From 009fcee154f96239f323a398b7f5d928f02062bb Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Tue, 27 Apr 2021 15:45:31 +0900
Subject: [PATCH] bpo-43651: Fix EncodingWarning in zipfile (GH-25650)

Backport of python/cpython#25650. Ref #84.
---
 test_zipp.py | 18 +++++++++---------
 zipp.py      |  3 +++
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/test_zipp.py b/test_zipp.py
index 77716a0..8b700ce 100644
--- a/test_zipp.py
+++ b/test_zipp.py
@@ -145,7 +145,7 @@ def test_subdir_is_dir(self, alpharep):
     def test_open(self, alpharep):
         root = zipp.Path(alpharep)
         a, b, g = root.iterdir()
-        with a.open() as strm:
+        with a.open(encoding="utf-8") as strm:
             data = strm.read()
         assert data == "content of a"
 
@@ -157,7 +157,7 @@ def test_open_write(self):
         zf = zipp.Path(zipfile.ZipFile(io.BytesIO(), mode='w'))
         with zf.joinpath('file.bin').open('wb') as strm:
             strm.write(b'binary contents')
-        with zf.joinpath('file.txt').open('w') as strm:
+        with zf.joinpath('file.txt').open('w', encoding="utf-8") as strm:
             strm.write('text file')
 
     def test_open_extant_directory(self):
@@ -188,7 +188,7 @@ def test_open_missing_directory(self):
     def test_read(self, alpharep):
         root = zipp.Path(alpharep)
         a, b, g = root.iterdir()
-        assert a.read_text() == "content of a"
+        assert a.read_text(encoding="utf-8") == "content of a"
         assert a.read_bytes() == b"content of a"
 
     @pass_alpharep
@@ -197,13 +197,13 @@ def test_joinpath(self, alpharep):
         a = root.joinpath("a.txt")
         assert a.is_file()
         e = root.joinpath("b").joinpath("d").joinpath("e.txt")
-        assert e.read_text() == "content of e"
+        assert e.read_text(encoding="utf-8") == "content of e"
 
     @pass_alpharep
     def test_joinpath_multiple(self, alpharep):
         root = zipp.Path(alpharep)
         e = root.joinpath("b", "d", "e.txt")
-        assert e.read_text() == "content of e"
+        assert e.read_text(encoding="utf-8") == "content of e"
 
     @pass_alpharep
     def test_traverse_truediv(self, alpharep):
@@ -211,7 +211,7 @@ def test_traverse_truediv(self, alpharep):
         a = root / "a.txt"
         assert a.is_file()
         e = root / "b" / "d" / "e.txt"
-        assert e.read_text() == "content of e"
+        assert e.read_text(encoding="utf-8") == "content of e"
 
     @pass_alpharep
     def test_traverse_simplediv(self, alpharep):
@@ -268,9 +268,9 @@ def test_mutability(self, alpharep):
         alpharep.writestr('foo.txt', 'foo')
         alpharep.writestr('bar/baz.txt', 'baz')
         assert any(child.name == 'foo.txt' for child in root.iterdir())
-        assert (root / 'foo.txt').read_text() == 'foo'
+        assert (root / 'foo.txt').read_text(encoding="utf-8") == 'foo'
         (baz,) = (root / 'bar').iterdir()
-        assert baz.read_text() == 'baz'
+        assert baz.read_text(encoding="utf-8") == 'baz'
 
     HUGE_ZIPFILE_NUM_ENTRIES = 2**13
 
@@ -304,7 +304,7 @@ def test_read_does_not_close(self, alpharep):
         alpharep = self.zipfile_ondisk(alpharep)
         with zipfile.ZipFile(alpharep) as file:
             for rep in range(2):
-                zipp.Path(file, 'a.txt').read_text()
+                zipp.Path(file, 'a.txt').read_text(encoding="utf-8")
 
     @pass_alpharep
     def test_subclass(self, alpharep):
diff --git a/zipp.py b/zipp.py
index 52c82a0..bf21cae 100644
--- a/zipp.py
+++ b/zipp.py
@@ -239,6 +239,8 @@ def open(self, mode='r', *args, pwd=None, **kwargs):
             if args or kwargs:
                 raise ValueError("encoding args invalid for binary operation")
             return stream
+        else:
+            kwargs["encoding"] = io.text_encoding(kwargs.get("encoding"))
         return io.TextIOWrapper(stream, *args, **kwargs)
 
     @property
@@ -262,6 +264,7 @@ def filename(self):
         return pathlib.Path(self.root.filename).joinpath(self.at)
 
     def read_text(self, *args, **kwargs):
+        kwargs["encoding"] = io.text_encoding(kwargs.get("encoding"))
         with self.open('r', *args, **kwargs) as strm:
             return strm.read()