From a8b7c0c6c4363adfadaf486d1847f9793c5a07d5 Mon Sep 17 00:00:00 2001
From: louyk18 <14280048+louyk18@user.noreply.gitee.com>
Date: Mon, 13 Jan 2025 17:19:13 +0800
Subject: [PATCH] improve performance

---
 python/graphy/utils/arxiv_fetcher.py | 33 ++++++----------------------
 1 file changed, 7 insertions(+), 26 deletions(-)

diff --git a/python/graphy/utils/arxiv_fetcher.py b/python/graphy/utils/arxiv_fetcher.py
index 6a07c192..0f342464 100644
--- a/python/graphy/utils/arxiv_fetcher.py
+++ b/python/graphy/utils/arxiv_fetcher.py
@@ -81,7 +81,7 @@ def __init__(
 
     def find_paper_from_arxiv(self, name, max_results):
         new_names = sorted(
-            [s for s in re.split(r"[.\\/]", name.strip()) if len(s) >= 20],
+            [s.strip() for s in re.split(r"[.\\/]", name.strip()) if len(s) >= 20],
             key=len,
             reverse=True,
         )
@@ -132,7 +132,7 @@ def find_paper_from_arxiv(self, name, max_results):
                     except Exception as e:
                         traceback.print_exc()
 
-                if highest_similarity > 0.9 or found_result:
+                if highest_similarity > 0.9:
                     break
                 logger.warning(f"Not Found: {query}")
 
@@ -230,27 +230,8 @@ def fetch_papers_concurrently(
 
 
 if __name__ == "__main__":
-    filenames = []
-
-    # Traverse the directory
-    for root, dirs, files in os.walk("inputs/download"):
-        for file in files:
-            # Append file names to the list
-            filenames.append(file)
-
-    for file_name in filenames:
-        download_foler = os.path.join(f"{WF_DOWNLOADS_DIR}", file_name.split(".")[0])
-        fetcher = ArxivFetcher(download_folder=download_foler)
-        os.makedirs(download_foler)
-        path = os.path.join("inputs", "download", file_name)
-        with open(f"{path}", "r") as f:
-            papers = f.readlines()
-            line_counter = 0
-            for paper in papers:
-                line_counter += 1
-                if line_counter % 2 == 0:
-                    continue
-                paper = paper.strip()
-                fetcher.download_paper(paper, 5)
-                # fetcher.download_paper(paper.split(",")[0], 5)
-    # print(json.dumps(data, indent=2))
+    af = ArxivFetcher()
+    output = af.find_paper_from_arxiv(
+        "Peiyi Wang, Lei Li, Zhihong Shao, RX Xu, Damai Dai, Yifei Li, Deli Chen, Y Wu, and Zhifang Sui. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. CoRR, abs/2312.08935 , 2023a."
+    )
+    print(output)