feat(ui): display scan report when extraction is skipped.

Co-authored-by: Krisztián Fekete <[email protected]>

Author: qkaiser

unblob/cli.py

@@ -8,12 +8,18 @@
 import click
 from rich.console import Console
 from rich.panel import Panel
+from rich.style import Style
 from rich.table import Table
 from structlog import get_logger
 
 from unblob.models import DirectoryHandlers, Handlers, ProcessResult
 from unblob.plugins import UnblobPluginManager
-from unblob.report import ChunkReport, Severity, StatReport, UnknownChunkReport
+from unblob.report import (
+    ChunkReport,
+    Severity,
+    StatReport,
+    UnknownChunkReport,
+)
 
 from .cli_options import verbosity_option
 from .dependencies import get_dependencies, pretty_format_dependencies
@@ -279,7 +285,10 @@ def cli(
     logger.info("Start processing file", file=file)
     process_results = process_file(config, file, report_file)
     if verbose == 0:
-        print_report(process_results)
+        if skip_extraction:
+            print_scan_report(process_results)
+        else:
+            print_report(process_results)
     return process_results
 
 
@@ -349,6 +358,50 @@ def get_size_report(task_results: List) -> Tuple[int, int, int, int]:
     return total_files, total_dirs, total_links, extracted_size
 
 
+def print_scan_report(reports: ProcessResult):
+    console = Console(stderr=True)
+
+    chunks_offset_table = Table(
+        expand=False,
+        show_lines=True,
+        show_edge=True,
+        style=Style(color="white"),
+        header_style=Style(color="white"),
+        row_styles=[Style(color="red")],
+    )
+    chunks_offset_table.add_column("Start offset")
+    chunks_offset_table.add_column("End offset")
+    chunks_offset_table.add_column("Size")
+    chunks_offset_table.add_column("Description")
+
+    for task_result in reports.results:
+        chunk_reports = [
+            report
+            for report in task_result.reports
+            if isinstance(report, (ChunkReport, UnknownChunkReport))
+        ]
+        chunk_reports.sort(key=lambda x: x.start_offset)
+
+        for chunk_report in chunk_reports:
+            if isinstance(chunk_report, ChunkReport):
+                chunks_offset_table.add_row(
+                    f"{chunk_report.start_offset:0d}",
+                    f"{chunk_report.end_offset:0d}",
+                    human_size(chunk_report.size),
+                    chunk_report.handler_name,
+                    style=Style(color="#00FFC8"),
+                )
+            if isinstance(chunk_report, UnknownChunkReport):
+                chunks_offset_table.add_row(
+                    f"{chunk_report.start_offset:0d}",
+                    f"{chunk_report.end_offset:0d}",
+                    human_size(chunk_report.size),
+                    "unknown",
+                    style=Style(color="#008ED5"),
+                )
+    console.print(chunks_offset_table)
+
+
 def print_report(reports: ProcessResult):
     total_files, total_dirs, total_links, extracted_size = get_size_report(
         reports.results

unblob/processing.py

@@ -476,7 +476,7 @@ def __init__(
     def process(self):
         logger.debug("Processing file", path=self.task.path, size=self.size)
 
-        if not self.config.skip_extraction and self.carve_dir.exists():
+        if self.carve_dir.exists() and not self.config.skip_extraction:
             # Extraction directory is not supposed to exist, it is usually a simple mistake of running
             # unblob again without cleaning up or using --force.
             # It would cause problems continuing, as it would mix up original and extracted files,