This commit is contained in:
Fabio Barbon 2026-02-02 21:28:59 +11:00 committed by GitHub
commit 375c2d4caf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 5133 additions and 2 deletions

View File

@ -13,7 +13,9 @@ fi
# --modified: files tracked by git that have been modified (staged or unstaged)
# --exclude-standard: ignores files in .gitignore
# Additionally exclude files in 'lib/EpdFont/builtinFonts/' as they are script-generated.
# Also exclude files in 'lib/Epub/Epub/hyphenation/generated/' as they are script-generated.
git ls-files --exclude-standard ${GIT_LS_FILES_FLAGS} \
| grep -E '\.(c|cpp|h|hpp)$' \
| grep -v -E '^lib/EpdFont/builtinFonts/' \
| grep -v -E '^lib/Epub/Epub/hyphenation/generated/' \
| xargs -r clang-format -style=file -i

View File

@ -8,6 +8,7 @@
#include "generated/hyph-en.trie.h"
#include "generated/hyph-es.trie.h"
#include "generated/hyph-fr.trie.h"
#include "generated/hyph-it.trie.h"
#include "generated/hyph-ru.trie.h"
namespace {
@ -18,15 +19,17 @@ LanguageHyphenator frenchHyphenator(fr_patterns, isLatinLetter, toLowerLatin);
LanguageHyphenator germanHyphenator(de_patterns, isLatinLetter, toLowerLatin);
LanguageHyphenator russianHyphenator(ru_ru_patterns, isCyrillicLetter, toLowerCyrillic);
LanguageHyphenator spanishHyphenator(es_patterns, isLatinLetter, toLowerLatin);
LanguageHyphenator italianHyphenator(it_patterns, isLatinLetter, toLowerLatin);
using EntryArray = std::array<LanguageEntry, 5>;
using EntryArray = std::array<LanguageEntry, 6>;
const EntryArray& entries() {
static const EntryArray kEntries = {{{"english", "en", &englishHyphenator},
{"french", "fr", &frenchHyphenator},
{"german", "de", &germanHyphenator},
{"russian", "ru", &russianHyphenator},
{"spanish", "es", &spanishHyphenator}}};
{"spanish", "es", &spanishHyphenator},
{"italian", "it", &italianHyphenator}}};
return kEntries;
}

View File

@ -0,0 +1,113 @@
#pragma once
#include <cstddef>
#include <cstdint>
#include "../SerializedHyphenationTrie.h"
// Auto-generated by generate_hyphenation_trie.py. Do not edit manually.
alignas(4) constexpr uint8_t it_trie_data[] = {
0x00, 0x00, 0x05, 0xC4, 0x17, 0x0C, 0x33, 0x35, 0x0C, 0x29, 0x22, 0x0D, 0x3E, 0x0B, 0x47, 0x20,
0x0D, 0x16, 0x0B, 0x34, 0x0D, 0x21, 0x0C, 0x3D, 0x1F, 0x0C, 0x2A, 0x17, 0x2A, 0x0B, 0x02, 0x0C,
0x01, 0x02, 0x16, 0x02, 0x0D, 0x0C, 0x0C, 0x0D, 0x03, 0x0C, 0x01, 0x0C, 0x0E, 0x0D, 0x04, 0x02,
0x0B, 0xA0, 0x00, 0x42, 0x21, 0x6E, 0xFD, 0xA0, 0x00, 0x72, 0x21, 0x6E, 0xFD, 0xA1, 0x00, 0x61,
0x6D, 0xFD, 0x21, 0x69, 0xFB, 0x21, 0x74, 0xFD, 0x22, 0x70, 0x6E, 0xEC, 0xFD, 0xA0, 0x00, 0x91,
0x21, 0x6F, 0xFD, 0x21, 0x69, 0xFD, 0xA0, 0x00, 0xA2, 0x21, 0x73, 0xFD, 0x21, 0x70, 0xFD, 0xA0,
0x00, 0xC2, 0x21, 0x6D, 0xFD, 0x21, 0x75, 0xFD, 0x21, 0x63, 0xFD, 0x21, 0x72, 0xFD, 0xA0, 0x00,
0xE1, 0x21, 0x6F, 0xFD, 0x21, 0x72, 0xFD, 0x21, 0x74, 0xFD, 0x21, 0x6E, 0xFD, 0xA3, 0x01, 0x11,
0x61, 0x69, 0x6F, 0xDF, 0xEE, 0xFD, 0xA0, 0x00, 0xF2, 0x21, 0x65, 0xFD, 0x21, 0x6E, 0xFD, 0x21,
0x69, 0xFD, 0x21, 0x63, 0xFD, 0x21, 0x73, 0xFD, 0xA1, 0x01, 0x11, 0x69, 0xFD, 0xA0, 0x01, 0x12,
0x21, 0x75, 0xFD, 0x21, 0x65, 0xFD, 0x21, 0x78, 0xFD, 0xA0, 0x01, 0x32, 0x21, 0x6B, 0xFD, 0x21,
0x6E, 0xFD, 0xA0, 0x00, 0x71, 0x21, 0x65, 0xFD, 0x22, 0x61, 0x65, 0xF7, 0xFD, 0x21, 0x72, 0xFB,
0xA0, 0x01, 0x52, 0x21, 0x61, 0xFD, 0x21, 0x73, 0xFD, 0x21, 0x70, 0xFD, 0x21, 0x69, 0xFD, 0xA0,
0x01, 0x71, 0x21, 0x6F, 0xFD, 0x21, 0x63, 0xFD, 0x21, 0x72, 0xFD, 0x21, 0x61, 0xFD, 0xA0, 0x00,
0x61, 0x21, 0x6F, 0xFD, 0x21, 0x74, 0xFD, 0x41, 0x70, 0xFF, 0x50, 0x21, 0x6F, 0xFC, 0x21, 0x74,
0xFD, 0x22, 0x70, 0x72, 0xF3, 0xFD, 0x21, 0x61, 0xE8, 0x21, 0x72, 0xFD, 0xA0, 0x00, 0xF1, 0x22,
0x6C, 0x72, 0xFD, 0xFD, 0x21, 0x69, 0xE3, 0x21, 0x6C, 0xFD, 0x41, 0x65, 0xFF, 0x43, 0xA0, 0x01,
0x11, 0x25, 0x61, 0x68, 0x6F, 0x72, 0x73, 0xE8, 0xEE, 0xF6, 0xF9, 0xFD, 0xA0, 0x01, 0x82, 0x21,
0x72, 0xFD, 0x21, 0x63, 0xFD, 0x21, 0x73, 0xFD, 0x21, 0x69, 0xFD, 0x21, 0x65, 0xFD, 0xA0, 0x01,
0xA2, 0x21, 0x65, 0xFD, 0x21, 0x72, 0xFD, 0x21, 0x61, 0xFD, 0x41, 0x75, 0xFF, 0x4C, 0x42, 0x6C,
0x72, 0xFF, 0xFC, 0xFF, 0x48, 0x21, 0x62, 0xF9, 0x22, 0x68, 0x75, 0xEF, 0xFD, 0x47, 0x63, 0x64,
0x6C, 0x6E, 0x70, 0x72, 0x74, 0xFF, 0x5C, 0xFF, 0x5C, 0xFF, 0x5C, 0xFF, 0x5C, 0xFF, 0x5C, 0xFF,
0x5C, 0xFF, 0x5C, 0x21, 0x73, 0xEA, 0x21, 0x6E, 0xFD, 0x21, 0x61, 0xFD, 0xA1, 0x01, 0x11, 0x72,
0xFD, 0x41, 0x6E, 0xFF, 0x15, 0x21, 0x67, 0xFC, 0xA0, 0x01, 0xC2, 0x21, 0x74, 0xFD, 0x21, 0x6C,
0xFD, 0x22, 0x61, 0x65, 0xF4, 0xFD, 0x52, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x6C, 0x6E, 0x6F,
0x70, 0x72, 0x73, 0x74, 0x77, 0x68, 0x6A, 0x6B, 0x7A, 0xFE, 0xC2, 0xFE, 0xCD, 0xFE, 0xF7, 0xFF,
0x12, 0xFF, 0x20, 0xFF, 0x37, 0xFF, 0x46, 0xFF, 0x55, 0xFF, 0x6B, 0xFF, 0x8B, 0xFF, 0xA5, 0xFF,
0xC2, 0xFF, 0xE6, 0xFF, 0xFB, 0xFF, 0x88, 0xFF, 0x88, 0xFF, 0x88, 0xFF, 0x88, 0xA0, 0x01, 0xE2,
0xA0, 0x00, 0xD1, 0x24, 0x61, 0x65, 0x6F, 0x75, 0xFD, 0xFD, 0xFD, 0xFD, 0x21, 0x6F, 0xF4, 0x21,
0x61, 0xF1, 0xA0, 0x01, 0xE1, 0x21, 0x2E, 0xFD, 0x24, 0x69, 0x75, 0x79, 0x74, 0xEB, 0xF4, 0xF7,
0xFD, 0x21, 0x75, 0xDF, 0xA0, 0x00, 0x51, 0x22, 0x69, 0x77, 0xFA, 0xFD, 0x21, 0x69, 0xD7, 0xAE,
0x02, 0x01, 0x62, 0x63, 0x64, 0x66, 0x6D, 0x6E, 0x70, 0x73, 0x74, 0x76, 0x6C, 0x72, 0x2E, 0x27,
0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xE3, 0xF5, 0xF5, 0xE3, 0xE3, 0x22, 0x2E,
0x27, 0xC4, 0xC7, 0xC6, 0x00, 0x51, 0x68, 0x2E, 0x27, 0x62, 0x72, 0x6E, 0xFF, 0xBF, 0xFF, 0xBF,
0xFF, 0xFB, 0xFF, 0xBF, 0xFE, 0xFB, 0xFF, 0xBF, 0xD0, 0x02, 0x01, 0x62, 0x63, 0x64, 0x66, 0x6B,
0x6D, 0x6E, 0x71, 0x73, 0x74, 0x7A, 0x68, 0x6C, 0x72, 0x2E, 0x27, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF,
0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF, 0xAA, 0xFF,
0xAA, 0xFF, 0xEB, 0xFF, 0xBC, 0xFF, 0xBC, 0xFF, 0xAA, 0xFF, 0xAA, 0xCE, 0x02, 0x01, 0x62, 0x64,
0x67, 0x6C, 0x6D, 0x6E, 0x70, 0x72, 0x73, 0x74, 0x76, 0x77, 0x2E, 0x27, 0xFF, 0x77, 0xFF, 0x77,
0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x89, 0xFF, 0x77, 0xFF, 0x77,
0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x77, 0xFF, 0x77, 0xCA, 0x02, 0x01, 0x62, 0x67, 0x66, 0x6E, 0x6C,
0x72, 0x73, 0x74, 0x2E, 0x27, 0xFF, 0x4A, 0xFF, 0x4A, 0xFF, 0x4A, 0xFF, 0x4A, 0xFF, 0x5C, 0xFF,
0x5C, 0xFF, 0x4A, 0xFF, 0x4A, 0xFF, 0x4A, 0xFF, 0x4A, 0xA0, 0x02, 0x12, 0xA1, 0x00, 0x51, 0x74,
0xFD, 0xD1, 0x02, 0x01, 0x62, 0x64, 0x66, 0x67, 0x68, 0x6C, 0x6D, 0x6E, 0x70, 0x72, 0x73, 0x74,
0x76, 0x77, 0x7A, 0x2E, 0x27, 0xFF, 0x21, 0xFF, 0x21, 0xFF, 0x21, 0xFF, 0x21, 0xFF, 0xFB, 0xFF,
0x33, 0xFF, 0x21, 0xFF, 0x33, 0xFF, 0x21, 0xFF, 0x33, 0xFF, 0x21, 0xFF, 0x21, 0xFF, 0x21, 0xFF,
0x21, 0xFF, 0x21, 0xFF, 0x21, 0xFF, 0x21, 0x41, 0x70, 0xFD, 0x4D, 0xCB, 0x02, 0x01, 0x62, 0x64,
0x68, 0x69, 0x6C, 0x6D, 0x6E, 0x72, 0x76, 0x2E, 0x27, 0xFE, 0xE7, 0xFE, 0xE7, 0xFE, 0xE7, 0xFF,
0xFC, 0xFE, 0xF9, 0xFE, 0xE7, 0xFE, 0xE7, 0xFE, 0xE7, 0xFE, 0xE7, 0xFE, 0xE7, 0xFE, 0xE7, 0xC2,
0x02, 0x01, 0x2E, 0x27, 0xFE, 0xC3, 0xFE, 0xC3, 0xCB, 0x02, 0x01, 0x67, 0x66, 0x68, 0x6B, 0x6C,
0x6D, 0x72, 0x73, 0x74, 0x2E, 0x27, 0xFE, 0xBA, 0xFE, 0xBA, 0xFE, 0xCC, 0xFE, 0xBA, 0xFE, 0xCC,
0xFE, 0xBA, 0xFE, 0xCC, 0xFE, 0xBA, 0xFE, 0xBA, 0xFE, 0xBA, 0xFE, 0xBA, 0xA0, 0x02, 0x33, 0x42,
0x2E, 0x27, 0xFE, 0x93, 0xFE, 0x93, 0xD5, 0x02, 0x01, 0x62, 0x63, 0x64, 0x66, 0x67, 0x68, 0x6A,
0x6B, 0x6C, 0x6D, 0x6E, 0x70, 0x71, 0x72, 0x73, 0x74, 0x76, 0x77, 0x7A, 0x2E, 0x27, 0xFE, 0x8C,
0xFE, 0x8C, 0xFE, 0x8C, 0xFF, 0xF6, 0xFE, 0x8C, 0xFE, 0x9E, 0xFE, 0x9E, 0xFE, 0x8C, 0xFE, 0x8C,
0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C,
0xFE, 0x8C, 0xFE, 0x8C, 0xFE, 0x8C, 0xFF, 0xF9, 0xCF, 0x02, 0x01, 0x62, 0x63, 0x66, 0x6C, 0x6D,
0x6E, 0x70, 0x71, 0x72, 0x73, 0x74, 0x76, 0x77, 0x2E, 0x27, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A,
0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A,
0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xFE, 0x4A, 0xA0, 0x02, 0x62, 0xA1, 0x01, 0xE1, 0x6E, 0xFD,
0x21, 0x72, 0xF8, 0x21, 0x65, 0xFD, 0xA1, 0x01, 0xE1, 0x66, 0xFD, 0x41, 0x74, 0xFE, 0x07, 0x21,
0x69, 0xFC, 0x21, 0x65, 0xFD, 0xD3, 0x02, 0x01, 0x62, 0x63, 0x64, 0x66, 0x67, 0x6B, 0x6C, 0x6D,
0x6E, 0x70, 0x71, 0x72, 0x73, 0x74, 0x76, 0x7A, 0x68, 0x2E, 0x27, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD,
0xFD, 0xFD, 0xFD, 0xFF, 0xE6, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD,
0xFD, 0xFD, 0xFD, 0xFF, 0xF1, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFD, 0xFF, 0xFD, 0xFD, 0xFD, 0xFD,
0xFD, 0xA0, 0x02, 0x82, 0xA1, 0x01, 0xE1, 0x65, 0xFD, 0x21, 0x63, 0xF8, 0xA1, 0x01, 0xE1, 0x69,
0xFD, 0xCB, 0x02, 0x01, 0x64, 0x68, 0x6C, 0x6E, 0x70, 0x72, 0x73, 0x74, 0x7A, 0x2E, 0x27, 0xFD,
0xB1, 0xFD, 0xC3, 0xFD, 0xC3, 0xFF, 0xF3, 0xFD, 0xB1, 0xFD, 0xC3, 0xFF, 0xFB, 0xFD, 0xB1, 0xFD,
0xB1, 0xFD, 0xB1, 0xFD, 0xB1, 0xC3, 0x02, 0x01, 0x71, 0x2E, 0x27, 0xFD, 0x8D, 0xFD, 0x8D, 0xFD,
0x8D, 0xA0, 0x02, 0x53, 0xA1, 0x01, 0xE1, 0x73, 0xFD, 0xD5, 0x02, 0x01, 0x62, 0x63, 0x64, 0x66,
0x68, 0x67, 0x6B, 0x6C, 0x6D, 0x6E, 0x70, 0x71, 0x72, 0x73, 0x74, 0x76, 0x78, 0x77, 0x7A, 0x2E,
0x27, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x8B, 0xFD, 0x79, 0xFD, 0x79, 0xFD,
0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFF, 0xFB, 0xFD,
0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0xFD, 0x79, 0x43, 0x6D, 0x2E, 0x27, 0xFD,
0x37, 0xFD, 0x37, 0xFD, 0x37, 0xA0, 0x02, 0xC2, 0xA1, 0x02, 0x32, 0x6D, 0xFD, 0x41, 0x6E, 0xFE,
0x8F, 0x4B, 0x62, 0x63, 0x64, 0x66, 0x67, 0x6D, 0x6E, 0x70, 0x73, 0x74, 0x76, 0xFD, 0x21, 0xFD,
0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD, 0x21, 0xFD,
0x21, 0xFD, 0x21, 0xA0, 0x02, 0xE1, 0x22, 0x2E, 0x27, 0xFD, 0xFD, 0xC7, 0x02, 0xA2, 0x68, 0x73,
0x70, 0x74, 0x7A, 0x2E, 0x27, 0xFF, 0xC0, 0xFF, 0xCD, 0xFF, 0xD2, 0xFF, 0xD6, 0xFC, 0xF7, 0xFF,
0xF8, 0xFF, 0xFB, 0xC1, 0x00, 0x51, 0x2E, 0xFC, 0xDF, 0x41, 0x68, 0xFF, 0x18, 0xA1, 0x00, 0x51,
0x63, 0xFC, 0xC1, 0x01, 0xE1, 0x73, 0xFE, 0xB6, 0xC2, 0x00, 0x51, 0x6B, 0x73, 0xFC, 0xCA, 0xFC,
0x06, 0xD2, 0x02, 0x01, 0x62, 0x63, 0x64, 0x66, 0x67, 0x68, 0x6C, 0x6D, 0x6E, 0x70, 0x72, 0x73,
0x74, 0x76, 0x77, 0x7A, 0x2E, 0x27, 0xFC, 0xC1, 0xFC, 0xC1, 0xFC, 0xC1, 0xFC, 0xC1, 0xFC, 0xC1,
0xFF, 0xE2, 0xFC, 0xD3, 0xFC, 0xC1, 0xFC, 0xC1, 0xFC, 0xC1, 0xFC, 0xD3, 0xFF, 0xEC, 0xFF, 0xF1,
0xFC, 0xC1, 0xFC, 0xC1, 0xFF, 0xF7, 0xFC, 0xC1, 0xFE, 0x2E, 0xC6, 0x02, 0x01, 0x63, 0x6C, 0x72,
0x76, 0x2E, 0x27, 0xFC, 0x88, 0xFC, 0x9A, 0xFC, 0x9A, 0xFC, 0x88, 0xFC, 0x88, 0xFD, 0xF5, 0x41,
0x72, 0xFB, 0xAF, 0xA0, 0x02, 0xF2, 0xC5, 0x02, 0x01, 0x68, 0x61, 0x79, 0x2E, 0x27, 0xFC, 0x7E,
0xFF, 0xF9, 0xFF, 0xFD, 0xFC, 0x6C, 0xFC, 0x6C, 0xCA, 0x02, 0x01, 0x62, 0x63, 0x66, 0x68, 0x6D,
0x70, 0x74, 0x77, 0x2E, 0x27, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC,
0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0xFC, 0x5A, 0x42, 0x6F, 0x69, 0xFC, 0x48, 0xFC, 0x27,
0xCB, 0x02, 0x01, 0x62, 0x64, 0x6C, 0x6E, 0x70, 0x74, 0x73, 0x76, 0x7A, 0x2E, 0x27, 0xFC, 0x32,
0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32, 0xFC, 0x32,
0xFC, 0x32, 0xFD, 0x9F, 0x5A, 0x2E, 0x27, 0x61, 0x65, 0x6F, 0x62, 0x63, 0x64, 0x66, 0x67, 0x68,
0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x70, 0x71, 0x72, 0x73, 0x74, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xFB,
0xC2, 0xFB, 0xF9, 0xFC, 0x14, 0xFC, 0x23, 0xFC, 0x28, 0xFC, 0x2B, 0xFC, 0x64, 0xFC, 0x97, 0xFC,
0xC4, 0xFC, 0xED, 0xFD, 0x27, 0xFD, 0x4B, 0xFD, 0x54, 0xFD, 0x82, 0xFD, 0xC4, 0xFE, 0x11, 0xFE,
0x5D, 0xFE, 0x81, 0xFE, 0x95, 0xFF, 0x17, 0xFF, 0x4D, 0xFF, 0x86, 0xFF, 0xA2, 0xFF, 0xB4, 0xFF,
0xD5, 0xFF, 0xDC,
};
constexpr SerializedHyphenationPatterns it_patterns = {
it_trie_data,
sizeof(it_trie_data),
};

View File

@ -43,6 +43,7 @@ const std::vector<LanguageConfig> kSupportedLanguages = {
{"german", "test/hyphenation_eval/resources/german_hyphenation_tests.txt", "de"},
{"russian", "test/hyphenation_eval/resources/russian_hyphenation_tests.txt", "ru"},
{"spanish", "test/hyphenation_eval/resources/spanish_hyphenation_tests.txt", "es"},
{"italian", "test/hyphenation_eval/resources/italian_hyphenation_tests.txt", "it"},
};
std::vector<size_t> expectedPositionsFromAnnotatedWord(const std::string& annotated) {

File diff suppressed because it is too large Load Diff