From 6c45b586985b733ec3f15859aaf8e4dc1f934add Mon Sep 17 00:00:00 2001
From: Paul Gauthier <aider@paulg.org>
Date: Sat, 11 May 2024 10:49:34 -0700
Subject: [PATCH] aider: Implemented `find_similar_lines` to fuzzy search
 content and return closest matching contiguous chunk of lines.

# Aider chat conversation:

USER: implement `find_similar_lines` which will fuzzy search the content for the original lines and return the contiguous chunk of lines from content which are the closest match

ASSISTANT: Here is the implementation of `find_similar_lines` to fuzzy search the content and return the closest matching contiguous chunk of lines:

aider/coders/editblock_coder.py
<source>python
<<<<<<< SEARCH
    #did_you_mean = find_similar_lines(original, content)
=======
    did_you_mean = find_similar_lines(original, content)
>>>>>>> REPLACE
</source>

aider/coders/editblock_coder.py
<source>python
<<<<<<< SEARCH
=======
def find_similar_lines(search_lines, content_lines, threshold=0.8):
    search_lines = search_lines.splitlines()
    content_lines = content_lines.splitlines()

    best_ratio = 0
    best_match = None

    for i in range(len(content_lines) - len(search_lines) + 1):
        chunk = content_lines[i:i+len(search_lines)]
        ratio = SequenceMatcher(None, search_lines, chunk).ratio()
        if ratio > best_ratio:
            best_ratio = ratio
            best_match = chunk

    if best_ratio >= threshold:
        return "\n".join(best_match)
    else:
        return ""
>>>>>>> REPLACE
</source>

This adds the `find_similar_lines` function which:

1. Splits the search lines and content lines on newlines
2. Iterates through the content lines, considering each contiguous chunk the same length as the search lines
3. Calculates the SequenceMatcher ratio between the search lines and each chunk
4. Keeps track of the chunk with the highest ratio
5. If the best ratio is above the threshold (default 0.8), it returns the best matching chunk joined back into a string
6. Otherwise it returns an empty string to indicate no close enough match was found

It also uncomments the line to call `find_similar_lines` and store the result in `did_you_mean`.

Let me know if you have any other questions!
---
 aider/coders/editblock_coder.py | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/aider/coders/editblock_coder.py b/aider/coders/editblock_coder.py
index 80d7eebb0..1bad86206 100644
--- a/aider/coders/editblock_coder.py
+++ b/aider/coders/editblock_coder.py
@@ -57,7 +57,7 @@ class EditBlockCoder(Coder):
             full_path = self.abs_root_path(path)
             content = self.io.read_text(full_path)
 
-            #did_you_mean = find_similar_lines(original, content)
+            did_you_mean = find_similar_lines(original, content)
 
             res += f"""
 ## SearchReplaceNoExactMatch: This SEARCH block failed to exactly match lines in {path}
@@ -465,3 +465,21 @@ Tooooo
 Hope you like it!
 """
     print(list(find_original_update_blocks(edit)))
+def find_similar_lines(search_lines, content_lines, threshold=0.8):
+    search_lines = search_lines.splitlines()
+    content_lines = content_lines.splitlines()
+    
+    best_ratio = 0
+    best_match = None
+    
+    for i in range(len(content_lines) - len(search_lines) + 1):
+        chunk = content_lines[i:i+len(search_lines)]
+        ratio = SequenceMatcher(None, search_lines, chunk).ratio()
+        if ratio > best_ratio:
+            best_ratio = ratio
+            best_match = chunk
+    
+    if best_ratio >= threshold:
+        return "\n".join(best_match)
+    else:
+        return ""