Browse Source

CMakeDetermineCompilerId: Consider UTF-16 encodings of INFO strings

Our compiler identification source encodes `INFO:compiler[...]` and
similar strings in compiled objects or binaries that we then extract to
get information about the compiler.  With most compilers the strings are
encoded in the binaries as a simple byte sequence.  However, some
compilers use other encodings.  For example, the MS CSharp compiler uses
UTF-16LE and a TI compiler uses UTF-16BE.  Try each encoding.

Fixes: #19459
Brad King 6 years ago
parent
commit
d1f38ba65d

+ 0 - 1
Modules/CMakeDetermineCSharpCompiler.cmake

@@ -18,7 +18,6 @@ if(NOT CMAKE_CSharp_COMPILER_ID_RUN)
   set(CMAKE_CSharp_COMPILER_ID_RUN 1)
 
   # Try to identify the compiler.
-  set(CMAKE_CSharp_COMPILER_ID_STRINGS_PARAMETERS ENCODING UTF-16LE)
   set(CMAKE_CSharp_COMPILER_ID)
   include(${CMAKE_ROOT}/Modules/CMakeDetermineCompilerId.cmake)
   CMAKE_DETERMINE_COMPILER_ID(CSharp CSFLAGS CMakeCSharpCompilerId.cs)

+ 8 - 4
Modules/CMakeDetermineCompilerId.cmake

@@ -640,10 +640,14 @@ function(CMAKE_DETERMINE_COMPILER_ID_CHECK lang file)
     set(ARCHITECTURE_ID)
     set(SIMULATE_ID)
     set(SIMULATE_VERSION)
-    file(STRINGS ${file}
-      CMAKE_${lang}_COMPILER_ID_STRINGS LIMIT_COUNT 38
-      ${CMAKE_${lang}_COMPILER_ID_STRINGS_PARAMETERS}
-      REGEX ".?I.?N.?F.?O.?:.?[A-Za-z0-9_]+\\[[^]]*\\]")
+    foreach(encoding "" "ENCODING;UTF-16LE" "ENCODING;UTF-16BE")
+      file(STRINGS "${file}" CMAKE_${lang}_COMPILER_ID_STRINGS
+        LIMIT_COUNT 38 ${encoding}
+        REGEX ".?I.?N.?F.?O.?:.?[A-Za-z0-9_]+\\[[^]]*\\]")
+      if(NOT CMAKE_${lang}_COMPILER_ID_STRINGS STREQUAL "")
+        break()
+      endif()
+    endforeach()
     set(COMPILER_ID_TWICE)
     # With the IAR Compiler, some strings are found twice, first time as incomplete
     # list like "?<Constant "INFO:compiler[IAR]">".  Remove the incomplete copies.