feat: Add swedish hyphenation (#1637)
## Summary * Add swedish hyphenation using scripts/update_hypenation.sh * Add hyphenation test data using the Swedish translation of Andy Weir's Project Hail Mary --- ### AI Usage While CrossPoint doesn't have restrictions on AI tools in contributing, please be transparent about their usage as it helps set the right context for reviewers. Did you use AI tools to help write this code? _**NO**_
This commit is contained in:
@@ -22,10 +22,9 @@ struct Iso639Mapping {
|
||||
const char* iso639_2;
|
||||
const char* iso639_1;
|
||||
};
|
||||
static constexpr Iso639Mapping kIso639Mappings[] = {
|
||||
{"eng", "en"}, {"fra", "fr"}, {"fre", "fr"}, {"deu", "de"}, {"ger", "de"},
|
||||
{"rus", "ru"}, {"spa", "es"}, {"ita", "it"}, {"ukr", "uk"},
|
||||
};
|
||||
static constexpr Iso639Mapping kIso639Mappings[] = {{"eng", "en"}, {"fra", "fr"}, {"fre", "fr"}, {"deu", "de"},
|
||||
{"ger", "de"}, {"rus", "ru"}, {"spa", "es"}, {"ita", "it"},
|
||||
{"ukr", "uk"}, {"swe", "sv"}};
|
||||
|
||||
// Maps a BCP-47 or ISO 639-2 language tag to a language-specific hyphenator.
|
||||
const LanguageHyphenator* hyphenatorForLanguage(const std::string& langTag) {
|
||||
|
||||
@@ -11,6 +11,7 @@
|
||||
#include "generated/hyph-it.trie.h"
|
||||
#include "generated/hyph-pl.trie.h"
|
||||
#include "generated/hyph-ru.trie.h"
|
||||
#include "generated/hyph-sv.trie.h"
|
||||
#include "generated/hyph-uk.trie.h"
|
||||
|
||||
namespace {
|
||||
@@ -22,10 +23,11 @@ LanguageHyphenator germanHyphenator(de_patterns, isLatinLetter, toLowerLatin);
|
||||
LanguageHyphenator russianHyphenator(ru_patterns, isCyrillicLetter, toLowerCyrillic);
|
||||
LanguageHyphenator spanishHyphenator(es_patterns, isLatinLetter, toLowerLatin);
|
||||
LanguageHyphenator italianHyphenator(it_patterns, isLatinLetter, toLowerLatin);
|
||||
LanguageHyphenator swedishHyphenator(sv_patterns, isLatinLetter, toLowerLatin);
|
||||
LanguageHyphenator ukrainianHyphenator(uk_patterns, isCyrillicLetter, toLowerCyrillic);
|
||||
LanguageHyphenator polishHyphenator(pl_patterns, isLatinLetter, toLowerLatin);
|
||||
|
||||
using EntryArray = std::array<LanguageEntry, 8>;
|
||||
using EntryArray = std::array<LanguageEntry, 9>;
|
||||
|
||||
const EntryArray& entries() {
|
||||
static const EntryArray kEntries = {{{"english", "en", &englishHyphenator},
|
||||
@@ -35,6 +37,7 @@ const EntryArray& entries() {
|
||||
{"spanish", "es", &spanishHyphenator},
|
||||
{"italian", "it", &italianHyphenator},
|
||||
{"polish", "pl", &polishHyphenator},
|
||||
{"swedish", "sv", &swedishHyphenator},
|
||||
{"ukrainian", "uk", &ukrainianHyphenator}}};
|
||||
return kEntries;
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -24,3 +24,4 @@ process ru
|
||||
process it
|
||||
process uk
|
||||
process pl
|
||||
process sv
|
||||
|
||||
@@ -45,6 +45,7 @@ const std::vector<LanguageConfig> kSupportedLanguages = {
|
||||
{"spanish", "test/hyphenation_eval/resources/spanish_hyphenation_tests.txt", "es"},
|
||||
{"italian", "test/hyphenation_eval/resources/italian_hyphenation_tests.txt", "it"},
|
||||
{"polish", "test/hyphenation_eval/resources/polish_hyphenation_tests.txt", "pl"},
|
||||
{"swedish", "test/hyphenation_eval/resources/swedish_hyphenation_tests.txt", "sv"},
|
||||
};
|
||||
|
||||
std::vector<size_t> expectedPositionsFromAnnotatedWord(const std::string& annotated) {
|
||||
@@ -388,4 +389,4 @@ int main(int argc, char* argv[]) {
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user