use fictional names instead of folder paths

compare50/__main__.py

@@ -14,6 +14,7 @@
 import tempfile
 import requests
 import packaging.version
+import names
 
 import attr
 import lib50
@@ -299,10 +300,10 @@ def expand_patterns(patterns):
 
 
 def check_version(package_name=__package__, timeout=5):
-    """Check for newer version of the package on PyPI"""    
+    """Check for newer version of the package on PyPI"""
     if not __version__:
         return
-    
+
     try:
         current = packaging.version.parse(__version__)
         latest = max(requests.get(f"https://pypi.org/pypi/{package_name}/json", timeout=timeout).json()["releases"], key=packaging.version.parse)
@@ -468,9 +469,23 @@ def main():
                     object.__setattr__(sub, "preprocessor", preprocessor)
                 pass_to_results[pass_] = _api.compare(scores, ignored_files, pass_)
 
+        all_subs = list(subs) + list(archive_subs) + list(ignored_subs)
+
+        # Generate a unique first name for each submission
+        fictional_names = []
+        used_names = set()
+        while len(fictional_names) < len(all_subs):
+            name = names.get_first_name()
+            if name not in used_names:
+                fictional_names.append(name)
+                used_names.add(name)
+
+        # Map each Submission to a fictional name
+        sub_to_machine_name = {sub: name for sub, name in zip(all_subs, fictional_names)}
+
         # Render results
         with _api.progress_bar("Rendering", disable=args.debug):
-            index = _renderer.render(pass_to_results, dest=args.output)
+            index = _renderer.render(pass_to_results, dest=args.output, sub_to_machine_name=sub_to_machine_name)
 
     termcolor.cprint(
         f"Done! Visit file://{index.absolute()} in a web browser to see the results.", "green")

compare50/_renderer/_renderer.py

@@ -68,6 +68,7 @@ def percentage(self):
 
 @attr.s(slots=True)
 class HTMLSubmission:
+    path = attr.ib(converter=str)
     name = attr.ib(converter=str)
     files = attr.ib()
     num_chars_matched = attr.ib()
@@ -81,7 +82,7 @@ def percentage(self):
             return 0
 
 
-def render(pass_to_results, dest):
+def render(pass_to_results, dest, sub_to_machine_name):
     bar = _api.get_progress_bar()
     dest = pathlib.Path(dest)
 
@@ -102,7 +103,7 @@ def render(pass_to_results, dest):
     with _api.Executor() as executor:
         # Load static files
         max_id = len(results_per_sub_pair)
-        for id, html in executor.map(_RenderTask(dest, max_id, match_js, match_css), enumerate(results_per_sub_pair, 1)):
+        for id, html in executor.map(_RenderTask(dest, max_id, match_js, match_css, sub_to_machine_name), enumerate(results_per_sub_pair, 1)):
             with open(dest / f"match_{id}.html", "w") as f:
                 f.write(html)
             bar.update()
@@ -125,13 +126,13 @@ def render(pass_to_results, dest):
     subs = set()
     graph_info = {"nodes": [], "links": [], "data": {}}
     for i, result in enumerate(ranking_results):
-        graph_info["links"].append({"index":i, "source": str(result.sub_a.path), "target": str(result.sub_b.path), "value": 10 * result.score.score/max_score})
+        graph_info["links"].append({"index":i, "source": sub_to_machine_name[result.sub_a], "target": sub_to_machine_name[result.sub_b], "value": 10 * result.score.score/max_score})
         subs.add(result.sub_a)
         subs.add(result.sub_b)
 
     for sub in subs:
-        graph_info["nodes"].append({"id": str(sub.path)})
-        graph_info["data"][str(sub.path)] = {"is_archive": sub.is_archive}
+        graph_info["nodes"].append({"id": sub_to_machine_name[sub]})
+        graph_info["data"][sub_to_machine_name[sub]] = {"is_archive": sub.is_archive, "path": str(sub.path)}
 
     index_css = common_css + [read_file(STATIC / "index.css")]
     index_js = [read_file(STATIC / f) for f in ("d3.v4.min.js", "d3-scale-chromatic.v1.min.js", "d3-simple-slider.js", "index.js")]
@@ -160,20 +161,21 @@ def read_file(fname):
 
 
 class _RenderTask:
-    def __init__(self, dest, max_id, js, css):
+    def __init__(self, dest, max_id, js, css, sub_to_machine_name):
         dest.mkdir(exist_ok=True)
         self.dest = dest
         self.max_id = max_id
         self.js = js
         self.css = css
+        self.sub_to_machine_name = sub_to_machine_name
 
     def __call__(self, arg):
         id, results = arg
         data = []
         match_htmls = []
 
         for result in results:
-            renderer = _Renderer(result.name)
+            renderer = _Renderer(result.name, self.sub_to_machine_name)
             score = result.score
             groups = result.groups
             ignored_spans = result.ignored_spans
@@ -236,8 +238,9 @@ def _prepare_dest(dest):
 
 
 class _Renderer:
-    def __init__(self, name):
+    def __init__(self, name, sub_to_machine_name):
         self.name = name
+        self.sub_to_machine_name = sub_to_machine_name
         self._frag_id_counter = -1
         self._span_id_store = IdStore()
         self._group_id_store = IdStore()
@@ -285,7 +288,7 @@ def html_submission(self, submission, file_to_spans, ignored_spans):
         html_files = self.html_files(submission, file_to_spans, ignored_spans)
         num_chars_matched = sum(f.num_chars_matched for f in html_files)
         num_chars = sum(f.num_chars for f in html_files)
-        return HTMLSubmission(submission.path, html_files, num_chars_matched, num_chars)
+        return HTMLSubmission(submission.path, self.sub_to_machine_name[submission], html_files, num_chars_matched, num_chars)
 
     def data(self, result, html_fragments, ignored_spans):
         fragment_to_spans = {}

compare50/_renderer/static/index.js

@@ -361,7 +361,11 @@ function update_index() {
         new_trs.append("td")
             .attr("class", "sub_name")
             .datum(d => d[field])
-            .html(d => GRAPH.data[d.id].is_archive ? `${ARCHIVE_IMG} ${d.id}` : d.id);
+            .html(d => {
+                const fic_name = GRAPH.data[d.id].is_archive ? `${ARCHIVE_IMG} ${d.id}` : d.id;
+                const path = GRAPH.data[d.id].path || '';
+                return `<span title="${path}">${fic_name}</span>`;
+            });
     }
 
     new_trs.append("td")

compare50/_renderer/templates/match.html

@@ -4,7 +4,7 @@
     <div class="row sticky-top bg-dark text-light" id="{{name}}sub_names">
         {% for sub in sub_a, sub_b %}
             <div class="col-sm-6 col-2 sub_name">
-                <h5>{{sub.name}} ({{sub.percentage}}%)</h5>
+                <h5 title="{{sub.path}}">{{sub.name}} ({{sub.percentage}}%)</h5>
             </div>
         {% endfor %}
     </div>

setup.py

@@ -12,7 +12,7 @@
     license="GPLv3",
     description="This is compare50, with which you can compare files for similarities.",
     long_description="This is compare50, with which you can compare files for similarities.",
-    install_requires=["attrs>=18,<21", "intervaltree>=3,<4", "lib50>=2,<4", "numpy>=1.15,<2", "pygments>=2.2,<3", "jinja2>=3,<4", "termcolor>=1.1.0,<2", "tqdm>=4.32,<5", "importlib"],
+    install_requires=["attrs>=18,<21", "intervaltree>=3,<4", "lib50>=2,<4", "numpy>=1.15,<2", "pygments>=2.2,<3", "jinja2>=3,<4", "termcolor>=1.1.0,<2", "tqdm>=4.32,<5", "importlib", "names"],
     extras_require = {
         "develop": ["sphinx", "sphinx_rtd_theme", "sphinx-autobuild", "line_profiler"]
     },
@@ -22,6 +22,6 @@
     packages=find_packages(exclude=["tests"]),
     scripts=["bin/compare50"],
     url="https://github.com/cs50/compare50",
-    version="1.2.13",
+    version="1.2.14",
     include_package_data=True,
 )