llvm-project/lldb/unittests/SymbolFile/NativePDB
Pavel Labath 0ff89dacaf PostfixExpression: Use signed integers in IntegerNode
Summary:
This is necessary to support parsing expressions like ".cfa -16 + ^", as
that format is used in breakpad STACK CFI expressions.

Since the PDB expressions use the same parser, this change will affect
them too, but I don't believe that should be a problem in practice. If
PDBs do contain the negative values, it's very likely that they are
intended to be parsed the same way, and if they don't, then it doesn't
matter.

In case that we do ever need to handle this differently, we can always
make the parser behavior customizable, or just use a different parser.

To make sure that the integer size is big enough for everyone, I switch
from using a (unsigned) 32-bit integer to a 64-bit (signed) one.

Reviewers: amccarth, clayborg, aleksandr.urakov

Subscribers: markmentovai, lldb-commits

Differential Revision: https://reviews.llvm.org/D61311

llvm-svn: 360166
2019-05-07 15:58:20 +00:00
..
CMakeLists.txt
PdbFPOProgramToDWARFExpressionTests.cpp PostfixExpression: Use signed integers in IntegerNode 2019-05-07 15:58:20 +00:00