SP-1260 Fix UTF-16 Filename Encoding (#46)

* changed line 310 to return a utf-8 compatible version of the filename

CHANGELOG.md

@@ -9,10 +9,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Upcoming changes...
 
-## [1.13.1] - PLACEHOLDER
+## [1.14.0] - 2024-08-09
 ### Added
 - Added support for Python3.12
-  - Module `pkg_resources` has been replaced with `importlib_resources` 
+  - Module `pkg_resources` has been replaced with `importlib_resources`
+- Added support for UTF-16 filenames 
 
 ## [1.13.0] - 2024-06-05
 ### Added
@@ -336,3 +337,4 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [1.12.2]: https://github.com/scanoss/scanoss.py/compare/v1.12.1...v1.12.2
 [1.12.3]: https://github.com/scanoss/scanoss.py/compare/v1.12.2...v1.12.3
 [1.13.0]: https://github.com/scanoss/scanoss.py/compare/v1.12.3...v1.13.0
+[1.14.0]: https://github.com/scanoss/scanoss.py/compare/v1.13.0...v1.14.0

src/scanoss/__init__.py

@@ -22,4 +22,4 @@
    THE SOFTWARE.
 """
 
-__version__ = '1.13.0'
+__version__ = '1.14.0'

src/scanoss/winnowing.py

@@ -307,11 +307,7 @@ def wfp_for_contents(self, file: str, bin_file: bool, contents: bytes) -> str:
             return ''
         # Print file line
         content_length = len(contents)
-        # Use repr() to get an unambiguous string representation
-        file = repr(file)
-        # Remove the surrounding quotes that repr() adds
-        file = file[1:-1]
-        wfp_filename = file
+        wfp_filename = repr(file).strip("'")  # return a utf-8 compatible version of the filename
         if self.obfuscate:  # hide the real size of the file and its name, but keep the suffix
             wfp_filename = f'{self.ob_count}{pathlib.Path(file).suffix}'
             self.ob_count = self.ob_count + 1