With .uni UTF-16 files, it is impossible for unicode code points to be
larger than 0xFFFF.
To support .utf8 UTF-8 unicode files, we need to also deal with the
possibility that the UTF-8 file contains unicode code points larger
than 16-bits. Since UEFI only supports 16-bit string data, we make
UniClassObject generate an error if a larger code point is seen in a
UTF-8 string value.
We only check string value data, so it is possible to use larger code
points in comments.
Cc: Yingke D Liu <yingke.d....@intel.com>
Contributed-under: TianoCore Contribution Agreement 1.0
Signed-off-by: Jordan Justen <jordan.l.jus...@intel.com>
---
BaseTools/Source/Python/AutoGen/UniClassObject.py | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/BaseTools/Source/Python/AutoGen/UniClassObject.py
b/BaseTools/Source/Python/AutoGen/UniClassObject.py
index df30c48..fef7135 100644
--- a/BaseTools/Source/Python/AutoGen/UniClassObject.py
+++ b/BaseTools/Source/Python/AutoGen/UniClassObject.py
@@ -259,6 +259,14 @@ class UniFileClassObject(object):
self.OrderedStringDict[LangName][Item.StringName] =
len(self.OrderedStringList[LangName]) - 1
return True
+ def Verify16bitCodePoints(self, String):
+ for cp in String:
+ if ord(cp) > 0xffff:
+ tmpl = 'The string {} defined in file {} ' + \
+ 'contains a character with a code point above 0xFFFF.'
+ error = tmpl.format(repr(String), self.File)
+ EdkLogger.error('Unicode File Parser', FORMAT_INVALID, error)
+
#
# Get String name and value
#
@@ -280,6 +288,7 @@ class UniFileClassObject(object):
Language = LanguageList[IndexI].split()[0]
Value = LanguageList[IndexI][LanguageList[IndexI].find(u'\"')
+ len(u'\"') : LanguageList[IndexI].rfind(u'\"')] #.replace(u'\r\n', u'')
Language = GetLanguageCode(Language, self.IsCompatibleMode,
self.File)
+ self.Verify16bitCodePoints(Value)
self.AddStringToList(Name, Language, Value)
#
@@ -433,6 +442,7 @@ class UniFileClassObject(object):
MatchString = re.match('[A-Z0-9_]+', Name, re.UNICODE)
if MatchString == None or MatchString.end(0) != len(Name):
EdkLogger.error('Unicode File Parser', FORMAT_INVALID,
'The string token name %s defined in UNI file %s contains the invalid lower
case character.' %(Name, self.File))
+ self.Verify16bitCodePoints(Value)
self.AddStringToList(Name, Language, Value)
continue
--
2.1.4
------------------------------------------------------------------------------
One dashboard for servers and applications across Physical-Virtual-Cloud
Widest out-of-the-box monitoring support with 50+ applications
Performance metrics, stats and reports that give you Actionable Insights
Deep dive visibility with transaction tracing using APM Insight.
http://ad.doubleclick.net/ddm/clk/290420510;117567292;y
_______________________________________________
edk2-devel mailing list
edk2-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/edk2-devel
