Filenames must now be all-ASCII

jwodder · Sep 3, 2018 · 1fba4de · 1fba4de
1 parent b60b9fd
commit 1fba4de
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,8 @@ v0.3.0 (in development)
 -----------------------
 - When fetching the list of files for a project, the project name is now used
   to resolve ambiguous filenames.
+- The filename parser now requires all filenames to be all-ASCII (except for
+  wheels).
 
 v0.2.0 (2018-09-01)
 -------------------

diff --git a/pypi_simple.py b/pypi_simple.py
@@ -236,7 +236,7 @@ def parse_links(html, base_url=None, from_encoding=None):
 VERSION = r'[A-Za-z0-9_.!+-]+?'
 VERSION_NODASH = r'[A-Za-z0-9_.!+]+?'
 ARCHIVE_EXT = r'\.(?:tar|tar\.(?:bz2|gz|lz|lzma|xz|Z)|tbz|tgz|tlz|txz|zip)'
-PLAT_NAME = r'(?:aix|cygwin|darwin|linux|macosx|solaris|sunos|[wW]in)[-.\w]*'
+PLAT_NAME = r'(?:aix|cygwin|darwin|linux|macosx|solaris|sunos|[wW]in)[-.A-Za-z0-9_]*'
 PYVER = r'py[0-9]+\.[0-9]+'
 
 #: Regexes for package filenames that can be parsed unambiguously