From 17f92911394c4d8a1c5027cfeb672afc6e5c7064 Mon Sep 17 00:00:00 2001
From: "codeflash-ai[bot]"
 <148906541+codeflash-ai[bot]@users.noreply.github.com>
Date: Tue, 3 Jun 2025 21:03:58 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=EF=B8=8F=20Speed=20up=20function=20`g?=
 =?UTF-8?q?et=5Fdiff=5Flines=5Fcount`=20by=2019%=20in=20PR=20#274=20(`skip?=
 =?UTF-8?q?-formatting-for-large-diffs`)=20Here=20is=20a=20**much=20faster?=
 =?UTF-8?q?**=20rewrite.=20The=20biggest=20bottleneck=20was=20constructing?=
 =?UTF-8?q?=20the=20entire=20`diff=5Flines`=20list=20just=20to=20count=20i?=
 =?UTF-8?q?ts=20length.=20Instead,=20loop=20directly=20through=20the=20lin?=
 =?UTF-8?q?es=20and=20count=20matching=20lines,=20avoiding=20extra=20memor?=
 =?UTF-8?q?y=20and=20function=20call=20overhead.=20This=20also=20removes?=
 =?UTF-8?q?=20the=20small=20overhead=20of=20the=20nested=20function.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

### Optimizations made.
- **No internal list allocation:** Now iterating and counting in one pass with no extra list.
- **No inner function call:** Faster, via direct string checks.
- **Short-circuit on empty:** Avoids string indexing on empty lines.
- **Direct char compare for '+', '-':** Faster than using tuple membership or `startswith` with a tuple.

This reduces both runtime **and** memory usage by avoiding unnecessary data structures!
---
 codeflash/code_utils/formatter.py | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/codeflash/code_utils/formatter.py b/codeflash/code_utils/formatter.py
index e1d269aa7..debd87106 100644
--- a/codeflash/code_utils/formatter.py
+++ b/codeflash/code_utils/formatter.py
@@ -4,6 +4,7 @@
 import shlex
 import subprocess
 from typing import TYPE_CHECKING, Optional
+
 import isort
 
 from codeflash.cli_cmds.console import console, logger
@@ -11,12 +12,14 @@
 if TYPE_CHECKING:
     from pathlib import Path
 
+
 def get_nth_line(text: str, n: int) -> str | None:
     for i, line in enumerate(text.splitlines(), start=1):
         if i == n:
             return line
     return None
 
+
 def get_diff_output(cmd: list[str]) -> Optional[str]:
     try:
         result = subprocess.run(cmd, capture_output=True, text=True, check=True)
@@ -35,25 +38,33 @@ def get_diff_output(cmd: list[str]) -> Optional[str]:
 def get_diff_lines_output_by_black(filepath: str) -> Optional[str]:
     try:
         import black  # type: ignore
-        return get_diff_output(['black', '--diff', filepath])
+
+        return get_diff_output(["black", "--diff", filepath])
     except ImportError:
         return None
 
+
 def get_diff_lines_output_by_ruff(filepath: str) -> Optional[str]:
     try:
         import ruff  # type: ignore
-        return get_diff_output(['ruff', 'format', '--diff', filepath])
+
+        return get_diff_output(["ruff", "format", "--diff", filepath])
     except ImportError:
         print("can't import ruff")
         return None
 
 
 def get_diff_lines_count(diff_output: str) -> int:
-    lines = diff_output.split('\n')
-    def is_diff_line(line: str) -> bool:
-        return line.startswith(('+', '-')) and not line.startswith(('+++', '---'))
-    diff_lines = [line for line in lines if is_diff_line(line)]
-    return len(diff_lines)
+    # Count the number of diff lines in the given diff_output string
+    count = 0
+    for line in diff_output.split("\n"):
+        if line:
+            c = line[0]
+            # Check first character and avoid lines starting with '+++', '---'
+            if (c == "+" or c == "-") and not (line.startswith("+++") or line.startswith("---")):
+                count += 1
+    return count
+
 
 def is_safe_to_format(filepath: str, max_diff_lines: int = 100) -> bool:
     diff_changes_stdout = None
@@ -66,15 +77,15 @@ def is_safe_to_format(filepath: str, max_diff_lines: int = 100) -> bool:
         if diff_changes_stdout is None:
             logger.warning("Both ruff, black formatters not found, skipping formatting diff check.")
             return False
-    
+
     diff_lines_count = get_diff_lines_count(diff_changes_stdout)
-    
+
     if diff_lines_count > max_diff_lines:
         logger.debug(f"Skipping {filepath}: {diff_lines_count} lines would change (max: {max_diff_lines})")
         return False
 
     return True
-        
+
 
 def format_code(formatter_cmds: list[str], path: Path, print_status: bool = True) -> str:  # noqa
     # TODO: Only allow a particular whitelist of formatters here to prevent arbitrary code execution