Applied some minor improvements

Author: dhondta

.github/workflows/python-package.yml

@@ -31,6 +31,7 @@ jobs:
         python -m pip install --upgrade pip
         python -m pip install pytest pytest-cov coverage
         pip install -r requirements.txt
+        pip install tinyscript>=1.31
         pip install .
     - name: Test ${{ env.package }} with pytest
       run: |
@@ -45,7 +46,7 @@ jobs:
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v4
       with:
-        python-version: "3.12"
+        python-version: "3.13"
     - name: Install ${{ env.package }}
       run: |
         python -m pip install --upgrade pip

requirements.txt

@@ -1,2 +1,2 @@
-markdown2>=2.5.4
 legacycrypt; python_version >= '3.13'
+markdown2>=2.5.4

src/codext/VERSION.txt

@@ -1 +1 @@
-1.15.9
+1.15.10

src/codext/__common__.py

@@ -6,7 +6,6 @@
 import os
 import random
 import re
-import sre_parse
 import sys
 from encodings.aliases import aliases as ALIASES
 from functools import reduce, update_wrapper, wraps
@@ -37,8 +36,12 @@
     from importlib import reload
 except ImportError:
     pass
+try:
+    import re._parser as sre_parse
+except ImportError:
+    import sre_parse
 
-# from Python 3.11, it seems that 'sre_parse' is not bound to 're' anymore
+# from Python 3.11, 'sre_parse' is bound as '_parser' ; monkey-patch it for backward-compatibility
 re.sre_parse = sre_parse
 
 
@@ -870,10 +873,9 @@ def _handle_error(token, position, output="", eename=None):
         :param output:   output, as decoded up to the position of the error
         """
         if errors == "strict":
-            msg = "'%s' codec can't %scode %s '%s' in %s %d"
-            token = ensure_str(token)
-            token = token[:7] + "..." if len(token) > 10 else token
-            err = getattr(builtins, exc)(msg % (eename or ename, ["en", "de"][decode], kind, token, item, position))
+            token = f"{token[:7]}..." if len(token := ensure_str(token)) > 10 else token
+            err = getattr(builtins, exc)(f"'{eename or ename}' codec can't {['en','de'][decode]}code {kind} '{token}' "
+                                         f"in {item} {position}")
             err.output = output
             err.__cause__ = err
             raise err
@@ -1264,8 +1266,8 @@ def __guess(prev_input, input, stop_func, depth, max_depth, min_depth, encodings
         if not stop and (show or debug) and found not in result:
             s = repr(input)
             s = s[2:-1] if s.startswith("b'") and s.endswith("'") else s
-            s = "[+] {', '.join(found)}: {s}"
-            print(s if len(s) <= 80 else s[:77] + "...")
+            s = f"[+] {', '.join(found)}: {s}"
+            print(s if len(s) <= 80 else f"{s[:77]}...")
         result[found] = input
     if depth >= max_depth or len(result) > 0 and stop:
         return
@@ -1275,7 +1277,7 @@ def __guess(prev_input, input, stop_func, depth, max_depth, min_depth, encodings
         if len(result) > 0 and stop:
             return
         if debug:
-            print(f"[*] Depth %0{len(str(max_depth))}d/%d: {encoding}" % (depth+1, max_depth))
+            print(f"[*] Depth {depth+1:0{len(str(max_depth))}}/{max_depth}: {encoding}")
         __guess(input, new_input, stop_func, depth+1, max_depth, min_depth, encodings, result, found + (encoding, ),
                 stop, show, scoring_heuristic, extended, debug)
 

src/codext/hashing/__init__.py

@@ -1,8 +1,9 @@
-# -*- coding: UTF-8 -*-
-from .blake import *
-from .checksums import *
-from .crypt import *
-from .md import *
-from .sha import *
-from .shake import *
-
+# -*- coding: UTF-8 -*-
+from .blake import *
+from .checksums import *
+from .crypt import *
+from .md import *
+from .mmh3 import *
+from .sha import *
+from .shake import *
+

src/codext/hashing/blake.py

@@ -1,5 +1,5 @@
 # -*- coding: UTF-8 -*-
-"""Case Codecs - string hashing with blake.
+"""Blake2 Codecs - string hashing with blake.
 
 These are codecs for hashing strings, for use with other codecs in encoding chains.
 

src/codext/hashing/checksums.py

@@ -1,5 +1,5 @@
 # -*- coding: UTF-8 -*-
-"""Case Codecs - string common checksums.
+"""Checksum Codecs - string common checksums.
 
 These are codecs for hashing strings, for use with other codecs in encoding chains.
 

src/codext/hashing/crypt.py

@@ -1,5 +1,5 @@
 # -*- coding: UTF-8 -*-
-"""Case Codecs - string hashing with Unix's Crypt.
+"""Crypt Hashing Codec - string hashing with Unix's Crypt.
 
 These are codecs for hashing strings, for use with other codecs in encoding chains.
 

src/codext/hashing/md.py

@@ -1,5 +1,5 @@
 # -*- coding: UTF-8 -*-
-"""Case Codecs - string hashing with Message Digest (MD).
+"""MD Hashing Codecs - string hashing with Message Digest (MD).
 
 These are codecs for hashing strings, for use with other codecs in encoding chains.
 
@@ -56,4 +56,3 @@ def md2(data):
 add("md5", lambda s, error="strict": (hashlib.new("md5", b(s)).hexdigest(), len(s)), guess=None)
 if "md4" in hashlib.algorithms_available:
     add("md4", lambda s, error="strict": (hashlib.new("md4", b(s)).hexdigest(), len(s)), guess=None)
-

src/codext/hashing/mmh3.py

@@ -0,0 +1,18 @@
+# -*- coding: UTF-8 -*-
+"""MMH3 Codecs - string hashing with MurmurHash3.
+
+These are codecs for hashing strings, for use with other codecs in encoding chains.
+
+These codecs:
+- transform strings from str to str
+- transform strings from bytes to bytes
+- transform file content from str to bytes (write)
+"""
+from ..__common__ import *
+
+
+if "mmh3_32" in hashlib.algorithms_available:
+    add("mmh3_32", lambda s, error="strict": (hashlib.mmh3_32(b(s)).hexdigest(), len(s)), guess=None)
+if "mmh3_128" in hashlib.algorithms_available:
+    add("mmh3_128", lambda s, error="strict": (hashlib.mmh3_128(b(s)).hexdigest(), len(s)), guess=None)
+