exeplot 0.4.3__tar.gz → 0.5.4__tar.gz

{exeplot-0.4.3 → exeplot-0.5.4}/.coveragerc

@@ -21,3 +21,4 @@ exclude_lines =
     if self.type not in ["ELF", "MachO", "PE"]:
     if j <= i or start2 is None:
     if s != self.__size:
+    glob['_IMP'] = True

{exeplot-0.4.3 → exeplot-0.5.4}/.github/workflows/python-package.yml

@@ -19,7 +19,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}

{exeplot-0.4.3 → exeplot-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exeplot
-Version: 0.4.3
+Version: 0.5.4
 Summary: Library for plotting executable samples supporting multiple formats
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -689,7 +689,7 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
 Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: <4,>=3.9
+Requires-Python: <4,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: lief>=0.16.1
@@ -736,7 +736,7 @@ Draw a simplified byte plot of `calc_packed.exe`:
 $ exeplot byte calc_packed.exe --no-title --no-legend
 ```
 
-![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
+![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte2.png?raw=true)
 
 Draw a pie plot of `calc_packed.exe`:
 

{exeplot-0.4.3 → exeplot-0.5.4}/README.md

@@ -32,7 +32,7 @@ Draw a simplified byte plot of `calc_packed.exe`:
 $ exeplot byte calc_packed.exe --no-title --no-legend
 ```
 
-![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
+![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte2.png?raw=true)
 
 Draw a pie plot of `calc_packed.exe`:
 

{exeplot-0.4.3 → exeplot-0.5.4}/docs/coverage.svg

@@ -1 +1 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 96.70%"><title>coverage: 96.70%</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">96.70%</text><text x="865" y="140" transform="scale(.1)" fill="#fff" textLength="430">96.70%</text></g></svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="114" height="20" role="img" aria-label="coverage: 96.62%"><title>coverage: 96.62%</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">96.62%</text><text x="865" y="140" transform="scale(.1)" fill="#fff" textLength="430">96.62%</text></g></svg>

{exeplot-0.4.3 → exeplot-0.5.4}/pyproject.toml

@@ -22,7 +22,7 @@ authors = [
 description = "Library for plotting executable samples supporting multiple formats"
 license = {file = "LICENSE"}
 keywords = ["python", "development", "programming", "executable-samples", "plot", "entropy", "cfg"]
-requires-python = ">=3.9,<4"
+requires-python = ">=3.10,<4"
 classifiers = [
   "Development Status :: 5 - Production/Stable",
   "Environment :: Console",

exeplot-0.5.4/src/exeplot/VERSION.txt

@@ -0,0 +1 @@
+0.5.4

{exeplot-0.4.3 → exeplot-0.5.4}/src/exeplot/__conf__.py

@@ -29,7 +29,7 @@ config = {
 numpy.int = numpy.int_  # dirty fix to "AttributeError: module 'numpy' has no attribute 'int'."
 
 
-def check_imports(*names):
+def check_imports(*names) -> None:
     import warnings
     from inspect import currentframe
     glob = currentframe().f_back.f_globals
@@ -42,7 +42,7 @@ def check_imports(*names):
             glob['_IMP'] = False
 
 
-def configure():  # pragma: no cover
+def configure() -> None:  # pragma: no cover
     from configparser import ConfigParser
     from os.path import exists, expanduser
     path = expanduser("~/.exeplot.conf")
@@ -58,7 +58,7 @@ def configure():  # pragma: no cover
     plt.rcParams['font.family'] = config['font_family']
 
 
-def configure_fonts(**kw):
+def configure_fonts(**kw) -> dict:
     import matplotlib
     matplotlib.rc('font', **{k.split("_")[1]: kw.pop(k, config[k]) for k in ['font_family', 'font_size']})
     kw['title-font'] = {'fontfamily': kw.pop('title_font_family', config['font_family']),

exeplot-0.5.4/src/exeplot/__init__.py

@@ -0,0 +1,9 @@
+# -*- coding: UTF-8 -*-
+"""Exeplot package.
+
+"""
+from .__conf__ import *
+from .__info__ import __author__, __copyright__, __license__, __version__
+from .plots import *
+from .plots import __all__
+

{exeplot-0.4.3 → exeplot-0.5.4}/src/exeplot/__main__.py

@@ -1,11 +1,12 @@
 # -*- coding: UTF-8 -*-
+from argparse import ArgumentParser, Namespace, RawTextHelpFormatter
+
 from .__info__ import __author__, __copyright__, __email__, __license__, __source__, __version__
 from .__init__ import *
 from .__init__ import __all__ as _plots
 
 
-def _parser(name, description, examples):
-    from argparse import ArgumentParser, RawTextHelpFormatter
+def _parser(name: str, description: str, examples: list[str]) -> ArgumentParser:
     descr = f"{name} {__version__}\n\nAuthor   : {__author__} ({__email__})\nCopyright: {__copyright__}\nLicense  :" \
             f" {__license__}\nSource   : {__source__}\n\n{description}.\n\n"
     examples = [f"exeplot {e}" if not e.startswith("exeplot ") else e for e in examples]
@@ -13,7 +14,7 @@ def _parser(name, description, examples):
                           epilog="usage examples:\n  " + "\n  ".join(examples) if len(examples) > 0 else None)
 
 
-def _setup(parser):  # pragma: no cover
+def _setup(parser: ArgumentParser) -> Namespace:  # pragma: no cover
     args = parser.parse_args()
     if hasattr(args, "verbose"):
         import logging
@@ -22,7 +23,7 @@ def _setup(parser):  # pragma: no cover
     return args
 
 
-def main():
+def main() -> None:  # pragma: no cover
     from os import makedirs
     parser = _parser("Exeplot", "This tool allows to plot executable sample(s) in different ways",
                      ["byte binary.exe", "entropy binary1.exe binary2.exe --scale"])

exeplot-0.5.4/src/exeplot/utils.py

@@ -0,0 +1,91 @@
+# -*- coding: UTF-8 -*-
+import numpy as np
+from math import log2
+from typing import Optional
+
+
+__all__ = ["ensure_str", "human_readable_size", "ngrams_counts", "ngrams_distribution", "shannon_entropy"]
+
+shannon_entropy = lambda b: -sum([p*log2(p) for p in [float(ctr)/len(b) for ctr in [b.count(c) for c in set(b)]]]) or 0.
+
+
+def ensure_str(s: str | bytes, encoding: str = "utf-8", errors: str = "strict") -> str:
+    """ Ensure that an input string is decoded. """
+    if isinstance(s, bytes):
+        try:
+            return s.decode(encoding, errors)
+        except:
+            return s.decode("latin-1")
+    elif not isinstance(s, (str, bytes)):
+        raise TypeError("not expecting type '%s'" % type(s))
+    return s
+
+
+def human_readable_size(size: int, precision: int = 0) -> str:
+    """ Display bytes' size in a human-readable format given a precision. """
+    i, units = 0, ["B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"]
+    while size >= 1024 and i < len(units)-1:
+        i += 1
+        size /= 1024.0
+    return "%.*f%s" % (precision, size, units[i])
+
+
+def ngrams_counts(byte_obj: bytes | object, n: int = 1, step: int = 1) -> list[tuple[bytes, int]]:
+    """ Output a sorted list of tuples (n-gram, counts) for an input byte sequence or byte object.
+         If the input is a byte object, the result is cached.
+    
+    :param byte_obj: byte sequence ('bytes') or byte object with "bytes" and "size" attributes (i.e. pathlib2.Path)
+    :param n:        n determining the size of n-grams, defaults to 1
+    :param step:     step for sliding the n-grams
+    """
+    if n not in (1, 2, 3):
+        raise ValueError("n must be 1, 2, or 3")
+    if step <= 0:
+        raise ValueError("step must be positive")
+    try:
+        return byte_obj._ngram_counts_cache[n]
+    except (AttributeError, KeyError):
+        pass
+    if isinstance(byte_obj, bytes) or hasattr(byte_obj, "bytes"):
+        a = np.frombuffer(data := byte_obj if isinstance(byte_obj, bytes) else byte_obj.bytes, dtype=np.uint8)
+        l = a.size
+        if l < n:
+            return {}
+        if n == 1:
+            counts = {b.to_bytes(1, "big"): int(c) for b, c in \
+                      enumerate(np.bincount(np.frombuffer(data, dtype=np.uint8)))}
+        else:
+            end = (m := (l - n) // step + 1) * step
+            grams = np.stack((a[0:end:step], a[1:1+end:step]), axis=1) if n == 2 else \
+                    np.stack((a[0:end:step], a[1:1+end:step], a[2:2+end:step]), axis=1)
+            counts = {bytes(row): int(c) for row, c in zip(*np.unique(grams, axis=0, return_counts=True))}
+        counts = sorted(counts.items(), key=lambda p: p[1], reverse=True)
+        if isinstance(byte_obj, bytes):
+            return counts
+        elif hasattr(byte_obj, "bytes"):
+            if not hasattr(byte_obj, "_ngram_counts_cache"):
+                byte_obj._ngram_counts_cache = {}
+            if n not in byte_obj._ngram_counts_cache.keys():
+                byte_obj._ngram_counts_cache[n] = counts
+            return byte_obj._ngram_counts_cache[n]
+    raise TypeError("Bad input type ; should be a byte sequence or object")
+
+
+def ngrams_distribution(byte_obj: bytes | object, n: int = 1, step: int = 1, n_most_common: Optional[int] = None,
+                        n_exclude_top: int = 0, exclude: Optional[list] = None) -> list[tuple[bytes, int]]:
+    """ Compute the n-grams distribution of an input byte sequence or byte object given exclusions.
+    
+    :param byte_obj:      byte sequence ('bytes') or byte object with "bytes" and "size" attributes (i.e. pathlib2.Path)
+    :param n:             n determining the size of n-grams, defaults to 1
+    :param step:          step for sliding the n-grams
+    :param n_most_common: number of n-grams to be kept in the result, keep all by default
+    :param n_exclude_top: number of n-grams to be excluded from the top of the histogram, no exclusion by default
+    :param exclude:       list of specific n-grams to be excluded, no exclusion by default
+    :return:              list of n_most_common (n-gram, count) pairs
+    """
+    c = ngrams_counts(byte_obj, n, step)
+    r = c[:len(c) if n_most_common is None else n_most_common + n_exclude_top + len(exclude or [])]
+    if exclude is not None:
+        r = [(ngram, count) for ngram, count in r if ngram not in exclude]
+    return r[n_exclude_top:n_exclude_top+(n_most_common or len(c))]
+

{exeplot-0.4.3 → exeplot-0.5.4}/src/exeplot.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exeplot
-Version: 0.4.3
+Version: 0.5.4
 Summary: Library for plotting executable samples supporting multiple formats
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -689,7 +689,7 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
 Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: <4,>=3.9
+Requires-Python: <4,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: lief>=0.16.1
@@ -736,7 +736,7 @@ Draw a simplified byte plot of `calc_packed.exe`:
 $ exeplot byte calc_packed.exe --no-title --no-legend
 ```
 
-![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
+![Simplified byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte2.png?raw=true)
 
 Draw a pie plot of `calc_packed.exe`:
 

{exeplot-0.4.3 → exeplot-0.5.4}/src/exeplot.egg-info/SOURCES.txt

@@ -15,6 +15,8 @@ docs/pages/index.md
 docs/pages/css/extra.css
 docs/pages/img/calc_orig_entropy.png
 docs/pages/img/calc_packed_byte.png
+docs/pages/img/calc_packed_byte2.png
+docs/pages/img/calc_packed_entropy.png
 docs/pages/img/calc_packed_nested_pie.png
 docs/pages/img/calc_packed_pie.png
 docs/pages/img/icon.png

{exeplot-0.4.3 → exeplot-0.5.4}/tests/test_others.py

@@ -2,7 +2,6 @@
 # -*- coding: UTF-8 -*-
 import matplotlib.pyplot as plt
 import os
-from collections import Counter
 from exeplot.plots.__common__ import Binary
 from exeplot.utils import *
 from unittest import TestCase
@@ -21,12 +20,15 @@ class TestOthers(TestCase):
 class TestUtils(TestCase):
     def test_ngrams_functions(self):
         self.assertRaises(TypeError, ngrams_counts, 123)
-        self.assertTrue(isinstance(ngrams_counts(seq := b"\x00" * 4 + os.urandom(120) + b"\xff" * 4), Counter))
+        for n in [0, 4]:
+            self.assertRaises(ValueError, ngrams_counts, b"abc", n=n)
+        self.assertRaises(ValueError, ngrams_counts, b"abc", step=-1)
+        self.assertEqual(ngrams_counts(b"a", n=2), {})
+        self.assertTrue(isinstance(ngrams_counts(seq := b"\x00" * 4 + os.urandom(120) + b"\xff" * 4), list))
+        self.assertTrue(isinstance(ngrams_counts(seq := b"\x00" * 4 + os.urandom(120) + b"\xff" * 4, n=2), list))
         class Test:
             bytes = seq
-            size = len(seq)
-        histogram = ngrams_distribution(t := Test(), exclude=(b"\x00", b"\xff"))
-        self.assertTrue(isinstance(histogram, list))
+        self.assertTrue(isinstance(histogram := ngrams_distribution(t := Test(), exclude=(b"\x00", b"\xff")), list))
         self.assertNotIn(b"\x00", [b for b, c in histogram])
         self.assertNotIn(b"\xff", [b for b, c in histogram])
         histogram2 = ngrams_distribution(t, n_most_common=300)

exeplot-0.4.3/src/exeplot/VERSION.txt

@@ -1 +0,0 @@
-0.4.3

exeplot-0.4.3/src/exeplot/__init__.py

@@ -1,5 +0,0 @@
-# -*- coding: UTF-8 -*-
-from .__conf__ import *
-from .plots import *
-from .plots import __all__
-

exeplot-0.4.3/src/exeplot/utils.py

@@ -1,67 +0,0 @@
-# -*- coding: UTF-8 -*-
-from math import log2
-
-
-__all__ = ["ensure_str", "human_readable_size", "ngrams_counts", "ngrams_distribution", "shannon_entropy"]
-
-shannon_entropy = lambda b: -sum([p*log2(p) for p in [float(ctr)/len(b) for ctr in [b.count(c) for c in set(b)]]]) or 0.
-
-
-def ensure_str(s, encoding='utf-8', errors='strict'):
-    """ Ensure that an input string is decoded. """
-    if isinstance(s, bytes):
-        try:
-            return s.decode(encoding, errors)
-        except:
-            return s.decode("latin-1")
-    elif not isinstance(s, (str, bytes)):
-        raise TypeError("not expecting type '%s'" % type(s))
-    return s
-
-
-def human_readable_size(size, precision=0):
-    """ Display bytes' size in a human-readable format given a precision. """
-    i, units = 0, ["B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"]
-    while size >= 1024 and i < len(units)-1:
-        i += 1
-        size /= 1024.0
-    return "%.*f%s" % (precision, size, units[i])
-
-
-def ngrams_counts(byte_obj, n=1, step=1):
-    """ Output the Counter instance for an input byte sequence or byte object based on n-grams.
-         If the input is a byte object, cache the result.
-    
-    :param byte_obj:      byte sequence ('bytes') or byte object with "bytes" and "size" attributes (i.e. pathlib2.Path)
-    :param n: n determining the size of n-grams, defaults to 1
-    :param step:          step for sliding the n-grams
-    """
-    from collections import Counter
-    if isinstance(byte_obj, (str, bytes)):
-        return Counter(byte_obj[i:i+n] for i in range(0, len(byte_obj)-n+1, step))
-    elif hasattr(byte_obj, "bytes") and hasattr(byte_obj, "size"):
-        if not hasattr(byte_obj, "_ngram_counts_cache"):
-            byte_obj._ngram_counts_cache = {}
-        if n not in byte_obj._ngram_counts_cache.keys():
-            byte_obj._ngram_counts_cache[n] = Counter(byte_obj.bytes[i:i+n] for i in range(0, byte_obj.size-n+1, step))
-        return byte_obj._ngram_counts_cache[n]
-    raise TypeError("Bad input type ; should be a byte sequence or object")
-
-
-def ngrams_distribution(byte_obj, n=1, step=1, n_most_common=None, n_exclude_top=0, exclude=None):
-    """ Compute the n-grams distribution of an input byte sequence or byte object given exclusions.
-    
-    :param byte_obj:      byte sequence ('bytes') or byte object with "bytes" and "size" attributes (i.e. pathlib2.Path)
-    :param n:             n determining the size of n-grams, defaults to 1
-    :param step:          step for sliding the n-grams
-    :param n_most_common: number of n-grams to be kept in the result, keep all by default
-    :param n_exclude_top: number of n-grams to be excluded from the top of the histogram, no exclusion by default
-    :param exclude:       list of specific n-grams to be excluded, no exclusion by default
-    :return:              list of n_most_common (n-gram, count) pairs
-    """
-    c = ngrams_counts(byte_obj, n, step)
-    r = c.most_common(len(c) if n_most_common is None else n_most_common + n_exclude_top + len(exclude or []))
-    if exclude is not None:
-        r = [(ngram, count) for ngram, count in r if ngram not in exclude]
-    return r[n_exclude_top:n_exclude_top+(n_most_common or len(c))]
-