Merge branch 'main' into refactor-binexport-launching

Author: RobinDavid

.gitattributes

@@ -0,0 +1 @@
+tests/data/** filter=lfs diff=lfs merge=lfs -text

.github/dependabot.yml

@@ -0,0 +1,24 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    groups:
+      python:
+        patterns:
+          - "*"
+    schedule:
+      interval: "daily"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    groups:
+      python:
+        patterns:
+          - "*"
+    schedule:
+      interval: "daily"

.github/workflows/release.yml

@@ -10,15 +10,15 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
         with:
           python-version: '3.10'
       - name: Install dependencies
         run: pip install build
       - name: Build wheel and sdist
         run: python -m build
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: artifact
           path: |
@@ -29,20 +29,20 @@ jobs:
     needs: build_wheel_and_sdist
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v6
         with:
           # unpacks default artifact into dist/
           # if `name: artifact` is omitted, the action will create extra parent dir
           name: artifact
           path: dist
 
       - name: Publish a Python distribution to PyPI
-        uses: pypa/gh-action-pypi-publish@v1.8.2
+        uses: pypa/gh-action-pypi-publish@v1.13.0
         with:
           password: ${{ secrets.PYPI_DEPLOY_TOKEN }}
 
       - name: Upload Python packages for release notes
-        uses: softprops/action-gh-release@v0.1.15
+        uses: softprops/action-gh-release@v2.5.0
         with:
           files: |
             dist/*

.github/workflows/testing.yml

@@ -0,0 +1,37 @@
+name: Testing
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  testing:
+    name: Run tests
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          lfs: true
+      - uses: actions/setup-python@v6
+        with:
+          python-version: |
+            3.11
+            3.12
+            3.10
+
+      - name: Install dependencies
+        run: pip install .[dev]
+
+      - name: Running pytest
+        run: tox run -- -s
+
+      - name: Generate coverage
+        run: tox run -e py310-coverage -- -s --cov-report=term
+
+      - uses: actions/upload-artifact@v5
+        with:
+          name: coverage
+          path: ./htmlcov

.gitignore

@@ -8,3 +8,6 @@ build/
 dist/
 *.egg-info/
 /venv/
+.tox/
+.coverage
+htmlcov/

pyproject.toml

@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "python-binexport"
-version = "0.3.6"
+version = "0.4.0"
 description = "Python wrapper to manipulate binexport files (protobuf)"
 readme = { file = "README.md", content-type = "text/markdown" }
 authors = [{ name = "Quarkslab", email = "diffing@quarkslab.com" }]
 license = {text = "AGPL-3.0"}
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dependencies = [
     "python-magic; os_name!='nt'",
     "python-magic-bin; os_name=='nt'",
@@ -34,6 +34,9 @@ Documentation = "https://quarkslab.github.io/diffing-portal/exporter/binexport.h
 [project.scripts]
 binexporter = 'binexport.__main__:main'
 
+[project.optional-dependencies]
+dev = ["tox"]
+
 [tool.black]
 line-length = 100
 target-version = ['py310']

src/binexport/basic_block.py

@@ -88,6 +88,36 @@ def function(self) -> FunctionBinExport:
         """
         return self._function()
 
+    @cached_property
+    def contiguous_ranges(self) -> list[tuple[Addr, bytes]]:
+        """
+        The contiguous ranges of instructions contained in this basic block. That identifies
+        the *real* basic blocks, as BinExport's basic blocks do not necessarily represent a
+        contiguous block of instructions.
+
+        :return: List of tuples (begin address, bytes), each of them representing a contiguous
+                 block of instructions.
+        """
+
+        ranges = []
+
+        # Ranges are in fact the true basic blocks but BinExport
+        # doesn't have the same basic block semantic and merge multiple basic blocks into one.
+        # For example: BB_1 -- unconditional_jmp --> BB_2
+        # might be merged into a single basic block so the edge gets lost.
+        for rng in self.pb_bb.instruction_index:
+            rng_bytes = b""
+            rng_addr = None
+            for idx in instruction_index_range(rng):
+                rng_bytes += self.program.proto.instruction[idx].raw_bytes
+
+                # The first instruction determines the basic block address
+                if rng_addr is None:
+                    rng_addr = get_instruction_address(self.program.proto, idx)
+            ranges.append((rng_addr, rng_bytes))
+
+        return ranges
+
     @cached_property
     def instructions(self) -> dict[Addr, InstructionBinExport]:
         """

src/binexport/instruction.py

@@ -36,6 +36,7 @@ def __init__(
         self._idx = i_idx
         self.data_refs: set[Addr] = self.program.data_refs[self._idx]  #: Data references address
         self.bytes = self.pb_instr.raw_bytes  #: bytes of the instruction (opcodes)
+        self.disasm = f"{self.mnemonic} {', '.join(str(o) for o in self.operands)}"
 
     def __hash__(self) -> int:
         return hash(self.addr)