1 files changed, 70 insertions, 0 deletions
diff --git a/coding/transliteration.cpp b/coding/transliteration.cpp
new file mode 100644
index 0000000000..e30a03820a
--- /dev/null
+++ b/coding/transliteration.cpp
@@ -0,0 +1,70 @@
+#include "coding/transliteration.hpp"
+#include "coding/multilang_utf8_string.hpp"
+
+#include "base/logging.hpp"
+
+#include "3party/icu/common/unicode/uclean.h"
+#include "3party/icu/common/unicode/unistr.h"
+#include "3party/icu/common/unicode/utypes.h"
+#include "3party/icu/i18n/unicode/translit.h"
+#include "3party/icu/i18n/unicode/utrans.h"
+
+Transliteration::~Transliteration()
+{
+  // The use of u_cleanup() just before an application terminates is optional,
+  // but it should be called only once for performance reasons.
+  // The primary benefit is to eliminate reports of memory or resource leaks originating
+  // in ICU code from the results generated by heap analysis tools.
+  // http://www.icu-project.org/apiref/icu4c/uclean_8h.html#a93f27d0ddc7c196a1da864763f2d8920
+  m_transliterators.clear();
+  u_cleanup();
+}
+
+Transliteration & Transliteration::Instance()
+{
+  static Transliteration instance;
+  return instance;
+}
+
+void Transliteration::Init(std::string const & icuDataDir)
+{
+  u_setDataDirectory(icuDataDir.c_str());
+
+  for (auto const & lang : StringUtf8Multilang::GetSupportedLanguages())
+  {
+    if (strlen(lang.m_transliteratorId) == 0 || m_transliterators.count(lang.m_transliteratorId) != 0)
+      continue;
+
+    UErrorCode status = U_ZERO_ERROR;
+    std::unique_ptr<Transliterator> transliterator(
+          Transliterator::createInstance(lang.m_transliteratorId, UTRANS_FORWARD, status));
+
+    if (transliterator != nullptr)
+       m_transliterators.emplace(lang.m_transliteratorId, std::move(transliterator));
+    else
+      LOG(LWARNING, ("Cannot create transliterator \"", lang.m_transliteratorId, "\", icu error =", status));
+  }
+}
+
+bool Transliteration::Transliterate(std::string const & str, int8_t langCode, std::string & out) const
+{
+  if (str.empty())
+    return false;
+
+  auto const transliteratorId = StringUtf8Multilang::GetTransliteratorIdByCode(langCode);
+  auto const & it = m_transliterators.find(transliteratorId);
+  if (it == m_transliterators.end())
+  {
+    LOG(LWARNING, ("Transliteration failed, unknown transliterator \"", transliteratorId, "\""));
+    return false;
+  }
+
+  UnicodeString ustr(str.c_str());
+  it->second->transliterate(ustr);
+
+  if (ustr.isEmpty())
+    return false;
+
+  ustr.toUTF8String(out);
+  return true;
+}