mirror of
https://github.com/daveallie/crosspoint-reader.git
synced 2026-02-04 06:37:38 +03:00
8824c87490
## 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>
43 lines
1.6 KiB
C++
43 lines
1.6 KiB
C++
#include "LanguageRegistry.h"
|
|
|
|
#include <algorithm>
|
|
#include <array>
|
|
|
|
#include "HyphenationCommon.h"
|
|
#include "generated/hyph-de.trie.h"
|
|
#include "generated/hyph-en.trie.h"
|
|
#include "generated/hyph-fr.trie.h"
|
|
#include "generated/hyph-ru.trie.h"
|
|
|
|
namespace {
|
|
|
|
// English hyphenation patterns (3/3 minimum prefix/suffix length)
|
|
LanguageHyphenator englishHyphenator(en_us_patterns, isLatinLetter, toLowerLatin, 3, 3);
|
|
LanguageHyphenator frenchHyphenator(fr_patterns, isLatinLetter, toLowerLatin);
|
|
LanguageHyphenator germanHyphenator(de_patterns, isLatinLetter, toLowerLatin);
|
|
LanguageHyphenator russianHyphenator(ru_ru_patterns, isCyrillicLetter, toLowerCyrillic);
|
|
|
|
using EntryArray = std::array<LanguageEntry, 4>;
|
|
|
|
const EntryArray& entries() {
|
|
static const EntryArray kEntries = {{{"english", "en", &englishHyphenator},
|
|
{"french", "fr", &frenchHyphenator},
|
|
{"german", "de", &germanHyphenator},
|
|
{"russian", "ru", &russianHyphenator}}};
|
|
return kEntries;
|
|
}
|
|
|
|
} // namespace
|
|
|
|
const LanguageHyphenator* getLanguageHyphenatorForPrimaryTag(const std::string& primaryTag) {
|
|
const auto& allEntries = entries();
|
|
const auto it = std::find_if(allEntries.begin(), allEntries.end(),
|
|
[&primaryTag](const LanguageEntry& entry) { return primaryTag == entry.primaryTag; });
|
|
return (it != allEntries.end()) ? it->hyphenator : nullptr;
|
|
}
|
|
|
|
LanguageEntryView getLanguageEntries() {
|
|
const auto& allEntries = entries();
|
|
return LanguageEntryView{allEntries.data(), allEntries.size()};
|
|
}
|