feat(processing/cli): added cli option to skip extraction (-s/--skip-extraction) along with matching functionality

Author: dorpvom

unblob/cli.py

@@ -151,6 +151,14 @@ def __init__(
     type=click.Path(path_type=Path),
     help="File to store metadata generated during the extraction process (in JSON format).",
 )
+@click.option(
+    "-s",
+    "--skip_extraction",
+    "skip_extraction",
+    is_flag=True,
+    show_default=True,
+    help="Only carve chunks and skip further extraction",
+)
 @click.option(
     "-k",
     "--keep-extracted-chunks",
@@ -176,6 +184,7 @@ def cli(
     depth: int,
     entropy_depth: int,
     skip_magic: Iterable[str],
+    skip_extraction: bool,
     keep_extracted_chunks: bool,
     handlers: Handlers,
     plugins_path: Optional[Path],
@@ -194,6 +203,7 @@ def cli(
         max_depth=depth,
         entropy_depth=entropy_depth,
         entropy_plot=bool(verbose >= 3),
+        skip_extraction=skip_extraction,
         skip_magic=skip_magic,
         process_num=process_num,
         handlers=handlers,

unblob/processing.py

@@ -80,6 +80,7 @@ class ExtractionConfig:
     entropy_plot: bool = False
     max_depth: int = DEFAULT_DEPTH
     skip_magic: Iterable[str] = DEFAULT_SKIP_MAGIC
+    skip_extraction: bool = False
     process_num: int = DEFAULT_PROCESS_NUM
     keep_extracted_chunks: bool = False
     extract_suffix: str = "_extract"
@@ -374,6 +375,10 @@ def _extract_chunk(self, file, chunk: ValidChunk):
             extract_dir = self.carve_dir / (inpath.name + self.config.extract_suffix)
             carved_path = inpath
 
+        if self.config.skip_extraction:
+            fix_extracted_directory(extract_dir, self.result)
+            return
+
         extraction_reports = []
         try:
             chunk.extract(inpath, extract_dir)