archae 2026.2.1__tar.gz → 2026.3__tar.gz

{archae-2026.2.1 → archae-2026.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: archae
-Version: 2026.2.1
+Version: 2026.3
 Summary: Archae explodes archives.
 Keywords: 
 Author: Shawn McNaughton
@@ -73,8 +73,8 @@ Archae explodes archives.
 Every once and a while, I run into an issue: multiple layers of archives. The reasons vary, but examples would include:
 
 - Searching for something in a ZIP of folders that contained a ZIP with a CD image in it
-- Running a malware scan and finding an obscure archive format was missed and not even flagged
-  Meanwhile, I want to make sure I don't fill my disk, especially if an archive bomb (more commonly known as a ZIP bomb) has been jammed in somewhere. They're only funny the first time. :D
+- Running a malware scan and finding an obscure archive format was missed and not even flagged.
+- Meanwhile, I want to make sure I don't fill my disk, especially if an archive bomb (more commonly known as a ZIP bomb) has been jammed in somewhere. They're only funny the first time. :D
 
 ## Features
 
@@ -88,6 +88,7 @@ Every once and a while, I run into an issue: multiple layers of archives. The re
     - MIN_ARCHIVE_RATIO - ensures very-high-compression-ratio archives are stopped
     - MIN_DISK_FREE_SPACE - minimum free space at the extraction location
     - MAX_DEPTH - allow setting a maximum archive depth to traverse
+    - DELETE_ARCHIVES_AFTER_EXTRACTION - delete pure archive types after deletion
 
 ## Installation
 

{archae-2026.2.1 → archae-2026.3}/README.md

@@ -20,8 +20,8 @@ Archae explodes archives.
 Every once and a while, I run into an issue: multiple layers of archives. The reasons vary, but examples would include:
 
 - Searching for something in a ZIP of folders that contained a ZIP with a CD image in it
-- Running a malware scan and finding an obscure archive format was missed and not even flagged
-  Meanwhile, I want to make sure I don't fill my disk, especially if an archive bomb (more commonly known as a ZIP bomb) has been jammed in somewhere. They're only funny the first time. :D
+- Running a malware scan and finding an obscure archive format was missed and not even flagged.
+- Meanwhile, I want to make sure I don't fill my disk, especially if an archive bomb (more commonly known as a ZIP bomb) has been jammed in somewhere. They're only funny the first time. :D
 
 ## Features
 
@@ -35,6 +35,7 @@ Every once and a while, I run into an issue: multiple layers of archives. The re
     - MIN_ARCHIVE_RATIO - ensures very-high-compression-ratio archives are stopped
     - MIN_DISK_FREE_SPACE - minimum free space at the extraction location
     - MAX_DEPTH - allow setting a maximum archive depth to traverse
+    - DELETE_ARCHIVES_AFTER_EXTRACTION - delete pure archive types after deletion
 
 ## Installation
 

{archae-2026.2.1 → archae-2026.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "archae"
-version = "2026.2.1"
+version = "2026.3"
 description = "Archae explodes archives."
 authors = [{name = "Shawn McNaughton", email = "shawngmc@gmail.com"}]
 readme = "README.md"

{archae-2026.2.1 → archae-2026.3}/src/archae/config.py

@@ -1,5 +1,6 @@
 """Runtime config management (default, userconfig and envvars)."""
 
+import ast
 import importlib
 import typing
 from pathlib import Path
@@ -66,6 +67,8 @@ def get_converter(converter_def: str) -> typing.Callable:
         return float
     if converter_def == "int":
         return int
+    if converter_def == "bool":
+        return ast.literal_eval
 
     # Split the definition into module path and class name
     module_name, class_name = converter_def.split(":")

{archae-2026.2.1 → archae-2026.3}/src/archae/default_settings.toml

@@ -7,3 +7,4 @@ MAX_ARCHIVE_SIZE_BYTES = "10G"
 MIN_ARCHIVE_RATIO = 0.005
 MIN_DISK_FREE_SPACE = "10G"
 MAX_DEPTH=0
+DELETE_ARCHIVES_AFTER_EXTRACTION="False"

{archae-2026.2.1 → archae-2026.3}/src/archae/extractor.py

@@ -17,6 +17,7 @@ if TYPE_CHECKING:
     from pathlib import Path
 
     from archae.util.archiver.base_archiver import BaseArchiver
+from archae.util.lists import skip_delete_extensions, skip_delete_mimetypes
 
 
 class WarningAccumulator(logging.Handler):
@@ -79,75 +80,75 @@ class ArchiveExtractor:
         file_size_bytes = file_path.stat().st_size
         self.file_tracker.track_file(base_hash, file_size_bytes)
         self.file_tracker.track_file_path(base_hash, file_path)
-        self.file_tracker.add_metadata_to_hash(
-            base_hash, "type", magic.from_file(file_path)
-        )
-        self.file_tracker.add_metadata_to_hash(
+        self.file_tracker.add_metadata(base_hash, "type", magic.from_file(file_path))
+        self.file_tracker.add_metadata(
             base_hash, "type_mime", magic.from_file(file_path, mime=True)
         )
         extension = file_path.suffix.lstrip(".").lower()
-        self.file_tracker.add_metadata_to_hash(base_hash, "extension", extension)
+        self.file_tracker.add_metadata(base_hash, "extension", extension)
         is_file_archive = self._is_archive(base_hash)
-        self.file_tracker.add_metadata_to_hash(base_hash, "is_archive", is_file_archive)
+        self.file_tracker.add_metadata(base_hash, "is_archive", is_file_archive)
         if is_file_archive:
             settings_dict = get_settings()
             if settings_dict["MAX_DEPTH"] == 0 or depth < settings_dict["MAX_DEPTH"]:
                 archiver = self._get_archiver_for_file(base_hash)
-                if archiver:
-                    extracted_size = archiver.get_archive_uncompressed_size(file_path)
-                    self.file_tracker.add_metadata_to_hash(
-                        base_hash, "extracted_size", extracted_size
+                if not archiver:
+                    logger.warning(
+                        "NO_ARCHIVER: No suitable archiver found for file: %s",
+                        file_path,
                     )
-                    compression_ratio = extracted_size / file_size_bytes
-                    self.file_tracker.add_metadata_to_hash(
-                        base_hash, "overall_compression_ratio", compression_ratio
+                    return
+
+                try:
+                    extracted_size = archiver.get_archive_uncompressed_size(file_path)
+                except RuntimeError as e:
+                    logger.warning(
+                        "SIZE_RETRIEVAL_FAILED: Could not retrieve size for archive %s: %s",
+                        file_path,
+                        str(e),
                     )
-                    if extracted_size > settings_dict["MAX_ARCHIVE_SIZE_BYTES"]:
-                        logger.warning(
-                            "MAX_ARCHIVE_SIZE_BYTES: Skipped archive %s because expected size %s is greater than MAX_ARCHIVE_SIZE_BYTES %s",
-                            file_path,
-                            extracted_size,
-                            settings_dict["MAX_ARCHIVE_SIZE_BYTES"],
-                        )
-                    elif (
-                        self.file_tracker.get_tracked_file_size() + extracted_size
-                        > settings_dict["MAX_TOTAL_SIZE_BYTES"]
-                    ):
-                        logger.warning(
-                            "MAX_TOTAL_SIZE_BYTES: Skipped archive %s because expected size %s + current tracked files %s is greater than MAX_TOTAL_SIZE_BYTES %s",
-                            file_path,
-                            extracted_size,
-                            self.file_tracker.get_tracked_file_size(),
-                            settings_dict["MAX_TOTAL_SIZE_BYTES"],
-                        )
-                    elif compression_ratio < settings_dict["MIN_ARCHIVE_RATIO"]:
-                        logger.warning(
-                            "MIN_ARCHIVE_RATIO: Skipped archive %s because compression ratio %.5f is less than MIN_ARCHIVE_RATIO %s",
+                    return
+                self.file_tracker.add_metadata(
+                    base_hash, "extracted_size", extracted_size
+                )
+                compression_ratio = extracted_size / file_size_bytes
+                self.file_tracker.add_metadata(
+                    base_hash, "overall_compression_ratio", compression_ratio
+                )
+
+                if self.__should_extract_archive(base_hash, file_path):
+                    try:
+                        extraction_dir = self.extract_dir / base_hash
+                        logger.info(
+                            "Extracting archive %s to %s",
                             file_path,
-                            compression_ratio,
-                            settings_dict["MIN_ARCHIVE_RATIO"],
+                            extraction_dir,
                         )
-                    elif (
-                        shutil.disk_usage(self.extract_dir).free - extracted_size
-                        < settings_dict["MIN_DISK_FREE_SPACE"]
-                    ):
+                        archiver.extract_archive(file_path, extraction_dir)
+                    except RuntimeError as e:
                         logger.warning(
-                            "MIN_DISK_FREE_SPACE:Skipped archive %s because extracting it would leave less than MIN_DISK_FREE_SPACE %s bytes free at extraction location %s",
+                            "EXTRACTION_FAILED: Extraction failed for archive %s: %s",
                             file_path,
-                            settings_dict["MIN_DISK_FREE_SPACE"],
-                            self.extract_dir,
+                            str(e),
                         )
-                    else:
-                        extraction_dir = self.extract_dir / base_hash
-                        archiver.extract_archive(file_path, extraction_dir)
-                        child_files = self._list_child_files(extraction_dir)
-                        for child_file in child_files:
-                            self.__handle_file(child_file, depth + 1)
-                else:
-                    logger.warning(
-                        "NO_ARCHIVER: No suitable archiver found for file: %s",
-                        file_path,
-                    )
+                        return
+                    child_files = self._list_child_files(extraction_dir)
+                    for child_file in child_files:
+                        self.__handle_file(child_file, depth + 1)
+
+                    if self.__should_delete_archive(base_hash, file_path):
+                        try:
+                            file_path.unlink()
+                            logger.info(
+                                "Deleted archive %s after extraction as per settings.",
+                                file_path,
+                            )
+                        except (PermissionError, OSError) as e:
+                            logger.warning(
+                                "DELETE_FAILED: Could not delete archive %s after extraction: %s",
+                                file_path,
+                                str(e),
+                            )
             else:
                 logger.warning(
                     "MAX_DEPTH: File %s is not extracted; max depth reached.", file_path
@@ -163,7 +164,7 @@ class ArchiveExtractor:
             bool: True if the file is an archive, otherwise False.
 
         """
-        metadata = self.file_tracker.get_tracked_file_metadata(file_hash)
+        metadata = self.file_tracker.get_file_metadata(file_hash)
         mime_type = metadata.get("type_mime", "").lower()
         extension = metadata.get("extension", "").lower()
 
@@ -182,7 +183,7 @@ class ArchiveExtractor:
         Returns:
             str | None: The name of the archiver tool if found, otherwise None.
         """
-        metadata = self.file_tracker.get_tracked_file_metadata(file_hash)
+        metadata = self.file_tracker.get_file_metadata(file_hash)
         mime_type = metadata.get("type_mime", "").lower()
         extension = metadata.get("extension", "").lower()
 
@@ -250,3 +251,76 @@ class ArchiveExtractor:
             extractor.apply_settings([("MAX_ARCHIVE_SIZE_BYTES", "5000000000")])
         """
         apply_options(option_list)
+
+    def __should_extract_archive(self, file_hash: str, file_path: Path) -> bool:
+        """Determine whether an archive should be extracted based on its metadata and current settings."""
+        settings_dict = get_settings()
+        metadata = self.file_tracker.get_file_metadata(file_hash)
+        extracted_size = metadata.get("extracted_size", 0)
+        if extracted_size > settings_dict["MAX_ARCHIVE_SIZE_BYTES"]:
+            logger.warning(
+                "MAX_ARCHIVE_SIZE_BYTES: Skipped archive %s because expected size %s is greater than MAX_ARCHIVE_SIZE_BYTES %s",
+                file_path,
+                extracted_size,
+                settings_dict["MAX_ARCHIVE_SIZE_BYTES"],
+            )
+            return False
+
+        total_extracted = self.file_tracker.get_total_tracked_file_size()
+        if total_extracted + extracted_size > settings_dict["MAX_TOTAL_SIZE_BYTES"]:
+            logger.warning(
+                "MAX_TOTAL_SIZE_BYTES: Skipped archive %s because expected size %s + current tracked files %s is greater than MAX_TOTAL_SIZE_BYTES %s",
+                file_path,
+                extracted_size,
+                total_extracted,
+                settings_dict["MAX_TOTAL_SIZE_BYTES"],
+            )
+            return False
+        compression_ratio = metadata.get("overall_compression_ratio", 0)
+        if compression_ratio < settings_dict["MIN_ARCHIVE_RATIO"]:
+            logger.warning(
+                "MIN_ARCHIVE_RATIO: Skipped archive %s because compression ratio %.5f is less than MIN_ARCHIVE_RATIO %s",
+                file_path,
+                compression_ratio,
+                settings_dict["MIN_ARCHIVE_RATIO"],
+            )
+            return False
+        if (
+            shutil.disk_usage(self.extract_dir).free - extracted_size
+            < settings_dict["MIN_DISK_FREE_SPACE"]
+        ):
+            logger.warning(
+                "MIN_DISK_FREE_SPACE: Skipped archive %s because extracting it would leave less than MIN_DISK_FREE_SPACE %s bytes free at extraction location %s",
+                file_path,
+                settings_dict["MIN_DISK_FREE_SPACE"],
+                self.extract_dir,
+            )
+            return False
+        return True
+
+    def __should_delete_archive(self, file_hash: str, file_path: Path) -> bool:
+        """Determine whether an archive should be deleted after extraction based on its metadata and current settings."""
+        settings_dict = get_settings()
+        if not settings_dict["DELETE_ARCHIVES_AFTER_EXTRACTION"]:
+            return False
+
+        metadata = self.file_tracker.get_file_metadata(file_hash)
+        extension = metadata.get("extension", "").lower()
+        if extension in skip_delete_extensions:
+            logger.warning(
+                "SKIP_DELETE_EXTENSION: Archive %s not deleted after extraction due to its extension '%s' being in the skip list.",
+                file_path,
+                extension,
+            )
+            return False
+
+        mime_type = metadata.get("type_mime", "").lower()
+        if mime_type in skip_delete_mimetypes:
+            logger.warning(
+                "SKIP_DELETE_MIMETYPE: Archive %s not deleted after extraction due to its mime type '%s' being in the skip list.",
+                file_path,
+                mime_type,
+            )
+            return False
+
+        return True

{archae-2026.2.1 → archae-2026.3}/src/archae/options.yaml

@@ -37,3 +37,10 @@ MAX_DEPTH:
     - 5
     - 10
     - 0
+DELETE_ARCHIVES_AFTER_EXTRACTION:
+  type: bool
+  converter: bool
+  help: Whether to delete archives after extraction.
+  examples:
+    - True
+    - False

{archae-2026.2.1 → archae-2026.3}/src/archae/util/archiver/peazip.py

@@ -31,7 +31,7 @@ class PeazipArchiver(BaseArchiver):
         "chi",
         "chq",
         "pptx",
-        "pptm ",
+        "pptm",
         "xlsx",
         "xlsm",
         "docx",
@@ -145,7 +145,14 @@ class PeazipArchiver(BaseArchiver):
             str(archive_path),
             str(extract_dir),
         ]
-        subprocess.run(command, check=True)  # noqa: S603
+        try:
+            subprocess.run(command, check=True, capture_output=True, text=True)  # noqa: S603
+        except subprocess.CalledProcessError as e:
+            msg = (
+                f"PeaZip extraction failed for archive {archive_path} "
+                f"with exit code {e.returncode}: {e.stderr}"
+            )
+            raise RuntimeError(msg) from e
 
     def get_archive_uncompressed_size(self, archive_path: Path) -> int:  # noqa: ARG002
         """Get the uncompressed size of the contents.

{archae-2026.2.1 → archae-2026.3}/src/archae/util/archiver/seven_zip.py

@@ -46,7 +46,7 @@ class SevenZipArchiver(BaseArchiver):
         "zip",
         "zipx",
         "appimage",
-        "dmg ",
+        "dmg",
         "img",
         "arj",
         "cpio",
@@ -176,7 +176,14 @@ class SevenZipArchiver(BaseArchiver):
             str(archive_path),
             f"-o{extract_dir!s}",
         ]
-        subprocess.run(command, check=True)  # noqa: S603
+        try:
+            subprocess.run(command, check=True, capture_output=True, text=True)  # noqa: S603
+        except subprocess.CalledProcessError as e:
+            msg = (
+                f"7zip extraction failed for archive {archive_path} "
+                f"with exit code {e.returncode}: {e.stderr}"
+            )
+            raise RuntimeError(msg) from e
 
     def get_archive_uncompressed_size(self, archive_path: Path) -> int:
         """Get the uncompressed size of the contents.
@@ -188,7 +195,14 @@ class SevenZipArchiver(BaseArchiver):
             int: The size of the contents
         """
         command: list[str] = [str(self.executable_path), "l", "-slt", str(archive_path)]
-        result = subprocess.run(command, check=True, capture_output=True, text=True)  # noqa: S603
+        try:
+            result = subprocess.run(command, check=True, capture_output=True, text=True)  # noqa: S603
+        except subprocess.CalledProcessError as e:
+            msg = (
+                f"7zip size retrieval failed for archive {archive_path} "
+                f"with exit code {e.returncode}: {e.stderr}"
+            )
+            raise RuntimeError(msg) from e
 
         result_lines = str(result.stdout).splitlines()
         exploded_size = 0

{archae-2026.2.1 → archae-2026.3}/src/archae/util/archiver/unar.py

@@ -24,9 +24,9 @@ class UnarArchiver(BaseArchiver):
         "deb",
         "cab",
         "pptx",
-        "pptm ",
-        "xlsx ",
+        "pptm",
         "xlsm",
+        "xlsx",
         "docx",
         "docm",
         "7z",
@@ -144,7 +144,14 @@ class UnarArchiver(BaseArchiver):
             str(extract_dir),
             str(archive_path),
         ]
-        subprocess.run(command, check=True)  # noqa: S603
+        try:
+            subprocess.run(command, check=True, capture_output=True, text=True)  # noqa: S603
+        except subprocess.CalledProcessError as e:
+            msg = (
+                f"unar extraction failed for archive {archive_path} "
+                f"with exit code {e.returncode}: {e.stderr}"
+            )
+            raise RuntimeError(msg) from e
 
     def get_archive_uncompressed_size(self, archive_path: Path) -> int:  # noqa: ARG002
         """Get the uncompressed size of the contents.

{archae-2026.2.1 → archae-2026.3}/src/archae/util/file_tracker.py

@@ -39,7 +39,18 @@ class FileTracker:
         """
         return file_hash in self.tracked_files
 
-    def get_tracked_file_metadata(self, file_hash: str) -> dict:
+    def get_file_size(self, file_hash: str) -> int:
+        """Get the size for a tracked file by its hash.
+
+        Args:
+            file_hash (str): The hash of the file.
+
+        Returns:
+            int: The size of the tracked file.
+        """
+        return self.tracked_files.get(file_hash, {}).get("size", 0)
+
+    def get_file_metadata(self, file_hash: str) -> dict:
         """Get metadata for a tracked file by its hash.
 
         Args:
@@ -63,7 +74,7 @@ class FileTracker:
         if file_path not in self.tracked_files[file_hash]["paths"]:
             self.tracked_files[file_hash]["paths"].append(file_path)
 
-    def add_metadata_to_hash(self, file_hash: str, key: str, value: Any) -> None:
+    def add_metadata(self, file_hash: str, key: str, value: Any) -> None:
         """Add metadata to a tracked file.
 
         Args:
@@ -73,7 +84,7 @@ class FileTracker:
         """
         self.tracked_files[file_hash]["metadata"][key] = value
 
-    def get_tracked_file_size(self) -> int:
+    def get_total_tracked_file_size(self) -> int:
         """Get the total size of all tracked files.
 
         Returns:

archae-2026.3/src/archae/util/lists.py

@@ -0,0 +1,58 @@
+"""Helper lists for various purposes."""
+
+skip_delete_extensions = [
+    "aar",
+    "appimage",
+    "cab",
+    "chi",
+    "chm",
+    "chq",
+    "chw",
+    "crx",
+    "deb",
+    "docm",
+    "docx",
+    "edb",
+    "edp",
+    "edr",
+    "esd",
+    "exe",
+    "ipa",
+    "iso",
+    "lib",
+    "msi",
+    "nsi",
+    "nsis",
+    "pptm",
+    "pptx",
+    "rpm",
+    "s7z",
+    "sitx",
+    "swm",
+    "ear",
+    "jar",
+    "war",
+    "xlsm",
+    "xlsx",
+    "xpi",
+    "zipx",
+]
+
+
+skip_delete_mimetypes = [
+    "application/java-archive",
+    "application/vnd.android.package-archive",
+    "application/vnd.debian.binary-package",
+    "application/vnd.ms-cab-compressed",
+    "application/vnd.ms-htmlhelp",
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "application/x-chrome-extension",
+    "application/x-iso9660-image",
+    "application/x-ole-storage",
+    "application/x-rpm",
+    "application/x-sitx",
+    "application/x-stuffitx",
+    "application/x-xpinstall",
+]