codeanalyzer-python 0.1.14__py3-none-any.whl → 0.2.0__py3-none-any.whl

codeanalyzer/__main__.py

@@ -7,13 +7,18 @@ from codeanalyzer.core import Codeanalyzer
 from codeanalyzer.utils import _set_log_level, logger
 from codeanalyzer.config import OutputFormat
 from codeanalyzer.schema import model_dump_json
-from codeanalyzer.options import AnalysisOptions
+from codeanalyzer.options import AnalysisOptions, EmitTarget
 
 
 def main(
     input: Annotated[
-        Path, typer.Option("-i", "--input", help="Path to the project root directory.")
-    ],
+        Optional[Path],
+        typer.Option(
+            "-i",
+            "--input",
+            help="Path to the project root directory (not required for --emit schema).",
+        ),
+    ] = None,
     output: Annotated[
         Optional[Path],
         typer.Option("-o", "--output", help="Output directory for artifacts."),
@@ -23,10 +28,61 @@ def main(
         typer.Option(
             "-f",
             "--format",
-            help="Output format: json or msgpack.",
+            help="Output format for --emit json: json or msgpack.",
             case_sensitive=False,
         ),
     ] = OutputFormat.JSON,
+    emit: Annotated[
+        EmitTarget,
+        typer.Option(
+            "--emit",
+            help="Output target: json (analysis.json, default) | neo4j (graph.cypher or live "
+            "Bolt push) | schema (the Neo4j schema.json contract).",
+            case_sensitive=False,
+        ),
+    ] = EmitTarget.JSON,
+    app_name: Annotated[
+        Optional[str],
+        typer.Option(
+            "--app-name",
+            help="Logical application name for the graph :PyApplication anchor "
+            "(default: input dir name).",
+        ),
+    ] = None,
+    neo4j_uri: Annotated[
+        Optional[str],
+        typer.Option(
+            "--neo4j-uri",
+            envvar="NEO4J_URI",
+            help="Push the graph to a live Neo4j over Bolt (incremental); omit to write "
+            "graph.cypher. [env: NEO4J_URI]",
+        ),
+    ] = None,
+    neo4j_user: Annotated[
+        str,
+        typer.Option(
+            "--neo4j-user",
+            envvar="NEO4J_USERNAME",
+            help="Neo4j username. [env: NEO4J_USERNAME]",
+        ),
+    ] = "neo4j",
+    neo4j_password: Annotated[
+        str,
+        typer.Option(
+            "--neo4j-password",
+            envvar="NEO4J_PASSWORD",
+            help="Neo4j password. Prefer the env var over the flag (the flag is visible in shell "
+            "history / process list). [env: NEO4J_PASSWORD]",
+        ),
+    ] = "neo4j",
+    neo4j_database: Annotated[
+        Optional[str],
+        typer.Option(
+            "--neo4j-database",
+            envvar="NEO4J_DATABASE",
+            help="Neo4j database name (default: server default). [env: NEO4J_DATABASE]",
+        ),
+    ] = None,
     using_codeql: Annotated[
         bool, typer.Option("--codeql/--no-codeql", help="Enable CodeQL-based analysis.")
     ] = False,
@@ -78,6 +134,12 @@ def main(
         input=input,
         output=output,
         format=format,
+        emit=emit,
+        app_name=app_name,
+        neo4j_uri=neo4j_uri,
+        neo4j_user=neo4j_user,
+        neo4j_password=neo4j_password,
+        neo4j_database=neo4j_database,
         using_codeql=using_codeql,
         using_ray=using_ray,
         rebuild_analysis=rebuild_analysis,
@@ -89,6 +151,18 @@ def main(
     )
 
     _set_log_level(options.verbosity)
+
+    # The schema contract is a static artifact — no project analysis required.
+    if options.emit == EmitTarget.SCHEMA:
+        from codeanalyzer.neo4j.emit import emit_schema
+
+        emit_schema(options.output)
+        return
+
+    # Every other target requires an input project.
+    if options.input is None:
+        logger.error("Missing option '-i' / '--input' (required for --emit json | neo4j).")
+        raise typer.Exit(code=1)
     if not options.input.exists():
         logger.error(f"Input path '{options.input}' does not exist.")
         raise typer.Exit(code=1)
@@ -112,7 +186,11 @@ def main(
     with Codeanalyzer(options) as analyzer:
         artifacts = analyzer.analyze()
 
-        if options.output is None:
+        if options.emit == EmitTarget.NEO4J:
+            from codeanalyzer.neo4j.emit import emit_neo4j
+
+            emit_neo4j(artifacts, options)
+        elif options.output is None:
             print(model_dump_json(artifacts, separators=(",", ":")))
         else:
             options.output.mkdir(parents=True, exist_ok=True)
@@ -142,7 +220,7 @@ def _write_output(artifacts, output_dir: Path, format: OutputFormat):
 
 app = typer.Typer(
     callback=main,
-    name="codeanalyzer",
+    name="canpy",
     help="Static Analysis on Python source code using Jedi, CodeQL and Tree sitter.",
     invoke_without_command=True,
     no_args_is_help=True,
@@ -151,5 +229,20 @@ app = typer.Typer(
     pretty_exceptions_show_locals=False,
 )
 
+def deprecated_main() -> None:
+    """Entry point for the legacy ``codeanalyzer`` command. Prints a one-line
+    deprecation notice to stderr (so piped stdout — e.g. ``--emit schema`` — stays
+    clean) and then runs the CLI unchanged. Kept for backwards compatibility; will
+    be removed in a future release."""
+    import sys
+
+    print(
+        "codeanalyzer: this command has been renamed to `canpy`. The `codeanalyzer` "
+        "alias is deprecated and will be removed in a future release — please use `canpy`.",
+        file=sys.stderr,
+    )
+    app()
+
+
 if __name__ == "__main__":
     app()

codeanalyzer/neo4j/__init__.py

@@ -0,0 +1,46 @@
+################################################################################
+# Copyright IBM Corporation 2025
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#       http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+################################################################################
+
+"""Neo4j output: a pure projection of the :class:`PyApplication` IR to graph rows,
+plus the two writers (cypher snapshot / bolt incremental). Nothing here runs
+unless ``--emit neo4j`` (or ``--emit schema``) is selected.
+"""
+from codeanalyzer.neo4j.bolt import BoltConfig, bolt_writer
+from codeanalyzer.neo4j.catalog import (
+    MARKER_LABELS,
+    NODE_LABELS,
+    REL_TYPES,
+    SCHEMA_VERSION,
+    build_schema_document,
+)
+from codeanalyzer.neo4j.cypher import render_cypher
+from codeanalyzer.neo4j.project import project
+from codeanalyzer.neo4j.rows import EdgeRow, GraphRows, NodeRow
+
+__all__ = [
+    "project",
+    "render_cypher",
+    "bolt_writer",
+    "BoltConfig",
+    "build_schema_document",
+    "SCHEMA_VERSION",
+    "NODE_LABELS",
+    "REL_TYPES",
+    "MARKER_LABELS",
+    "GraphRows",
+    "NodeRow",
+    "EdgeRow",
+]

codeanalyzer/neo4j/bolt.py

@@ -0,0 +1,223 @@
+################################################################################
+# Copyright IBM Corporation 2025
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#       http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+################################################################################
+
+"""The incremental writer: push :class:`GraphRows` into a live Neo4j over Bolt.
+Unlike the snapshot writer, this one reads the DB's current state and updates
+only what changed.
+
+Algorithm (the module subgraph is the unit of idempotent replacement):
+  1. ensure constraints + indexes.
+  2. diff each module's ``content_hash`` against the DB → the set of changed modules.
+  3. per changed module, in a transaction: delete the edges it owned (edges out of
+     its nodes), detach-delete the declarations it no longer emits, then upsert
+     its current nodes.
+  4. upsert edges owned by changed modules (+ the shared edges).
+  5. on a FULL run only, prune modules whose source file vanished.
+
+Nodes are MERGE-upserted, never blindly deleted, so a declaration another
+(unchanged) module still references survives and its incoming edges stay valid.
+``:PyExternal`` / ``:PyPackage`` / ``:PyDecorator`` are shared (no ``_module``) and are
+MERGE-only.
+
+The ``neo4j`` driver is imported lazily so it stays an optional dependency and
+off the default (json) output path entirely.
+"""
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Dict, List, Optional
+
+from codeanalyzer.neo4j.rows import EdgeRow, GraphRows, NodeRow, chunk
+from codeanalyzer.neo4j.schema import CONSTRAINTS, INDEXES
+from codeanalyzer.utils import logger
+
+DESCENDANTS = "[:PY_DECLARES|PY_HAS_METHOD|PY_HAS_ATTRIBUTE|PY_DECLARES_VAR|PY_HAS_CALLSITE*1..]"
+BATCH = 1000
+
+
+@dataclass
+class BoltConfig:
+    uri: str
+    user: str
+    password: str
+    database: Optional[str] = None
+
+
+def bolt_writer(rows: GraphRows, cfg: BoltConfig, full_run: bool) -> None:
+    try:
+        import neo4j  # noqa: WPS433 (lazy, optional dependency)
+    except ImportError as exc:  # pragma: no cover - exercised only without the extra
+        raise RuntimeError(
+            "The 'neo4j' driver is required for '--emit neo4j --neo4j-uri'. "
+            "Install it with: pip install 'codeanalyzer-python[neo4j]'"
+        ) from exc
+
+    driver = neo4j.GraphDatabase.driver(cfg.uri, auth=(cfg.user, cfg.password))
+    session_kwargs = {"database": cfg.database} if cfg.database else {}
+
+    def session():
+        return driver.session(**session_kwargs)
+
+    try:
+        # 1. schema (DDL runs in its own autocommit transactions).
+        with session() as s:
+            for stmt in [*CONSTRAINTS, *INDEXES]:
+                s.run(stmt)
+
+        # Partition nodes by owning module; shared nodes have no _module.
+        by_module: Dict[str, List[NodeRow]] = {}
+        shared: List[NodeRow] = []
+        module_of: Dict[str, str] = {}  # node value → owning module
+        for n in rows.nodes:
+            m = n.props.get("_module")
+            if isinstance(m, str):
+                by_module.setdefault(m, []).append(n)
+                module_of[n.value] = m
+            else:
+                shared.append(n)
+
+        # 2. diff content_hash.
+        db_hash: Dict[str, Optional[str]] = {}
+        with session() as s:
+            res = s.run("MATCH (m:PyModule) RETURN m.file_key AS k, m.content_hash AS h")
+            for rec in res:
+                db_hash[rec["k"]] = rec["h"]
+        changed = set()
+        for m, nodes in by_module.items():
+            row_hash = _hash_of(nodes, m)
+            if m not in db_hash or row_hash is None or row_hash != db_hash.get(m):
+                changed.add(m)
+        logger.info(
+            f"neo4j(bolt): {len(by_module)} modules ({len(changed)} changed), "
+            f"{len(shared)} shared nodes, {len(rows.edges)} edges"
+        )
+
+        # 3. shared nodes are always upserted (MERGE-only).
+        _upsert_nodes(session, neo4j, shared)
+
+        # 4. per changed module: purge owned edges + vanished decls, then upsert its nodes.
+        for m in changed:
+            nodes = by_module[m]
+            keys = [n.value for n in nodes]
+            with session() as s:
+                def _purge(tx, module=m, node_keys=keys):
+                    tx.run("MATCH (x {_module: $m})-[r]->() DELETE r", m=module)
+                    tx.run(
+                        "MATCH (x {_module: $m}) "
+                        "WHERE NOT coalesce(x.signature, x.id, x.file_key) IN $keys "
+                        "DETACH DELETE x",
+                        m=module,
+                        keys=node_keys,
+                    )
+
+                s.execute_write(_purge)
+            _upsert_nodes(session, neo4j, nodes)
+
+        # 5. upsert edges owned by a changed module (owner = source node's module) or shared.
+        edges = [
+            e
+            for e in rows.edges
+            if module_of.get(e.from_ref.value) is None or module_of.get(e.from_ref.value) in changed
+        ]
+        _upsert_edges(session, neo4j, edges)
+
+        # 6. orphan prune — only safe on a full run (a targeted run can't tell deleted from untargeted).
+        if full_run:
+            present = list(by_module.keys())
+            with session() as s:
+                res = s.run(
+                    "MATCH (m:PyModule) WHERE NOT m.file_key IN $present "
+                    f"OPTIONAL MATCH (m)-{DESCENDANTS}->(x) DETACH DELETE x, m "
+                    "RETURN count(m) AS pruned",
+                    present=present,
+                )
+                pruned = res.single()
+                pruned_count = pruned["pruned"] if pruned else 0
+                logger.info(f"neo4j(bolt): pruned {pruned_count} vanished module(s)")
+        else:
+            logger.info(
+                "neo4j(bolt): targeted run — orphan pruning skipped (deleted files not removed)"
+            )
+    finally:
+        driver.close()
+
+
+# ----------------------------------------------------------------------------------------------
+# Batched upserts
+# ----------------------------------------------------------------------------------------------
+
+
+def _upsert_nodes(session, neo4j, nodes: List[NodeRow]) -> None:
+    groups: Dict[str, List[NodeRow]] = {}
+    for n in nodes:
+        groups.setdefault(f"{':'.join(n.labels)}|{n.key_prop}", []).append(n)
+
+    for group in groups.values():
+        labels = group[0].labels
+        key_prop = group[0].key_prop
+        set_labels = f", n:{':'.join(labels[1:])}" if len(labels) > 1 else ""
+        cypher = (
+            f"UNWIND $rows AS row MERGE (n:{labels[0]} {{{key_prop}: row.k}}) "
+            f"SET n += row.p{set_labels}"
+        )
+        for batch in chunk(group, BATCH):
+            payload = [{"k": n.value, "p": _to_params(n.props, neo4j)} for n in batch]
+            with session() as s:
+                s.run(cypher, rows=payload)
+
+
+def _upsert_edges(session, neo4j, edges: List[EdgeRow]) -> None:
+    groups: Dict[str, List[EdgeRow]] = {}
+    for e in edges:
+        key = f"{e.type}|{e.from_ref.label}.{e.from_ref.key_prop}|{e.to_ref.label}.{e.to_ref.key_prop}"
+        groups.setdefault(key, []).append(e)
+
+    for group in groups.values():
+        first = group[0]
+        from_ref, to_ref = first.from_ref, first.to_ref
+        cypher = (
+            f"UNWIND $rows AS row "
+            f"MATCH (a:{from_ref.label} {{{from_ref.key_prop}: row.f}}) "
+            f"MATCH (b:{to_ref.label} {{{to_ref.key_prop}: row.t}}) "
+            f"MERGE (a)-[r:{first.type}]->(b) SET r += row.p"
+        )
+        for batch in chunk(group, BATCH):
+            payload = [
+                {"f": e.from_ref.value, "t": e.to_ref.value, "p": _to_params(e.props, neo4j)}
+                for e in batch
+            ]
+            with session() as s:
+                s.run(cypher, rows=payload)
+
+
+# ----------------------------------------------------------------------------------------------
+# Helpers
+# ----------------------------------------------------------------------------------------------
+
+
+def _hash_of(nodes: List[NodeRow], file_key: str) -> Optional[str]:
+    for n in nodes:
+        if n.labels[0] == "PyModule" and n.value == file_key:
+            h = n.props.get("content_hash")
+            return h if isinstance(h, str) else None
+    return None
+
+
+def _to_params(props, neo4j) -> dict:
+    """Map props to driver params. The Python driver already distinguishes int
+    from float, so unlike the JS driver no integer coercion is needed — this is a
+    straight passthrough kept symmetric with the snapshot writer's shape."""
+    return dict(props)

codeanalyzer/neo4j/catalog.py

@@ -0,0 +1,245 @@
+################################################################################
+# Copyright IBM Corporation 2025
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#       http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+################################################################################
+
+"""The declarative Neo4j schema catalog — the single in-repo source of truth for
+the graph contract (node labels, their keys and typed properties, relationship
+types and their endpoints). ``--emit schema`` serializes this (with the DDL from
+:mod:`codeanalyzer.neo4j.schema`) to a machine-readable ``schema.json``, and the
+conformance test (``test/test_neo4j_schema.py``) asserts the real emitter never
+produces a label / relationship / property that isn't declared here — so this
+file cannot silently drift from :mod:`codeanalyzer.neo4j.project`.
+
+SCHEMA_VERSION is the contract version: bump MAJOR on a breaking change
+(renamed/removed label, relationship or key), MINOR on an additive change (new
+label/rel/property). It is stamped onto the ``:PyApplication`` node of every
+emitted graph so any consumer can detect a producer/consumer mismatch at runtime.
+"""
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Dict, List
+
+from codeanalyzer.neo4j.schema import CONSTRAINTS, INDEXES
+
+SCHEMA_VERSION = "1.0.0"
+
+# PropType ∈ {"string", "integer", "float", "boolean", "string[]", "integer[]"}.
+
+
+@dataclass
+class NodeLabel:
+    label: str  # the specific label (also the catalog key)
+    merge_label: str  # the label the uniqueness constraint / MERGE is on
+    key: str
+    properties: Dict[str, str]
+
+
+@dataclass
+class RelType:
+    type: str
+    from_labels: List[str]
+    to_labels: List[str]
+    properties: Dict[str, str] = field(default_factory=dict)
+
+
+# Labels layered onto a node in addition to its primary/specific label.
+MARKER_LABELS: List[str] = []
+
+_SPAN = {"start_line": "integer", "end_line": "integer"}
+
+
+NODE_LABELS: List[NodeLabel] = [
+    NodeLabel(
+        "PyApplication",
+        "PyApplication",
+        "name",
+        {"name": "string", "schema_version": "string"},
+    ),
+    NodeLabel(
+        "PyModule",
+        "PyModule",
+        "file_key",
+        {
+            "file_key": "string",
+            "module_name": "string",
+            "content_hash": "string",
+            "last_modified": "float",
+            "file_size": "integer",
+            "_module": "string",
+        },
+    ),
+    NodeLabel(
+        "PyClass",
+        "PySymbol",
+        "signature",
+        {
+            "signature": "string",
+            "name": "string",
+            "code": "string",
+            "base_classes": "string[]",
+            "docstring": "string",
+            **_SPAN,
+            "_module": "string",
+        },
+    ),
+    NodeLabel(
+        "PyCallable",
+        "PySymbol",
+        "signature",
+        {
+            "signature": "string",
+            "name": "string",
+            "path": "string",
+            "return_type": "string",
+            "cyclomatic_complexity": "integer",
+            "code": "string",
+            "code_start_line": "integer",
+            **_SPAN,
+            "docstring": "string",
+            "decorators": "string[]",
+            "parameters_json": "string",
+            "accessed_symbols_json": "string",
+            "_module": "string",
+        },
+    ),
+    NodeLabel(
+        "PyExternal",
+        "PySymbol",
+        "signature",
+        {"signature": "string", "name": "string"},
+    ),
+    NodeLabel("PyPackage", "PyPackage", "name", {"name": "string"}),
+    NodeLabel(
+        "PyDecorator",
+        "PyDecorator",
+        "name",
+        {"name": "string"},
+    ),
+    NodeLabel(
+        "PyCallSite",
+        "PyCallSite",
+        "id",
+        {
+            "id": "string",
+            "method_name": "string",
+            "receiver_expr": "string",
+            "receiver_type": "string",
+            "argument_types": "string[]",
+            "return_type": "string",
+            "callee_signature": "string",
+            "is_constructor_call": "boolean",
+            "start_line": "integer",
+            "start_column": "integer",
+            "end_line": "integer",
+            "end_column": "integer",
+            "_module": "string",
+        },
+    ),
+    NodeLabel(
+        "PyAttribute",
+        "PyAttribute",
+        "id",
+        {
+            "id": "string",
+            "name": "string",
+            "type": "string",
+            "docstring": "string",
+            **_SPAN,
+            "_module": "string",
+        },
+    ),
+    NodeLabel(
+        "PyVariable",
+        "PyVariable",
+        "id",
+        {
+            "id": "string",
+            "name": "string",
+            "type": "string",
+            "initializer": "string",
+            "scope": "string",
+            **_SPAN,
+            "_module": "string",
+        },
+    ),
+]
+
+_DECL_TARGETS = ["PyClass", "PyCallable"]
+
+
+REL_TYPES: List[RelType] = [
+    RelType("PY_HAS_MODULE", ["PyApplication"], ["PyModule"]),
+    RelType("PY_DECLARES", ["PyModule", "PyClass", "PyCallable"], _DECL_TARGETS),
+    RelType("PY_HAS_METHOD", ["PyClass"], ["PyCallable"]),
+    RelType("PY_HAS_ATTRIBUTE", ["PyClass"], ["PyAttribute"]),
+    RelType("PY_DECLARES_VAR", ["PyModule", "PyCallable"], ["PyVariable"]),
+    RelType("PY_HAS_CALLSITE", ["PyCallable"], ["PyCallSite"]),
+    RelType("PY_RESOLVES_TO", ["PyCallSite"], ["PyCallable", "PyExternal"]),
+    RelType(
+        "PY_CALLS",
+        ["PyCallable", "PyExternal"],
+        ["PyCallable", "PyExternal"],
+        {"weight": "integer", "provenance": "string[]"},
+    ),
+    RelType("PY_EXTENDS", ["PyClass"], ["PyClass"]),
+    RelType(
+        "PY_IMPORTS",
+        ["PyModule"],
+        ["PyPackage"],
+        {"imported_names": "string[]", "aliases": "string[]"},
+    ),
+    RelType("PY_DECORATED_BY", ["PyCallable"], ["PyDecorator"]),
+]
+
+
+@dataclass
+class SchemaDocument:
+    schema_version: str
+    generator: str
+    marker_labels: List[str]
+    node_labels: List[NodeLabel]
+    relationship_types: List[RelType]
+    constraints: List[str]
+    indexes: List[str]
+
+
+def build_schema_document() -> dict:
+    """Build the full machine-readable schema document emitted by ``--emit schema``."""
+    return {
+        "schema_version": SCHEMA_VERSION,
+        "generator": "codeanalyzer-python",
+        "marker_labels": list(MARKER_LABELS),
+        "node_labels": [
+            {
+                "label": n.label,
+                "merge_label": n.merge_label,
+                "key": n.key,
+                "properties": n.properties,
+            }
+            for n in NODE_LABELS
+        ],
+        "relationship_types": [
+            {
+                "type": r.type,
+                "from": r.from_labels,
+                "to": r.to_labels,
+                "properties": r.properties,
+            }
+            for r in REL_TYPES
+        ],
+        "constraints": list(CONSTRAINTS),
+        "indexes": list(INDEXES),
+    }