Improve the encoding/decoding to/from system encoding on Windows

runtime/bin/utils_android.cc

Index: runtime/bin/utils_android.cc
diff --git a/runtime/bin/utils_android.cc b/runtime/bin/utils_android.cc
index 615dae966a2bdc151852484e8cdd330f9f33b4e9..4e535eb1e730a1a978cf28df75cfe0229f533f85 100644
--- a/runtime/bin/utils_android.cc
+++ b/runtime/bin/utils_android.cc
@@ -42,38 +42,58 @@ void OSError::SetCodeAndMessage(SubSystem sub_system, int code) {
   }
 }
 
-const char* StringUtils::ConsoleStringToUtf8(const char* str) {
+const char* StringUtils::ConsoleStringToUtf8(
+    const char* str, intptr_t len, intptr_t* result_len) {
+  if (result_len != NULL) {
+    *result_len = len;
+  }
   return str;
 }
 
-const char* StringUtils::Utf8ToConsoleString(const char* utf8) {
+const char* StringUtils::Utf8ToConsoleString(
+    const char* utf8, intptr_t len, intptr_t* result_len) {
+  if (result_len != NULL) {
+    *result_len = len;
+  }
   return utf8;
 }
 
-char* StringUtils::ConsoleStringToUtf8(char* str) {
+char* StringUtils::ConsoleStringToUtf8(
+    char* str, intptr_t len, intptr_t* result_len) {
+  if (result_len != NULL) {
+    *result_len = len;
+  }
   return str;
 }
 
-char* StringUtils::Utf8ToConsoleString(char* utf8) {
+char* StringUtils::Utf8ToConsoleString(
+    char* utf8, intptr_t len, intptr_t* result_len) {
+  if (result_len != NULL) {
+    *result_len = len;
+  }
   return utf8;

[kustermann, 2015/06/22 11:11:21]

There is potential for issues here. Previously the assumption was that
conversion is 0-terminated. Which means we can just return the (hopefully
already 0-terminated) input.

Now if len is not the length of the input string, but rather shorter, we still
return the same string. This seems inconsistent with the windows implementation,
which would make a copy and 0-terminate the shorter string.

tl;dr Do we need to make a shorter 0-terminated copy iff "strlen(utf8) != len" ?

[Søren Gjesse, 2015/06/23 11:17:59]

Changed this to be only implemented on Windows. This code path is *never*
reached on other platforms, so I don't want to reason about what to do there.

 }
 
-wchar_t* StringUtils::Utf8ToWide(char* utf8) {
+wchar_t* StringUtils::Utf8ToWide(
+    char* utf8, intptr_t len, intptr_t* result_len) {
   UNIMPLEMENTED();
   return NULL;
 }
 
-const wchar_t* StringUtils::Utf8ToWide(const char* utf8) {
+const wchar_t* StringUtils::Utf8ToWide(
+    const char* utf8, intptr_t len, intptr_t* result_len) {
   UNIMPLEMENTED();
   return NULL;
 }
 
-char* StringUtils::WideToUtf8(wchar_t* str) {
+char* StringUtils::WideToUtf8(
+    wchar_t* str, intptr_t len, intptr_t* result_len) {
   UNIMPLEMENTED();
   return NULL;
 }
 
-const char* StringUtils::WideToUtf8(const wchar_t* str) {
+const char* StringUtils::WideToUtf8(
+    const wchar_t* str, intptr_t len, intptr_t* result_len) {
   UNIMPLEMENTED();
   return NULL;
 }