dexpp 0.2.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- dexpp-0.2.0/.clang-format +26 -0
- dexpp-0.2.0/.gitignore +53 -0
- dexpp-0.2.0/CHANGELOG.md +170 -0
- dexpp-0.2.0/CMakeLists.txt +160 -0
- dexpp-0.2.0/LICENSE +201 -0
- dexpp-0.2.0/PKG-INFO +142 -0
- dexpp-0.2.0/README.md +119 -0
- dexpp-0.2.0/bindings/c/dexpp.h +111 -0
- dexpp-0.2.0/bindings/c/dexpp_c.cpp +269 -0
- dexpp-0.2.0/bindings/c/dexpp_model.cpp +310 -0
- dexpp-0.2.0/bindings/c/dexpp_model.h +190 -0
- dexpp-0.2.0/bindings/go/README.md +111 -0
- dexpp-0.2.0/bindings/go/dexpp/dexpp.go +329 -0
- dexpp-0.2.0/bindings/go/dexpp/dexpp_test.go +102 -0
- dexpp-0.2.0/bindings/go/dexpp/model.go +336 -0
- dexpp-0.2.0/bindings/go/dexpp/model_test.go +260 -0
- dexpp-0.2.0/bindings/go/example/main.go +55 -0
- dexpp-0.2.0/bindings/go/go.mod +3 -0
- dexpp-0.2.0/bindings/python/dexpp.pyi +897 -0
- dexpp-0.2.0/bindings/python/dexpp_model_py.cpp +304 -0
- dexpp-0.2.0/bindings/python/dexpp_module.cpp +1187 -0
- dexpp-0.2.0/bindings/python/test_androguard_parity.py +608 -0
- dexpp-0.2.0/bindings/python/test_dexpp.py +685 -0
- dexpp-0.2.0/pyproject.toml +57 -0
- dexpp-0.2.0/src/analysis/access_flags.hpp +5 -0
- dexpp-0.2.0/src/analysis/analysis_context.cpp +703 -0
- dexpp-0.2.0/src/analysis/analysis_context.hpp +121 -0
- dexpp-0.2.0/src/analysis/analysis_context_impl.hpp +174 -0
- dexpp-0.2.0/src/analysis/analysis_error.hpp +24 -0
- dexpp-0.2.0/src/analysis/annotations.cpp +130 -0
- dexpp-0.2.0/src/analysis/annotations.hpp +103 -0
- dexpp-0.2.0/src/analysis/call_graph.cpp +1068 -0
- dexpp-0.2.0/src/analysis/call_graph.hpp +224 -0
- dexpp-0.2.0/src/analysis/cfg.cpp +258 -0
- dexpp-0.2.0/src/analysis/cfg.hpp +87 -0
- dexpp-0.2.0/src/analysis/class.cpp +130 -0
- dexpp-0.2.0/src/analysis/class.hpp +83 -0
- dexpp-0.2.0/src/analysis/class_fwd.hpp +5 -0
- dexpp-0.2.0/src/analysis/class_hierarchy.cpp +233 -0
- dexpp-0.2.0/src/analysis/class_hierarchy.hpp +127 -0
- dexpp-0.2.0/src/analysis/class_ref.cpp +37 -0
- dexpp-0.2.0/src/analysis/class_ref.hpp +54 -0
- dexpp-0.2.0/src/analysis/field.cpp +103 -0
- dexpp-0.2.0/src/analysis/field.hpp +64 -0
- dexpp-0.2.0/src/analysis/instruction.cpp +657 -0
- dexpp-0.2.0/src/analysis/instruction.hpp +284 -0
- dexpp-0.2.0/src/analysis/invoke_sites.hpp +27 -0
- dexpp-0.2.0/src/analysis/method.cpp +231 -0
- dexpp-0.2.0/src/analysis/method.hpp +173 -0
- dexpp-0.2.0/src/analysis/type_descriptor.cpp +43 -0
- dexpp-0.2.0/src/analysis/type_descriptor.hpp +49 -0
- dexpp-0.2.0/src/analysis/xrefs.cpp +212 -0
- dexpp-0.2.0/src/analysis/xrefs.hpp +196 -0
- dexpp-0.2.0/src/apk/apk.cpp +131 -0
- dexpp-0.2.0/src/apk/apk.hpp +71 -0
- dexpp-0.2.0/src/apk/axml.cpp +118 -0
- dexpp-0.2.0/src/apk/axml.hpp +131 -0
- dexpp-0.2.0/src/apk/manifest.cpp +181 -0
- dexpp-0.2.0/src/apk/manifest.hpp +131 -0
- dexpp-0.2.0/src/apk/resources.cpp +255 -0
- dexpp-0.2.0/src/apk/resources.hpp +86 -0
- dexpp-0.2.0/src/apk/signing.cpp +379 -0
- dexpp-0.2.0/src/apk/signing.hpp +52 -0
- dexpp-0.2.0/src/apk/string_pool.cpp +133 -0
- dexpp-0.2.0/src/apk/string_pool.hpp +48 -0
- dexpp-0.2.0/src/common/access_flags.hpp +48 -0
- dexpp-0.2.0/src/common/annotation_visibility.hpp +14 -0
- dexpp-0.2.0/src/common/ids.cpp +33 -0
- dexpp-0.2.0/src/common/ids.hpp +52 -0
- dexpp-0.2.0/src/dex.hpp +33 -0
- dexpp-0.2.0/src/main.cpp +42 -0
- dexpp-0.2.0/src/model/io.hpp +141 -0
- dexpp-0.2.0/src/model/model.hpp +7 -0
- dexpp-0.2.0/src/model/read.cpp +967 -0
- dexpp-0.2.0/src/model/rename.cpp +531 -0
- dexpp-0.2.0/src/model/rules.hpp +96 -0
- dexpp-0.2.0/src/model/types.cpp +154 -0
- dexpp-0.2.0/src/model/types.hpp +884 -0
- dexpp-0.2.0/src/model/validate.cpp +876 -0
- dexpp-0.2.0/src/model/write.cpp +2322 -0
- dexpp-0.2.0/src/raw/byte_writer.hpp +76 -0
- dexpp-0.2.0/src/raw/constants.hpp +42 -0
- dexpp-0.2.0/src/raw/descriptors.cpp +269 -0
- dexpp-0.2.0/src/raw/descriptors.hpp +78 -0
- dexpp-0.2.0/src/raw/digest.cpp +154 -0
- dexpp-0.2.0/src/raw/digest.hpp +16 -0
- dexpp-0.2.0/src/raw/error.cpp +33 -0
- dexpp-0.2.0/src/raw/error.hpp +41 -0
- dexpp-0.2.0/src/raw/mutf8.cpp +329 -0
- dexpp-0.2.0/src/raw/mutf8.hpp +69 -0
- dexpp-0.2.0/src/raw/opcodes.cpp +657 -0
- dexpp-0.2.0/src/raw/opcodes.hpp +138 -0
- dexpp-0.2.0/src/raw/parser.cpp +1154 -0
- dexpp-0.2.0/src/raw/parser.hpp +150 -0
- dexpp-0.2.0/src/raw/parsing_utils.cpp +187 -0
- dexpp-0.2.0/src/raw/parsing_utils.hpp +76 -0
- dexpp-0.2.0/src/raw/types.cpp +62 -0
- dexpp-0.2.0/src/raw/types.hpp +468 -0
- dexpp-0.2.0/src/raw/zip.cpp +240 -0
- dexpp-0.2.0/src/raw/zip.hpp +58 -0
- dexpp-0.2.0/src/version.hpp +12 -0
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
BasedOnStyle: LLVM
|
|
2
|
+
|
|
3
|
+
IndentWidth: 4
|
|
4
|
+
TabWidth: 4
|
|
5
|
+
UseTab: Never
|
|
6
|
+
|
|
7
|
+
BreakBeforeBraces: Custom
|
|
8
|
+
BraceWrapping:
|
|
9
|
+
AfterClass: true
|
|
10
|
+
AfterControlStatement: false
|
|
11
|
+
AfterFunction: true
|
|
12
|
+
AfterNamespace: false
|
|
13
|
+
AfterStruct: true
|
|
14
|
+
AfterUnion: true
|
|
15
|
+
BeforeCatch: true
|
|
16
|
+
BeforeElse: true
|
|
17
|
+
|
|
18
|
+
AlignAfterOpenBracket: Align
|
|
19
|
+
AlignConsecutiveAssignments: false
|
|
20
|
+
AlignConsecutiveDeclarations: false
|
|
21
|
+
|
|
22
|
+
ColumnLimit: 100
|
|
23
|
+
|
|
24
|
+
ReflowComments: true
|
|
25
|
+
|
|
26
|
+
InsertNewlineAtEOF: true
|
dexpp-0.2.0/.gitignore
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
# IDE files
|
|
2
|
+
.idea/
|
|
3
|
+
*.iml
|
|
4
|
+
*.ipr
|
|
5
|
+
*.iws
|
|
6
|
+
|
|
7
|
+
# Build directories
|
|
8
|
+
build/
|
|
9
|
+
build-*/
|
|
10
|
+
cmake-build-debug/
|
|
11
|
+
cmake-build-release/
|
|
12
|
+
|
|
13
|
+
# Compiled output
|
|
14
|
+
*.o
|
|
15
|
+
*.obj
|
|
16
|
+
*.exe
|
|
17
|
+
*.out
|
|
18
|
+
*.app
|
|
19
|
+
|
|
20
|
+
# CMake
|
|
21
|
+
CMakeCache.txt
|
|
22
|
+
CMakeFiles/
|
|
23
|
+
cmake_install.cmake
|
|
24
|
+
Makefile
|
|
25
|
+
compile_commands.json
|
|
26
|
+
CTestTestfile.cmake
|
|
27
|
+
_deps/
|
|
28
|
+
|
|
29
|
+
# Local files
|
|
30
|
+
.local/
|
|
31
|
+
|
|
32
|
+
# OS files
|
|
33
|
+
.DS_Store
|
|
34
|
+
Thumbs.db
|
|
35
|
+
|
|
36
|
+
# Backup files
|
|
37
|
+
*~
|
|
38
|
+
*.bak
|
|
39
|
+
*.swp
|
|
40
|
+
*.swo
|
|
41
|
+
|
|
42
|
+
# Locally generated benchmark APK (not a test fixture)
|
|
43
|
+
tests/data/bench.apk
|
|
44
|
+
|
|
45
|
+
# Python packaging
|
|
46
|
+
*.egg-info/
|
|
47
|
+
dist/
|
|
48
|
+
wheelhouse/
|
|
49
|
+
__pycache__/
|
|
50
|
+
|
|
51
|
+
# Stray build artifacts
|
|
52
|
+
TestDex.class
|
|
53
|
+
cmake_test_discovery_*.json
|
dexpp-0.2.0/CHANGELOG.md
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
## 0.2.0
|
|
4
|
+
|
|
5
|
+
### Editable DEX model (new)
|
|
6
|
+
|
|
7
|
+
`dex::model` (include `model/model.hpp`, or `dex.hpp`) reads a DEX file into
|
|
8
|
+
plain C++ structs, lets you change them or build new ones from scratch, and
|
|
9
|
+
writes a valid DEX file again.
|
|
10
|
+
|
|
11
|
+
- The model holds no pool indices and no byte offsets. References are written
|
|
12
|
+
out in full (type descriptors, prototypes, `MethodId`, `FieldId`) and
|
|
13
|
+
branches point at labels. `write()` collects the references, sorts and
|
|
14
|
+
numbers the pools, and picks each instruction's encoding (`Const` becomes
|
|
15
|
+
`const/4`, `const/16`, `const/high16` or `const`; a branch grows to
|
|
16
|
+
`goto/16`, `goto/32`, or a reversed `if` around a `goto/32` when it does not
|
|
17
|
+
reach). So splitting a file, merging files, renaming classes and generating
|
|
18
|
+
code are ordinary edits followed by `write()`.
|
|
19
|
+
- `read()` / `read_file()`, `write()` / `write_file()`, `validate()` (the
|
|
20
|
+
rules of ART's DEX file verifier that apply, plus what the encoding needs),
|
|
21
|
+
`required_version()`, `pool_stats()` and `rename_types()` (every type
|
|
22
|
+
reference, including the class names inside generic signatures).
|
|
23
|
+
- Strings keep unpaired surrogates (as WTF-8), floats keep their exact bits,
|
|
24
|
+
and values keep their exact type (a `char` stays a `char`), so a file
|
|
25
|
+
survives a read and a write unchanged in meaning. Writing is deterministic,
|
|
26
|
+
and writing a re-read output gives the same bytes again.
|
|
27
|
+
- Checked on 776 DEX files from 253 real apps: all but one round-trip (the
|
|
28
|
+
exception is a corrupt file that ART also rejects), and ART's verifier
|
|
29
|
+
(through the SDK's `dexdump`) accepts every written file.
|
|
30
|
+
- Speed and memory on the largest of them (42 MB, 6.9M instructions): read in
|
|
31
|
+
0.6 s, write in 1.6 s; the model takes about 15 times the file size.
|
|
32
|
+
|
|
33
|
+
From Python and Go, the model works a whole class at a time. Building or
|
|
34
|
+
editing a class instruction by instruction stays in C++.
|
|
35
|
+
|
|
36
|
+
- Python: `dexpp.Model` reads a DEX file (`Model.read`, `Model.read_file`) or
|
|
37
|
+
starts empty (`Model(version)`). It lists and inspects classes
|
|
38
|
+
(`class_descriptors`, `class_info`, `class_interfaces`), copies, moves and
|
|
39
|
+
removes whole classes between models (`copy_class`, `move_class`,
|
|
40
|
+
`remove_class`), renames types (`rename_types`), and checks and writes the
|
|
41
|
+
result (`validate`, `pool_stats`, `required_version`, `write`,
|
|
42
|
+
`write_file`). Errors raise `FileNotFoundError` or `ValueError`.
|
|
43
|
+
- C and Go: `bindings/c/dexpp_model.h` gives the same operations on an opaque
|
|
44
|
+
`DexppModelDex` handle, and the Go package wraps them as `Model`
|
|
45
|
+
(`ReadModel`, `ReadModelFile`, `NewModel`, `CopyClass`, `MoveClass`,
|
|
46
|
+
`RemoveClass`, `RenameTypes`, `Validate`, `PoolStats`, `Write`, ...).
|
|
47
|
+
|
|
48
|
+
### Packaging
|
|
49
|
+
|
|
50
|
+
- dexpp is now on PyPI: `pip install dexpp`. The wheels are also still
|
|
51
|
+
attached to each GitHub release.
|
|
52
|
+
- dexpp now needs Python 3.14 or newer (breaking: 0.1.0 worked with 3.9 and
|
|
53
|
+
newer). The wheels are built for CPython 3.14 only.
|
|
54
|
+
|
|
55
|
+
### Smaller changes
|
|
56
|
+
|
|
57
|
+
- `MethodId`, `FieldId` (and their hashes), `AccessFlags` and
|
|
58
|
+
`AnnotationVisibility` moved to `src/common/`, so the analysis layer and
|
|
59
|
+
the model share them. Their names and namespace are unchanged, and the old
|
|
60
|
+
headers still work. `AccessFlags` gained `Bridge` and `Varargs`.
|
|
61
|
+
- `dex::raw` gained what writing needs: one opcode table for all 256 opcodes
|
|
62
|
+
with an instruction decoder and encoder (`raw/opcodes.hpp`; the analysis
|
|
63
|
+
decoder now uses it too), lossless MUTF-8 decoding and encoding
|
|
64
|
+
(`raw/mutf8.hpp`), name and descriptor rules (`raw/descriptors.hpp`),
|
|
65
|
+
SHA-1 / SHA-256 (`raw/digest.hpp`, moved from APK signing), a debug-info
|
|
66
|
+
parser (`parse_debug_info`), and a byte writer (`raw/byte_writer.hpp`).
|
|
67
|
+
- `raw::parser::compute_signature` is now implemented. `verify_offsets`, which
|
|
68
|
+
was declared but never implemented, is removed.
|
|
69
|
+
- `compute_checksum` is several times faster.
|
|
70
|
+
- The raw parser no longer negates `INT32_MIN` (undefined behavior) when a
|
|
71
|
+
catch handler declares that size.
|
|
72
|
+
|
|
73
|
+
### Call graph: virtual dispatch is stored once per method (breaking)
|
|
74
|
+
|
|
75
|
+
A virtual or interface call can reach every override of the called method in
|
|
76
|
+
the app. These possible targets depend only on the called method, but the
|
|
77
|
+
call graph used to store them again at every call site, as one edge per site
|
|
78
|
+
and per target. On large apps that came to tens or hundreds of millions of
|
|
79
|
+
edges, and on the largest (for example the Facebook APK, 164K classes) the
|
|
80
|
+
call graph ran out of memory.
|
|
81
|
+
|
|
82
|
+
They are now stored once per called method, and the graph is built with
|
|
83
|
+
integer ids instead of strings. It holds the same information, in far less
|
|
84
|
+
time and memory (building the call graph after loading the APK; peak memory
|
|
85
|
+
includes the loaded APK):
|
|
86
|
+
|
|
87
|
+
| App | Stored before | Stored now | Build time before → now | Peak memory before → now |
|
|
88
|
+
| --- | --- | --- | --- | --- |
|
|
89
|
+
| Facebook | 181M edges | 3.7M edges + 206K dispatch entries | ran out of memory → 0.54 s | over 10.9 GB → 1.05 GB |
|
|
90
|
+
| GitHub | 89M edges | 0.76M edges + 74K dispatch entries | 4.4 s → 0.13 s | 5.8 GB → 0.21 GB |
|
|
91
|
+
| Instagram | 89M edges | 2.3M edges + 168K dispatch entries | 8.0 s → 0.36 s | 5.9 GB → 0.68 GB |
|
|
92
|
+
| YouTube | 31M edges | 1.4M edges + 105K dispatch entries | 3.9 s → 0.23 s | 2.8 GB → 0.46 GB |
|
|
93
|
+
|
|
94
|
+
Building the call graph also no longer decodes every instruction into the
|
|
95
|
+
context's instruction cache, and no longer builds the class hierarchy.
|
|
96
|
+
|
|
97
|
+
For an app split over several large DEX files, part of the build runs on one
|
|
98
|
+
thread per DEX file. `ApkLoadOptions::threads` (Python: `from_apk(threads=...)`)
|
|
99
|
+
now also sets these threads: `1` keeps the whole build on the calling thread.
|
|
100
|
+
The result never depends on the number of threads.
|
|
101
|
+
|
|
102
|
+
API changes, in C++ (`dex::CallGraph`) and Python (`dexpp.CallGraph`):
|
|
103
|
+
|
|
104
|
+
- `edges()` holds one `Declared` edge per call site, plus the
|
|
105
|
+
`InheritedResolution` edge when there is one. `EdgeOrigin::ChaOverride`
|
|
106
|
+
(`EdgeOrigin.CHA_OVERRIDE`) is removed.
|
|
107
|
+
- `dispatch_targets(node)` lists the overrides a virtual or interface call to
|
|
108
|
+
that method may reach, and `dispatch_sources(node)` is the reverse.
|
|
109
|
+
`dispatch_targets(edge)` gives the targets that apply at one call site (empty
|
|
110
|
+
for super, direct and static calls). Python: `CallNode.dispatch_targets`,
|
|
111
|
+
`CallNode.dispatch_sources`, `CallEdge.dispatch_targets`.
|
|
112
|
+
- `callees(node)` and `callers(node)` list every method a method may call, or
|
|
113
|
+
be called by, with virtual dispatch included. Python: `CallNode.callees`,
|
|
114
|
+
`CallNode.callers`.
|
|
115
|
+
- `CallNode.outgoing` / `incoming` (and `out_edges` / `in_edges` in Python) no
|
|
116
|
+
longer include dispatch targets. Use `callees` / `callers` for those.
|
|
117
|
+
- The deprecated Python property `CallEdge.via_override` is removed.
|
|
118
|
+
|
|
119
|
+
## 0.1.0 — first release
|
|
120
|
+
|
|
121
|
+
The first public release. The API is still alpha: it may change in later
|
|
122
|
+
0.x releases.
|
|
123
|
+
|
|
124
|
+
### APK metadata (`dex::apk` / `dexpp.Apk`)
|
|
125
|
+
|
|
126
|
+
- Archive listing and entry extraction (stored and deflate entries; no ZIP64).
|
|
127
|
+
- Binary `AndroidManifest.xml` decoding: package, version, SDK levels,
|
|
128
|
+
permissions, declared permissions and their protection levels, components
|
|
129
|
+
with their exported / intent-filter / permission attributes, launcher
|
|
130
|
+
activity, `debuggable`, `allowBackup`.
|
|
131
|
+
- `Component.is_reachable`: exported and not gated behind an app-declared
|
|
132
|
+
`signature` permission.
|
|
133
|
+
- `resources.arsc` decoding: string resolution, resource names, reverse
|
|
134
|
+
lookup.
|
|
135
|
+
- Signing scheme detection (v1, v2, v3/v3.1) and X.509 certificate details
|
|
136
|
+
with SHA-1 / SHA-256 fingerprints. Signatures are identified, not verified.
|
|
137
|
+
|
|
138
|
+
### Code analysis (`dex` / `dexpp.AnalysisContext`)
|
|
139
|
+
|
|
140
|
+
- Load a single DEX, several DEX files, or every `classes*.dex` of an APK.
|
|
141
|
+
Loading is lazy: the file is memory-mapped and only what a query touches is
|
|
142
|
+
decoded. Multidex APKs are decompressed in parallel.
|
|
143
|
+
- Classes, methods, fields, access flags, annotations, and static field
|
|
144
|
+
initial values.
|
|
145
|
+
- Decoded bytecode with mnemonics, try/catch blocks, register frames, and a
|
|
146
|
+
control-flow graph per method.
|
|
147
|
+
- Per-method forward references: calls, field accesses, string loads, type
|
|
148
|
+
uses.
|
|
149
|
+
- Whole-program call graph with class-hierarchy-aware virtual dispatch, a
|
|
150
|
+
class hierarchy, and a cross-reference index (who calls / reads / writes /
|
|
151
|
+
loads what).
|
|
152
|
+
|
|
153
|
+
### Python bindings
|
|
154
|
+
|
|
155
|
+
- One extension module with type stubs (`mypy` and `pyright`).
|
|
156
|
+
- The call graph, xrefs, and CFG tables are zero-copy views; call-graph nodes
|
|
157
|
+
and edges can be navigated directly.
|
|
158
|
+
- `dexpp.__version__`.
|
|
159
|
+
|
|
160
|
+
### Packaging
|
|
161
|
+
|
|
162
|
+
- Prebuilt wheels for Linux x86_64 (glibc and musl), attached to the GitHub
|
|
163
|
+
release. The C++ library and the C / Go bindings are source-only
|
|
164
|
+
for now.
|
|
165
|
+
- No system dependencies: DEFLATE decoding uses libdeflate, compiled in.
|
|
166
|
+
|
|
167
|
+
### Robustness
|
|
168
|
+
|
|
169
|
+
- The parsers are hardened against malformed and hostile input (bounds
|
|
170
|
+
checks, allocation limits against oversized counts and zip bombs).
|
|
@@ -0,0 +1,160 @@
|
|
|
1
|
+
cmake_minimum_required(VERSION 3.18)
|
|
2
|
+
|
|
3
|
+
# The version lives in src/version.hpp (shared with the Python package metadata).
|
|
4
|
+
file(STRINGS src/version.hpp DEXPP_VERSION_LINE REGEX "^#define DEXPP_VERSION \"")
|
|
5
|
+
string(REGEX REPLACE "^#define DEXPP_VERSION \"([^\"]+)\".*" "\\1" DEXPP_VERSION "${DEXPP_VERSION_LINE}")
|
|
6
|
+
project(dex++ VERSION ${DEXPP_VERSION})
|
|
7
|
+
|
|
8
|
+
set(CMAKE_CXX_STANDARD 23)
|
|
9
|
+
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
|
10
|
+
|
|
11
|
+
option(DEXPP_BUILD_PYTHON "Build the dexpp Python extension module" OFF)
|
|
12
|
+
option(DEXPP_BUILD_TESTS "Build the unit tests and demo CLI" ON)
|
|
13
|
+
option(DEXPP_BUILD_C "Build the C ABI shim (bindings/c, for Go/cgo and other FFI)" ON)
|
|
14
|
+
set(DEXPP_SANITIZE "" CACHE STRING
|
|
15
|
+
"Sanitizers to build everything with, e.g. 'address,undefined' (empty = off)")
|
|
16
|
+
|
|
17
|
+
# SKBUILD is set by scikit-build-core during `pip install` / wheel builds:
|
|
18
|
+
# build only the Python module there, no tests, demo CLI, or C shim.
|
|
19
|
+
if(SKBUILD)
|
|
20
|
+
set(DEXPP_BUILD_PYTHON ON)
|
|
21
|
+
set(DEXPP_BUILD_TESTS OFF)
|
|
22
|
+
set(DEXPP_BUILD_C OFF)
|
|
23
|
+
endif()
|
|
24
|
+
|
|
25
|
+
# Sanitizer instrumentation is applied directory-wide (before any target is
|
|
26
|
+
# declared) so the library and the fetched test frameworks are built
|
|
27
|
+
# consistently.
|
|
28
|
+
if(DEXPP_SANITIZE)
|
|
29
|
+
add_compile_options(-fsanitize=${DEXPP_SANITIZE}
|
|
30
|
+
-fno-sanitize-recover=all -fno-omit-frame-pointer -g)
|
|
31
|
+
add_link_options(-fsanitize=${DEXPP_SANITIZE})
|
|
32
|
+
endif()
|
|
33
|
+
|
|
34
|
+
include(FetchContent)
|
|
35
|
+
|
|
36
|
+
# libdeflate decompresses the APK's DEX entries. Its decompression sources are
|
|
37
|
+
# compiled straight into dexpp_core rather than linked as a separate library, so
|
|
38
|
+
# libdexpp_core.a stays self-contained: the Go static link and the Python wheel
|
|
39
|
+
# need no extra system library. SOURCE_SUBDIR points at a directory with no
|
|
40
|
+
# CMakeLists.txt so libdeflate's own build (and its targets) is never added.
|
|
41
|
+
FetchContent_Declare(
|
|
42
|
+
libdeflate
|
|
43
|
+
URL https://github.com/ebiggers/libdeflate/archive/refs/tags/v1.26.tar.gz
|
|
44
|
+
URL_HASH SHA256=bba03fffc5538576213675ce6968fcff6ce2e67d82e4d5febea2d05f9f13cf85
|
|
45
|
+
SOURCE_SUBDIR not-a-cmake-project
|
|
46
|
+
)
|
|
47
|
+
FetchContent_MakeAvailable(libdeflate)
|
|
48
|
+
set(LIBDEFLATE_SOURCES
|
|
49
|
+
${libdeflate_SOURCE_DIR}/lib/deflate_decompress.c
|
|
50
|
+
${libdeflate_SOURCE_DIR}/lib/utils.c
|
|
51
|
+
${libdeflate_SOURCE_DIR}/lib/x86/cpu_features.c
|
|
52
|
+
${libdeflate_SOURCE_DIR}/lib/arm/cpu_features.c
|
|
53
|
+
)
|
|
54
|
+
set_source_files_properties(${LIBDEFLATE_SOURCES} PROPERTIES COMPILE_OPTIONS "-std=c11")
|
|
55
|
+
|
|
56
|
+
add_library(dexpp_core STATIC
|
|
57
|
+
src/common/ids.cpp
|
|
58
|
+
src/raw/error.cpp
|
|
59
|
+
src/raw/parser.cpp
|
|
60
|
+
src/raw/types.cpp
|
|
61
|
+
src/raw/parsing_utils.cpp
|
|
62
|
+
src/raw/zip.cpp
|
|
63
|
+
src/raw/mutf8.cpp
|
|
64
|
+
src/raw/descriptors.cpp
|
|
65
|
+
src/raw/digest.cpp
|
|
66
|
+
src/raw/opcodes.cpp
|
|
67
|
+
src/model/types.cpp
|
|
68
|
+
src/model/read.cpp
|
|
69
|
+
src/model/write.cpp
|
|
70
|
+
src/model/validate.cpp
|
|
71
|
+
src/model/rename.cpp
|
|
72
|
+
src/analysis/analysis_context.cpp
|
|
73
|
+
src/analysis/class.cpp
|
|
74
|
+
src/analysis/class_ref.cpp
|
|
75
|
+
src/analysis/method.cpp
|
|
76
|
+
src/analysis/field.cpp
|
|
77
|
+
src/analysis/type_descriptor.cpp
|
|
78
|
+
src/analysis/instruction.cpp
|
|
79
|
+
src/analysis/cfg.cpp
|
|
80
|
+
src/analysis/call_graph.cpp
|
|
81
|
+
src/analysis/class_hierarchy.cpp
|
|
82
|
+
src/analysis/xrefs.cpp
|
|
83
|
+
src/analysis/annotations.cpp
|
|
84
|
+
src/apk/string_pool.cpp
|
|
85
|
+
src/apk/axml.cpp
|
|
86
|
+
src/apk/resources.cpp
|
|
87
|
+
src/apk/manifest.cpp
|
|
88
|
+
src/apk/signing.cpp
|
|
89
|
+
src/apk/apk.cpp
|
|
90
|
+
${LIBDEFLATE_SOURCES}
|
|
91
|
+
)
|
|
92
|
+
|
|
93
|
+
target_include_directories(dexpp_core PUBLIC src)
|
|
94
|
+
target_include_directories(dexpp_core PRIVATE ${libdeflate_SOURCE_DIR})
|
|
95
|
+
# Required for linking into the Python shared module.
|
|
96
|
+
set_target_properties(dexpp_core PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
|
97
|
+
|
|
98
|
+
# C ABI shim: a static library (libdexpp_c.a) exposing bindings/c/dexpp.h, for
|
|
99
|
+
# consumers that speak C rather than C++ (e.g. Go via cgo). Bundles dexpp_core.
|
|
100
|
+
if(DEXPP_BUILD_C)
|
|
101
|
+
add_library(dexpp_c STATIC bindings/c/dexpp_c.cpp bindings/c/dexpp_model.cpp)
|
|
102
|
+
target_include_directories(dexpp_c PUBLIC bindings/c)
|
|
103
|
+
target_link_libraries(dexpp_c PUBLIC dexpp_core)
|
|
104
|
+
set_target_properties(dexpp_c PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
|
105
|
+
endif()
|
|
106
|
+
|
|
107
|
+
if(DEXPP_BUILD_TESTS)
|
|
108
|
+
FetchContent_Declare(
|
|
109
|
+
googletest
|
|
110
|
+
URL https://github.com/google/googletest/archive/52eb8108c5bdec04579160ae17225d66034bd723.zip
|
|
111
|
+
)
|
|
112
|
+
FetchContent_MakeAvailable(googletest)
|
|
113
|
+
|
|
114
|
+
add_executable(main_test
|
|
115
|
+
src/main.cpp
|
|
116
|
+
)
|
|
117
|
+
|
|
118
|
+
target_link_libraries(main_test PRIVATE dexpp_core)
|
|
119
|
+
|
|
120
|
+
enable_testing()
|
|
121
|
+
|
|
122
|
+
file(GLOB_RECURSE TEST_SOURCES
|
|
123
|
+
tests/*.cc
|
|
124
|
+
)
|
|
125
|
+
|
|
126
|
+
add_executable(unit_tests
|
|
127
|
+
${TEST_SOURCES}
|
|
128
|
+
)
|
|
129
|
+
|
|
130
|
+
target_link_libraries(unit_tests
|
|
131
|
+
dexpp_core
|
|
132
|
+
GTest::gtest_main
|
|
133
|
+
)
|
|
134
|
+
|
|
135
|
+
include(GoogleTest)
|
|
136
|
+
gtest_discover_tests(unit_tests WORKING_DIRECTORY ${CMAKE_SOURCE_DIR})
|
|
137
|
+
endif()
|
|
138
|
+
|
|
139
|
+
if(DEXPP_BUILD_PYTHON)
|
|
140
|
+
FetchContent_Declare(
|
|
141
|
+
pybind11
|
|
142
|
+
URL https://github.com/pybind/pybind11/archive/refs/tags/v2.13.6.zip
|
|
143
|
+
)
|
|
144
|
+
FetchContent_MakeAvailable(pybind11)
|
|
145
|
+
|
|
146
|
+
pybind11_add_module(dexpp bindings/python/dexpp_module.cpp bindings/python/dexpp_model_py.cpp)
|
|
147
|
+
target_link_libraries(dexpp PRIVATE dexpp_core)
|
|
148
|
+
|
|
149
|
+
if(SKBUILD)
|
|
150
|
+
install(TARGETS dexpp DESTINATION .)
|
|
151
|
+
# Both stub layouts: a sibling .pyi (pyright) and a PEP 561 stub-only
|
|
152
|
+
# package (mypy).
|
|
153
|
+
install(FILES bindings/python/dexpp.pyi DESTINATION .)
|
|
154
|
+
install(FILES bindings/python/dexpp.pyi DESTINATION dexpp-stubs RENAME __init__.pyi)
|
|
155
|
+
# libdeflate is built into the module; its MIT license ships in the
|
|
156
|
+
# wheel's .dist-info/licenses directory.
|
|
157
|
+
install(FILES ${libdeflate_SOURCE_DIR}/COPYING
|
|
158
|
+
DESTINATION ${SKBUILD_METADATA_DIR}/licenses RENAME libdeflate-COPYING)
|
|
159
|
+
endif()
|
|
160
|
+
endif()
|
dexpp-0.2.0/LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|