Otherwise any build flags like -tags won't be used, and we might easily
end up with errors or incorrect packages.
The common case with -tags is covered by one of the integration test
scripts. On top of that, we add a table-driven unit test to cover all
edge cases, since there are many we can do quickly in a unit test.
Fixes#82.
We don't really care about tools other than "compile" and "link". Stop
trying to keep a complete list.
Use "if err := f(); err != nil {" where it makes sense.
Simplify some declarations, and use a better variable name than "fW".
Instead of doing a 'go list' call every time we need to fetch a
dependency's export file, we now do a single 'go list' call before the
build begins. With the '-deps' flag, it gives us all the dependency
packages recursively.
We store that data in the gob format in a temporary file, and share it
with the future garble sub-processes via an env var.
This required lazy parsing of flags for the 'build' and 'test' commands,
since now we need to run 'go list' with the same package pattern
arguments.
Fixes#63.
The following identifiers are now skipped,
because they never show up in the binary:
- constant identifiers
- identifiers of local variables
(includes function params and named returns)
- identifiers of local types
First, unindent some of the AST code.
Second, genRandInt is unused; delete it.
Third, genRandIntn is really just mathrand.Intn. Just use it directly.
Fourth, don't use inline comments if they result in super long lines.
Since the new linker was failing on our crypto/aes shenanigans until the
recent commit to remove it for literal obfuscation.
Building Go does take about two minutes on the CI machine, but that's
fast enough. One can see the exact version that was used via the 'go
version' line.
Implement a literal obfuscator interface,
to allow the easy addition of new encodings.
Add literal obfuscation for byte literals.
Choose a random obfuscator on literal obfuscation,
useful when multiple obfuscators are implemented.
Fixes#62
Injected functions were mistaken for functions implemented outside go.
Asm functions:
obj.Scope().Pos() == 0
obj.Scope().End() == 0
Injected functions:
obj.Scope().Pos() == 0
obj.Scope().End() == 1
We now check for the End instead of the Pos.
This requires a bit of extra magic to replace one constant in
runtime/internal/sys, but that was simple enough given that we can reuse
a lot of the code to parse the files and write them to a temporary dir.
We can also drop the -X flags, as runtime.buildVersion is based on the
constant that we replace here.
Fixes#44, again.
Generating DWARF in the compiler object files could take as much as 10%
extra CPU time, while we ignore it entirely at the link stage.
Speeds up 'go test -short' from ~19.5s to ~18.5s on my laptop.
I now implemented and tested hex encoded strings, binary literals, and fmt.Sprintf("%q", data).
In the case of garble all produce the exact same binary size.
I decided to use %q because it is the simplest, leads to the smallest garbled code file size size
of the three, and is faster at compile time than binary literals.
It looks like:
var ztN0xdMLL = garbleDecrypt([]byte("\xaf\xbd\x01\\&\x14\xab\xeb\x94\x10Q\xf2H#\xde\x17\a\x8f\x89MmZs\u0088\xcfw\xba?\x9e\xe1\x81\x1eպD\xe1@\xf2\x8d\xe3Ije\xca\bB\xbey\x8b"))
From the fmt docs:
String and slice of bytes (treated equivalently with these verbs):
[...]
%q a double-quoted string safely escaped with Go syntax
Fixes#40.
Whilst it may not be particularly common, it is legal to embed fields
where the type has universe scope (e.g. int, error, etc). This can
cause a panic in 2 difference places:
- When embedding `error`, a named type is resolved but the package is
nil. The call to `pkg.Name()` results in a panic
- When embedding a basic type such as `int`, no named type is resolved
at all. The call to `namedType(obj.Type()).Obj()` results in a panic
I'm assuming it is OK to return early when a named type cannot be
resolved.. we could let it continue but I think `pkg` should be set to
nil to be correct, so it'd end up returning straight away anyway.