Optional use of UTF-8 strings in resource bundles
Allows the use of UTF-8 for packing resources instead of the
default of UTF-16 for Java. When strings are extracted from the
ResStringPool, they are converted to UTF-16 and the result is
cached for subsequent calls.
When using aapt to package, add in the "-8" switch to pack the
resources using UTF-8. This will result in the value, key, and
type strings as well as the compiled XML string values taking
significantly less space in the final application package in
most scenarios.
Change-Id: I129483f8b3d3b1c5869dced05cb525e494a6c83a
diff --git a/libs/utils/String16.cpp b/libs/utils/String16.cpp
index aef67f2..eab7b2b 100644
--- a/libs/utils/String16.cpp
+++ b/libs/utils/String16.cpp
@@ -172,10 +172,6 @@
: 0);
}
-// ---------------------------------------------------------------------------
-
-namespace android {
-
static inline size_t
utf8_char_len(uint8_t ch)
{
@@ -215,8 +211,38 @@
//printf("Char at %p: len=%d, utf-16=%p\n", src, length, (void*)result);
}
+void
+utf8_to_utf16(const uint8_t *src, size_t srcLen,
+ char16_t* dst, const size_t dstLen)
+{
+ const uint8_t* const end = src + srcLen;
+ const char16_t* const dstEnd = dst + dstLen;
+ while (src < end && dst < dstEnd) {
+ size_t len = utf8_char_len(*src);
+ uint32_t codepoint = utf8_to_utf32((const uint8_t*)src, len);
+
+ // Convert the UTF32 codepoint to one or more UTF16 codepoints
+ if (codepoint <= 0xFFFF) {
+ // Single UTF16 character
+ *dst++ = (char16_t) codepoint;
+ } else {
+ // Multiple UTF16 characters with surrogates
+ codepoint = codepoint - 0x10000;
+ *dst++ = (char16_t) ((codepoint >> 10) + 0xD800);
+ *dst++ = (char16_t) ((codepoint & 0x3FF) + 0xDC00);
+ }
+
+ src += len;
+ }
+ if (dst < dstEnd) {
+ *dst = 0;
+ }
+}
+
// ---------------------------------------------------------------------------
+namespace android {
+
static SharedBuffer* gEmptyStringBuf = NULL;
static char16_t* gEmptyString = NULL;
@@ -260,30 +286,14 @@
p += utf8len;
}
- SharedBuffer* buf = SharedBuffer::alloc((chars+1)*sizeof(char16_t));
+ size_t bufSize = (chars+1)*sizeof(char16_t);
+ SharedBuffer* buf = SharedBuffer::alloc(bufSize);
if (buf) {
p = in;
char16_t* str = (char16_t*)buf->data();
- char16_t* d = str;
- while (p < end) {
- size_t len = utf8_char_len(*p);
- uint32_t codepoint = utf8_to_utf32((const uint8_t*)p, len);
-
- // Convert the UTF32 codepoint to one or more UTF16 codepoints
- if (codepoint <= 0xFFFF) {
- // Single UTF16 character
- *d++ = (char16_t) codepoint;
- } else {
- // Multiple UTF16 characters with surrogates
- codepoint = codepoint - 0x10000;
- *d++ = (char16_t) ((codepoint >> 10) + 0xD800);
- *d++ = (char16_t) ((codepoint & 0x3FF) + 0xDC00);
- }
-
- p += len;
- }
- *d = 0;
+ utf8_to_utf16((const uint8_t*)p, len, str, bufSize);
+
//printf("Created UTF-16 string from UTF-8 \"%s\":", in);
//printHexData(1, str, buf->size(), 16, 1);
//printf("\n");