codext 1.15.9__tar.gz → 1.15.11__tar.gz

{codext-1.15.9 → codext-1.15.11}/.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

{codext-1.15.9 → codext-1.15.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codext
-Version: 1.15.9
+Version: 1.15.11
 Summary: Native codecs extension
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE

{codext-1.15.9 → codext-1.15.11}/docs/coverage.svg

@@ -1 +1 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 98.90%"><title>coverage: 98.90%</title><linearGradient id="s" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="r"><rect width="114" height="20" rx="3" fill="#fff"/></clipPath><g clip-path="url(#r)"><rect width="61" height="20" fill="#555"/><rect x="61" width="53" height="20" fill="#4c1"/><rect width="114" height="20" fill="url(#s)"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><text aria-hidden="true" x="315" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="510">coverage</text><text x="315" y="140" transform="scale(.1)" fill="#fff" textLength="510">coverage</text><text aria-hidden="true" x="865" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="430">98.90%</text><text x="865" y="140" transform="scale(.1)" fill="#fff" textLength="430">98.90%</text></g></svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 98.83%"><title>coverage: 98.83%</title><linearGradient id="s" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="r"><rect width="114" height="20" rx="3" fill="#fff"/></clipPath><g clip-path="url(#r)"><rect width="61" height="20" fill="#555"/><rect x="61" width="53" height="20" fill="#4c1"/><rect width="114" height="20" fill="url(#s)"/></g><g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" text-rendering="geometricPrecision" font-size="110"><text aria-hidden="true" x="315" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="510">coverage</text><text x="315" y="140" transform="scale(.1)" fill="#fff" textLength="510">coverage</text><text aria-hidden="true" x="865" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="430">98.83%</text><text x="865" y="140" transform="scale(.1)" fill="#fff" textLength="430">98.83%</text></g></svg>

{codext-1.15.9 → codext-1.15.11}/requirements.txt

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

codext-1.15.11/src/codext/VERSION.txt

@@ -0,0 +1 @@
+1.15.11

{codext-1.15.9 → codext-1.15.11}/src/codext/__common__.py

@@ -6,7 +6,6 @@ import json
 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 @@ try:  # Python3
     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(ename, errors, sep="", repl_char="?", repl_minlen=1, decode=Fal
         :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)
 

{codext-1.15.9 → codext-1.15.11}/src/codext/binary/baudot.py

@@ -102,7 +102,7 @@ ITA2_METEO = [
 # Russian MTK-2 alphabet (source: https://fr.qwe.wiki/wiki/Baudot_code)
 MTK2 = [
     "11111", "11011",
-    "\x00Е\n\xff СИУ\r\xffРЙНФЦКТЗЛВХЫПЯОБГ\xffМЬЖ\xff",
+    "\x00Е\nA СИУ\r\xffРЙНФЦКТЗЛВХЫПЯОБГ\xffМЬЖ\xff",
     "\x003\n- '87\r\xff4Ю,Э:(5+)2Щ6019?Ш\xff./=\xff",
 ]
 # Murray code ; NB: not all fractions are supported (source: https://en.wikipedia.org/wiki/Baudot_code)

{codext-1.15.9 → codext-1.15.11}/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 *
+

{codext-1.15.9 → codext-1.15.11}/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.
 

{codext-1.15.9 → codext-1.15.11}/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.
 

codext-1.15.11/src/codext/hashing/crypt.py

@@ -0,0 +1,36 @@
+# -*- coding: UTF-8 -*-
+"""Crypt Hashing Codec - string hashing with Unix's Crypt.
+
+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 add, ensure_str, UNIX
+
+
+if UNIX:
+    try:
+        import crypt
+    except ImportError:
+        try:
+            import legacycrypt as crypt
+        except ImportError:
+            crypt = None
+    
+    if crypt is not None:
+        METHODS = [x[7:].lower() for x in crypt.__dict__ if x.startswith("METHOD_")]
+        
+        def crypt_hash(method):
+            method = (method or "").lstrip("-_") or "blowfish"
+            if method not in METHODS:
+                raise NotImplementedError("method '%s' is not implemented" % method)
+            def _encode(input, error="strict"):
+                m = getattr(crypt, "METHOD_" + method.upper())
+                return crypt.crypt(ensure_str(input), crypt.mksalt(m)), len(input)
+            return _encode
+        
+        add("crypt", crypt_hash, pattern=r"^crypt(|[-_](?:%s))$" % "|".join(METHODS), guess=None)
+

{codext-1.15.9 → codext-1.15.11}/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.
 

codext-1.15.11/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)
+

{codext-1.15.9 → codext-1.15.11}/src/codext/hashing/sha.py

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

{codext-1.15.9 → codext-1.15.11}/src/codext/hashing/shake.py

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

{codext-1.15.9 → codext-1.15.11}/src/codext.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codext
-Version: 1.15.9
+Version: 1.15.11
 Summary: Native codecs extension
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE

{codext-1.15.9 → codext-1.15.11}/src/codext.egg-info/SOURCES.txt

@@ -87,6 +87,7 @@ src/codext/hashing/blake.py
 src/codext/hashing/checksums.py
 src/codext/hashing/crypt.py
 src/codext/hashing/md.py
+src/codext/hashing/mmh3.py
 src/codext/hashing/sha.py
 src/codext/hashing/shake.py
 src/codext/languages/__init__.py

{codext-1.15.9 → codext-1.15.11}/tests/test_manual.py

@@ -128,8 +128,12 @@ class ManualTestCase(TestCase):
             try:
                 import crypt
             except ImportError:
-                import legacycrypt as crypt
-            METHODS = [x[7:].lower() for x in crypt.__dict__ if x.startswith("METHOD_")]
+                try:
+                    import legacycrypt as crypt
+                except ImportError:
+                    crypt = None
+            METHODS = [x[7:].lower() for x in crypt.__dict__ if x.startswith("METHOD_")] \
+                      if crypt is not None else []
             for m in METHODS:
                 h = "crypt-" + m
                 self.assertIsNotNone(codecs.encode(STR, h))

codext-1.15.9/src/codext/VERSION.txt

@@ -1 +0,0 @@
-1.15.9

codext-1.15.9/src/codext/hashing/crypt.py

@@ -1,32 +0,0 @@
-# -*- coding: UTF-8 -*-
-"""Case Codecs - string hashing with Unix's Crypt.
-
-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 add, ensure_str, UNIX
-
-
-if UNIX:
-    try:
-        import crypt
-    except ImportError:
-        import legacycrypt as crypt
-    
-    METHODS = [x[7:].lower() for x in crypt.__dict__ if x.startswith("METHOD_")]
-    
-    def crypt_hash(method):
-        method = (method or "").lstrip("-_") or "blowfish"
-        if method not in METHODS:
-            raise NotImplementedError("method '%s' is not implemented" % method)
-        def _encode(input, error="strict"):
-            m = getattr(crypt, "METHOD_" + method.upper())
-            return crypt.crypt(ensure_str(input), crypt.mksalt(m)), len(input)
-        return _encode
-    
-    add("crypt", crypt_hash, pattern=r"^crypt(|[-_](?:%s))$" % "|".join(METHODS), guess=None)
-