Merge pull request #171 from Zeecka/worker/file

Fix #158 - Add FileAnalyzer, remove old image_resize artefacts, update foremost …

README.md

@@ -45,6 +45,7 @@ Aperi'Solve is an open-source steganalysis web platform that performs automated
   - [steghide](https://steghide.sourceforge.net/) (extraction with password)
   - [strings](https://pubs.opengroup.org/onlinepubs/9799919799/utilities/strings.html)
   - [zsteg](https://github.com/zed-0xff/zsteg) (LSB text/data extraction)
+  - [file](https://www.darwinsys.com/file/) (MIME type and format detection)
 - Worker queue architecture for offloading heavy/slow analyzers (Redis + background workers).
 - Results stored for later browsing and download.
 

aperisolve/analyzers/file.py

@@ -0,0 +1,25 @@
+# flake8: noqa: E203,E501,W503
+# pylint: disable=C0413,W0718,R0903,R0801
+# mypy: disable-error-code=unused-awaitable
+"""File Analyzer for Image Submissions."""
+from pathlib import Path
+
+from .base_analyzer import SubprocessAnalyzer
+
+
+class FileAnalyzer(SubprocessAnalyzer):
+    """Analyzer for the `file` command."""
+
+    def __init__(self, input_img: Path, output_dir: Path) -> None:
+        super().__init__("file", input_img, output_dir)
+        self.cmd = ["file", "-b", self.img]
+
+    def process_output(self, stdout: str, stderr: str) -> str | list[str] | dict[str, str]:
+        """Process the stdout into a list of lines."""
+        return stdout
+
+
+def analyze_file(input_img: Path, output_dir: Path) -> None:
+    """Analyze an image submission using `file`."""
+    analyzer = FileAnalyzer(input_img, output_dir)
+    analyzer.analyze()

aperisolve/analyzers/foremost.py

@@ -22,7 +22,7 @@ class ForemostAnalyzer(SubprocessAnalyzer):
     def process_output(self, stdout: str, stderr: str) -> str | list[str] | dict[str, str]:
         """Process the stdout/stderr."""
         if "Processing" in stderr and "|*|" in stderr:
-            return stderr.strip().split("\n")
+            return stderr.strip().replace("\n", "")
         return []
 
 

aperisolve/config.py

@@ -7,7 +7,7 @@ from os import getenv
 from pathlib import Path
 
 IMAGE_EXTENSIONS = [".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp", ".tiff"]
-WORKER_FILES = ["binwalk", "foremost", "steghide", "zsteg", "image_resize", "openstego", "pcrt"]
+WORKER_FILES = ["binwalk", "foremost", "steghide", "zsteg", "openstego", "pcrt"]
 
 RESULT_FOLDER = Path(__file__).parent.resolve() / "results"
 REMOVED_IMAGES_FOLDER = Path(__file__).parent.resolve() / "removed_images"

aperisolve/static/js/aperisolve.js

@@ -1,5 +1,6 @@
 const TOOL_ORDER = [
   "decomposer",
+  "file",
   "exiftool",
   "binwalk",
   "foremost",
@@ -9,7 +10,7 @@ const TOOL_ORDER = [
   "steghide",
   "openstego",
   "zsteg",
-  "strings",
+  "strings"
 ];
 
 function escapeHtml(text) {

aperisolve/workers.py

@@ -16,6 +16,7 @@ initialize_sentry()
 from .analyzers.binwalk import analyze_binwalk  # pylint: disable=C0413
 from .analyzers.decomposer import analyze_decomposer
 from .analyzers.exiftool import analyze_exiftool
+from .analyzers.file import analyze_file
 from .analyzers.foremost import analyze_foremost
 from .analyzers.openstego import analyze_openstego
 from .analyzers.outguess import analyze_outguess
@@ -103,6 +104,7 @@ def analyze_image(submission_hash: str) -> None:
                 (analyze_binwalk, img_path, result_path),
                 (analyze_decomposer, img_path, result_path),
                 (analyze_exiftool, img_path, result_path),
+                (analyze_file, img_path, result_path),
                 (analyze_foremost, img_path, result_path),
                 (analyze_openstego, img_path, result_path, submission.password),
                 (analyze_pngcheck, img_path, result_path),

docs/adding-analyzer.md

@@ -146,6 +146,7 @@ And also in `aperisolve.js` in the `TOOL_ORDER` constant:
 ```js
 const TOOL_ORDER = [
   "decomposer",
+  "file",
   "exiftool",
   "binwalk",
   "mytool"  // My new tool
@@ -157,7 +158,6 @@ const TOOL_ORDER = [
   "openstego",
   "zsteg",
   "strings",
-  "image_resize",
 ];
 ```