rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// Copyright (c) 2020, The Garble Authors.
|
|
|
|
|
// See LICENSE for licensing information.
|
|
|
|
|
|
|
|
|
|
package main
|
|
|
|
|
|
|
|
|
|
import (
|
|
|
|
|
"bytes"
|
|
|
|
|
"fmt"
|
|
|
|
|
"go/ast"
|
|
|
|
|
"go/parser"
|
|
|
|
|
"go/printer"
|
|
|
|
|
"path/filepath"
|
|
|
|
|
"strings"
|
|
|
|
|
|
|
|
|
|
"golang.org/x/exp/slices"
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
)
|
|
|
|
|
|
|
|
|
|
func isDirective(text string) bool {
|
|
|
|
|
// TODO: can we remove the check for "// +build" now that we require Go 1.18
|
|
|
|
|
// or later? we should update the tests too.
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
return strings.HasPrefix(text, "//go:") || strings.HasPrefix(text, "// +build")
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
var printBuf1, printBuf2 bytes.Buffer
|
|
|
|
|
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// printFile prints a Go file to a buffer, while also removing non-directive
|
|
|
|
|
// comments and adding extra compiler directives to obfuscate position
|
|
|
|
|
// information.
|
|
|
|
|
func printFile(file1 *ast.File) ([]byte, error) {
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
printConfig := printer.Config{Mode: printer.RawFormat}
|
|
|
|
|
|
|
|
|
|
printBuf1.Reset()
|
|
|
|
|
if err := printConfig.Fprint(&printBuf1, fset, file1); err != nil {
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
return nil, err
|
|
|
|
|
}
|
|
|
|
|
src := printBuf1.Bytes()
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
|
deprecate using GOPRIVATE in favor of GOGARBLE (#427)
Piggybacking off of GOPRIVATE is great for a number of reasons:
* People tend to obfuscate private code, whose package paths will
generally be in GOPRIVATE already
* Its meaning and syntax are well understood
* It allows all the flexibility we need without adding our own env var
or config option
However, using GOPRIVATE directly has one main drawback.
It's fairly common to also want to obfuscate public dependencies,
to make the code in private packages even harder to follow.
However, using "GOPRIVATE=*" will result in two main downsides:
* GONOPROXY defaults to GOPRIVATE, so the proxy would be entirely disabled.
Downloading modules, such as when adding or updating dependencies,
or when the local cache is cold, can be less reliable.
* GONOSUMDB defaults to GOPRIVATE, so the sumdb would be entirely disabled.
Adding entries to go.sum, such as when adding or updating dependencies,
can be less secure.
We will continue to consume GOPRIVATE as a fallback,
but we now expect users to set GOGARBLE instead.
The new logic is documented in the README.
While here, rewrite some uses of "private" with "to obfuscate",
to make the code easier to follow and harder to misunderstand.
Fixes #276.
3 years ago
|
|
|
if !curPkg.ToObfuscate {
|
|
|
|
|
// TODO(mvdan): make transformCompile handle untouched
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// packages like runtime earlier on, to remove these checks.
|
|
|
|
|
return src, nil
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
absFilename := fset.Position(file1.Pos()).Filename
|
|
|
|
|
filename := filepath.Base(absFilename)
|
|
|
|
|
if strings.HasPrefix(filename, "_cgo_") {
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// cgo-generated files don't need changed line numbers.
|
|
|
|
|
// Plus, the compiler can complain rather easily.
|
|
|
|
|
return src, nil
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Many parts of garble, notably the literal obfuscator, modify the AST.
|
|
|
|
|
// Unfortunately, comments are free-floating in File.Comments,
|
|
|
|
|
// and those are the only source of truth that go/printer uses.
|
|
|
|
|
// So the positions of the comments in the given file are wrong.
|
|
|
|
|
// The only way we can get the final ones is to parse again.
|
use an empty filename when re-parsing source files
In printFile, we print and re-parse the modified AST to be able to have
reliable position information.
The re-parsing step can fail if something goes very wrong, such as a bug
in -literals. It should generally not happen. However, in rare cases it
has happened, and it's confusing for the end user to see syntax errors
pointing at an existing file on disk, when the code doesn't align
- since we're on a modified copy.
To prevent such confusion, use an empty filename. Syntax errors will
still not be terribly helpful, but they should be extremely rare and
promptly fixed, so that's not a huge concern.
For that same reason, we can't really add a good test here. We could
perhaps add a test that forces garble to mess up the src slice in some
way, but that would be a weird test, and not particularly worth it.
Fixes #286.
4 years ago
|
|
|
//
|
|
|
|
|
// We use an empty filename here.
|
|
|
|
|
// Syntax errors should be rare, and when they do happen,
|
|
|
|
|
// we don't want to point to the original source file on disk.
|
|
|
|
|
// That would be confusing, as we've changed the source in memory.
|
|
|
|
|
file2, err := parser.ParseFile(fset, "", src, parser.ParseComments)
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
if err != nil {
|
set positions when using cursor.Replace
The regular obfuscation process simply modifies some simple nodes, such
as identifiers and strings. In those cases, we modify the nodes
in-place, meaning that their positions remain the same. This hasn't
caused any problems.
Literal obfuscation is trickier. Since we replace one expression with an
entirely different one, we use cursor.Replace. The new expression is
entirely made up on the spot, so it lacks position information.
This was causing problems. For example, in the added test input:
> garble -literals build
[stderr]
# test/main
dgcm4t6w.go:3: misplaced compiler directive
dgcm4t6w.go:4: misplaced compiler directive
dgcm4t6w.go:3: misplaced compiler directive
dgcm4t6w.go:6: misplaced compiler directive
dgcm4t6w.go:7: misplaced compiler directive
dgcm4t6w.go:3: misplaced compiler directive
dgcm4t6w.go:9: misplaced compiler directive
dgcm4t6w.go:3: misplaced compiler directive
dgcm4t6w.go:3: too many errors
The build errors are because we'd move the compiler directives, which
makes the compiler unhappy as they must be directly followed by a
function declaration.
The root cause there seems to be that, since the replacement nodes lack
position information, go/printer would try to estimate its printing
position by adding to the last known position. Since -literals adds
code, this would result in the printer position increasing rapidly, and
potentially printing directive comments earlier than needed.
For now, making the replacement nodes have the same position as the
original node seems to stop go/printer from making this mistake.
It's possible that this workaround won't be bulletproof forever, but it
works well for now, and I don't see a simpler workaround right now.
It would be possible to use fancier mechanisms like go/ast.CommentMap or
dave/dst, but those are a significant amount of added complexity as well.
Fixes #285.
4 years ago
|
|
|
return nil, fmt.Errorf("re-parse error: %w", err)
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Remove any comments by making them whitespace.
|
|
|
|
|
// Keep directives, as they affect the build.
|
|
|
|
|
// This is superior to removing the comments before printing,
|
|
|
|
|
// because then the final source would have different line numbers.
|
|
|
|
|
for _, group := range file2.Comments {
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
for _, comment := range group.List {
|
|
|
|
|
if isDirective(comment.Text) {
|
|
|
|
|
continue
|
|
|
|
|
}
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
start := fset.Position(comment.Pos()).Offset
|
|
|
|
|
end := fset.Position(comment.End()).Offset
|
|
|
|
|
for i := start; i < end; i++ {
|
|
|
|
|
src[i] = ' '
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
var origCallExprs []*ast.CallExpr
|
|
|
|
|
ast.Inspect(file1, func(node ast.Node) bool {
|
|
|
|
|
if node, ok := node.(*ast.CallExpr); ok {
|
|
|
|
|
origCallExprs = append(origCallExprs, node)
|
|
|
|
|
}
|
|
|
|
|
return true
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
// Keep the compiler directives, and change position info.
|
|
|
|
|
type commentToAdd struct {
|
|
|
|
|
offset int
|
|
|
|
|
text string
|
|
|
|
|
}
|
|
|
|
|
var toAdd []commentToAdd
|
|
|
|
|
i := 0
|
|
|
|
|
ast.Inspect(file2, func(node ast.Node) bool {
|
|
|
|
|
node, ok := node.(*ast.CallExpr)
|
|
|
|
|
if !ok {
|
|
|
|
|
return true
|
|
|
|
|
}
|
|
|
|
|
origNode := origCallExprs[i]
|
|
|
|
|
i++
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
newName := ""
|
unify the definition and storage of flag values
The parent garble process parses the original flags,
as provided by the user via the command line.
Previously, those got stored in the shared cache file,
so that child processes spawned by toolexec could see them.
Unfortunately, this made the code relatively easy to misuse.
A child process would always see flagLiterals as zero value,
given that it should never see such a flag argument directly.
Similarly, one would have to be careful with cached options,
as they could only be consumed after the cache file is loaded.
Simplify the situation by deduplicating the storage of flags.
Now, the parent passes all flags onto children via toolexec.
One exception is GarbleDir, which now becomes an env var.
This seems in line with other top-level dirs like GARBLE_SHARED.
Finally, we turn -seed into a flag.Value,
which lets us implement its "set" behavior as part of flag.Parse.
Overall, we barely reduce the amount of code involved,
but we certainly remove a couple of footguns.
As part of the cleanup, we also introduce appendFlags.
3 years ago
|
|
|
if !flagTiny {
|
|
|
|
|
origPos := fmt.Sprintf("%s:%d", filename, fset.Position(origNode.Pos()).Offset)
|
|
|
|
|
newName = hashWithPackage(curPkg, origPos) + ".go"
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// log.Printf("%q hashed with %x to %q", origPos, curPkg.GarbleActionID, newName)
|
|
|
|
|
}
|
|
|
|
|
pos := fset.Position(node.Pos())
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
|
|
|
|
|
// We use the "/*text*/" form, since we can use multiple of them
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
// on a single line, and they don't require extra newlines.
|
|
|
|
|
toAdd = append(toAdd, commentToAdd{
|
|
|
|
|
offset: pos.Offset,
|
|
|
|
|
text: fmt.Sprintf("/*line %s:1*/", newName),
|
|
|
|
|
})
|
|
|
|
|
return true
|
|
|
|
|
})
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
|
|
|
|
|
// We add comments in order.
|
|
|
|
|
slices.SortFunc(toAdd, func(a, b commentToAdd) bool {
|
|
|
|
|
return a.offset < b.offset
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
})
|
|
|
|
|
|
|
|
|
|
copied := 0
|
|
|
|
|
printBuf2.Reset()
|
|
|
|
|
|
|
|
|
|
// Make sure the entire file gets a zero filename by default,
|
|
|
|
|
// in case we miss any positions below.
|
|
|
|
|
// We use a //-style comment, because there might be build tags.
|
|
|
|
|
// toAdd is for /*-style comments, so add it to printBuf2 directly.
|
|
|
|
|
printBuf2.WriteString("//line :1\n")
|
|
|
|
|
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
for _, comment := range toAdd {
|
|
|
|
|
printBuf2.Write(src[copied:comment.offset])
|
|
|
|
|
copied = comment.offset
|
|
|
|
|
|
|
|
|
|
// We assume that all comments are of the form "/*text*/".
|
|
|
|
|
// Make sure there is whitespace at either side of a comment.
|
|
|
|
|
// Otherwise, we could change the syntax of the program.
|
|
|
|
|
// Inserting "/*text*/" in "a/b" // must be "a/ /*text*/ b",
|
|
|
|
|
// as "a//*text*/b" is tokenized as a "//" comment.
|
|
|
|
|
printBuf2.WriteByte(' ')
|
|
|
|
|
printBuf2.WriteString(comment.text)
|
|
|
|
|
printBuf2.WriteByte(' ')
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
}
|
|
|
|
|
printBuf2.Write(src[copied:])
|
|
|
|
|
return printBuf2.Bytes(), nil
|
rework the position obfuscator (#282)
First, rename line_obfuscator.go to position.go. We obfuscate filenames,
not just line numbers, and "obfuscator" is a bit redundant.
Second, use "/*line :x*/" comments rather than the "//line :x" form, as
the former allows us to insert them in any position without adding
unnecessary newlines. This will be important for changing the position
of call sites, which will be important for "garble reverse".
Third, do not rely on go/ast to remove and add comments. Since they are
free-floating, we can very easily end up with misplaced comments,
especially as the literal obfuscator heavily modifies the AST.
The new method prints and re-parses the file, to ensure all node
positions are consistent with a buffer, buf1. Then, we copy the contents
into a new buffer, buf2, while inserting the comments that we need.
The new method also modifies line numbers at the very end of obfuscating
a Go file, instead of at the very beginning. That's going to be more
robust long-term, as we will also obfuscate line numbers for any
additions or modifications to the AST.
Fourth, detachedDirectives is unnecessary, as we can accomplish the same
with two simple prefix matches.
Finally, this means we can stop using detachedComments entirely, as
printFile already inserts the comments we need.
For #5.
4 years ago
|
|
|
}
|
