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

3 files changed, 20 insertions, 2 deletions

diff --git a/include/utils/ResourceTypes.h b/include/utils/ResourceTypes.h
index 49145e8..a845908 100644
--- a/include/utils/ResourceTypes.h
+++ b/include/utils/ResourceTypes.h
@@ -393,7 +393,10 @@ struct ResStringPool_header
     enum {
         // If set, the string index is sorted by the string values (based
         // on strcmp16()).
-        SORTED_FLAG = 1<<0
+        SORTED_FLAG = 1<<0,
+
+        // String pool is encoded in UTF-8
+        UTF8_FLAG = 1<<8
     };
     uint32_t flags;
 
@@ -456,9 +459,11 @@ private:
     void*                       mOwnedData;
     const ResStringPool_header* mHeader;
     size_t                      mSize;
+    mutable Mutex               mDecodeLock;
     const uint32_t*             mEntries;
     const uint32_t*             mEntryStyles;
-    const char16_t*             mStrings;
+    const void*                 mStrings;
+    char16_t**                  mCache;
     uint32_t                    mStringPoolSize;    // number of uint16_t
     const uint32_t*             mStyles;
     uint32_t                    mStylePoolSize;    // number of uint32_t
diff --git a/include/utils/String16.h b/include/utils/String16.h
index a2d22ee..07a0c11 100644
--- a/include/utils/String16.h
+++ b/include/utils/String16.h
@@ -49,12 +49,17 @@ int strzcmp16(const char16_t *s1, size_t n1, const char16_t *s2, size_t n2);
 // Version of strzcmp16 for comparing strings in different endianness.
 int strzcmp16_h_n(const char16_t *s1H, size_t n1, const char16_t *s2N, size_t n2);
 
+// Convert UTF-8 to UTF-16 including surrogate pairs
+void utf8_to_utf16(const uint8_t *src, size_t srcLen, char16_t* dst, const size_t dstLen);
+
 }
 
 // ---------------------------------------------------------------------------
 
 namespace android {
 
+// ---------------------------------------------------------------------------
+
 class String8;
 class TextOutput;
 
diff --git a/include/utils/String8.h b/include/utils/String8.h
index ecc5774..c4b18a4 100644
--- a/include/utils/String8.h
+++ b/include/utils/String8.h
@@ -60,6 +60,11 @@ size_t utf32_length(const char *src, size_t src_len);
 /*
  * Returns the UTF-8 length of "src".
  */
+size_t utf8_length_from_utf16(const char16_t *src, size_t src_len);
+
+/*
+ * Returns the UTF-8 length of "src".
+ */
 size_t utf8_length_from_utf32(const char32_t *src, size_t src_len);
 
 /*
@@ -120,6 +125,9 @@ size_t utf8_to_utf32(const char* src, size_t src_len,
 size_t utf32_to_utf8(const char32_t* src, size_t src_len,
                      char* dst, size_t dst_len);
 
+size_t utf16_to_utf8(const char16_t* src, size_t src_len,
+                     char* dst, size_t dst_len);
+
 }
 
 // ---------------------------------------------------------------------------