From: Dmitri Gribenko <gribozavr@gmail.com>
Date: Fri, 27 Jul 2012 20:36:22 +0000 (+0000)
Subject: Add a function to convert a single Unicode code point to a UTF8 sequence.
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=e43031344b17cdb345957c4acc9d39d26f86efd3;p=clang

Add a function to convert a single Unicode code point to a UTF8 sequence.


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@160890 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/include/clang/Basic/ConvertUTF.h b/include/clang/Basic/ConvertUTF.h
index 53d451485d..e7cfa8a767 100644
--- a/include/clang/Basic/ConvertUTF.h
+++ b/include/clang/Basic/ConvertUTF.h
@@ -110,6 +110,8 @@ typedef unsigned char   Boolean; /* 0 or 1 */
 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
 
+#define UNI_MAX_UTF8_BYTES_PER_CODE_POINT 4
+
 typedef enum {
   conversionOK,           /* conversion successful */
   sourceExhausted,        /* partial character in source, but hit end */
@@ -139,11 +141,13 @@ ConversionResult ConvertUTF8toUTF32 (
 ConversionResult ConvertUTF16toUTF8 (
   const UTF16** sourceStart, const UTF16* sourceEnd,
   UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
+#endif
 
 ConversionResult ConvertUTF32toUTF8 (
   const UTF32** sourceStart, const UTF32* sourceEnd,
   UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
 
+#ifdef CLANG_NEEDS_THESE_ONE_DAY
 ConversionResult ConvertUTF16toUTF32 (
   const UTF16** sourceStart, const UTF16* sourceEnd,
   UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
@@ -177,6 +181,18 @@ namespace clang {
 bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
                        char *&ResultPtr);
 
+/**
+ * Convert an Unicode code point to UTF8 sequence.
+ *
+ * \param Source a Unicode code point.
+ * \param [in,out] ResultPtr pointer to the output buffer, needs to be at least
+ * \c UNI_MAX_UTF8_BYTES_PER_CODE_POINT bytes.  On success \c ResultPtr is
+ * updated one past end of the converted sequence.
+ *
+ * \returns true on success.
+ */
+bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr);
+
 }
 #endif
 
diff --git a/lib/Basic/ConvertUTF.c b/lib/Basic/ConvertUTF.c
index e1970039e1..4793b251f6 100644
--- a/lib/Basic/ConvertUTF.c
+++ b/lib/Basic/ConvertUTF.c
@@ -285,6 +285,7 @@ ConversionResult ConvertUTF16toUTF8 (
     *targetStart = target;
     return result;
 }
+#endif
 
 /* --------------------------------------------------------------------- */
 
@@ -339,8 +340,6 @@ ConversionResult ConvertUTF32toUTF8 (
     return result;
 }
 
-#endif
-
 /* --------------------------------------------------------------------- */
 
 /*
diff --git a/lib/Basic/ConvertUTFWrapper.cpp b/lib/Basic/ConvertUTFWrapper.cpp
index 42b4f58079..a1b3f7fd9d 100644
--- a/lib/Basic/ConvertUTFWrapper.cpp
+++ b/lib/Basic/ConvertUTFWrapper.cpp
@@ -51,4 +51,20 @@ bool ConvertUTF8toWide(unsigned WideCharWidth, llvm::StringRef Source,
   return result == conversionOK;
 }
 
+bool ConvertCodePointToUTF8(unsigned Source, char *&ResultPtr) {
+  const UTF32 *SourceStart = &Source;
+  const UTF32 *SourceEnd = SourceStart + 1;
+  UTF8 *TargetStart = reinterpret_cast<UTF8 *>(ResultPtr);
+  UTF8 *TargetEnd = TargetStart + 4;
+  ConversionResult CR = ConvertUTF32toUTF8(&SourceStart, SourceEnd,
+                                           &TargetStart, TargetEnd,
+                                           strictConversion);
+  if (CR != conversionOK)
+    return false;
+
+  ResultPtr = reinterpret_cast<char*>(TargetStart);
+  return true;
 }
+
+} // end namespace clang
+