mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-03 00:52:32 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
108 lines
3.7 KiB
Python
108 lines
3.7 KiB
Python
"""Fixtures for insightsql-no-string-table-chain rule.
|
|
|
|
Lines marked with the must-find annotation are expected to match the rule.
|
|
Lines marked as ok must not match. Run semgrep --test .semgrep/ locally.
|
|
"""
|
|
|
|
from insights.insightsql import ast
|
|
from insights.insightsql.context import InsightsQLContext
|
|
from insights.insightsql.database.schema.events import EVENTS_TABLE_TYPES, EventsTable
|
|
from insights.insightsql.database.schema.persons import PersonsTable
|
|
|
|
|
|
# ============================================================================
|
|
# SHOULD FIND — production code comparing AST chains to table-name strings
|
|
# ============================================================================
|
|
|
|
|
|
def bad_events_check(node: ast.JoinExpr) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
if isinstance(node.table, ast.Field) and node.table.chain == ["events"]:
|
|
return True
|
|
return False
|
|
|
|
|
|
def bad_persons_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["persons"]
|
|
|
|
|
|
def bad_sessions_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["sessions"]
|
|
|
|
|
|
def bad_groups_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["groups"]
|
|
|
|
|
|
def bad_logs_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["logs"]
|
|
|
|
|
|
def bad_qualified_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["insights", "events"]
|
|
|
|
|
|
def bad_ai_events_check(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return field.chain == ["insights", "ai_events"]
|
|
|
|
|
|
def bad_reversed_operand(field: ast.Field) -> bool:
|
|
# ruleid: insightsql-no-string-table-chain
|
|
return ["events"] == field.chain
|
|
|
|
|
|
# ============================================================================
|
|
# SHOULD NOT FIND — correct patterns and unrelated chain comparisons
|
|
# ============================================================================
|
|
|
|
|
|
def good_isinstance_check(context: InsightsQLContext, field: ast.Field) -> bool:
|
|
# ok: insightsql-no-string-table-chain
|
|
if context.database is None:
|
|
return False
|
|
resolved = context.database.get_table([str(c) for c in field.chain])
|
|
return isinstance(resolved, EventsTable)
|
|
|
|
|
|
def good_events_family_check(context: InsightsQLContext, field: ast.Field) -> bool:
|
|
# ok: insightsql-no-string-table-chain
|
|
if context.database is None:
|
|
return False
|
|
resolved = context.database.get_table([str(c) for c in field.chain])
|
|
return isinstance(resolved, EVENTS_TABLE_TYPES)
|
|
|
|
|
|
def good_persons_isinstance(context: InsightsQLContext, field: ast.Field) -> bool:
|
|
# ok: insightsql-no-string-table-chain
|
|
resolved = context.database.get_table([str(c) for c in field.chain]) if context.database else None
|
|
return isinstance(resolved, PersonsTable)
|
|
|
|
|
|
def good_column_name_check(field: ast.Field) -> bool:
|
|
# Comparing a field chain to a COLUMN name (not a table name) is fine — these are
|
|
# property lookups, not table-identity checks.
|
|
# ok: insightsql-no-string-table-chain
|
|
if field.chain == ["timestamp"]:
|
|
return True
|
|
# ok: insightsql-no-string-table-chain
|
|
if field.chain == ["event"]:
|
|
return True
|
|
# ok: insightsql-no-string-table-chain
|
|
if field.chain == ["person_id"]:
|
|
return True
|
|
# ok: insightsql-no-string-table-chain
|
|
if field.chain == ["properties"]:
|
|
return True
|
|
return False
|
|
|
|
|
|
def good_multi_segment_property(field: ast.Field) -> bool:
|
|
# ok: insightsql-no-string-table-chain
|
|
return field.chain == ["events", "person_id"]
|