codeanalyzer-python 1.4.0__py3-none-any.whl → 1.5.0__py3-none-any.whl

codeanalyzer/core.py

@@ -19,6 +19,7 @@ from codeanalyzer.schema import (
     model_validate_json,
 )
 from codeanalyzer.schema.assign_ids import assign_ids
+from codeanalyzer.schema.ids import external_id
 from codeanalyzer.schema.l1_body import populate_l1_body
 from codeanalyzer.schema.l2_callees import backfill_callees
 from codeanalyzer.schema.call_graph_ids import reidentify_call_graph
@@ -564,8 +565,7 @@ class Codeanalyzer:
                 if sig in sig_to_id:
                     continue
                 module, name = sig.rsplit(".", 1) if "." in sig else (None, sig)
-                ext_id = f"{app_id}/@external/{module}/{name}" if module else \
-                    f"{app_id}/@external/{name}"
+                ext_id = external_id(app_id, module, name)
                 sig_to_id[sig] = ext_id
                 externals[ext_id] = PyExternalSymbol(
                     id=ext_id, name=name, module=module

codeanalyzer/dataflow/builder.py

@@ -43,6 +43,7 @@ from codeanalyzer.dataflow.alias import TypeBasedAliasOracle
 from codeanalyzer.dataflow.pdg import build_pdg
 from codeanalyzer.dataflow.sdg import ProgramGraphsIR, assemble_sdg
 from codeanalyzer.dataflow.summaries import CallSite, FunctionInfo, compute_summaries
+from codeanalyzer.schema.ids import stamp_body_ids
 from codeanalyzer.schema.py_schema import PyApplication, PyCallable, PyClass, PyModule
 from codeanalyzer.utils import logger
 
@@ -333,6 +334,7 @@ def emit_l3_body(
                     for e in pdg.edges
                     if e.type == "DDG"
                 ]
+            stamp_body_ids(pycallable)
 
 
 def build_program_graphs(
@@ -538,6 +540,7 @@ def emit_l4(
             pycallable.body[im.local(pn.id)] = BodyNode(
                 kind=pn.kind, of=pn.var, parent=parent
             )
+        stamp_body_ids(pycallable)
 
     # (b/c/d) SDG edges → summary / param_in / param_out; CALL dropped.
     for e in ir.sdg_edges:

codeanalyzer/dataflow/identity.py

@@ -16,6 +16,8 @@ from __future__ import annotations
 from collections import defaultdict
 from typing import Dict, Iterable, Optional, Tuple
 
+from codeanalyzer.schema.ids import global_ordinal
+
 
 class IdentityMap:
     def __init__(self, callable_id: str, id_to_local: Dict[int, str]):
@@ -83,9 +85,7 @@ class IdentityMap:
 
     def global_id(self, node_id: int) -> str:
         """Fully addressable id: ``"<callable-id>@<local>"``."""
-        loc = self._map[node_id]
-        # local statements are "line:col"; bookends already carry the leading "@"
-        return f"{self._callable_id}{loc}" if loc.startswith("@") else f"{self._callable_id}@{loc}"
+        return global_ordinal(self._callable_id, self._map[node_id])
 
     def node_ids(self) -> Iterable[int]:
         return self._map.keys()

codeanalyzer/entrypoints/matching.py

@@ -64,7 +64,8 @@ def _compile(pattern: str) -> str:
         if ch == "{":
             j = pattern.index("}", i)
             alts = pattern[i + 1 : j].split(",")
-            out.append("(?:" + "|".join(re.escape(a.strip()) for a in alts) + ")")
+            # `*` keeps its meaning inside an alternative, so `{route,*.route}` works.
+            out.append("(?:" + "|".join(_compile(a.strip()) for a in alts) + ")")
             i = j + 1
         elif ch == "*":
             out.append(r"[^.\s]*")
@@ -93,15 +94,17 @@ def _route_of(dec, spec: Optional[Dict[str, Any]]) -> Optional[str]:
     if idx >= len(args):
         return None
     value = _literal(args[idx])
+    if isinstance(value, (list, tuple)):
+        value = next((v for v in value if isinstance(v, str)), None)
     return value if isinstance(value, str) else None
 
 
-def _methods_of(dec, spec: Optional[Dict[str, Any]]) -> List[str]:
+def _methods_of(dec, spec: Optional[Dict[str, Any]], qualified: Optional[str] = None) -> List[str]:
     if not spec:
         return []
     source = spec.get("from")
     if source == "match_suffix":
-        verb = (dec.qualified_name or "").rsplit(".", 1)[-1]
+        verb = (qualified or dec.qualified_name or "").rsplit(".", 1)[-1]
         return [verb.upper()]
     if source == "keyword":
         raw = (dec.keyword_arguments or {}).get(spec.get("name", ""))
@@ -113,12 +116,27 @@ def _methods_of(dec, spec: Optional[Dict[str, Any]]) -> List[str]:
 
 
 def entrypoints_from_decorators(
-    node, framework: str, rules: Iterable["DecoratorRule"]
+    node,
+    framework: str,
+    rules: Iterable["DecoratorRule"],
+    resolve: Optional[Callable[[str], str]] = None,
+    on_written: bool = False,
 ) -> List[PyEntrypoint]:
+    """``resolve`` is the module's import-table resolver (#177): when Jedi could
+    not resolve a decorator (the framework is not importable in the analysis
+    environment -- every ``--no-venv`` run), ``@http.route`` still resolves to
+    ``odoo.http.route`` from ``from odoo import http`` alone, the same way base
+    classes already do. Jedi's definition path wins when it exists.
+
+    ``on_written`` is the heuristic tier: rules match the decorator's spelling
+    as WRITTEN (``http.route``, ``router.post``), no resolution at all, so a
+    shape that reads as an HTTP entrypoint is recorded whether or not any
+    framework rule knows the library behind it."""
     out: List[PyEntrypoint] = []
     for dec in getattr(node, "decorators", []) or []:
+        qualified = dec.name if on_written else decorator_qualified_name(dec, resolve)
         for rule in rules:
-            if not match_pattern(rule.match, dec.qualified_name):
+            if not match_pattern(rule.match, qualified):
                 continue
             out.append(
                 PyEntrypoint(
@@ -126,14 +144,25 @@ def entrypoints_from_decorators(
                     confidence=rule.confidence,
                     rule=rule.id,
                     ruleset=rule.origin,
-                    evidence=dec.qualified_name,
+                    evidence=qualified,
                     route=_route_of(dec, rule.route),
-                    http_methods=_methods_of(dec, rule.methods),
+                    http_methods=_methods_of(dec, rule.methods, qualified),
                 )
             )
     return out
 
 
+def decorator_qualified_name(dec, resolve: Optional[Callable[[str], str]]) -> Optional[str]:
+    """Jedi's resolution, else the import-table resolution of the written
+    spelling, else ``None`` (a spelling the import table cannot map either)."""
+    if dec.qualified_name:
+        return dec.qualified_name
+    if resolve is None:
+        return None
+    resolved = resolve(dec.name)
+    return resolved if resolved != dec.name else None
+
+
 def entrypoints_from_bases(
     cls,
     framework: str,

codeanalyzer/entrypoints/pipeline.py

@@ -6,11 +6,14 @@ loses flags, never the analysis.
 """
 from __future__ import annotations
 
+import builtins
 from pathlib import Path
-from typing import Dict, Iterable, Iterator
+from typing import Dict, Iterable, Iterator, Set
 
 from codeanalyzer.entrypoints.detect import detected_frameworks
-from codeanalyzer.entrypoints.matching import entrypoints_from_bases, entrypoints_from_decorators
+from codeanalyzer.entrypoints.matching import (
+    decorator_qualified_name, entrypoints_from_bases, entrypoints_from_decorators,
+)
 from codeanalyzer.entrypoints.rules import RuleSet, load_rules
 from codeanalyzer.schema.py_schema import PyApplication, PyCallable, PyClass, PyModule
 from codeanalyzer.utils import logger
@@ -56,18 +59,34 @@ def _run_stages(app: PyApplication, project_dir: Path, rules: RuleSet) -> None:
     """
     for node in _walk(app):
         node.entrypoints = []
+    app.entrypoint_report.unresolved = {}
 
     app.entrypoint_report.rulesets = list(rules.rulesets)
     frameworks = detected_frameworks(app, project_dir, rules)
     app.entrypoint_report.frameworks_detected = sorted(frameworks)
 
     names = sorted(frameworks)
+    unresolved = app.entrypoint_report.unresolved
     for mod in app.symbol_table.values():
         resolve = _base_resolver(mod)
+        known = _known_heads(mod)
         for node in _walk_module(mod):
+            # #177: what neither Jedi nor the import table could name. This is
+            # the counter that makes silence visible; it was never written before.
+            # A builtin, a declared class, or a name whose head is imported is
+            # nameable and is not counted (`object`, `Exception`, `typing.Generic[T]`).
+            for dec in getattr(node, "decorators", None) or []:
+                if decorator_qualified_name(dec, resolve) is None and _unnameable(dec.name, known):
+                    unresolved[dec.name] = unresolved.get(dec.name, 0) + 1
+            if isinstance(node, PyClass):
+                for base in node.base_classes or []:
+                    if _unnameable(base, known):
+                        unresolved[base] = unresolved.get(base, 0) + 1
             for name in names:
                 fw = rules.frameworks[name]
-                node.entrypoints.extend(entrypoints_from_decorators(node, name, fw.decorators))
+                node.entrypoints.extend(
+                    entrypoints_from_decorators(node, name, fw.decorators, resolve)
+                )
                 if isinstance(node, PyClass) and fw.bases:
                     class_eps, method_eps = entrypoints_from_bases(
                         node, name, fw.bases, resolve
@@ -77,6 +96,34 @@ def _run_stages(app: PyApplication, project_dir: Path, rules: RuleSet) -> None:
                         target = (node.callables or {}).get(method_name)
                         if target is not None:
                             target.entrypoints.extend(eps)
+            # Heuristic tier: the written spelling, no framework needed. Runs
+            # last so a node a framework rule already claimed keeps one record.
+            if not node.entrypoints and rules.heuristics:
+                node.entrypoints.extend(
+                    entrypoints_from_decorators(
+                        node, "heuristic", rules.heuristics, resolve, on_written=True
+                    )
+                )
+
+
+_BUILTIN_NAMES: Set[str] = set(dir(builtins))
+
+
+def _known_heads(mod: PyModule) -> Set[str]:
+    """Names that can head a nameable spelling in this module: its declared classes
+    and every imported name or alias."""
+    heads = {cl.name for cl in (mod.types or {}).values()}
+    for imp in mod.imports or []:
+        heads.add(imp.alias or imp.name)
+    return heads
+
+
+def _unnameable(written: str, known: Set[str]) -> bool:
+    """Whether a written base/decorator spelling maps to nothing this module can
+    name: not a builtin, not a declared class, and its head is not imported.
+    Subscripts (`Generic[T]`, `dict[K, V]`) are stripped before the check."""
+    head = written.split("[", 1)[0].split(".", 1)[0].strip()
+    return bool(head) and head not in _BUILTIN_NAMES and head not in known
 
 
 def _base_resolver(mod: PyModule):
@@ -90,7 +137,8 @@ def _base_resolver(mod: PyModule):
     aliases: Dict[str, str] = {}
     for imp in mod.imports or []:
         original = imp.alias or imp.name
-        aliases[imp.name] = imp.module if imp.module == original else f"{imp.module}.{original}"
+        module = imp.resolved_module or imp.module
+        aliases[imp.name] = module if imp.module == original else f"{module}.{original}"
 
     def resolve(written: str) -> str:
         head, _, rest = written.partition(".")

codeanalyzer/entrypoints/rules.py

@@ -22,7 +22,7 @@ _CONFIDENCE = {"declared", "certain", "heuristic"}
 # blocks (Units 4-5) not implemented yet; they are deliberately absent here
 # rather than accepted-and-ignored, so a user file using them fails loudly
 # instead of loading clean and doing nothing.
-_TOP_LEVEL_KEYS = {"version", "frameworks", "disable"}
+_TOP_LEVEL_KEYS = {"version", "frameworks", "heuristics", "disable"}
 
 
 class RulesError(Exception):
@@ -60,6 +60,10 @@ class Framework:
 @dataclass
 class RuleSet:
     frameworks: Dict[str, Framework] = field(default_factory=dict)
+    # Framework-independent decorator rules matched on the WRITTEN spelling,
+    # confidence `heuristic` by default. They run on every node regardless of
+    # `frameworks_detected` and never double a record a framework rule made.
+    heuristics: List[DecoratorRule] = field(default_factory=list)
     rulesets: List[str] = field(default_factory=list)
 
 
@@ -103,9 +107,16 @@ def _merge(out: RuleSet, data: Dict[str, Any], origin: str) -> None:
         for raw in body.get("bases") or []:
             fw.bases.append(_base_rule(raw, origin))
 
+    heuristics = data.get("heuristics") or {}
+    if not isinstance(heuristics, dict):
+        raise RulesError(f"{origin}: `heuristics` must be a mapping")
+    for raw in heuristics.get("decorators") or []:
+        out.heuristics.append(_decorator_rule({"confidence": "heuristic", **raw}, origin))
+
     for fw in out.frameworks.values():
         fw.decorators = [r for r in fw.decorators if r.id not in disabled]
         fw.bases = [r for r in fw.bases if r.id not in disabled]
+    out.heuristics = [r for r in out.heuristics if r.id not in disabled]
 
 
 def _disable_list(data: Dict[str, Any], origin: str) -> List[str]:

codeanalyzer/entrypoints/rules.yml

@@ -22,6 +22,24 @@ frameworks:
         transitive: true
         dispatch: [get, post, put, delete, patch]
 
+  odoo:
+    detect: [odoo]
+    decorators:
+      # `route` is a plain function in odoo/http.py, so Jedi's definition path
+      # and the import-table fallback (`from odoo import http` + `@http.route`,
+      # the shape every --no-venv run sees) both spell it `odoo.http.route`.
+      # The first positional may be one route or a list of them. Odoo serves
+      # GET and POST on a route unless `methods=` narrows it (json-typed routes
+      # are POST), so the default is both, not GET.
+      - id: odoo.route
+        match: "odoo.http.route"
+        route: {from: positional, index: 0}
+        methods: {from: keyword, name: methods, default: [GET, POST]}
+    bases:
+      - id: odoo.controller
+        match: "odoo.http.Controller"
+        transitive: true
+
   fastapi:
     detect: [fastapi]
     decorators:
@@ -86,3 +104,19 @@ frameworks:
         match: "django.views.generic.*"
         transitive: true
         dispatch: [get, post, put, patch, delete, head, options]
+
+# Framework-independent tier. Matched on the decorator's WRITTEN spelling, never
+# on a resolved name, so a shape that reads as an HTTP entrypoint is flagged even
+# when the library behind it has no `frameworks:` block above (or is not
+# importable). Confidence `heuristic`; a consumer wanting only certain hits
+# filters on it. A node a framework rule already matched gets no heuristic record.
+heuristics:
+  decorators:
+    - id: heuristic.http-route
+      match: "{route,*.route,*.*.route}"
+      route: {from: positional, index: 0}
+      methods: {from: keyword, name: methods}
+    - id: heuristic.http-verb
+      match: "{*,*.*}.{get,post,put,patch,delete,head,options,websocket}"
+      route: {from: positional, index: 0}
+      methods: {from: match_suffix}

codeanalyzer/neo4j/bolt.py

@@ -37,13 +37,16 @@ opt-in under the same flag that already forces a clean analysis rebuild.
 
 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
+``:PyExternal`` / ``:PyPackage`` / ``:PyDecorator`` have no owning module and are
 MERGE-only.
 
-Every ``_module`` match is anchored on the python-owned labels
-(``schema.MODULE_OWNED_PATTERN``). ``_module`` is a shared convention, not a python-private
-one -- codeanalyzer-java and codeanalyzer-typescript set it on their nodes too -- so an
-unlabelled match reaches a sibling analyzer's graph in a shared database (#171).
+**Every destructive statement is scoped on the ``can://`` id prefix** (#173). The id is a
+path — ``can://<app>/python/<file>/...`` — so ``id = <module-id> OR id STARTS WITH
+<module-id> + '/'`` is containment, and it is one application, one language and one
+module at once. That is what neither a label anchor nor the retired ``_module`` property
+could give: two python applications sharing ``src/foo.py`` carry identical labels and an
+identical file key, and only the id tells them apart. ``:PyCanNode`` anchors the predicate
+so it seeks an index instead of scanning the store; it carries no safety claim.
 
 The ``neo4j`` driver is imported lazily so it stays an optional dependency and
 off the default (json) output path entirely.
@@ -53,16 +56,34 @@ 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, MODULE_OWNED_PATTERN
+from codeanalyzer.neo4j.rows import (
+    CAN_NODE, EdgeRow, GraphRows, NodeRow, application_prefix, chunk, descendant_prefix,
+)
+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|PY_HAS_BODY_NODE*1..]"
-)
 BATCH = 1000
 
+# The per-module purge (#173): the module by equality, its subtree by prefix. Anchored
+# on :PyCanNode only so the predicate can seek (see ``rows.CAN_NODE``).
+PURGE_MODULE_EDGES = (
+    f"MATCH (x:{CAN_NODE}) WHERE x.id = $mid OR x.id STARTS WITH $pre "
+    "MATCH (x)-[r]->() DELETE r"
+)
+PURGE_VANISHED_NODES = (
+    f"MATCH (x:{CAN_NODE}) WHERE (x.id = $mid OR x.id STARTS WITH $pre) "
+    "AND NOT x.id IN $keys DETACH DELETE x"
+)
+# The orphan prune: modules inside this application's prefix that the run no longer
+# emits, and everything under each. Batched — deleting a large application in one
+# transaction exhausts dbms.memory.transaction.total.max (typescript#116).
+PRUNE_VANISHED_MODULES = (
+    f"MATCH (m:PyModule:{CAN_NODE}) WHERE m.id STARTS WITH $app AND NOT m.id IN $present "
+    f"CALL {{ WITH m MATCH (x:{CAN_NODE}) WHERE x.id = m.id OR x.id STARTS WITH m.id + '/' "
+    "DETACH DELETE x } IN TRANSACTIONS OF 1000 ROWS "
+    "RETURN count(*) AS pruned"
+)
+
 
 @dataclass
 class BoltConfig:
@@ -93,35 +114,50 @@ def bolt_writer(rows: GraphRows, cfg: BoltConfig, full_run: bool, eager: bool =
             for stmt in [*CONSTRAINTS, *INDEXES]:
                 s.run(stmt)
 
-        # The application anchor (a shared node) — used to scope the orphan prune
-        # so it never touches modules belonging to a different :PyApplication.
+        # The application anchor. Every destructive statement below is scoped to
+        # ``can://<app>/``; an empty application is refused up front rather than
+        # becoming ``STARTS WITH ''`` (every node in the database). The root row is
+        # keyed on its ``can://`` id now, so the name comes off its props — reading
+        # ``n.value`` here would build ``can://can://<app>/``.
         app_name = next(
-            (n.value for n in rows.nodes if n.labels and n.labels[0] == "PyApplication"),
+            (
+                n.props.get("name")
+                for n in rows.nodes
+                if n.labels and n.labels[0] == "PyApplication"
+            ),
             None,
         )
+        app_prefix = application_prefix(app_name)
 
-        # Partition nodes by owning module; shared nodes have no _module.
+        # Partition nodes by owning module (an in-memory field, never emitted, #173);
+        # shared nodes have none.
         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
+            if n.module is not None:
+                by_module.setdefault(n.module, []).append(n)
+                module_of[n.value] = n.module
             else:
                 shared.append(n)
 
-        # 2. diff content_hash.
+        # 2. diff content_hash, keyed by module id inside this application's prefix.
+        # Keyed by file key it was application-blind: a second application whose
+        # module shares the path and the hash looked "unchanged" and was never written.
         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")
+            res = s.run(
+                f"MATCH (m:PyModule:{CAN_NODE}) WHERE m.id STARTS WITH $app "
+                "RETURN m.id AS k, m.content_hash AS h",
+                app=app_prefix,
+            )
             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):
+            mid = _module_id_of(nodes)
+            row_hash = _hash_of(nodes)
+            if mid not in db_hash or row_hash is None or row_hash != db_hash.get(mid):
                 changed.add(m)
         logger.info(
             f"neo4j(bolt): {len(by_module)} modules ({len(changed)} changed), "
@@ -139,23 +175,19 @@ def bolt_writer(rows: GraphRows, cfg: BoltConfig, full_run: bool, eager: bool =
             if not eager:
                 _upsert_nodes(session, neo4j, nodes)
                 continue
+            # The module id comes from the module's own row, never by splitting a
+            # declaration's id: a file key may itself contain '/'.
+            module_id = _module_id_of(nodes)
+            if module_id is None or not module_id.startswith(app_prefix):
+                raise ValueError(
+                    f"neo4j: module {m!r} has no can:// id under {app_prefix!r}; "
+                    "refusing to purge"
+                )
             with session() as s:
-                def _purge(tx, module=m, node_keys=keys):
-                    # Anchored on python-owned labels: `_module` is also set by the java
-                    # and typescript analyzers, so an unlabelled match would delete a
-                    # sibling's nodes wherever a file key collides (#171).
-                    tx.run(
-                        f"MATCH (x:{MODULE_OWNED_PATTERN}) WHERE x._module = $m "
-                        "MATCH (x)-[r]->() DELETE r",
-                        m=module,
-                    )
-                    tx.run(
-                        f"MATCH (x:{MODULE_OWNED_PATTERN}) WHERE x._module = $m "
-                        "AND NOT coalesce(x.signature, x.id, x.file_key) IN $keys "
-                        "DETACH DELETE x",
-                        m=module,
-                        keys=node_keys,
-                    )
+                def _purge(tx, mid=module_id, node_keys=keys):
+                    params = {"mid": mid, "pre": descendant_prefix(mid)}
+                    tx.run(PURGE_MODULE_EDGES, **params)
+                    tx.run(PURGE_VANISHED_NODES, keys=node_keys, **params)
 
                 s.execute_write(_purge)
             _upsert_nodes(session, neo4j, nodes)
@@ -169,19 +201,13 @@ def bolt_writer(rows: GraphRows, cfg: BoltConfig, full_run: bool, eager: bool =
         _upsert_edges(session, neo4j, edges)
 
         # 6. orphan prune — only safe on a full run (a targeted run can't tell deleted from untargeted).
-        # Scope to THIS application's anchor so a full run for application B never
-        # deletes application A's modules from a shared database.
-        if full_run and eager and app_name is not None:
-            present = list(by_module.keys())
+        # Scoped to ``can://<app>/`` so a full run for application B never deletes
+        # application A's modules from a shared database — even when both are python and
+        # share a module path.
+        if full_run and eager:
+            present = [mid for mid in (_module_id_of(ns) for ns in by_module.values()) if mid]
             with session() as s:
-                res = s.run(
-                    "MATCH (:PyApplication {name: $app})-[:PY_HAS_MODULE]->(m:PyModule) "
-                    "WHERE NOT m.file_key IN $present "
-                    f"OPTIONAL MATCH (m)-{DESCENDANTS}->(x) DETACH DELETE x, m "
-                    "RETURN count(m) AS pruned",
-                    app=app_name,
-                    present=present,
-                )
+                res = s.run(PRUNE_VANISHED_MODULES, app=app_prefix, present=present)
                 pruned = res.single()
                 pruned_count = pruned["pruned"] if pruned else 0
                 logger.info(f"neo4j(bolt): pruned {pruned_count} vanished module(s)")
@@ -263,12 +289,19 @@ def _upsert_edges(session, neo4j, edges: List[EdgeRow]) -> None:
 # ----------------------------------------------------------------------------------------------
 
 
-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 _module_row(nodes: List[NodeRow]) -> Optional[NodeRow]:
+    return next((n for n in nodes if n.labels[0] == "PyModule"), None)
+
+
+def _module_id_of(nodes: List[NodeRow]) -> Optional[str]:
+    row = _module_row(nodes)
+    return row.value if row is not None else None
+
+
+def _hash_of(nodes: List[NodeRow]) -> Optional[str]:
+    row = _module_row(nodes)
+    h = row.props.get("content_hash") if row is not None else None
+    return h if isinstance(h, str) else None
 
 
 def _to_params(props, neo4j) -> dict:

codeanalyzer/neo4j/cypher.py

@@ -28,14 +28,17 @@ from __future__ import annotations
 from typing import Dict, List
 
 from codeanalyzer.neo4j.rows import (
+    CAN_NODE,
     EdgeRow,
     GraphRows,
     NodeRow,
+    application_prefix,
     chunk,
     cypher_map,
     cypher_value,
 )
 from codeanalyzer.neo4j.schema import CONSTRAINTS, INDEXES
+from codeanalyzer.schema.ids import application_id
 
 BATCH = 500
 
@@ -66,13 +69,24 @@ def render_cypher(rows: GraphRows, app_name: str) -> str:
 
 
 def _wipe(app_name: str) -> str:
-    name = cypher_value(app_name)
+    """The application root by equality plus everything under ``can://<app>/`` (#173).
+    Scoped by id prefix, so it is one application by construction — a second python
+    app sharing a module path, and a sibling analyzer's :Py* graph, are outside it.
+    :Package nodes (``pkg:`` purls) stay outside too.
+
+    Two things moved with the app-outermost grammar. The root is matched by its
+    ``can://<app>`` id rather than by the free-text ``--app-name``, so two apps
+    sharing a name no longer wipe each other's root; and the app's :Artifact /
+    :ConfigKey nodes are now *inside* the prefix, so the snapshot rebuilds them
+    instead of leaving them to accumulate. That is deliberate, and it is the one
+    behavioural widening here: a cross-language edge into a shared :Artifact is
+    dropped by a python snapshot and restored on that analyzer's next push."""
+    prefix = cypher_value(application_prefix(app_name))
+    app_id = cypher_value(application_id(app_name))
     return "\n".join(
         [
-            f"MATCH (a:PyApplication {{name: {name}}})",
-            "OPTIONAL MATCH (a)-[:PY_HAS_MODULE]->(m:PyModule)",
-            "OPTIONAL MATCH (m)-[:PY_DECLARES|PY_HAS_METHOD|PY_HAS_ATTRIBUTE|PY_DECLARES_VAR|PY_HAS_CALLSITE*1..]->(x)",
-            "DETACH DELETE x, m, a;",
+            f"MATCH (x:{CAN_NODE}) WHERE x.id = {app_id} OR x.id STARTS WITH {prefix}",
+            "CALL { WITH x DETACH DELETE x } IN TRANSACTIONS OF 1000 ROWS;",
         ]
     )