From e6fb522465f554efb55285e49514940ded7491c9 Mon Sep 17 00:00:00 2001
From: Saiyam Jain <jimisierra2@gmail.com>
Date: Mon, 26 Oct 2026 02:44:26 +0530
Subject: [PATCH 1/2] gh-160309: Fix StreamReader.read() silently dropping
 incomplete final character

When a byte stream ends with an incomplete multibyte sequence (e.g. a
truncated UTF-8 character), StreamReader.read() would silently discard
those bytes: the read loop exited on empty newdata while bytebuffer still
held the fragment, and bytebuffer was never decoded.

Fix by detecting leftover bytes in bytebuffer when the underlying stream
is exhausted and decoding them immediately.  The codec's stateless decode
function (e.g. utf_8_decode with final=True) then applies the error
handler: 'strict' raises UnicodeDecodeError, 'replace' emits the
replacement character, and 'ignore' drops the bytes - matching the
behaviour of bytes.decode() and io.TextIOWrapper.
---
 Lib/codecs.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Lib/codecs.py b/Lib/codecs.py
index af6ab031157e790..eaa5da00630cd54 100644
--- a/Lib/codecs.py
+++ b/Lib/codecs.py
@@ -525,6 +525,15 @@ def read(self, size=-1, chars=-1, firstline=False):
             self.charbuffer += newchars
             # there was no data available
             if not newdata:
+                # The stream is exhausted.  If there are leftover bytes in
+                # bytebuffer, they form an incomplete character.  Decode them
+                # now so that the error handler is applied (strict raises,
+                # replace emits the replacement character, ignore drops them).
+                if self.bytebuffer:
+                    newchars, decodedbytes = self.decode(
+                        self.bytebuffer, self.errors)
+                    self.bytebuffer = self.bytebuffer[decodedbytes:]
+                    self.charbuffer += newchars
                 break
         if chars < 0:
             # Return everything we've got

From 51b3fda87983efa6fe209508bae24bb9d19b09b0 Mon Sep 17 00:00:00 2001
From: "blurb-it[bot]" <43283697+blurb-it[bot]@users.noreply.github.com>
Date: Sun, 25 Oct 2026 21:18:29 +0000
Subject: [PATCH 2/2] =?UTF-8?q?=F0=9F=93=9C=F0=9F=A4=96=20Added=20by=20blu?=
 =?UTF-8?q?rb=5Fit.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../next/Library/2026-10-25-21-18-27.gh-issue-160309.wJyl0Q.rst  | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 Misc/NEWS.d/next/Library/2026-10-25-21-18-27.gh-issue-160309.wJyl0Q.rst

diff --git a/Misc/NEWS.d/next/Library/2026-10-25-21-18-27.gh-issue-160309.wJyl0Q.rst b/Misc/NEWS.d/next/Library/2026-10-25-21-18-27.gh-issue-160309.wJyl0Q.rst
new file mode 100644
index 000000000000000..0c34090b71e44c1
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2026-10-25-21-18-27.gh-issue-160309.wJyl0Q.rst
@@ -0,0 +1 @@
+Fix codecs.StreamReader.read() silently dropping an incomplete character at the end of the stream.