codemesh 0.1.1__py3-none-any.whl

codemesh/db/schema.py

@@ -0,0 +1,125 @@
+"""Database schema definitions and migration support."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from codemesh.db.connection import get_connection
+
+SCHEMA_SQL = """
+-- Nodes table: code symbols
+CREATE TABLE IF NOT EXISTS nodes (
+    id TEXT PRIMARY KEY,
+    kind TEXT NOT NULL,
+    name TEXT NOT NULL,
+    qualified_name TEXT NOT NULL,
+    file_path TEXT NOT NULL,
+    language TEXT NOT NULL,
+    start_line INTEGER NOT NULL,
+    end_line INTEGER NOT NULL,
+    start_column INTEGER DEFAULT 0,
+    end_column INTEGER DEFAULT 0,
+    docstring TEXT DEFAULT '',
+    signature TEXT DEFAULT '',
+    visibility TEXT DEFAULT 'public',
+    parent_id TEXT,
+    metadata TEXT DEFAULT '{}',
+    is_exported INTEGER DEFAULT 0,
+    is_async INTEGER DEFAULT 0,
+    is_static INTEGER DEFAULT 0,
+    is_abstract INTEGER DEFAULT 0,
+    content_hash TEXT DEFAULT '',
+    created_at INTEGER DEFAULT (unixepoch())
+);
+
+-- Edges table: relationships between symbols
+CREATE TABLE IF NOT EXISTS edges (
+    id TEXT PRIMARY KEY,
+    source_id TEXT NOT NULL,
+    target_id TEXT NOT NULL,
+    kind TEXT NOT NULL,
+    confidence REAL DEFAULT 1.0,
+    weight_source TEXT DEFAULT 'ast',
+    line INTEGER DEFAULT 0,
+    column INTEGER DEFAULT 0,
+    metadata TEXT DEFAULT '{}',
+    resolved_target TEXT DEFAULT '',
+    type_context TEXT DEFAULT '',
+    created_at INTEGER DEFAULT (unixepoch())
+);
+
+-- File-to-node dependency mapping for delta indexing
+CREATE TABLE IF NOT EXISTS file_node_deps (
+    file_path TEXT NOT NULL,
+    node_id TEXT NOT NULL,
+    PRIMARY KEY (file_path, node_id)
+);
+
+-- Full-text search virtual table (BM25 via FTS5)
+-- Column weights: id=0, name=20, qualified_name=5, docstring=1, signature=2
+-- Heavy name weight ensures exact/prefix name matches rank above incidental
+-- mentions in long docstrings or qualified names of nested symbols.
+CREATE VIRTUAL TABLE IF NOT EXISTS nodes_fts USING fts5(
+    id,
+    name,
+    qualified_name,
+    docstring,
+    signature,
+    content='nodes',
+    content_rowid='rowid'
+);
+
+-- Query log for analytics
+CREATE TABLE IF NOT EXISTS query_log (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    query_text TEXT NOT NULL,
+    retrieved_nodes TEXT NOT NULL,
+    created_at INTEGER NOT NULL DEFAULT (unixepoch())
+);
+
+-- Indexes
+CREATE INDEX IF NOT EXISTS idx_nodes_kind ON nodes(kind);
+CREATE INDEX IF NOT EXISTS idx_nodes_file ON nodes(file_path);
+CREATE INDEX IF NOT EXISTS idx_nodes_language ON nodes(language);
+CREATE INDEX IF NOT EXISTS idx_nodes_qualified ON nodes(qualified_name);
+CREATE INDEX IF NOT EXISTS idx_nodes_lower_name ON nodes(lower(name));
+CREATE INDEX IF NOT EXISTS idx_edges_source ON edges(source_id);
+CREATE INDEX IF NOT EXISTS idx_edges_target ON edges(target_id);
+CREATE INDEX IF NOT EXISTS idx_edges_kind ON edges(kind);
+CREATE INDEX IF NOT EXISTS idx_edges_confidence ON edges(confidence);
+CREATE INDEX IF NOT EXISTS idx_edges_dataflow ON edges(kind, source_id) WHERE kind IN ('data_flow', 'reads', 'writes');
+CREATE INDEX IF NOT EXISTS idx_edges_resolved ON edges(resolved_target) WHERE resolved_target != '';
+CREATE INDEX IF NOT EXISTS idx_nodes_content_hash ON nodes(content_hash) WHERE content_hash != '';
+CREATE INDEX IF NOT EXISTS idx_fnd_node ON file_node_deps(node_id);
+
+-- FTS5 triggers to keep index in sync
+CREATE TRIGGER IF NOT EXISTS nodes_ai AFTER INSERT ON nodes BEGIN
+    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
+    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
+END;
+
+CREATE TRIGGER IF NOT EXISTS nodes_ad AFTER DELETE ON nodes BEGIN
+    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
+    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
+END;
+
+CREATE TRIGGER IF NOT EXISTS nodes_au AFTER UPDATE ON nodes BEGIN
+    INSERT INTO nodes_fts(nodes_fts, rowid, id, name, qualified_name, docstring, signature)
+    VALUES ('delete', OLD.rowid, OLD.id, OLD.name, OLD.qualified_name, OLD.docstring, OLD.signature);
+    INSERT INTO nodes_fts(rowid, id, name, qualified_name, docstring, signature)
+    VALUES (NEW.rowid, NEW.id, NEW.name, NEW.qualified_name, NEW.docstring, NEW.signature);
+END;
+"""
+
+
+def init_db(db_path: Path | None = None) -> None:
+    """Initialize the database schema."""
+    if db_path is None:
+        db_path = Path.cwd() / ".codemesh" / "index.db"
+    with get_connection(db_path) as conn:
+        conn.executescript(SCHEMA_SQL)
+
+
+def migrate_db(db_path: Path | None = None) -> None:
+    """Run any pending migrations."""
+    init_db(db_path)

codemesh/embedding/__init__.py

@@ -0,0 +1,3 @@
+"""Code embedding generation."""
+
+from __future__ import annotations

codemesh/extraction/__init__.py

@@ -0,0 +1,7 @@
+"""Code extraction layer: tree-sitter AST parsing into knowledge graph."""
+
+from __future__ import annotations
+
+from codemesh.extraction.orchestrator import ExtractionOrchestrator
+
+__all__ = ["ExtractionOrchestrator"]

codemesh/extraction/languages/__init__.py

@@ -0,0 +1,95 @@
+"""Language-specific tree-sitter extractors."""
+
+from __future__ import annotations
+
+from pathlib import Path  # noqa: TC003
+from typing import Protocol
+
+from codemesh.types import Edge, Language, Node
+
+
+class LanguageExtractor(Protocol):
+    """Protocol for language-specific extractors."""
+
+    def extract(
+        self,
+        file_path: Path,
+        source: bytes,
+        root_node: object,
+        language: Language,
+    ) -> tuple[list[Node], list[Edge]]: ...
+
+
+_EXTRACTORS: dict[Language, LanguageExtractor] = {}
+
+
+def register_extractor(language: Language, extractor: LanguageExtractor) -> None:
+    """Register a language extractor."""
+    _EXTRACTORS[language] = extractor
+
+
+def get_extractor(language: Language) -> LanguageExtractor | None:
+    """Get the extractor for a language."""
+    return _EXTRACTORS.get(language)
+
+
+# Import and register all extractors
+def _register_all() -> None:
+    """Register all available extractors."""
+    try:
+        from codemesh.extraction.languages.python import PythonExtractor
+
+        register_extractor(Language.PYTHON, PythonExtractor())
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.typescript import TypeScriptExtractor
+
+        ts_extractor = TypeScriptExtractor()
+        register_extractor(Language.TYPESCRIPT, ts_extractor)
+        register_extractor(Language.JAVASCRIPT, ts_extractor)
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.rust import RustExtractor
+
+        register_extractor(Language.RUST, RustExtractor())
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.swift import SwiftExtractor
+
+        register_extractor(Language.SWIFT, SwiftExtractor())
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.go import GoExtractor
+
+        register_extractor(Language.GO, GoExtractor())
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.java import JavaExtractor
+
+        java_extractor = JavaExtractor()
+        register_extractor(Language.JAVA, java_extractor)
+        register_extractor(Language.KOTLIN, java_extractor)
+    except ImportError:
+        pass
+
+    try:
+        from codemesh.extraction.languages.c_family import CFamilyExtractor
+
+        c_family_extractor = CFamilyExtractor()
+        register_extractor(Language.C, c_family_extractor)
+        register_extractor(Language.CPP, c_family_extractor)
+    except ImportError:
+        pass
+
+
+_register_all()