicitBreakInfos;
}
// Ask language hyphenator for legal break points.
std::vector<size_t> indexes;
if (hyphenator) {
indexes = hyphenator->breakIndexes(cps);
}
// Only add fallback breaks if needed
if (includeFallback && indexes.empty()) {
const size_t minPrefix = hyphenator ? hyphenator->minPrefix() : LiangWordConfig::kDefaultMinPrefix;
const size_t minSuffix = hyphenator ? hyphenator->minSuffix() : LiangWordConfig::kDefaultMinSuffix;
for (size_t idx = minPrefix; idx + minSuffix <= cps.size(); ++idx) {
indexes.push_back(idx);
}
}
if (indexes.empty()) {
return {};
}
std::vector<Hyphenator::BreakInfo> breaks;
breaks.reserve(indexes.size());
for (const size_t idx : indexes) {
breaks.push_back({byteOffsetForIndex(cps, idx), true});
}
return breaks;
}
void Hyphenator::setPreferredLanguage(const std::string& lang) { cachedHyphenator_ = hyphenatorForLanguage(lang); }