From 0f5ed52469a16466d2c5f780ab4c7a886011c444 Mon Sep 17 00:00:00 2001
From: "codeflash-ai[bot]"
 <148906541+codeflash-ai[bot]@users.noreply.github.com>
Date: Mon, 22 Dec 2025 08:24:28 +0000
Subject: [PATCH] Optimize find_common_tags

**Key optimizations:**
- Pre-extract all tag lists upfront (avoids repeated `.get("tags", [])` lookups in the critical loop).
- Early exit if any tag list is empty (intersection must be empty if any is empty).
- Sort tag lists by size before intersection to reduce intermediate set size as quickly as possible (much faster for many articles, especially when tag set sizes vary).
- All comments and code behavior are preserved. The return values, exceptions, and input/output remain exactly as in the original code.
---
 src/algorithms/string.py | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/src/algorithms/string.py b/src/algorithms/string.py
index 658439e..6074b42 100644
--- a/src/algorithms/string.py
+++ b/src/algorithms/string.py
@@ -41,9 +41,18 @@ def find_common_tags(articles: list[dict[str, list[str]]]) -> set[str]:
     if not articles:
         return set()
 
-    common_tags = set(articles[0].get("tags", []))
-    for article in articles[1:]:
-        common_tags.intersection_update(article.get("tags", []))
+    # Pre-extract all tag lists for faster access and avoid repeated .get lookups
+    tag_lists = [article.get("tags", []) for article in articles]
+
+    # If any tag list is empty, the intersection will be empty
+    if any(len(tags) == 0 for tags in tag_lists):
+        return set()
+
+    # Sort tag_lists by length to start intersection from smallest, reducing work early
+    tag_lists.sort(key=len)
+    common_tags = set(tag_lists[0])
+    for tags in tag_lists[1:]:
+        common_tags.intersection_update(tags)
         if not common_tags:
             break
     return common_tags