🗓 Mar 17, 2024 9:32:53 PM

🐙 update to_html_entity to reflect cyberchef. closes #33
🧪 tests added/updated

Author: securisec

TODO

@@ -30,6 +30,7 @@ New ideas:
   ☐ register support in callstack
   ☐ extract phone numbers. r'^(?:\+\d{1,3}|0\d{1,3}|00\d{1,2})?(?:\s?\(\d+\))?(?:[-\/\s.]|\d)+(x\d+)?$'
   ☐ load csv data
+  ☐ 🔥 update python_requires in setup.py on python version change
 
 Bug:
 

chepy/__version__.py

@@ -1,2 +1,2 @@
-__version__ = "6.6.1"  # pragma: no cover
+__version__ = "6.7.0"  # pragma: no cover
 __author__ = "@securisec"  # pragma: no cover

chepy/modules/dataformat.py

@@ -17,7 +17,6 @@
     Rotate,
     Uint1Array,
     UUEncoderDecoder,
-    LZ77Compressor,
 )
 
 yaml = lazy_import.lazy_module("yaml")
@@ -176,7 +175,7 @@ def dict_get_items(self, *keys) -> DataFormatT:
         return self
 
     @ChepyDecorators.call_stack
-    def yaml_to_json(self) -> DataFormatT:
+    def yaml_to_json(self) -> DataFormatT:  # pragma: no cover
         """Convert yaml to a json string
 
         Returns:
@@ -1034,19 +1033,36 @@ def from_octal(self, delimiter: str = None, join_by: str = "") -> DataFormatT:
         return self
 
     @ChepyDecorators.call_stack
-    def to_html_entity(self) -> DataFormatT:
+    def to_html_entity(self, format="named", all_chars=False) -> DataFormatT:
         """Encode html entities
 
         Encode special html characters like & > < etc
 
+        Args:
+            format (str): Encoding format. Valid formats are named, numeric and hex. Defaults to named
+            all_chars (bool): If all chars should be encoded. By default a-ZA-Z0-9 are skipped. Defaults to False
+
         Returns:
             Chepy: The Chepy object.
 
         Examples:
             >>> Chepy('https://google.com&a="lol"').to_html_entity().o
             "https://google.com&amp;a=&quot;lol&quot;"
         """
-        self.state = html.escape(self._convert_to_str())
+        data = self._convert_to_str()
+        chars = {k: 1 for k in string.ascii_letters + string.digits}
+        hold = ""
+        for d in data:
+            if not all_chars and chars.get(d) is not None:
+                hold += d
+                continue
+            if format == "named":
+                hold += Encoding.BYTE_TO_ENTITY.get(ord(d), f"&#{ord(d)};")
+            elif format == "hex":
+                hold += f"&#x{d.encode().hex()};"
+            elif format == "numeric":
+                hold += f"&#{ord(d)};"
+        self.state = hold
         return self
 
     @ChepyDecorators.call_stack

chepy/modules/dataformat.pyi

@@ -57,7 +57,7 @@ class DataFormat(ChepyCore):
     def from_binary(self: DataFormatT, delimiter: Union[str, None]=None, byte_length: int=...) -> DataFormatT: ...
     def to_octal(self: DataFormatT, join_by: str=...) -> DataFormatT: ...
     def from_octal(self: DataFormatT, delimiter: str=..., join_by: str=...) -> DataFormatT: ...
-    def to_html_entity(self: DataFormatT) -> DataFormatT: ...
+    def to_html_entity(self: DataFormatT, format:Literal['named', 'numeric', 'hex']='named', all_chars:bool=False) -> DataFormatT: ...
     def from_html_entity(self: DataFormatT) -> DataFormatT: ...
     def to_punycode(self: DataFormatT) -> DataFormatT: ...
     def from_punycode(self: DataFormatT) -> DataFormatT: ...