1
0
Fork 0
Code Issues Pull requests Projects Releases 2 Packages Wiki Activity Actions Pages
DocForge2/src/docforge/graph_projection.py

497 lines
16 KiB
Python

"""Pure, bounded portable-graph planning over one immutable graph generation."""
from __future__ import annotations
import re
from dataclasses import dataclass
from typing import Literal, cast
from .errors import DocForgeError
from .models import Edge, Node, ProjectSnapshot
from .project import project_root_fingerprint
from .projection_contract import GraphViewPlanV1
GraphViewMode = Literal["nodes", "flow", "web", "logic"]
MAX_GRAPH_VIEW_DEPTH = 32
MAX_GRAPH_VIEW_NODES = 1_000
MAX_GRAPH_VIEW_EDGES = 4_000
MAX_GRAPH_VIEW_WORK = 1_000_000
MAX_GRAPH_VIEW_FILTERS = 64
MAX_GRAPH_VIEW_STRING_CHARS = 1_024
MAX_GRAPH_VIEW_QUERY_CHARS = 10_000
_QUERY_TOKEN = re.compile(r"\w+", re.UNICODE)
_DETAIL_FIELDS = (
"node_id",
"title",
"family",
"authority",
"status",
"tags",
"summary",
"content_hash",
)
@dataclass(frozen=True)
class GraphViewRequestV1:
"""One closed, inert graph selection request."""
view_id: str
title: str
root_node_id: str | None = None
query: str | None = None
initial_mode: GraphViewMode = "nodes"
depth: int = 1
max_nodes: int = 100
max_edges: int = 400
max_work: int = 100_000
families: tuple[str, ...] = ()
relations: tuple[str, ...] = ()
authorities: tuple[str, ...] = ()
statuses: tuple[str, ...] = ()
tags: tuple[str, ...] = ()
include_logic: bool = False
@dataclass(frozen=True)
class _ValidatedRequest:
view_id: str
title: str
root_node_id: str | None
query: str | None
initial_mode: GraphViewMode
depth: int
max_nodes: int
max_edges: int
max_work: int
families: tuple[str, ...]
relations: tuple[str, ...]
authorities: tuple[str, ...]
statuses: tuple[str, ...]
tags: tuple[str, ...]
include_logic: bool
def _invalid(message: str, **details: object) -> DocForgeError:
return DocForgeError("invalid_graph_view_request", message, **details)
def _string(value: object, *, field: str, maximum: int = MAX_GRAPH_VIEW_STRING_CHARS) -> str:
if not isinstance(value, str) or not value.strip() or len(value) > maximum or "\0" in value:
raise _invalid("Graph view request string is invalid", field=field)
return value.strip()
def _filter_values(values: object, *, field: str) -> tuple[str, ...]:
if not isinstance(values, tuple):
raise _invalid("Graph view filter is invalid", field=field)
tuple_values = cast(tuple[object, ...], values)
if not all(isinstance(value, str) for value in tuple_values):
raise _invalid("Graph view filter is invalid", field=field)
if len(tuple_values) > MAX_GRAPH_VIEW_FILTERS:
raise _invalid("Graph view filter is invalid", field=field)
normalized = tuple(_string(value, field=field) for value in cast(tuple[str, ...], tuple_values))
if len(normalized) != len(set(normalized)):
raise _invalid("Graph view filter contains duplicates", field=field)
return tuple(sorted(normalized))
def _validated_request(request: GraphViewRequestV1) -> _ValidatedRequest:
view_id = _string(request.view_id, field="view_id")
title = _string(request.title, field="title")
if (request.root_node_id is None) == (request.query is None):
raise _invalid("Choose exactly one exact root or lexical query")
root_node_id = (
None
if request.root_node_id is None
else _string(request.root_node_id, field="root_node_id")
)
query = (
None
if request.query is None
else _string(
request.query,
field="query",
maximum=MAX_GRAPH_VIEW_QUERY_CHARS,
)
)
if request.initial_mode not in {"nodes", "flow", "web", "logic"}:
raise _invalid("Graph view initial mode is unsupported")
if type(request.depth) is not int or not 1 <= request.depth <= MAX_GRAPH_VIEW_DEPTH:
raise _invalid(
"Graph view depth is outside the fixed boundary",
maximum=MAX_GRAPH_VIEW_DEPTH,
)
for field, value, minimum, maximum in (
("max_nodes", request.max_nodes, 1, MAX_GRAPH_VIEW_NODES),
("max_edges", request.max_edges, 0, MAX_GRAPH_VIEW_EDGES),
("max_work", request.max_work, 1, MAX_GRAPH_VIEW_WORK),
):
if type(value) is not int or not minimum <= value <= maximum:
raise _invalid(
"Graph view bound is outside the fixed boundary",
field=field,
minimum=minimum,
maximum=maximum,
)
if type(request.include_logic) is not bool:
raise _invalid("Graph view Logic selection must be Boolean")
return _ValidatedRequest(
view_id=view_id,
title=title,
root_node_id=root_node_id,
query=query,
initial_mode=request.initial_mode,
depth=request.depth,
max_nodes=request.max_nodes,
max_edges=request.max_edges,
max_work=request.max_work,
families=_filter_values(request.families, field="families"),
relations=_filter_values(request.relations, field="relations"),
authorities=_filter_values(request.authorities, field="authorities"),
statuses=_filter_values(request.statuses, field="statuses"),
tags=_filter_values(request.tags, field="tags"),
include_logic=request.include_logic,
)
def _validated_graph(
snapshot: ProjectSnapshot,
) -> tuple[tuple[Node, ...], tuple[Edge, ...], dict[str, Node]]:
nodes = tuple(sorted(snapshot.nodes, key=lambda node: node.node_id))
node_by_id = {node.node_id: node for node in nodes}
if len(node_by_id) != len(nodes):
raise DocForgeError(
"invalid_projection",
"Graph view snapshot contains duplicate node identities",
)
edges = tuple(
sorted(
snapshot.edges,
key=lambda edge: (edge.source_id, edge.relation, edge.target_id),
)
)
edge_keys = {(edge.source_id, edge.relation, edge.target_id) for edge in edges}
if len(edge_keys) != len(edges) or any(
edge.source_id not in node_by_id or edge.target_id not in node_by_id for edge in edges
):
raise DocForgeError(
"invalid_projection",
"Graph view snapshot contains invalid relationships",
)
return nodes, edges, node_by_id
def _eligible(node: Node, request: _ValidatedRequest) -> bool:
return (
(not request.families or node.family in request.families)
and (not request.authorities or node.authority in request.authorities)
and (not request.statuses or node.status in request.statuses)
and (not request.tags or set(request.tags).issubset(node.tags))
)
def _relation_allowed(edge: Edge, request: _ValidatedRequest) -> bool:
return not request.relations or edge.relation in request.relations
def _lexical_text(node: Node) -> str:
return " ".join(
(
node.node_id,
node.title,
node.summary,
node.family,
node.authority,
node.status,
*node.tags,
)
).casefold()
def _lexical_nodes(
nodes: tuple[Node, ...],
request: _ValidatedRequest,
omissions: list[dict[str, object]],
) -> tuple[set[str], int, bool]:
query = request.query
maximum_nodes = request.max_nodes
maximum_work = request.max_work
assert query is not None
terms = tuple(dict.fromkeys(_QUERY_TOKEN.findall(query.casefold())))
if not terms:
raise _invalid("Lexical graph scope contains no searchable text")
selected: set[str] = set()
work = 0
work_limited = False
for node in nodes:
if work >= maximum_work:
work_limited = True
break
work += 1
if not _eligible(node, request) or not all(term in _lexical_text(node) for term in terms):
continue
if len(selected) >= maximum_nodes:
omissions.append(
{
"code": "node_result_limit",
"subject": "nodes",
"limit": maximum_nodes,
"minimum_omitted": 1,
}
)
break
selected.add(node.node_id)
return selected, work, work_limited
def _root_nodes(
edges: tuple[Edge, ...],
node_by_id: dict[str, Node],
request: _ValidatedRequest,
omissions: list[dict[str, object]],
) -> tuple[set[str], int, bool]:
root_node_id = request.root_node_id
maximum_nodes = request.max_nodes
maximum_work = request.max_work
depth = request.depth
assert root_node_id is not None
root = node_by_id.get(root_node_id)
if root is None:
raise DocForgeError(
"missing_node",
"No node has the requested stable ID",
node_id=root_node_id,
)
if not _eligible(root, request):
raise _invalid("Exact graph root is excluded by the closed node filters")
selected = {root_node_id}
frontier = {root_node_id}
work = 0
work_limited = False
node_limited = False
for _ in range(depth):
if not frontier:
break
next_frontier: set[str] = set()
for edge in edges:
if work >= maximum_work:
work_limited = True
break
work += 1
if not _relation_allowed(edge, request):
continue
candidate: str | None = None
if edge.source_id in frontier:
candidate = edge.target_id
elif edge.target_id in frontier:
candidate = edge.source_id
if candidate is None or candidate in selected:
continue
node = node_by_id[candidate]
if not _eligible(node, request):
continue
if len(selected) >= maximum_nodes:
node_limited = True
continue
selected.add(candidate)
next_frontier.add(candidate)
if work_limited:
break
frontier = next_frontier
if node_limited:
omissions.append(
{
"code": "node_result_limit",
"subject": "nodes",
"limit": maximum_nodes,
"minimum_omitted": 1,
}
)
return selected, work, work_limited
def _selected_edges(
edges: tuple[Edge, ...],
selected_ids: set[str],
request: _ValidatedRequest,
*,
initial_work: int,
omissions: list[dict[str, object]],
) -> tuple[list[Edge], int, bool]:
maximum_edges = request.max_edges
maximum_work = request.max_work
selected: list[Edge] = []
work = initial_work
work_limited = False
edge_limited = False
for edge in edges:
if work >= maximum_work:
work_limited = True
break
work += 1
if (
edge.source_id not in selected_ids
or edge.target_id not in selected_ids
or not _relation_allowed(edge, request)
):
continue
if len(selected) >= maximum_edges:
edge_limited = True
break
selected.append(edge)
if edge_limited:
omissions.append(
{
"code": "edge_result_limit",
"subject": "edges",
"limit": maximum_edges,
"minimum_omitted": 1,
}
)
return selected, work, work_limited
def _node_payload(node: Node) -> dict[str, object]:
return {
"node_id": node.node_id,
"title": node.title,
"family": node.family,
"authority": node.authority,
"status": node.status,
"tags": sorted(node.tags),
"summary": node.summary,
"content_hash": node.content_hash,
}
def _edge_payload(edge: Edge) -> dict[str, str]:
return {
"source_id": edge.source_id,
"relation": edge.relation,
"target_id": edge.target_id,
}
def build_graph_view_plan(
snapshot: ProjectSnapshot,
request: GraphViewRequestV1,
allow_logic: bool,
) -> GraphViewPlanV1:
"""Build one deterministic, path-free graph plan without rendering or storage access."""
if type(allow_logic) is not bool:
raise _invalid("Graph view Logic policy must be Boolean")
normalized = _validated_request(request)
nodes, edges, node_by_id = _validated_graph(snapshot)
omissions: list[dict[str, object]] = []
if normalized.root_node_id is not None:
selected_ids, work, work_limited = _root_nodes(
edges,
node_by_id,
normalized,
omissions,
)
scope: dict[str, object] = {
"kind": "exact_root",
"root_node_id": normalized.root_node_id,
"depth": normalized.depth,
}
else:
selected_ids, work, work_limited = _lexical_nodes(
nodes,
normalized,
omissions,
)
scope = {
"kind": "lexical",
"query": normalized.query,
}
selected_edges, work, edge_work_limited = _selected_edges(
edges,
selected_ids,
normalized,
initial_work=work,
omissions=omissions,
)
work_limited = work_limited or edge_work_limited
if work_limited:
omissions.append(
{
"code": "work_limit",
"subject": "selection",
"limit": normalized.max_work,
"examined": work,
"minimum_omitted": 1,
}
)
logic_requested = normalized.include_logic
if logic_requested and not allow_logic:
omissions.append(
{
"code": "logic_forbidden",
"subject": "logic",
"minimum_omitted": 1,
}
)
omissions.sort(key=lambda item: (str(item["code"]), str(item["subject"])))
selected_nodes = [node_by_id[node_id] for node_id in sorted(selected_ids)]
filters: dict[str, list[str]] = {
"families": list(normalized.families),
"relations": list(normalized.relations),
"authorities": list(normalized.authorities),
"statuses": list(normalized.statuses),
"tags": list(normalized.tags),
}
return GraphViewPlanV1.create(
{
"project": {
"project_id": snapshot.descriptor.project_id,
"project_root_fingerprint": project_root_fingerprint(snapshot.descriptor.root),
"adapter": snapshot.descriptor.adapter,
"revision": snapshot.revision,
"source_hash": snapshot.source_hash,
},
"view": {
"view_id": normalized.view_id,
"title": normalized.title,
"initial_mode": normalized.initial_mode,
"scope": scope,
"filters": filters,
"detail_fields": list(_DETAIL_FIELDS),
},
"bounds": {
"depth": normalized.depth,
"max_nodes": normalized.max_nodes,
"max_edges": normalized.max_edges,
"max_work": normalized.max_work,
},
"policy": {
"visibility": "selected_graph_only",
"source_paths": "excluded",
"source_bodies": "excluded",
"database_queries": "forbidden",
"executable_content": "forbidden",
"logic": "allowed" if allow_logic else "forbidden",
"logic_requested": logic_requested,
},
"graph": {
"root_node_id": normalized.root_node_id,
"nodes": [_node_payload(node) for node in selected_nodes],
"edges": [_edge_payload(edge) for edge in selected_edges],
"logic_projections": [],
},
"omissions": omissions,
"diagnostics": {
"selection": scope["kind"],
"returned_nodes": len(selected_nodes),
"returned_edges": len(selected_edges),
"examined_work_units": work,
"truncated": bool(omissions),
"ordering": "node_id;source_id,relation,target_id",
},
}
)