@embedder/embedder 1.1.0 → 2.0.5

package/bundle/repomap-python/queries/tree-sitter-languages/ruby-tags.scm

@@ -1,64 +0,0 @@
-; Method definitions
-
-(
-  (comment)* @doc
-  .
-  [
-    (method
-      name: (_) @name.definition.method) @definition.method
-    (singleton_method
-      name: (_) @name.definition.method) @definition.method
-  ]
-  (#strip! @doc "^#\\s*")
-  (#select-adjacent! @doc @definition.method)
-)
-
-(alias
-  name: (_) @name.definition.method) @definition.method
-
-(setter
-  (identifier) @ignore)
-
-; Class definitions
-
-(
-  (comment)* @doc
-  .
-  [
-    (class
-      name: [
-        (constant) @name.definition.class
-        (scope_resolution
-          name: (_) @name.definition.class)
-      ]) @definition.class
-    (singleton_class
-      value: [
-        (constant) @name.definition.class
-        (scope_resolution
-          name: (_) @name.definition.class)
-      ]) @definition.class
-  ]
-  (#strip! @doc "^#\\s*")
-  (#select-adjacent! @doc @definition.class)
-)
-
-; Module definitions
-
-(
-  (module
-    name: [
-      (constant) @name.definition.module
-      (scope_resolution
-        name: (_) @name.definition.module)
-    ]) @definition.module
-)
-
-; Calls
-
-(call method: (identifier) @name.reference.call) @reference.call
-
-(
-  [(identifier) (constant)] @name.reference.call @reference.call
-  (#is-not? local)
-  (#not-match? @name.reference.call "^(lambda|load|require|require_relative|__FILE__|__LINE__)$")
-)

package/bundle/repomap-python/queries/tree-sitter-languages/rust-tags.scm

@@ -1,60 +0,0 @@
-; ADT definitions
-
-(struct_item
-    name: (type_identifier) @name.definition.class) @definition.class
-
-(enum_item
-    name: (type_identifier) @name.definition.class) @definition.class
-
-(union_item
-    name: (type_identifier) @name.definition.class) @definition.class
-
-; type aliases
-
-(type_item
-    name: (type_identifier) @name.definition.class) @definition.class
-
-; method definitions
-
-(declaration_list
-    (function_item
-        name: (identifier) @name.definition.method)) @definition.method
-
-; function definitions
-
-(function_item
-    name: (identifier) @name.definition.function) @definition.function
-
-; trait definitions
-(trait_item
-    name: (type_identifier) @name.definition.interface) @definition.interface
-
-; module definitions
-(mod_item
-    name: (identifier) @name.definition.module) @definition.module
-
-; macro definitions
-
-(macro_definition
-    name: (identifier) @name.definition.macro) @definition.macro
-
-; references
-
-(call_expression
-    function: (identifier) @name.reference.call) @reference.call
-
-(call_expression
-    function: (field_expression
-        field: (field_identifier) @name.reference.call)) @reference.call
-
-(macro_invocation
-    macro: (identifier) @name.reference.call) @reference.call
-
-; implementations
-
-(impl_item
-    trait: (type_identifier) @name.reference.implementation) @reference.implementation
-
-(impl_item
-    type: (type_identifier) @name.reference.implementation
-    !trait) @reference.implementation

package/bundle/repomap-python/queries/tree-sitter-languages/scala-tags.scm

@@ -1,65 +0,0 @@
-; Definitions
-
-(package_clause
-  name: (package_identifier) @name.definition.module) @definition.module
-
-(trait_definition
-  name: (identifier) @name.definition.interface) @definition.interface
-
-(enum_definition
-  name: (identifier) @name.definition.enum) @definition.enum
-
-(simple_enum_case
-  name: (identifier) @name.definition.class) @definition.class
-
-(full_enum_case
-  name: (identifier) @name.definition.class) @definition.class
-
-(class_definition
-  name: (identifier) @name.definition.class) @definition.class
-
-(object_definition
-  name: (identifier) @name.definition.object) @definition.object
-
-(function_definition
-  name: (identifier) @name.definition.function) @definition.function
-
-(val_definition
-  pattern: (identifier) @name.definition.variable) @definition.variable
-
-(given_definition
-  name: (identifier) @name.definition.variable) @definition.variable
-
-(var_definition
-  pattern: (identifier) @name.definition.variable) @definition.variable
-
-(val_declaration
-  name: (identifier) @name.definition.variable) @definition.variable
-
-(var_declaration
-  name: (identifier) @name.definition.variable) @definition.variable
-
-(type_definition
-  name: (type_identifier) @name.definition.type) @definition.type
-
-(class_parameter
-  name: (identifier) @name.definition.property) @definition.property
-
-; References
-
-(call_expression
-  (identifier) @name.reference.call) @reference.call
-
-(instance_expression
-  (type_identifier) @name.reference.interface) @reference.interface
-
-(instance_expression
-  (generic_type
-    (type_identifier) @name.reference.interface)) @reference.interface
-
-(extends_clause
-  (type_identifier) @name.reference.class) @reference.class
-
-(extends_clause
-  (generic_type
-    (type_identifier) @name.reference.class)) @reference.class

package/bundle/repomap-python/queries/tree-sitter-languages/typescript-tags.scm

@@ -1,41 +0,0 @@
-(function_signature
-  name: (identifier) @name.definition.function) @definition.function
-
-(method_signature
-  name: (property_identifier) @name.definition.method) @definition.method
-
-(abstract_method_signature
-  name: (property_identifier) @name.definition.method) @definition.method
-
-(abstract_class_declaration
-  name: (type_identifier) @name.definition.class) @definition.class
-
-(module
-  name: (identifier) @name.definition.module) @definition.module
-
-(interface_declaration
-  name: (type_identifier) @name.definition.interface) @definition.interface
-
-(type_annotation
-  (type_identifier) @name.reference.type) @reference.type
-
-(new_expression
-  constructor: (identifier) @name.reference.class) @reference.class
-
-(function_declaration
-  name: (identifier) @name.definition.function) @definition.function
-
-(method_definition
-  name: (property_identifier) @name.definition.method) @definition.method
-
-(class_declaration
-  name: (type_identifier) @name.definition.class) @definition.class
-
-(interface_declaration
-  name: (type_identifier) @name.definition.class) @definition.class
-
-(type_alias_declaration
-  name: (type_identifier) @name.definition.type) @definition.type
-
-(enum_declaration
-  name: (identifier) @name.definition.enum) @definition.enum

package/bundle/repomap-python/repomap.py

@@ -1,229 +0,0 @@
-#!/usr/bin/env python3
-"""
-Standalone RepoMap Tool
-
-A command-line tool that generates a "map" of a software repository,
-highlighting important files and definitions based on their relevance.
-Uses Tree-sitter for parsing and PageRank for ranking importance.
-"""
-
-import argparse
-import os
-import sys
-from pathlib import Path
-from typing import List
-
-from utils import count_tokens, read_text, Tag
-from scm import get_scm_fname
-from importance import is_important, filter_important_files
-from repomap_class import RepoMap
-
-
-def find_src_files(directory: str) -> List[str]:
-    """Find source files in a directory."""
-    if not os.path.isdir(directory):
-        return [directory] if os.path.isfile(directory) else []
-    
-    src_files = []
-    for root, dirs, files in os.walk(directory):
-        # Skip hidden directories and common non-source directories
-        dirs[:] = [d for d in dirs if not d.startswith('.') and d not in {'node_modules', '__pycache__', 'venv', 'env'}]
-        
-        for file in files:
-            if not file.startswith('.'):
-                full_path = os.path.join(root, file)
-                src_files.append(full_path)
-    
-    return src_files
-
-
-def tool_output(*messages):
-    """Print informational messages."""
-    print(*messages, file=sys.stdout)
-
-
-def tool_warning(message):
-    """Print warning messages."""
-    print(f"Warning: {message}", file=sys.stderr)
-
-
-def tool_error(message):
-    """Print error messages."""
-    print(f"Error: {message}", file=sys.stderr)
-
-
-def main():
-    """Main CLI entry point."""
-    parser = argparse.ArgumentParser(
-        description="Generate a repository map showing important code structures.",
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-        epilog="""
-Examples:
-  %(prog)s .                    # Map current directory
-  %(prog)s src/ --map-tokens 2048  # Map src/ with 2048 token limit
-  %(prog)s file1.py file2.py    # Map specific files
-  %(prog)s --chat-files main.py --other-files src/  # Specify chat vs other files
-        """
-    )
-    
-    parser.add_argument(
-        "paths",
-        nargs="*",
-        help="Files or directories to include in the map"
-    )
-    
-    parser.add_argument(
-        "--root",
-        default=".",
-        help="Repository root directory (default: current directory)"
-    )
-    
-    parser.add_argument(
-        "--map-tokens",
-        type=int,
-        default=8192,
-        help="Maximum tokens for the generated map (default: 8192)"
-    )
-    
-    parser.add_argument(
-        "--chat-files",
-        nargs="*",
-        help="Files currently being edited (given higher priority)"
-    )
-    
-    parser.add_argument(
-        "--other-files",
-        nargs="*",
-        help="Other files to consider for the map"
-    )
-    
-    parser.add_argument(
-        "--mentioned-files",
-        nargs="*",
-        help="Files explicitly mentioned (given higher priority)"
-    )
-    
-    parser.add_argument(
-        "--mentioned-idents",
-        nargs="*",
-        help="Identifiers explicitly mentioned (given higher priority)"
-    )
-    
-    parser.add_argument(
-        "--verbose",
-        action="store_true",
-        help="Enable verbose output"
-    )
-    
-    parser.add_argument(
-        "--model",
-        default="gpt-4",
-        help="Model name for token counting (default: gpt-4)"
-    )
-    
-    parser.add_argument(
-        "--max-context-window",
-        type=int,
-        help="Maximum context window size"
-    )
-    
-    parser.add_argument(
-        "--force-refresh",
-        action="store_true",
-        help="Force refresh of caches"
-    )
-
-    parser.add_argument(
-        "--exclude-unranked",
-        action="store_true",
-        help="Exclude files with Page Rank 0 from the map"
-    )
-    
-    args = parser.parse_args()
-    
-    # Set up token counter with specified model
-    def token_counter(text: str) -> int:
-        return count_tokens(text, args.model)
-    
-    # Set up output handlers
-    output_handlers = {
-        'info': tool_output,
-        'warning': tool_warning,
-        'error': tool_error
-    }
-    
-    # Process file arguments
-    chat_files_from_args = args.chat_files or [] # These are the paths as strings from the CLI
-    
-    # Determine the list of unresolved path specifications that will form the 'other_files'
-    # These can be files or directories. find_src_files will expand them.
-    unresolved_paths_for_other_files_specs = []
-    if args.other_files:  # If --other-files is explicitly provided, it's the source
-        unresolved_paths_for_other_files_specs.extend(args.other_files)
-    elif args.paths:  # Else, if positional paths are given, they are the source
-        unresolved_paths_for_other_files_specs.extend(args.paths)
-    # If neither, unresolved_paths_for_other_files_specs remains empty.
-
-    # Now, expand all directory paths in unresolved_paths_for_other_files_specs into actual file lists
-    # and collect all file paths. find_src_files handles both files and directories.
-    effective_other_files_unresolved = []
-    for path_spec_str in unresolved_paths_for_other_files_specs:
-        effective_other_files_unresolved.extend(find_src_files(path_spec_str))
-    
-    # Convert to absolute paths
-    root_path = Path(args.root).resolve()
-    # chat_files for RepoMap are from --chat-files argument, resolved.
-    chat_files = [str(Path(f).resolve()) for f in chat_files_from_args]
-    # other_files for RepoMap are the effective_other_files, resolved after expansion.
-    other_files = [str(Path(f).resolve()) for f in effective_other_files_unresolved]
-
-    print(f"Chat files: {chat_files}")
-    
-    # Convert mentioned files to sets
-    mentioned_fnames = set(args.mentioned_files) if args.mentioned_files else None
-    mentioned_idents = set(args.mentioned_idents) if args.mentioned_idents else None
-    
-    # Create RepoMap instance
-    repo_map = RepoMap(
-        map_tokens=args.map_tokens,
-        root=str(root_path),
-        token_counter_func=token_counter,
-        file_reader_func=read_text,
-        output_handler_funcs=output_handlers,
-        verbose=args.verbose,
-        max_context_window=args.max_context_window,
-        exclude_unranked=args.exclude_unranked
-    )
-    
-    # Generate the map
-    try:
-        map_content = repo_map.get_repo_map(
-            chat_files=chat_files,
-            other_files=other_files,
-            mentioned_fnames=mentioned_fnames,
-            mentioned_idents=mentioned_idents,
-            force_refresh=args.force_refresh
-        )
-        
-        if map_content:
-            if args.verbose:
-                tokens = repo_map.token_count(map_content)
-                tool_output(f"Generated map: {len(map_content)} chars, ~{tokens} tokens")
-            
-            print(map_content)
-        else:
-            tool_output("No repository map generated.")
-            
-    except KeyboardInterrupt:
-        tool_error("Interrupted by user")
-        sys.exit(1)
-    except Exception as e:
-        tool_error(f"Error generating repository map: {e}")
-        if args.verbose:
-            import traceback
-            traceback.print_exc()
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

package/bundle/repomap-python/repomap_bridge.py

@@ -1,234 +0,0 @@
-#!/usr/bin/env python3
-"""
-RepoMapper Bridge for TypeScript communication
-Reads JSON requests from stdin and outputs JSON responses to stdout
-"""
-
-import sys
-import json
-import os
-import logging
-from pathlib import Path
-from typing import Dict, Any, List, Optional
-
-# Add the current directory to the path so we can import our modules
-sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-
-from repomap_class import RepoMap
-from utils import count_tokens, read_text
-from scm import get_scm_fname
-from importance import filter_important_files
-
-# Suppress logs to stderr to avoid interfering with JSON communication
-root_logger = logging.getLogger()
-root_logger.setLevel(logging.ERROR)
-
-def find_src_files(directory: str) -> List[str]:
-    """Find source files in a directory."""
-    if not os.path.isdir(directory):
-        return [directory] if os.path.isfile(directory) else []
-    
-    src_files = []
-    for root, dirs, files in os.walk(directory):
-        # Skip hidden directories and common non-source directories
-        dirs[:] = [d for d in dirs if not d.startswith('.') and d not in {'node_modules', '__pycache__', 'venv', 'env'}]
-        
-        for file in files:
-            if not file.startswith('.'):
-                full_path = os.path.join(root, file)
-                src_files.append(full_path)
-    
-    return src_files
-
-def generate_repo_map(request: Dict[str, Any]) -> Dict[str, Any]:
-    """Generate repository map from request parameters."""
-    try:
-        project_root = request.get('project_root')
-        if not project_root or not os.path.isdir(project_root):
-            return {"error": f"Project root directory not found: {project_root}"}
-        
-        # Extract parameters with defaults
-        chat_files = request.get('chat_files', [])
-        mentioned_files = request.get('mentioned_files', [])
-        other_files = request.get('other_files', [])
-        mentioned_idents = request.get('mentioned_idents', [])
-        token_limit = request.get('token_limit', 8192)
-        exclude_unranked = request.get('exclude_unranked', False)
-        force_refresh = request.get('force_refresh', False)
-        verbose = request.get('verbose', False)
-        max_context_window = request.get('max_context_window')
-        
-        # Convert to sets for mentioned items
-        mentioned_fnames_set = set(mentioned_files) if mentioned_files else None
-        mentioned_idents_set = set(mentioned_idents) if mentioned_idents else None
-        
-        # If no other_files specified, auto-discover
-        effective_other_files = other_files if other_files else find_src_files(project_root)
-        
-        # Convert to absolute paths
-        root_path = Path(project_root).resolve()
-        abs_chat_files = [str(root_path / f) for f in chat_files] if chat_files else []
-        abs_other_files = [str(root_path / f) for f in effective_other_files] if effective_other_files else []
-        
-        # Remove any chat files from other_files to avoid duplication
-        abs_chat_files_set = set(abs_chat_files)
-        abs_other_files = [f for f in abs_other_files if f not in abs_chat_files_set]
-        
-        # Create output handlers that suppress output
-        output_handlers = {
-            'info': lambda *args: None,
-            'warning': lambda *args: None,
-            'error': lambda *args: None
-        }
-        
-        # Create RepoMap instance
-        repo_mapper = RepoMap(
-            map_tokens=token_limit,
-            root=str(root_path),
-            token_counter_func=lambda text: count_tokens(text, "gpt-4"),
-            file_reader_func=read_text,
-            output_handler_funcs=output_handlers,
-            verbose=verbose,
-            exclude_unranked=exclude_unranked,
-            max_context_window=max_context_window
-        )
-        
-        # Generate the repository map
-        map_content, file_report = repo_mapper.get_repo_map(
-            chat_files=abs_chat_files,
-            other_files=abs_other_files,
-            mentioned_fnames=mentioned_fnames_set,
-            mentioned_idents=mentioned_idents_set,
-            force_refresh=force_refresh,
-            show_preview=True  # Ensure we get the full map content, not just "complete"
-        )
-        
-        # Convert FileReport to dictionary for JSON serialization
-        report_dict = {
-            "excluded": file_report.excluded,
-            "definition_matches": file_report.definition_matches,
-            "reference_matches": file_report.reference_matches,
-            "total_files_considered": file_report.total_files_considered
-        }
-        
-        return {
-            "map": map_content or "No repository map could be generated.",
-            "report": report_dict
-        }
-        
-    except Exception as e:
-        return {"error": f"Error generating repository map: {str(e)}"}
-
-def search_identifiers(request: Dict[str, Any]) -> Dict[str, Any]:
-    """Search for identifiers in the codebase."""
-    try:
-        project_root = request.get('project_root')
-        if not project_root or not os.path.isdir(project_root):
-            return {"error": f"Project root directory not found: {project_root}"}
-        
-        query = request.get('query', '')
-        max_results = request.get('max_results', 50)
-        context_lines = request.get('context_lines', 2)
-        include_definitions = request.get('include_definitions', True)
-        include_references = request.get('include_references', True)
-        
-        # Create RepoMap instance for searching
-        repo_map = RepoMap(
-            root=project_root,
-            token_counter_func=lambda text: count_tokens(text, "gpt-4"),
-            file_reader_func=read_text,
-            output_handler_funcs={'info': lambda *args: None, 'warning': lambda *args: None, 'error': lambda *args: None},
-            verbose=False,
-            exclude_unranked=True
-        )
-        
-        # Find all source files
-        all_files = find_src_files(project_root)
-        
-        # Get all tags for all files
-        all_tags = []
-        for file_path in all_files:
-            rel_path = str(Path(file_path).relative_to(project_root))
-            tags = repo_map.get_tags(file_path, rel_path)
-            all_tags.extend(tags)
-        
-        # Filter tags based on search query and options
-        matching_tags = []
-        query_lower = query.lower()
-        
-        for tag in all_tags:
-            if query_lower in tag.name.lower():
-                if (tag.kind == "def" and include_definitions) or \
-                   (tag.kind == "ref" and include_references):
-                    matching_tags.append(tag)
-        
-        # Sort by relevance (definitions first, then references)
-        matching_tags.sort(key=lambda x: (x.kind != "def", x.name.lower().find(query_lower)))
-        
-        # Limit results
-        matching_tags = matching_tags[:max_results]
-        
-        # Format results with context
-        results = []
-        for tag in matching_tags:
-            file_path = str(Path(project_root) / tag.rel_fname)
-            
-            # Calculate context range
-            start_line = max(1, tag.line - context_lines)
-            end_line = tag.line + context_lines
-            context_range = list(range(start_line, end_line + 1))
-            
-            context = repo_map.render_tree(
-                file_path,
-                tag.rel_fname,
-                context_range
-            )
-            
-            if context:
-                results.append({
-                    "file": tag.rel_fname,
-                    "line": tag.line,
-                    "name": tag.name,
-                    "kind": tag.kind,
-                    "context": context
-                })
-        
-        return {"results": results}
-        
-    except Exception as e:
-        return {"error": f"Error searching identifiers: {str(e)}"}
-
-def main():
-    """Main bridge entry point - reads JSON from stdin, processes request, outputs JSON to stdout."""
-    try:
-        # Read JSON request from stdin
-        input_data = sys.stdin.read().strip()
-        if not input_data:
-            result = {"error": "No input data received"}
-        else:
-            request = json.loads(input_data)
-            
-            # Check for action type
-            action = request.get('action', 'repo_map')
-            
-            if action == 'search_identifiers':
-                result = search_identifiers(request)
-            else:
-                # Default action is to generate repository map
-                result = generate_repo_map(request)
-        
-        # Output JSON result to stdout
-        print(json.dumps(result, indent=2))
-        
-    except json.JSONDecodeError as e:
-        error_result = {"error": f"Invalid JSON input: {str(e)}"}
-        print(json.dumps(error_result, indent=2))
-        sys.exit(1)
-        
-    except Exception as e:
-        error_result = {"error": f"Unexpected error: {str(e)}"}
-        print(json.dumps(error_result, indent=2))
-        sys.exit(1)
-
-if __name__ == "__main__":
-    main()