From be264422c95c781a345978f17b7e80b91f816eda Mon Sep 17 00:00:00 2001 From: Jordan Justen Date: Tue, 23 Jun 2015 23:34:28 +0000 Subject: BaseTools/UniClassObject: Support UTF-8 string data in .uni files This allows .uni input files to be encoded with UTF-8. Today, we only support UTF-16 encoding. The strings are still converted to UCS-2 data for use in EDK II modules. (This is the only unicode character format supported by UEFI and EDK II.) Although UTF-8 would allow any UCS-4 character to be present in the source file, we restrict the entire file to the UCS-2 range. (Including comments.) This allows the files to be converted to UTF-16 if needed. v2: * Drop .utf8 extension. Use .uni file for UTF-8 data (mdkinney) * Merge in 'BaseTools/UniClassObject: Verify string data is 16-bit' commit v3: * Restrict the entire file's characters (including comments) to the UCS-2 range in addition to string data. (mdkinney) Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Jordan Justen Reviewed-by: Michael D Kinney Reviewed-by: Yingke Liu git-svn-id: https://svn.code.sf.net/p/edk2/code/trunk/edk2@17696 6f19259b-4bc3-4df7-8a09-765794883524 --- BaseTools/Source/Python/AutoGen/UniClassObject.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'BaseTools') diff --git a/BaseTools/Source/Python/AutoGen/UniClassObject.py b/BaseTools/Source/Python/AutoGen/UniClassObject.py index d0cbb1d0bb..02a15cc0f0 100644 --- a/BaseTools/Source/Python/AutoGen/UniClassObject.py +++ b/BaseTools/Source/Python/AutoGen/UniClassObject.py @@ -297,9 +297,12 @@ class UniFileClassObject(object): EdkLogger.Error("build", FILE_OPEN_FAILURE, ExtraData=File) # - # We currently only support UTF-16 + # Detect Byte Order Mark at beginning of file. Default to UTF-8 # - Encoding = 'utf-16' + Encoding = 'utf-8' + if (FileIn.startswith(codecs.BOM_UTF16_BE) or + FileIn.startswith(codecs.BOM_UTF16_LE)): + Encoding = 'utf-16' self.VerifyUcs2Data(FileIn, FileName, Encoding) -- cgit v1.2.3