- fixed a bug with commits comprised of non-UTF8 text

Author: Gal Ben David

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name='PyRepScan',
-    version='0.5.0',
+    version='0.5.1',
     author='Gal Ben David',
     author_email='[email protected]',
     url='https://github.com/intsights/PyRepScan',

src/git_repository_scanner.cpp

@@ -10,6 +10,7 @@
 #include <pybind11/pybind11.h>
 #include <pybind11/stl.h>
 #include <taskflow/taskflow.hpp>
+#include <utf8/utf8.h>
 
 #include "rules_manager.hpp"
 
@@ -135,18 +136,27 @@ class GitRepositoryScanner {
                     git_oid_fmt(current_commit_id_string, current_commit_id);
 
                     const git_signature * current_commit_author = git_commit_author(current_commit);
-                    std::string current_commit_message = git_commit_message(current_commit);
+                    std::string current_commit_message = utf8::replace_invalid(
+                        git_commit_message(current_commit),
+                        '?'
+                    );
 
                     char new_file_oid[41] = {0};
                     git_oid_fmt(new_file_oid, &delta->new_file.id);
 
                     std::string current_commit_author_name = "";
                     if (nullptr != current_commit_author->name) {
-                        current_commit_author_name = current_commit_author->name;
+                        current_commit_author_name = utf8::replace_invalid(
+                            current_commit_author->name,
+                            '?'
+                        );
                     }
                     std::string current_commit_author_email = "";
                     if (nullptr != current_commit_author->email) {
-                        current_commit_author_email = current_commit_author->email;
+                        current_commit_author_email = utf8::replace_invalid(
+                            current_commit_author->email,
+                            '?'
+                        );
                     }
 
                     git_time_t commit_time = git_commit_time(current_commit);

src/utf8/utf8.h

@@ -0,0 +1,34 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "utf8/checked.h"
+#include "utf8/unchecked.h"
+
+#endif // header guard