From f7b88e9fd8e0051b7f3efc3630f79a802a87785f Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Fri, 29 May 2026 00:34:48 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20Bolt:=20Optimize=20yEnc=20decoding?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Replace manual byte iteration with `bytes.translate` and `bytes.find`
- Handle `==` consecutive escapes correctly without failing like `.split`
- Improve yEnc deep check performance
- Document learnings in `.jules/bolt.md`

Co-authored-by: xbmc4lyfe <273732874+xbmc4lyfe@users.noreply.github.com>
---
 .jules/bolt.md |  3 +++
 verify_nzb.py  | 38 ++++++++++++++++++++++++++++----------
 2 files changed, 31 insertions(+), 10 deletions(-)
 create mode 100644 .jules/bolt.md

diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 0000000..4272daa
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## 2024-05-29 - yEnc decoding optimization with bytes.find() and bytes.translate()
+**Learning:** Using `bytes.split(b'=')` for yEnc decoding fails when lines contain consecutive escapes (e.g., `==`) due to how splitting creates empty strings and fails to track indices correctly. To optimize Python byte string processing effectively while handling escapes correctly, use `bytes.translate()` for bulk decoding and `bytes.find()` to locate and apply escapes manually.
+**Action:** Prioritize `bytes.translate` and `bytes.find` over `.split` when translating strings with multi-character escape sequences, ensuring correctness on edge cases like consecutive escapes.
diff --git a/verify_nzb.py b/verify_nzb.py
index 953dccd..c2d5dfc 100644
--- a/verify_nzb.py
+++ b/verify_nzb.py
@@ -115,19 +115,37 @@ def _parse_yenc_attrs(line: bytes) -> dict[str, str]:
     return attrs
 
 
+# Translation tables for yEnc decoding to avoid slow byte-by-byte iteration in Python.
+# Normal bytes are shifted by 42. Escaped bytes are shifted by 42+64=106.
+_YENC_TRANS = bytes((i - 42) % 256 for i in range(256))
+_YENC_ESCAPE_TRANS = bytes((i - 106) % 256 for i in range(256))
+
 def _decode_yenc_lines(lines: Iterable[bytes]) -> bytes:
+    """
+    Decodes yEnc-encoded lines into bytes.
+    Optimized to use C-backed bytes.translate() and bytes.find() instead of manual iteration.
+    """
     decoded = bytearray()
     for line in lines:
-        index = 0
-        while index < len(line):
-            byte = line[index]
-            if byte == 61:
-                index += 1
-                if index >= len(line):
-                    raise ValueError("dangling yEnc escape")
-                byte = (line[index] - 64) % 256
-            decoded.append((byte - 42) % 256)
-            index += 1
+        # Fast path: no escapes in the line
+        if b"=" not in line:
+            decoded.extend(line.translate(_YENC_TRANS))
+            continue
+
+        # Slow path: apply escapes manually using string find
+        idx = 0
+        length = len(line)
+        while idx < length:
+            next_eq = line.find(b"=", idx)
+            if next_eq == -1:
+                decoded.extend(line[idx:].translate(_YENC_TRANS))
+                break
+            decoded.extend(line[idx:next_eq].translate(_YENC_TRANS))
+            idx = next_eq + 1
+            if idx >= length:
+                raise ValueError("dangling yEnc escape")
+            decoded.append(_YENC_ESCAPE_TRANS[line[idx]])
+            idx += 1
     return bytes(decoded)