Reviewers: Christian Plesner Hansen,
Message:
Return number of characters written in String::WriteUtf8(). Explanation here
http://groups.google.com/group/v8-users/browse_thread/thread/6a7d6bb735196336
Description:
Change String::WriteUtf8() to return characters written.
Explanation:
http://groups.google.com/group/v8-users/browse_thread/thread/6a7d6bb735196336
Please review this at http://codereview.chromium.org/1539013
Affected files:
M include/v8.h
M src/api.cc
M test/cctest/test-strings.cc
Index: include/v8.h
diff --git a/include/v8.h b/include/v8.h
index
f64b3867367ab1f65729b04c4b6666c1a385fc1c..90c43831f4165505a8a92c8916a34d255ebabc16
100644
--- a/include/v8.h
+++ b/include/v8.h
@@ -855,12 +855,15 @@ class V8EXPORT String : public Primitive {
* \param start The starting position within the string at which
* copying begins.
* \param length The number of bytes to copy from the string.
- * \return The number of characters copied to the buffer
+ * \param nchars The number of characters written.
+ * \return The number of bytes copied to the buffer
* excluding the NULL terminator.
*/
int Write(uint16_t* buffer, int start = 0, int length = -1) const; //
UTF-16
int WriteAscii(char* buffer, int start = 0, int length = -1) const; //
ASCII
- int WriteUtf8(char* buffer, int length = -1) const; // UTF-8
+ int WriteUtf8(char* buffer,
+ int length = -1,
+ int* nchars = NULL) const; // UTF-8
/**
* A zero length string.
Index: src/api.cc
diff --git a/src/api.cc b/src/api.cc
index
2100480e85864356f1f6c04cfaee13736eede544..3ba22d63ea659fc7e774e823c8322afab4d1a83b
100644
--- a/src/api.cc
+++ b/src/api.cc
@@ -2639,7 +2639,7 @@ int String::Utf8Length() const {
}
-int String::WriteUtf8(char* buffer, int capacity) const {
+int String::WriteUtf8(char* buffer, int capacity, int *ncharsRef) const {
if (IsDeadCheck("v8::String::WriteUtf8()")) return 0;
LOG_API("String::WriteUtf8");
ENTER_V8;
@@ -2653,10 +2653,12 @@ int String::WriteUtf8(char* buffer, int capacity)
const {
int fast_end = capacity - (unibrow::Utf8::kMaxEncodedSize - 1);
int i;
int pos = 0;
+ int nchars = 0;
for (i = 0; i < len && (capacity == -1 || pos < fast_end); i++) {
i::uc32 c = write_input_buffer.GetNext();
int written = unibrow::Utf8::Encode(buffer + pos, c);
pos += written;
+ nchars++;
}
if (i < len) {
// For the last characters we need to check the length for each one
@@ -2670,12 +2672,14 @@ int String::WriteUtf8(char* buffer, int capacity)
const {
for (int j = 0; j < written; j++)
buffer[pos + j] = intermediate[j];
pos += written;
+ nchars++;
} else {
// We've reached the end of the buffer
break;
}
}
}
+ if (ncharsRef) *ncharsRef = nchars;
if (i == len && (capacity == -1 || pos < capacity))
buffer[pos++] = '\0';
return pos;
Index: test/cctest/test-strings.cc
diff --git a/test/cctest/test-strings.cc b/test/cctest/test-strings.cc
index
59a40af2a675c586df40e2f41dde5cf2955dfe27..a87398740b53c08bee028618c96937826315f0b6
100644
--- a/test/cctest/test-strings.cc
+++ b/test/cctest/test-strings.cc
@@ -323,6 +323,7 @@ TEST(Utf8Conversion) {
0xE3, 0x81, 0x85, 0x00};
// The number of bytes expected to be written for each length
const int lengths[12] = {0, 0, 2, 3, 3, 3, 6, 7, 7, 7, 10, 11};
+ const int charLengths[12] = {0, 0, 1, 2, 2, 2, 3, 4, 4, 4, 5, 5};
v8::Handle<v8::String> mixed = v8::String::New(mixed_string, 5);
CHECK_EQ(10, mixed->Utf8Length());
// Try encoding the string with all capacities
@@ -332,8 +333,10 @@ TEST(Utf8Conversion) {
// Clear the buffer before reusing it
for (int j = 0; j < 11; j++)
buffer[j] = kNoChar;
- int written = mixed->WriteUtf8(buffer, i);
+ int charsWritten;
+ int written = mixed->WriteUtf8(buffer, i, &charsWritten);
CHECK_EQ(lengths[i], written);
+ CHECK_EQ(charLengths[i], charsWritten);
// Check that the contents are correct
for (int j = 0; j < lengths[i]; j++)
CHECK_EQ(as_utf8[j], static_cast<unsigned char>(buffer[j]));
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
To unsubscribe, reply using "remove me" as the subject.
