Merge branch 'limit-ctx-line-length'

Author: johnhuang316

src/code_index_mcp/search/ag.py

@@ -27,7 +27,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a search using The Silver Searcher (ag).
@@ -40,6 +41,7 @@ def search(
             file_pattern: File pattern to filter
             fuzzy: Enable word boundary matching (not true fuzzy search)
             regex: Enable regex pattern matching
+            max_line_length: Optional. Limit the length of lines when context_lines is used
         """
         # ag prints line numbers and groups by file by default, which is good.
         # --noheading is used to be consistent with other tools' output format.
@@ -116,10 +118,10 @@ def search(
             if process.returncode > 1:
                  raise RuntimeError(f"ag failed with exit code {process.returncode}: {process.stderr}")
 
-            return parse_search_output(process.stdout, base_path)
+            return parse_search_output(process.stdout, base_path, max_line_length)
 
         except FileNotFoundError:
             raise RuntimeError("'ag' (The Silver Searcher) not found. Please install it and ensure it's in your PATH.")
         except Exception as e:
             # Re-raise other potential exceptions like permission errors
-            raise RuntimeError(f"An error occurred while running ag: {e}") 
+            raise RuntimeError(f"An error occurred while running ag: {e}")

src/code_index_mcp/search/base.py

@@ -14,13 +14,18 @@
 
 from ..indexing.qualified_names import normalize_file_path
 
-def parse_search_output(output: str, base_path: str) -> Dict[str, List[Tuple[int, str]]]:
+def parse_search_output(
+    output: str,
+    base_path: str,
+    max_line_length: Optional[int] = None
+) -> Dict[str, List[Tuple[int, str]]]:
     """
     Parse the output of command-line search tools (grep, ag, rg).
 
     Args:
         output: The raw output from the command-line tool.
         base_path: The base path of the project to make file paths relative.
+        max_line_length: Optional maximum line length to truncate long lines.
 
     Returns:
         A dictionary where keys are file paths and values are lists of (line_number, line_content) tuples.
@@ -71,6 +76,10 @@ def parse_search_output(output: str, base_path: str) -> Dict[str, List[Tuple[int
             # Normalize path separators for consistency
             relative_path = normalize_file_path(relative_path)
 
+            # Truncate content if it exceeds max_line_length
+            if max_line_length and len(content) > max_line_length:
+                content = content[:max_line_length] + '... (truncated)'
+
             if relative_path not in results:
                 results[relative_path] = []
             results[relative_path].append((line_number, content))
@@ -193,7 +202,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a search using the specific strategy.
@@ -211,4 +221,3 @@ def search(
             A dictionary mapping filenames to lists of (line_number, line_content) tuples.
         """
         pass
-

src/code_index_mcp/search/basic.py

@@ -46,7 +46,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a basic, line-by-line search.
@@ -60,6 +61,7 @@ def search(
             file_pattern: File pattern to filter
             fuzzy: Enable word boundary matching
             regex: Enable regex pattern matching
+            max_line_length: Optional. Limit the length of lines when context_lines is used
         """
         results: Dict[str, List[Tuple[int, str]]] = {}
 
@@ -94,15 +96,20 @@ def search(
                     with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
                         for line_num, line in enumerate(f, 1):
                             if search_regex.search(line):
+                                content = line.rstrip('\n')
+                                # Truncate content if it exceeds max_line_length
+                                if max_line_length and len(content) > max_line_length:
+                                    content = content[:max_line_length] + '... (truncated)'
+                                
                                 if rel_path not in results:
                                     results[rel_path] = []
                                 # Strip newline for consistent output
-                                results[rel_path].append((line_num, line.rstrip('\n')))
+                                results[rel_path].append((line_num, content))
                 except (UnicodeDecodeError, PermissionError, OSError):
                     # Ignore files that can't be opened or read due to encoding/permission issues
                     continue
                 except Exception:
                     # Ignore any other unexpected exceptions to maintain robustness
                     continue
 
-        return results 
+        return results

src/code_index_mcp/search/grep.py

@@ -32,7 +32,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a search using standard grep.
@@ -45,6 +46,7 @@ def search(
             file_pattern: File pattern to filter
             fuzzy: Enable word boundary matching
             regex: Enable regex pattern matching
+            max_line_length: Optional. Limit the length of lines when context_lines is used
         """
         # -r: recursive, -n: line number
         cmd = ['grep', '-r', '-n']
@@ -102,9 +104,9 @@ def search(
             if process.returncode > 1:
                  raise RuntimeError(f"grep failed with exit code {process.returncode}: {process.stderr}")
 
-            return parse_search_output(process.stdout, base_path)
+            return parse_search_output(process.stdout, base_path, max_line_length)
 
         except FileNotFoundError:
             raise RuntimeError("'grep' not found. Please install it and ensure it's in your PATH.")
         except Exception as e:
-            raise RuntimeError(f"An error occurred while running grep: {e}") 
+            raise RuntimeError(f"An error occurred while running grep: {e}")

src/code_index_mcp/search/ripgrep.py

@@ -27,7 +27,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a search using ripgrep.
@@ -40,6 +41,7 @@ def search(
             file_pattern: File pattern to filter
             fuzzy: Enable word boundary matching (not true fuzzy search)
             regex: Enable regex pattern matching
+            max_line_length: Optional. Limit the length of lines when context_lines is used
         """
         cmd = ['rg', '--line-number', '--no-heading', '--color=never', '--no-ignore']
 
@@ -87,10 +89,10 @@ def search(
             if process.returncode > 1:
                 raise RuntimeError(f"ripgrep failed with exit code {process.returncode}: {process.stderr}")
 
-            return parse_search_output(process.stdout, base_path)
+            return parse_search_output(process.stdout, base_path, max_line_length)
 
         except FileNotFoundError:
             raise RuntimeError("ripgrep (rg) not found. Please install it and ensure it's in your PATH.")
         except Exception as e:
             # Re-raise other potential exceptions like permission errors
-            raise RuntimeError(f"An error occurred while running ripgrep: {e}") 
+            raise RuntimeError(f"An error occurred while running ripgrep: {e}")

src/code_index_mcp/search/ugrep.py

@@ -27,7 +27,8 @@ def search(
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: bool = False
+        regex: bool = False,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, List[Tuple[int, str]]]:
         """
         Execute a search using the 'ug' command-line tool.
@@ -40,6 +41,7 @@ def search(
             file_pattern: File pattern to filter
             fuzzy: Enable true fuzzy search (ugrep native support)
             regex: Enable regex pattern matching
+            max_line_length: Optional. Limit the length of lines when context_lines is used
         """
         if not self.is_available():
             return {"error": "ugrep (ug) command not found."}
@@ -89,7 +91,7 @@ def search(
                 error_output = process.stderr.strip()
                 return {"error": f"ugrep execution failed with code {process.returncode}", "details": error_output}
 
-            return parse_search_output(process.stdout, base_path)
+            return parse_search_output(process.stdout, base_path, max_line_length)
 
         except FileNotFoundError:
             return {"error": "ugrep (ug) command not found. Please ensure it's installed and in your PATH."}

src/code_index_mcp/server.py

@@ -138,7 +138,8 @@ def search_code_advanced(
     context_lines: int = 0,
     file_pattern: str = None,
     fuzzy: bool = False,
-    regex: bool = None
+    regex: bool = None,
+    max_line_length: int = None
 ) -> Dict[str, Any]:
     """
     Search for a code pattern in the project using an advanced, fast tool.
@@ -152,6 +153,7 @@ def search_code_advanced(
         context_lines: Number of lines to show before and after the match.
         file_pattern: A glob pattern to filter files to search in
                      (e.g., "*.py", "*.js", "test_*.py").
+        max_line_length: Optional. Default None (no limit). Limits the length of lines when context_lines is used.
                      All search tools now handle glob patterns consistently:
                      - ugrep: Uses glob patterns (*.py, *.{js,ts})
                      - ripgrep: Uses glob patterns (*.py, *.{js,ts})
@@ -180,7 +182,8 @@ def search_code_advanced(
         context_lines=context_lines,
         file_pattern=file_pattern,
         fuzzy=fuzzy,
-        regex=regex
+        regex=regex,
+        max_line_length=max_line_length
     )
 
 @mcp.tool()

src/code_index_mcp/services/search_service.py

@@ -31,7 +31,8 @@ def search_code(  # pylint: disable=too-many-arguments
         context_lines: int = 0,
         file_pattern: Optional[str] = None,
         fuzzy: bool = False,
-        regex: Optional[bool] = None
+        regex: Optional[bool] = None,
+        max_line_length: Optional[int] = None
     ) -> Dict[str, Any]:
         """
         Search for code patterns in the project.
@@ -45,6 +46,7 @@ def search_code(  # pylint: disable=too-many-arguments
             file_pattern: Glob pattern to filter files
             fuzzy: Whether to enable fuzzy matching
             regex: Regex mode - True/False to force, None for auto-detection
+            max_line_length: Optional. Default None (no limit). Limits the length of lines when context_lines is used.
 
         Returns:
             Dictionary with search results or error information
@@ -89,7 +91,8 @@ def search_code(  # pylint: disable=too-many-arguments
                 context_lines=context_lines,
                 file_pattern=file_pattern,
                 fuzzy=fuzzy,
-                regex=regex
+                regex=regex,
+                max_line_length=max_line_length
             )
             return ResponseFormatter.search_results_response(results)
         except Exception as e: