exeplot 0.4.2__tar.gz → 0.5.2__tar.gz

{exeplot-0.4.2 → exeplot-0.5.2}/.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-0.4.2 → exeplot-0.5.2}/.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-0.4.2 → exeplot-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exeplot
-Version: 0.4.2
+Version: 0.5.2
 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
@@ -730,6 +730,14 @@ $ exeplot byte calc_packed.exe
 
 ![Byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
 
+Draw a simplified byte plot of `calc_packed.exe`:
+
+```sh
+$ 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_byte2.png?raw=true)
+
 Draw a pie plot of `calc_packed.exe`:
 
 ```sh
@@ -754,4 +762,12 @@ $ exeplot entropy calc_orig.exe calc_packed.exe
 
 ![Entropy plot of `calc_orig.exe` and `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_orig_entropy.png?raw=true)
 
+Draw a simplified entropy plot of `calc_packed.exe`:
+
+```sh
+$ exeplot entropy calc_packed.exe --no-title --no-legend --no-label --no-entrypoint
+```
+
+![Simplified entropy plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_entropy.png?raw=true)
+
 

{exeplot-0.4.2 → exeplot-0.5.2}/README.md

@@ -26,6 +26,14 @@ $ exeplot byte calc_packed.exe
 
 ![Byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
 
+Draw a simplified byte plot of `calc_packed.exe`:
+
+```sh
+$ 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_byte2.png?raw=true)
+
 Draw a pie plot of `calc_packed.exe`:
 
 ```sh
@@ -50,4 +58,12 @@ $ exeplot entropy calc_orig.exe calc_packed.exe
 
 ![Entropy plot of `calc_orig.exe` and `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_orig_entropy.png?raw=true)
 
+Draw a simplified entropy plot of `calc_packed.exe`:
+
+```sh
+$ exeplot entropy calc_packed.exe --no-title --no-legend --no-label --no-entrypoint
+```
+
+![Simplified entropy plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_entropy.png?raw=true)
+
 

{exeplot-0.4.2 → exeplot-0.5.2}/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: 96.54%"><title>coverage: 96.54%</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">96.54%</text><text x="865" y="140" transform="scale(.1)" fill="#fff" textLength="430">96.54%</text></g></svg>

{exeplot-0.4.2 → exeplot-0.5.2}/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-0.5.2/src/exeplot/VERSION.txt

@@ -0,0 +1 @@
+0.5.2

{exeplot-0.4.2 → exeplot-0.5.2}/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-0.4.2 → exeplot-0.5.2}/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"])
@@ -34,6 +35,14 @@ def main():
         plot_func = globals()[plot]
         plot_parser = plot_func.__args__(plots.add_parser(plot, help=plot_func.__doc__.strip(), add_help=False))
         opt = plot_parser.add_argument_group("options")
+        if plot == "diff":
+            opt.add_argument("--no-colormap", action="store_true", help="do not display the color map (default: False)")
+        if plot == "entropy":
+            opt.add_argument("--no-entrypoint", action="store_true",
+                             help="do not display the entry point (default: False)")
+        if plot in ["entropy", "pie"]:
+            opt.add_argument("--no-label", action="store_true", help="do not display the labels (default: False)")
+        opt.add_argument("--no-legend", action="store_true", help="do not display the legend (default: False)")
         opt.add_argument("--no-title", action="store_true", help="do not display the title (default: False)")
         extra = plot_parser.add_argument_group("extra arguments")
         extra.add_argument("-h", "--help", action="help", help="show this help message and exit")

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/plots/byte.py

@@ -53,39 +53,41 @@ def plot(executable, height=600, grayscale=False, **kwargs):
                 pass
         max_w = sum(max_txt_w) + (n_cols - 1) * txt_spacing
         # draw a separator
-        images.append(Image.new(m, (int(.05 * height), height), "white"))
+        if not kwargs.get('no_legend', False):
+            images.append(Image.new(m, (int(.05 * height), height), "white"))
         # draw a sections plot aside
         img = Image.new(m, (s, s), "white")
         # draw the legend with section names
-        legend = Image.new(m, (max_w, height), "white")
-        draw = ImageDraw.Draw(legend)
-        _xy = lambda n, c: (txt_spacing + sum(max_txt_w[:c]) + len(max_txt_w[:c]) * txt_spacing, \
-                            txt_spacing + (n % n_lab_per_col) * (txt_spacing + txt_h))
-        _c_func = [_rgb, _gs][grayscale]
-        for i, name, start, end, color in binary:
-            if start != end:
-                x0, y0 = min(max(ceil(((start / factor) % s)) - 1, 0), s - 1), \
-                         min(max(ceil(start / s / factor) - 1, 0), s - 1)
-                xN, yN = min(max(ceil(((end / factor) % s)) - 1, 0), s - 1), \
-                         min(max(ceil(end / s / factor) - 1, 0), s - 1)
-                if y0 == yN:
-                    xN = min(max(x0 + 1, xN), s - 1)
-                c = _c_func(color)
-                for x in range(x0, s if y0 < yN else xN):
-                    img.putpixel((x, y0), c)
-                for y in range(y0 + 1, yN):
-                    for x in range(0, s):
-                        img.putpixel((x, y), c)
-                if yN > y0:
-                    for x in range(0, xN):
-                        img.putpixel((x, yN), c)
-            # fill the legend with the current section name
-            if name.startswith("TOTAL"):
-                color = "black"
-            draw.text(_xy(i, ceil((i + 1) / n_lab_per_col) - 1), name, fill=_c_func(color), font=font)
-        images.append(img.resize((int(img.size[0] * sf * .2), height), resample=Image.Resampling.BOX))
-        images.append(Image.new(m, (int(.03 * height), height), "white"))  # draw another separator
-        images.append(legend)
+        if not kwargs.get('no_legend', False):
+            legend = Image.new(m, (max_w, height), "white")
+            draw = ImageDraw.Draw(legend)
+            _xy = lambda n, c: (txt_spacing + sum(max_txt_w[:c]) + len(max_txt_w[:c]) * txt_spacing, \
+                                txt_spacing + (n % n_lab_per_col) * (txt_spacing + txt_h))
+            _c_func = [_rgb, _gs][grayscale]
+            for i, name, start, end, color in binary:
+                if start != end:
+                    x0, y0 = min(max(ceil(((start / factor) % s)) - 1, 0), s - 1), \
+                             min(max(ceil(start / s / factor) - 1, 0), s - 1)
+                    xN, yN = min(max(ceil(((end / factor) % s)) - 1, 0), s - 1), \
+                             min(max(ceil(end / s / factor) - 1, 0), s - 1)
+                    if y0 == yN:
+                        xN = min(max(x0 + 1, xN), s - 1)
+                    c = _c_func(color)
+                    for x in range(x0, s if y0 < yN else xN):
+                        img.putpixel((x, y0), c)
+                    for y in range(y0 + 1, yN):
+                        for x in range(0, s):
+                            img.putpixel((x, y), c)
+                    if yN > y0:
+                        for x in range(0, xN):
+                            img.putpixel((x, yN), c)
+                # fill the legend with the current section name
+                if name.startswith("TOTAL"):
+                    color = "black"
+                draw.text(_xy(i, ceil((i + 1) / n_lab_per_col) - 1), name, fill=_c_func(color), font=font)
+            images.append(img.resize((int(img.size[0] * sf * .2), height), resample=Image.Resampling.BOX))
+            images.append(Image.new(m, (int(.03 * height), height), "white"))  # draw another separator
+            images.append(legend)
     # combine images horizontally
     x, img = 0, Image.new(m, (sum(i.size[0] for i in images), height))
     for i in images:

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/plots/diff.py

@@ -133,13 +133,14 @@ def plot(executable, executable2, legend1="", legend2="", **kwargs):
                      va="center")
     # ---------------------------------------------- CONFIGURE THE FIGURE ----------------------------------------------
     logger.debug("> configuring the figure")
-    cb = plt.colorbar(ScalarMappable(cmap=ListedColormap(colors, N=4)),
-                      location='bottom', ax=objs[-1], fraction=0.3, aspect=50, ticks=[0.125, 0.375, 0.625, 0.875])
-    cb.set_ticklabels(['removed', 'modified', 'untouched', 'added'])
-    cb.ax.tick_params(length=0)
-    cb.outline.set_visible(False)
+    if not kwargs.get('no_colorbar', False):
+        cb = plt.colorbar(ScalarMappable(cmap=ListedColormap(colors, N=4)),
+                          location='bottom', ax=objs[-1], fraction=0.3, aspect=50, ticks=[0.125, 0.375, 0.625, 0.875])
+        cb.set_ticklabels(['removed', 'modified', 'untouched', 'added'])
+        cb.ax.tick_params(length=0)
+        cb.outline.set_visible(False)
     plt.subplots_adjust(left=[.15, .02][legend1 == "" and legend2 == ""], bottom=.5/max(1.75, nf))
     h, l = (objs[int(title)] if nf+int(title) > 1 else objs).get_legend_handles_labels()
-    if len(h) > 0:
+    if len(h) > 0 and not kwargs.get('no_legend', False):
         plt.figlegend(h, l, loc=[.8, .135], ncol=1, prop={'size': fs_ref*.7})
 

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/plots/entropy.py

@@ -58,8 +58,7 @@ def data(executable, n_samples=N_SAMPLES, window_size=lambda s: 2*s, **kwargs):
         name = binary.section_names[section.name]
         start = max(data['sections'][-1][1] if len(data['sections']) > 0 else 0, int(section.offset // cs))
         rawsize = max(section.size, len(section.content)) # take section header's raw size but consider real size too
-        max_end = min(max(start + MIN_ZONE_WIDTH, int((section.offset + rawsize) // cs)),
-                      len(data['entropy']) - 1)
+        max_end = min(max(start + MIN_ZONE_WIDTH, int((section.offset + rawsize) // cs)), len(data['entropy']) - 1)
         data['sections'].append(__d(int(min(start, max_end - MIN_ZONE_WIDTH)), int(max_end), name))
     # adjust the entry point (be sure that its position on the plot is within the EP section)
     if data['ep']:
@@ -121,36 +120,37 @@ def plot(*filenames, labels=None, sublabel=None, scale=False, target=None, **kwa
             fig.suptitle(f"Entropy per section of {d['type']} file: {target or d['name']}", x=x_t, y=y_t,
                          ha="center", va="bottom", **kwargs['title-font'])
         # set the label and sublabel and display them
-        try:
-            label = labels[i]
-            if isinstance(label, type(lambda: 0)):
-                label = label(d)
-        except:
-            pass
         ref_point = .55
-        if sublabel and not (isinstance(sublabel, str) and "ep" in sublabel and d['ep'] is None):
-            if isinstance(sublabel, str):
-                sublabel = SUBLABELS.get(sublabel)
-            sl = sublabel(d) if isinstance(sublabel, type(lambda: 0)) else None
-            if sl:
-                nl, y_pos, f_color = len(sl.split("\n")), ref_point, "black"
-                if label:
-                    f_size, f_color = fs_ref*.6 if nl <= 2 else fs_ref*.5, "gray"
-                    y_pos = max(0., ref_point - nl * [.16, .12, .09, .08][min(4, nl)-1])
-                else:
-                    f_size = fs_ref * [.7, .6, .5][min(3, nl)-1]
-                obj.text(s=sl, x=-420., y=y_pos, fontsize=f_size, color=f_color, ha="left", va="center")
-        if label:
-            y_pos = ref_point
-            if sublabel:
-                nl = len(sl.split("\n"))
-                y_pos = min(1.3, ref_point + .3 + nl * [.16, .12, .09, .08][min(4, nl)-1])
-            obj.text(s=label, x=-420., y=y_pos, fontsize=fs_ref, ha="left", va="center")
-            h, h_midlen = d['hash'], round(len(d['hash'])/2+.5)
-            h = f"{h[:h_midlen]}\n{h[h_midlen:]}"
-            obj.text(s=h, x=-420., y=y_pos-.35, fontsize=fs_ref*.5, ha="left", va="center")
+        if not kwargs.get('no_label', False):
+            try:
+                label = labels[i]
+                if isinstance(label, type(lambda: 0)):
+                    label = label(d)
+            except:
+                pass
+            if sublabel and not (isinstance(sublabel, str) and "ep" in sublabel and d['ep'] is None):
+                if isinstance(sublabel, str):
+                    sublabel = SUBLABELS.get(sublabel)
+                sl = sublabel(d) if isinstance(sublabel, type(lambda: 0)) else None
+                if sl:
+                    nl, y_pos, f_color = len(sl.split("\n")), ref_point, "black"
+                    if label:
+                        f_size, f_color = fs_ref*.6 if nl <= 2 else fs_ref*.5, "gray"
+                        y_pos = max(0., ref_point - nl * [.16, .12, .09, .08][min(4, nl)-1])
+                    else:
+                        f_size = fs_ref * [.7, .6, .5][min(3, nl)-1]
+                    obj.text(s=sl, x=-420., y=y_pos, fontsize=f_size, color=f_color, ha="left", va="center")
+            if label:
+                y_pos = ref_point
+                if sublabel:
+                    nl = len(sl.split("\n"))
+                    y_pos = min(1.3, ref_point + .3 + nl * [.16, .12, .09, .08][min(4, nl)-1])
+                obj.text(s=label, x=-420., y=y_pos, fontsize=fs_ref, ha="left", va="center")
+                h, h_midlen = d['hash'], round(len(d['hash'])/2+.5)
+                h = f"{h[:h_midlen]}\n{h[h_midlen:]}"
+                obj.text(s=h, x=-420., y=y_pos-.35, fontsize=fs_ref*.5, ha="left", va="center")
         # display the entry point
-        if d['ep']:
+        if d['ep'] and not kwargs.get('no_entrypoint', False):
             obj.vlines(x=d['ep'][0], ymin=0, ymax=1, color="r", zorder=11).set_label("Entry point")
             obj.text(d['ep'][0], -.15, "______", c="r", ha="center", rotation=90, size=.8,
                      bbox={'boxstyle': "rarrow", 'fc': "r", 'ec': "r", 'lw': 1})
@@ -166,7 +166,7 @@ def plot(*filenames, labels=None, sublabel=None, scale=False, target=None, **kwa
                 color_cursor += 1
             # draw the section
             obj.fill_between(x, 0, 1, facecolor=c, alpha=.2)
-            if name not in ["Headers", "Overlay"]:
+            if name not in ["Headers", "Overlay"] and not kwargs.get('no_label', False):
                 if last is None or (start + end) // 2 - (last[0] + last[1]) // 2 > n // 12:
                     pos_y = N_TOP
                 else:
@@ -197,6 +197,6 @@ def plot(*filenames, labels=None, sublabel=None, scale=False, target=None, **kwa
     h, l = (objs[[0, 1][title]] if nf+[0, 1][title] > 1 else objs).get_legend_handles_labels()
     h.append(Patch(facecolor="black")), l.append("Headers")
     h.append(Patch(facecolor="lightgray")), l.append("Overlay")
-    if len(h) > 0:
+    if len(h) > 0 and not kwargs.get('no_legend', False):
         plt.figlegend(h, l, loc=lloc, ncol=1 if lloc_side else len(l), prop={'size': fs_ref*.7})
 

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/plots/nested_pie.py

@@ -32,9 +32,10 @@ def plot(executable, **kwargs):
         ax.pie(w, radius=1-i*size, colors=colors, startangle=90, wedgeprops={'width': size}, **pie_kw)
     # ---------------------------------------------- CONFIGURE THE FIGURE ----------------------------------------------
     logger.debug("> configuring the figure")
-    ncols = ceil(len(legend['colors']) / 12)
-    ax.legend([plt.Rectangle((0, 0), 1, 1, color=c) for c in legend['colors']], legend['texts'], loc="center left",
-              bbox_to_anchor=(1, 0, 0.5, 1), ncol=ncols, fontsize=ceil(kwargs['config']['font_size']*.7))
+    if not kwargs.get('no_legend', False):
+        ncols = ceil(len(legend['colors']) / 12)
+        ax.legend([plt.Rectangle((0, 0), 1, 1, color=c) for c in legend['colors']], legend['texts'], loc="center left",
+                  bbox_to_anchor=(1, 0, 0.5, 1), ncol=ncols, fontsize=ceil(kwargs['config']['font_size']*.7))
     if not kwargs.get('no_title', False):
         fsp = plt.gcf().subplotpars
         plt.title(f"Nested pie plot of {binary.type} file: {binary.basename}", **kwargs['title-font'])

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/plots/pie.py

@@ -23,16 +23,19 @@ def plot(executable, donut=False, **kwargs):
     for _, _, data, _, colors, legend in binary._data():
         pass
     ncols, n = ceil(len(legend['colors']) / 12), sum(data)
-    labels = [f"{100 * d / n:.1f}%" if round(d / n, 2) >= .02 and c != "white" else "" for d, c in zip(data, colors)]
     txt_kw = {k: v for k, v in kwargs['xlabel-font'].items()}
     txt_kw['color'] = "w"
     pie_kw = {'shadow': SHADOW} if kwargs['config']['shadow'] else {}
-    _, texts = ax.pie(data, colors=colors, labels=labels, textprops=txt_kw, labeldistance=.55, startangle=90,
+    if not kwargs.get('no_label', False):
+        pie_kw['labels'] = [f"{100 * d / n:.1f}%" if round(d / n, 2) >= .02 and c != "white" else "" \
+                            for d, c in zip(data, colors)]
+    _, texts = ax.pie(data, colors=colors, textprops=txt_kw, labeldistance=.55, startangle=90,
                            wedgeprops={'width': [1., .55][donut]}, **pie_kw)
     # ---------------------------------------------- CONFIGURE THE FIGURE ----------------------------------------------
     logger.debug("> configuring the figure")
-    ax.legend([plt.Rectangle((0, 0), 1, 1, color=c) for c in legend['colors']], legend['texts'], loc="center left",
-              bbox_to_anchor=(1, 0, 0.5, 1), ncol=ncols, fontsize=ceil(fs_ref*.7))
+    if not kwargs.get('no_legend', False):
+        ax.legend([plt.Rectangle((0, 0), 1, 1, color=c) for c in legend['colors']], legend['texts'], loc="center left",
+                  bbox_to_anchor=(1, 0, 0.5, 1), ncol=ncols, fontsize=ceil(fs_ref*.7))
     plt.setp(texts, size=fs_ref*.8, weight="bold")
     if not kwargs.get('no_title', False):
         fsp = plt.gcf().subplotpars

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot/utils.py

@@ -1,5 +1,7 @@
 # -*- 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"]
@@ -7,7 +9,7 @@ __all__ = ["ensure_str", "human_readable_size", "ngrams_counts", "ngrams_distrib
 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'):
+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:
@@ -19,7 +21,7 @@ def ensure_str(s, encoding='utf-8', errors='strict'):
     return s
 
 
-def human_readable_size(size, precision=0):
+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:
@@ -28,27 +30,45 @@ def human_readable_size(size, precision=0):
     return "%.*f%s" % (precision, size, units[i])
 
 
-def ngrams_counts(byte_obj, n=1, step=1):
+def ngrams_counts(byte_obj: bytes | object, n: int = 1, step: int = 1) -> dict[bytes, int]:
     """ 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
+    :param start:         number of bytes to start from
     """
-    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]
+    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")
+    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))}
+        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, n=1, step=1, n_most_common=None, n_exclude_top=0, exclude=None):
+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)
@@ -60,7 +80,8 @@ def ngrams_distribution(byte_obj, n=1, step=1, n_most_common=None, n_exclude_top
     :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 []))
+    n = len(c) if n_most_common is None else n_most_common + n_exclude_top + len(exclude or [])
+    r = sorted(c.items(), key=lambda p: p[1], reverse=True)[:n]
     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-0.4.2 → exeplot-0.5.2}/src/exeplot.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exeplot
-Version: 0.4.2
+Version: 0.5.2
 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
@@ -730,6 +730,14 @@ $ exeplot byte calc_packed.exe
 
 ![Byte plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_byte.png?raw=true)
 
+Draw a simplified byte plot of `calc_packed.exe`:
+
+```sh
+$ 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_byte2.png?raw=true)
+
 Draw a pie plot of `calc_packed.exe`:
 
 ```sh
@@ -754,4 +762,12 @@ $ exeplot entropy calc_orig.exe calc_packed.exe
 
 ![Entropy plot of `calc_orig.exe` and `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_orig_entropy.png?raw=true)
 
+Draw a simplified entropy plot of `calc_packed.exe`:
+
+```sh
+$ exeplot entropy calc_packed.exe --no-title --no-legend --no-label --no-entrypoint
+```
+
+![Simplified entropy plot of `calc_packed.exe`](https://github.com/packing-box/python-exeplot/blob/main/docs/pages/img/calc_packed_entropy.png?raw=true)
+
 

{exeplot-0.4.2 → exeplot-0.5.2}/src/exeplot.egg-info/SOURCES.txt

@@ -15,10 +15,14 @@ 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
 docs/pages/img/logo.png
+docs/pages/img/upx_calc_byte.png
+docs/pages/img/upx_calc_entropy.png
 src/exeplot/VERSION.txt
 src/exeplot/__conf__.py
 src/exeplot/__info__.py

{exeplot-0.4.2 → exeplot-0.5.2}/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
@@ -21,10 +20,14 @@ 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), dict))
+        self.assertTrue(isinstance(ngrams_counts(seq := b"\x00" * 4 + os.urandom(120) + b"\xff" * 4, n=2), dict))
         class Test:
             bytes = seq
-            size = len(seq)
         histogram = ngrams_distribution(t := Test(), exclude=(b"\x00", b"\xff"))
         self.assertTrue(isinstance(histogram, list))
         self.assertNotIn(b"\x00", [b for b, c in histogram])

{exeplot-0.4.2 → exeplot-0.5.2}/tests/test_plots.py

@@ -6,6 +6,7 @@ from exeplot import *
 from exeplot import __all__ as _plots
 from exeplot.__conf__ import configure
 from exeplot.__main__ import _parser
+from itertools import cycle
 from unittest import TestCase
 
 
@@ -69,6 +70,13 @@ class TestPlotOptions(TestCase):
                            scale=True):
             os.remove(img)
             plt.clf()
+        g = cycle(iter_files())
+        for k in ["title", "legend", "label", "entrypoint"]:
+            path, kw = next(g), {(k := f'no_{k}'): True}
+            print(f"plotting entropy of {path} ({k}=True)...")
+            for img in entropy(path, **kw):
+                os.remove(img)
+                plt.clf()
     
     def test_pie_plot_function(self):
         for path in iter_files():
@@ -76,4 +84,11 @@ class TestPlotOptions(TestCase):
             for img in pie(path, donut=True):
                 os.remove(img)
                 plt.clf()
+        g = cycle(iter_files())
+        for k in ["title", "legend", "label"]:
+            path, kw = next(g), {(k := f'no_{k}'): True}
+            print(f"plotting pie of {path} ({k}=True)...")
+            for img in pie(path, **kw):
+                os.remove(img)
+                plt.clf()
 

exeplot-0.4.2/src/exeplot/VERSION.txt

@@ -1 +0,0 @@
-0.4.2