[llvm] Create a CharSetConverter class with both iconv and icu support (PR #74516)

Abhina Sree via llvm-commits llvm-commits at lists.llvm.org
Tue Dec 5 12:13:52 PST 2023


https://github.com/abhina-sree created https://github.com/llvm/llvm-project/pull/74516

This patch adds a wrapper class called CharSetConverter for ConverterEBCDIC. This class is then extended to support the ICU library or iconv library. The ICU library currently takes priority over the iconv library. 

>From 509d698ec793f9dc9e096044404ac4c0f280ec3f Mon Sep 17 00:00:00 2001
From: Abhina Sreeskantharajan <Abhina.Sreeskantharajan at ibm.com>
Date: Tue, 5 Dec 2023 15:08:43 -0500
Subject: [PATCH] Create a CharSetConverter class with both iconv and icu
 support.

---
 llvm/cmake/config-ix.cmake              |  16 +
 llvm/include/llvm/Config/config.h.cmake |   6 +
 llvm/include/llvm/Support/CharSet.h     | 160 ++++++++++
 llvm/lib/Support/CMakeLists.txt         |  17 ++
 llvm/lib/Support/CharSet.cpp            | 370 ++++++++++++++++++++++++
 llvm/unittests/Support/CMakeLists.txt   |   1 +
 llvm/unittests/Support/CharSetTest.cpp  | 279 ++++++++++++++++++
 7 files changed, 849 insertions(+)
 create mode 100644 llvm/include/llvm/Support/CharSet.h
 create mode 100644 llvm/lib/Support/CharSet.cpp
 create mode 100644 llvm/unittests/Support/CharSetTest.cpp

diff --git a/llvm/cmake/config-ix.cmake b/llvm/cmake/config-ix.cmake
index 7bb3e98333eff..b2505968e430d 100644
--- a/llvm/cmake/config-ix.cmake
+++ b/llvm/cmake/config-ix.cmake
@@ -257,6 +257,22 @@ else()
   set(LLVM_ENABLE_TERMINFO 0)
 endif()
 
+#Check for icu.
+find_package(ICU COMPONENTS uc i18n)
+if(ICU_FOUND)
+  set(HAVE_ICU 1)
+else()
+  set(HAVE_ICU 0)
+endif()
+
+# Check for iconv.
+find_package(Iconv)
+if(Iconv_FOUND)
+  set(HAVE_ICONV 1)
+else()
+  set(HAVE_ICONV 0)
+endif()
+
 # function checks
 check_symbol_exists(arc4random "stdlib.h" HAVE_DECL_ARC4RANDOM)
 find_package(Backtrace)
diff --git a/llvm/include/llvm/Config/config.h.cmake b/llvm/include/llvm/Config/config.h.cmake
index fc1f9bf342f8d..74003e1b22494 100644
--- a/llvm/include/llvm/Config/config.h.cmake
+++ b/llvm/include/llvm/Config/config.h.cmake
@@ -281,6 +281,12 @@
 /* Have host's ___chkstk_ms */
 #cmakedefine HAVE____CHKSTK_MS ${HAVE____CHKSTK_MS}
 
+/* Define if icu library is available */
+#cmakedefine HAVE_ICU ${HAVE_ICU}
+
+/* Define if iconv library is available */
+#cmakedefine HAVE_ICONV ${HAVE_ICONV}
+
 /* Linker version detected at compile time. */
 #cmakedefine HOST_LINK_VERSION "${HOST_LINK_VERSION}"
 
diff --git a/llvm/include/llvm/Support/CharSet.h b/llvm/include/llvm/Support/CharSet.h
new file mode 100644
index 0000000000000..856b3be65ff7e
--- /dev/null
+++ b/llvm/include/llvm/Support/CharSet.h
@@ -0,0 +1,160 @@
+//===-- CharSet.h - Utility class to convert between char sets ----*- C++ -*-=//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file provides a utility class to convert between different character
+/// set encodings.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_CHARSET_H
+#define LLVM_SUPPORT_CHARSET_H
+
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Config/config.h"
+#include "llvm/Support/ErrorOr.h"
+
+#include <functional>
+#include <string>
+#include <system_error>
+
+namespace llvm {
+
+template <typename T> class SmallVectorImpl;
+
+namespace details {
+class CharSetConverterImplBase {
+public:
+  virtual ~CharSetConverterImplBase() = default;
+
+  /// Converts a string.
+  /// \param[in] Source source string
+  /// \param[in,out] Result container for converted string
+  /// \param[in] ShouldAutoFlush Append shift-back sequence after conversion
+  /// for multi-byte encodings iff true.
+  /// \return error code in case something went wrong
+  ///
+  /// The following error codes can occur, among others:
+  ///   - std::errc::argument_list_too_long: The result requires more than
+  ///     std::numeric_limits<size_t>::max() bytes.
+  ///   - std::errc::illegal_byte_sequence: The input contains an invalid
+  ///     multibyte sequence.
+  ///   - std::errc::invalid_argument: The input contains an incomplete
+  ///     multibyte sequence.
+  ///
+  /// In case of an error, the result string contains the successfully converted
+  /// part of the input string.
+  ///
+
+  virtual std::error_code convert(StringRef Source,
+                                  SmallVectorImpl<char> &Result,
+                                  bool ShouldAutoFlush) const = 0;
+
+  /// Restore the conversion to the original state.
+  /// \return error code in case something went wrong
+  ///
+  /// If the original character set or the destination character set
+  /// are multi-byte character sets, set the shift state to the initial
+  /// state. Otherwise this is a no-op.
+  virtual std::error_code flush() const = 0;
+
+  virtual std::error_code flush(SmallVectorImpl<char> &Result) const = 0;
+};
+} // namespace details
+
+// Names inspired by https://wg21.link/p1885.
+namespace text_encoding {
+enum class id {
+  /// UTF-8 character set encoding.
+  UTF8,
+
+  /// IBM EBCDIC 1047 character set encoding.
+  IBM1047
+};
+} // end namespace text_encoding
+
+/// Utility class to convert between different character set encodings.
+/// The class always supports converting between EBCDIC 1047 and Latin-1/UTF-8.
+class CharSetConverter {
+  // details::CharSetConverterImplBase *Converter;
+  std::unique_ptr<details::CharSetConverterImplBase> Converter;
+
+  CharSetConverter(std::unique_ptr<details::CharSetConverterImplBase> Converter)
+      : Converter(std::move(Converter)) {}
+
+public:
+  /// Creates a CharSetConverter instance.
+  /// \param[in] CSFrom name of the source character encoding
+  /// \param[in] CSTo name of the target character encoding
+  /// \return a CharSetConverter instance
+  static CharSetConverter create(text_encoding::id CSFrom,
+                                 text_encoding::id CSTo);
+
+  /// Creates a CharSetConverter instance.
+  /// Returns std::errc::invalid_argument in case the requested conversion is
+  /// not supported.
+  /// \param[in] CPFrom name of the source character encoding
+  /// \param[in] CPTo name of the target character encoding
+  /// \return a CharSetConverter instance or an error code
+  static ErrorOr<CharSetConverter> create(StringRef CPFrom, StringRef CPTo);
+
+  CharSetConverter(const CharSetConverter &) = delete;
+  CharSetConverter &operator=(const CharSetConverter &) = delete;
+
+  CharSetConverter(CharSetConverter &&Other) {
+    Converter = std::move(Other.Converter);
+  }
+
+  CharSetConverter &operator=(CharSetConverter &&Other) {
+    if (this != &Other)
+      Converter = std::move(Other.Converter);
+    return *this;
+  }
+
+  ~CharSetConverter() = default;
+
+  /// Converts a string.
+  /// \param[in] Source source string
+  /// \param[in,out] Result container for converted string
+  /// \param[in] ShouldAutoFlush Append shift-back sequence after conversion
+  /// for multi-byte encodings.
+  /// \return error code in case something went wrong
+  std::error_code convert(StringRef Source, SmallVectorImpl<char> &Result,
+                          bool ShouldAutoFlush = true) const {
+    return Converter->convert(Source, Result, ShouldAutoFlush);
+  }
+
+  char convert(char SingleChar) const {
+    SmallString<1> Result;
+    Converter->convert(StringRef(&SingleChar, 1), Result, false);
+    return Result[0];
+  }
+
+  /// Converts a string.
+  /// \param[in] Source source string
+  /// \param[in,out] Result container for converted string
+  /// \param[in] ShouldAutoFlush Append shift-back sequence after conversion
+  /// for multi-byte encodings iff true.
+  /// \return error code in case something went wrong
+  std::error_code convert(const std::string &Source,
+                          SmallVectorImpl<char> &Result,
+                          bool ShouldAutoFlush = true) const {
+    return convert(StringRef(Source), Result, ShouldAutoFlush);
+  }
+
+  std::error_code flush() const { return Converter->flush(); }
+
+  std::error_code flush(SmallVectorImpl<char> &Result) const {
+    return Converter->flush(Result);
+  }
+};
+
+} // namespace llvm
+
+#endif
diff --git a/llvm/lib/Support/CMakeLists.txt b/llvm/lib/Support/CMakeLists.txt
index b96d62c7a6224..b366b915df719 100644
--- a/llvm/lib/Support/CMakeLists.txt
+++ b/llvm/lib/Support/CMakeLists.txt
@@ -153,6 +153,7 @@ add_llvm_component_library(LLVMSupport
   CachePruning.cpp
   Caching.cpp
   circular_raw_ostream.cpp
+  CharSet.cpp
   Chrono.cpp
   COM.cpp
   CodeGenCoverage.cpp
@@ -291,6 +292,22 @@ add_llvm_component_library(LLVMSupport
   Demangle
   )
 
+# Link icu library if it is an external library.
+if(ICU_FOUND)
+  target_link_libraries(LLVMSupport
+  PRIVATE
+  ${ICU_LIBRARIES}
+  )
+else()
+  # Link iconv library if it is an external library.
+  if(Iconv_FOUND AND NOT Iconv_IS_BUILT_IN)
+    target_link_libraries(LLVMSupport
+    PRIVATE
+    ${Iconv_LIBRARIES}
+    )
+  endif()
+endif()
+
 set(llvm_system_libs ${system_libs})
 
 # This block is only needed for llvm-config. When we deprecate llvm-config and
diff --git a/llvm/lib/Support/CharSet.cpp b/llvm/lib/Support/CharSet.cpp
new file mode 100644
index 0000000000000..dbc2cb7c1839d
--- /dev/null
+++ b/llvm/lib/Support/CharSet.cpp
@@ -0,0 +1,370 @@
+//===-- CharSet.cpp - Utility class to convert between char sets --*- C++ -*-=//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file provides utility classes to convert between different character
+/// set encoding.
+///
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/CharSet.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringExtras.h"
+#include "llvm/Support/ConvertEBCDIC.h"
+#include "llvm/Support/raw_ostream.h"
+#include <algorithm>
+#include <limits>
+#include <system_error>
+
+#ifdef HAVE_ICU
+#include <unicode/ucnv.h>
+#elif defined(HAVE_ICONV)
+#include <iconv.h>
+#endif
+
+using namespace llvm;
+
+// Normalize the charset name with the charset alias matching algorithm proposed
+// in https://www.unicode.org/reports/tr22/tr22-8.html#Charset_Alias_Matching.
+void normalizeCharSetName(StringRef CSName, SmallVectorImpl<char> &Normalized) {
+  bool PrevDigit = false;
+  for (auto Ch : CSName) {
+    if (isAlnum(Ch)) {
+      Ch = toLower(Ch);
+      if (Ch != '0' || PrevDigit) {
+        PrevDigit = isDigit(Ch);
+        Normalized.push_back(Ch);
+      }
+    }
+  }
+}
+
+// Maps the charset name to enum constant if possible.
+std::optional<text_encoding::id> getKnownCharSet(StringRef CSName) {
+  SmallString<16> Normalized;
+  normalizeCharSetName(CSName, Normalized);
+#define CSNAME(CS, STR)                                                        \
+  if (Normalized.equals(STR))                                                  \
+  return CS
+  CSNAME(text_encoding::id::UTF8, "utf8");
+  CSNAME(text_encoding::id::IBM1047, "ibm1047");
+#undef CSNAME
+  return std::nullopt;
+}
+
+namespace {
+enum ConversionType {
+  UTFToIBM1047,
+  IBM1047ToUTF,
+};
+
+// Support conversion between EBCDIC 1047 and UTF8. This class uses
+// built-in translation tables that allow for translation between the
+// aforementioned character sets. The use of tables for conversion is only
+// possible because EBCDIC 1047 is a single-byte, stateless encoding; other
+// character sets are not supported.
+class CharSetConverterTable : public details::CharSetConverterImplBase {
+  ConversionType ConvType;
+
+public:
+  CharSetConverterTable(ConversionType ConvType) : ConvType(ConvType) {}
+
+  std::error_code convert(StringRef Source, SmallVectorImpl<char> &Result,
+                          bool ShouldAutoFlush) const override;
+  std::error_code flush() const override;
+  std::error_code flush(SmallVectorImpl<char> &Result) const override;
+};
+
+std::error_code CharSetConverterTable::convert(StringRef Source,
+                                               SmallVectorImpl<char> &Result,
+                                               bool ShouldAutoFlush) const {
+  if (ConvType == IBM1047ToUTF) {
+    ConverterEBCDIC::convertToUTF8(Source, Result);
+    return std::error_code();
+  } else if (ConvType == UTFToIBM1047) {
+    return ConverterEBCDIC::convertToEBCDIC(Source, Result);
+  }
+  llvm_unreachable("Invalid ConvType!");
+  return std::error_code();
+}
+
+std::error_code CharSetConverterTable::flush() const {
+  return std::error_code();
+}
+
+std::error_code
+CharSetConverterTable::flush(SmallVectorImpl<char> &Result) const {
+  return std::error_code();
+}
+
+#ifdef HAVE_ICU
+class CharSetConverterICU : public details::CharSetConverterImplBase {
+  UConverter *FromConvDesc;
+  UConverter *ToConvDesc;
+
+public:
+  CharSetConverterICU(UConverter *Converter) {
+    UErrorCode EC = U_ZERO_ERROR;
+    FromConvDesc = nullptr;
+    ToConvDesc = ucnv_safeClone(Converter, nullptr, nullptr, &EC);
+    if (U_FAILURE(EC)) {
+      ToConvDesc = nullptr;
+    }
+  };
+
+  CharSetConverterICU(UConverter *FromConverter, UConverter *ToConverter) {
+    UErrorCode EC = U_ZERO_ERROR;
+    FromConvDesc = ucnv_safeClone(FromConverter, nullptr, nullptr, &EC);
+    if (U_FAILURE(EC))
+      FromConvDesc = nullptr;
+    ToConvDesc = ucnv_safeClone(ToConverter, nullptr, nullptr, &EC);
+    if (U_FAILURE(EC))
+      ToConvDesc = nullptr;
+  }
+
+  std::error_code convert(StringRef Source, SmallVectorImpl<char> &Result,
+                          bool ShouldAutoFlush) const override;
+  std::error_code flush() const override;
+  std::error_code flush(SmallVectorImpl<char> &Result) const override;
+};
+
+std::error_code CharSetConverterICU::convert(StringRef Source,
+                                             SmallVectorImpl<char> &Result,
+                                             bool ShouldAutoFlush) const {
+  // Setup the output. We directly write into the SmallVector.
+  size_t OutputLength, Capacity = Result.capacity();
+  char *Output, *Out;
+
+  UErrorCode EC = U_ZERO_ERROR;
+
+  auto HandleError = [&Capacity, &Output, &OutputLength,
+                      &Result](UErrorCode UEC) {
+    if (UEC == U_BUFFER_OVERFLOW_ERROR &&
+        Capacity < std::numeric_limits<size_t>::max()) {
+      // No space left in output buffer. Double the size of the underlying
+      // memory in the SmallVectorImpl, adjust pointer and length and continue
+      // the conversion.
+      Capacity = (Capacity < std::numeric_limits<size_t>::max() / 2)
+                     ? 2 * Capacity
+                     : std::numeric_limits<size_t>::max();
+      Result.resize_for_overwrite(Capacity);
+      Output = static_cast<char *>(Result.data());
+      OutputLength = Capacity;
+      return std::error_code();
+    } else {
+      // Some other error occured.
+      return std::error_code(errno, std::generic_category());
+    }
+  };
+
+  do {
+    EC = U_ZERO_ERROR;
+    size_t InputLength = Source.size();
+    const char *Input =
+        InputLength ? const_cast<char *>(Source.data()) : nullptr;
+    const char *In = Input;
+    Output = InputLength ? static_cast<char *>(Result.data()) : nullptr;
+    OutputLength = Capacity;
+    Out = Output;
+    Result.resize_for_overwrite(Capacity);
+    ucnv_convertEx(ToConvDesc, FromConvDesc, &Output, Out + OutputLength,
+                   &Input, In + InputLength, /*pivotStart=*/NULL,
+                   /*pivotSource=*/NULL, /*pivotTarget=*/NULL,
+                   /*pivotLimit=*/NULL, /*reset=*/true, /*flush=*/true, &EC);
+    if (U_FAILURE(EC)) {
+      if (auto error = HandleError(EC))
+        return error;
+    } else if (U_SUCCESS(EC))
+      break;
+  } while (U_FAILURE(EC));
+
+  Result.resize(Output - Out);
+  return std::error_code();
+}
+
+std::error_code CharSetConverterICU::flush() const { return std::error_code(); }
+
+std::error_code
+CharSetConverterICU::flush(SmallVectorImpl<char> &Result) const {
+  return std::error_code();
+}
+
+#elif defined(HAVE_ICONV)
+class CharSetConverterIconv : public details::CharSetConverterImplBase {
+  iconv_t ConvDesc;
+
+public:
+  CharSetConverterIconv(iconv_t ConvDesc) : ConvDesc(ConvDesc) {}
+
+  std::error_code convert(StringRef Source, SmallVectorImpl<char> &Result,
+                          bool ShouldAutoFlush) const override;
+  std::error_code flush() const override;
+  std::error_code flush(SmallVectorImpl<char> &Result) const override;
+};
+
+std::error_code CharSetConverterIconv::convert(StringRef Source,
+                                               SmallVectorImpl<char> &Result,
+                                               bool ShouldAutoFlush) const {
+  // Setup the input. Use nullptr to reset iconv state if input length is zero.
+  size_t InputLength = Source.size();
+  char *Input = InputLength ? const_cast<char *>(Source.data()) : nullptr;
+  // Setup the output. We directly write into the SmallVector.
+  size_t Capacity = Result.capacity();
+  Result.resize_for_overwrite(Capacity);
+  char *Output = InputLength ? static_cast<char *>(Result.data()) : nullptr;
+  size_t OutputLength = Capacity;
+
+  size_t Ret;
+
+  // Handle errors returned from iconv().
+  auto HandleError = [&Capacity, &Output, &OutputLength, &Result](size_t Ret) {
+    if (Ret == static_cast<size_t>(-1)) {
+      // An error occured. Check if we can gracefully handle it.
+      if (errno == E2BIG && Capacity < std::numeric_limits<size_t>::max()) {
+        // No space left in output buffer. Double the size of the underlying
+        // memory in the SmallVectorImpl, adjust pointer and length and continue
+        // the conversion.
+        const size_t Used = Capacity - OutputLength;
+        Capacity = (Capacity < std::numeric_limits<size_t>::max() / 2)
+                       ? 2 * Capacity
+                       : std::numeric_limits<size_t>::max();
+        Result.resize_for_overwrite(Capacity);
+        Output = static_cast<char *>(Result.data()) + Used;
+        OutputLength = Capacity - Used;
+        return std::error_code();
+      } else {
+        // Some other error occured.
+        return std::error_code(errno, std::generic_category());
+      }
+    } else {
+      // A positive return value indicates that some characters were converted
+      // in a nonreversible way, that is, replaced with a SUB symbol. Returning
+      // an error in this case makes sure that both conversion routines behave
+      // in the same way.
+      return std::make_error_code(std::errc::illegal_byte_sequence);
+    }
+  };
+
+  // Convert the string.
+  while ((Ret = iconv(ConvDesc, &Input, &InputLength, &Output, &OutputLength)))
+    if (auto EC = HandleError(Ret))
+      return EC;
+  if (ShouldAutoFlush) {
+    while ((Ret = iconv(ConvDesc, nullptr, nullptr, &Output, &OutputLength)))
+      if (auto EC = HandleError(Ret))
+        return EC;
+  }
+
+  // Re-adjust size to actual size.
+  Result.resize(Capacity - OutputLength);
+  return std::error_code();
+}
+
+std::error_code CharSetConverterIconv::flush() const {
+  size_t Ret = iconv(ConvDesc, nullptr, nullptr, nullptr, nullptr);
+  if (Ret == static_cast<size_t>(-1)) {
+    return std::error_code(errno, std::generic_category());
+  }
+  return std::error_code();
+}
+
+std::error_code
+CharSetConverterIconv::flush(SmallVectorImpl<char> &Result) const {
+  char *Output = Result.data();
+  size_t OutputLength = Result.capacity();
+  size_t Capacity = Result.capacity();
+  Result.resize_for_overwrite(Capacity);
+
+  // Handle errors returned from iconv().
+  auto HandleError = [&Capacity, &Output, &OutputLength, &Result](size_t Ret) {
+    if (Ret == static_cast<size_t>(-1)) {
+      // An error occured. Check if we can gracefully handle it.
+      if (errno == E2BIG && Capacity < std::numeric_limits<size_t>::max()) {
+        // No space left in output buffer. Increase the size of the underlying
+        // memory in the SmallVectorImpl by 2 bytes, adjust pointer and length
+        // and continue the conversion.
+        const size_t Used = Capacity - OutputLength;
+        Capacity = (Capacity < std::numeric_limits<size_t>::max() - 2)
+                       ? 2 + Capacity
+                       : std::numeric_limits<size_t>::max();
+        Result.resize_for_overwrite(Capacity);
+        Output = static_cast<char *>(Result.data()) + Used;
+        OutputLength = Capacity - Used;
+        return std::error_code();
+      } else {
+        // Some other error occured.
+        return std::error_code(errno, std::generic_category());
+      }
+    } else {
+      // A positive return value indicates that some characters were converted
+      // in a nonreversible way, that is, replaced with a SUB symbol. Returning
+      // an error in this case makes sure that both conversion routines behave
+      // in the same way.
+      return std::make_error_code(std::errc::illegal_byte_sequence);
+    }
+  };
+
+  size_t Ret;
+  while ((Ret = iconv(ConvDesc, nullptr, nullptr, &Output, &OutputLength)))
+    if (auto EC = HandleError(Ret))
+      return EC;
+
+  // Re-adjust size to actual size.
+  Result.resize(Capacity - OutputLength);
+  return std::error_code();
+}
+
+#endif // HAVE_ICONV
+} // namespace
+
+CharSetConverter CharSetConverter::create(text_encoding::id CPFrom,
+                                          text_encoding::id CPTo) {
+
+  assert(CPFrom != CPTo && "Text encodings should be distinct");
+
+  ConversionType Conversion;
+  if (CPFrom == text_encoding::id::UTF8 && CPTo == text_encoding::id::IBM1047)
+    Conversion = UTFToIBM1047;
+  else
+    Conversion = IBM1047ToUTF;
+  std::unique_ptr<details::CharSetConverterImplBase> Converter =
+      std::make_unique<CharSetConverterTable>(Conversion);
+
+  return CharSetConverter(std::move(Converter));
+}
+
+ErrorOr<CharSetConverter> CharSetConverter::create(StringRef CSFrom,
+                                                   StringRef CSTo) {
+  std::optional<text_encoding::id> From = getKnownCharSet(CSFrom);
+  std::optional<text_encoding::id> To = getKnownCharSet(CSTo);
+  if (From && To)
+    return create(*From, *To);
+#ifdef HAVE_ICU
+  UErrorCode EC = U_ZERO_ERROR;
+  UConverter *FromConvDesc = ucnv_open(CSFrom.str().c_str(), &EC);
+  if (U_FAILURE(EC)) {
+    return std::error_code(errno, std::generic_category());
+  }
+  UConverter *ToConvDesc = ucnv_open(CSTo.str().c_str(), &EC);
+  if (U_FAILURE(EC)) {
+    return std::error_code(errno, std::generic_category());
+  }
+  std::unique_ptr<details::CharSetConverterImplBase> Converter =
+      std::make_unique<CharSetConverterICU>(FromConvDesc, ToConvDesc);
+  return CharSetConverter(std::move(Converter));
+#elif defined(HAVE_ICONV)
+  iconv_t ConvDesc = iconv_open(CSTo.str().c_str(), CSFrom.str().c_str());
+  if (ConvDesc == (iconv_t)-1)
+    return std::error_code(errno, std::generic_category());
+  std::unique_ptr<details::CharSetConverterImplBase> Converter =
+      std::make_unique<CharSetConverterIconv>(ConvDesc);
+  return CharSetConverter(std::move(Converter));
+#endif
+  return std::make_error_code(std::errc::invalid_argument);
+}
diff --git a/llvm/unittests/Support/CMakeLists.txt b/llvm/unittests/Support/CMakeLists.txt
index e1bf793536b68..3746434b384d8 100644
--- a/llvm/unittests/Support/CMakeLists.txt
+++ b/llvm/unittests/Support/CMakeLists.txt
@@ -17,6 +17,7 @@ add_llvm_unittest(SupportTests
   BalancedPartitioningTest.cpp
   BranchProbabilityTest.cpp
   CachePruningTest.cpp
+  CharSetTest.cpp
   CrashRecoveryTest.cpp
   Casting.cpp
   CheckedArithmeticTest.cpp
diff --git a/llvm/unittests/Support/CharSetTest.cpp b/llvm/unittests/Support/CharSetTest.cpp
new file mode 100644
index 0000000000000..572c4bfc7fe7e
--- /dev/null
+++ b/llvm/unittests/Support/CharSetTest.cpp
@@ -0,0 +1,279 @@
+//===- unittests/Support/CharSetTest.cpp - Charset conversion tests -------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ADT/SmallString.h"
+#include "llvm/Support/CharSet.h"
+#include "gtest/gtest.h"
+using namespace llvm;
+
+namespace {
+
+// String "Hello World!"
+static const char HelloA[] =
+    "\x48\x65\x6C\x6C\x6F\x20\x57\x6F\x72\x6C\x64\x21\x0a";
+static const char HelloE[] =
+    "\xC8\x85\x93\x93\x96\x40\xE6\x96\x99\x93\x84\x5A\x15";
+
+// String "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+static const char ABCStrA[] =
+    "\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4A\x4B\x4C\x4D\x4E\x4F\x50\x51\x52"
+    "\x53\x54\x55\x56\x57\x58\x59\x5A\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6A"
+    "\x6B\x6C\x6D\x6E\x6F\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7A";
+static const char ABCStrE[] =
+    "\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9"
+    "\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\x81\x82\x83\x84\x85\x86\x87\x88\x89\x91"
+    "\x92\x93\x94\x95\x96\x97\x98\x99\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9";
+
+// String "¡¢£AÄÅÆEÈÉÊaàáâãäeèéêë"
+static const char AccentUTF[] =
+    "\xc2\xa1\xc2\xa2\xc2\xa3\x41\xc3\x84\xc3\x85\xc3\x86\x45\xc3\x88\xc3\x89"
+    "\xc3\x8a\x61\xc3\xa0\xc3\xa1\xc3\xa2\xc3\xa3\xc3\xa4\x65\xc3\xa8\xc3\xa9"
+    "\xc3\xaa\xc3\xab";
+static const char AccentE[] = "\xaa\x4a\xb1\xc1\x63\x67\x9e\xc5\x74\x71\x72"
+                              "\x81\x44\x45\x42\x46\x43\x85\x54\x51\x52\x53";
+
+// String with Cyrillic character ya.
+static const char CyrillicUTF[] = "\xd0\xaf";
+
+// String "Earth地球".
+// ISO-2022-JP: Sequence ESC $ B (\x1B\x24\x42) switches to JIS X 0208-1983, and
+// sequence ESC ( B (\x1B\x28\x42) switches back to ASCII.
+// IBM-939: Byte 0x0E shifts from single byte to double byte, and 0x0F shifts
+// back.
+static const char EarthUTF[] = "\x45\x61\x72\x74\x68\xe5\x9c\xb0\xe7\x90\x83";
+// Identical to above, except the final character (球) has its last byte taken
+// away from it.
+static const char EarthISO2022[] =
+    "\x45\x61\x72\x74\x68\x1B\x24\x42\x43\x4F\x35\x65\x1B\x28\x42";
+static const char EarthIBM939[] =
+    "\xc5\x81\x99\xa3\x88\x0e\x45\xc2\x48\xdb\x0f";
+
+TEST(CharSet, FromUTF8) {
+  // Hello string.
+  StringRef Src(HelloA);
+  SmallString<64> Dst;
+
+  CharSetConverter Conv = CharSetConverter::create(text_encoding::id::UTF8,
+                                                   text_encoding::id::IBM1047);
+  std::error_code EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(HelloE, static_cast<std::string>(Dst).c_str());
+  Dst.clear();
+
+  // ABC string.
+  Src = ABCStrA;
+  EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(ABCStrE, static_cast<std::string>(Dst).c_str());
+  Dst.clear();
+
+  // Accent string.
+  Src = AccentUTF;
+  EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(AccentE, static_cast<std::string>(Dst).c_str());
+  Dst.clear();
+
+  // Cyrillic string. Results in error because not representable in 1047.
+  Src = CyrillicUTF;
+  EC = Conv.convert(Src, Dst, true);
+  EXPECT_EQ(EC, std::errc::illegal_byte_sequence);
+}
+
+TEST(CharSet, ToUTF8) {
+  // Hello string.
+  StringRef Src(HelloE);
+  SmallString<64> Dst;
+
+  CharSetConverter Conv = CharSetConverter::create(text_encoding::id::IBM1047,
+                                                   text_encoding::id::UTF8);
+  std::error_code EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(HelloA, static_cast<std::string>(Dst).c_str());
+  Dst.clear();
+
+  // ABC string.
+  Src = ABCStrE;
+  EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(ABCStrA, static_cast<std::string>(Dst).c_str());
+  Dst.clear();
+
+  // Accent string.
+  Src = AccentE;
+  EC = Conv.convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(AccentUTF, static_cast<std::string>(Dst).c_str());
+}
+
+TEST(CharSet, RoundTrip) {
+  ErrorOr<CharSetConverter> ConvToUTF16 =
+      CharSetConverter::create("IBM-1047", "UTF-16");
+  // Stop test if conversion is not supported (no underlying iconv support).
+  if (!ConvToUTF16) {
+    ASSERT_EQ(ConvToUTF16.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+  ErrorOr<CharSetConverter> ConvToUTF32 =
+      CharSetConverter::create("UTF-16", "UTF-32");
+  // Stop test if conversion is not supported (no underlying iconv support).
+  if (!ConvToUTF32) {
+    ASSERT_EQ(ConvToUTF32.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+  ErrorOr<CharSetConverter> ConvToEBCDIC =
+      CharSetConverter::create("UTF-32", "IBM-1047");
+  // Stop test if conversion is not supported (no underlying iconv support).
+  if (!ConvToEBCDIC) {
+    ASSERT_EQ(ConvToEBCDIC.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  // Setup source string.
+  char SrcStr[256];
+  for (size_t I = 0; I < 256; ++I)
+    SrcStr[I] = (I + 1) % 256;
+
+  SmallString<99> Dst1Str, Dst2Str, Dst3Str;
+
+  std::error_code EC = ConvToUTF16->convert(StringRef(SrcStr), Dst1Str, true);
+  EXPECT_TRUE(!EC);
+  EC = ConvToUTF32->convert(Dst1Str, Dst2Str, true);
+  EXPECT_TRUE(!EC);
+  EC = ConvToEBCDIC->convert(Dst2Str, Dst3Str, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(SrcStr, static_cast<std::string>(Dst3Str).c_str());
+}
+
+TEST(CharSet, ShiftState2022) {
+  // Earth string.
+  StringRef Src(EarthUTF);
+  SmallString<64> Dst;
+
+  ErrorOr<CharSetConverter> ConvTo2022 =
+      CharSetConverter::create("UTF-8", "ISO-2022-JP");
+  // Stop test if conversion is not supported (no underlying iconv support).
+  if (!ConvTo2022) {
+    ASSERT_EQ(ConvTo2022.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  // Check that the string is properly converted.
+  std::error_code EC = ConvTo2022->convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(EarthISO2022, static_cast<std::string>(Dst).c_str());
+}
+
+TEST(CharSet, ShiftStateIBM939) {
+  // Earth string.
+  StringRef Src(EarthUTF);
+  SmallString<64> Dst;
+
+  ErrorOr<CharSetConverter> ConvToIBM939 =
+      CharSetConverter::create("UTF-8", "IBM-939");
+  // Stop test if conversion is not supported (no underlying iconv support).
+  if (!ConvToIBM939) {
+    ASSERT_EQ(ConvToIBM939.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  // Check that the string is properly converted.
+  std::error_code EC = ConvToIBM939->convert(Src, Dst, true);
+  EXPECT_TRUE(!EC);
+  EXPECT_STREQ(EarthIBM939, static_cast<std::string>(Dst).c_str());
+}
+
+#if not defined(HAVE_ICU) && defined(HAVE_ICONV)
+
+// Identical to EarthUTF, except the final character (球) has its last byte
+// taken away from it.
+static const char EarthUTFBroken[] = "\x45\x61\x72\x74\x68\xe5\x9c\xb0\xe7\x90";
+static const char EarthISO2022ShiftBack[] =
+    "\x45\x61\x72\x74\x68\x1B\x24\x42\x43\x4F\x35\x65";
+static const char ShiftBackOnly[] = "\x1B\x28\x42";
+
+// String "地球".
+static const char EarthKanjiOnlyUTF[] = "\xe5\x9c\xb0\xe7\x90\x83";
+static const char EarthKanjiOnlyISO2022[] =
+    "\x1B\x24\x42\x43\x4F\x35\x65\x1b\x28\x42";
+static const char EarthKanjiOnlyIBM939[] = "\x0e\x45\xc2\x48\xdb\x0f";
+
+TEST(CharSet, ShiftState2022Flush) {
+  StringRef Src0(EarthUTFBroken);
+  StringRef Src1(EarthKanjiOnlyUTF);
+  SmallString<64> Dst0;
+  SmallString<64> Dst1;
+  ErrorOr<CharSetConverter> ConvTo2022Flush =
+      CharSetConverter::create("UTF-8", "ISO-2022-JP");
+  if (!ConvTo2022Flush) {
+    ASSERT_EQ(ConvTo2022Flush.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  // This should emit an error; there is a malformed multibyte character in the input string.
+  std::error_code EC0 = ConvTo2022Flush->convert(Src0, Dst0, true);
+  EXPECT_TRUE(EC0);
+  std::error_code EC1 = ConvTo2022Flush->flush();
+  EXPECT_TRUE(!EC1);
+  std::error_code EC2 = ConvTo2022Flush->convert(Src1, Dst1, true);
+  EXPECT_TRUE(!EC2);
+  EXPECT_STREQ(EarthKanjiOnlyISO2022, static_cast<std::string>(Dst1).c_str());
+}
+
+TEST(CharSet, ShiftStateIBM939Flush) {
+  StringRef Src0(EarthUTFBroken);
+  StringRef Src1(EarthKanjiOnlyUTF);
+  SmallString<64> Dst0;
+  SmallString<64> Dst1;
+  ErrorOr<CharSetConverter> ConvTo939Flush =
+      CharSetConverter::create("UTF-8", "IBM-939");
+  if (!ConvTo939Flush) {
+    ASSERT_EQ(ConvTo939Flush.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  // This should emit an error; there is a malformed multibyte character in the input string.
+  std::error_code EC0 = ConvTo939Flush->convert(Src0, Dst0, true);
+  EXPECT_TRUE(EC0);
+  std::error_code EC1 = ConvTo939Flush->flush();
+  EXPECT_TRUE(!EC1);
+  std::error_code EC2 = ConvTo939Flush->convert(Src1, Dst1, true);
+  EXPECT_TRUE(!EC2);
+  EXPECT_STREQ(EarthKanjiOnlyIBM939, static_cast<std::string>(Dst1).c_str());
+}
+
+TEST(CharSet, ShiftState2022Flush1) {
+  StringRef Src0(EarthUTF);
+  SmallString<64> Dst0;
+  SmallString<64> Dst1;
+  ErrorOr<CharSetConverter> ConvTo2022Flush =
+      CharSetConverter::create("UTF-8", "ISO-2022-JP");
+  if (!ConvTo2022Flush) {
+    ASSERT_EQ(ConvTo2022Flush.getError(),
+              std::make_error_code(std::errc::invalid_argument));
+    return;
+  }
+
+  std::error_code EC0 = ConvTo2022Flush->convert(Src0, Dst0, false);
+  EXPECT_TRUE(!EC0);
+  EXPECT_STREQ(EarthISO2022ShiftBack, static_cast<std::string>(Dst0).c_str());
+  std::error_code EC1 = ConvTo2022Flush->flush(Dst1);
+  EXPECT_TRUE(!EC1);
+  EXPECT_STREQ(ShiftBackOnly, static_cast<std::string>(Dst1).c_str());
+}
+
+#endif
+
+} // namespace



More information about the llvm-commits mailing list