credsweeper 1.11.0__tar.gz → 1.11.1__tar.gz

{credsweeper-1.11.0 → credsweeper-1.11.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: credsweeper
-Version: 1.11.0
+Version: 1.11.1
 Summary: Credential Sweeper
 Project-URL: Homepage, https://github.com/Samsung/CredSweeper
 Project-URL: Bug Tracker, https://github.com/Samsung/CredSweeper/issues

{credsweeper-1.11.0 → credsweeper-1.11.1}/credsweeper/__init__.py

@@ -18,4 +18,4 @@ __all__ = [
     '__version__'
 ]
 
-__version__ = "1.11.0"
+__version__ = "1.11.1"

{credsweeper-1.11.0 → credsweeper-1.11.1}/credsweeper/deep_scanner/deep_scanner.py

@@ -28,6 +28,7 @@ from .pdf_scanner import PdfScanner
 from .pkcs12_scanner import Pkcs12Scanner
 from .pptx_scanner import PptxScanner
 from .tar_scanner import TarScanner
+from .tmx_scanner import TmxScanner
 from .xlsx_scanner import XlsxScanner
 from .xml_scanner import XmlScanner
 from .zip_scanner import ZipScanner
@@ -126,6 +127,10 @@ class DeepScanner(
                 deep_scanners.append(MxfileScanner)
                 deep_scanners.append(XmlScanner)
                 fallback_scanners.append(ByteScanner)
+            elif Util.is_tmx(data):
+                deep_scanners.append(TmxScanner)
+                fallback_scanners.append(XmlScanner)
+                fallback_scanners.append(ByteScanner)
             else:
                 deep_scanners.append(XmlScanner)
                 fallback_scanners.append(ByteScanner)

credsweeper-1.11.1/credsweeper/deep_scanner/tmx_scanner.py

@@ -0,0 +1,45 @@
+import logging
+from abc import ABC
+from typing import List, Optional
+
+from lxml import etree
+
+from credsweeper.common.constants import MIN_DATA_LEN
+from credsweeper.credentials import Candidate
+from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
+from credsweeper.file_handler.data_content_provider import DataContentProvider
+from credsweeper.file_handler.string_content_provider import StringContentProvider
+from credsweeper.utils import Util
+
+logger = logging.getLogger(__name__)
+
+
+class TmxScanner(AbstractScanner, ABC):
+    """Realises tmX files scanning for values only. Image tags are skipped."""
+
+    def data_scan(
+            self,  #
+            data_provider: DataContentProvider,  #
+            depth: int,  #
+            recursive_limit_size: int) -> Optional[List[Candidate]]:
+        """Tries to represent data as xml text and scan as text lines"""
+        try:
+            lines = []
+            # the format is always in single line xlm, so line numbers are not actual
+            tree = etree.fromstring(data_provider.data)
+            for element in tree.iter():
+                tag = Util.extract_element_data(element, "tag")
+                if "Image" in tag:
+                    continue
+                text = Util.extract_element_data(element, "text")
+                if MIN_DATA_LEN > len(text):
+                    continue
+                lines.append(text)
+            tmx_data_provider = StringContentProvider(lines=lines,
+                                                      file_path=data_provider.file_path,
+                                                      file_type=data_provider.file_type,
+                                                      info=f"{data_provider.info}|TMX")
+            return self.scanner.scan(tmx_data_provider)
+        except Exception as exc:
+            logger.warning("Cannot processed tmX file %s %s", str(data_provider.file_path), str(exc))
+        return None

{credsweeper-1.11.0 → credsweeper-1.11.1}/credsweeper/utils/util.py

@@ -517,6 +517,18 @@ class Util:
                 return True
         return False
 
+    @staticmethod
+    def is_tmx(data: Union[bytes, bytearray]) -> bool:
+        """Used to detect tm7,tm6,etc. (ThreadModeling) format."""
+        if isinstance(data, (bytes, bytearray)):
+            for opening_tag, closing_tag in [(b"<ThreatModel", b"</ThreatModel>"),
+                                             (b"<KnowledgeBase", b"</KnowledgeBase>")]:
+                opening_pos = data.find(opening_tag, 0, MAX_LINE_LENGTH)
+                if 0 <= opening_pos < data.find(closing_tag, opening_pos):
+                    # opening and closing tags were found - suppose it is an HTML
+                    return True
+        return False
+
     # A well-formed XML must start from < or a whitespace character
     XML_FIRST_BRACKET_PATTERN = re.compile(rb"^\s*<")
     XML_OPENING_TAG_PATTERN = re.compile(rb"<([0-9A-Za-z_]{1,256})")
@@ -583,14 +595,14 @@ class Util:
         line_nums = []
         tree = etree.fromstringlist(xml_lines)
         for element in tree.iter():
-            tag = Util._extract_element_data(element, "tag")
-            text = Util._extract_element_data(element, "text")
+            tag = Util.extract_element_data(element, "tag")
+            text = Util.extract_element_data(element, "text")
             lines.append(f"{tag} : {text}")
             line_nums.append(element.sourceline)
         return lines, line_nums
 
     @staticmethod
-    def _extract_element_data(element, attr) -> str:
+    def extract_element_data(element: Any, attr: str) -> str:
         """Extract xml element data to string.
 
         Try to extract the xml data and strip() the string.
@@ -605,7 +617,7 @@ class Util:
         """
         element_attr: Any = getattr(element, attr)
         if element_attr is None or not isinstance(element_attr, str):
-            return ""
+            return ''
         return str(element_attr).strip()
 
     @staticmethod