From 6d1c5d44911a3be7551adc9e97b98c1a0c3ac001 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 17 Mar 2026 03:00:17 -0700
Subject: [PATCH] refactor(tools): extract position calculation logic in
 fuzzy_match (#1681)

Extract the repeated line-position calculation pattern into a
_calculate_line_positions() helper. The same 4-line pattern was
duplicated across _strategy_trimmed_boundary, _strategy_block_anchor,
_strategy_context_aware, and _find_normalized_matches. Also
standardizes the end_pos clamping (some sites used min(), some used
an if-guard).

Based on PR #1604 by aydnOktay.

Co-authored-by: aydnOktay <aydnOktay@users.noreply.github.com>
---
 tools/fuzzy_match.py | 51 ++++++++++++++++++++++++++++----------------
 1 file changed, 33 insertions(+), 18 deletions(-)

diff --git a/tools/fuzzy_match.py b/tools/fuzzy_match.py
index f53451c6..ddcdf427 100644
--- a/tools/fuzzy_match.py
+++ b/tools/fuzzy_match.py
@@ -254,10 +254,9 @@ def _strategy_trimmed_boundary(content: str, pattern: str) -> List[Tuple[int, in
         
         if '\n'.join(check_lines) == modified_pattern:
             # Found match - calculate original positions
-            start_pos = sum(len(line) + 1 for line in content_lines[:i])
-            end_pos = sum(len(line) + 1 for line in content_lines[:i + pattern_line_count]) - 1
-            if end_pos >= len(content):
-                end_pos = len(content)
+            start_pos, end_pos = _calculate_line_positions(
+                content_lines, i, i + pattern_line_count, len(content)
+            )
             matches.append((start_pos, end_pos))
     
     return matches
@@ -309,9 +308,10 @@ def _strategy_block_anchor(content: str, pattern: str) -> List[Tuple[int, int]]:
         
         if similarity >= threshold:
             # Calculate positions using ORIGINAL lines to ensure correct character offsets in the file
-            start_pos = sum(len(line) + 1 for line in orig_content_lines[:i])
-            end_pos = sum(len(line) + 1 for line in orig_content_lines[:i + pattern_line_count]) - 1
-            matches.append((start_pos, min(end_pos, len(content))))
+            start_pos, end_pos = _calculate_line_positions(
+                orig_content_lines, i, i + pattern_line_count, len(content)
+            )
+            matches.append((start_pos, end_pos))
     
     return matches
 
@@ -343,10 +343,9 @@ def _strategy_context_aware(content: str, pattern: str) -> List[Tuple[int, int]]
         
         # Need at least 50% of lines to have high similarity
         if high_similarity_count >= len(pattern_lines) * 0.5:
-            start_pos = sum(len(line) + 1 for line in content_lines[:i])
-            end_pos = sum(len(line) + 1 for line in content_lines[:i + pattern_line_count]) - 1
-            if end_pos >= len(content):
-                end_pos = len(content)
+            start_pos, end_pos = _calculate_line_positions(
+                content_lines, i, i + pattern_line_count, len(content)
+            )
             matches.append((start_pos, end_pos))
     
     return matches
@@ -356,6 +355,26 @@ def _strategy_context_aware(content: str, pattern: str) -> List[Tuple[int, int]]
 # Helper Functions
 # =============================================================================
 
+def _calculate_line_positions(content_lines: List[str], start_line: int,
+                              end_line: int, content_length: int) -> Tuple[int, int]:
+    """Calculate start and end character positions from line indices.
+
+    Args:
+        content_lines: List of lines (without newlines)
+        start_line: Starting line index (0-based)
+        end_line: Ending line index (exclusive, 0-based)
+        content_length: Total length of the original content string
+
+    Returns:
+        Tuple of (start_pos, end_pos) in the original content
+    """
+    start_pos = sum(len(line) + 1 for line in content_lines[:start_line])
+    end_pos = sum(len(line) + 1 for line in content_lines[:end_line]) - 1
+    if end_pos >= content_length:
+        end_pos = content_length
+    return start_pos, end_pos
+
+
 def _find_normalized_matches(content: str, content_lines: List[str],
                               content_normalized_lines: List[str],
                               pattern: str, pattern_normalized: str) -> List[Tuple[int, int]]:
@@ -383,13 +402,9 @@ def _find_normalized_matches(content: str, content_lines: List[str],
         
         if block == pattern_normalized:
             # Found a match - calculate original positions
-            start_pos = sum(len(line) + 1 for line in content_lines[:i])
-            end_pos = sum(len(line) + 1 for line in content_lines[:i + num_pattern_lines]) - 1
-            
-            # Handle case where end is past content
-            if end_pos >= len(content):
-                end_pos = len(content)
-            
+            start_pos, end_pos = _calculate_line_positions(
+                content_lines, i, i + num_pattern_lines, len(content)
+            )
             matches.append((start_pos, end_pos))
     
     return matches