19 Commits
Author SHA1 Message Date
zemion 2c2b11f860 feat(connectors): add managed file and PostgreSQL origins
Module Package Release / publish-packages (push) Successful in 12s
2026-08-21 19:29:58 +02:00
zemion e6ab8291ec feat(connectors): govern RSS and Atom publication
Module Package Release / publish-packages (push) Successful in 11s
2026-08-21 17:36:19 +02:00
zemion de8e74b866 feat(connectors): add governed DSAR coverage 2026-08-21 13:05:54 +02:00
zemion 0f61fe4607 feat: govern connector configurations and simulations 2026-08-20 12:58:53 +02:00
zemion 3964a2e4e7 Release v0.1.18
Module Package Release / publish-packages (push) Successful in 11s
2026-08-05 21:07:44 +02:00
zemion b88f1b2c2d Release v0.1.17
Module Package Release / publish-packages (push) Successful in 10s
2026-08-05 20:33:58 +02:00
zemion 32cac8835b Release v0.1.16
Module Package Release / publish-packages (push) Successful in 11s
2026-08-05 19:52:00 +02:00
zemion c69d68f1da Release v0.1.15
Module Package Release / publish-packages (push) Successful in 11s
2026-08-04 15:10:18 +02:00
zemion 1caae6e49e Make package publication retries hash-safe 2026-08-04 14:32:19 +02:00
zemion 84c9bb7711 Harden module package publication 2026-08-04 14:02:39 +02:00
zemion 20146ef8fe Bound connector source previews 2026-08-04 12:05:27 +02:00
zemion c33380b957 Add protected package release workflow 2026-08-04 04:14:03 +02:00
zemion dfa717b9ba Fence governed connector acquisitions 2026-08-03 05:43:54 +02:00
zemion 26f8898d11 Announce shared connector runtime contract 2026-08-02 14:54:56 +02:00
zemion 7be93785a2 feat: declare governed external provider state 2026-08-01 17:48:25 +02:00
zemion 52fe33568c Add governed RSS and Atom connectors 2026-07-31 22:48:07 +02:00
zemion c5a43b3dae feat: acquire immutable sanctions snapshots 2026-07-29 18:46:53 +02:00
zemion 27302f0c39 feat: expose connector datasource origins 2026-07-28 12:43:26 +02:00
zemion ba5ccea5b0 Implement governed tabular source snapshots 2026-07-28 11:13:22 +02:00
49 changed files with 13024 additions and 9 deletions
+270
View File
@@ -0,0 +1,270 @@
name: Module Package Release
on:
push:
tags:
- "v*"
workflow_dispatch:
inputs:
release_tag:
description: Existing protected version tag to publish
required: true
type: string
jobs:
publish-packages:
runs-on: ubuntu-latest
env:
GITEA_REPOSITORY: ${{ gitea.repository }}
steps:
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
with:
fetch-depth: 0
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065
with:
python-version: "3.12"
- uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020
with:
node-version: "22"
- name: Select and validate protected release tag
shell: bash
env:
REQUESTED_TAG: ${{ inputs.release_tag }}
TRIGGER_TAG: ${{ gitea.ref_name }}
run: |
set -euo pipefail
tag="${REQUESTED_TAG:-$TRIGGER_TAG}"
case "$tag" in
v[0-9]*.[0-9]*.[0-9]*) ;;
*) echo "Release tag must start with a SemVer-shaped vX.Y.Z value" >&2; exit 1 ;;
esac
git fetch --force origin "refs/tags/$tag:refs/tags/$tag" refs/heads/main:refs/remotes/origin/main
tag_commit="$(git rev-list -n 1 "$tag")"
git merge-base --is-ancestor "$tag_commit" refs/remotes/origin/main || {
echo "Release tag is not contained in main" >&2
exit 1
}
git checkout --detach "$tag"
printf 'RELEASE_TAG=%s\n' "$tag" >> "$GITEA_ENV"
printf 'SOURCE_DATE_EPOCH=%s\n' "$(git show -s --format=%ct HEAD)" >> "$GITEA_ENV"
- name: Validate package versions
run: |
python - <<'PY'
import json
from pathlib import Path
import os
import re
import tomllib
tag = os.environ["RELEASE_TAG"]
expected = tag.removeprefix("v")
project = tomllib.loads(Path("pyproject.toml").read_text(encoding="utf-8"))["project"]
if project.get("version") != expected:
raise SystemExit(f"pyproject version {project.get('version')!r} does not match {tag}")
if re.fullmatch(r"govoplan-[a-z0-9-]+", str(project.get("name", ""))) is None:
raise SystemExit("Python distribution name must use the govoplan-* namespace")
webui = Path("webui/package.json")
if webui.is_file():
package = json.loads(webui.read_text(encoding="utf-8"))
if package.get("version") != expected:
raise SystemExit(f"WebUI version {package.get('version')!r} does not match {tag}")
if re.fullmatch(r"@govoplan/[a-z0-9-]+-webui", str(package.get("name", ""))) is None:
raise SystemExit("WebUI package name must use the @govoplan/*-webui namespace")
release = Path("webui/package.release.json")
if release.is_file():
release_package = json.loads(release.read_text(encoding="utf-8"))
if (
release_package.get("name") != package.get("name")
or release_package.get("version") != expected
):
raise SystemExit("WebUI release package identity does not match package.json and the release tag")
PY
- name: Build immutable package artifacts
shell: bash
run: |
set -euo pipefail
python -m pip install --disable-pip-version-check build==1.5.0 twine==7.0.0
rm -rf dist .package-webui
python -m build --wheel --outdir dist
python -m twine check dist/*.whl
if [[ -f webui/package.json ]]; then
mkdir .package-webui
cp -a webui/. .package-webui/
rm -rf .package-webui/node_modules .package-webui/dist
if [[ -f .package-webui/package.release.json ]]; then
cp .package-webui/package.release.json .package-webui/package.json
fi
node <<'NODE'
const fs = require("node:fs");
const path = ".package-webui/package.json";
const packageJson = JSON.parse(fs.readFileSync(path, "utf8"));
const groups = ["dependencies", "optionalDependencies", "peerDependencies"];
for (const group of groups) {
for (const [name, specifier] of Object.entries(packageJson[group] || {})) {
if (!name.startsWith("@govoplan/")) continue;
if (typeof specifier !== "string") {
throw new Error(`${group}.${name} must use a string version`);
}
const packageSlug = name.slice("@govoplan/".length);
if (!packageSlug.endsWith("-webui")) {
throw new Error(`${group}.${name} is outside the WebUI package namespace`);
}
const repository = `govoplan-${packageSlug.slice(0, -"-webui".length)}`;
const escapedRepository = repository.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
const gitTag = specifier.match(
new RegExp(
`^git\\+(?:ssh://git@|https://)git\\.add-ideas\\.de/(?:GovOPlaN|add-ideas)/${escapedRepository}\\.git#v([0-9]+\\.[0-9]+\\.[0-9]+)$`,
),
);
if (gitTag) {
packageJson[group][name] = gitTag[1];
continue;
}
if (specifier.startsWith("file:") || specifier.startsWith("git+")) {
throw new Error(
`${group}.${name} must resolve to an exact registry version for publication`,
);
}
}
}
delete packageJson.private;
fs.writeFileSync(path, `${JSON.stringify(packageJson, null, 2)}\n`);
NODE
npm pkg delete private --prefix .package-webui
(cd .package-webui && npm pack --ignore-scripts --pack-destination ../dist)
fi
python - <<'PY'
import hashlib
import json
from pathlib import Path
import os
import subprocess
artifacts = []
for path in sorted(Path("dist").iterdir()):
if path.suffix not in {".whl", ".tgz"}:
continue
digest = hashlib.sha256(path.read_bytes()).hexdigest()
artifacts.append({"filename": path.name, "sha256": digest, "size": path.stat().st_size})
payload = {
"schema_version": "1",
"repository": os.environ["GITEA_REPOSITORY"],
"tag": os.environ["RELEASE_TAG"],
"commit": subprocess.check_output(["git", "rev-parse", "HEAD"], text=True).strip(),
"artifacts": artifacts,
}
Path("dist/package-artifacts.json").write_text(
json.dumps(payload, indent=2, sort_keys=True) + "\n",
encoding="utf-8",
)
PY
- name: Retain package hash evidence
uses: actions/upload-artifact@a8a3f3ad30e3422c9c7b888a15615d19a852ae32
with:
name: module-packages-${{ gitea.ref_name }}
path: dist/package-artifacts.json
- name: Check immutable registry state
shell: bash
env:
PACKAGE_TOKEN: ${{ secrets.GOVOPLAN_PACKAGE_TOKEN }}
run: |
set -euo pipefail
test -n "$PACKAGE_TOKEN"
python - <<'PY'
import hashlib
import json
import os
from pathlib import Path
import tomllib
from urllib.error import HTTPError
from urllib.parse import quote
from urllib.request import Request, urlopen
api_root = "https://git.add-ideas.de/api/v1/packages/GovOPlaN"
token = os.environ["PACKAGE_TOKEN"]
def should_publish(kind, name, version, path):
package_url = "/".join(
(api_root, kind, quote(name, safe=""), quote(version, safe=""), "files")
)
request = Request(
package_url,
headers={"Accept": "application/json", "Authorization": f"token {token}"},
)
try:
with urlopen(request, timeout=30) as response:
files = json.load(response)
except HTTPError as exc:
if exc.code == 404:
print(f"{kind} package {name}=={version} is not published yet")
return True
raise
if not isinstance(files, list) or len(files) != 1:
raise SystemExit(
f"immutable {kind} package {name}=={version} has an unexpected file set"
)
expected_sha256 = hashlib.sha256(path.read_bytes()).hexdigest()
if files[0].get("sha256") != expected_sha256:
raise SystemExit(
f"immutable {kind} package {name}=={version} already exists with a different SHA-256"
)
print(f"verified existing {kind} package {name}=={version} ({expected_sha256})")
return False
project = tomllib.loads(Path("pyproject.toml").read_text(encoding="utf-8"))["project"]
wheels = tuple(Path("dist").glob("*.whl"))
if len(wheels) != 1:
raise SystemExit("release build must contain exactly one wheel")
publish_pypi = should_publish(
"pypi", str(project["name"]), str(project["version"]), wheels[0]
)
tarballs = tuple(Path("dist").glob("*.tgz"))
if len(tarballs) > 1:
raise SystemExit("release build must contain at most one npm package")
publish_npm = False
if tarballs:
webui = json.loads(
Path(".package-webui/package.json").read_text(encoding="utf-8")
)
publish_npm = should_publish(
"npm", str(webui["name"]), str(webui["version"]), tarballs[0]
)
with Path(os.environ["GITEA_ENV"]).open("a", encoding="utf-8") as env_file:
env_file.write(f"PUBLISH_PYPI={int(publish_pypi)}\n")
env_file.write(f"PUBLISH_NPM={int(publish_npm)}\n")
PY
- name: Publish wheel and WebUI package
shell: bash
env:
PACKAGE_USERNAME: ${{ secrets.GOVOPLAN_PACKAGE_USERNAME }}
PACKAGE_TOKEN: ${{ secrets.GOVOPLAN_PACKAGE_TOKEN }}
run: |
set -euo pipefail
test -n "$PACKAGE_USERNAME"
test -n "$PACKAGE_TOKEN"
if [[ "$PUBLISH_PYPI" == 1 ]]; then
TWINE_USERNAME="$PACKAGE_USERNAME" TWINE_PASSWORD="$PACKAGE_TOKEN" \
python -m twine upload --non-interactive \
--repository-url https://git.add-ideas.de/api/packages/GovOPlaN/pypi \
dist/*.whl
else
echo "Exact wheel is already present; skipping immutable retry."
fi
shopt -s nullglob
webui_packages=(dist/*.tgz)
if (( ${#webui_packages[@]} )) && [[ "$PUBLISH_NPM" == 1 ]]; then
npmrc="$(mktemp)"
trap 'rm -f "$npmrc"' EXIT
chmod 600 "$npmrc"
printf '%s\n' \
'@govoplan:registry=https://git.add-ideas.de/api/packages/GovOPlaN/npm/' \
"//git.add-ideas.de/api/packages/GovOPlaN/npm/:_authToken=$PACKAGE_TOKEN" \
> "$npmrc"
NPM_CONFIG_USERCONFIG="$npmrc" npm publish "./${webui_packages[0]}" \
--ignore-scripts --access public \
--registry https://git.add-ideas.de/api/packages/GovOPlaN/npm/
elif (( ${#webui_packages[@]} )); then
echo "Exact WebUI package is already present; skipping immutable retry."
fi
+16
View File
@@ -0,0 +1,16 @@
# GovOPlaN Connectors Codex Guide
## Scope
This repository owns reusable external connection profiles, protocol adapters, governed snapshots, and connector capability contracts.
## Documentation Contract
- Treat documentation as part of every behavior change. Update this module's manifest-driven `DocumentationTopic` contributions for affected user and administrator behavior.
- Keep feature content here; `govoplan-docs` projects it without importing Connectors internals.
- Maintain a static user/admin baseline and run `/mnt/DATA/git/govoplan/tools/checks/check-manifest-shapes.py` after behavior or manifest changes.
## Boundaries
- Domain modules own business semantics; connectors own transport, credentials, synchronization, and diagnostics.
- Keep optional adapters behind capabilities and enforce egress and peer-validation policy.
+78 -2
View File
@@ -4,14 +4,89 @@
**Repository type:** connector (connector-hub). **Repository type:** connector (connector-hub).
<!-- govoplan-repository-type:end --> <!-- govoplan-repository-type:end -->
`govoplan-connectors` will own integration catalogues and generic external `govoplan-connectors` owns integration catalogues and generic external system
system connection patterns for GovOPlaN. connection patterns for GovOPlaN.
The module should make external systems discoverable, testable, and usable The module should make external systems discoverable, testable, and usable
without taking ownership of their business semantics. Domain-specific modules without taking ownership of their business semantics. Domain-specific modules
remain responsible for case, file, workflow, payment, mail, identity, document, remain responsible for case, file, workflow, payment, mail, identity, document,
or reporting behavior. or reporting behavior.
## Executable First Slice
The executable connector capability provides tenant-isolated tabular origins.
Operators can import bounded JSON or CSV snapshots, bind an exact managed Files
CSV/XLSX version, or discover a table through an active governed PostgreSQL
configuration. Every origin exposes a reviewed schema, opaque reference, and
content/discovery fingerprint through `connectors.datasource_origins@0.1.0`.
Preview reads enforce provider ceilings for rows, serialized bytes, and elapsed
time and report the effective limits and any truncation as structured
diagnostics.
Connectors owns acquisition, connection profiles, credentials, discovery, and
provider health. `govoplan-datasources` registers an origin as a governed live
or cached datasource and owns staging, materializations, frozen states, and
consumer access. Dataflow consumes that Datasources contract and never imports
connector implementations or stores connector credentials.
Each origin declares whether it is live, cached, file-backed, or static, its
structured health state, and which projection, filter, aggregation, sorting,
and pagination operations it can push down. The snapshot, managed-file, and
PostgreSQL providers currently support projection and pagination only;
consumers must keep other operations in Dataflow rather than assuming
transport-side execution.
Managed-file sources are authorized and opened through
`files.tabular_content@1.0.0`; Files remains authoritative for ownership,
shares, download permission, exact versions, integrity, quarantine, encryption,
retention, and legal holds. CSV must be UTF-8. XLSX input is protected by
compressed-entry, expanded-byte, compression-ratio, row, and column limits.
A newer current version is reported but never silently replaces the pinned
version.
The PostgreSQL adapter accepts only an active governed connector configuration
whose secret-free endpoint uses the PostgreSQL driver. Authentication is
resolved from a tenant/scope/module/server-restricted Core credential envelope.
The adapter reflects a simple schema/table identifier, uses read-only
transactions and a statement timeout, and blocks configuration, credential, or
schema drift until an operator refreshes and reviews the source. Secrets are
never copied into source metadata or diagnostics. Other database, REST/HTTP,
directory, and warehouse providers can implement the same origin contract
without changing Datasources or Dataflow.
Governed sanctions and feed snapshot acquisitions use Core recovery operations.
The source revision/cursor, redacted dry-run decision, canonical request digest,
and distributed lease are durable before network I/O. Immutable snapshot rows
and the terminal recovery checkpoint commit atomically, and an
`Idempotency-Key` replays the committed result without contacting the provider.
Current acquisition transports are read-only. The exported external-mutation
recovery contract requires stable idempotency, provider verification, and
operator reconciliation, but no connector currently claims a production write
or delete path.
RSS and Atom emission is a bounded renderer, not an authority shortcut. Every
selected entry declares whether it came from a GovOPlaN event, publication,
case, or report and carries an opaque owning-module reference and optional
revision. Public-feed permission can render only public entries. Tenant and
private audiences require a separate restricted-feed permission, and the API
derives the allowed visibility set from that audience instead of accepting a
caller-controlled allow-list. Portal or Reporting remains responsible for any
durable public or authenticated route and must re-authorize restricted access.
The governed connector runtime adds immutable definition revisions,
revision-pinned tenant configurations, protected local overrides, explicit
package-update adoption, bounded dry-runs and simulations, redacted provenance,
idempotency, and configurable ambiguity handling through review, quarantine,
or rejection. Its administration surface is contributed to the shared system
administration workspace. Provider-specific adapters still own live writes.
Development:
```bash
/mnt/DATA/git/govoplan/.venv/bin/python -m pip install -e .
/mnt/DATA/git/govoplan/.venv/bin/python -m unittest discover -s tests
```
See: See:
- [Connector concept](docs/CONCEPT.md) - [Connector concept](docs/CONCEPT.md)
@@ -19,3 +94,4 @@ See:
- [Connector source lifecycle](docs/CONNECTOR_SOURCE_LIFECYCLE.md) - [Connector source lifecycle](docs/CONNECTOR_SOURCE_LIFECYCLE.md)
- [OpenProject connector concept](docs/OPENPROJECT_CONNECTOR.md) - [OpenProject connector concept](docs/OPENPROJECT_CONNECTOR.md)
- [OpenDesk integration map](docs/OPENDESK_INTEGRATION_MAP.md) - [OpenDesk integration map](docs/OPENDESK_INTEGRATION_MAP.md)
- [Governed connector configuration](docs/GOVERNED_CONNECTOR_CONFIGURATION.md)
+34
View File
@@ -11,6 +11,13 @@ results, credential references, and generic integration events. Protocol-heavy
or domain-heavy integrations may live in dedicated modules once their scope is or domain-heavy integrations may live in dedicated modules once their scope is
clear. clear.
Connector capability is not source ownership. Each configured binding also
declares whether GovOPlaN is authoritative, the external system is
authoritative, GovOPlaN keeps a mirror, both sides use governed synchronization,
GovOPlaN supplies only a governance overlay, or the object is link-only. The
same connector may be configured differently by tenant, service, object type,
or field group.
Detailed follow-up documents: Detailed follow-up documents:
- [Public-sector integration catalogue](PUBLIC_SECTOR_INTEGRATION_CATALOGUE.md) - [Public-sector integration catalogue](PUBLIC_SECTOR_INTEGRATION_CATALOGUE.md)
@@ -18,6 +25,20 @@ Detailed follow-up documents:
- [OpenProject connector concept](OPENPROJECT_CONNECTOR.md) - [OpenProject connector concept](OPENPROJECT_CONNECTOR.md)
- [OpenDesk integration map](OPENDESK_INTEGRATION_MAP.md) - [OpenDesk integration map](OPENDESK_INTEGRATION_MAP.md)
## Shared runtime boundary
Connector transports use the versioned Core runtime contract for bounded dry
runs and diagnostics. Connectors owns endpoint discovery, authentication
hand-off, protocol reads, retry/backoff, and source health. A consuming module
owns domain mappings and mutations: Addresses, for example, owns contact and
vCard semantics even when Connectors supplies reusable LDAP, CardDAV, Exchange,
or Google transport patterns.
Dry runs carry an immutable input hash, source revision and fingerprint,
redacted effects, diagnostics, truncation state, and an apply token. Apply must
reject a changed input or source revision. URLs and diagnostics never contain
credential material; they retain only credential-envelope references.
## Ownership ## Ownership
The module owns: The module owns:
@@ -29,9 +50,13 @@ The module owns:
- connector health status and last-test evidence - connector health status and last-test evidence
- operator-visible integration inventory - operator-visible integration inventory
- cross-module discovery of available external capabilities - cross-module discovery of available external capabilities
- supported integration maturity, source-authority modes, operation limits,
and effect/reconciliation behavior for each connector type
The module does not own: The module does not own:
- governed datasource identity, staging, materializations, frozen states, or
consumer read semantics, owned by `govoplan-datasources`
- file storage semantics, owned by files/DMS - file storage semantics, owned by files/DMS
- identity provisioning semantics, owned by IDM/access - identity provisioning semantics, owned by IDM/access
- mail/calendar semantics, owned by mail/calendar - mail/calendar semantics, owned by mail/calendar
@@ -59,6 +84,9 @@ The module should integrate through:
- module manifest metadata, route factories, permissions, and migrations - module manifest metadata, route factories, permissions, and migrations
- a connector catalogue API for listing available connector types - a connector catalogue API for listing available connector types
- a connection profile API with secret references, not plaintext secrets - a connection profile API with secret references, not plaintext secrets
- a provider declaration that composes authority mode, maturity, supported
operations, revisions/freshness, health, limits, idempotency, conflicts,
evidence, and reconciliation behavior
- capability declarations such as `connectors.catalog`, - capability declarations such as `connectors.catalog`,
`connectors.profileTester`, and `connectors.health` `connectors.profileTester`, and `connectors.health`
- events such as `connector.profile_created`, `connector.test_succeeded`, - events such as `connector.profile_created`, `connector.test_succeeded`,
@@ -69,6 +97,11 @@ Domain modules should ask whether a connector capability exists and request a
profile/test result through core-mediated capabilities. They must not import profile/test result through core-mediated capabilities. They must not import
connector implementation modules directly. connector implementation modules directly.
Data-oriented consumers use a two-layer path: Connectors publishes a
provider-specific datasource origin, then Datasources registers and governs it.
Dataflow, Workflow, Reporting, and other consumers use Datasources rather than
calling the connector origin directly.
## Reference Journeys ## Reference Journeys
### OpenProject Connector First ### OpenProject Connector First
@@ -106,6 +139,7 @@ The first implementation should provide:
- WebUI catalogue and profile pages - WebUI catalogue and profile pages
- configuration-package fragment support - configuration-package fragment support
- generic external-reference DTOs - generic external-reference DTOs
- source-authority binding and provider-operation metadata
- health summary provider - health summary provider
## Permissions ## Permissions
+92 -6
View File
@@ -14,6 +14,22 @@ predictable and avoids hidden module imports.
- `bidirectional`: GovOPlaN supports both directions with conflict detection and - `bidirectional`: GovOPlaN supports both directions with conflict detection and
reconciliation rules. reconciliation rules.
Direction describes transport. Every binding also needs a source-authority
mode:
- `native_authoritative`
- `external_authoritative`
- `external_mirror`
- `governed_sync`
- `governance_overlay`
- `linked_reference`
The authority mode and the connector's integration maturity are orthogonal. A
bidirectional connector may be configured as an external mirror, and a native
GovOPlaN object may publish to an external target without transferring
authority. The effective binding must identify its scope and provenance rather
than relying on a profile-wide `sync` boolean.
## Source Data Lifecycle ## Source Data Lifecycle
Connector profiles have operational states, while individual external records Connector profiles have operational states, while individual external records
@@ -88,12 +104,38 @@ this lifecycle when a connector publishes status.
2. Fetch only the minimal remote data required for the declared use case. 2. Fetch only the minimal remote data required for the declared use case.
3. Normalize into a connector-owned staging payload. 3. Normalize into a connector-owned staging payload.
4. Validate shape, required fields, and source trust level. 4. Validate shape, required fields, and source trust level.
5. Emit a core-mediated event such as `connector.record_discovered`. 5. Publish data-shaped inputs as versioned datasource origins.
6. Let domain modules claim or transform staged data through capabilities, not 6. Let Datasources register live/cached origins or stage immutable snapshots.
imports. 7. Let domain modules consume governed datasource references through
7. Store external references with source system, object type, object id, version capabilities, not imports.
8. Emit a core-mediated event such as `connector.record_discovered`.
9. Store external references with source system, object type, object id, version
or ETag, and last-seen timestamp. or ETag, and last-seen timestamp.
## Tabular source discovery and refresh
Immutable JSON/CSV snapshots, exact managed Files versions, and live PostgreSQL
tables share the same catalogue and bounded-preview contract. A managed-file
origin stores only the Files asset id, exact immutable version id, checksum,
parser settings, reviewed schema, and discovery fingerprint. Files re-authorizes
the current principal and verifies storage integrity and any encryption envelope
on every preview. A newer current version produces a warning; only an explicit
source refresh changes the pinned version and increments the discovery revision.
A PostgreSQL origin references an active governed connector configuration. Its
endpoint must contain no credentials. Connectors resolves the referenced Core
credential envelope for the current tenant, scope, module, and server, opens a
read-only connection, reflects a simple schema/table identifier, and records the
configuration hash/revision, credential revision, schema, and discovery
fingerprint. Configuration, credential, or schema drift blocks preview until an
explicit refresh. Missing Files capability, revoked file access, quarantine,
oversized or malformed content, inactive/stale credentials, unreachable SQL,
and timeout failures produce sanitized unavailable/validation diagnostics.
All three current providers declare projection and pagination pushdown only.
Filters, aggregations, and sorting remain in Dataflow until an adapter explicitly
declares and tests those operations.
## Publish Flow ## Publish Flow
1. Domain module requests publish through a core-mediated connector capability. 1. Domain module requests publish through a core-mediated connector capability.
@@ -101,8 +143,11 @@ this lifecycle when a connector publishes status.
shape. shape.
3. Connector sends the remote request. 3. Connector sends the remote request.
4. Connector stores the remote id, version/ETag, and response diagnostics. 4. Connector stores the remote id, version/ETag, and response diagnostics.
5. Connector emits `connector.record_published` or `connector.publish_failed`. 5. A timeout or lost acknowledgement after dispatch becomes outcome-unknown,
6. Domain module stores only the external-reference DTO and any domain result. not an ordinary failure or permission to duplicate the command.
6. Connector emits a confirmed, retryable, outcome-unknown, reconciled, or
corrected result event.
7. Domain module stores only the external-reference DTO and any domain result.
## Reconciliation ## Reconciliation
@@ -114,6 +159,45 @@ Every connector that writes to an external system needs a reconciliation story:
- retry policy for temporary failures - retry policy for temporary failures
- explicit operator action for destructive overwrite or deletion - explicit operator action for destructive overwrite or deletion
- audit trace from GovOPlaN record to external request and response summary - audit trace from GovOPlaN record to external request and response summary
- explicit requested, approved, dispatched, possibly-executed, confirmed, and
reconciled/corrected effect states
## Durable recovery operations
Connectors declares two recovery classes. A read-only acquisition into an
immutable snapshot is `atomic`: the source revision or conditional cursor,
redacted dry-run decision, canonical request digest, and distributed
tenant/provider lease are durable before the fetch. The acquired domain rows
and terminal Core recovery checkpoint commit in one PostgreSQL transaction. A
caller-supplied `Idempotency-Key` replays that committed result without a second
provider request. A failed or stale transaction has no remote mutation and may
be repeated only as a new deliberate acquisition.
An external create, update, publish, or delete is `forward_recovery`. It must
start through the connector mutation recovery contract with a stable
idempotency key, SHA-256 request digest, source revision/cursor, and dry-run
evidence. Definitive rejection is terminal. A timeout or lost acknowledgement
after dispatch is `outcome_unknown` and blocks replay until the owning connector
verifies provider state. The contract and conformance tests exist; no current
connector advertises a production external mutation, so write/delete adoption
remains explicitly planned rather than implied.
## Provider Declaration
An executable connector type should publish machine-readable metadata for:
- owned object and field groups, plus supported authority modes;
- supported discovery, link, search, read, publish, synchronize, migrate, and
replacement maturity;
- read/write/delete/preview/dry-run operations and bounded response limits;
- revision/concurrency token, freshness, health, timeout, retry, and conflict
semantics;
- idempotency and outcome-unknown handling;
- evidence, rollback/compensation, correction, and reconciliation paths;
- classification, purpose, retention, secret, degraded, and outage behavior.
This declaration composes Core contracts. It does not move protocol behavior
or domain semantics into Core or Connectors.
## Capability Boundary ## Capability Boundary
@@ -124,6 +208,7 @@ should ask core for capabilities such as:
- `connectors.profileTester` - `connectors.profileTester`
- `connectors.health` - `connectors.health`
- `connectors.externalReferences` - `connectors.externalReferences`
- `connectors.datasourceOrigins`
- `connectors.sourceConsumer` - `connectors.sourceConsumer`
- `connectors.sourcePublisher` - `connectors.sourcePublisher`
@@ -155,5 +240,6 @@ Before shipping an executable connector type:
- Add unavailable-optional-module tests for every consuming domain module. - Add unavailable-optional-module tests for every consuming domain module.
- Add profile test and health status fixtures. - Add profile test and health status fixtures.
- Add external-reference DTO tests. - Add external-reference DTO tests.
- Add source-authority and provider-declaration validation tests.
- Add lifecycle transition tests for pause, retry, retirement, and uninstall - Add lifecycle transition tests for pause, retry, retirement, and uninstall
guard behavior. guard behavior.
+39 -1
View File
@@ -25,7 +25,7 @@ logic should remain visible and reviewable.
## Runtime Expectations ## Runtime Expectations
Connectors should support: Connectors supports the generic governed-definition and simulation portion of:
- discovery where possible - discovery where possible
- typed configuration through UI-managed controls - typed configuration through UI-managed controls
@@ -39,6 +39,44 @@ Connectors should support:
Configuration packages may install connector definitions, but local overrides Configuration packages may install connector definitions, but local overrides
must be protected from accidental package updates. must be protected from accidental package updates.
## Implemented Runtime Slice
The module now persists tenant-scoped connector definitions as immutable
revisions. A governed definition explicitly validates its provider, protocol,
capabilities, input/output schemas, mapping version and rules, validation,
preview metadata, audit expectations, classification, retention, limits, and
retry policy. Definitions record whether they are locally owned or supplied by
a named package.
Configurations pin a definition revision. They store an endpoint and a secret
reference, never credentials embedded in the URL. Tenant-local override values
are merged into the pinned definition and every overridden leaf is exposed as
a protected path. Installing a later package revision only marks the
configuration as having an update available. Adoption is an explicit,
optimistically locked action that reapplies the protected overrides over the
new package revision.
The generic execution surface supports bounded dry-runs and simulations. Each
run has a caller idempotency key and retains hashes of its inputs and effective
configuration together with definition, configuration, mapping, external
revision, actor, classification, and retention provenance. Samples redact the
definition's protected fields. Ambiguous uniqueness results follow the
configuration's policy and become either:
- `manual_review` with a pending decision;
- `quarantined` until an administrator decides; or
- `rejected` without a review queue entry.
Review decisions require a reason and are audited. The generic runtime stops
at deterministic preview evidence: provider-specific adapters remain
responsible for live external writes and must satisfy the Core connector
recovery contract before claiming write maturity.
The Connector governance administration page follows the shared workspace
archetype. Reload and Save stay in the semantic action bar, dirty navigation is
guarded, package adoption is a separate action, and simulation results and
review decisions remain visibly distinct from configuration editing.
## Relationship To Datasources And Dataflow ## Relationship To Datasources And Dataflow
Recurring extraction and transformation should start as configuration across Recurring extraction and transformation should start as configuration across
+26
View File
@@ -0,0 +1,26 @@
[build-system]
requires = ["setuptools>=69", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "govoplan-connectors"
version = "0.1.20"
description = "Governed connector catalogue and tabular source capabilities for GovOPlaN."
readme = "README.md"
requires-python = ">=3.12"
license = "AGPL-3.0-or-later"
authors = [{ name = "GovOPlaN" }]
dependencies = [
"defusedxml>=0.7,<1",
"govoplan-core>=0.1.19",
"openpyxl>=3.1.5,<4",
]
[tool.setuptools.packages.find]
where = ["src"]
[tool.setuptools.package-data]
govoplan_connectors = ["py.typed"]
[project.entry-points."govoplan.modules"]
connectors = "govoplan_connectors.backend.manifest:get_manifest"
+3
View File
@@ -0,0 +1,3 @@
"""GovOPlaN Connectors module."""
__all__: list[str] = []
@@ -0,0 +1 @@
"""Connector backend package."""
@@ -0,0 +1,151 @@
from __future__ import annotations
from govoplan_core.core.datasources import (
DatasourceAccessError,
DatasourceField,
DatasourceNotFoundError,
DatasourceOrigin,
DatasourceOriginReadRequest,
DatasourceOriginReadResult,
DatasourceUnavailableError,
DatasourceValidationError,
)
from govoplan_core.core.tabular_sources import (
TabularReadRequest,
TabularSource,
TabularSourceAccessError,
TabularSourceError,
TabularSourceNotFoundError,
TabularSourceUnavailableError,
TabularSourceValidationError,
)
from govoplan_connectors.backend.tabular_sources import SqlTabularSourceProvider
class ConnectorDatasourceOriginProvider:
"""Expose connector-owned sources through the Datasources origin contract."""
def __init__(self, provider: SqlTabularSourceProvider | None = None) -> None:
self._provider = provider or SqlTabularSourceProvider()
def list_origins(
self,
session: object,
principal: object,
*,
query: str = "",
limit: int = 100,
):
try:
rows = self._provider.list_sources(
session,
principal,
query=query,
limit=limit,
)
except TabularSourceError as exc:
raise _datasource_error(exc) from exc
return tuple(_origin(source) for source in rows)
def get_origin(
self,
session: object,
principal: object,
*,
origin_ref: str,
) -> DatasourceOrigin | None:
try:
source = self._provider.get_source(
session,
principal,
source_ref=origin_ref,
)
except TabularSourceError as exc:
raise _datasource_error(exc) from exc
return _origin(source) if source is not None else None
def read_origin(
self,
session: object,
principal: object,
*,
request: DatasourceOriginReadRequest,
) -> DatasourceOriginReadResult:
try:
result = self._provider.read_source(
session,
principal,
request=TabularReadRequest(
source_ref=request.origin_ref,
limit=request.limit,
offset=request.offset,
columns=request.columns,
expected_fingerprint=request.expected_fingerprint,
max_bytes=request.max_bytes,
timeout_ms=request.timeout_ms,
),
)
except TabularSourceError as exc:
raise _datasource_error(exc) from exc
return DatasourceOriginReadResult(
origin=_origin(result.source),
rows=result.rows,
total_rows=result.total_rows,
truncated=result.truncated,
returned_bytes=result.returned_bytes,
elapsed_ms=result.elapsed_ms,
effective_row_limit=result.effective_row_limit,
effective_byte_limit=result.effective_byte_limit,
effective_timeout_ms=result.effective_timeout_ms,
diagnostics=result.diagnostics,
)
def _origin(source: TabularSource) -> DatasourceOrigin:
kind = {
"managed_file": "file",
"postgresql": "database",
}.get(source.provider, "upload")
return DatasourceOrigin(
ref=source.ref,
source_name=source.source_name,
name=source.name,
description=source.description,
kind=kind,
shape="tabular",
supported_modes=("live", "cached"),
provider=f"connectors.{source.provider}",
schema=tuple(
DatasourceField(
name=column.name,
data_type=column.data_type,
nullable=column.nullable,
)
for column in source.schema
),
schema_version=source.schema_version,
fingerprint=source.fingerprint,
row_count=source.row_count,
byte_count=source.byte_count,
updated_at=source.updated_at,
capabilities=source.capabilities,
metadata=dict(source.metadata),
source_mode=source.source_mode,
pushdown=source.pushdown,
health=source.health,
)
def _datasource_error(exc: TabularSourceError):
if isinstance(exc, TabularSourceAccessError):
return DatasourceAccessError(str(exc))
if isinstance(exc, TabularSourceNotFoundError):
return DatasourceNotFoundError(str(exc))
if isinstance(exc, TabularSourceUnavailableError):
return DatasourceUnavailableError(str(exc))
if isinstance(exc, TabularSourceValidationError):
return DatasourceValidationError(str(exc))
return DatasourceValidationError(str(exc))
__all__ = ["ConnectorDatasourceOriginProvider"]
@@ -0,0 +1,3 @@
from govoplan_connectors.backend.db.models import ConnectorTabularSource
__all__ = ["ConnectorTabularSource"]
@@ -0,0 +1,468 @@
from __future__ import annotations
import uuid
from datetime import datetime
from typing import Any
from sqlalchemy import (
Boolean,
DateTime,
ForeignKey,
Index,
Integer,
JSON,
LargeBinary,
String,
Text,
UniqueConstraint,
)
from sqlalchemy.orm import Mapped, mapped_column
from govoplan_core.db.base import Base, TimestampMixin
def new_uuid() -> str:
return str(uuid.uuid4())
class ConnectorTabularSource(Base, TimestampMixin):
__tablename__ = "connector_tabular_sources"
__table_args__ = (
UniqueConstraint("tenant_id", "source_name", name="uq_connector_tabular_source_name"),
Index("ix_connector_tabular_sources_tenant_status", "tenant_id", "status"),
Index("ix_connector_tabular_sources_tenant_updated", "tenant_id", "updated_at"),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
provider: Mapped[str] = mapped_column(String(50), default="snapshot", nullable=False, index=True)
source_name: Mapped[str] = mapped_column(String(120), nullable=False)
name: Mapped[str] = mapped_column(String(300), nullable=False)
description: Mapped[str | None] = mapped_column(Text)
status: Mapped[str] = mapped_column(String(30), default="active", nullable=False, index=True)
schema_version: Mapped[int] = mapped_column(Integer, default=1, nullable=False)
schema_: Mapped[list[dict[str, Any]]] = mapped_column("schema", JSON, default=list, nullable=False)
rows: Mapped[list[dict[str, Any]]] = mapped_column(JSON, default=list, nullable=False)
fingerprint: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
row_count: Mapped[int] = mapped_column(Integer, nullable=False)
byte_count: Mapped[int] = mapped_column(Integer, nullable=False)
metadata_: Mapped[dict[str, Any]] = mapped_column("metadata", JSON, default=dict, nullable=False)
created_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
updated_by: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
deleted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True, index=True)
class ConnectorSanctionsAcquisitionRun(Base, TimestampMixin):
__tablename__ = "connector_sanctions_acquisition_runs"
__table_args__ = (
Index(
"ix_connector_sanctions_run_health",
"tenant_id",
"provider_id",
"status",
"started_at",
),
)
id: Mapped[str] = mapped_column(
String(36),
primary_key=True,
default=new_uuid,
)
tenant_id: Mapped[str] = mapped_column(
String(36),
nullable=False,
index=True,
)
provider_id: Mapped[str] = mapped_column(
String(100),
nullable=False,
index=True,
)
source_id: Mapped[str] = mapped_column(
String(200),
nullable=False,
index=True,
)
status: Mapped[str] = mapped_column(
String(40),
default="running",
nullable=False,
index=True,
)
attempt_count: Mapped[int] = mapped_column(
Integer,
default=0,
nullable=False,
)
request_evidence: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
response_evidence: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
started_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
nullable=False,
index=True,
)
finished_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True),
nullable=True,
)
snapshot_id: Mapped[str | None] = mapped_column(
String(36),
nullable=True,
index=True,
)
error: Mapped[str | None] = mapped_column(
Text,
nullable=True,
)
created_by: Mapped[str | None] = mapped_column(
String(255),
nullable=True,
index=True,
)
class ConnectorSanctionsSnapshot(Base, TimestampMixin):
__tablename__ = "connector_sanctions_snapshots"
__table_args__ = (
UniqueConstraint(
"connector_run_id",
name="uq_connector_sanctions_snapshot_run",
),
Index(
"ix_connector_sanctions_snapshot_source",
"tenant_id",
"provider_id",
"acquired_at",
),
Index(
"ix_connector_sanctions_snapshot_version",
"provider_id",
"source_id",
"source_version",
),
)
id: Mapped[str] = mapped_column(
String(36),
primary_key=True,
default=new_uuid,
)
tenant_id: Mapped[str] = mapped_column(
String(36),
nullable=False,
index=True,
)
provider_id: Mapped[str] = mapped_column(
String(100),
nullable=False,
index=True,
)
publisher: Mapped[str] = mapped_column(
String(300),
nullable=False,
)
jurisdiction: Mapped[str] = mapped_column(
String(100),
nullable=False,
index=True,
)
list_type: Mapped[str] = mapped_column(
String(100),
nullable=False,
index=True,
)
source_id: Mapped[str] = mapped_column(
String(200),
nullable=False,
index=True,
)
source_version: Mapped[str] = mapped_column(
String(255),
nullable=False,
index=True,
)
publication_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True),
nullable=True,
)
effective_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True),
nullable=True,
)
acquired_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
nullable=False,
index=True,
)
source_url: Mapped[str | None] = mapped_column(
String(1500),
nullable=True,
)
content_type: Mapped[str] = mapped_column(
String(200),
nullable=False,
)
byte_count: Mapped[int] = mapped_column(
Integer,
nullable=False,
)
sha256: Mapped[str] = mapped_column(
String(64),
nullable=False,
index=True,
)
signature_evidence: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
parser_version: Mapped[str] = mapped_column(
String(100),
nullable=False,
)
licence_notes: Mapped[str | None] = mapped_column(
Text,
nullable=True,
)
trust_notes: Mapped[str | None] = mapped_column(
Text,
nullable=True,
)
connector_run_id: Mapped[str] = mapped_column(
ForeignKey(
"connector_sanctions_acquisition_runs.id",
ondelete="RESTRICT",
),
nullable=False,
index=True,
)
transport_evidence: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
raw_content: Mapped[bytes] = mapped_column(
LargeBinary,
nullable=False,
)
class ConnectorDefinition(Base, TimestampMixin):
__tablename__ = "connector_definitions"
__table_args__ = (
UniqueConstraint(
"tenant_id",
"definition_key",
name="uq_connector_definition_tenant_key",
),
Index(
"ix_connector_definitions_tenant_status",
"tenant_id",
"status",
),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
definition_key: Mapped[str] = mapped_column(String(160), nullable=False)
name: Mapped[str] = mapped_column(String(300), nullable=False)
description: Mapped[str | None] = mapped_column(Text)
status: Mapped[str] = mapped_column(
String(30),
default="active",
nullable=False,
index=True,
)
current_revision: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
source_package: Mapped[str | None] = mapped_column(String(300))
local_definition: Mapped[bool] = mapped_column(
Boolean,
default=False,
nullable=False,
)
class ConnectorDefinitionRevision(Base, TimestampMixin):
__tablename__ = "connector_definition_revisions"
__table_args__ = (
UniqueConstraint(
"definition_id",
"revision",
name="uq_connector_definition_revision",
),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
definition_id: Mapped[str] = mapped_column(
ForeignKey("connector_definitions.id", ondelete="CASCADE"),
nullable=False,
index=True,
)
revision: Mapped[int] = mapped_column(Integer, nullable=False)
specification: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
definition_hash: Mapped[str] = mapped_column(
String(64),
nullable=False,
index=True,
)
origin: Mapped[str] = mapped_column(String(30), nullable=False)
package_ref: Mapped[str | None] = mapped_column(String(300))
created_by: Mapped[str | None] = mapped_column(String(255), index=True)
class ConnectorConfiguration(Base, TimestampMixin):
__tablename__ = "connector_configurations"
__table_args__ = (
UniqueConstraint(
"tenant_id",
"name",
name="uq_connector_configuration_tenant_name",
),
Index(
"ix_connector_configurations_tenant_status",
"tenant_id",
"status",
),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
definition_id: Mapped[str] = mapped_column(
ForeignKey("connector_definitions.id", ondelete="RESTRICT"),
nullable=False,
index=True,
)
name: Mapped[str] = mapped_column(String(300), nullable=False)
status: Mapped[str] = mapped_column(
String(30),
default="draft",
nullable=False,
index=True,
)
endpoint_url: Mapped[str | None] = mapped_column(String(1500))
credential_ref: Mapped[str | None] = mapped_column(String(500))
base_definition_revision: Mapped[int] = mapped_column(
Integer,
nullable=False,
)
local_overrides: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
protected_paths: Mapped[list[str]] = mapped_column(
JSON,
default=list,
nullable=False,
)
effective_configuration: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
effective_hash: Mapped[str] = mapped_column(
String(64),
nullable=False,
index=True,
)
resource_revision: Mapped[int] = mapped_column(
Integer,
default=1,
nullable=False,
)
ambiguity_policy: Mapped[str] = mapped_column(
String(30),
default="manual_review",
nullable=False,
)
updated_by: Mapped[str | None] = mapped_column(String(255), index=True)
class ConnectorSimulationRun(Base, TimestampMixin):
__tablename__ = "connector_simulation_runs"
__table_args__ = (
UniqueConstraint(
"tenant_id",
"configuration_id",
"mode",
"idempotency_key",
name="uq_connector_simulation_run_idempotency",
),
Index(
"ix_connector_simulation_runs_review",
"tenant_id",
"review_state",
"created_at",
),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
tenant_id: Mapped[str] = mapped_column(String(36), nullable=False, index=True)
configuration_id: Mapped[str] = mapped_column(
ForeignKey("connector_configurations.id", ondelete="CASCADE"),
nullable=False,
index=True,
)
mode: Mapped[str] = mapped_column(String(30), nullable=False, index=True)
idempotency_key: Mapped[str] = mapped_column(String(255), nullable=False)
request_hash: Mapped[str] = mapped_column(String(64), nullable=False)
status: Mapped[str] = mapped_column(String(30), nullable=False, index=True)
review_state: Mapped[str] = mapped_column(
String(30),
default="not_required",
nullable=False,
index=True,
)
definition_revision: Mapped[int] = mapped_column(Integer, nullable=False)
configuration_revision: Mapped[int] = mapped_column(Integer, nullable=False)
configuration_hash: Mapped[str] = mapped_column(String(64), nullable=False)
input_hash: Mapped[str] = mapped_column(String(64), nullable=False)
summary: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
effects: Mapped[list[dict[str, Any]]] = mapped_column(
JSON,
default=list,
nullable=False,
)
diagnostics: Mapped[list[dict[str, Any]]] = mapped_column(
JSON,
default=list,
nullable=False,
)
provenance: Mapped[dict[str, Any]] = mapped_column(
JSON,
default=dict,
nullable=False,
)
created_by: Mapped[str | None] = mapped_column(String(255), index=True)
reviewed_by: Mapped[str | None] = mapped_column(String(255), index=True)
reviewed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
review_reason: Mapped[str | None] = mapped_column(Text)
__all__ = [
"ConnectorConfiguration",
"ConnectorDefinition",
"ConnectorDefinitionRevision",
"ConnectorSanctionsAcquisitionRun",
"ConnectorSanctionsSnapshot",
"ConnectorSimulationRun",
"ConnectorTabularSource",
"new_uuid",
]
@@ -0,0 +1,482 @@
from __future__ import annotations
from collections.abc import Sequence
from dataclasses import dataclass
from datetime import datetime, timezone
from sqlalchemy import or_
from sqlalchemy.orm import Session
from govoplan_core.core.dsar import (
DsarErasureActionRef,
DsarExecutionResultRef,
DsarRecordRef,
DsarSubjectRef,
dsar_capability_name,
)
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorDefinitionRevision,
ConnectorSanctionsAcquisitionRun,
ConnectorSimulationRun,
ConnectorTabularSource,
)
CONNECTORS_DSAR_CAPABILITY = dsar_capability_name("connectors")
_MAX_RECORDS = 5_000
_CONFLICT = object()
@dataclass(frozen=True, slots=True)
class _SubjectSelectors:
account_id: str
source_id: str | None
acquisition_id: str | None
definition_id: str | None
configuration_id: str | None
simulation_id: str | None
@property
def narrowed(self) -> bool:
return any(
(
self.source_id,
self.acquisition_id,
self.definition_id,
self.configuration_id,
self.simulation_id,
)
)
class ConnectorsDsarProvider:
provider_id = "connectors"
module_id = "connectors"
def search_subject(
self,
session: object,
*,
tenant_id: str,
subject: DsarSubjectRef,
) -> Sequence[DsarRecordRef]:
db = _session(session)
selectors = _subject_selectors(subject)
if selectors is None:
return ()
records: list[DsarRecordRef] = []
if not selectors.narrowed or selectors.source_id:
query = db.query(ConnectorTabularSource).filter(
ConnectorTabularSource.tenant_id == tenant_id,
or_(
ConnectorTabularSource.created_by == selectors.account_id,
ConnectorTabularSource.updated_by == selectors.account_id,
),
)
if selectors.source_id:
query = query.filter(ConnectorTabularSource.id == selectors.source_id)
records.extend(
_source_attribution(row, selectors.account_id)
for row in _limited(
query,
ConnectorTabularSource.created_at,
ConnectorTabularSource.id,
label="source attribution",
)
)
if not selectors.narrowed or selectors.acquisition_id:
query = db.query(ConnectorSanctionsAcquisitionRun).filter(
ConnectorSanctionsAcquisitionRun.tenant_id == tenant_id,
ConnectorSanctionsAcquisitionRun.created_by == selectors.account_id,
)
if selectors.acquisition_id:
query = query.filter(
ConnectorSanctionsAcquisitionRun.id == selectors.acquisition_id
)
records.extend(
_acquisition_attribution(row)
for row in _limited(
query,
ConnectorSanctionsAcquisitionRun.started_at,
ConnectorSanctionsAcquisitionRun.id,
label="acquisition attribution",
)
)
if not selectors.narrowed or selectors.definition_id:
query = (
db.query(ConnectorDefinitionRevision, ConnectorDefinition)
.join(
ConnectorDefinition,
ConnectorDefinition.id == ConnectorDefinitionRevision.definition_id,
)
.filter(
ConnectorDefinition.tenant_id == tenant_id,
ConnectorDefinitionRevision.created_by == selectors.account_id,
)
)
if selectors.definition_id:
query = query.filter(ConnectorDefinition.id == selectors.definition_id)
records.extend(
_definition_attribution(revision, definition)
for revision, definition in _limited(
query,
ConnectorDefinitionRevision.created_at,
ConnectorDefinitionRevision.id,
label="definition attribution",
)
)
if not selectors.narrowed or selectors.configuration_id:
query = db.query(ConnectorConfiguration).filter(
ConnectorConfiguration.tenant_id == tenant_id,
ConnectorConfiguration.updated_by == selectors.account_id,
)
if selectors.configuration_id:
query = query.filter(
ConnectorConfiguration.id == selectors.configuration_id
)
records.extend(
_configuration_attribution(row)
for row in _limited(
query,
ConnectorConfiguration.updated_at,
ConnectorConfiguration.id,
label="configuration attribution",
)
)
if not selectors.narrowed or selectors.simulation_id:
query = db.query(ConnectorSimulationRun).filter(
ConnectorSimulationRun.tenant_id == tenant_id,
or_(
ConnectorSimulationRun.created_by == selectors.account_id,
ConnectorSimulationRun.reviewed_by == selectors.account_id,
),
)
if selectors.simulation_id:
query = query.filter(
ConnectorSimulationRun.id == selectors.simulation_id
)
records.extend(
_simulation_attribution(row, selectors.account_id)
for row in _limited(
query,
ConnectorSimulationRun.created_at,
ConnectorSimulationRun.id,
label="simulation attribution",
)
)
if len(records) > _MAX_RECORDS:
raise ValueError("Connectors DSAR result limit exceeded; narrow selectors.")
return tuple(
sorted(records, key=lambda item: (item.resource_type, item.resource_id))
)
def plan_erasure(
self,
session: object,
*,
tenant_id: str,
subject: DsarSubjectRef,
records: Sequence[DsarRecordRef],
) -> Sequence[DsarErasureActionRef]:
del tenant_id
_session(session)
if _subject_selectors(subject) is None:
raise ValueError("Connectors DSAR subject selectors conflict.")
actions: list[DsarErasureActionRef] = []
for record in records:
_validate_record(record)
actions.append(
DsarErasureActionRef(
action_id=(
f"connectors:retain:{record.resource_type}:{record.resource_id}"
),
provider_id=self.provider_id,
module_id=self.module_id,
kind="retain",
resource_type=record.resource_type,
resource_id=record.resource_id,
title=f"Retain {record.title}",
rationale=(
record.retention_reason
or "Connector operator attribution remains governance evidence."
),
executable=False,
)
)
return tuple(actions)
def execute_erasure(
self,
session: object,
*,
tenant_id: str,
subject: DsarSubjectRef,
actions: Sequence[DsarErasureActionRef],
request_id: str,
) -> Sequence[DsarExecutionResultRef]:
del tenant_id
_session(session)
if _subject_selectors(subject) is None:
raise ValueError("Connectors DSAR subject selectors conflict.")
results: list[DsarExecutionResultRef] = []
for action in actions:
_validate_action(action)
if action.executable or action.kind != "retain":
raise ValueError("Connectors DSAR publishes retain actions only.")
results.append(
DsarExecutionResultRef(
action_id=action.action_id,
status="blocked",
summary="Connector operator attribution remains governance evidence.",
evidence={"request_id": request_id},
)
)
return tuple(results)
def _subject_selectors(subject: DsarSubjectRef) -> _SubjectSelectors | None:
references = subject.external_references
account = _coalesce(
subject.account_id,
references.get("connectors.account"),
references.get("access.account"),
)
values = {
"source_id": _coalesce(
references.get("connectors.source"),
references.get("connectors.source_id"),
),
"acquisition_id": _coalesce(
references.get("connectors.acquisition"),
references.get("connectors.acquisition_id"),
),
"definition_id": _coalesce(
references.get("connectors.definition"),
references.get("connectors.definition_id"),
),
"configuration_id": _coalesce(
references.get("connectors.configuration"),
references.get("connectors.configuration_id"),
),
"simulation_id": _coalesce(
references.get("connectors.simulation"),
references.get("connectors.simulation_id"),
),
}
if account is _CONFLICT or any(value is _CONFLICT for value in values.values()):
return None
account_id = _optional_string(account)
if not account_id:
return None
return _SubjectSelectors(
account_id=account_id,
source_id=_optional_string(values["source_id"]),
acquisition_id=_optional_string(values["acquisition_id"]),
definition_id=_optional_string(values["definition_id"]),
configuration_id=_optional_string(values["configuration_id"]),
simulation_id=_optional_string(values["simulation_id"]),
)
def _source_attribution(row: ConnectorTabularSource, account_id: str) -> DsarRecordRef:
activities = []
if row.created_by == account_id:
activities.append("created_source_snapshot")
if row.updated_by == account_id:
activities.append("updated_source_snapshot")
return _record(
resource_type="source_actor_attribution",
resource_id=row.id,
title="Connector source actor attribution",
data={
"source_id": row.id,
"provider": row.provider,
"status": row.status,
"schema_version": row.schema_version,
"row_count": row.row_count,
"activities": activities,
"created_at": _iso(row.created_at),
"updated_at": _iso(row.updated_at),
"retired_at": _iso(row.deleted_at),
},
observed_at=row.updated_at,
)
def _acquisition_attribution(row: ConnectorSanctionsAcquisitionRun) -> DsarRecordRef:
return _record(
resource_type="acquisition_actor_attribution",
resource_id=row.id,
title="Connector acquisition actor attribution",
data={
"acquisition_id": row.id,
"provider_id": row.provider_id,
"source_id": row.source_id,
"status": row.status,
"attempt_count": row.attempt_count,
"started_at": _iso(row.started_at),
"finished_at": _iso(row.finished_at),
"activity": "started_source_acquisition",
},
observed_at=row.finished_at or row.started_at,
)
def _definition_attribution(
row: ConnectorDefinitionRevision, definition: ConnectorDefinition
) -> DsarRecordRef:
return _record(
resource_type="definition_actor_attribution",
resource_id=row.id,
title="Connector definition actor attribution",
data={
"definition_id": definition.id,
"revision_id": row.id,
"revision": row.revision,
"origin": row.origin,
"activity": "created_definition_revision",
"created_at": _iso(row.created_at),
},
observed_at=row.created_at,
)
def _configuration_attribution(row: ConnectorConfiguration) -> DsarRecordRef:
return _record(
resource_type="configuration_actor_attribution",
resource_id=row.id,
title="Connector configuration actor attribution",
data={
"configuration_id": row.id,
"definition_id": row.definition_id,
"status": row.status,
"base_definition_revision": row.base_definition_revision,
"resource_revision": row.resource_revision,
"ambiguity_policy": row.ambiguity_policy,
"activity": "updated_connector_configuration",
"updated_at": _iso(row.updated_at),
},
observed_at=row.updated_at,
)
def _simulation_attribution(
row: ConnectorSimulationRun, account_id: str
) -> DsarRecordRef:
activities = []
if row.created_by == account_id:
activities.append("created_simulation")
if row.reviewed_by == account_id:
activities.append("reviewed_simulation")
return _record(
resource_type="simulation_actor_attribution",
resource_id=row.id,
title="Connector simulation actor attribution",
data={
"simulation_id": row.id,
"configuration_id": row.configuration_id,
"mode": row.mode,
"status": row.status,
"review_state": row.review_state,
"definition_revision": row.definition_revision,
"configuration_revision": row.configuration_revision,
"activities": activities,
"created_at": _iso(row.created_at),
"reviewed_at": _iso(row.reviewed_at),
},
observed_at=row.reviewed_at or row.created_at,
)
def _record(
*,
resource_type: str,
resource_id: str,
title: str,
data: dict[str, object],
observed_at: datetime | None,
) -> DsarRecordRef:
return DsarRecordRef(
provider_id="connectors",
module_id="connectors",
resource_type=resource_type,
resource_id=resource_id,
category="connector_governance_attribution",
title=title,
data=data,
observed_at=_aware(observed_at),
immutable_evidence=True,
retention_reason=(
"Connector attribution is retained for configuration, review, and "
"external-operation accountability."
),
)
def _limited(query, first, second, *, label: str):
rows = query.order_by(first, second).limit(_MAX_RECORDS + 1).all()
if len(rows) > _MAX_RECORDS:
raise ValueError(f"Connectors DSAR {label} limit exceeded; narrow selectors.")
return rows
def _coalesce(*values: str | None) -> str | None | object:
normalized = {str(value).strip() for value in values if str(value or "").strip()}
if len(normalized) > 1:
return _CONFLICT
return next(iter(normalized), None)
def _optional_string(value: object) -> str | None:
return value if isinstance(value, str) and value else None
def _iso(value: datetime | None) -> str | None:
aware = _aware(value)
return aware.isoformat() if aware else None
def _aware(value: datetime | None) -> datetime | None:
if value is None or value.tzinfo is not None:
return value
return value.replace(tzinfo=timezone.utc)
def _session(value: object) -> Session:
if not isinstance(value, Session):
raise TypeError("Connectors DSAR requires a SQLAlchemy Session.")
return value
_RESOURCE_TYPES = {
"source_actor_attribution",
"acquisition_actor_attribution",
"definition_actor_attribution",
"configuration_actor_attribution",
"simulation_actor_attribution",
}
def _validate_record(record: DsarRecordRef) -> None:
if record.provider_id != "connectors" or record.module_id != "connectors":
raise ValueError("Connectors DSAR cannot plan a foreign provider record.")
if record.resource_type not in _RESOURCE_TYPES or not record.resource_id:
raise ValueError("Connectors DSAR record identity is invalid.")
def _validate_action(action: DsarErasureActionRef) -> None:
if action.provider_id != "connectors" or action.module_id != "connectors":
raise ValueError("Connectors DSAR cannot execute a foreign provider action.")
if not action.action_id.startswith("connectors:retain:"):
raise ValueError("Connectors DSAR action identity is invalid.")
__all__ = ["CONNECTORS_DSAR_CAPABILITY", "ConnectorsDsarProvider"]
+421
View File
@@ -0,0 +1,421 @@
from __future__ import annotations
import hashlib
import re
import xml.etree.ElementTree as ET
from collections.abc import Mapping
from dataclasses import replace
from datetime import datetime, timedelta, timezone
from email.utils import format_datetime, parsedate_to_datetime
from defusedxml import ElementTree as SafeET
from defusedxml.common import DefusedXmlException
from govoplan_core.core.feeds import (
FeedCapabilityError,
FeedDocument,
FeedEntry,
FeedProvider,
FeedRenderRequest,
FeedRenderResult,
)
from govoplan_core.security.http_fetch import fetch_http
MAX_FEED_BYTES = 5_000_000
ATOM_NS = "http://www.w3.org/2005/Atom"
FEED_PUBLISH_SCOPE = "connectors:feeds:publish"
FEED_PRIVATE_PUBLISH_SCOPE = "connectors:feeds:publish_private"
class ConnectorFeedProvider(FeedProvider):
def fetch(
self,
url: str,
*,
timeout: float = 15,
max_entries: int = 2_000,
) -> FeedDocument:
try:
response = fetch_http(
url,
timeout=timeout,
label="RSS/Atom feed URL",
headers={
"Accept": (
"application/atom+xml, application/rss+xml, "
"application/xml;q=0.9, text/xml;q=0.8"
)
},
max_bytes=MAX_FEED_BYTES,
)
except Exception as exc:
raise FeedCapabilityError(f"Feed acquisition failed: {exc}") from exc
if response.status < 200 or response.status >= 300:
raise FeedCapabilityError(
f"Feed acquisition returned HTTP {response.status}."
)
content_type = _header(response.headers, "content-type")
document = self.parse(
response.body,
source_url=url,
content_type=content_type,
max_entries=max_entries,
)
acquired_at = datetime.now(timezone.utc)
return replace(
document,
acquired_at=acquired_at,
fresh_until=_fresh_until(response.headers, acquired_at),
etag=_header(response.headers, "etag"),
last_modified=_header(response.headers, "last-modified"),
metadata={
**dict(document.metadata),
"http_status": response.status,
"byte_count": len(response.body),
},
)
def parse(
self,
content: bytes,
*,
source_url: str,
content_type: str | None = None,
max_entries: int = 2_000,
) -> FeedDocument:
if not content:
raise FeedCapabilityError("Feed content is empty.")
if len(content) > MAX_FEED_BYTES:
raise FeedCapabilityError(
f"Feeds are limited to {MAX_FEED_BYTES // 1_000_000} MB."
)
try:
root = SafeET.fromstring(content)
except (ET.ParseError, DefusedXmlException) as exc:
raise FeedCapabilityError(f"Feed XML is not safe or valid: {exc}") from exc
local_name = _local_name(root.tag)
if local_name == "rss":
document = _parse_rss(root, source_url=source_url, max_entries=max_entries)
elif local_name == "feed":
document = _parse_atom(root, source_url=source_url, max_entries=max_entries)
else:
raise FeedCapabilityError("The document is neither an RSS nor an Atom feed.")
return replace(
document,
content_type=content_type,
sha256=hashlib.sha256(content).hexdigest(),
)
def render(self, request: FeedRenderRequest) -> FeedRenderResult:
if not request.title.strip() or not request.feed_url.strip():
raise FeedCapabilityError("Feed title and feed URL are required.")
entries = tuple(
entry
for entry in request.entries
if entry.visibility in request.allowed_visibilities
)
root = (
_render_rss(request, entries)
if request.format == "rss"
else _render_atom(request, entries)
)
body = ET.tostring(root, encoding="utf-8", xml_declaration=True)
return FeedRenderResult(
format=request.format,
content_type=(
"application/rss+xml; charset=utf-8"
if request.format == "rss"
else "application/atom+xml; charset=utf-8"
),
body=body,
included_entries=len(entries),
excluded_entries=len(request.entries) - len(entries),
)
def feed_rows(document: FeedDocument) -> tuple[Mapping[str, object], ...]:
"""Map feed entries to the connector tabular shape used by Datasources."""
return tuple(
{
"id": entry.id,
"title": entry.title,
"url": entry.url,
"summary": entry.summary,
"content": entry.content,
"author": entry.author,
"published_at": (
entry.published_at.isoformat() if entry.published_at else None
),
"updated_at": entry.updated_at.isoformat() if entry.updated_at else None,
"categories": list(entry.categories),
"enclosures": [dict(item) for item in entry.enclosures],
}
for entry in document.entries
)
def _parse_rss(root: ET.Element, *, source_url: str, max_entries: int) -> FeedDocument:
channel = _first_child(root, "channel")
if channel is None:
raise FeedCapabilityError("RSS feed is missing its channel element.")
entries: list[FeedEntry] = []
for item in _children(channel, "item"):
if len(entries) >= max_entries:
raise FeedCapabilityError(f"Feeds are limited to {max_entries:,} entries.")
url = _text(item, "link")
identifier = _text(item, "guid") or url or _entry_fallback_id(item)
entries.append(
FeedEntry(
id=identifier,
title=_text(item, "title") or "(Untitled)",
url=url,
summary=_text(item, "description"),
content=_text(item, "encoded"),
author=_text(item, "author") or _text(item, "creator"),
published_at=_parse_date(_text(item, "pubDate")),
categories=tuple(
value for child in _children(item, "category")
if (value := (child.text or "").strip())
),
enclosures=tuple(
{
"url": child.attrib.get("url"),
"media_type": child.attrib.get("type"),
"size_bytes": _integer(child.attrib.get("length")),
}
for child in _children(item, "enclosure")
),
)
)
return FeedDocument(
format="rss",
title=_text(channel, "title") or "Untitled feed",
source_url=source_url,
entries=tuple(entries),
description=_text(channel, "description"),
home_url=_text(channel, "link"),
language=_text(channel, "language"),
updated_at=_parse_date(
_text(channel, "lastBuildDate") or _text(channel, "pubDate")
),
)
def _parse_atom(root: ET.Element, *, source_url: str, max_entries: int) -> FeedDocument:
entries: list[FeedEntry] = []
for item in _children(root, "entry"):
if len(entries) >= max_entries:
raise FeedCapabilityError(f"Feeds are limited to {max_entries:,} entries.")
alternate = _atom_link(item, "alternate")
identifier = _text(item, "id") or alternate or _entry_fallback_id(item)
author = _first_child(item, "author")
entries.append(
FeedEntry(
id=identifier,
title=_text(item, "title") or "(Untitled)",
url=alternate,
summary=_text(item, "summary"),
content=_text(item, "content"),
author=_text(author, "name") if author is not None else None,
published_at=_parse_date(_text(item, "published")),
updated_at=_parse_date(_text(item, "updated")),
categories=tuple(
value for child in _children(item, "category")
if (value := (child.attrib.get("term") or "").strip())
),
enclosures=tuple(
{
"url": child.attrib.get("href"),
"media_type": child.attrib.get("type"),
"size_bytes": _integer(child.attrib.get("length")),
}
for child in _children(item, "link")
if child.attrib.get("rel") == "enclosure"
),
)
)
return FeedDocument(
format="atom",
title=_text(root, "title") or "Untitled feed",
source_url=source_url,
entries=tuple(entries),
description=_text(root, "subtitle"),
home_url=_atom_link(root, "alternate"),
updated_at=_parse_date(_text(root, "updated")),
)
def _render_rss(request: FeedRenderRequest, entries: tuple[FeedEntry, ...]) -> ET.Element:
ET.register_namespace("atom", ATOM_NS)
root = ET.Element("rss", {"version": "2.0"})
channel = ET.SubElement(root, "channel")
_element(channel, "title", request.title)
_element(channel, "link", request.home_url)
_element(channel, "description", request.description or request.title)
_element(channel, f"{{{ATOM_NS}}}link", None, {
"href": request.feed_url,
"rel": "self",
"type": "application/rss+xml",
})
if request.language:
_element(channel, "language", request.language)
for entry in entries:
item = ET.SubElement(channel, "item")
_element(item, "guid", entry.id, {"isPermaLink": "false"})
_element(item, "title", entry.title)
if entry.url:
_element(item, "link", entry.url)
if entry.summary or entry.content:
_element(item, "description", entry.summary or entry.content)
if entry.author:
_element(item, "author", entry.author)
date = entry.published_at or entry.updated_at
if date:
_element(item, "pubDate", format_datetime(_utc(date)))
for category in entry.categories:
_element(item, "category", category)
for enclosure in entry.enclosures:
attributes = {
"url": str(enclosure.get("url") or ""),
"type": str(enclosure.get("media_type") or "application/octet-stream"),
"length": str(enclosure.get("size_bytes") or 0),
}
if attributes["url"]:
_element(item, "enclosure", None, attributes)
return root
def _render_atom(request: FeedRenderRequest, entries: tuple[FeedEntry, ...]) -> ET.Element:
ET.register_namespace("", ATOM_NS)
root = ET.Element(f"{{{ATOM_NS}}}feed")
_element(root, f"{{{ATOM_NS}}}id", request.feed_url)
_element(root, f"{{{ATOM_NS}}}title", request.title)
_element(root, f"{{{ATOM_NS}}}link", None, {"href": request.home_url})
_element(
root,
f"{{{ATOM_NS}}}link",
None,
{"href": request.feed_url, "rel": "self", "type": "application/atom+xml"},
)
latest = max(
(date for entry in entries for date in (entry.updated_at, entry.published_at) if date),
default=datetime.now(timezone.utc),
)
_element(root, f"{{{ATOM_NS}}}updated", _utc(latest).isoformat().replace("+00:00", "Z"))
if request.description:
_element(root, f"{{{ATOM_NS}}}subtitle", request.description)
for value in entries:
entry = ET.SubElement(root, f"{{{ATOM_NS}}}entry")
_element(entry, f"{{{ATOM_NS}}}id", value.id)
_element(entry, f"{{{ATOM_NS}}}title", value.title)
if value.url:
_element(entry, f"{{{ATOM_NS}}}link", None, {"href": value.url})
if value.summary:
_element(entry, f"{{{ATOM_NS}}}summary", value.summary)
if value.content:
_element(entry, f"{{{ATOM_NS}}}content", value.content, {"type": "html"})
updated = value.updated_at or value.published_at or latest
_element(entry, f"{{{ATOM_NS}}}updated", _utc(updated).isoformat().replace("+00:00", "Z"))
if value.published_at:
_element(entry, f"{{{ATOM_NS}}}published", _utc(value.published_at).isoformat().replace("+00:00", "Z"))
if value.author:
author = ET.SubElement(entry, f"{{{ATOM_NS}}}author")
_element(author, f"{{{ATOM_NS}}}name", value.author)
for category in value.categories:
_element(entry, f"{{{ATOM_NS}}}category", None, {"term": category})
return root
def _children(element: ET.Element, name: str) -> tuple[ET.Element, ...]:
return tuple(child for child in element if _local_name(child.tag) == name)
def _first_child(element: ET.Element, name: str) -> ET.Element | None:
return next((child for child in element if _local_name(child.tag) == name), None)
def _text(element: ET.Element | None, name: str) -> str | None:
if element is None:
return None
child = _first_child(element, name)
if child is None:
return None
value = "".join(child.itertext()).strip()
return value or None
def _local_name(tag: str) -> str:
return tag.rsplit("}", 1)[-1].split(":", 1)[-1]
def _atom_link(element: ET.Element, relation: str) -> str | None:
for child in _children(element, "link"):
if (child.attrib.get("rel") or "alternate") == relation:
return child.attrib.get("href")
return None
def _parse_date(value: str | None) -> datetime | None:
if not value:
return None
try:
parsed = parsedate_to_datetime(value)
except (TypeError, ValueError, OverflowError):
try:
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
except ValueError:
return None
return _utc(parsed)
def _utc(value: datetime) -> datetime:
if value.tzinfo is None:
return value.replace(tzinfo=timezone.utc)
return value.astimezone(timezone.utc)
def _integer(value: str | None) -> int | None:
try:
return int(value) if value is not None else None
except ValueError:
return None
def _entry_fallback_id(element: ET.Element) -> str:
body = ET.tostring(element, encoding="utf-8")
return f"urn:sha256:{hashlib.sha256(body).hexdigest()}"
def _header(headers: Mapping[str, str], name: str) -> str | None:
lowered = name.casefold()
return next((value for key, value in headers.items() if key.casefold() == lowered), None)
def _fresh_until(headers: Mapping[str, str], acquired_at: datetime) -> datetime | None:
cache_control = _header(headers, "cache-control") or ""
match = re.search(r"(?:^|,)\s*max-age\s*=\s*(\d+)", cache_control, re.IGNORECASE)
if match:
return acquired_at + timedelta(seconds=int(match.group(1)))
return _parse_date(_header(headers, "expires"))
def _element(
parent: ET.Element,
tag: str,
text: str | None,
attributes: Mapping[str, str] | None = None,
) -> ET.Element:
child = ET.SubElement(parent, tag, dict(attributes or {}))
child.text = text
return child
__all__ = [
"ConnectorFeedProvider",
"FEED_PRIVATE_PUBLISH_SCOPE",
"FEED_PUBLISH_SCOPE",
"MAX_FEED_BYTES",
"feed_rows",
]
@@ -0,0 +1,921 @@
from __future__ import annotations
import copy
from datetime import UTC, datetime
import hashlib
import json
from typing import Any, Mapping, Sequence
from sqlalchemy.orm import Session
from govoplan_core.audit.logging import audit_from_principal
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.connector_runtime import ConnectorContractError, ConnectorEndpoint
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorDefinitionRevision,
ConnectorSimulationRun,
)
from govoplan_connectors.backend.governed_schemas import (
ConnectorConfigurationCreateRequest,
ConnectorConfigurationItem,
ConnectorConfigurationUpdateRequest,
ConnectorDefinitionItem,
ConnectorDefinitionUpsertRequest,
ConnectorReviewRequest,
ConnectorRunItem,
ConnectorRunRequest,
GovernedConnectorSpecification,
)
class GovernedConnectorError(ValueError):
def __init__(self, code: str, message: str) -> None:
super().__init__(message)
self.code = code
def list_definitions(
session: Session,
*,
tenant_id: str,
) -> list[ConnectorDefinitionItem]:
rows = (
session.query(ConnectorDefinition)
.filter(
ConnectorDefinition.tenant_id == tenant_id,
ConnectorDefinition.status == "active",
)
.order_by(ConnectorDefinition.name.asc())
.all()
)
return [
definition_item(
session,
row,
_definition_revision(session, row, row.current_revision),
)
for row in rows
]
def upsert_definition(
session: Session,
principal: ApiPrincipal,
payload: ConnectorDefinitionUpsertRequest,
) -> ConnectorDefinitionItem:
specification = payload.specification.model_dump(mode="json")
definition_hash = _hash(specification)
definition = (
session.query(ConnectorDefinition)
.filter(
ConnectorDefinition.tenant_id == principal.tenant_id,
ConnectorDefinition.definition_key == payload.definition_key,
)
.one_or_none()
)
expected_local = payload.origin == "local"
if definition is None:
definition = ConnectorDefinition(
tenant_id=principal.tenant_id,
definition_key=payload.definition_key,
name=payload.name.strip(),
description=_optional_text(payload.description),
status="active",
current_revision=0,
source_package=payload.package_ref,
local_definition=expected_local,
)
session.add(definition)
session.flush()
elif definition.local_definition != expected_local:
if definition.local_definition:
raise GovernedConnectorError(
"local_definition_protected",
"A package update cannot replace a locally owned connector definition.",
)
raise GovernedConnectorError(
"package_definition_requires_overrides",
"Use configuration overrides instead of converting a package definition into a local definition.",
)
else:
current = _definition_revision(
session,
definition,
definition.current_revision,
)
if current.definition_hash == definition_hash:
return definition_item(session, definition, current)
definition.name = payload.name.strip()
definition.description = _optional_text(payload.description)
definition.source_package = payload.package_ref
definition.current_revision += 1
revision = ConnectorDefinitionRevision(
definition_id=definition.id,
revision=definition.current_revision,
specification=specification,
definition_hash=definition_hash,
origin=payload.origin,
package_ref=payload.package_ref,
created_by=principal.user.id,
)
session.add(revision)
session.flush()
audit_from_principal(
session,
principal,
action="connectors.definition.revision_created",
object_type="connector_definition",
object_id=definition.id,
details={
"definition_key": definition.definition_key,
"revision": revision.revision,
"definition_hash": definition_hash,
"origin": payload.origin,
"package_ref": payload.package_ref,
"provider": payload.specification.provider,
"protocol": payload.specification.protocol,
"capabilities": sorted(payload.specification.capabilities),
},
)
session.commit()
return definition_item(session, definition, revision)
def list_configurations(
session: Session,
*,
tenant_id: str,
) -> list[ConnectorConfigurationItem]:
rows = (
session.query(ConnectorConfiguration)
.filter(ConnectorConfiguration.tenant_id == tenant_id)
.order_by(ConnectorConfiguration.name.asc())
.all()
)
return [configuration_item(session, row) for row in rows]
def create_configuration(
session: Session,
principal: ApiPrincipal,
payload: ConnectorConfigurationCreateRequest,
) -> ConnectorConfigurationItem:
definition = _tenant_definition(
session,
tenant_id=principal.tenant_id,
definition_id=payload.definition_id,
)
_validate_endpoint(payload.endpoint_url, payload.credential_ref)
revision = _definition_revision(session, definition, definition.current_revision)
overrides = copy.deepcopy(payload.local_overrides)
effective = _effective_specification(revision.specification, overrides)
item = ConnectorConfiguration(
tenant_id=principal.tenant_id,
definition_id=definition.id,
name=payload.name.strip(),
status=payload.status,
endpoint_url=_optional_text(payload.endpoint_url),
credential_ref=_optional_text(payload.credential_ref),
base_definition_revision=definition.current_revision,
local_overrides=overrides,
protected_paths=_protected_paths(overrides),
effective_configuration=effective,
effective_hash=_hash(effective),
resource_revision=1,
ambiguity_policy=payload.ambiguity_policy,
updated_by=principal.user.id,
)
session.add(item)
session.flush()
_audit_configuration(
session,
principal,
item,
action="connectors.configuration.created",
)
session.commit()
return configuration_item(session, item)
def update_configuration(
session: Session,
principal: ApiPrincipal,
*,
configuration_id: str,
payload: ConnectorConfigurationUpdateRequest,
) -> ConnectorConfigurationItem:
item = _tenant_configuration(
session,
tenant_id=principal.tenant_id,
configuration_id=configuration_id,
)
if item.resource_revision != payload.expected_revision:
raise GovernedConnectorError(
"configuration_conflict",
"The connector configuration changed; reload it before saving.",
)
supplied = payload.model_fields_set
definition = _tenant_definition(
session,
tenant_id=principal.tenant_id,
definition_id=item.definition_id,
)
if "name" in supplied and payload.name is not None:
item.name = payload.name.strip()
if "endpoint_url" in supplied:
item.endpoint_url = _optional_text(payload.endpoint_url)
if "credential_ref" in supplied:
item.credential_ref = _optional_text(payload.credential_ref)
if "local_overrides" in supplied and payload.local_overrides is not None:
item.local_overrides = copy.deepcopy(payload.local_overrides)
if payload.ambiguity_policy is not None:
item.ambiguity_policy = payload.ambiguity_policy
if payload.status is not None:
item.status = payload.status
if payload.adopt_latest_definition:
item.base_definition_revision = definition.current_revision
_validate_endpoint(item.endpoint_url, item.credential_ref)
base = _definition_revision(
session,
definition,
item.base_definition_revision,
)
effective = _effective_specification(base.specification, item.local_overrides)
item.protected_paths = _protected_paths(item.local_overrides)
item.effective_configuration = effective
item.effective_hash = _hash(effective)
item.resource_revision += 1
item.updated_by = principal.user.id
_audit_configuration(
session,
principal,
item,
action="connectors.configuration.updated",
extra={"adopted_latest_definition": payload.adopt_latest_definition},
)
session.commit()
return configuration_item(session, item)
def execute_run(
session: Session,
principal: ApiPrincipal,
*,
configuration_id: str,
mode: str,
payload: ConnectorRunRequest,
) -> ConnectorRunItem:
if mode not in {"dry_run", "simulation"}:
raise GovernedConnectorError("invalid_mode", "Unsupported connector run mode.")
configuration = _tenant_configuration(
session,
tenant_id=principal.tenant_id,
configuration_id=configuration_id,
)
if configuration.status == "disabled":
raise GovernedConnectorError(
"configuration_disabled",
"Disabled connector configurations cannot be executed.",
)
specification = GovernedConnectorSpecification.model_validate(
configuration.effective_configuration
)
if mode == "dry_run" and not specification.dry_run.supported:
raise GovernedConnectorError(
"dry_run_unsupported",
"This connector definition does not support dry runs.",
)
if mode == "simulation" and not specification.dry_run.simulation_supported:
raise GovernedConnectorError(
"simulation_unsupported",
"This connector definition does not support simulation.",
)
rows = (
list(payload.input_rows)
if payload.input_rows is not None
else list(specification.dry_run.sample_rows)
)
request_payload = {
"mode": mode,
"configuration_id": configuration.id,
"configuration_revision": configuration.resource_revision,
"configuration_hash": configuration.effective_hash,
"external_revision": payload.external_revision,
"input_rows": rows,
}
request_hash = _hash(request_payload)
existing = (
session.query(ConnectorSimulationRun)
.filter(
ConnectorSimulationRun.tenant_id == principal.tenant_id,
ConnectorSimulationRun.configuration_id == configuration.id,
ConnectorSimulationRun.mode == mode,
ConnectorSimulationRun.idempotency_key == payload.idempotency_key,
)
.one_or_none()
)
if existing is not None:
if existing.request_hash != request_hash:
raise GovernedConnectorError(
"idempotency_conflict",
"The idempotency key was already used with different run inputs.",
)
return run_item(existing)
limit = specification.dry_run.max_items
truncated = len(rows) > limit
bounded_rows = rows[:limit]
effects, diagnostics, ambiguous_count = _simulate(
bounded_rows,
specification,
)
if truncated:
diagnostics.append(
{
"severity": "warning",
"code": "connectors.run.truncated",
"message": f"The run was limited to {limit} input rows.",
"stage": "planning",
"retryable": False,
}
)
errors = sum(1 for item in diagnostics if item["severity"] == "error")
if ambiguous_count:
status_value, review_state = {
"manual_review": ("manual_review", "pending"),
"quarantine": ("quarantined", "quarantined"),
"reject": ("rejected", "not_required"),
}[configuration.ambiguity_policy]
elif errors:
status_value, review_state = "invalid", "not_required"
else:
status_value, review_state = "ready", "not_required"
input_hash = _hash(bounded_rows)
summary = {
"total": len(effects),
"creates": sum(1 for item in effects if item["effect"] == "create"),
"updates": 0,
"deletes": 0,
"conflicts": sum(1 for item in effects if item["effect"] == "conflict"),
"unchanged": 0,
"ignored": sum(1 for item in effects if item["effect"] == "ignored"),
"ambiguous": ambiguous_count,
"errors": errors,
"truncated": truncated,
}
now = datetime.now(UTC)
provenance = {
"contract_version": "1.0",
"definition_id": configuration.definition_id,
"definition_revision": configuration.base_definition_revision,
"configuration_id": configuration.id,
"configuration_revision": configuration.resource_revision,
"configuration_hash": configuration.effective_hash,
"mapping_version": specification.mapping.version,
"input_hash": input_hash,
"external_revision": payload.external_revision,
"generated_at": now.isoformat(),
"actor_id": principal.user.id,
"mode": mode,
"provider": specification.provider,
"protocol": specification.protocol,
"privacy_classification": specification.privacy_classification,
"retention_class": specification.retention_class,
}
run = ConnectorSimulationRun(
tenant_id=principal.tenant_id,
configuration_id=configuration.id,
mode=mode,
idempotency_key=payload.idempotency_key,
request_hash=request_hash,
status=status_value,
review_state=review_state,
definition_revision=configuration.base_definition_revision,
configuration_revision=configuration.resource_revision,
configuration_hash=configuration.effective_hash,
input_hash=input_hash,
summary=summary,
effects=effects,
diagnostics=diagnostics,
provenance=provenance,
created_by=principal.user.id,
)
session.add(run)
session.flush()
audit_from_principal(
session,
principal,
action=f"connectors.configuration.{mode}_completed",
object_type="connector_simulation_run",
object_id=run.id,
details={
"configuration_id": configuration.id,
"configuration_revision": configuration.resource_revision,
"configuration_hash": configuration.effective_hash,
"definition_revision": configuration.base_definition_revision,
"input_hash": input_hash,
"status": status_value,
"review_state": review_state,
"summary": summary,
},
)
session.commit()
return run_item(run)
def list_runs(
session: Session,
*,
tenant_id: str,
configuration_id: str | None = None,
review_state: str | None = None,
limit: int = 100,
) -> list[ConnectorRunItem]:
query = session.query(ConnectorSimulationRun).filter(
ConnectorSimulationRun.tenant_id == tenant_id
)
if configuration_id:
query = query.filter(
ConnectorSimulationRun.configuration_id == configuration_id
)
if review_state:
query = query.filter(ConnectorSimulationRun.review_state == review_state)
rows = (
query.order_by(ConnectorSimulationRun.created_at.desc())
.limit(max(1, min(int(limit), 500)))
.all()
)
return [run_item(row) for row in rows]
def review_run(
session: Session,
principal: ApiPrincipal,
*,
run_id: str,
payload: ConnectorReviewRequest,
) -> ConnectorRunItem:
run = (
session.query(ConnectorSimulationRun)
.filter(
ConnectorSimulationRun.id == run_id,
ConnectorSimulationRun.tenant_id == principal.tenant_id,
)
.one_or_none()
)
if run is None:
raise GovernedConnectorError("run_not_found", "Connector run not found.")
if run.review_state not in {"pending", "quarantined"}:
raise GovernedConnectorError(
"run_not_reviewable",
"Only pending or quarantined connector results can be reviewed.",
)
run.review_state = payload.decision
run.status = f"review_{payload.decision}"
run.reviewed_by = principal.user.id
run.reviewed_at = datetime.now(UTC)
run.review_reason = payload.reason.strip()
audit_from_principal(
session,
principal,
action=f"connectors.simulation.{payload.decision}",
object_type="connector_simulation_run",
object_id=run.id,
details={
"configuration_id": run.configuration_id,
"input_hash": run.input_hash,
"configuration_hash": run.configuration_hash,
"decision": payload.decision,
"reason": run.review_reason,
},
)
session.commit()
return run_item(run)
def definition_item(
session: Session,
definition: ConnectorDefinition,
revision: ConnectorDefinitionRevision,
) -> ConnectorDefinitionItem:
del session
return ConnectorDefinitionItem(
id=definition.id,
tenant_id=definition.tenant_id,
definition_key=definition.definition_key,
name=definition.name,
description=definition.description,
status=definition.status,
current_revision=definition.current_revision,
source_package=definition.source_package,
local_definition=definition.local_definition,
revision_id=revision.id,
definition_hash=revision.definition_hash,
origin=revision.origin,
package_ref=revision.package_ref,
specification=GovernedConnectorSpecification.model_validate(
revision.specification
),
created_at=definition.created_at,
updated_at=definition.updated_at,
)
def configuration_item(
session: Session,
item: ConnectorConfiguration,
) -> ConnectorConfigurationItem:
definition = _tenant_definition(
session,
tenant_id=item.tenant_id,
definition_id=item.definition_id,
)
return ConnectorConfigurationItem(
id=item.id,
tenant_id=item.tenant_id,
definition_id=item.definition_id,
definition_key=definition.definition_key,
definition_name=definition.name,
name=item.name,
status=item.status,
endpoint_url=item.endpoint_url,
credential_ref=item.credential_ref,
base_definition_revision=item.base_definition_revision,
latest_definition_revision=definition.current_revision,
update_available=definition.current_revision > item.base_definition_revision,
local_overrides=dict(item.local_overrides or {}),
protected_paths=list(item.protected_paths or []),
effective_configuration=dict(item.effective_configuration or {}),
effective_hash=item.effective_hash,
resource_revision=item.resource_revision,
ambiguity_policy=item.ambiguity_policy,
updated_at=item.updated_at,
)
def run_item(run: ConnectorSimulationRun) -> ConnectorRunItem:
return ConnectorRunItem(
id=run.id,
tenant_id=run.tenant_id,
configuration_id=run.configuration_id,
mode=run.mode, # type: ignore[arg-type]
idempotency_key=run.idempotency_key,
status=run.status,
review_state=run.review_state,
definition_revision=run.definition_revision,
configuration_revision=run.configuration_revision,
configuration_hash=run.configuration_hash,
input_hash=run.input_hash,
summary=dict(run.summary or {}),
effects=list(run.effects or []),
diagnostics=list(run.diagnostics or []),
provenance=dict(run.provenance or {}),
reviewed_by=run.reviewed_by,
reviewed_at=run.reviewed_at,
review_reason=run.review_reason,
created_at=run.created_at,
)
def _simulate(
rows: Sequence[Mapping[str, Any]],
specification: GovernedConnectorSpecification,
) -> tuple[list[dict[str, Any]], list[dict[str, Any]], int]:
mapped_rows: list[dict[str, Any]] = []
row_errors: dict[int, list[dict[str, Any]]] = {}
diagnostics: list[dict[str, Any]] = []
for index, row in enumerate(rows):
mapped: dict[str, Any] = {}
for rule in specification.mapping.rules:
value, found = _path_value(row, rule.source)
if not found:
value = rule.default
if rule.required and value in (None, ""):
diagnostic = _diagnostic(
"error",
"connectors.mapping.required_source_missing",
f"Required source field {rule.source!r} is missing.",
"mapping",
index=index,
field=rule.source,
)
row_errors.setdefault(index, []).append(diagnostic)
diagnostics.append(diagnostic)
_set_path(mapped, rule.target, value)
mapped_rows.append(mapped)
ambiguous_indexes: set[int] = set()
for rule in specification.validation_rules:
if rule.kind == "unique":
seen: dict[str, list[int]] = {}
for index, row in enumerate(mapped_rows):
value, found = _path_value(row, rule.field)
if found and value not in (None, ""):
seen.setdefault(_stable_value(value), []).append(index)
for indexes in seen.values():
if len(indexes) > 1:
ambiguous_indexes.update(indexes)
for index in indexes:
diagnostic = _diagnostic(
rule.severity,
rule.code,
rule.message,
"validation",
index=index,
field=rule.field,
)
row_errors.setdefault(index, []).append(diagnostic)
diagnostics.append(diagnostic)
continue
for index, row in enumerate(mapped_rows):
value, found = _path_value(row, rule.field)
invalid = (
rule.kind == "required" and (not found or value in (None, ""))
) or (
rule.kind == "one_of" and found and value not in rule.values
)
if invalid:
diagnostic = _diagnostic(
rule.severity,
rule.code,
rule.message,
"validation",
index=index,
field=rule.field,
)
row_errors.setdefault(index, []).append(diagnostic)
diagnostics.append(diagnostic)
redacted = set(specification.dry_run.redacted_fields)
effects: list[dict[str, Any]] = []
for index, mapped in enumerate(mapped_rows):
errors = row_errors.get(index, [])
has_error = any(item["severity"] == "error" for item in errors)
effect = "conflict" if has_error or index in ambiguous_indexes else "create"
effects.append(
{
"effect": effect,
"source_object_ref": _source_ref(rows[index], index),
"target_object_ref": None,
"changed_fields": sorted(_leaf_paths(mapped)),
"sample": _redact_fields(mapped, redacted),
"reason_code": (
"ambiguous_external_result"
if index in ambiguous_indexes
else errors[0]["code"] if errors else None
),
"outcome": "preview",
"revision": specification.mapping.version,
}
)
return effects, diagnostics, len(ambiguous_indexes)
def _audit_configuration(
session: Session,
principal: ApiPrincipal,
item: ConnectorConfiguration,
*,
action: str,
extra: Mapping[str, Any] | None = None,
) -> None:
audit_from_principal(
session,
principal,
action=action,
object_type="connector_configuration",
object_id=item.id,
details={
"definition_id": item.definition_id,
"base_definition_revision": item.base_definition_revision,
"resource_revision": item.resource_revision,
"effective_hash": item.effective_hash,
"protected_paths": list(item.protected_paths or []),
"ambiguity_policy": item.ambiguity_policy,
"status": item.status,
"credential_reference_present": bool(item.credential_ref),
**dict(extra or {}),
},
)
def _tenant_definition(
session: Session,
*,
tenant_id: str,
definition_id: str,
) -> ConnectorDefinition:
item = (
session.query(ConnectorDefinition)
.filter(
ConnectorDefinition.id == definition_id,
ConnectorDefinition.tenant_id == tenant_id,
)
.one_or_none()
)
if item is None:
raise GovernedConnectorError(
"definition_not_found",
"Connector definition not found.",
)
return item
def _tenant_configuration(
session: Session,
*,
tenant_id: str,
configuration_id: str,
) -> ConnectorConfiguration:
item = (
session.query(ConnectorConfiguration)
.filter(
ConnectorConfiguration.id == configuration_id,
ConnectorConfiguration.tenant_id == tenant_id,
)
.one_or_none()
)
if item is None:
raise GovernedConnectorError(
"configuration_not_found",
"Connector configuration not found.",
)
return item
def _definition_revision(
session: Session,
definition: ConnectorDefinition,
revision: int,
) -> ConnectorDefinitionRevision:
item = (
session.query(ConnectorDefinitionRevision)
.filter(
ConnectorDefinitionRevision.definition_id == definition.id,
ConnectorDefinitionRevision.revision == revision,
)
.one_or_none()
)
if item is None:
raise GovernedConnectorError(
"definition_revision_not_found",
"Connector definition revision not found.",
)
return item
def _effective_specification(
base: Mapping[str, Any],
overrides: Mapping[str, Any],
) -> dict[str, Any]:
merged = _deep_merge(base, overrides)
return GovernedConnectorSpecification.model_validate(merged).model_dump(mode="json")
def _deep_merge(
base: Mapping[str, Any],
overrides: Mapping[str, Any],
) -> dict[str, Any]:
result = copy.deepcopy(dict(base))
for key, value in overrides.items():
if isinstance(value, Mapping) and isinstance(result.get(key), Mapping):
result[key] = _deep_merge(result[key], value) # type: ignore[arg-type]
else:
result[key] = copy.deepcopy(value)
return result
def _protected_paths(value: Mapping[str, Any], prefix: str = "") -> list[str]:
paths: list[str] = []
for key in sorted(value):
path = f"{prefix}.{key}" if prefix else str(key)
item = value[key]
if isinstance(item, Mapping) and item:
paths.extend(_protected_paths(item, path))
else:
paths.append(path)
return paths
def _leaf_paths(value: Mapping[str, Any], prefix: str = "") -> set[str]:
paths: set[str] = set()
for key, item in value.items():
path = f"{prefix}.{key}" if prefix else str(key)
if isinstance(item, Mapping) and item:
paths.update(_leaf_paths(item, path))
else:
paths.add(path)
return paths
def _path_value(value: Mapping[str, Any], path: str) -> tuple[Any, bool]:
current: Any = value
for part in path.split("."):
if not isinstance(current, Mapping) or part not in current:
return None, False
current = current[part]
return current, True
def _set_path(target: dict[str, Any], path: str, value: Any) -> None:
parts = path.split(".")
current = target
for part in parts[:-1]:
nested = current.get(part)
if not isinstance(nested, dict):
nested = {}
current[part] = nested
current = nested
current[parts[-1]] = value
def _source_ref(row: Mapping[str, Any], index: int) -> str:
for key in ("id", "external_id", "source_id"):
value = row.get(key)
if value not in (None, ""):
return f"sample:{value}"
return f"sample:row:{index + 1}"
def _redact_fields(value: Mapping[str, Any], fields: set[str]) -> dict[str, Any]:
result = copy.deepcopy(dict(value))
for path in fields:
parts = path.split(".")
current: Any = result
for part in parts[:-1]:
if not isinstance(current, dict):
break
current = current.get(part)
else:
if isinstance(current, dict) and parts[-1] in current:
current[parts[-1]] = "<redacted>"
return result
def _diagnostic(
severity: str,
code: str,
message: str,
stage: str,
**details: Any,
) -> dict[str, Any]:
return {
"severity": severity,
"code": code,
"message": message,
"stage": stage,
"retryable": False,
"details": details,
}
def _validate_endpoint(
endpoint_url: str | None,
credential_ref: str | None,
) -> None:
if endpoint_url:
try:
ConnectorEndpoint(
url=endpoint_url,
credential_ref=_optional_text(credential_ref),
)
except ConnectorContractError as exc:
raise GovernedConnectorError("invalid_endpoint", str(exc)) from exc
elif credential_ref:
raise GovernedConnectorError(
"credential_without_endpoint",
"A credential reference requires a configured endpoint.",
)
def _stable_value(value: Any) -> str:
return json.dumps(value, sort_keys=True, separators=(",", ":"), default=str)
def _hash(value: Any) -> str:
return hashlib.sha256(
json.dumps(value, sort_keys=True, separators=(",", ":"), default=str).encode()
).hexdigest()
def _optional_text(value: object | None) -> str | None:
normalized = str(value or "").strip()
return normalized or None
__all__ = [
"GovernedConnectorError",
"configuration_item",
"create_configuration",
"execute_run",
"list_configurations",
"list_definitions",
"list_runs",
"review_run",
"run_item",
"update_configuration",
"upsert_definition",
]
@@ -0,0 +1,221 @@
from __future__ import annotations
from datetime import datetime
from typing import Any, Literal
from pydantic import BaseModel, ConfigDict, Field, model_validator
class ConnectorMappingRule(BaseModel):
model_config = ConfigDict(extra="forbid")
source: str = Field(min_length=1, max_length=255)
target: str = Field(min_length=1, max_length=255)
required: bool = False
default: Any = None
class ConnectorMappingDefinition(BaseModel):
model_config = ConfigDict(extra="forbid")
version: str = Field(min_length=1, max_length=100)
rules: list[ConnectorMappingRule] = Field(default_factory=list, max_length=500)
class ConnectorValidationRule(BaseModel):
model_config = ConfigDict(extra="forbid")
kind: Literal["required", "one_of", "unique"]
field: str = Field(min_length=1, max_length=255)
values: list[Any] = Field(default_factory=list, max_length=500)
severity: Literal["warning", "error"] = "error"
code: str = Field(min_length=1, max_length=120)
message: str = Field(min_length=1, max_length=500)
@model_validator(mode="after")
def validate_values(self) -> "ConnectorValidationRule":
if self.kind == "one_of" and not self.values:
raise ValueError("one_of validation requires allowed values")
if self.kind != "one_of" and self.values:
raise ValueError("Only one_of validation accepts values")
return self
class ConnectorDryRunMetadata(BaseModel):
model_config = ConfigDict(extra="forbid")
supported: bool = True
simulation_supported: bool = True
sample_rows: list[dict[str, Any]] = Field(default_factory=list, max_length=500)
max_items: int = Field(default=500, ge=1, le=10_000)
redacted_fields: list[str] = Field(default_factory=list, max_length=100)
class ConnectorAuditMetadata(BaseModel):
model_config = ConfigDict(extra="forbid")
event_prefix: str = Field(min_length=1, max_length=120)
expected_events: list[str] = Field(default_factory=list, max_length=100)
evidence_fields: list[str] = Field(default_factory=list, max_length=100)
class GovernedConnectorSpecification(BaseModel):
model_config = ConfigDict(extra="forbid")
provider: str = Field(min_length=1, max_length=120)
protocol: str = Field(min_length=1, max_length=80)
capabilities: list[str] = Field(min_length=1, max_length=100)
input_schema: dict[str, Any]
output_schema: dict[str, Any]
mapping: ConnectorMappingDefinition
validation_rules: list[ConnectorValidationRule] = Field(
default_factory=list,
max_length=500,
)
dry_run: ConnectorDryRunMetadata
audit: ConnectorAuditMetadata
privacy_classification: Literal[
"public",
"internal",
"confidential",
"restricted",
] = "internal"
retention_class: str = Field(min_length=1, max_length=120)
operational_limits: dict[str, Any] = Field(default_factory=dict)
retry_policy: dict[str, Any] = Field(default_factory=dict)
class ConnectorDefinitionUpsertRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
definition_key: str = Field(pattern=r"^[a-z0-9][a-z0-9._-]{0,159}$")
name: str = Field(min_length=1, max_length=300)
description: str | None = Field(default=None, max_length=4000)
origin: Literal["package", "local"] = "local"
package_ref: str | None = Field(default=None, max_length=300)
specification: GovernedConnectorSpecification
@model_validator(mode="after")
def package_provenance(self) -> "ConnectorDefinitionUpsertRequest":
if self.origin == "package" and not self.package_ref:
raise ValueError("Package definitions require package_ref")
if self.origin == "local" and self.package_ref:
raise ValueError("Local definitions cannot claim package_ref")
return self
class ConnectorDefinitionItem(BaseModel):
id: str
tenant_id: str
definition_key: str
name: str
description: str | None = None
status: str
current_revision: int
source_package: str | None = None
local_definition: bool
revision_id: str
definition_hash: str
origin: str
package_ref: str | None = None
specification: GovernedConnectorSpecification
created_at: datetime
updated_at: datetime
class ConnectorDefinitionListResponse(BaseModel):
items: list[ConnectorDefinitionItem]
class ConnectorConfigurationCreateRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
definition_id: str = Field(min_length=1, max_length=36)
name: str = Field(min_length=1, max_length=300)
endpoint_url: str | None = Field(default=None, max_length=1500)
credential_ref: str | None = Field(default=None, max_length=500)
local_overrides: dict[str, Any] = Field(default_factory=dict)
ambiguity_policy: Literal["manual_review", "quarantine", "reject"] = (
"manual_review"
)
status: Literal["draft", "active", "disabled"] = "draft"
class ConnectorConfigurationUpdateRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
expected_revision: int = Field(ge=1)
name: str | None = Field(default=None, min_length=1, max_length=300)
endpoint_url: str | None = Field(default=None, max_length=1500)
credential_ref: str | None = Field(default=None, max_length=500)
local_overrides: dict[str, Any] | None = None
ambiguity_policy: Literal["manual_review", "quarantine", "reject"] | None = None
status: Literal["draft", "active", "disabled"] | None = None
adopt_latest_definition: bool = False
class ConnectorConfigurationItem(BaseModel):
id: str
tenant_id: str
definition_id: str
definition_key: str
definition_name: str
name: str
status: str
endpoint_url: str | None = None
credential_ref: str | None = None
base_definition_revision: int
latest_definition_revision: int
update_available: bool
local_overrides: dict[str, Any]
protected_paths: list[str]
effective_configuration: dict[str, Any]
effective_hash: str
resource_revision: int
ambiguity_policy: str
updated_at: datetime
class ConnectorConfigurationListResponse(BaseModel):
items: list[ConnectorConfigurationItem]
class ConnectorRunRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
idempotency_key: str = Field(min_length=1, max_length=255)
input_rows: list[dict[str, Any]] | None = Field(default=None, max_length=500)
external_revision: str | None = Field(default=None, max_length=255)
class ConnectorRunItem(BaseModel):
id: str
tenant_id: str
configuration_id: str
mode: Literal["dry_run", "simulation"]
idempotency_key: str
status: str
review_state: str
definition_revision: int
configuration_revision: int
configuration_hash: str
input_hash: str
summary: dict[str, Any]
effects: list[dict[str, Any]]
diagnostics: list[dict[str, Any]]
provenance: dict[str, Any]
reviewed_by: str | None = None
reviewed_at: datetime | None = None
review_reason: str | None = None
created_at: datetime
class ConnectorRunListResponse(BaseModel):
items: list[ConnectorRunItem]
class ConnectorReviewRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
decision: Literal["approved", "rejected"]
reason: str = Field(min_length=5, max_length=1000)
+753
View File
@@ -0,0 +1,753 @@
from __future__ import annotations
from pathlib import Path
from govoplan_core.core.access import (
CAPABILITY_AUTH_PERMISSION_EVALUATOR,
CAPABILITY_AUTH_PRINCIPAL_RESOLVER,
)
from govoplan_core.core.module_guards import (
drop_table_retirement_provider,
persistent_table_uninstall_guard,
)
from govoplan_core.core.datasources import CAPABILITY_DATASOURCE_ORIGINS
from govoplan_core.core.feeds import CAPABILITY_CONNECTORS_FEEDS
from govoplan_core.core.modules import (
CapabilityDocumentation,
DocumentationTopic,
FrontendModule,
MigrationSpec,
ModuleInterfaceProvider,
ModuleInterfaceRequirement,
ModuleManifest,
PermissionDefinition,
RoleTemplate,
ViewSurface,
)
from govoplan_core.core.provider_governance import (
ExternalProviderDeclaration,
ExternalProviderStateProviderRegistration,
ModuleArchitectureDeclaration,
ModuleArchitectureDocumentation,
ModuleMaturityEvidence,
ProviderBehaviorDeclaration,
ProviderObjectDeclaration,
)
from govoplan_core.core.tabular_sources import (
CAPABILITY_CONNECTORS_TABULAR_SNAPSHOT_WRITER,
CAPABILITY_CONNECTORS_TABULAR_SOURCES,
)
from govoplan_core.core.files import CAPABILITY_FILES_TABULAR_CONTENT
from govoplan_core.core.sanctions import (
CAPABILITY_CONNECTORS_SANCTIONS_SNAPSHOTS,
)
from govoplan_core.db.base import Base
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorDefinitionRevision,
ConnectorSanctionsAcquisitionRun,
ConnectorSanctionsSnapshot,
ConnectorSimulationRun,
ConnectorTabularSource,
)
from govoplan_connectors.backend.dsar_provider import (
CONNECTORS_DSAR_CAPABILITY,
ConnectorsDsarProvider,
)
from govoplan_connectors.backend.sanctions_sources import (
SANCTIONS_READ_SCOPE,
SANCTIONS_REFRESH_SCOPE,
SqlSanctionsSnapshotProvider,
)
from govoplan_connectors.backend.tabular_sources import (
ADMIN_SCOPE,
READ_SCOPE,
WRITE_SCOPE,
SqlTabularSourceProvider,
)
from govoplan_connectors.backend.datasource_origins import (
ConnectorDatasourceOriginProvider,
)
from govoplan_connectors.backend.feeds import (
FEED_PRIVATE_PUBLISH_SCOPE,
FEED_PUBLISH_SCOPE,
ConnectorFeedProvider,
)
from govoplan_connectors.backend.provider_state import (
SANCTIONS_PROVIDER_ID,
TABULAR_PROVIDER_ID,
sanctions_provider_states,
tabular_provider_states,
)
MODULE_ID = "connectors"
MODULE_VERSION = "0.1.20"
TABULAR_SOURCE_INTERFACE_VERSION = "0.1.0"
DATASOURCE_ORIGIN_INTERFACE_VERSION = "0.1.0"
SANCTIONS_SNAPSHOT_INTERFACE_VERSION = "1.0.0"
FEED_INTERFACE_VERSION = "0.2.0"
CONNECTOR_RUNTIME_INTERFACE_VERSION = "1.0.0"
ARCHITECTURE = ModuleArchitectureDeclaration(
layer="data_reporting_integration",
kind="integration",
maturity="vertical_slice",
evidence=(
ModuleMaturityEvidence(
kind="test",
reference="tests/test_tabular_sources.py",
summary="Exercises tenant-safe immutable tabular snapshots and bounded reads.",
),
ModuleMaturityEvidence(
kind="test",
reference="tests/test_tabular_origin_provider.py",
summary="Exercises exact managed-file versions, reviewed refresh, live SQL projection, configuration drift, and tenant isolation.",
),
ModuleMaturityEvidence(
kind="test",
reference="tests/test_tabular_adapters.py",
summary="Exercises bounded CSV/XLSX parsing and the credential-governed read-only PostgreSQL adapter.",
),
ModuleMaturityEvidence(
kind="test",
reference="tests/test_sanctions_sources.py",
summary="Exercises source acquisition health, checksums, retries, and immutable evidence.",
),
ModuleMaturityEvidence(
kind="recovery",
reference="tests/test_recovery.py",
summary="Proves atomic snapshot commits, idempotent replay, distributed fences, tamper rejection, and unknown external-effect handling.",
),
ModuleMaturityEvidence(
kind="test",
reference="tests/test_governed_runtime.py",
summary="Exercises immutable definition revisions, protected local overrides, idempotent simulations, and explicit ambiguity review.",
),
ModuleMaturityEvidence(
kind="documentation",
reference="docs/CONNECTOR_SOURCE_LIFECYCLE.md",
summary="Defines source lifecycle, authority, evidence, and outage boundaries.",
),
),
known_limits=(
"Tabular origins support immutable snapshots, exact managed CSV/XLSX versions, and read-only PostgreSQL tables; arbitrary REST and other database adapters remain future providers.",
"Feed publication renders a governed document but does not yet push it to an external publishing endpoint.",
"The generic governed runtime simulates deterministic mapping and validation; provider-specific live writes remain owned by explicit connector adapters.",
),
supported_authority_modes=(
"external_authoritative",
"external_mirror",
"linked_reference",
),
owned_concepts=(
"external transport profiles",
"protocol interaction",
"immutable connector snapshots",
"connector acquisition health",
),
non_owned_concepts=(
"datasource catalogue identity and lifecycle",
"domain records and business semantics",
"data transformations",
"screening dispositions",
),
target_tested_providers=(
TABULAR_PROVIDER_ID,
SANCTIONS_PROVIDER_ID,
),
documentation=ModuleArchitectureDocumentation(
migration=("src/govoplan_connectors/backend/migrations/versions",),
upgrade=("docs/CONNECTOR_SOURCE_LIFECYCLE.md",),
recovery=("docs/CONNECTOR_SOURCE_LIFECYCLE.md",),
security=("docs/CONNECTOR_SOURCE_LIFECYCLE.md",),
operations=("docs/CONNECTOR_SOURCE_LIFECYCLE.md",),
),
)
EXTERNAL_PROVIDERS = (
ExternalProviderDeclaration(
id=TABULAR_PROVIDER_ID,
module_id=MODULE_ID,
label="Governed tabular source providers",
maturity="read",
operations=("discover", "search", "read", "preview", "dry_run"),
objects=(
ProviderObjectDeclaration(
object_type="tabular_source_snapshot",
field_groups=("identity", "schema", "rows", "source_provenance"),
authority_modes=("external_authoritative", "external_mirror"),
default_authority_mode="external_mirror",
),
),
behavior=ProviderBehaviorDeclaration(
revision_tokens="Source fingerprints, exact file versions, SQL configuration revisions, credential revisions, and discovery revisions are retained.",
concurrency="Reads may require the expected fingerprint; file versions remain pinned and SQL configuration or schema drift blocks reads until reviewed refresh.",
freshness="Snapshot acquisition time, exact/current file versions, and live SQL discovery health are exposed.",
health="Import validation, Files access/integrity, SQL authentication, configuration drift, schema drift, timeouts, and source unavailability are explicit without exposing secrets.",
max_read_items=1000,
idempotency="Feed imports accept a caller request key and replay the same committed immutable source without refetching.",
retry="Read-only acquisition may be retried only as a new deliberate request after a failed atomic operation.",
outcome_unknown="Provider reads do not mutate remote state; an uncertain database commit is resolved by the atomic recovery transaction.",
outcome_unknown_supported=False,
evidence="Rows, schema, fingerprint, source metadata, and acquisition provenance remain linked.",
correction="Import a replacement snapshot; retain the prior snapshot as evidence.",
rollback="Snapshot rows and the terminal recovery checkpoint commit or roll back together.",
reconciliation="Compare source and snapshot fingerprints before selecting a new current state.",
outage="Existing snapshots remain available and visibly stale; no live-source claim is made.",
classifications=("internal", "confidential", "restricted"),
purposes=("governed import", "dataflow input", "evidence reconstruction"),
retention="Datasources or the consuming domain supplies retention and hold policy.",
secret_handling="Snapshots and managed-file sources contain no connector credential; PostgreSQL uses a scoped Core credential-envelope reference and never stores or returns the resolved secret.",
),
capability_names=(
CAPABILITY_CONNECTORS_TABULAR_SOURCES,
CAPABILITY_DATASOURCE_ORIGINS,
),
interface_names=(
"connectors.tabular_sources",
"connectors.datasource_origins",
),
documentation_topic_ids=(
"connectors.authority-and-effects",
"connectors.tabular-sources",
),
),
ExternalProviderDeclaration(
id=SANCTIONS_PROVIDER_ID,
module_id=MODULE_ID,
label="Sanctions source snapshot provider",
maturity="read",
operations=("discover", "search", "read", "preview"),
objects=(
ProviderObjectDeclaration(
object_type="sanctions_source_snapshot",
field_groups=(
"source_identity",
"raw_evidence",
"entries",
"acquisition_health",
),
authority_modes=("external_authoritative", "external_mirror"),
default_authority_mode="external_mirror",
),
),
behavior=ProviderBehaviorDeclaration(
revision_tokens="Provider source version, ETag, Last-Modified, and SHA-256 digest are retained when available.",
concurrency="Refreshes use conditional source requests, a distributed per-tenant/provider fence, and immutable snapshots.",
freshness="Latest successful acquisition, source timestamp, and stale health are reported.",
health="Transport, parsing, source-change, and malformed-source states are explicit.",
max_read_items=5000,
idempotency="A caller request key identifies one acquisition run and replays its committed result without contacting the source again.",
retry="Bounded HTTP retries are safe because acquisition is read-only; failed runs require a new deliberate request key.",
timeout_seconds=30,
outcome_unknown="The external operation is read-only; snapshot rows and recovery evidence commit atomically.",
outcome_unknown_supported=False,
evidence="Raw source bytes, checksum, acquisition run, parser result, and normalized entry count are linked.",
correction="A corrected source creates a new immutable snapshot and acquisition run.",
rollback="A failed database transaction leaves no snapshot and the stale atomic fence resolves as failed.",
reconciliation="Compare source version and digest, then preserve both prior and corrected evidence.",
outage="The latest accepted snapshot stays usable with stale/unavailable source health.",
classifications=("public", "internal"),
purposes=("sanctions source acquisition", "compliance screening evidence"),
retention="Risk and Records policies determine accepted snapshot retention and legal holds.",
secret_handling="Public sources require no subject data or source credential; configured proxy secrets remain external to snapshots.",
),
capability_names=(CAPABILITY_CONNECTORS_SANCTIONS_SNAPSHOTS,),
interface_names=("connectors.sanctions_snapshots",),
documentation_topic_ids=(
"connectors.authority-and-effects",
"connectors.sanctions-snapshots",
),
),
)
def _permission(scope: str, label: str, description: str) -> PermissionDefinition:
module_id, resource, action = scope.split(":", 2)
return PermissionDefinition(
scope=scope,
label=label,
description=description,
category="Connectors",
level="tenant",
module_id=module_id,
resource=resource,
action=action,
)
PERMISSIONS = (
_permission(
READ_SCOPE,
"View tabular sources",
"Discover and preview policy-visible tabular connector sources.",
),
_permission(
WRITE_SCOPE,
"Manage tabular sources",
"Import and retire bounded tabular snapshots.",
),
_permission(
ADMIN_SCOPE,
"Administer connector sources",
"Manage tenant connector sources, versioned definitions, protected overrides, and review policies.",
),
_permission(
FEED_PUBLISH_SCOPE,
"Publish public feeds",
"Render provenance-bearing public RSS or Atom output from selected GovOPlaN objects.",
),
_permission(
FEED_PRIVATE_PUBLISH_SCOPE,
"Publish restricted feeds",
"Render tenant or private RSS or Atom output after the owning product surface has authorized every selected object.",
),
_permission(
SANCTIONS_READ_SCOPE,
"View sanctions source evidence",
"Inspect immutable sanctions snapshots and acquisition health.",
),
_permission(
SANCTIONS_REFRESH_SCOPE,
"Refresh sanctions sources",
"Acquire a new immutable sanctions source snapshot.",
),
)
ROLE_TEMPLATES = (
RoleTemplate(
slug="connector_administrator",
name="Connector administrator",
description="Govern connector definitions, local configurations, simulations, and manual review.",
permissions=(
READ_SCOPE,
WRITE_SCOPE,
ADMIN_SCOPE,
FEED_PUBLISH_SCOPE,
FEED_PRIVATE_PUBLISH_SCOPE,
SANCTIONS_READ_SCOPE,
SANCTIONS_REFRESH_SCOPE,
),
),
RoleTemplate(
slug="connector_source_manager",
name="Connector source manager",
description="Discover, import, preview, and retire tabular sources.",
permissions=(
READ_SCOPE,
WRITE_SCOPE,
FEED_PUBLISH_SCOPE,
SANCTIONS_READ_SCOPE,
SANCTIONS_REFRESH_SCOPE,
),
),
RoleTemplate(
slug="connector_source_reader",
name="Connector source reader",
description="Discover and preview tabular connector sources.",
permissions=(READ_SCOPE, SANCTIONS_READ_SCOPE),
),
)
def _router(_context):
from govoplan_connectors.backend.router import router
return router
def _provider(_context) -> SqlTabularSourceProvider:
return SqlTabularSourceProvider(registry=getattr(_context, "registry", None))
def _datasource_origin_provider(_context) -> ConnectorDatasourceOriginProvider:
return ConnectorDatasourceOriginProvider(
SqlTabularSourceProvider(registry=getattr(_context, "registry", None))
)
def _sanctions_snapshot_provider(
_context,
) -> SqlSanctionsSnapshotProvider:
return SqlSanctionsSnapshotProvider()
def _feed_provider(_context) -> ConnectorFeedProvider:
return ConnectorFeedProvider()
def _dsar_provider(_context) -> ConnectorsDsarProvider:
return ConnectorsDsarProvider()
def _tenant_summary(session, tenant_id: str) -> dict[str, int]:
return {
"connector_definitions": (
session.query(ConnectorDefinition)
.filter(ConnectorDefinition.tenant_id == tenant_id)
.count()
),
"connector_configurations": (
session.query(ConnectorConfiguration)
.filter(ConnectorConfiguration.tenant_id == tenant_id)
.count()
),
"connector_simulation_runs": (
session.query(ConnectorSimulationRun)
.filter(ConnectorSimulationRun.tenant_id == tenant_id)
.count()
),
"connector_tabular_sources": (
session.query(ConnectorTabularSource)
.filter(
ConnectorTabularSource.tenant_id == tenant_id,
ConnectorTabularSource.deleted_at.is_(None),
)
.count()
),
"connector_sanctions_snapshots": (
session.query(ConnectorSanctionsSnapshot)
.filter(ConnectorSanctionsSnapshot.tenant_id == tenant_id)
.count()
),
"connector_sanctions_runs": (
session.query(ConnectorSanctionsAcquisitionRun)
.filter(ConnectorSanctionsAcquisitionRun.tenant_id == tenant_id)
.count()
),
}
manifest = ModuleManifest(
id=MODULE_ID,
name="Connectors",
version=MODULE_VERSION,
optional_dependencies=(
"access",
"audit",
"files",
"policy",
"datasources",
"portal",
"reporting",
"risk_compliance",
),
required_capabilities=(
CAPABILITY_AUTH_PRINCIPAL_RESOLVER,
CAPABILITY_AUTH_PERMISSION_EVALUATOR,
),
provides_interfaces=(
ModuleInterfaceProvider(
name="connectors.tabular_sources",
version=TABULAR_SOURCE_INTERFACE_VERSION,
),
ModuleInterfaceProvider(
name="connectors.tabular_snapshot_writer",
version=TABULAR_SOURCE_INTERFACE_VERSION,
),
ModuleInterfaceProvider(
name="connectors.datasource_origins",
version=DATASOURCE_ORIGIN_INTERFACE_VERSION,
),
ModuleInterfaceProvider(
name="connectors.sanctions_snapshots",
version=SANCTIONS_SNAPSHOT_INTERFACE_VERSION,
),
ModuleInterfaceProvider(
name="connectors.feeds",
version=FEED_INTERFACE_VERSION,
),
ModuleInterfaceProvider(
name="connectors.runtime_contract",
version=CONNECTOR_RUNTIME_INTERFACE_VERSION,
),
ModuleInterfaceProvider(name=CONNECTORS_DSAR_CAPABILITY, version="0.1.0"),
),
requires_interfaces=(
ModuleInterfaceRequirement(
name=CAPABILITY_FILES_TABULAR_CONTENT,
version_min="1.0.0",
version_max_exclusive="2.0.0",
optional=True,
),
),
permissions=PERMISSIONS,
role_templates=ROLE_TEMPLATES,
route_factory=_router,
frontend=FrontendModule(
module_id=MODULE_ID,
package_name="@govoplan/connectors-webui",
view_surfaces=(
ViewSurface(
id="connectors.admin.governed-configurations",
module_id=MODULE_ID,
kind="section",
label="Connector governance",
order=45,
),
ViewSurface(
id="connectors.admin.simulation-review",
module_id=MODULE_ID,
kind="section",
label="Connector simulation review",
parent_id="connectors.admin.governed-configurations",
order=20,
),
),
),
capability_factories={
CAPABILITY_CONNECTORS_TABULAR_SOURCES: _provider,
CAPABILITY_CONNECTORS_TABULAR_SNAPSHOT_WRITER: _provider,
CAPABILITY_DATASOURCE_ORIGINS: _datasource_origin_provider,
CAPABILITY_CONNECTORS_SANCTIONS_SNAPSHOTS: (_sanctions_snapshot_provider),
CAPABILITY_CONNECTORS_FEEDS: _feed_provider,
CONNECTORS_DSAR_CAPABILITY: _dsar_provider,
},
capability_documentation={
CONNECTORS_DSAR_CAPABILITY: CapabilityDocumentation(
label="Connector data-subject request provider",
summary=(
"Exports minimized operator attribution without connector secrets, "
"external payloads, or transport evidence."
),
contract_version="0.1.0",
),
},
tenant_summary_providers=(_tenant_summary,),
architecture=ARCHITECTURE,
external_providers=EXTERNAL_PROVIDERS,
external_provider_state_providers=(
ExternalProviderStateProviderRegistration(
module_id=MODULE_ID,
provider_id=TABULAR_PROVIDER_ID,
provider=tabular_provider_states,
),
ExternalProviderStateProviderRegistration(
module_id=MODULE_ID,
provider_id=SANCTIONS_PROVIDER_ID,
provider=sanctions_provider_states,
),
),
migration_spec=MigrationSpec(
module_id=MODULE_ID,
metadata=Base.metadata,
script_location=str(Path(__file__).with_name("migrations") / "versions"),
retirement_supported=True,
retirement_provider=drop_table_retirement_provider(
ConnectorSimulationRun,
ConnectorConfiguration,
ConnectorDefinitionRevision,
ConnectorDefinition,
ConnectorSanctionsSnapshot,
ConnectorSanctionsAcquisitionRun,
ConnectorTabularSource,
label="Connectors",
),
retirement_notes=(
"Destructive retirement drops connector-owned source snapshots after "
"the installer captures a database snapshot."
),
),
uninstall_guard_providers=(
persistent_table_uninstall_guard(
ConnectorSimulationRun,
ConnectorConfiguration,
ConnectorDefinitionRevision,
ConnectorDefinition,
ConnectorSanctionsSnapshot,
ConnectorSanctionsAcquisitionRun,
ConnectorTabularSource,
label="Connectors",
),
),
documentation=(
DocumentationTopic(
id="connectors.data-subject-requests",
title="Connector data-subject requests",
summary=(
"Export accountable connector activity without disclosing credentials "
"or external data."
),
body=(
"Connectors correlates only an exact tenant account identifier and can "
"narrow an already verified search to one source, acquisition, "
"definition, configuration, or simulation. The export identifies the "
"subject's configuration, acquisition, simulation, and review activity "
"using bounded lifecycle metadata. It never includes credential or "
"endpoint references, source rows, external responses, request payloads, "
"mapping and configuration documents, diagnostics, provenance, hashes, "
"or transport evidence. Connector attribution remains immutable "
"governance and external-operation evidence and is retained rather than "
"automatically erased. Email or object identifiers without a verified "
"account identifier do not establish a match."
),
layer="configured",
documentation_types=("admin", "user"),
audience=("user", "operator", "module_admin", "auditor"),
related_modules=("core", "access", "audit", "policy"),
order=37,
metadata={
"help_contexts": ["privacy.data-subject-requests"],
"consequence_classes": {
"export_operator_attribution": (
"Returns minimized connector activity for the exact account."
),
"exclude_connector_secrets": (
"Never returns credentials, endpoints, external rows, or evidence payloads."
),
"retain_connector_evidence": (
"Preserves configuration and external-operation accountability."
),
},
},
),
DocumentationTopic(
id="connectors.governed-configuration",
title="Govern connector definitions and simulations",
summary="Version connector schemas and mappings while preserving tenant-local overrides and review evidence.",
body=(
"Connector administrators create package-managed or local definitions that explicitly declare provider, protocol, capabilities, schemas, mapping rules, validation, preview support, audit expectations, privacy, retention, limits, and retry metadata. Every definition change creates an immutable revision. A tenant configuration pins one revision and stores only a credential reference; package updates remain available but do not change the effective configuration until an administrator adopts them. Local override leaf paths are displayed as protected and are reapplied when an update is adopted. Dry-runs and simulations are bounded, redact configured fields, are idempotent by caller key, and retain configuration, mapping, input, and external revision provenance. Ambiguous results follow the configuration policy: manual review, quarantine, or rejection. Pending and quarantined evidence requires an explicit approve or reject decision with a reason. Provider-specific live writes are not implied by a successful generic simulation."
),
layer="configured",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "integration_admin"),
related_modules=("policy", "audit", "dataflow", "ops"),
order=38,
metadata={
"kind": "guide",
"help_contexts": ["connectors.admin.governed-configurations"],
"prerequisites": [
"A connector definition has been installed or authored.",
"Credential material is stored outside the connector URL and referenced by an approved secret identifier.",
],
"outcome": "The active connector behavior is inspectable, version-pinned, testable, and reviewable before any provider-specific write.",
"verification": "Reload the configuration, inspect protected paths and effective hash, run a simulation with a new idempotency key, and resolve any pending review result.",
},
),
DocumentationTopic(
id="connectors.authority-and-effects",
title="Connector authority and effect behavior",
summary="Connector direction, technical maturity, and configured source authority are separate and must remain visible.",
body=(
"A connector can consume, publish, or work bidirectionally and can mature from discovery through replacement. "
"Each binding separately states whether GovOPlaN is authoritative, follows an external authority, keeps a mirror, synchronizes under conflict rules, adds a governance overlay, or retains only a link. "
"Writable providers must explain revisions, limits, idempotency, outcome-unknown handling, evidence, reconciliation, correction, outage behavior, and secret requirements."
),
layer="available",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "power_user", "product_owner"),
related_modules=("datasources", "dataflow", "ops", "policy", "audit"),
order=39,
),
DocumentationTopic(
id="connectors.runtime-preview-contract",
title="Connector previews and diagnostics",
summary="Use one bounded, redacted dry-run shape across external transports.",
body=(
"Connectors owns endpoint discovery, authentication hand-off, transport limits, retries, and protocol health. "
"Domain modules own field mapping, validation, reconciliation, and record mutation. The shared Core runtime "
"contract reports redacted effects and diagnostics with source revisions, fingerprints, and immutable input hashes. "
"Tabular previews enforce effective row, serialized-byte, and elapsed-time ceilings and report limit truncation "
"as structured diagnostics. A commit must reject stale, truncated, conflicting, or error-bearing previews, and "
"credentials never appear in URLs or samples."
),
layer="available",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "power_user"),
related_modules=("addresses", "datasources", "dataflow", "policy", "audit"),
order=40,
),
DocumentationTopic(
id="connectors.tabular-sources",
title="Governed tabular sources",
summary="Provider-neutral source discovery and bounded reads for Dataflow.",
body=(
"Connectors owns source configuration, access checks, schema discovery, "
"fingerprints, and bounded reads. Dataflow stores only opaque source "
"references and expected fingerprints. Each source declares its live, "
"cached, file-backed, or static mode, structured health, and supported "
"projection, filter, aggregation, sorting, and pagination pushdown. "
"Immutable JSON/CSV snapshots remain available. Managed CSV/XLSX "
"sources use the optional Files capability, pin an exact authorized "
"version, apply archive and expansion limits, and require explicit "
"refresh before adopting a newer version. The PostgreSQL adapter uses "
"an active governed configuration and scoped Core credential envelope, "
"reflects simple schema/table identifiers, runs read-only bounded "
"projection and pagination, and blocks configuration, credential, or "
"schema drift until reviewed refresh. Credentials, endpoints, storage "
"keys, and raw file internals are never exposed through the origin."
),
layer="available",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "power_user"),
related_modules=("dataflow", "files", "reporting", "risk_compliance"),
order=40,
),
DocumentationTopic(
id="connectors.rss-atom",
title="RSS and Atom feeds",
summary="Import governed feed snapshots and emit visibility-filtered feeds.",
body=(
"Connectors owns bounded, SSRF-protected RSS/Atom transport and XML "
"parsing. Imported entries become immutable tabular snapshots exposed "
"through Datasources, including acquisition, freshness, ETag, content "
"digest, and source provenance. Emission accepts only provenance-bearing "
"event, publication, case, or report selections from an owning surface. "
"The requested audience determines the visibility ceiling: public output "
"contains only public entries, while tenant or private output requires a "
"separate restricted-feed permission. Callers cannot supply their own "
"visibility allow-list. Portal or Reporting owns durable publication "
"routes and must re-authorize access on every restricted feed request. "
"A separate RSS module is only warranted if GovOPlaN later needs a "
"dedicated feed-reader product surface."
),
layer="available",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "power_user"),
related_modules=("datasources", "dataflow", "portal", "reporting"),
order=42,
),
DocumentationTopic(
id="connectors.sanctions-snapshots",
title="Sanctions source snapshots",
summary=(
"Acquire immutable, checksum-verifiable sanctions list "
"evidence without transmitting screening subjects."
),
body=(
"Connectors provides a deterministic synthetic fixture and "
"the official United Nations Security Council consolidated "
"XML source. Each fetch records conditional transport "
"evidence, bounded retries, health state, source metadata, "
"raw evidence, and a SHA-256 checksum. Refreshes acquire a "
"distributed recovery fence before provider I/O; the immutable "
"snapshot and terminal recovery checkpoint then commit in one "
"transaction. A repeated request key returns the same result. "
"Risk Compliance owns "
"normalization, matching, legal review, and dispositions."
),
layer="available",
documentation_types=("admin", "user"),
audience=("operator", "module_admin", "compliance_reviewer"),
related_modules=("risk_compliance", "dataflow"),
order=41,
),
),
)
def get_manifest() -> ModuleManifest:
return manifest
__all__ = [
"MODULE_ID",
"MODULE_VERSION",
"DATASOURCE_ORIGIN_INTERFACE_VERSION",
"SANCTIONS_SNAPSHOT_INTERFACE_VERSION",
"TABULAR_SOURCE_INTERFACE_VERSION",
"get_manifest",
"manifest",
]
@@ -0,0 +1 @@
"""Connectors migrations."""
@@ -0,0 +1 @@
"""Connectors migration revisions."""
@@ -0,0 +1,214 @@
"""governed connector definitions and simulation evidence
Revision ID: a8d9e0f1b2c3
Revises: f7c8d9e0a1b2
Create Date: 2026-08-20 12:30:00.000000
"""
from __future__ import annotations
from alembic import op
import sqlalchemy as sa
revision = "a8d9e0f1b2c3"
down_revision = "f7c8d9e0a1b2"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.create_table(
"connector_definitions",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("definition_key", sa.String(length=160), nullable=False),
sa.Column("name", sa.String(length=300), nullable=False),
sa.Column("description", sa.Text(), nullable=True),
sa.Column("status", sa.String(length=30), nullable=False),
sa.Column("current_revision", sa.Integer(), nullable=False),
sa.Column("source_package", sa.String(length=300), nullable=True),
sa.Column("local_definition", sa.Boolean(), nullable=False),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
sa.PrimaryKeyConstraint("id", name=op.f("pk_connector_definitions")),
sa.UniqueConstraint(
"tenant_id",
"definition_key",
name="uq_connector_definition_tenant_key",
),
)
op.create_index(
op.f("ix_connector_definitions_tenant_id"),
"connector_definitions",
["tenant_id"],
)
op.create_index(
op.f("ix_connector_definitions_status"),
"connector_definitions",
["status"],
)
op.create_index(
"ix_connector_definitions_tenant_status",
"connector_definitions",
["tenant_id", "status"],
)
op.create_table(
"connector_definition_revisions",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("definition_id", sa.String(length=36), nullable=False),
sa.Column("revision", sa.Integer(), nullable=False),
sa.Column("specification", sa.JSON(), nullable=False),
sa.Column("definition_hash", sa.String(length=64), nullable=False),
sa.Column("origin", sa.String(length=30), nullable=False),
sa.Column("package_ref", sa.String(length=300), nullable=True),
sa.Column("created_by", sa.String(length=255), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(
["definition_id"],
["connector_definitions.id"],
name=op.f(
"fk_connector_definition_revisions_definition_id_connector_definitions"
),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint(
"id",
name=op.f("pk_connector_definition_revisions"),
),
sa.UniqueConstraint(
"definition_id",
"revision",
name="uq_connector_definition_revision",
),
)
op.create_index(
op.f("ix_connector_definition_revisions_definition_id"),
"connector_definition_revisions",
["definition_id"],
)
op.create_index(
op.f("ix_connector_definition_revisions_definition_hash"),
"connector_definition_revisions",
["definition_hash"],
)
op.create_index(
op.f("ix_connector_definition_revisions_created_by"),
"connector_definition_revisions",
["created_by"],
)
op.create_table(
"connector_configurations",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("definition_id", sa.String(length=36), nullable=False),
sa.Column("name", sa.String(length=300), nullable=False),
sa.Column("status", sa.String(length=30), nullable=False),
sa.Column("endpoint_url", sa.String(length=1500), nullable=True),
sa.Column("credential_ref", sa.String(length=500), nullable=True),
sa.Column("base_definition_revision", sa.Integer(), nullable=False),
sa.Column("local_overrides", sa.JSON(), nullable=False),
sa.Column("protected_paths", sa.JSON(), nullable=False),
sa.Column("effective_configuration", sa.JSON(), nullable=False),
sa.Column("effective_hash", sa.String(length=64), nullable=False),
sa.Column("resource_revision", sa.Integer(), nullable=False),
sa.Column("ambiguity_policy", sa.String(length=30), nullable=False),
sa.Column("updated_by", sa.String(length=255), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(
["definition_id"],
["connector_definitions.id"],
name=op.f(
"fk_connector_configurations_definition_id_connector_definitions"
),
ondelete="RESTRICT",
),
sa.PrimaryKeyConstraint("id", name=op.f("pk_connector_configurations")),
sa.UniqueConstraint(
"tenant_id",
"name",
name="uq_connector_configuration_tenant_name",
),
)
for name, columns in (
("ix_connector_configurations_tenant_id", ["tenant_id"]),
("ix_connector_configurations_definition_id", ["definition_id"]),
("ix_connector_configurations_status", ["status"]),
("ix_connector_configurations_effective_hash", ["effective_hash"]),
("ix_connector_configurations_updated_by", ["updated_by"]),
):
op.create_index(op.f(name), "connector_configurations", columns)
op.create_index(
"ix_connector_configurations_tenant_status",
"connector_configurations",
["tenant_id", "status"],
)
op.create_table(
"connector_simulation_runs",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("configuration_id", sa.String(length=36), nullable=False),
sa.Column("mode", sa.String(length=30), nullable=False),
sa.Column("idempotency_key", sa.String(length=255), nullable=False),
sa.Column("request_hash", sa.String(length=64), nullable=False),
sa.Column("status", sa.String(length=30), nullable=False),
sa.Column("review_state", sa.String(length=30), nullable=False),
sa.Column("definition_revision", sa.Integer(), nullable=False),
sa.Column("configuration_revision", sa.Integer(), nullable=False),
sa.Column("configuration_hash", sa.String(length=64), nullable=False),
sa.Column("input_hash", sa.String(length=64), nullable=False),
sa.Column("summary", sa.JSON(), nullable=False),
sa.Column("effects", sa.JSON(), nullable=False),
sa.Column("diagnostics", sa.JSON(), nullable=False),
sa.Column("provenance", sa.JSON(), nullable=False),
sa.Column("created_by", sa.String(length=255), nullable=True),
sa.Column("reviewed_by", sa.String(length=255), nullable=True),
sa.Column("reviewed_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("review_reason", sa.Text(), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
sa.ForeignKeyConstraint(
["configuration_id"],
["connector_configurations.id"],
name=op.f(
"fk_connector_simulation_runs_configuration_id_connector_configurations"
),
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint(
"id",
name=op.f("pk_connector_simulation_runs"),
),
sa.UniqueConstraint(
"tenant_id",
"configuration_id",
"mode",
"idempotency_key",
name="uq_connector_simulation_run_idempotency",
),
)
for name, columns in (
("ix_connector_simulation_runs_tenant_id", ["tenant_id"]),
("ix_connector_simulation_runs_configuration_id", ["configuration_id"]),
("ix_connector_simulation_runs_mode", ["mode"]),
("ix_connector_simulation_runs_status", ["status"]),
("ix_connector_simulation_runs_review_state", ["review_state"]),
("ix_connector_simulation_runs_created_by", ["created_by"]),
("ix_connector_simulation_runs_reviewed_by", ["reviewed_by"]),
):
op.create_index(op.f(name), "connector_simulation_runs", columns)
op.create_index(
"ix_connector_simulation_runs_review",
"connector_simulation_runs",
["tenant_id", "review_state", "created_at"],
)
def downgrade() -> None:
op.drop_table("connector_simulation_runs")
op.drop_table("connector_configurations")
op.drop_table("connector_definition_revisions")
op.drop_table("connector_definitions")
@@ -0,0 +1,141 @@
"""v0.1.14 Connectors baseline
Revision ID: e6b7c8d9f0a1
Revises: None
Create Date: 2026-07-28 00:00:00.000000
"""
from __future__ import annotations
from alembic import op
import sqlalchemy as sa
revision = "e6b7c8d9f0a1"
down_revision = None
branch_labels = None
depends_on = None
def upgrade() -> None:
op.create_table(
"connector_tabular_sources",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("provider", sa.String(length=50), nullable=False),
sa.Column("source_name", sa.String(length=120), nullable=False),
sa.Column("name", sa.String(length=300), nullable=False),
sa.Column("description", sa.Text(), nullable=True),
sa.Column("status", sa.String(length=30), nullable=False),
sa.Column("schema_version", sa.Integer(), nullable=False),
sa.Column("schema", sa.JSON(), nullable=False),
sa.Column("rows", sa.JSON(), nullable=False),
sa.Column("fingerprint", sa.String(length=64), nullable=False),
sa.Column("row_count", sa.Integer(), nullable=False),
sa.Column("byte_count", sa.Integer(), nullable=False),
sa.Column("metadata", sa.JSON(), nullable=False),
sa.Column("created_by", sa.String(length=255), nullable=True),
sa.Column("updated_by", sa.String(length=255), nullable=True),
sa.Column("deleted_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
sa.PrimaryKeyConstraint("id", name=op.f("pk_connector_tabular_sources")),
sa.UniqueConstraint(
"tenant_id",
"source_name",
name="uq_connector_tabular_source_name",
),
)
op.create_index(
op.f("ix_connector_tabular_sources_created_by"),
"connector_tabular_sources",
["created_by"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_deleted_at"),
"connector_tabular_sources",
["deleted_at"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_fingerprint"),
"connector_tabular_sources",
["fingerprint"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_provider"),
"connector_tabular_sources",
["provider"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_status"),
"connector_tabular_sources",
["status"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_tenant_id"),
"connector_tabular_sources",
["tenant_id"],
unique=False,
)
op.create_index(
op.f("ix_connector_tabular_sources_updated_by"),
"connector_tabular_sources",
["updated_by"],
unique=False,
)
op.create_index(
"ix_connector_tabular_sources_tenant_status",
"connector_tabular_sources",
["tenant_id", "status"],
unique=False,
)
op.create_index(
"ix_connector_tabular_sources_tenant_updated",
"connector_tabular_sources",
["tenant_id", "updated_at"],
unique=False,
)
def downgrade() -> None:
op.drop_index(
"ix_connector_tabular_sources_tenant_updated",
table_name="connector_tabular_sources",
)
op.drop_index(
"ix_connector_tabular_sources_tenant_status",
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_updated_by"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_tenant_id"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_status"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_provider"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_fingerprint"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_deleted_at"),
table_name="connector_tabular_sources",
)
op.drop_index(
op.f("ix_connector_tabular_sources_created_by"),
table_name="connector_tabular_sources",
)
op.drop_table("connector_tabular_sources")
@@ -0,0 +1,192 @@
"""Add immutable sanctions source snapshots.
Revision ID: f7c8d9e0a1b2
Revises: e6b7c8d9f0a1
Create Date: 2026-07-29
"""
from __future__ import annotations
from alembic import op
import sqlalchemy as sa
revision = "f7c8d9e0a1b2"
down_revision = "e6b7c8d9f0a1"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.create_table(
"connector_sanctions_acquisition_runs",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("provider_id", sa.String(length=100), nullable=False),
sa.Column("source_id", sa.String(length=200), nullable=False),
sa.Column("status", sa.String(length=40), nullable=False),
sa.Column("attempt_count", sa.Integer(), nullable=False),
sa.Column("request_evidence", sa.JSON(), nullable=False),
sa.Column("response_evidence", sa.JSON(), nullable=False),
sa.Column(
"started_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.Column(
"finished_at",
sa.DateTime(timezone=True),
nullable=True,
),
sa.Column("snapshot_id", sa.String(length=36), nullable=True),
sa.Column("error", sa.Text(), nullable=True),
sa.Column("created_by", sa.String(length=255), nullable=True),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.PrimaryKeyConstraint(
"id",
name=op.f("pk_connector_sanctions_acquisition_runs"),
),
)
for column in (
"tenant_id",
"provider_id",
"source_id",
"status",
"started_at",
"snapshot_id",
"created_by",
):
op.create_index(
op.f(
"ix_connector_sanctions_acquisition_runs_"
f"{column}"
),
"connector_sanctions_acquisition_runs",
[column],
)
op.create_index(
"ix_connector_sanctions_run_health",
"connector_sanctions_acquisition_runs",
["tenant_id", "provider_id", "status", "started_at"],
)
op.create_table(
"connector_sanctions_snapshots",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("tenant_id", sa.String(length=36), nullable=False),
sa.Column("provider_id", sa.String(length=100), nullable=False),
sa.Column("publisher", sa.String(length=300), nullable=False),
sa.Column("jurisdiction", sa.String(length=100), nullable=False),
sa.Column("list_type", sa.String(length=100), nullable=False),
sa.Column("source_id", sa.String(length=200), nullable=False),
sa.Column(
"source_version",
sa.String(length=255),
nullable=False,
),
sa.Column(
"publication_at",
sa.DateTime(timezone=True),
nullable=True,
),
sa.Column(
"effective_at",
sa.DateTime(timezone=True),
nullable=True,
),
sa.Column(
"acquired_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.Column("source_url", sa.String(length=1500), nullable=True),
sa.Column(
"content_type",
sa.String(length=200),
nullable=False,
),
sa.Column("byte_count", sa.Integer(), nullable=False),
sa.Column("sha256", sa.String(length=64), nullable=False),
sa.Column("signature_evidence", sa.JSON(), nullable=False),
sa.Column(
"parser_version",
sa.String(length=100),
nullable=False,
),
sa.Column("licence_notes", sa.Text(), nullable=True),
sa.Column("trust_notes", sa.Text(), nullable=True),
sa.Column(
"connector_run_id",
sa.String(length=36),
nullable=False,
),
sa.Column("transport_evidence", sa.JSON(), nullable=False),
sa.Column("raw_content", sa.LargeBinary(), nullable=False),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.Column(
"updated_at",
sa.DateTime(timezone=True),
nullable=False,
),
sa.ForeignKeyConstraint(
["connector_run_id"],
["connector_sanctions_acquisition_runs.id"],
name=op.f(
"fk_connector_sanctions_snapshots_connector_run_id_"
"connector_sanctions_acquisition_runs"
),
ondelete="RESTRICT",
),
sa.PrimaryKeyConstraint(
"id",
name=op.f("pk_connector_sanctions_snapshots"),
),
sa.UniqueConstraint(
"connector_run_id",
name="uq_connector_sanctions_snapshot_run",
),
)
for column in (
"tenant_id",
"provider_id",
"jurisdiction",
"list_type",
"source_id",
"source_version",
"acquired_at",
"sha256",
"connector_run_id",
):
op.create_index(
op.f(f"ix_connector_sanctions_snapshots_{column}"),
"connector_sanctions_snapshots",
[column],
)
op.create_index(
"ix_connector_sanctions_snapshot_source",
"connector_sanctions_snapshots",
["tenant_id", "provider_id", "acquired_at"],
)
op.create_index(
"ix_connector_sanctions_snapshot_version",
"connector_sanctions_snapshots",
["provider_id", "source_id", "source_version"],
)
def downgrade() -> None:
op.drop_table("connector_sanctions_snapshots")
op.drop_table("connector_sanctions_acquisition_runs")
@@ -0,0 +1,216 @@
from __future__ import annotations
from datetime import UTC, datetime
from hashlib import sha256
from sqlalchemy import func, select
from sqlalchemy.orm import Session
from govoplan_connectors.backend.db.models import (
ConnectorSanctionsAcquisitionRun,
ConnectorSanctionsSnapshot,
ConnectorTabularSource,
)
from govoplan_core.core.provider_governance import (
ExternalProviderRuntimeState,
ExternalProviderStateContext,
)
TABULAR_PROVIDER_ID = "connectors.tabular_snapshot"
SANCTIONS_PROVIDER_ID = "connectors.sanctions_snapshot"
def tabular_provider_states(
context: ExternalProviderStateContext,
) -> tuple[ExternalProviderRuntimeState, ...]:
session = _session(context)
statement = select(ConnectorTabularSource).where(
ConnectorTabularSource.deleted_at.is_(None)
)
if context.tenant_id is not None:
statement = statement.where(
ConnectorTabularSource.tenant_id == context.tenant_id
)
sources = tuple(
session.scalars(
statement.order_by(
ConnectorTabularSource.tenant_id,
ConnectorTabularSource.id,
).limit(context.max_items + 1)
)
)
observed_at = datetime.now(UTC)
return tuple(_tabular_state(item, observed_at=observed_at) for item in sources)
def sanctions_provider_states(
context: ExternalProviderStateContext,
) -> tuple[ExternalProviderRuntimeState, ...]:
session = _session(context)
statement = select(ConnectorSanctionsAcquisitionRun)
if context.tenant_id is not None:
statement = statement.where(
ConnectorSanctionsAcquisitionRun.tenant_id == context.tenant_id
)
runs = tuple(
session.scalars(
statement.order_by(
ConnectorSanctionsAcquisitionRun.tenant_id,
ConnectorSanctionsAcquisitionRun.provider_id,
ConnectorSanctionsAcquisitionRun.source_id,
ConnectorSanctionsAcquisitionRun.started_at.desc(),
).limit(max(context.max_items * 10, context.max_items + 1))
)
)
latest_by_binding: dict[tuple[str, str, str], ConnectorSanctionsAcquisitionRun] = {}
for run in runs:
key = (run.tenant_id, run.provider_id, run.source_id)
latest_by_binding.setdefault(key, run)
if len(latest_by_binding) >= context.max_items + 1:
break
snapshot_counts = _snapshot_counts(
session,
binding_keys=tuple(latest_by_binding),
)
observed_at = datetime.now(UTC)
return tuple(
_sanctions_state(
run,
observed_at=observed_at,
snapshot_count=snapshot_counts.get(key, 0),
)
for key, run in latest_by_binding.items()
)
def _session(context: ExternalProviderStateContext) -> Session:
if not isinstance(context.session, Session):
raise RuntimeError("Connectors provider state requires a database session.")
return context.session
def _tabular_state(
source: ConnectorTabularSource,
*,
observed_at: datetime,
) -> ExternalProviderRuntimeState:
active = source.status == "active"
live_origin = source.provider in {"managed_file", "postgresql"}
labels = {
"managed_file": "Exact managed-file origin",
"postgresql": "Live PostgreSQL origin",
"snapshot": "Immutable tabular snapshot",
}
label = labels.get(source.provider, "Tabular source")
return ExternalProviderRuntimeState(
provider_id=TABULAR_PROVIDER_ID,
binding_ref=f"connectors:tabular-source:{source.id}",
authority_mode="external_mirror",
observed_at=observed_at,
configured=True,
active=active,
health=("unknown" if active and live_origin else "healthy" if active else "inactive"),
freshness="unknown" if active and live_origin else "not_applicable",
conflict="not_applicable",
recovery="ready" if active else "not_applicable",
last_success_at=_aware(source.updated_at or source.created_at),
detail=(
f"{label} is configured; live access and drift are checked on preview."
if active and live_origin
else f"{label} is available."
if active
else f"{label} is inactive."
),
metrics={
"provider": source.provider,
"row_count": int(source.row_count),
"byte_count": int(source.byte_count),
"schema_version": int(source.schema_version),
},
)
def _snapshot_counts(
session: Session,
*,
binding_keys: tuple[tuple[str, str, str], ...],
) -> dict[tuple[str, str, str], int]:
if not binding_keys:
return {}
tenant_ids = {item[0] for item in binding_keys}
rows = session.execute(
select(
ConnectorSanctionsSnapshot.tenant_id,
ConnectorSanctionsSnapshot.provider_id,
ConnectorSanctionsSnapshot.source_id,
func.count(ConnectorSanctionsSnapshot.id),
)
.where(ConnectorSanctionsSnapshot.tenant_id.in_(tenant_ids))
.group_by(
ConnectorSanctionsSnapshot.tenant_id,
ConnectorSanctionsSnapshot.provider_id,
ConnectorSanctionsSnapshot.source_id,
)
)
return {
(str(tenant_id), str(provider_id), str(source_id)): int(count)
for tenant_id, provider_id, source_id, count in rows
if (str(tenant_id), str(provider_id), str(source_id)) in binding_keys
}
def _sanctions_state(
run: ConnectorSanctionsAcquisitionRun,
*,
observed_at: datetime,
snapshot_count: int,
) -> ExternalProviderRuntimeState:
status = str(run.status)
success = status in {"succeeded", "success", "not_modified"}
running = status in {"running", "pending", "retry"}
has_snapshot = bool(run.snapshot_id) or snapshot_count > 0
health = "healthy" if success else "warning" if running else "error"
binding_digest = sha256(
f"{run.tenant_id}\0{run.provider_id}\0{run.source_id}".encode("utf-8")
).hexdigest()[:24]
return ExternalProviderRuntimeState(
provider_id=SANCTIONS_PROVIDER_ID,
binding_ref=f"connectors:sanctions-source:{binding_digest}",
authority_mode="external_mirror",
observed_at=observed_at,
configured=True,
active=True,
health=health,
freshness="unknown",
conflict="not_applicable",
recovery="ready" if success and has_snapshot else "attention",
last_success_at=_aware(run.finished_at) if success else None,
detail=(
"Latest sanctions acquisition completed."
if success
else "Sanctions acquisition is in progress."
if running
else "Latest sanctions acquisition failed; prior accepted snapshots remain separate evidence."
),
metrics={
"latest_status": status,
"attempt_count": int(run.attempt_count),
"accepted_snapshots": int(snapshot_count),
},
)
def _aware(value: datetime | None) -> datetime | None:
if value is None:
return None
return value.replace(tzinfo=UTC) if value.tzinfo is None else value.astimezone(UTC)
__all__ = [
"SANCTIONS_PROVIDER_ID",
"TABULAR_PROVIDER_ID",
"sanctions_provider_states",
"tabular_provider_states",
]
+381
View File
@@ -0,0 +1,381 @@
from __future__ import annotations
from dataclasses import dataclass
import hashlib
from typing import Any
from uuid import NAMESPACE_URL, uuid4, uuid5
from sqlalchemy.orm import Session, sessionmaker
from govoplan_core.core.recovery import (
RecoveryGuaranteeError,
RecoveryMode,
RecoveryPlan,
RecoveryStatus,
)
from govoplan_core.core.recovery_runtime import (
DurableRecoveryOperation,
RecoveryOperationBusy,
RecoveryOperationStateConflict,
begin_durable_recovery_operation,
)
from govoplan_core.core.runtime_coordination import process_runtime_identity
class ConnectorRecoveryError(RuntimeError):
pass
@dataclass(frozen=True, slots=True)
class ConnectorRecoveryDeclaration:
operation_type: str
mode: RecoveryMode
provider_mutation: bool
idempotency: str
verification: tuple[str, ...]
recovery: tuple[str, ...]
implemented: bool
CONNECTOR_RECOVERY_OPERATIONS = (
ConnectorRecoveryDeclaration(
operation_type="read-snapshot",
mode=RecoveryMode.ATOMIC,
provider_mutation=False,
idempotency=(
"Caller-supplied request keys replay a committed immutable snapshot; "
"otherwise each deliberate acquisition receives a generated key."
),
verification=(
"provider revision or conditional cursor is recorded before fetch",
"domain snapshot and terminal recovery checkpoint commit together",
"stored bytes and provider evidence are checksum verified",
),
recovery=(
"a stale running transaction is failed after its database transaction rolls back",
"a new deliberate acquisition may then use a new request key",
),
implemented=True,
),
ConnectorRecoveryDeclaration(
operation_type="external-mutation",
mode=RecoveryMode.FORWARD_RECOVERY,
provider_mutation=True,
idempotency="A stable caller key and canonical request digest are mandatory.",
verification=(
"record the remote revision and bounded provider result",
"verify the provider state before reporting success",
),
recovery=(
"unknown outcomes remain unresolved until provider-backed reconciliation",
"never retry the same remote effect solely to reconstruct local state",
),
implemented=False,
),
)
def connector_session_factory(session: Session) -> sessionmaker[Session]:
bind = session.get_bind()
if bind is None:
raise ConnectorRecoveryError("Connector recovery requires a bound database session")
return sessionmaker(bind=bind, expire_on_commit=False)
def _digest(value: str) -> str:
return hashlib.sha256(value.encode("utf-8")).hexdigest()
def _clean_key(value: str | None) -> str:
clean = str(value or "").strip()
if clean and len(clean) > 500:
raise ConnectorRecoveryError("Connector idempotency keys are limited to 500 characters")
return clean or str(uuid4())
def _stable_resource_id(
*,
tenant_id: str,
provider_id: str,
operation_type: str,
request_key: str,
) -> str:
return str(
uuid5(
NAMESPACE_URL,
f"govoplan:{tenant_id}:{provider_id}:{operation_type}:{request_key}",
)
)
@dataclass(slots=True)
class ConnectorReadSnapshotRecovery:
operation: DurableRecoveryOperation | None
operation_id: str
request_key: str
resource_id: str
replayed: bool
def commit_success(self, session: Session, *, evidence: dict[str, Any]) -> None:
if self.operation is None:
raise ConnectorRecoveryError("A replayed connector read cannot be committed again")
try:
self.operation.commit_atomic_success(session, evidence=evidence)
except Exception as exc:
raise ConnectorRecoveryError(
"The connector snapshot and recovery evidence did not commit atomically"
) from exc
def commit_failure(
self,
session: Session,
*,
summary: str,
evidence: dict[str, Any],
) -> None:
if self.operation is None:
raise ConnectorRecoveryError("A replayed connector read cannot be failed again")
try:
self.operation.commit_atomic_failure(
session,
summary=summary,
evidence=evidence,
)
except Exception as exc:
raise ConnectorRecoveryError(
"The connector failure evidence did not commit atomically"
) from exc
def fail_without_projection(
self,
*,
summary: str,
code: str,
) -> None:
if self.operation is None:
return
self.operation.fail(
summary=summary,
evidence={
"verified": True,
"checks": {
"provider_mutation": False,
"projection_committed": False,
"failure_code": code,
},
},
)
def begin_connector_read_snapshot(
session: Session,
*,
tenant_id: str,
provider_id: str,
idempotency_key: str | None,
source_revision: str | None,
cursor: str | None,
dry_run_evidence: dict[str, Any],
request_metadata: dict[str, Any] | None = None,
resource_type: str = "connector_sync_run",
) -> ConnectorReadSnapshotRecovery:
request_key = _clean_key(idempotency_key)
resource_id = _stable_resource_id(
tenant_id=tenant_id,
provider_id=provider_id,
operation_type="read-snapshot",
request_key=request_key,
)
request = {
"tenant_id": tenant_id,
"provider_id": provider_id,
"dry_run": dry_run_evidence,
"request_key_sha256": _digest(request_key),
**dict(request_metadata or {}),
}
try:
started = begin_durable_recovery_operation(
connector_session_factory(session),
identity=process_runtime_identity(),
module_id="connectors",
operation_type="read-snapshot",
idempotency_key=f"connector-read:{_digest(f'{tenant_id}:{provider_id}:{request_key}')}",
request=request,
recovery_plan=RecoveryPlan(
mode=RecoveryMode.ATOMIC,
preconditions=(
"the actor is authorized for the connector source",
"the provider request is read-only",
"the source revision, cursor, and dry-run decision are durable",
),
verification_steps=(
"validate the bounded provider response and source revision",
"commit the immutable snapshot and terminal checkpoint atomically",
"compare the stored content digest with the acquired bytes",
),
),
precondition_evidence={
"provider_id": provider_id,
"source_revision": source_revision,
"cursor_sha256": _digest(cursor) if cursor else None,
"dry_run": dry_run_evidence,
"provider_mutation": False,
},
lease_resource_key=f"connectors:read:{tenant_id}:{_digest(provider_id)[:40]}",
lease_ttl_seconds=15 * 60,
resource_type=resource_type,
resource_id=resource_id,
metadata={
"resources": ["postgresql", "external-provider"],
"provider_mutation": False,
"recovery_declaration": "read-snapshot",
},
)
except RecoveryOperationBusy as exc:
raise ConnectorRecoveryError(
"Another runtime is already acquiring this connector source"
) from exc
except RecoveryOperationStateConflict as exc:
raise ConnectorRecoveryError(
"This connector request is active or unresolved; reconcile it before retrying"
) from exc
except (RecoveryGuaranteeError, RuntimeError) as exc:
raise ConnectorRecoveryError(
"The connector recovery ledger is unavailable; the provider was not contacted"
) from exc
return ConnectorReadSnapshotRecovery(
operation=started.operation,
operation_id=started.operation_id,
request_key=request_key,
resource_id=resource_id,
replayed=started.replayed,
)
@dataclass(slots=True)
class ConnectorExternalMutationRecovery:
operation: DurableRecoveryOperation | None
operation_id: str
replayed: bool
def succeed(self, *, provider_evidence: dict[str, Any]) -> None:
if self.operation is not None:
self.operation.succeed(evidence=provider_evidence)
def reject(self, *, summary: str, provider_code: str) -> None:
if self.operation is not None:
self.operation.reject(
summary=summary,
evidence={
"verified": True,
"checks": {"provider_rejection": provider_code},
},
)
def outcome_unknown(self, *, summary: str, provider_code: str) -> None:
if self.operation is not None:
self.operation.unresolved(
status=RecoveryStatus.OUTCOME_UNKNOWN,
summary=summary,
evidence={"effect_started": True, "provider_code": provider_code},
failure_summary="Inspect provider state before any retry",
)
def begin_connector_external_mutation(
session: Session,
*,
tenant_id: str,
provider_id: str,
idempotency_key: str,
request_sha256: str,
source_revision: str | None,
cursor: str | None,
dry_run_evidence: dict[str, Any],
resource_type: str,
resource_id: str,
) -> ConnectorExternalMutationRecovery:
if not str(idempotency_key or "").strip():
raise ConnectorRecoveryError("External connector mutations require an idempotency key")
request_key = _clean_key(idempotency_key)
if len(request_sha256) != 64 or any(
character not in "0123456789abcdefABCDEF" for character in request_sha256
):
raise ConnectorRecoveryError("External connector mutations require a SHA-256 request digest")
try:
started = begin_durable_recovery_operation(
connector_session_factory(session),
identity=process_runtime_identity(),
module_id="connectors",
operation_type="external-mutation",
idempotency_key=f"connector-write:{_digest(f'{tenant_id}:{provider_id}:{request_key}')}",
request={
"tenant_id": tenant_id,
"provider_id": provider_id,
"request_sha256": request_sha256,
"source_revision": source_revision,
"cursor_sha256": _digest(cursor) if cursor else None,
"dry_run": dry_run_evidence,
},
recovery_plan=RecoveryPlan(
mode=RecoveryMode.FORWARD_RECOVERY,
preconditions=(
"the actor and effective connector policy authorize the mutation",
"a stable idempotency key and canonical request digest are present",
"the dry-run and source revision evidence are durable",
),
forward_recovery_steps=(
"inspect provider state without repeating the mutation",
"record whether the provider accepted the requested revision",
"retry only under a new deliberate key when absence is proven",
),
verification_steps=(
"compare provider identity and revision with the canonical request",
"verify the consuming domain state independently",
),
),
precondition_evidence={
"request_sha256": request_sha256,
"source_revision": source_revision,
"cursor_sha256": _digest(cursor) if cursor else None,
"dry_run": dry_run_evidence,
"provider_mutation": True,
},
lease_resource_key=(
f"connectors:write:{tenant_id}:{_digest(provider_id)[:24]}:"
f"{_digest(resource_id)[:24]}"
),
lease_ttl_seconds=15 * 60,
resource_type=resource_type,
resource_id=resource_id,
metadata={
"resources": ["postgresql", "queue", "external-provider"],
"provider_mutation": True,
"recovery_declaration": "external-mutation",
},
)
except (RecoveryOperationBusy, RecoveryOperationStateConflict) as exc:
raise ConnectorRecoveryError(
"This external connector effect is active or unresolved"
) from exc
except (RecoveryGuaranteeError, RuntimeError) as exc:
raise ConnectorRecoveryError(
"The connector recovery ledger is unavailable; no external mutation started"
) from exc
return ConnectorExternalMutationRecovery(
operation=started.operation,
operation_id=started.operation_id,
replayed=started.replayed,
)
__all__ = [
"CONNECTOR_RECOVERY_OPERATIONS",
"ConnectorExternalMutationRecovery",
"ConnectorReadSnapshotRecovery",
"ConnectorRecoveryDeclaration",
"ConnectorRecoveryError",
"begin_connector_external_mutation",
"begin_connector_read_snapshot",
"connector_session_factory",
]
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+305
View File
@@ -0,0 +1,305 @@
from __future__ import annotations
from datetime import datetime
from typing import Any, Literal
from pydantic import BaseModel, Field, model_validator
class FeedAcquireRequest(BaseModel):
url: str = Field(min_length=1, max_length=2000)
max_entries: int = Field(default=2_000, ge=1, le=10_000)
class FeedImportRequest(FeedAcquireRequest):
name: str = Field(min_length=1, max_length=300)
source_name: str = Field(
min_length=1,
max_length=120,
pattern=r"^[A-Za-z_][A-Za-z0-9_]*$",
)
description: str | None = Field(default=None, max_length=4000)
class FeedEntryPayload(BaseModel):
id: str = Field(min_length=1, max_length=2000)
title: str = Field(min_length=1, max_length=1000)
url: str | None = Field(default=None, max_length=2000)
summary: str | None = None
content: str | None = None
author: str | None = Field(default=None, max_length=500)
published_at: datetime | None = None
updated_at: datetime | None = None
categories: list[str] = Field(default_factory=list, max_length=100)
enclosures: list[dict[str, Any]] = Field(default_factory=list, max_length=100)
visibility: Literal["public", "tenant", "private"] = "public"
metadata: dict[str, Any] = Field(default_factory=dict)
class FeedPublicationEntryPayload(FeedEntryPayload):
source_kind: Literal["event", "publication", "case", "report"]
source_module: str = Field(
min_length=1,
max_length=100,
pattern=r"^[a-z][a-z0-9_]*$",
)
source_ref: str = Field(min_length=1, max_length=500)
source_revision: str | None = Field(default=None, max_length=200)
class FeedDocumentResponse(BaseModel):
format: Literal["rss", "atom"]
title: str
source_url: str
description: str | None = None
home_url: str | None = None
language: str | None = None
updated_at: datetime | None = None
acquired_at: datetime | None = None
fresh_until: datetime | None = None
etag: str | None = None
last_modified: str | None = None
content_type: str | None = None
sha256: str
entries: list[FeedEntryPayload]
metadata: dict[str, Any] = Field(default_factory=dict)
class FeedRenderPayload(BaseModel):
format: Literal["rss", "atom"]
title: str = Field(min_length=1, max_length=1000)
feed_url: str = Field(min_length=1, max_length=2000)
home_url: str = Field(min_length=1, max_length=2000)
description: str | None = None
language: str | None = Field(default=None, max_length=100)
entries: list[FeedPublicationEntryPayload] = Field(
default_factory=list,
max_length=10_000,
)
audience: Literal["public", "tenant", "private"] = "public"
class SnapshotCreateRequest(BaseModel):
name: str = Field(min_length=1, max_length=300)
source_name: str = Field(
min_length=1,
max_length=120,
pattern=r"^[A-Za-z_][A-Za-z0-9_]*$",
)
description: str | None = Field(default=None, max_length=4000)
format: Literal["json", "csv"] = "json"
rows: list[dict[str, Any]] | None = Field(default=None, max_length=10_000)
csv_text: str | None = Field(default=None, max_length=5_000_000)
delimiter: Literal[",", ";", "\t", "|"] = ","
@model_validator(mode="after")
def validate_payload(self) -> "SnapshotCreateRequest":
if self.format == "json" and self.rows is None:
raise ValueError("JSON snapshots require rows.")
if self.format == "json" and self.csv_text is not None:
raise ValueError("JSON snapshots cannot include CSV text.")
if self.format == "csv" and not self.csv_text:
raise ValueError("CSV snapshots require CSV text.")
if self.format == "csv" and self.rows is not None:
raise ValueError("CSV snapshots cannot include JSON rows.")
return self
class ManagedFileSourceCreateRequest(BaseModel):
name: str = Field(min_length=1, max_length=300)
source_name: str = Field(
min_length=1,
max_length=120,
pattern=r"^[A-Za-z_][A-Za-z0-9_]*$",
)
description: str | None = Field(default=None, max_length=4000)
file_asset_id: str = Field(min_length=1, max_length=36)
file_version_id: str | None = Field(default=None, min_length=1, max_length=36)
delimiter: Literal[",", ";", "\t", "|"] = ","
sheet_name: str | None = Field(default=None, min_length=1, max_length=255)
class SqlSourceCreateRequest(BaseModel):
name: str = Field(min_length=1, max_length=300)
source_name: str = Field(
min_length=1,
max_length=120,
pattern=r"^[A-Za-z_][A-Za-z0-9_]*$",
)
description: str | None = Field(default=None, max_length=4000)
configuration_id: str = Field(min_length=1, max_length=36)
schema_name: str | None = Field(
default=None,
pattern=r"^[A-Za-z_][A-Za-z0-9_$-]{0,127}$",
)
table_name: str = Field(
min_length=1,
max_length=128,
pattern=r"^[A-Za-z_][A-Za-z0-9_$-]{0,127}$",
)
class TabularColumnResponse(BaseModel):
name: str
data_type: str
nullable: bool
class TabularPushdownResponse(BaseModel):
projections: bool
pagination: bool
filters: list[str]
aggregations: list[str]
sorting: list[str]
class TabularHealthResponse(BaseModel):
status: Literal["healthy", "warning", "error", "unknown"]
code: str
summary: str
checked_at: str | None
details: dict[str, Any]
class TabularPreviewDiagnosticResponse(BaseModel):
severity: Literal["info", "warning", "error"]
code: str
message: str
details: dict[str, Any]
class TabularSourceResponse(BaseModel):
ref: str
provider: str
source_name: str
name: str
description: str | None
columns: list[TabularColumnResponse]
schema_version: str
fingerprint: str
row_count: int | None
byte_count: int | None
updated_at: str | None
capabilities: list[str]
metadata: dict[str, Any]
source_mode: Literal["live", "cached", "file_backed", "static"]
pushdown: TabularPushdownResponse
health: TabularHealthResponse
class TabularSourceListResponse(BaseModel):
sources: list[TabularSourceResponse]
class TabularSourcePreviewResponse(BaseModel):
source: TabularSourceResponse
rows: list[dict[str, Any]]
total_rows: int
truncated: bool
returned_bytes: int
elapsed_ms: int
effective_row_limit: int
effective_byte_limit: int
effective_timeout_ms: int
diagnostics: list[TabularPreviewDiagnosticResponse]
class TabularSourceDeleteResponse(BaseModel):
deleted: bool
source_ref: str
class SanctionsSourceResponse(BaseModel):
provider_id: str
publisher: str
jurisdiction: str
list_type: str
source_id: str
source_url: str | None
parser_version: str
licence_notes: str
trust_notes: str
class SanctionsSourceListResponse(BaseModel):
sources: list[SanctionsSourceResponse]
class SanctionsSnapshotResponse(BaseModel):
ref: str
provider_id: str
publisher: str
jurisdiction: str
list_type: str
source_id: str
source_version: str
publication_at: datetime | None
effective_at: datetime | None
acquired_at: datetime
content_type: str
byte_count: int
sha256: str
parser_version: str
raw_evidence_ref: str
connector_run_id: str
signature_evidence: dict[str, Any]
licence_notes: str | None
trust_notes: str | None
transport_evidence: dict[str, Any]
class SanctionsSnapshotListResponse(BaseModel):
snapshots: list[SanctionsSnapshotResponse]
class SanctionsAcquisitionRunResponse(BaseModel):
id: str
provider_id: str
source_id: str
status: str
attempt_count: int
request_evidence: dict[str, Any]
response_evidence: dict[str, Any]
started_at: datetime
finished_at: datetime | None
snapshot_id: str | None
error: str | None
class SanctionsAcquisitionRunListResponse(BaseModel):
runs: list[SanctionsAcquisitionRunResponse]
class SanctionsRefreshResponse(BaseModel):
run_id: str
provider_id: str
status: str
snapshot: SanctionsSnapshotResponse | None
error: str | None
__all__ = [
"FeedAcquireRequest",
"FeedDocumentResponse",
"FeedEntryPayload",
"FeedImportRequest",
"FeedRenderPayload",
"ManagedFileSourceCreateRequest",
"SnapshotCreateRequest",
"SqlSourceCreateRequest",
"SanctionsAcquisitionRunListResponse",
"SanctionsAcquisitionRunResponse",
"SanctionsRefreshResponse",
"SanctionsSnapshotListResponse",
"SanctionsSnapshotResponse",
"SanctionsSourceListResponse",
"SanctionsSourceResponse",
"TabularColumnResponse",
"TabularHealthResponse",
"TabularPreviewDiagnosticResponse",
"TabularPushdownResponse",
"TabularSourceDeleteResponse",
"TabularSourceListResponse",
"TabularSourcePreviewResponse",
"TabularSourceResponse",
]
@@ -0,0 +1,849 @@
from __future__ import annotations
import hashlib
import json
import math
import re
import zipfile
from collections.abc import Callable, Mapping, Sequence
from dataclasses import dataclass
from datetime import date, datetime
from decimal import Decimal
from io import BytesIO
from typing import Any
from openpyxl import load_workbook
from sqlalchemy import (
JSON,
BigInteger,
Boolean,
Date,
DateTime,
Float,
Integer,
LargeBinary,
MetaData,
Numeric,
String,
Table,
Text,
create_engine,
func,
select,
)
from sqlalchemy.engine import Engine, URL, make_url
from sqlalchemy.exc import SQLAlchemyError
from sqlalchemy.orm import Session
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.files import (
ManagedTabularFileAccessError,
ManagedTabularFileError,
ManagedTabularFileValidationError,
managed_tabular_file_provider,
)
from govoplan_core.core.tabular_sources import (
TabularColumn,
TabularPreviewDiagnostic,
TabularPushdown,
TabularSourceHealth,
TabularSourceUnavailableError,
TabularSourceValidationError,
parse_tabular_csv,
)
from govoplan_core.security.credential_envelopes import (
CredentialAccessContext,
CredentialEnvelopeError,
resolve_credential_envelope,
)
from govoplan_core.security.redaction import is_sensitive_key
from govoplan_connectors.backend.db.models import ConnectorConfiguration
MAX_FILE_BYTES = 5_000_000
MAX_FILE_ROWS = 10_000
MAX_FILE_COLUMNS = 500
MAX_XLSX_ENTRIES = 5_000
MAX_XLSX_EXPANDED_BYTES = 50_000_000
MAX_XLSX_COMPRESSION_RATIO = 100
POSTGRESQL_SCHEMES = frozenset({"postgresql", "postgresql+psycopg"})
_IDENTIFIER = re.compile(r"^[A-Za-z_][A-Za-z0-9_$-]{0,127}$")
@dataclass(frozen=True, slots=True)
class TabularOriginInspection:
provider: str
schema: tuple[TabularColumn, ...]
fingerprint: str
row_count: int
byte_count: int
metadata: Mapping[str, object]
health: TabularSourceHealth
pushdown: TabularPushdown
rows: tuple[Mapping[str, object], ...] = ()
diagnostics: tuple[TabularPreviewDiagnostic, ...] = ()
@dataclass(frozen=True, slots=True)
class TabularOriginRead:
inspection: TabularOriginInspection
rows: tuple[Mapping[str, object], ...]
total_rows: int
diagnostics: tuple[TabularPreviewDiagnostic, ...] = ()
class ManagedFileTabularAdapter:
def __init__(self, registry: object | None) -> None:
self._registry = registry
def inspect(
self,
session: Session,
principal: ApiPrincipal,
*,
file_asset_id: str,
file_version_id: str | None,
delimiter: str = ",",
sheet_name: str | None = None,
) -> TabularOriginInspection:
provider = managed_tabular_file_provider(self._registry)
if provider is None:
raise TabularSourceUnavailableError(
"Managed file sources require the Files module."
)
try:
metadata = provider.get_tabular_file(
session,
principal,
file_asset_id=file_asset_id,
file_version_id=file_version_id,
)
if metadata is None:
raise TabularSourceUnavailableError(
"Managed tabular file or version is unavailable."
)
content = provider.read_tabular_file(
session,
principal,
file_asset_id=file_asset_id,
file_version_id=metadata.file_version_id,
max_bytes=MAX_FILE_BYTES,
)
except ManagedTabularFileAccessError as exc:
raise TabularSourceUnavailableError(
"Managed tabular file access is no longer authorized."
) from exc
except ManagedTabularFileValidationError as exc:
raise TabularSourceValidationError(str(exc)) from exc
except ManagedTabularFileError as exc:
raise TabularSourceUnavailableError(str(exc)) from exc
rows, resolved_sheet = parse_managed_tabular_content(
content.payload,
filename=content.file.filename,
content_type=content.file.content_type,
delimiter=delimiter,
sheet_name=sheet_name,
)
schema = infer_tabular_schema(rows)
fingerprint = origin_fingerprint(
schema,
tokens=(
"managed_file",
content.file.file_asset_id,
content.file.file_version_id,
content.file.sha256,
resolved_sheet or "",
delimiter,
),
)
try:
current = provider.get_tabular_file(
session,
principal,
file_asset_id=file_asset_id,
)
except ManagedTabularFileAccessError as exc:
raise TabularSourceUnavailableError(
"Managed tabular file access is no longer authorized."
) from exc
except ManagedTabularFileError as exc:
raise TabularSourceUnavailableError(str(exc)) from exc
changed = bool(
current is not None
and current.file_version_id != content.file.file_version_id
)
health = TabularSourceHealth(
status="warning" if changed else "healthy",
code=(
"files.newer_version_available"
if changed
else "files.exact_version_ready"
),
summary=(
"A newer managed file version is available for explicit review."
if changed
else "The exact managed file version passed access and integrity checks."
),
checked_at=content.file.updated_at,
details={
"pinned_version_id": content.file.file_version_id,
"current_version_id": (
current.file_version_id if current is not None else None
),
},
)
return TabularOriginInspection(
provider="managed_file",
schema=schema,
fingerprint=fingerprint,
row_count=len(rows),
byte_count=len(content.payload),
metadata={
"origin_kind": "managed_file",
"file_asset_id": content.file.file_asset_id,
"file_version_id": content.file.file_version_id,
"file_sha256": content.file.sha256,
"filename": content.file.filename,
"content_type": content.file.content_type,
"format": "xlsx" if _is_xlsx(content.file.filename, content.file.content_type) else "csv",
"delimiter": delimiter,
"sheet_name": resolved_sheet,
},
health=health,
pushdown=TabularPushdown(projections=True, pagination=True),
rows=rows,
diagnostics=(
(
TabularPreviewDiagnostic(
severity="warning",
code="files.newer_version_available",
message=(
"The preview remains pinned to the reviewed file version; "
"refresh the source to adopt the newer version."
),
details=dict(health.details),
),
)
if changed
else ()
),
)
def read(
self,
session: Session,
principal: ApiPrincipal,
*,
metadata: Mapping[str, object],
) -> TabularOriginRead:
inspection = self.inspect(
session,
principal,
file_asset_id=_required_metadata(metadata, "file_asset_id"),
file_version_id=_required_metadata(metadata, "file_version_id"),
delimiter=str(metadata.get("delimiter") or ","),
sheet_name=_optional_text(metadata.get("sheet_name")),
)
expected_sha256 = _required_metadata(metadata, "file_sha256")
if inspection.metadata.get("file_sha256") != expected_sha256:
raise TabularSourceUnavailableError(
"Managed file content no longer matches its exact-version checksum."
)
return TabularOriginRead(
inspection=inspection,
rows=inspection.rows,
total_rows=inspection.row_count,
diagnostics=inspection.diagnostics,
)
class PostgresqlTabularAdapter:
"""Read-only SQLAlchemy adapter with a production PostgreSQL allow-list."""
def __init__(
self,
*,
engine_factory: Callable[[URL], Engine] | None = None,
allow_sqlite_for_tests: bool = False,
) -> None:
self._engine_factory = engine_factory or (
lambda url: create_engine(url, pool_pre_ping=True)
)
self._allow_sqlite_for_tests = allow_sqlite_for_tests
def inspect(
self,
session: Session,
principal: ApiPrincipal,
*,
configuration_id: str,
table_name: str,
schema_name: str | None = None,
timeout_ms: int = 2_000,
) -> TabularOriginInspection:
configuration, url, credential_revision = self._connection(
session,
principal,
configuration_id=configuration_id,
)
table_name = _sql_identifier(table_name, "table")
schema_name = (
_sql_identifier(schema_name, "schema") if schema_name else None
)
engine = self._engine_factory(_bounded_connection_url(url, timeout_ms))
try:
with engine.connect() as connection:
_configure_read_only(connection, url, timeout_ms)
table = Table(
table_name,
MetaData(),
schema=schema_name,
autoload_with=connection,
)
schema = tuple(_sql_column(column) for column in table.columns)
if not schema:
raise TabularSourceValidationError(
"SQL tabular sources require at least one column."
)
row_count = int(
connection.execute(select(func.count()).select_from(table)).scalar_one()
)
except TabularSourceValidationError:
raise
except SQLAlchemyError as exc:
raise TabularSourceUnavailableError(
"SQL source discovery failed; verify the active configuration, credential, table, and provider health."
) from exc
finally:
engine.dispose()
fingerprint = origin_fingerprint(
schema,
tokens=(
"postgresql",
configuration.id,
configuration.effective_hash,
credential_revision or "",
schema_name or "",
table_name,
),
)
return TabularOriginInspection(
provider="postgresql",
schema=schema,
fingerprint=fingerprint,
row_count=row_count,
byte_count=0,
metadata={
"origin_kind": "sql",
"configuration_id": configuration.id,
"configuration_revision": configuration.resource_revision,
"configuration_hash": configuration.effective_hash,
"credential_revision": credential_revision,
"schema_name": schema_name,
"table_name": table_name,
},
health=TabularSourceHealth(
status="healthy",
code="sql.source_ready",
summary="The governed PostgreSQL source is reachable and its schema was discovered.",
checked_at=configuration.updated_at,
details={
"configuration_id": configuration.id,
"configuration_revision": configuration.resource_revision,
},
),
pushdown=TabularPushdown(projections=True, pagination=True),
)
def read(
self,
session: Session,
principal: ApiPrincipal,
*,
metadata: Mapping[str, object],
columns: Sequence[str],
offset: int,
limit: int,
timeout_ms: int,
) -> TabularOriginRead:
configuration_id = _required_metadata(metadata, "configuration_id")
current_configuration, _current_url, current_credential_revision = (
self._connection(
session,
principal,
configuration_id=configuration_id,
)
)
if current_configuration.effective_hash != metadata.get(
"configuration_hash"
):
raise TabularSourceValidationError(
"The SQL connector configuration changed; refresh the source before previewing it."
)
if current_credential_revision != metadata.get("credential_revision"):
raise TabularSourceValidationError(
"The SQL source credential changed; refresh the source before previewing it."
)
inspection = self.inspect(
session,
principal,
configuration_id=configuration_id,
table_name=_required_metadata(metadata, "table_name"),
schema_name=_optional_text(metadata.get("schema_name")),
timeout_ms=timeout_ms,
)
if inspection.fingerprint != metadata.get("discovery_fingerprint"):
raise TabularSourceValidationError(
"The SQL source schema drifted; refresh and review the source before previewing it."
)
configuration, url, _credential_revision = self._connection(
session,
principal,
configuration_id=configuration_id,
)
engine = self._engine_factory(_bounded_connection_url(url, timeout_ms))
try:
with engine.connect() as connection:
_configure_read_only(connection, url, timeout_ms)
table = Table(
_required_metadata(metadata, "table_name"),
MetaData(),
schema=_optional_text(metadata.get("schema_name")),
autoload_with=connection,
)
selected_names = tuple(dict.fromkeys(str(item) for item in columns))
selected = (
[table.c[name] for name in selected_names]
if selected_names
else list(table.columns)
)
statement = select(*selected).offset(max(0, int(offset))).limit(
max(1, int(limit))
)
rows = tuple(
_json_row(dict(row._mapping))
for row in connection.execute(statement)
)
except KeyError as exc:
raise TabularSourceValidationError(
f"Unknown SQL source column: {exc.args[0]}"
) from exc
except SQLAlchemyError as exc:
raise TabularSourceUnavailableError(
"SQL source preview failed or exceeded its provider budget."
) from exc
finally:
engine.dispose()
return TabularOriginRead(
inspection=inspection,
rows=rows,
total_rows=inspection.row_count,
)
def _connection(
self,
session: Session,
principal: ApiPrincipal,
*,
configuration_id: str,
) -> tuple[ConnectorConfiguration, URL, str | None]:
configuration = session.scalar(
select(ConnectorConfiguration).where(
ConnectorConfiguration.id == configuration_id,
ConnectorConfiguration.tenant_id == principal.tenant_id,
)
)
if configuration is None:
raise TabularSourceUnavailableError(
"SQL connector configuration is unavailable."
)
if configuration.status != "active":
raise TabularSourceUnavailableError(
"SQL connector configuration is not active."
)
endpoint = _optional_text(configuration.endpoint_url)
if not endpoint:
raise TabularSourceUnavailableError(
"SQL connector configuration has no endpoint."
)
specification = dict(configuration.effective_configuration or {})
provider = str(specification.get("provider") or "").strip().casefold()
protocol = str(specification.get("protocol") or "").strip().casefold()
if provider not in {"postgres", "postgresql", "sql"} or protocol not in {
"postgres",
"postgresql",
"sql",
}:
raise TabularSourceValidationError(
"The selected connector configuration is not a PostgreSQL tabular reader."
)
try:
url = make_url(endpoint)
except (TypeError, ValueError) as exc:
raise TabularSourceValidationError(
"SQL connector endpoint is invalid."
) from exc
if url.username or url.password:
raise TabularSourceValidationError(
"SQL connector endpoints must not contain credentials."
)
if any(is_sensitive_key(key) for key in url.query):
raise TabularSourceValidationError(
"SQL connector endpoint query parameters must not contain credentials."
)
allowed_schemes = set(POSTGRESQL_SCHEMES)
if self._allow_sqlite_for_tests:
allowed_schemes.update({"sqlite", "sqlite+pysqlite"})
if url.drivername not in allowed_schemes:
raise TabularSourceValidationError(
"Only the governed PostgreSQL tabular adapter is enabled."
)
credential_revision: str | None = None
credential_ref = _optional_text(configuration.credential_ref)
if credential_ref:
try:
credential = resolve_credential_envelope(
session,
credential_id=credential_ref,
context=CredentialAccessContext(
tenant_id=principal.tenant_id,
user_id=_principal_user_id(principal),
group_ids=frozenset(principal.principal.group_ids),
target_scope_type="tenant",
target_scope_id=principal.tenant_id,
module_id="connectors",
server_ref=endpoint,
),
)
except CredentialEnvelopeError as exc:
raise TabularSourceUnavailableError(
"SQL source credential is unavailable, inactive, or outside its allowed scope."
) from exc
public_data = dict(credential.public_data)
secret_data = dict(credential.secret_data)
username = _optional_text(
public_data.get("username")
or secret_data.get("username")
or secret_data.get("user")
)
password = _optional_text(secret_data.get("password"))
if url.drivername in POSTGRESQL_SCHEMES and (not username or not password):
raise TabularSourceUnavailableError(
"SQL source credential does not provide a username and password."
)
url = url.set(username=username, password=password)
credential_revision = credential.revision
elif url.drivername in POSTGRESQL_SCHEMES:
raise TabularSourceUnavailableError(
"PostgreSQL tabular sources require a credential envelope reference."
)
return configuration, url, credential_revision
def parse_managed_tabular_content(
payload: bytes,
*,
filename: str,
content_type: str | None,
delimiter: str,
sheet_name: str | None,
) -> tuple[tuple[Mapping[str, object], ...], str | None]:
if len(payload) > MAX_FILE_BYTES:
raise TabularSourceValidationError(
f"Managed tabular files are limited to {MAX_FILE_BYTES:,} bytes."
)
if _is_xlsx(filename, content_type):
return _parse_xlsx(payload, sheet_name=sheet_name)
try:
text = payload.decode("utf-8-sig")
except UnicodeDecodeError as exc:
raise TabularSourceValidationError(
"Managed CSV files must use UTF-8 encoding."
) from exc
return (
tuple(parse_tabular_csv(text, delimiter=delimiter, max_rows=MAX_FILE_ROWS)),
None,
)
def _parse_xlsx(
payload: bytes,
*,
sheet_name: str | None,
) -> tuple[tuple[Mapping[str, object], ...], str]:
_validate_xlsx_archive(payload)
try:
workbook = load_workbook(
BytesIO(payload),
read_only=True,
data_only=True,
keep_links=False,
)
except Exception as exc:
raise TabularSourceValidationError(
"Managed XLSX content could not be parsed."
) from exc
try:
available = tuple(workbook.sheetnames)
if not available:
raise TabularSourceValidationError(
"Managed XLSX content requires at least one worksheet."
)
selected_name = _optional_text(sheet_name) or available[0]
if selected_name not in available:
raise TabularSourceValidationError(
f"Managed XLSX worksheet {selected_name!r} was not found."
)
worksheet = workbook[selected_name]
iterator = worksheet.iter_rows(values_only=True)
try:
raw_headers = next(iterator)
except StopIteration as exc:
raise TabularSourceValidationError(
"Managed XLSX worksheet requires a header row."
) from exc
headers = _xlsx_headers(raw_headers)
rows: list[Mapping[str, object]] = []
for values in iterator:
if len(rows) >= MAX_FILE_ROWS:
raise TabularSourceValidationError(
f"Managed XLSX worksheets are limited to {MAX_FILE_ROWS:,} data rows."
)
normalized = tuple(values[: len(headers)])
if all(value in (None, "") for value in normalized):
continue
rows.append(
{
header: _json_value(
normalized[index] if index < len(normalized) else None
)
for index, header in enumerate(headers)
}
)
return tuple(rows), selected_name
finally:
workbook.close()
def _validate_xlsx_archive(payload: bytes) -> None:
try:
with zipfile.ZipFile(BytesIO(payload)) as archive:
entries = archive.infolist()
if len(entries) > MAX_XLSX_ENTRIES:
raise TabularSourceValidationError(
"Managed XLSX content contains too many archive entries."
)
expanded = sum(max(0, item.file_size) for item in entries)
if expanded > MAX_XLSX_EXPANDED_BYTES:
raise TabularSourceValidationError(
"Managed XLSX content exceeds the expanded-size limit."
)
compressed = sum(max(1, item.compress_size) for item in entries)
if expanded > compressed * MAX_XLSX_COMPRESSION_RATIO:
raise TabularSourceValidationError(
"Managed XLSX content exceeds the compression-ratio limit."
)
if any(
item.filename.startswith(("/", "\\"))
or ".." in item.filename.replace("\\", "/").split("/")
for item in entries
):
raise TabularSourceValidationError(
"Managed XLSX content contains an unsafe archive path."
)
except zipfile.BadZipFile as exc:
raise TabularSourceValidationError(
"Managed XLSX content is not a valid workbook archive."
) from exc
def _xlsx_headers(values: Sequence[object]) -> tuple[str, ...]:
if len(values) > MAX_FILE_COLUMNS:
raise TabularSourceValidationError(
f"Managed XLSX worksheets are limited to {MAX_FILE_COLUMNS:,} columns."
)
headers = tuple(str(value or "").strip() for value in values)
while headers and not headers[-1]:
headers = headers[:-1]
if not headers or any(not header for header in headers):
raise TabularSourceValidationError(
"Managed XLSX content requires a non-empty header row."
)
if len(set(headers)) != len(headers):
raise TabularSourceValidationError(
"Managed XLSX column names must be unique."
)
return headers
def infer_tabular_schema(
rows: Sequence[Mapping[str, object]],
) -> tuple[TabularColumn, ...]:
names: list[str] = []
for row in rows:
for name in row:
if name not in names:
names.append(name)
result: list[TabularColumn] = []
for name in names:
values = [row.get(name) for row in rows]
concrete = [value for value in values if value is not None]
data_type = _type_name(concrete[0]) if concrete else "unknown"
if any(_type_name(value) != data_type for value in concrete[1:]):
data_type = "mixed"
result.append(
TabularColumn(
name=name,
data_type=data_type,
nullable=len(concrete) != len(values),
)
)
return tuple(result)
def origin_fingerprint(
schema: Sequence[TabularColumn],
*,
tokens: Sequence[str],
) -> str:
payload = {
"schema": [
{
"name": column.name,
"data_type": column.data_type,
"nullable": column.nullable,
}
for column in schema
],
"tokens": list(tokens),
}
return hashlib.sha256(
json.dumps(payload, sort_keys=True, separators=(",", ":")).encode("utf-8")
).hexdigest()
def _sql_column(column: Any) -> TabularColumn:
column_type = column.type
if isinstance(column_type, Boolean):
data_type = "boolean"
elif isinstance(column_type, (Integer, BigInteger)):
data_type = "integer"
elif isinstance(column_type, (Numeric, Float)):
data_type = "number"
elif isinstance(column_type, DateTime):
data_type = "datetime"
elif isinstance(column_type, Date):
data_type = "date"
elif isinstance(column_type, JSON):
data_type = "object"
elif isinstance(column_type, LargeBinary):
data_type = "binary"
elif isinstance(column_type, (String, Text)):
data_type = "string"
else:
data_type = str(column_type).casefold()
return TabularColumn(
name=str(column.name),
data_type=data_type,
nullable=bool(column.nullable),
)
def _configure_read_only(connection: Any, url: URL, timeout_ms: int) -> None:
if url.drivername not in POSTGRESQL_SCHEMES:
return
effective_timeout = max(1, min(int(timeout_ms), 30_000))
connection.exec_driver_sql("SET TRANSACTION READ ONLY")
connection.exec_driver_sql(f"SET LOCAL statement_timeout = {effective_timeout}")
def _bounded_connection_url(url: URL, timeout_ms: int) -> URL:
if url.drivername not in POSTGRESQL_SCHEMES:
return url
connect_timeout = max(1, math.ceil(min(int(timeout_ms), 30_000) / 1_000))
return url.update_query_dict({"connect_timeout": str(connect_timeout)})
def _sql_identifier(value: object, label: str) -> str:
normalized = str(value or "").strip()
if not _IDENTIFIER.fullmatch(normalized):
raise TabularSourceValidationError(
f"SQL {label} names must use a simple identifier."
)
return normalized
def _required_metadata(metadata: Mapping[str, object], key: str) -> str:
value = _optional_text(metadata.get(key))
if not value:
raise TabularSourceValidationError(
f"Tabular source metadata is missing {key}."
)
return value
def _optional_text(value: object | None) -> str | None:
normalized = str(value or "").strip()
return normalized or None
def _principal_user_id(principal: ApiPrincipal) -> str | None:
return _optional_text(getattr(principal.user, "id", None))
def _is_xlsx(filename: str, content_type: str | None) -> bool:
normalized_type = str(content_type or "").split(";", 1)[0].strip().casefold()
return str(filename or "").strip().casefold().endswith(".xlsx") or normalized_type == (
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
def _json_row(row: Mapping[str, object]) -> dict[str, object]:
return {str(key): _json_value(value) for key, value in row.items()}
def _json_value(value: object) -> object:
if value is None or isinstance(value, (str, bool, int)):
return value
if isinstance(value, float):
if not math.isfinite(value):
return str(value)
return value
if isinstance(value, Decimal):
return float(value)
if isinstance(value, (datetime, date)):
return value.isoformat()
if isinstance(value, bytes):
return value.hex()
if isinstance(value, (list, dict)):
return json.loads(json.dumps(value, default=str))
return str(value)
def _type_name(value: object) -> str:
if isinstance(value, bool):
return "boolean"
if isinstance(value, int):
return "integer"
if isinstance(value, (float, Decimal)):
return "number"
if isinstance(value, str):
return "string"
if isinstance(value, list):
return "array"
if isinstance(value, dict):
return "object"
return type(value).__name__.casefold()
__all__ = [
"MAX_FILE_BYTES",
"MAX_FILE_ROWS",
"ManagedFileTabularAdapter",
"PostgresqlTabularAdapter",
"TabularOriginInspection",
"TabularOriginRead",
"infer_tabular_schema",
"origin_fingerprint",
"parse_managed_tabular_content",
]
@@ -0,0 +1,770 @@
from __future__ import annotations
import hashlib
import json
import time
from collections.abc import Mapping, Sequence
from datetime import datetime
from decimal import Decimal
from typing import Any, Callable
from sqlalchemy import or_, select
from sqlalchemy.orm import Session
from govoplan_core.auth import ApiPrincipal, has_scope
from govoplan_core.core.tabular_sources import (
TabularColumn,
TabularPreviewDiagnostic,
TabularPushdown,
TabularReadRequest,
TabularReadResult,
TabularSnapshotInput,
TabularSource,
TabularSourceAccessError,
TabularSourceNotFoundError,
TabularSourceHealth,
TabularSourceUnavailableError,
TabularSourceValidationError,
parse_tabular_csv,
)
from govoplan_core.core.runtime import get_registry
from govoplan_core.db.base import utcnow
from govoplan_connectors.backend.db.models import ConnectorTabularSource
from govoplan_connectors.backend.tabular_adapters import (
ManagedFileTabularAdapter,
PostgresqlTabularAdapter,
TabularOriginInspection,
)
READ_SCOPE = "connectors:source:read"
WRITE_SCOPE = "connectors:source:write"
ADMIN_SCOPE = "connectors:source:admin"
MAX_SNAPSHOT_ROWS = 10_000
MAX_SNAPSHOT_BYTES = 5_000_000
MAX_READ_ROWS = 500
MAX_READ_BYTES = 1_000_000
MAX_READ_TIMEOUT_MS = 2_000
class SqlTabularSourceProvider:
def __init__(
self,
*,
registry: object | None = None,
clock: Callable[[], float] = time.monotonic,
sql_adapter: PostgresqlTabularAdapter | None = None,
) -> None:
self._registry = registry
self._clock = clock
self._sql_adapter = sql_adapter or PostgresqlTabularAdapter()
def list_sources(
self,
session: object,
principal: object,
*,
query: str = "",
limit: int = 100,
) -> Sequence[TabularSource]:
db, api_principal = _context(session, principal, READ_SCOPE)
normalized_query = str(query or "").strip()
statement = select(ConnectorTabularSource).where(
ConnectorTabularSource.tenant_id == api_principal.tenant_id,
ConnectorTabularSource.deleted_at.is_(None),
ConnectorTabularSource.status == "active",
)
if normalized_query:
pattern = f"%{_escape_like(normalized_query)}%"
statement = statement.where(
or_(
ConnectorTabularSource.name.ilike(pattern, escape="\\"),
ConnectorTabularSource.source_name.ilike(pattern, escape="\\"),
)
)
statement = statement.order_by(
ConnectorTabularSource.updated_at.desc(),
ConnectorTabularSource.name,
).limit(max(1, min(int(limit), 100)))
return tuple(_source_dto(item) for item in db.scalars(statement))
def get_source(
self,
session: object,
principal: object,
*,
source_ref: str,
) -> TabularSource | None:
db, api_principal = _context(session, principal, READ_SCOPE)
item = _source_record(
db,
tenant_id=api_principal.tenant_id,
source_ref=source_ref,
)
return _source_dto(item) if item is not None else None
def read_source(
self,
session: object,
principal: object,
*,
request: TabularReadRequest,
) -> TabularReadResult:
db, api_principal = _context(session, principal, READ_SCOPE)
item = _source_record(
db,
tenant_id=api_principal.tenant_id,
source_ref=request.source_ref,
)
if item is None:
raise TabularSourceNotFoundError("Tabular source not found.")
if request.expected_fingerprint and request.expected_fingerprint != item.fingerprint:
raise TabularSourceValidationError(
"The source fingerprint changed; refresh the source node before running it."
)
limit = max(1, min(int(request.limit), MAX_READ_ROWS))
byte_limit = max(2, min(int(request.max_bytes), MAX_READ_BYTES))
timeout_ms = max(1, min(int(request.timeout_ms), MAX_READ_TIMEOUT_MS))
offset = max(0, int(request.offset))
diagnostics: list[TabularPreviewDiagnostic] = []
if limit != request.limit:
diagnostics.append(
_preview_diagnostic(
"preview.row_limit_tightened",
"The provider tightened the requested row limit.",
requested=request.limit,
effective=limit,
)
)
if byte_limit != request.max_bytes:
diagnostics.append(
_preview_diagnostic(
"preview.byte_limit_tightened",
"The provider tightened the requested byte limit.",
requested=request.max_bytes,
effective=byte_limit,
)
)
if timeout_ms != request.timeout_ms:
diagnostics.append(
_preview_diagnostic(
"preview.timeout_tightened",
"The provider tightened the requested time limit.",
requested=request.timeout_ms,
effective=timeout_ms,
)
)
selected_columns = tuple(dict.fromkeys(request.columns))
known_columns = {column["name"] for column in item.schema_}
unknown_columns = [column for column in selected_columns if column not in known_columns]
if unknown_columns:
raise TabularSourceValidationError(
f"Unknown source columns: {', '.join(unknown_columns)}"
)
started = self._clock()
source_rows: Sequence[Mapping[str, object]]
total_rows = item.row_count
source = _source_dto(item)
base_offset = offset
if item.provider == "managed_file":
read = self._file_adapter().read(
db,
api_principal,
metadata=item.metadata_,
)
if read.inspection.fingerprint != item.fingerprint:
raise TabularSourceValidationError(
"The managed file source changed; refresh and review it before previewing."
)
source_rows = read.rows[offset:]
total_rows = read.total_rows
source = _source_dto(item, inspection=read.inspection)
diagnostics.extend(read.diagnostics)
elif item.provider == "postgresql":
read = self._sql_adapter.read(
db,
api_principal,
metadata=item.metadata_,
columns=selected_columns,
offset=offset,
limit=limit + 1,
timeout_ms=timeout_ms,
)
source_rows = read.rows
total_rows = read.total_rows
source = _source_dto(item, inspection=read.inspection)
diagnostics.extend(read.diagnostics)
else:
source_rows = item.rows[offset:]
if int(max(0.0, self._clock() - started) * 1_000) >= timeout_ms:
raise TabularSourceUnavailableError(
"Tabular source preview exceeded its time budget."
)
rows: list[dict[str, object]] = []
returned_bytes = 2
stopped_for = ""
for row in source_rows:
if len(rows) >= limit:
stopped_for = "rows"
break
elapsed_ms = int(max(0.0, self._clock() - started) * 1_000)
if elapsed_ms >= timeout_ms:
if not rows:
raise TabularSourceUnavailableError(
"Tabular source preview exceeded its time budget."
)
stopped_for = "time"
break
selected = {
key: value
for key, value in row.items()
if not selected_columns or key in selected_columns
}
row_bytes = len(
json.dumps(
selected,
sort_keys=True,
separators=(",", ":"),
default=str,
).encode("utf-8")
)
additional_bytes = row_bytes + (1 if rows else 0)
if returned_bytes + additional_bytes > byte_limit:
if not rows:
raise TabularSourceValidationError(
"A single source row exceeds the preview byte limit."
)
stopped_for = "bytes"
break
rows.append(selected)
returned_bytes += additional_bytes
elapsed_ms = int(max(0.0, self._clock() - started) * 1_000)
if stopped_for:
labels = {
"rows": ("preview.row_limit_reached", "row"),
"bytes": ("preview.byte_limit_reached", "byte"),
"time": ("preview.timeout_reached", "time"),
}
code, label = labels[stopped_for]
diagnostics.append(
TabularPreviewDiagnostic(
severity="warning",
code=code,
message=f"The preview stopped at its effective {label} limit.",
)
)
return TabularReadResult(
source=source,
rows=tuple(rows),
total_rows=total_rows,
truncated=base_offset + len(rows) < total_rows,
returned_bytes=returned_bytes,
elapsed_ms=elapsed_ms,
effective_row_limit=limit,
effective_byte_limit=byte_limit,
effective_timeout_ms=timeout_ms,
diagnostics=tuple(diagnostics),
)
def create_file_source(
self,
session: object,
principal: object,
*,
name: str,
source_name: str,
file_asset_id: str,
file_version_id: str | None = None,
description: str | None = None,
delimiter: str = ",",
sheet_name: str | None = None,
) -> TabularSource:
db, api_principal = _context(session, principal, WRITE_SCOPE)
inspection = self._file_adapter().inspect(
db,
api_principal,
file_asset_id=file_asset_id,
file_version_id=file_version_id,
delimiter=delimiter,
sheet_name=sheet_name,
)
return self._create_origin(
db,
api_principal,
name=name,
source_name=source_name,
description=description,
inspection=inspection,
)
def create_sql_source(
self,
session: object,
principal: object,
*,
name: str,
source_name: str,
configuration_id: str,
table_name: str,
schema_name: str | None = None,
description: str | None = None,
) -> TabularSource:
db, api_principal = _context(session, principal, WRITE_SCOPE)
inspection = self._sql_adapter.inspect(
db,
api_principal,
configuration_id=configuration_id,
table_name=table_name,
schema_name=schema_name,
timeout_ms=MAX_READ_TIMEOUT_MS,
)
return self._create_origin(
db,
api_principal,
name=name,
source_name=source_name,
description=description,
inspection=inspection,
)
def refresh_source(
self,
session: object,
principal: object,
*,
source_ref: str,
) -> TabularSource:
db, api_principal = _context(session, principal, WRITE_SCOPE)
item = _source_record(
db,
tenant_id=api_principal.tenant_id,
source_ref=source_ref,
)
if item is None:
raise TabularSourceNotFoundError("Tabular source not found.")
if item.provider == "managed_file":
inspection = self._file_adapter().inspect(
db,
api_principal,
file_asset_id=str(item.metadata_.get("file_asset_id") or ""),
file_version_id=None,
delimiter=str(item.metadata_.get("delimiter") or ","),
sheet_name=_clean_optional(item.metadata_.get("sheet_name")),
)
elif item.provider == "postgresql":
inspection = self._sql_adapter.inspect(
db,
api_principal,
configuration_id=str(
item.metadata_.get("configuration_id") or ""
),
table_name=str(item.metadata_.get("table_name") or ""),
schema_name=_clean_optional(item.metadata_.get("schema_name")),
timeout_ms=MAX_READ_TIMEOUT_MS,
)
else:
raise TabularSourceValidationError(
"Immutable snapshots cannot be refreshed; import a replacement snapshot."
)
item.schema_version += 1
item.schema_ = [_column_payload(column) for column in inspection.schema]
item.fingerprint = inspection.fingerprint
item.row_count = inspection.row_count
item.byte_count = inspection.byte_count
item.metadata_ = {
**dict(inspection.metadata),
"discovery_fingerprint": inspection.fingerprint,
}
item.updated_by = _actor_id(api_principal)
db.flush()
return _source_dto(item, inspection=inspection)
def _create_origin(
self,
db: Session,
principal: ApiPrincipal,
*,
name: str,
source_name: str,
description: str | None,
inspection: TabularOriginInspection,
) -> TabularSource:
clean_name = str(name or "").strip()
clean_source_name = str(source_name or "").strip()
if not clean_name or not clean_source_name:
raise TabularSourceValidationError(
"Tabular source name and source identifier are required."
)
existing = db.scalar(
select(ConnectorTabularSource.id).where(
ConnectorTabularSource.tenant_id == principal.tenant_id,
ConnectorTabularSource.source_name == clean_source_name,
)
)
if existing is not None:
raise TabularSourceValidationError(
f"A tabular source named {clean_source_name!r} already exists."
)
actor_id = _actor_id(principal)
item = ConnectorTabularSource(
tenant_id=principal.tenant_id,
provider=inspection.provider,
source_name=clean_source_name,
name=clean_name,
description=_clean_optional(description),
status="active",
schema_version=1,
schema_=[_column_payload(column) for column in inspection.schema],
rows=[],
fingerprint=inspection.fingerprint,
row_count=inspection.row_count,
byte_count=inspection.byte_count,
metadata_={
**dict(inspection.metadata),
"discovery_fingerprint": inspection.fingerprint,
},
created_by=actor_id,
updated_by=actor_id,
)
db.add(item)
db.flush()
return _source_dto(item, inspection=inspection)
def _file_adapter(self) -> ManagedFileTabularAdapter:
return ManagedFileTabularAdapter(self._registry or get_registry())
def create_snapshot(
self,
session: object,
principal: object,
*,
snapshot: TabularSnapshotInput,
source_id: str | None = None,
) -> TabularSource:
db, api_principal = _context(session, principal, WRITE_SCOPE)
name = snapshot.name.strip()
source_name = snapshot.source_name.strip()
if not name:
raise TabularSourceValidationError("Snapshot name is required.")
if not source_name:
raise TabularSourceValidationError("Snapshot source name is required.")
if len(snapshot.rows) > MAX_SNAPSHOT_ROWS:
raise TabularSourceValidationError(
f"Snapshots are limited to {MAX_SNAPSHOT_ROWS:,} rows."
)
rows = [_json_row(row) for row in snapshot.rows]
encoded = json.dumps(rows, sort_keys=True, separators=(",", ":"), default=str).encode("utf-8")
if len(encoded) > MAX_SNAPSHOT_BYTES:
raise TabularSourceValidationError(
f"Snapshots are limited to {MAX_SNAPSHOT_BYTES // 1_000_000} MB."
)
existing = db.scalar(
select(ConnectorTabularSource.id).where(
ConnectorTabularSource.tenant_id == api_principal.tenant_id,
ConnectorTabularSource.source_name == source_name,
)
)
if existing is not None:
raise TabularSourceValidationError(
f"A tabular source named {source_name!r} already exists."
)
schema = infer_schema(rows)
fingerprint = snapshot_fingerprint(rows, schema)
actor_id = _actor_id(api_principal)
item = ConnectorTabularSource(
tenant_id=api_principal.tenant_id,
provider="snapshot",
source_name=source_name,
name=name,
description=_clean_optional(snapshot.description),
status="active",
schema_version=1,
schema_=[_column_payload(column) for column in schema],
rows=rows,
fingerprint=fingerprint,
row_count=len(rows),
byte_count=len(encoded),
metadata_=dict(snapshot.metadata),
created_by=actor_id,
updated_by=actor_id,
)
if source_id:
item.id = source_id
db.add(item)
db.flush()
return _source_dto(item)
def delete_snapshot(
self,
session: object,
principal: object,
*,
source_ref: str,
) -> TabularSource:
db, api_principal = _context(session, principal, WRITE_SCOPE)
item = _source_record(
db,
tenant_id=api_principal.tenant_id,
source_ref=source_ref,
)
if item is None:
raise TabularSourceNotFoundError("Tabular source not found.")
item.deleted_at = utcnow()
item.status = "retired"
item.updated_by = _actor_id(api_principal)
db.flush()
return _source_dto(item)
def parse_csv_snapshot(csv_text: str, *, delimiter: str) -> tuple[Mapping[str, object], ...]:
return parse_tabular_csv(
csv_text,
delimiter=delimiter,
max_rows=MAX_SNAPSHOT_ROWS,
)
def infer_schema(rows: Sequence[Mapping[str, object]]) -> tuple[TabularColumn, ...]:
names: list[str] = []
for row in rows:
for name in row:
if name not in names:
names.append(name)
result: list[TabularColumn] = []
for name in names:
values = [row.get(name) for row in rows]
concrete = [value for value in values if value is not None]
data_type = _type_name(concrete[0]) if concrete else "unknown"
if any(_type_name(value) != data_type for value in concrete[1:]):
data_type = "mixed"
result.append(
TabularColumn(
name=name,
data_type=data_type,
nullable=len(concrete) != len(values),
)
)
return tuple(result)
def snapshot_fingerprint(
rows: Sequence[Mapping[str, object]],
schema: Sequence[TabularColumn],
) -> str:
payload = {
"schema": [_column_payload(column) for column in schema],
"rows": [dict(row) for row in rows],
}
encoded = json.dumps(payload, sort_keys=True, separators=(",", ":"), default=str)
return hashlib.sha256(encoded.encode("utf-8")).hexdigest()
def _source_record(
session: Session,
*,
tenant_id: str,
source_ref: str,
) -> ConnectorTabularSource | None:
prefix, separator, source_id = str(source_ref or "").partition(":")
provider_by_prefix = {
"snapshot": "snapshot",
"file": "managed_file",
"sql": "postgresql",
}
provider = provider_by_prefix.get(prefix)
if not separator or not source_id or provider is None:
return None
return session.scalar(
select(ConnectorTabularSource).where(
ConnectorTabularSource.id == source_id,
ConnectorTabularSource.tenant_id == tenant_id,
ConnectorTabularSource.provider == provider,
ConnectorTabularSource.deleted_at.is_(None),
)
)
def _source_dto(
item: ConnectorTabularSource,
*,
inspection: TabularOriginInspection | None = None,
) -> TabularSource:
prefix_by_provider = {
"snapshot": "snapshot",
"managed_file": "file",
"postgresql": "sql",
}
source_mode = {
"managed_file": "file_backed",
"postgresql": "live",
}.get(item.provider, "cached")
if inspection is not None:
pushdown = inspection.pushdown
health = inspection.health
elif item.provider == "managed_file":
pushdown = TabularPushdown(projections=True, pagination=True)
health = TabularSourceHealth(
status="unknown",
code="files.exact_version_not_checked",
summary="The exact managed file version will be re-authorized and integrity-checked on preview.",
checked_at=item.updated_at,
details={
"file_version_id": item.metadata_.get("file_version_id"),
},
)
elif item.provider == "postgresql":
pushdown = TabularPushdown(projections=True, pagination=True)
health = TabularSourceHealth(
status="unknown",
code="sql.health_not_checked",
summary="The live SQL source will be checked against its pinned configuration, credential, and schema on preview.",
checked_at=item.updated_at,
details={
"configuration_id": item.metadata_.get("configuration_id"),
"configuration_revision": item.metadata_.get(
"configuration_revision"
),
},
)
else:
pushdown = TabularPushdown(
projections=True,
pagination=True,
)
health = TabularSourceHealth(
status="healthy",
code="snapshot.ready",
summary="The immutable connector snapshot is ready.",
checked_at=item.updated_at,
details={"immutable": True},
)
return TabularSource(
ref=f"{prefix_by_provider.get(item.provider, 'snapshot')}:{item.id}",
provider=item.provider,
source_name=item.source_name,
name=item.name,
description=item.description,
schema=tuple(TabularColumn(**column) for column in item.schema_),
schema_version=str(item.schema_version),
fingerprint=item.fingerprint,
row_count=item.row_count,
byte_count=item.byte_count,
updated_at=item.updated_at,
capabilities=("read", "preview"),
metadata=dict(item.metadata_),
source_mode=source_mode,
pushdown=pushdown,
health=health,
)
def _preview_diagnostic(
code: str,
message: str,
*,
requested: int,
effective: int,
) -> TabularPreviewDiagnostic:
return TabularPreviewDiagnostic(
severity="info",
code=code,
message=message,
details={"requested": requested, "effective": effective},
)
def _context(
session: object,
principal: object,
required_scope: str,
) -> tuple[Session, ApiPrincipal]:
if not isinstance(session, Session):
raise TypeError("Tabular source providers require a SQLAlchemy session.")
if not isinstance(principal, ApiPrincipal):
raise TabularSourceAccessError("A tenant API principal is required.")
accepted_scopes = {required_scope, ADMIN_SCOPE}
if required_scope == READ_SCOPE:
accepted_scopes.update(
{
WRITE_SCOPE,
"datasources:catalogue:read",
"datasources:source:write",
"datasources:source:admin",
}
)
if not any(has_scope(principal, scope) for scope in accepted_scopes):
raise TabularSourceAccessError(f"Missing scope: {required_scope}")
return session, principal
def _json_row(row: Mapping[str, object]) -> dict[str, Any]:
normalized = {str(key).strip(): value for key, value in row.items()}
if not normalized or any(not key for key in normalized):
raise TabularSourceValidationError("Every snapshot row needs named columns.")
try:
json.dumps(normalized, default=_unsupported_json)
except (TypeError, ValueError) as exc:
raise TabularSourceValidationError(f"Snapshot values must be JSON compatible: {exc}") from exc
return json.loads(json.dumps(normalized, default=_unsupported_json))
def _unsupported_json(value: object) -> object:
if isinstance(value, (datetime, Decimal)):
return str(value)
raise TypeError(f"{type(value).__name__} is not JSON serializable")
def _type_name(value: object) -> str:
if isinstance(value, bool):
return "boolean"
if isinstance(value, int):
return "integer"
if isinstance(value, (float, Decimal)):
return "number"
if isinstance(value, str):
return "string"
if isinstance(value, list):
return "array"
if isinstance(value, dict):
return "object"
return type(value).__name__.lower()
def _column_payload(column: TabularColumn) -> dict[str, object]:
return {
"name": column.name,
"data_type": column.data_type,
"nullable": column.nullable,
}
def _actor_id(principal: ApiPrincipal) -> str | None:
return principal.account_id or principal.membership_id or principal.identity_id
def _clean_optional(value: str | None) -> str | None:
cleaned = str(value or "").strip()
return cleaned or None
def _escape_like(value: str) -> str:
return value.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
__all__ = [
"ADMIN_SCOPE",
"MAX_READ_ROWS",
"MAX_READ_BYTES",
"MAX_READ_TIMEOUT_MS",
"MAX_SNAPSHOT_BYTES",
"MAX_SNAPSHOT_ROWS",
"READ_SCOPE",
"SqlTabularSourceProvider",
"WRITE_SCOPE",
"infer_schema",
"parse_csv_snapshot",
"snapshot_fingerprint",
]
+1
View File
@@ -0,0 +1 @@
+92
View File
@@ -0,0 +1,92 @@
from __future__ import annotations
import unittest
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.datasources import DatasourceOriginReadRequest
from govoplan_core.core.tabular_sources import TabularSnapshotInput
from govoplan_core.db.base import Base
from govoplan_connectors.backend.datasource_origins import (
ConnectorDatasourceOriginProvider,
)
from govoplan_connectors.backend.db.models import ConnectorTabularSource
from govoplan_connectors.backend.tabular_sources import (
WRITE_SCOPE,
SqlTabularSourceProvider,
)
def principal(*, scopes: tuple[str, ...]) -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id="tenant-1",
scopes=frozenset(scopes),
),
account=object(),
user=object(),
)
class ConnectorDatasourceOriginTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite:///:memory:")
Base.metadata.create_all(
self.engine,
tables=[ConnectorTabularSource.__table__],
)
self.Session = sessionmaker(bind=self.engine)
self.session = self.Session()
provider = SqlTabularSourceProvider()
self.source = provider.create_snapshot(
self.session,
principal(scopes=(WRITE_SCOPE,)),
snapshot=TabularSnapshotInput(
name="Imported cases",
source_name="imported_cases",
rows=({"id": 1, "name": "Ada"},),
),
)
self.session.commit()
self.origins = ConnectorDatasourceOriginProvider(provider)
def tearDown(self) -> None:
self.session.close()
Base.metadata.drop_all(
self.engine,
tables=[ConnectorTabularSource.__table__],
)
self.engine.dispose()
def test_datasource_reader_can_discover_and_read_connector_origin(self) -> None:
datasource_principal = principal(
scopes=("datasources:catalogue:read",),
)
origins = self.origins.list_origins(
self.session,
datasource_principal,
)
result = self.origins.read_origin(
self.session,
datasource_principal,
request=DatasourceOriginReadRequest(origin_ref=self.source.ref),
)
self.assertEqual((self.source.ref,), tuple(item.ref for item in origins))
self.assertEqual(("live", "cached"), origins[0].supported_modes)
self.assertEqual(({"id": 1, "name": "Ada"},), result.rows)
self.assertEqual("cached", origins[0].source_mode)
self.assertTrue(origins[0].pushdown.projections)
self.assertEqual("healthy", origins[0].health.status)
self.assertGreater(result.returned_bytes, 2)
self.assertEqual(1_000_000, result.effective_byte_limit)
if __name__ == "__main__":
unittest.main()
+339
View File
@@ -0,0 +1,339 @@
from __future__ import annotations
import json
import unittest
from datetime import UTC, datetime
from sqlalchemy import create_engine
from sqlalchemy.orm import Session
from govoplan_core.core.dsar import DsarProvider, DsarSubjectRef
from govoplan_core.db.base import Base
from govoplan_core.privacy.dsar_workflow import (
create_data_subject_request,
search_data_subject_request,
)
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorDefinitionRevision,
ConnectorSanctionsAcquisitionRun,
ConnectorSimulationRun,
ConnectorTabularSource,
)
from govoplan_connectors.backend.dsar_provider import (
CONNECTORS_DSAR_CAPABILITY,
ConnectorsDsarProvider,
)
from govoplan_connectors.backend.manifest import manifest
NOW = datetime(2026, 8, 22, 9, 0, tzinfo=UTC)
class _Registry:
def __init__(self, provider: ConnectorsDsarProvider) -> None:
self.provider = provider
def capability_names(self):
return (CONNECTORS_DSAR_CAPABILITY,)
def capability_owner(self, name):
if name != CONNECTORS_DSAR_CAPABILITY:
raise KeyError(name)
return "connectors"
def tenant_entitlement_resolver(self):
class _Resolver:
@staticmethod
def resolve(session, tenant_id):
del session, tenant_id
return type("State", (), {"effective_modules": ("connectors",)})()
return _Resolver()
def require_tenant_capability(self, name, session, **kwargs):
del session, kwargs
if name != CONNECTORS_DSAR_CAPABILITY:
raise KeyError(name)
return self.provider
def manifests(self):
return (type("Manifest", (), {"id": "connectors"})(),)
class ConnectorsDsarProviderTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(self.engine)
self.session = Session(self.engine)
self.provider = ConnectorsDsarProvider()
self.assertIsInstance(self.provider, DsarProvider)
self._seed()
self.session.commit()
def tearDown(self) -> None:
self.session.close()
self.engine.dispose()
def _seed(self) -> None:
self.session.add_all(
(
ConnectorTabularSource(
id="source-1",
tenant_id="tenant-1",
provider="snapshot",
source_name="people",
name="People import",
description="Do not export this business description",
status="active",
schema_version=1,
schema_=[{"name": "email"}],
rows=[{"email": "third-party@example.test"}],
fingerprint="source-fingerprint-do-not-export",
row_count=1,
byte_count=100,
metadata_={"secret": "source-metadata-do-not-export"},
created_by="account-1",
updated_by="account-1",
created_at=NOW,
updated_at=NOW,
),
ConnectorTabularSource(
id="source-other",
tenant_id="tenant-2",
provider="snapshot",
source_name="other",
name="Other tenant",
status="active",
schema_version=1,
schema_=[],
rows=[],
fingerprint="other-fingerprint",
row_count=0,
byte_count=0,
metadata_={},
created_by="account-1",
updated_by="account-1",
),
ConnectorSanctionsAcquisitionRun(
id="acquisition-1",
tenant_id="tenant-1",
provider_id="un",
source_id="consolidated",
status="complete",
attempt_count=1,
request_evidence={"secret": "request-evidence-do-not-export"},
response_evidence={"secret": "response-evidence-do-not-export"},
started_at=NOW,
finished_at=NOW,
snapshot_id="snapshot-1",
error="transport-detail-do-not-export",
created_by="account-1",
created_at=NOW,
updated_at=NOW,
),
ConnectorDefinition(
id="definition-1",
tenant_id="tenant-1",
definition_key="address-reader",
name="Address reader",
description="Definition detail",
status="active",
current_revision=1,
source_package="package-secret-do-not-export",
local_definition=True,
created_at=NOW,
updated_at=NOW,
),
ConnectorDefinitionRevision(
id="definition-revision-1",
definition_id="definition-1",
revision=1,
specification={"secret": "specification-do-not-export"},
definition_hash="definition-hash-do-not-export",
origin="local",
package_ref="package-ref-do-not-export",
created_by="account-1",
created_at=NOW,
updated_at=NOW,
),
ConnectorConfiguration(
id="configuration-1",
tenant_id="tenant-1",
definition_id="definition-1",
name="Production addresses",
status="active",
endpoint_url="https://secret.example.test/api",
credential_ref="vault://secret-do-not-export",
base_definition_revision=1,
local_overrides={"secret": "override-do-not-export"},
protected_paths=["secret"],
effective_configuration={"secret": "effective-do-not-export"},
effective_hash="configuration-hash-do-not-export",
resource_revision=2,
ambiguity_policy="manual_review",
updated_by="account-1",
created_at=NOW,
updated_at=NOW,
),
ConnectorSimulationRun(
id="simulation-1",
tenant_id="tenant-1",
configuration_id="configuration-1",
mode="dry_run",
idempotency_key="simulation-idempotency-do-not-export",
request_hash="simulation-request-hash-do-not-export",
status="complete",
review_state="approved",
definition_revision=1,
configuration_revision=2,
configuration_hash="simulation-config-hash-do-not-export",
input_hash="simulation-input-hash-do-not-export",
summary={"secret": "summary-do-not-export"},
effects=[{"secret": "effect-do-not-export"}],
diagnostics=[{"secret": "diagnostic-do-not-export"}],
provenance={"secret": "provenance-do-not-export"},
created_by="account-1",
reviewed_by="account-1",
reviewed_at=NOW,
review_reason="review-reason-do-not-export",
created_at=NOW,
updated_at=NOW,
),
)
)
@staticmethod
def _subject() -> DsarSubjectRef:
return DsarSubjectRef(account_id="account-1")
def test_search_exports_minimized_operator_attribution(self) -> None:
records = self.provider.search_subject(
self.session, tenant_id="tenant-1", subject=self._subject()
)
self.assertEqual(
{
"source_actor_attribution",
"acquisition_actor_attribution",
"definition_actor_attribution",
"configuration_actor_attribution",
"simulation_actor_attribution",
},
{record.resource_type for record in records},
)
exported = json.dumps([record.to_dict() for record in records])
for excluded in (
"third-party@example.test",
"source-fingerprint-do-not-export",
"source-metadata-do-not-export",
"request-evidence-do-not-export",
"response-evidence-do-not-export",
"transport-detail-do-not-export",
"specification-do-not-export",
"definition-hash-do-not-export",
"package-ref-do-not-export",
"https://secret.example.test/api",
"vault://secret-do-not-export",
"override-do-not-export",
"effective-do-not-export",
"configuration-hash-do-not-export",
"simulation-idempotency-do-not-export",
"simulation-request-hash-do-not-export",
"simulation-config-hash-do-not-export",
"simulation-input-hash-do-not-export",
"summary-do-not-export",
"effect-do-not-export",
"diagnostic-do-not-export",
"provenance-do-not-export",
"review-reason-do-not-export",
):
self.assertNotIn(excluded, exported)
def test_requires_exact_account_and_enforces_tenant(self) -> None:
email_only = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(email="operator@example.test"),
)
conflict = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
external_references={"connectors.account": "account-other"},
),
)
records = self.provider.search_subject(
self.session, tenant_id="tenant-1", subject=self._subject()
)
self.assertEqual((), email_only)
self.assertEqual((), conflict)
self.assertNotIn("source-other", {record.resource_id for record in records})
def test_object_narrowing_does_not_broaden_the_search(self) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
external_references={"connectors.simulation": "simulation-1"},
),
)
self.assertEqual(
[("simulation_actor_attribution", "simulation-1")],
[(record.resource_type, record.resource_id) for record in records],
)
def test_erasure_retains_external_operation_evidence(self) -> None:
records = self.provider.search_subject(
self.session, tenant_id="tenant-1", subject=self._subject()
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=self._subject(),
records=records,
)
self.assertTrue(actions)
self.assertTrue(
all(action.kind == "retain" and not action.executable for action in actions)
)
results = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=self._subject(),
actions=actions,
request_id="dsar-connectors-1",
)
self.assertTrue(all(result.status == "blocked" for result in results))
def test_manifest_and_core_workflow_discover_provider(self) -> None:
self.assertIn(CONNECTORS_DSAR_CAPABILITY, manifest.capability_factories)
self.assertIn(
"connectors.data-subject-requests",
{topic.id for topic in manifest.documentation},
)
row = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-CONNECTORS-1",
request_kind="access",
subject=self._subject(),
purpose="Connector attribution access request",
legal_basis=None,
due_at=None,
requested_by_account_id="operator-1",
)
search_data_subject_request(
self.session,
registry=_Registry(self.provider),
row=row,
expected_revision=row.resource_revision,
)
self.assertEqual("searched", row.status)
self.assertEqual(5, row.search_result["record_count"])
if __name__ == "__main__":
unittest.main()
+180
View File
@@ -0,0 +1,180 @@
from __future__ import annotations
import unittest
from unittest.mock import patch
from defusedxml import ElementTree as SafeET
from fastapi import HTTPException
from govoplan_connectors.backend.feeds import (
FEED_PRIVATE_PUBLISH_SCOPE,
FEED_PUBLISH_SCOPE,
ConnectorFeedProvider,
feed_rows,
)
from govoplan_connectors.backend.router import api_render_feed
from govoplan_connectors.backend.schemas import FeedRenderPayload
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.feeds import (
FeedCapabilityError,
FeedEntry,
FeedRenderRequest,
)
from govoplan_core.security.http_fetch import HttpFetchResponse
RSS = b"""<?xml version="1.0"?>
<rss version="2.0"><channel>
<title>Decisions</title><link>https://example.test/</link>
<description>Published decisions</description>
<item><guid>decision-1</guid><title>Decision one</title>
<link>https://example.test/1</link>
<pubDate>Fri, 31 Jul 2026 10:00:00 GMT</pubDate>
<category>planning</category>
</item>
</channel></rss>"""
ATOM = b"""<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<id>https://example.test/feed</id><title>Updates</title>
<updated>2026-07-31T10:00:00Z</updated>
<link href="https://example.test/" />
<entry><id>update-1</id><title>Update one</title>
<updated>2026-07-31T10:00:00Z</updated>
<link href="https://example.test/update-1" />
</entry>
</feed>"""
class ConnectorFeedProviderTests(unittest.TestCase):
def setUp(self) -> None:
self.provider = ConnectorFeedProvider()
def test_rss_and_atom_are_normalized_to_tabular_entries(self) -> None:
rss = self.provider.parse(RSS, source_url="https://example.test/rss")
atom = self.provider.parse(ATOM, source_url="https://example.test/atom")
self.assertEqual("rss", rss.format)
self.assertEqual("decision-1", rss.entries[0].id)
self.assertEqual("atom", atom.format)
self.assertEqual("https://example.test/update-1", atom.entries[0].url)
self.assertEqual("decision-1", feed_rows(rss)[0]["id"])
self.assertEqual(64, len(rss.sha256))
def test_fetch_records_transport_freshness_and_provenance(self) -> None:
with patch(
"govoplan_connectors.backend.feeds.fetch_http",
return_value=HttpFetchResponse(
status=200,
headers={
"Content-Type": "application/rss+xml",
"Cache-Control": "public, max-age=600",
"ETag": '"feed-1"',
},
body=RSS,
),
):
document = self.provider.fetch("https://example.test/rss")
self.assertEqual('"feed-1"', document.etag)
self.assertIsNotNone(document.acquired_at)
self.assertEqual(600, int((document.fresh_until - document.acquired_at).total_seconds()))
self.assertEqual(len(RSS), document.metadata["byte_count"])
def test_render_filters_entries_by_explicit_visibility(self) -> None:
request = FeedRenderRequest(
format="atom",
title="Public updates",
feed_url="https://example.test/feed.atom",
home_url="https://example.test/",
entries=(
FeedEntry(id="public-1", title="Public", visibility="public"),
FeedEntry(id="tenant-1", title="Tenant", visibility="tenant"),
),
allowed_visibilities=frozenset({"public"}),
)
result = self.provider.render(request)
root = SafeET.fromstring(result.body)
self.assertEqual(1, result.included_entries)
self.assertEqual(1, result.excluded_entries)
self.assertIn(b"Public", result.body)
self.assertNotIn(b"Tenant", result.body)
self.assertTrue(root.tag.endswith("feed"))
def test_unsafe_xml_is_rejected(self) -> None:
payload = b'<!DOCTYPE x [<!ENTITY y SYSTEM "file:///etc/passwd">]><rss>&y;</rss>'
with self.assertRaisesRegex(FeedCapabilityError, "not safe or valid"):
self.provider.parse(payload, source_url="https://example.test/rss")
def test_render_api_derives_visibility_from_audience_and_permissions(self) -> None:
entries = [
{
"id": visibility,
"title": visibility.title(),
"visibility": visibility,
"source_kind": source_kind,
"source_module": source_module,
"source_ref": f"{source_kind}:{visibility}",
"source_revision": "7",
}
for visibility, source_kind, source_module in (
("public", "publication", "docs"),
("tenant", "case", "cases"),
("private", "report", "reporting"),
)
]
public_payload = FeedRenderPayload(
format="rss",
title="Selected GovOPlaN updates",
feed_url="https://example.test/feed.xml",
home_url="https://example.test/",
audience="public",
entries=entries,
)
public = api_render_feed(
public_payload,
principal=_principal(FEED_PUBLISH_SCOPE),
)
self.assertEqual("public", public.headers["x-govoplan-feed-audience"])
self.assertEqual("1", public.headers["x-govoplan-feed-included"])
self.assertEqual("2", public.headers["x-govoplan-feed-excluded"])
self.assertIn(b"Public", public.body)
self.assertNotIn(b"Tenant", public.body)
restricted_payload = public_payload.model_copy(update={"audience": "private"})
with self.assertRaises(HTTPException) as denied:
api_render_feed(
restricted_payload,
principal=_principal(FEED_PUBLISH_SCOPE),
)
self.assertEqual(403, denied.exception.status_code)
restricted = api_render_feed(
restricted_payload,
principal=_principal(
FEED_PUBLISH_SCOPE,
FEED_PRIVATE_PUBLISH_SCOPE,
),
)
self.assertEqual("3", restricted.headers["x-govoplan-feed-included"])
self.assertIn(b"Private", restricted.body)
def _principal(*scopes: str) -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id="tenant-1",
scopes=frozenset(scopes),
),
account=object(),
user=object(),
)
if __name__ == "__main__":
unittest.main()
+339
View File
@@ -0,0 +1,339 @@
from __future__ import annotations
from types import SimpleNamespace
import unittest
from unittest.mock import patch
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.db.base import Base
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorDefinitionRevision,
ConnectorSimulationRun,
)
from govoplan_connectors.backend.governed_runtime import (
GovernedConnectorError,
create_configuration,
execute_run,
list_configurations,
review_run,
update_configuration,
upsert_definition,
)
from govoplan_connectors.backend.governed_schemas import (
ConnectorConfigurationCreateRequest,
ConnectorConfigurationUpdateRequest,
ConnectorDefinitionUpsertRequest,
ConnectorReviewRequest,
ConnectorRunRequest,
)
def principal(tenant_id: str = "tenant-1") -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id=tenant_id,
scopes=frozenset(
{
"connectors:source:read",
"connectors:source:write",
"connectors:source:admin",
}
),
),
account=SimpleNamespace(id="account-1"),
user=SimpleNamespace(id="user-1"),
)
def definition_payload(
*,
mapping_version: str = "1",
package_ref: str = "municipal-addresses@1",
timeout_seconds: int = 10,
) -> ConnectorDefinitionUpsertRequest:
return ConnectorDefinitionUpsertRequest.model_validate(
{
"definition_key": "municipal.addresses",
"name": "Municipal addresses",
"description": "A package-managed reference connector.",
"origin": "package",
"package_ref": package_ref,
"specification": {
"provider": "municipal-directory",
"protocol": "rest",
"capabilities": ["discover", "read", "dry_run"],
"input_schema": {"type": "object"},
"output_schema": {"type": "object"},
"mapping": {
"version": mapping_version,
"rules": [
{
"source": "external_id",
"target": "address.external_id",
"required": True,
},
{
"source": "street",
"target": "address.street",
"required": True,
},
],
},
"validation_rules": [
{
"kind": "unique",
"field": "address.external_id",
"severity": "error",
"code": "addresses.external_id.ambiguous",
"message": "The external identifier is not unique.",
}
],
"dry_run": {
"supported": True,
"simulation_supported": True,
"max_items": 50,
"redacted_fields": ["address.street"],
"sample_rows": [
{"external_id": "A-1", "street": "Sample street"}
],
},
"audit": {
"event_prefix": "connectors.municipal_addresses",
"expected_events": ["simulation.completed"],
"evidence_fields": ["input_hash", "configuration_hash"],
},
"privacy_classification": "confidential",
"retention_class": "connector-preview-30d",
"operational_limits": {"timeout_seconds": timeout_seconds},
"retry_policy": {"max_attempts": 2},
},
}
)
class GovernedConnectorRuntimeTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite:///:memory:")
self.tables = [
ConnectorDefinition.__table__,
ConnectorDefinitionRevision.__table__,
ConnectorConfiguration.__table__,
ConnectorSimulationRun.__table__,
]
Base.metadata.create_all(self.engine, tables=self.tables)
self.Session = sessionmaker(bind=self.engine)
self.session = self.Session()
self.audit = patch(
"govoplan_connectors.backend.governed_runtime.audit_from_principal"
)
self.audit_mock = self.audit.start()
def tearDown(self) -> None:
self.audit.stop()
self.session.close()
Base.metadata.drop_all(self.engine, tables=reversed(self.tables))
self.engine.dispose()
def _configuration(
self,
*,
ambiguity_policy: str = "manual_review",
):
definition = upsert_definition(
self.session,
principal(),
definition_payload(),
)
return create_configuration(
self.session,
principal(),
ConnectorConfigurationCreateRequest(
definition_id=definition.id,
name=f"Address import {ambiguity_policy}",
endpoint_url="https://directory.example.invalid/v1",
credential_ref="vault://connectors/address-reader",
local_overrides={"retry_policy": {"max_attempts": 5}},
ambiguity_policy=ambiguity_policy,
status="active",
),
)
def test_package_update_is_explicit_and_preserves_local_overrides(self) -> None:
configuration = self._configuration()
updated_definition = upsert_definition(
self.session,
principal(),
definition_payload(
mapping_version="2",
package_ref="municipal-addresses@2",
timeout_seconds=20,
),
)
unchanged = next(
item
for item in list_configurations(self.session, tenant_id="tenant-1")
if item.id == configuration.id
)
self.assertEqual(2, updated_definition.current_revision)
self.assertTrue(unchanged.update_available)
self.assertEqual("1", unchanged.effective_configuration["mapping"]["version"])
self.assertEqual(5, unchanged.effective_configuration["retry_policy"]["max_attempts"])
self.assertEqual(["retry_policy.max_attempts"], unchanged.protected_paths)
adopted = update_configuration(
self.session,
principal(),
configuration_id=configuration.id,
payload=ConnectorConfigurationUpdateRequest(
expected_revision=configuration.resource_revision,
adopt_latest_definition=True,
),
)
self.assertFalse(adopted.update_available)
self.assertEqual("2", adopted.effective_configuration["mapping"]["version"])
self.assertEqual(
20,
adopted.effective_configuration["operational_limits"]["timeout_seconds"],
)
self.assertEqual(5, adopted.effective_configuration["retry_policy"]["max_attempts"])
self.assertEqual(["retry_policy.max_attempts"], adopted.protected_paths)
def test_ambiguous_simulation_requires_review_and_is_idempotent(self) -> None:
configuration = self._configuration()
payload = ConnectorRunRequest(
idempotency_key="simulation-1",
external_revision="directory-etag-22",
input_rows=[
{"external_id": "duplicate", "street": "First"},
{"external_id": "duplicate", "street": "Second"},
],
)
created = execute_run(
self.session,
principal(),
configuration_id=configuration.id,
mode="simulation",
payload=payload,
)
replayed = execute_run(
self.session,
principal(),
configuration_id=configuration.id,
mode="simulation",
payload=payload,
)
self.assertEqual(created.id, replayed.id)
self.assertEqual("manual_review", created.status)
self.assertEqual("pending", created.review_state)
self.assertEqual(2, created.summary["ambiguous"])
self.assertEqual("<redacted>", created.effects[0]["sample"]["address"]["street"])
self.assertEqual("directory-etag-22", created.provenance["external_revision"])
reviewed = review_run(
self.session,
principal(),
run_id=created.id,
payload=ConnectorReviewRequest(
decision="approved",
reason="The duplicate rows represent an approved upstream alias.",
),
)
self.assertEqual("approved", reviewed.review_state)
self.assertEqual("review_approved", reviewed.status)
with self.assertRaisesRegex(GovernedConnectorError, "different run inputs"):
execute_run(
self.session,
principal(),
configuration_id=configuration.id,
mode="simulation",
payload=ConnectorRunRequest(
idempotency_key="simulation-1",
input_rows=[{"external_id": "other", "street": "Other"}],
),
)
def test_ambiguity_policy_can_quarantine_or_reject(self) -> None:
for policy, expected_status, expected_review in (
("quarantine", "quarantined", "quarantined"),
("reject", "rejected", "not_required"),
):
configuration = self._configuration(ambiguity_policy=policy)
result = execute_run(
self.session,
principal(),
configuration_id=configuration.id,
mode="dry_run",
payload=ConnectorRunRequest(
idempotency_key=f"{policy}-1",
input_rows=[
{"external_id": "same", "street": "First"},
{"external_id": "same", "street": "Second"},
],
),
)
self.assertEqual(expected_status, result.status)
self.assertEqual(expected_review, result.review_state)
def test_endpoint_credentials_and_stale_saves_are_rejected(self) -> None:
definition = upsert_definition(
self.session,
principal(),
definition_payload(),
)
with self.assertRaisesRegex(GovernedConnectorError, "must not contain credentials"):
create_configuration(
self.session,
principal(),
ConnectorConfigurationCreateRequest(
definition_id=definition.id,
name="Unsafe",
endpoint_url="https://user:secret@example.invalid/v1",
),
)
configuration = self._configuration()
with self.assertRaisesRegex(GovernedConnectorError, "reload it before saving"):
update_configuration(
self.session,
principal(),
configuration_id=configuration.id,
payload=ConnectorConfigurationUpdateRequest(
expected_revision=configuration.resource_revision + 1,
name="Stale",
),
)
def test_definition_ownership_cannot_change_implicitly(self) -> None:
package_definition = upsert_definition(
self.session,
principal(),
definition_payload(),
)
local_payload = definition_payload().model_copy(
update={"origin": "local", "package_ref": None}
)
with self.assertRaisesRegex(
GovernedConnectorError,
"configuration overrides",
):
upsert_definition(self.session, principal(), local_payload)
self.assertFalse(package_definition.local_definition)
if __name__ == "__main__":
unittest.main()
+47
View File
@@ -0,0 +1,47 @@
from __future__ import annotations
import unittest
from govoplan_core.core.tabular_sources import (
CAPABILITY_CONNECTORS_TABULAR_SNAPSHOT_WRITER,
CAPABILITY_CONNECTORS_TABULAR_SOURCES,
)
from govoplan_core.core.sanctions import (
CAPABILITY_CONNECTORS_SANCTIONS_SNAPSHOTS,
)
from govoplan_connectors.backend.manifest import manifest
class ConnectorsManifestTests(unittest.TestCase):
def test_manifest_exposes_versioned_tabular_capabilities(self) -> None:
self.assertEqual("connectors", manifest.id)
self.assertIn("access", manifest.optional_dependencies)
self.assertIn(
"connectors.tabular_sources",
{interface.name for interface in manifest.provides_interfaces},
)
self.assertIn(
CAPABILITY_CONNECTORS_TABULAR_SOURCES,
manifest.capability_factories,
)
self.assertIn(
CAPABILITY_CONNECTORS_TABULAR_SNAPSHOT_WRITER,
manifest.capability_factories,
)
self.assertIn(
CAPABILITY_CONNECTORS_SANCTIONS_SNAPSHOTS,
manifest.capability_factories,
)
self.assertIsNotNone(manifest.migration_spec)
self.assertEqual(
"@govoplan/connectors-webui",
manifest.frontend.package_name,
)
self.assertIn(
"connectors.governed-configuration",
{topic.id for topic in manifest.documentation},
)
if __name__ == "__main__":
unittest.main()
+46
View File
@@ -0,0 +1,46 @@
from __future__ import annotations
import tempfile
import unittest
from pathlib import Path
from alembic.runtime.migration import MigrationContext
from sqlalchemy import create_engine, inspect
from govoplan_connectors.backend.manifest import get_manifest
from govoplan_core.db.migrations import migrate_database
class ConnectorsMigrationTests(unittest.TestCase):
def test_baseline_creates_connector_tables_and_head(self) -> None:
with tempfile.TemporaryDirectory(prefix="govoplan-connectors-migration-") as directory:
url = f"sqlite:///{Path(directory) / 'connectors.db'}"
migrate_database(
database_url=url,
enabled_modules=("connectors",),
manifest_factories=(get_manifest,),
)
engine = create_engine(url)
try:
with engine.connect() as connection:
self.assertIn(
"a8d9e0f1b2c3",
set(MigrationContext.configure(connection).get_current_heads()),
)
self.assertTrue(
{
"connector_tabular_sources",
"connector_sanctions_snapshots",
"connector_sanctions_acquisition_runs",
"connector_definitions",
"connector_definition_revisions",
"connector_configurations",
"connector_simulation_runs",
}.issubset(inspect(connection).get_table_names())
)
finally:
engine.dispose()
if __name__ == "__main__":
unittest.main()
+118
View File
@@ -0,0 +1,118 @@
from __future__ import annotations
from datetime import UTC, datetime
import unittest
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_connectors.backend.db.models import (
ConnectorSanctionsAcquisitionRun,
ConnectorSanctionsSnapshot,
ConnectorTabularSource,
)
from govoplan_connectors.backend.manifest import manifest
from govoplan_connectors.backend.provider_state import (
SANCTIONS_PROVIDER_ID,
TABULAR_PROVIDER_ID,
sanctions_provider_states,
tabular_provider_states,
)
from govoplan_core.core.provider_governance import ExternalProviderStateContext
from govoplan_core.db.base import Base
class ConnectorsProviderStateTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite+pysqlite:///:memory:", future=True)
Base.metadata.create_all(
self.engine,
tables=(
ConnectorTabularSource.__table__,
ConnectorSanctionsAcquisitionRun.__table__,
ConnectorSanctionsSnapshot.__table__,
),
)
self.session = sessionmaker(bind=self.engine, expire_on_commit=False)()
def tearDown(self) -> None:
self.session.close()
self.engine.dispose()
def test_immutable_tabular_snapshot_reports_ready_state(self) -> None:
self.session.add(
ConnectorTabularSource(
id="tabular-1",
tenant_id="tenant-1",
source_name="monthly",
name="Monthly input",
status="active",
schema_version=1,
schema_=[{"name": "id", "type": "string"}],
rows=[{"id": "1"}],
fingerprint="a" * 64,
row_count=1,
byte_count=10,
)
)
self.session.commit()
state = tabular_provider_states(
ExternalProviderStateContext(session=self.session, tenant_id="tenant-1")
)[0]
self.assertEqual("healthy", state.health)
self.assertEqual("ready", state.recovery)
self.assertEqual("not_applicable", state.freshness)
def test_sanctions_state_hashes_binding_and_manifest_registers_state(self) -> None:
now = datetime.now(UTC)
run = ConnectorSanctionsAcquisitionRun(
id="run-1",
tenant_id="tenant-1",
provider_id="eu",
source_id="secret-source-name",
status="succeeded",
attempt_count=1,
started_at=now,
finished_at=now,
)
snapshot = ConnectorSanctionsSnapshot(
id="snapshot-1",
tenant_id="tenant-1",
provider_id="eu",
publisher="European Union",
jurisdiction="EU",
list_type="sanctions",
source_id="secret-source-name",
source_version="2026-08-01",
acquired_at=now,
source_url="https://source.example.test/list.xml",
content_type="application/xml",
byte_count=8,
sha256="b" * 64,
parser_version="1",
connector_run_id=run.id,
raw_content=b"<list/>",
)
run.snapshot_id = snapshot.id
self.session.add_all((run, snapshot))
self.session.commit()
state = sanctions_provider_states(
ExternalProviderStateContext(session=self.session, tenant_id="tenant-1")
)[0]
self.assertEqual("healthy", state.health)
self.assertEqual("ready", state.recovery)
rendered = str(state.to_dict())
self.assertNotIn("secret-source-name", rendered)
self.assertNotIn("source.example.test", rendered)
self.assertEqual(
{TABULAR_PROVIDER_ID, SANCTIONS_PROVIDER_ID},
{item.provider_id for item in manifest.external_provider_state_providers},
)
if __name__ == "__main__":
unittest.main()
+263
View File
@@ -0,0 +1,263 @@
from __future__ import annotations
from datetime import datetime, timedelta, timezone
import unittest
from unittest.mock import patch
from sqlalchemy import create_engine, select
from sqlalchemy.orm import Session
from govoplan_connectors.backend.db.models import ConnectorTabularSource
from govoplan_connectors.backend.feeds import ConnectorFeedProvider
from govoplan_connectors.backend.recovery import (
CONNECTOR_RECOVERY_OPERATIONS,
ConnectorRecoveryError,
begin_connector_external_mutation,
begin_connector_read_snapshot,
)
from govoplan_connectors.backend.router import api_import_feed_snapshot
from govoplan_connectors.backend.schemas import FeedImportRequest
from govoplan_connectors.backend.tabular_sources import WRITE_SCOPE
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.recovery import (
RecoveryCheckpoint,
RecoveryOperation,
RecoveryStatus,
)
from govoplan_core.core.recovery_runtime import (
RecoveryOperationStateConflict,
claim_durable_recovery_operation,
)
from govoplan_core.core.tabular_sources import TabularSnapshotInput
from govoplan_core.core.runtime_coordination import (
DistributedLease,
RuntimeIdentity,
bind_process_runtime_identity,
)
from govoplan_core.db.base import Base
from govoplan_connectors.backend.tabular_sources import SqlTabularSourceProvider
RSS = b"""<?xml version="1.0"?>
<rss version="2.0"><channel><title>Updates</title>
<link>https://example.test/</link><description>Updates</description>
<item><guid>1</guid><title>One</title></item></channel></rss>"""
def _identity(node: str, incarnation: str) -> RuntimeIdentity:
return RuntimeIdentity(
installation_id="connector-recovery-tests",
node_id=node,
incarnation=incarnation,
role="worker",
software_version="test",
composition_hash="a" * 64,
)
def _principal() -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id="tenant-1",
scopes=frozenset({WRITE_SCOPE}),
),
account=object(),
user=object(),
)
class ConnectorRecoveryTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(
self.engine,
tables=(
DistributedLease.__table__,
RecoveryOperation.__table__,
RecoveryCheckpoint.__table__,
ConnectorTabularSource.__table__,
),
)
self.session = Session(self.engine, expire_on_commit=False)
bind_process_runtime_identity(_identity("node-1", "incarnation-1"))
def tearDown(self) -> None:
bind_process_runtime_identity(None)
self.session.close()
self.engine.dispose()
def test_feed_snapshot_and_recovery_checkpoint_commit_atomically_and_replay(self) -> None:
document = ConnectorFeedProvider().parse(
RSS,
source_url="https://example.test/feed.xml",
)
payload = FeedImportRequest(
url="https://example.test/feed.xml",
name="Updates",
source_name="updates",
)
with (
patch(
"govoplan_connectors.backend.router.feed_transport.fetch",
return_value=document,
) as fetch,
patch("govoplan_connectors.backend.router.audit_event"),
):
first = api_import_feed_snapshot(
payload,
session=self.session,
principal=_principal(),
idempotency_key="feed-import-1",
)
replay = api_import_feed_snapshot(
payload,
session=self.session,
principal=_principal(),
idempotency_key="feed-import-1",
)
self.assertEqual(first.ref, replay.ref)
fetch.assert_called_once()
operation = self.session.scalar(select(RecoveryOperation))
assert operation is not None
self.assertEqual(RecoveryStatus.SUCCEEDED.value, operation.status)
self.assertEqual(
first.ref.removeprefix("snapshot:"),
operation.resource_id,
)
def test_recovery_metadata_distinguishes_reads_from_external_mutations(self) -> None:
declarations = {
item.operation_type: item for item in CONNECTOR_RECOVERY_OPERATIONS
}
self.assertFalse(declarations["read-snapshot"].provider_mutation)
self.assertTrue(declarations["read-snapshot"].implemented)
self.assertTrue(declarations["external-mutation"].provider_mutation)
self.assertFalse(declarations["external-mutation"].implemented)
def test_stale_atomic_connector_fence_fails_without_claiming_an_effect(self) -> None:
recovery = begin_connector_read_snapshot(
self.session,
tenant_id="tenant-1",
provider_id="provider-1",
idempotency_key="read-1",
source_revision="revision-1",
cursor="cursor-1",
dry_run_evidence={"performed": True, "approved": True},
)
lease = self.session.scalar(select(DistributedLease))
assert lease is not None
lease.expires_at = datetime.now(timezone.utc) - timedelta(seconds=1)
self.session.commit()
bind_process_runtime_identity(_identity("node-2", "incarnation-2"))
with self.assertRaises(RecoveryOperationStateConflict):
claim_durable_recovery_operation(
recovery.operation.session_factory,
identity=_identity("node-2", "incarnation-2"),
operation_id=recovery.operation_id,
)
operation = self.session.get(RecoveryOperation, recovery.operation_id)
self.session.refresh(operation)
self.assertEqual(RecoveryStatus.FAILED.value, operation.status)
def test_external_mutation_unknown_outcome_blocks_blind_retry(self) -> None:
kwargs = {
"tenant_id": "tenant-1",
"provider_id": "provider-1",
"idempotency_key": "publish-1",
"request_sha256": "b" * 64,
"source_revision": "revision-1",
"cursor": None,
"dry_run_evidence": {"performed": True, "approved": True},
"resource_type": "external_record",
"resource_id": "record-1",
}
recovery = begin_connector_external_mutation(self.session, **kwargs)
recovery.outcome_unknown(
summary="The provider connection closed after dispatch",
provider_code="connection_closed",
)
with self.assertRaises(ConnectorRecoveryError):
begin_connector_external_mutation(self.session, **kwargs)
operation = self.session.get(RecoveryOperation, recovery.operation_id)
self.session.refresh(operation)
self.assertEqual(RecoveryStatus.OUTCOME_UNKNOWN.value, operation.status)
def test_tampered_chain_rolls_back_the_atomic_connector_projection(self) -> None:
recovery = begin_connector_read_snapshot(
self.session,
tenant_id="tenant-1",
provider_id="provider-1",
idempotency_key="tampered-read",
source_revision=None,
cursor=None,
dry_run_evidence={"performed": False, "reason": "read-only"},
)
checkpoint = self.session.scalar(
select(RecoveryCheckpoint)
.where(RecoveryCheckpoint.operation_id == recovery.operation_id)
.order_by(RecoveryCheckpoint.sequence)
.limit(1)
)
assert checkpoint is not None
checkpoint.summary = "tampered"
self.session.commit()
source = SqlTabularSourceProvider().create_snapshot(
self.session,
_principal(),
snapshot=TabularSnapshotInput(
name="Tampered",
source_name="tampered",
rows=({"id": 1},),
),
source_id=recovery.resource_id,
)
with self.assertRaises(ConnectorRecoveryError):
recovery.commit_success(
self.session,
evidence={
"verified": True,
"checks": {"snapshot_ref": source.ref},
},
)
self.assertIsNone(
self.session.get(ConnectorTabularSource, recovery.resource_id)
)
operation = self.session.get(RecoveryOperation, recovery.operation_id)
self.session.refresh(operation)
self.assertEqual(RecoveryStatus.RUNNING.value, operation.status)
def test_definitive_external_rejection_is_terminal(self) -> None:
recovery = begin_connector_external_mutation(
self.session,
tenant_id="tenant-1",
provider_id="provider-1",
idempotency_key="publish-rejected",
request_sha256="c" * 64,
source_revision="revision-1",
cursor=None,
dry_run_evidence={"performed": True, "approved": True},
resource_type="external_record",
resource_id="record-2",
)
recovery.reject(
summary="The provider rejected the requested revision",
provider_code="revision_conflict",
)
operation = self.session.get(RecoveryOperation, recovery.operation_id)
self.session.refresh(operation)
self.assertEqual(RecoveryStatus.REJECTED.value, operation.status)
if __name__ == "__main__":
unittest.main()
+391
View File
@@ -0,0 +1,391 @@
from __future__ import annotations
from datetime import timedelta
import hashlib
import unittest
from unittest.mock import patch
from urllib.error import URLError
from sqlalchemy import create_engine
from sqlalchemy.orm import Session
from govoplan_connectors.backend.db.models import (
ConnectorSanctionsAcquisitionRun,
ConnectorSanctionsSnapshot,
)
from govoplan_connectors.backend.sanctions_sources import (
SANCTIONS_READ_SCOPE,
SANCTIONS_REFRESH_SCOPE,
SOURCE_DEFINITIONS,
SYNTHETIC_PROVIDER_ID,
SYNTHETIC_UN_XML,
SanctionsSourceError,
SqlSanctionsSnapshotProvider,
TransportResponse,
UNSC_PROVIDER_ID,
UrllibSanctionsTransport,
)
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.recovery import (
RecoveryCheckpoint,
RecoveryOperation,
RecoveryStatus,
)
from govoplan_core.core.runtime_coordination import (
DistributedLease,
RuntimeIdentity,
bind_process_runtime_identity,
)
from govoplan_core.db.base import Base, utcnow
def principal(
tenant_id: str = "tenant-1",
*,
scopes: tuple[str, ...] = (
SANCTIONS_READ_SCOPE,
SANCTIONS_REFRESH_SCOPE,
),
) -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id=tenant_id,
scopes=frozenset(scopes),
),
account=object(),
user=object(),
)
class _Transport:
def __init__(self, responses):
self.responses = list(responses)
self.headers = []
def fetch(self, definition, *, headers):
del definition
self.headers.append(dict(headers))
response = self.responses.pop(0)
if isinstance(response, Exception):
raise response
return response
def response(
content: bytes = SYNTHETIC_UN_XML,
*,
status: int = 200,
content_type: str = "application/xml",
etag: str = '"fixture-v1"',
) -> TransportResponse:
return TransportResponse(
status=status,
final_url="https://scsanctions.un.org/consolidated.xml",
headers={
"content-type": content_type,
"etag": etag,
},
content=content,
attempts=1,
)
class SanctionsSourcesTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite:///:memory:")
Base.metadata.create_all(
self.engine,
tables=(
DistributedLease.__table__,
RecoveryOperation.__table__,
RecoveryCheckpoint.__table__,
ConnectorSanctionsAcquisitionRun.__table__,
ConnectorSanctionsSnapshot.__table__,
),
)
self.session = Session(self.engine)
bind_process_runtime_identity(
RuntimeIdentity(
installation_id="connectors-tests",
node_id="connectors-test-node",
incarnation="connectors-test-incarnation",
role="worker",
software_version="test",
composition_hash="a" * 64,
)
)
def tearDown(self) -> None:
bind_process_runtime_identity(None)
self.session.close()
self.engine.dispose()
def test_fixture_refreshes_are_immutable_and_evidence_is_readable(
self,
) -> None:
provider = SqlSanctionsSnapshotProvider()
first = provider.refresh_source(
self.session,
principal(),
provider_id=SYNTHETIC_PROVIDER_ID,
)
second = provider.refresh_source(
self.session,
principal(),
provider_id=SYNTHETIC_PROVIDER_ID,
)
self.session.commit()
self.assertEqual("succeeded", first.status)
self.assertEqual("succeeded", second.status)
self.assertNotEqual(first.snapshot.ref, second.snapshot.ref)
self.assertEqual(
hashlib.sha256(SYNTHETIC_UN_XML).hexdigest(),
first.snapshot.sha256,
)
self.assertEqual(
SYNTHETIC_UN_XML,
provider.read_snapshot(
self.session,
principal(),
snapshot_ref=first.snapshot.ref,
).content,
)
runs = provider.list_runs(
self.session,
principal(),
)
self.assertTrue(
all(
run.request_evidence["subject_data_transmitted"]
is False
for run in runs
)
)
def test_conditional_fetch_reuses_prior_immutable_snapshot(self) -> None:
transport = _Transport(
(
response(),
response(b"", status=304),
)
)
provider = SqlSanctionsSnapshotProvider(transport)
first = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
second = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
self.assertEqual("not_modified", second.status)
self.assertEqual(first.snapshot.ref, second.snapshot.ref)
self.assertEqual(
{'If-None-Match': '"fixture-v1"'},
transport.headers[1],
)
self.assertEqual(
1,
self.session.query(ConnectorSanctionsSnapshot).count(),
)
def test_malformed_and_changed_sources_have_explicit_health(
self,
) -> None:
cases = (
(
b"<CONSOLIDATED_LIST>",
"application/xml",
"malformed",
),
(
b"<DIFFERENT><INDIVIDUALS/><ENTITIES/></DIFFERENT>",
"application/xml",
"unexpected_change",
),
(
SYNTHETIC_UN_XML,
"text/html",
"unexpected_change",
),
)
for payload, content_type, expected in cases:
with self.subTest(expected=expected, content_type=content_type):
provider = SqlSanctionsSnapshotProvider(
_Transport(
(
response(
payload,
content_type=content_type,
),
)
)
)
result = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
self.assertEqual(expected, result.status)
self.assertIsNotNone(result.error)
def test_unavailable_source_becomes_stale_when_evidence_is_old(
self,
) -> None:
provider = SqlSanctionsSnapshotProvider(
_Transport(
(
response(),
SanctionsSourceError("offline"),
)
)
)
first = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
record = self.session.get(
ConnectorSanctionsSnapshot,
first.snapshot.ref.removeprefix("sanctions-snapshot:"),
)
record.acquired_at = utcnow() - timedelta(days=3)
self.session.commit()
result = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
self.assertEqual("stale", result.status)
self.assertEqual(first.snapshot.ref, result.snapshot.ref)
def test_idempotent_refresh_replays_the_committed_acquisition(self) -> None:
transport = _Transport((response(),))
provider = SqlSanctionsSnapshotProvider(transport)
first = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
idempotency_key="scheduled-refresh-1",
)
replay = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
idempotency_key="scheduled-refresh-1",
)
self.assertEqual(first.run_id, replay.run_id)
self.assertEqual(first.snapshot.ref, replay.snapshot.ref)
self.assertEqual([], transport.responses)
operation = self.session.query(RecoveryOperation).one()
self.assertEqual(RecoveryStatus.SUCCEEDED.value, operation.status)
def test_provider_failure_commits_failed_run_and_terminal_recovery(self) -> None:
provider = SqlSanctionsSnapshotProvider(
_Transport((SanctionsSourceError("offline"),))
)
result = provider.refresh_source(
self.session,
principal(),
provider_id=UNSC_PROVIDER_ID,
)
self.assertEqual("unavailable", result.status)
operation = self.session.query(RecoveryOperation).one()
self.assertEqual(RecoveryStatus.FAILED.value, operation.status)
self.assertEqual(
result.run_id,
self.session.query(ConnectorSanctionsAcquisitionRun).one().id,
)
def test_snapshot_access_is_tenant_and_scope_isolated(self) -> None:
provider = SqlSanctionsSnapshotProvider()
created = provider.refresh_source(
self.session,
principal(),
provider_id=SYNTHETIC_PROVIDER_ID,
)
self.assertIsNone(
provider.get_snapshot(
self.session,
principal("tenant-2"),
snapshot_ref=created.snapshot.ref,
)
)
with self.assertRaisesRegex(Exception, "Missing scope"):
provider.list_snapshots(
self.session,
principal(scopes=()),
)
def test_transport_retries_transient_network_failures(self) -> None:
class _Headers(dict):
pass
class _Response:
status = 200
headers = _Headers(
{
"Content-Type": "application/xml",
"Content-Length": str(len(SYNTHETIC_UN_XML)),
}
)
def __enter__(self):
return self
def __exit__(self, *args):
return False
def geturl(self):
return (
"https://scsanctions.un.org/"
"resources/xml/en/consolidated.xml"
)
def read(self, size):
del size
if hasattr(self, "_read"):
return b""
self._read = True
return SYNTHETIC_UN_XML
opener = unittest.mock.Mock()
opener.open.side_effect = (
URLError("temporary"),
URLError("temporary"),
_Response(),
)
sleeps = []
transport = UrllibSanctionsTransport(
sleeper=sleeps.append
)
with patch(
"govoplan_connectors.backend.sanctions_sources.build_opener",
return_value=opener,
):
fetched = transport.fetch(
SOURCE_DEFINITIONS[UNSC_PROVIDER_ID],
headers={},
)
self.assertEqual(3, fetched.attempts)
self.assertEqual([1.0, 2.0], sleeps)
if __name__ == "__main__":
unittest.main()
+341
View File
@@ -0,0 +1,341 @@
from __future__ import annotations
import tempfile
import unittest
from io import BytesIO
from pathlib import Path
from types import SimpleNamespace
from openpyxl import Workbook
from sqlalchemy import Column, Integer, MetaData, String, Table, create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.files import (
CAPABILITY_FILES_TABULAR_CONTENT,
ManagedTabularFile,
ManagedTabularFileContent,
)
from govoplan_core.core.tabular_sources import (
TabularSourceUnavailableError,
TabularSourceValidationError,
)
from govoplan_core.db.base import Base
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
)
from govoplan_connectors.backend.tabular_adapters import (
ManagedFileTabularAdapter,
PostgresqlTabularAdapter,
parse_managed_tabular_content,
)
def principal(tenant_id: str = "tenant-1") -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id=tenant_id,
scopes=frozenset(
{
"connectors:source:read",
"connectors:source:write",
"files:file:read",
"files:file:download",
}
),
),
account=object(),
user=SimpleNamespace(id="user-1"),
)
class _ManagedFiles:
def __init__(self, payload: bytes, *, filename: str = "cases.csv") -> None:
self.payload = payload
self.filename = filename
self.current_version_id = "version-2"
def _file(self, version_id: str) -> ManagedTabularFile:
return ManagedTabularFile(
file_asset_id="asset-1",
file_version_id=version_id,
filename=self.filename,
display_path=f"Imports/{self.filename}",
content_type=(
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
if self.filename.endswith(".xlsx")
else "text/csv"
),
size_bytes=len(self.payload),
sha256=("a" if version_id == "version-1" else "b") * 64,
current_version=version_id == self.current_version_id,
)
def list_tabular_files(self, session, principal, *, query="", limit=100):
del session, principal, query, limit
return (self._file(self.current_version_id),)
def get_tabular_file(
self,
session,
principal,
*,
file_asset_id,
file_version_id=None,
):
del session, principal
if file_asset_id != "asset-1":
return None
return self._file(file_version_id or self.current_version_id)
def read_tabular_file(
self,
session,
principal,
*,
file_asset_id,
file_version_id,
max_bytes,
):
del session, principal, file_asset_id
if len(self.payload) > max_bytes:
raise AssertionError("test payload exceeded adapter limit")
return ManagedTabularFileContent(
file=self._file(file_version_id),
payload=self.payload,
)
class _Registry:
def __init__(self, provider) -> None:
self.provider = provider
def has_capability(self, name):
return name == CAPABILITY_FILES_TABULAR_CONTENT
def require_capability(self, name):
if not self.has_capability(name):
raise KeyError(name)
return self.provider
class ManagedFileTabularAdapterTests(unittest.TestCase):
def test_csv_is_exact_version_pinned_and_reports_newer_version(self) -> None:
adapter = ManagedFileTabularAdapter(
_Registry(_ManagedFiles(b"id,amount\n0012,12.5\n2,7\n"))
)
result = adapter.inspect(
object(),
principal(),
file_asset_id="asset-1",
file_version_id="version-1",
)
self.assertEqual("managed_file", result.provider)
self.assertEqual("version-1", result.metadata["file_version_id"])
self.assertEqual("warning", result.health.status)
self.assertEqual("files.newer_version_available", result.health.code)
self.assertEqual("mixed", result.schema[0].data_type)
self.assertEqual(2, result.row_count)
self.assertTrue(result.pushdown.projections)
self.assertEqual("files.newer_version_available", result.diagnostics[0].code)
def test_xlsx_uses_requested_sheet_and_closed_typed_schema(self) -> None:
workbook = Workbook()
first = workbook.active
first.title = "Ignore"
first.append(["ignored"])
target = workbook.create_sheet("Monthly")
target.append(["case_id", "amount", "active"])
target.append(["A-1", 12.5, True])
target.append(["A-2", None, False])
payload = BytesIO()
workbook.save(payload)
workbook.close()
rows, sheet = parse_managed_tabular_content(
payload.getvalue(),
filename="monthly.xlsx",
content_type=(
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
),
delimiter=",",
sheet_name="Monthly",
)
self.assertEqual("Monthly", sheet)
self.assertEqual("A-1", rows[0]["case_id"])
self.assertIsNone(rows[1]["amount"])
def test_missing_files_capability_is_explicitly_unavailable(self) -> None:
with self.assertRaisesRegex(
TabularSourceUnavailableError,
"require the Files module",
):
ManagedFileTabularAdapter(None).inspect(
object(),
principal(),
file_asset_id="asset-1",
file_version_id=None,
)
class PostgresqlTabularAdapterTests(unittest.TestCase):
def setUp(self) -> None:
self.directory = tempfile.TemporaryDirectory(
prefix="govoplan-connectors-sql-adapter-"
)
source_path = Path(self.directory.name) / "source.db"
self.source_url = f"sqlite+pysqlite:///{source_path}"
source_engine = create_engine(self.source_url)
metadata = MetaData()
self.table = Table(
"monthly_cases",
metadata,
Column("case_id", String, nullable=False),
Column("amount", Integer, nullable=True),
)
metadata.create_all(source_engine)
with source_engine.begin() as connection:
connection.execute(
self.table.insert(),
(
{"case_id": "A-1", "amount": 12},
{"case_id": "A-2", "amount": None},
),
)
source_engine.dispose()
self.catalog_engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(
self.catalog_engine,
tables=(
ConnectorDefinition.__table__,
ConnectorConfiguration.__table__,
),
)
self.session = sessionmaker(bind=self.catalog_engine)()
definition = ConnectorDefinition(
id="definition-1",
tenant_id="tenant-1",
definition_key="postgresql.reader",
name="PostgreSQL reader",
status="active",
current_revision=1,
local_definition=True,
)
self.configuration = ConnectorConfiguration(
id="configuration-1",
tenant_id="tenant-1",
definition_id=definition.id,
name="Monthly SQL",
status="active",
endpoint_url=self.source_url,
credential_ref=None,
base_definition_revision=1,
local_overrides={},
protected_paths=[],
effective_configuration={"provider": "sql", "protocol": "sql"},
effective_hash="configuration-hash-1",
resource_revision=1,
ambiguity_policy="manual_review",
)
self.session.add_all((definition, self.configuration))
self.session.commit()
self.adapter = PostgresqlTabularAdapter(allow_sqlite_for_tests=True)
def tearDown(self) -> None:
self.session.close()
self.catalog_engine.dispose()
self.directory.cleanup()
def test_discovers_and_reads_projection_from_governed_sql_configuration(self) -> None:
inspection = self.adapter.inspect(
self.session,
principal(),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
metadata = {
**dict(inspection.metadata),
"discovery_fingerprint": inspection.fingerprint,
}
read = self.adapter.read(
self.session,
principal(),
metadata=metadata,
columns=("case_id",),
offset=1,
limit=10,
timeout_ms=2_000,
)
self.assertEqual("live", "live")
self.assertEqual(["case_id", "amount"], [item.name for item in inspection.schema])
self.assertEqual(2, inspection.row_count)
self.assertEqual(({"case_id": "A-2"},), read.rows)
self.assertTrue(inspection.pushdown.projections)
self.assertFalse(inspection.pushdown.filters)
def test_schema_drift_and_tenant_isolation_fail_closed(self) -> None:
inspection = self.adapter.inspect(
self.session,
principal(),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
metadata = {
**dict(inspection.metadata),
"discovery_fingerprint": inspection.fingerprint,
}
engine = create_engine(self.source_url)
with engine.begin() as connection:
connection.exec_driver_sql(
"ALTER TABLE monthly_cases ADD COLUMN category TEXT"
)
engine.dispose()
with self.assertRaisesRegex(TabularSourceValidationError, "schema drifted"):
self.adapter.read(
self.session,
principal(),
metadata=metadata,
columns=(),
offset=0,
limit=10,
timeout_ms=2_000,
)
with self.assertRaisesRegex(
TabularSourceUnavailableError,
"configuration is unavailable",
):
self.adapter.inspect(
self.session,
principal("tenant-2"),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
def test_endpoint_query_credentials_are_rejected_before_connection(self) -> None:
self.configuration.endpoint_url = f"{self.source_url}?password=not-allowed"
self.session.commit()
with self.assertRaisesRegex(
TabularSourceValidationError,
"query parameters must not contain credentials",
):
self.adapter.inspect(
self.session,
principal(),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
if __name__ == "__main__":
unittest.main()
+313
View File
@@ -0,0 +1,313 @@
from __future__ import annotations
import tempfile
import unittest
from pathlib import Path
from types import SimpleNamespace
from sqlalchemy import Column, Integer, MetaData, String, Table, create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.files import (
CAPABILITY_FILES_TABULAR_CONTENT,
ManagedTabularFile,
ManagedTabularFileContent,
)
from govoplan_core.core.tabular_sources import (
TabularReadRequest,
TabularSourceUnavailableError,
TabularSourceValidationError,
)
from govoplan_core.db.base import Base
from govoplan_core.security.credential_envelopes import CredentialEnvelope
from govoplan_connectors.backend.db.models import (
ConnectorConfiguration,
ConnectorDefinition,
ConnectorTabularSource,
)
from govoplan_connectors.backend.tabular_adapters import PostgresqlTabularAdapter
from govoplan_connectors.backend.tabular_sources import SqlTabularSourceProvider
def principal(tenant_id: str = "tenant-1") -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id=tenant_id,
scopes=frozenset(
{
"connectors:source:read",
"connectors:source:write",
"files:file:read",
"files:file:download",
}
),
),
account=object(),
user=SimpleNamespace(id="user-1"),
)
class _ManagedFiles:
def __init__(self) -> None:
self.current = "version-1"
self.payloads = {
"version-1": b"id,name\n1,Ada\n2,Lin\n",
"version-2": b"id,name,active\n1,Ada,true\n2,Lin,false\n",
}
def _metadata(self, version_id: str) -> ManagedTabularFile:
payload = self.payloads[version_id]
return ManagedTabularFile(
file_asset_id="asset-1",
file_version_id=version_id,
filename="people.csv",
display_path="Imports/people.csv",
content_type="text/csv",
size_bytes=len(payload),
sha256=("a" if version_id == "version-1" else "b") * 64,
current_version=version_id == self.current,
)
def list_tabular_files(self, session, principal, *, query="", limit=100):
del session, principal, query, limit
return (self._metadata(self.current),)
def get_tabular_file(
self,
session,
principal,
*,
file_asset_id,
file_version_id=None,
):
del session, principal
if file_asset_id != "asset-1":
return None
return self._metadata(file_version_id or self.current)
def read_tabular_file(
self,
session,
principal,
*,
file_asset_id,
file_version_id,
max_bytes,
):
del session, principal, file_asset_id, max_bytes
return ManagedTabularFileContent(
file=self._metadata(file_version_id),
payload=self.payloads[file_version_id],
)
class _Registry:
def __init__(self, files) -> None:
self.files = files
def has_capability(self, name):
return name == CAPABILITY_FILES_TABULAR_CONTENT
def require_capability(self, name):
if not self.has_capability(name):
raise KeyError(name)
return self.files
class ConnectorTabularOriginProviderTests(unittest.TestCase):
def setUp(self) -> None:
self.catalog_engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(
self.catalog_engine,
tables=(
ConnectorTabularSource.__table__,
ConnectorDefinition.__table__,
ConnectorConfiguration.__table__,
CredentialEnvelope.__table__,
),
)
self.session = sessionmaker(bind=self.catalog_engine)()
self.files = _ManagedFiles()
self.directory = tempfile.TemporaryDirectory(
prefix="govoplan-connectors-origin-provider-"
)
source_path = Path(self.directory.name) / "source.db"
self.sql_url = f"sqlite+pysqlite:///{source_path}"
source_engine = create_engine(self.sql_url)
metadata = MetaData()
source_table = Table(
"monthly_cases",
metadata,
Column("case_id", String, nullable=False),
Column("amount", Integer, nullable=True),
)
metadata.create_all(source_engine)
with source_engine.begin() as connection:
connection.execute(
source_table.insert(),
(
{"case_id": "A-1", "amount": 12},
{"case_id": "A-2", "amount": None},
),
)
source_engine.dispose()
definition = ConnectorDefinition(
id="definition-1",
tenant_id="tenant-1",
definition_key="postgresql.reader",
name="PostgreSQL reader",
status="active",
current_revision=1,
local_definition=True,
)
self.configuration = ConnectorConfiguration(
id="configuration-1",
tenant_id="tenant-1",
definition_id=definition.id,
name="Monthly SQL",
status="active",
endpoint_url=self.sql_url,
credential_ref=None,
base_definition_revision=1,
local_overrides={},
protected_paths=[],
effective_configuration={"provider": "sql", "protocol": "sql"},
effective_hash="configuration-hash-1",
resource_revision=1,
ambiguity_policy="manual_review",
)
self.session.add_all((definition, self.configuration))
self.session.commit()
self.provider = SqlTabularSourceProvider(
registry=_Registry(self.files),
sql_adapter=PostgresqlTabularAdapter(allow_sqlite_for_tests=True),
)
def tearDown(self) -> None:
self.session.close()
self.catalog_engine.dispose()
self.directory.cleanup()
def test_managed_file_source_stays_pinned_until_explicit_refresh(self) -> None:
created = self.provider.create_file_source(
self.session,
principal(),
name="Managed people",
source_name="managed_people",
file_asset_id="asset-1",
)
self.session.commit()
self.files.current = "version-2"
preview = self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(source_ref=created.ref, limit=10),
)
refreshed = self.provider.refresh_source(
self.session,
principal(),
source_ref=created.ref,
)
self.assertTrue(created.ref.startswith("file:"))
self.assertEqual("file_backed", preview.source.source_mode)
self.assertEqual("version-1", preview.source.metadata["file_version_id"])
self.assertEqual(
"files.newer_version_available",
preview.diagnostics[0].code,
)
self.assertEqual("version-2", refreshed.metadata["file_version_id"])
self.assertEqual("2", refreshed.schema_version)
self.assertEqual(3, len(refreshed.schema))
def test_sql_source_projects_and_blocks_changed_configuration_until_refresh(self) -> None:
created = self.provider.create_sql_source(
self.session,
principal(),
name="Monthly cases",
source_name="monthly_cases",
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
self.session.commit()
preview = self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
columns=("case_id",),
limit=1,
),
)
self.assertTrue(created.ref.startswith("sql:"))
self.assertEqual("live", preview.source.source_mode)
self.assertEqual(({"case_id": "A-1"},), preview.rows)
self.assertEqual("preview.row_limit_reached", preview.diagnostics[-1].code)
self.assertIsNone(
self.provider.get_source(
self.session,
principal("tenant-2"),
source_ref=created.ref,
)
)
self.configuration.effective_hash = "configuration-hash-2"
self.configuration.resource_revision = 2
self.session.commit()
with self.assertRaisesRegex(
TabularSourceValidationError,
"configuration changed",
):
self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(source_ref=created.ref),
)
refreshed = self.provider.refresh_source(
self.session,
principal(),
source_ref=created.ref,
)
self.assertEqual("2", refreshed.schema_version)
self.assertEqual("configuration-hash-2", refreshed.metadata["configuration_hash"])
def test_inactive_or_stale_sql_credentials_have_sanitized_diagnostics(self) -> None:
self.configuration.endpoint_url = (
"postgresql+psycopg://db.example.invalid/govoplan"
)
self.configuration.credential_ref = "missing-credential"
self.session.commit()
adapter = PostgresqlTabularAdapter()
with self.assertRaisesRegex(
TabularSourceUnavailableError,
"credential is unavailable, inactive, or outside its allowed scope",
):
adapter.inspect(
self.session,
principal(),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
self.configuration.status = "disabled"
self.session.commit()
with self.assertRaisesRegex(
TabularSourceUnavailableError,
"configuration is not active",
):
adapter.inspect(
self.session,
principal(),
configuration_id=self.configuration.id,
table_name="monthly_cases",
)
if __name__ == "__main__":
unittest.main()
+268
View File
@@ -0,0 +1,268 @@
from __future__ import annotations
import unittest
from fastapi import HTTPException
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.access import PrincipalRef
from govoplan_core.core.tabular_sources import (
TabularReadRequest,
TabularSnapshotInput,
TabularSourceAccessError,
TabularSourceUnavailableError,
TabularSourceValidationError,
)
from govoplan_core.db.base import Base
from govoplan_connectors.backend.db.models import ConnectorTabularSource
from govoplan_connectors.backend.router import api_create_tabular_snapshot
from govoplan_connectors.backend.schemas import SnapshotCreateRequest
from govoplan_connectors.backend.tabular_sources import (
READ_SCOPE,
WRITE_SCOPE,
SqlTabularSourceProvider,
parse_csv_snapshot,
)
def principal(
tenant_id: str = "tenant-1",
*,
scopes: tuple[str, ...] = (READ_SCOPE, WRITE_SCOPE),
) -> ApiPrincipal:
return ApiPrincipal(
principal=PrincipalRef(
account_id="account-1",
membership_id="membership-1",
tenant_id=tenant_id,
scopes=frozenset(scopes),
),
account=object(),
user=object(),
)
class ConnectorsTabularSourceTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite:///:memory:")
Base.metadata.create_all(self.engine, tables=[ConnectorTabularSource.__table__])
self.Session = sessionmaker(bind=self.engine)
self.session = self.Session()
self.provider = SqlTabularSourceProvider()
def tearDown(self) -> None:
self.session.close()
Base.metadata.drop_all(self.engine, tables=[ConnectorTabularSource.__table__])
self.engine.dispose()
def test_snapshot_round_trip_preserves_schema_fingerprint_and_bounds(self) -> None:
created = self.provider.create_snapshot(
self.session,
principal(),
snapshot=TabularSnapshotInput(
name="Monthly cases",
source_name="monthly_cases_2026_07",
rows=(
{"case_id": "A-1", "amount": 12, "active": True},
{"case_id": "A-2", "amount": None, "active": False},
),
),
)
self.session.commit()
listed = self.provider.list_sources(self.session, principal())
preview = self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
limit=1,
expected_fingerprint=created.fingerprint,
),
)
self.assertEqual((created.ref,), tuple(source.ref for source in listed))
self.assertEqual(
["case_id", "amount", "active"],
[column.name for column in created.schema],
)
self.assertEqual(2, preview.total_rows)
self.assertEqual(1, len(preview.rows))
self.assertTrue(preview.truncated)
self.assertEqual(created.fingerprint, preview.source.fingerprint)
self.assertEqual("cached", preview.source.source_mode)
self.assertTrue(preview.source.pushdown.projections)
self.assertTrue(preview.source.pushdown.pagination)
self.assertEqual("healthy", preview.source.health.status)
self.assertGreater(preview.returned_bytes, 2)
self.assertEqual(1, preview.effective_row_limit)
self.assertEqual("preview.row_limit_reached", preview.diagnostics[0].code)
def test_preview_enforces_byte_time_and_provider_ceiling_budgets(self) -> None:
created = self.provider.create_snapshot(
self.session,
principal(),
snapshot=TabularSnapshotInput(
name="Bounded",
source_name="bounded",
rows=(
{"id": 1, "value": "first"},
{"id": 2, "value": "second"},
),
),
)
self.session.commit()
bounded = self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
limit=500,
max_bytes=35,
timeout_ms=2_000,
),
)
self.assertEqual(1, len(bounded.rows))
self.assertTrue(bounded.truncated)
self.assertEqual(
"preview.byte_limit_reached",
bounded.diagnostics[-1].code,
)
with self.assertRaisesRegex(
TabularSourceValidationError,
"single source row exceeds",
):
self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
max_bytes=2,
),
)
tightened = self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
limit=5_000,
max_bytes=5_000_000,
timeout_ms=10_000,
),
)
self.assertEqual(500, tightened.effective_row_limit)
self.assertEqual(1_000_000, tightened.effective_byte_limit)
self.assertEqual(2_000, tightened.effective_timeout_ms)
self.assertEqual(
{
"preview.row_limit_tightened",
"preview.byte_limit_tightened",
"preview.timeout_tightened",
},
{item.code for item in tightened.diagnostics},
)
times = iter((0.0, 0.01))
timeout_provider = SqlTabularSourceProvider(clock=lambda: next(times))
with self.assertRaisesRegex(
TabularSourceUnavailableError,
"time budget",
):
timeout_provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
timeout_ms=1,
),
)
def test_tenant_and_scope_isolation_are_enforced(self) -> None:
created = self.provider.create_snapshot(
self.session,
principal(),
snapshot=TabularSnapshotInput(
name="Private",
source_name="private_source",
rows=({"id": 1},),
),
)
self.session.commit()
self.assertEqual((), self.provider.list_sources(self.session, principal("tenant-2")))
self.assertIsNone(
self.provider.get_source(
self.session,
principal("tenant-2"),
source_ref=created.ref,
)
)
with self.assertRaises(TabularSourceAccessError):
self.provider.list_sources(
self.session,
principal(scopes=()),
)
def test_duplicate_source_name_and_stale_fingerprint_are_rejected(self) -> None:
snapshot = TabularSnapshotInput(
name="Cases",
source_name="cases",
rows=({"id": 1},),
)
created = self.provider.create_snapshot(self.session, principal(), snapshot=snapshot)
self.session.commit()
with self.assertRaises(TabularSourceValidationError):
self.provider.create_snapshot(self.session, principal(), snapshot=snapshot)
with self.assertRaises(TabularSourceValidationError):
self.provider.read_source(
self.session,
principal(),
request=TabularReadRequest(
source_ref=created.ref,
expected_fingerprint="stale",
),
)
def test_csv_parser_infers_scalar_values_and_rejects_duplicate_headers(self) -> None:
rows = parse_csv_snapshot(
"\ufeffid;amount;active;note\n0012;12.5;true;\n2;7;false;ok\n",
delimiter=";",
)
self.assertEqual(
(
{"id": "0012", "amount": 12.5, "active": True, "note": None},
{"id": 2, "amount": 7, "active": False, "note": "ok"},
),
rows,
)
with self.assertRaises(TabularSourceValidationError):
parse_csv_snapshot("id,id\n1,2\n", delimiter=",")
with self.assertRaises(TabularSourceValidationError):
parse_csv_snapshot("id,name\n1,Ada,extra\n", delimiter=",")
def test_malformed_csv_api_request_is_reported_as_validation_error(self) -> None:
payload = SnapshotCreateRequest(
name="Malformed",
source_name="malformed",
format="csv",
csv_text="id,name\n1,Ada,extra\n",
)
with self.assertRaises(HTTPException) as raised:
api_create_tabular_snapshot(
payload,
session=self.session,
principal=principal(),
)
self.assertEqual(422, raised.exception.status_code)
if __name__ == "__main__":
unittest.main()
+29
View File
@@ -0,0 +1,29 @@
{
"name": "@govoplan/connectors-webui",
"version": "0.1.20",
"private": true,
"type": "module",
"main": "src/index.ts",
"module": "src/index.ts",
"types": "src/index.ts",
"exports": {
".": {
"types": "./src/index.ts",
"import": "./src/index.ts"
},
"./styles/connectors.css": "./src/styles/connectors.css"
},
"peerDependencies": {
"@govoplan/core-webui": "^0.1.18",
"react": ">=19.2.7 <20",
"react-dom": ">=19.2.7 <20"
},
"peerDependenciesMeta": {
"@govoplan/core-webui": {
"optional": true
}
},
"scripts": {
"test:connector-governance-ui": "node tests/connector-governance-ui-structure.test.mjs"
}
}
+204
View File
@@ -0,0 +1,204 @@
import { apiFetch, apiPath, type ApiSettings } from "@govoplan/core-webui";
export type GovernedConnectorSpecification = {
provider: string;
protocol: string;
capabilities: string[];
input_schema: Record<string, unknown>;
output_schema: Record<string, unknown>;
mapping: {
version: string;
rules: Array<{
source: string;
target: string;
required?: boolean;
default?: unknown;
}>;
};
validation_rules: Array<{
kind: "required" | "one_of" | "unique";
field: string;
values?: unknown[];
severity: "warning" | "error";
code: string;
message: string;
}>;
dry_run: {
supported: boolean;
simulation_supported: boolean;
sample_rows: Array<Record<string, unknown>>;
max_items: number;
redacted_fields: string[];
};
audit: {
event_prefix: string;
expected_events: string[];
evidence_fields: string[];
};
privacy_classification: "public" | "internal" | "confidential" | "restricted";
retention_class: string;
operational_limits: Record<string, unknown>;
retry_policy: Record<string, unknown>;
};
export type ConnectorDefinition = {
id: string;
definition_key: string;
name: string;
description?: string | null;
status: string;
current_revision: number;
source_package?: string | null;
local_definition: boolean;
definition_hash: string;
specification: GovernedConnectorSpecification;
updated_at: string;
};
export type ConnectorConfiguration = {
id: string;
definition_id: string;
definition_key: string;
definition_name: string;
name: string;
status: "draft" | "active" | "disabled";
endpoint_url?: string | null;
credential_ref?: string | null;
base_definition_revision: number;
latest_definition_revision: number;
update_available: boolean;
local_overrides: Record<string, unknown>;
protected_paths: string[];
effective_configuration: GovernedConnectorSpecification;
effective_hash: string;
resource_revision: number;
ambiguity_policy: "manual_review" | "quarantine" | "reject";
updated_at: string;
};
export type ConnectorRun = {
id: string;
configuration_id: string;
mode: "dry_run" | "simulation";
idempotency_key: string;
status: string;
review_state: string;
definition_revision: number;
configuration_revision: number;
configuration_hash: string;
input_hash: string;
summary: Record<string, number | boolean>;
effects: Array<Record<string, unknown>>;
diagnostics: Array<Record<string, unknown>>;
provenance: Record<string, unknown>;
reviewed_by?: string | null;
reviewed_at?: string | null;
review_reason?: string | null;
created_at: string;
};
export type ConnectorConfigurationDraft = {
name: string;
status: ConnectorConfiguration["status"];
endpoint_url: string;
credential_ref: string;
local_overrides: string;
ambiguity_policy: ConnectorConfiguration["ambiguity_policy"];
};
const ROOT = "/api/v1/connectors/governed";
export async function listConnectorDefinitions(
settings: ApiSettings
): Promise<ConnectorDefinition[]> {
const response = await apiFetch<{ items: ConnectorDefinition[] }>(
settings,
`${ROOT}/definitions`
);
return response.items;
}
export async function upsertConnectorDefinition(
settings: ApiSettings,
payload: Record<string, unknown>
): Promise<ConnectorDefinition> {
return apiFetch(settings, `${ROOT}/definitions`, {
method: "POST",
body: JSON.stringify(payload)
});
}
export async function listConnectorConfigurations(
settings: ApiSettings
): Promise<ConnectorConfiguration[]> {
const response = await apiFetch<{ items: ConnectorConfiguration[] }>(
settings,
`${ROOT}/configurations`
);
return response.items;
}
export function createConnectorConfiguration(
settings: ApiSettings,
payload: Record<string, unknown>
): Promise<ConnectorConfiguration> {
return apiFetch(settings, `${ROOT}/configurations`, {
method: "POST",
body: JSON.stringify(payload)
});
}
export function updateConnectorConfiguration(
settings: ApiSettings,
configurationId: string,
payload: Record<string, unknown>
): Promise<ConnectorConfiguration> {
return apiFetch(
settings,
`${ROOT}/configurations/${encodeURIComponent(configurationId)}`,
{ method: "PUT", body: JSON.stringify(payload) }
);
}
export async function listConnectorRuns(
settings: ApiSettings,
configurationId?: string
): Promise<ConnectorRun[]> {
const response = await apiFetch<{ items: ConnectorRun[] }>(
settings,
apiPath(`${ROOT}/runs`, {
configuration_id: configurationId || undefined,
limit: 100
})
);
return response.items;
}
export function executeConnectorRun(
settings: ApiSettings,
configurationId: string,
mode: "dry-runs" | "simulations",
payload: Record<string, unknown>
): Promise<ConnectorRun> {
return apiFetch(
settings,
`${ROOT}/configurations/${encodeURIComponent(configurationId)}/${mode}`,
{ method: "POST", body: JSON.stringify(payload) }
);
}
export function reviewConnectorRun(
settings: ApiSettings,
runId: string,
decision: "approved" | "rejected",
reason: string
): Promise<ConnectorRun> {
return apiFetch(
settings,
`${ROOT}/runs/${encodeURIComponent(runId)}/review`,
{
method: "POST",
body: JSON.stringify({ decision, reason })
}
);
}
@@ -0,0 +1,661 @@
import { useCallback, useEffect, useMemo, useState } from "react";
import {
AdminPageLayout,
Button,
Card,
DataGrid,
Dialog,
FilterBar,
FormField,
FormGrid,
MetricCard,
MetricGrid,
PageActionBar,
SelectionList,
SelectionListItem,
SelectionListItemContent,
StatePanel,
StatusBadge,
TableActionGroup,
WorkspaceLayout,
formatDateTime,
hasScope,
useUnsavedChanges,
useUnsavedDraftGuard,
type ApiSettings,
type AuthInfo,
type DataGridColumn
} from "@govoplan/core-webui";
import {
createConnectorConfiguration,
executeConnectorRun,
listConnectorConfigurations,
listConnectorDefinitions,
listConnectorRuns,
reviewConnectorRun,
updateConnectorConfiguration,
upsertConnectorDefinition,
type ConnectorConfiguration,
type ConnectorConfigurationDraft,
type ConnectorDefinition,
type ConnectorRun
} from "../api/governedConnectors";
type Props = {
settings: ApiSettings;
auth: AuthInfo;
};
const EMPTY_DRAFT: ConnectorConfigurationDraft = {
name: "",
status: "draft",
endpoint_url: "",
credential_ref: "",
local_overrides: "{}",
ambiguity_policy: "manual_review"
};
const EXAMPLE_DEFINITION = JSON.stringify({
definition_key: "example.reference-data",
name: "Example reference data",
description: "Locally governed example connector",
origin: "local",
specification: {
provider: "example-provider",
protocol: "rest",
capabilities: ["discover", "read", "dry_run"],
input_schema: { type: "object" },
output_schema: { type: "object" },
mapping: {
version: "1",
rules: [{ source: "id", target: "record.id", required: true }]
},
validation_rules: [{
kind: "unique",
field: "record.id",
severity: "error",
code: "record.id.ambiguous",
message: "The record identifier is not unique."
}],
dry_run: {
supported: true,
simulation_supported: true,
sample_rows: [{ id: "sample-1" }],
max_items: 500,
redacted_fields: []
},
audit: {
event_prefix: "connectors.example",
expected_events: ["simulation.completed"],
evidence_fields: ["input_hash", "configuration_hash"]
},
privacy_classification: "internal",
retention_class: "connector-preview-30d",
operational_limits: { timeout_seconds: 30 },
retry_policy: { max_attempts: 2 }
}
}, null, 2);
export default function ConnectorGovernancePage({ settings, auth }: Props) {
const [definitions, setDefinitions] = useState<ConnectorDefinition[]>([]);
const [configurations, setConfigurations] = useState<ConnectorConfiguration[]>([]);
const [runs, setRuns] = useState<ConnectorRun[]>([]);
const [selectedId, setSelectedId] = useState("");
const [draft, setDraft] = useState<ConnectorConfigurationDraft>(EMPTY_DRAFT);
const [savedKey, setSavedKey] = useState("");
const [search, setSearch] = useState("");
const [loading, setLoading] = useState(true);
const [busy, setBusy] = useState(false);
const [error, setError] = useState("");
const [success, setSuccess] = useState("");
const [definitionOpen, setDefinitionOpen] = useState(false);
const [definitionJson, setDefinitionJson] = useState(EXAMPLE_DEFINITION);
const [configurationOpen, setConfigurationOpen] = useState(false);
const [newDefinitionId, setNewDefinitionId] = useState("");
const [newDraft, setNewDraft] = useState<ConnectorConfigurationDraft>(EMPTY_DRAFT);
const [sampleJson, setSampleJson] = useState("[]");
const [externalRevision, setExternalRevision] = useState("");
const [reviewRun, setReviewRun] = useState<ConnectorRun | null>(null);
const [reviewReason, setReviewReason] = useState("");
const { requestDiscard } = useUnsavedChanges();
const selected = configurations.find((item) => item.id === selectedId) ?? null;
const canAdmin = hasScope(auth, "connectors:source:admin");
const canExecute = canAdmin || hasScope(auth, "connectors:source:write");
const dirty = Boolean(selected && draftKey(draft) !== savedKey);
const applyConfiguration = useCallback((item: ConnectorConfiguration | null) => {
const next = item ? draftFromConfiguration(item) : EMPTY_DRAFT;
setDraft(next);
setSavedKey(item ? draftKey(next) : "");
setSampleJson(JSON.stringify(
item?.effective_configuration.dry_run.sample_rows ?? [],
null,
2
));
}, []);
const reload = useCallback(async (preferredId?: string) => {
setLoading(true);
setError("");
try {
const [nextDefinitions, nextConfigurations] = await Promise.all([
listConnectorDefinitions(settings),
listConnectorConfigurations(settings)
]);
const nextId = preferredId && nextConfigurations.some((item) => item.id === preferredId)
? preferredId
: nextConfigurations.some((item) => item.id === selectedId)
? selectedId
: nextConfigurations[0]?.id ?? "";
const nextRuns = await listConnectorRuns(settings, nextId || undefined);
setDefinitions(nextDefinitions);
setConfigurations(nextConfigurations);
setRuns(nextRuns);
setSelectedId(nextId);
applyConfiguration(nextConfigurations.find((item) => item.id === nextId) ?? null);
if (!newDefinitionId && nextDefinitions[0]) setNewDefinitionId(nextDefinitions[0].id);
} catch (caught) {
setError(errorMessage(caught));
} finally {
setLoading(false);
}
}, [applyConfiguration, newDefinitionId, selectedId, settings]);
useEffect(() => {
void reload();
}, [settings.apiBaseUrl, settings.apiKey, settings.accessToken]);
const visibleConfigurations = useMemo(() => {
const needle = search.trim().toLocaleLowerCase();
return configurations.filter((item) => !needle ||
`${item.name} ${item.definition_name} ${item.status}`
.toLocaleLowerCase()
.includes(needle));
}, [configurations, search]);
const save = async (): Promise<boolean> => {
if (!selected || !canAdmin) return false;
setBusy(true);
setError("");
try {
const overrides = parseObject(draft.local_overrides, "Local overrides");
const updated = await updateConnectorConfiguration(settings, selected.id, {
expected_revision: selected.resource_revision,
name: draft.name.trim(),
status: draft.status,
endpoint_url: draft.endpoint_url.trim() || null,
credential_ref: draft.credential_ref.trim() || null,
local_overrides: overrides,
ambiguity_policy: draft.ambiguity_policy
});
setSuccess("Connector configuration saved.");
await reload(updated.id);
return true;
} catch (caught) {
setError(errorMessage(caught));
return false;
} finally {
setBusy(false);
}
};
useUnsavedDraftGuard({
dirty,
onSave: save,
onDiscard: () => applyConfiguration(selected),
title: "Unsaved connector changes",
message: "Save or discard the current connector changes before continuing."
});
const selectConfiguration = (item: ConnectorConfiguration) => {
if (item.id === selectedId) return;
requestDiscard(() => {
setSelectedId(item.id);
applyConfiguration(item);
setRuns([]);
setError("");
setSuccess("");
void listConnectorRuns(settings, item.id).then(setRuns).catch((caught) => {
setError(errorMessage(caught));
});
});
};
const createDefinition = async () => {
setBusy(true);
setError("");
try {
const payload = parseObject(definitionJson, "Definition");
const created = await upsertConnectorDefinition(settings, payload);
setDefinitionOpen(false);
setSuccess("Connector definition revision saved.");
setNewDefinitionId(created.id);
await reload(selectedId);
} catch (caught) {
setError(errorMessage(caught));
} finally {
setBusy(false);
}
};
const createConfiguration = async () => {
if (!newDefinitionId || !newDraft.name.trim()) return;
setBusy(true);
setError("");
try {
const created = await createConnectorConfiguration(settings, {
definition_id: newDefinitionId,
name: newDraft.name.trim(),
status: newDraft.status,
endpoint_url: newDraft.endpoint_url.trim() || null,
credential_ref: newDraft.credential_ref.trim() || null,
local_overrides: parseObject(newDraft.local_overrides, "Local overrides"),
ambiguity_policy: newDraft.ambiguity_policy
});
setConfigurationOpen(false);
setNewDraft(EMPTY_DRAFT);
setSuccess("Connector configuration created.");
await reload(created.id);
} catch (caught) {
setError(errorMessage(caught));
} finally {
setBusy(false);
}
};
const adoptUpdate = async () => {
if (!selected || dirty || !selected.update_available) return;
setBusy(true);
setError("");
try {
const updated = await updateConnectorConfiguration(settings, selected.id, {
expected_revision: selected.resource_revision,
adopt_latest_definition: true
});
setSuccess("Package revision adopted; protected local overrides were reapplied.");
await reload(updated.id);
} catch (caught) {
setError(errorMessage(caught));
} finally {
setBusy(false);
}
};
const run = async (mode: "dry-runs" | "simulations") => {
if (!selected || dirty) return;
setBusy(true);
setError("");
try {
const inputRows = parseRows(sampleJson);
const created = await executeConnectorRun(settings, selected.id, mode, {
idempotency_key: `${mode}-${crypto.randomUUID()}`,
input_rows: inputRows,
external_revision: externalRevision.trim() || null
});
setSuccess(`${mode === "dry-runs" ? "Dry-run" : "Simulation"} completed with status ${created.status}.`);
setRuns(await listConnectorRuns(settings, selected.id));
} catch (caught) {
setError(errorMessage(caught));
} finally {
setBusy(false);
}
};
const decideReview = async (decision: "approved" | "rejected") => {
if (!reviewRun || reviewReason.trim().length < 5) return;
setBusy(true);
setError("");
try {
await reviewConnectorRun(settings, reviewRun.id, decision, reviewReason.trim());
setReviewRun(null);
setReviewReason("");
setSuccess(`Simulation ${decision}.`);
setRuns(await listConnectorRuns(settings, selectedId));
} catch (caught) {
setError(errorMessage(caught));
} finally {
setBusy(false);
}
};
const runColumns = useMemo<DataGridColumn<ConnectorRun>[]>(() => [
{
id: "created",
header: "Run",
width: 190,
sortable: true,
value: (row) => row.created_at,
render: (row) => <>{row.mode}<br /><span className="muted">{formatDateTime(row.created_at)}</span></>
},
{
id: "status",
header: "Status",
width: 150,
sortable: true,
value: (row) => row.status,
render: (row) => <StatusBadge status={row.status} label={row.status.replaceAll("_", " ")} />
},
{
id: "summary",
header: "Effects",
width: "1fr",
minWidth: 220,
render: (row) => `${row.summary.total ?? 0} total · ${row.summary.ambiguous ?? 0} ambiguous · ${row.summary.errors ?? 0} errors`
},
{
id: "revision",
header: "Evidence",
width: 170,
render: (row) => <code title={row.configuration_hash}>r{row.configuration_revision} · {row.input_hash.slice(0, 8)}</code>
},
{
id: "actions",
header: "Actions",
width: 90,
sticky: "end",
align: "right",
render: (row) => <TableActionGroup actions={[{
id: "review",
label: "Review result",
icon: <span></span>,
applicable: ["pending", "quarantined"].includes(row.review_state),
disabled: !canAdmin || busy,
disabledReason: !canAdmin ? "Connector administration permission is required." : undefined,
onClick: () => setReviewRun(row)
}]} />
}
], [busy, canAdmin]);
const actionBar = <PageActionBar
variant="editor"
state={busy ? "saving" : dirty ? "dirty" : "clean"}
refreshable
reloadAction={{ onReload: () => void reload(selectedId), loading }}
primaryActions={<>
<Button onClick={() => setDefinitionOpen(true)} disabled={!canAdmin || busy}>
New definition
</Button>
<Button onClick={() => setConfigurationOpen(true)} disabled={!canAdmin || busy || !definitions.length}>
New configuration
</Button>
{selected?.update_available ? <Button
variant="secondary"
onClick={() => void adoptUpdate()}
disabled={!canAdmin || busy || dirty}
disabledReason={dirty ? "Save or discard local edits before adopting a package update." : undefined}
>
Adopt package revision {selected.latest_definition_revision}
</Button> : null}
</>}
discardAction={{
label: "Discard changes",
disabled: !selected,
onClick: () => applyConfiguration(selected)
}}
saveAction={{
label: "Save",
disabled: !selected || !canAdmin || busy,
disabledReason: !canAdmin ? "Connector administration permission is required." : undefined,
onClick: () => void save()
}}
/>;
return <AdminPageLayout
archetype="workspace"
title="Connector governance"
description="Version schemas and mappings, protect local overrides, and review deterministic simulations before provider-specific writes."
loading={loading && !configurations.length}
error={error}
success={success}
actions={actionBar}
className="connector-governance-page"
helpContextId="connectors.admin.governed-configurations"
>
<MetricGrid columns={4} density="compact" minimum="compact">
<MetricCard label="Definitions" value={definitions.length} />
<MetricCard label="Configurations" value={configurations.length} />
<MetricCard label="Updates available" value={configurations.filter((item) => item.update_available).length} tone="warning" />
<MetricCard label="Awaiting review" value={runs.filter((item) => ["pending", "quarantined"].includes(item.review_state)).length} tone="warning" />
</MetricGrid>
<WorkspaceLayout
variant="split"
primarySize="compact"
surface="contained"
primaryScrollable={false}
contentScrollable={false}
primaryLabel="Connector configurations"
contentLabel="Configuration details"
primary={<div className="connector-governance-list">
<FilterBar surface="panel">
<input
type="search"
value={search}
onChange={(event) => setSearch(event.target.value)}
placeholder="Search configurations"
aria-label="Search connector configurations"
/>
</FilterBar>
<SelectionList variant="navigation" label="Connector configurations">
{visibleConfigurations.map((item) => <SelectionListItem
key={item.id}
selected={item.id === selectedId}
onClick={() => selectConfiguration(item)}
>
<SelectionListItemContent
title={item.name}
description={`${item.definition_name} · revision ${item.base_definition_revision}`}
/>
<StatusBadge status={item.update_available ? "warning" : item.status} />
</SelectionListItem>)}
{!visibleConfigurations.length
? <StatePanel size="compact" description="No matching configurations." />
: null}
</SelectionList>
</div>}
>
{!selected ? <StatePanel
size="fill"
title="Connector configurations"
description="Create or select a configuration to inspect its pinned definition and simulation evidence."
/> : <div className="connector-governance-detail">
<Card title={selected.name}>
<div className="connector-revision-line">
<StatusBadge status={selected.status} />
<span>Definition revision {selected.base_definition_revision}</span>
{selected.update_available
? <StatusBadge status="warning" label={`Revision ${selected.latest_definition_revision} available`} />
: null}
<code title={selected.effective_hash}>{selected.effective_hash.slice(0, 12)}</code>
</div>
<FormGrid columns={2} collapseAt="standard" className="">
<FormField label="Name">
<input value={draft.name} disabled={!canAdmin || busy} onChange={(event) => setDraft({ ...draft, name: event.target.value })} />
</FormField>
<FormField label="Status">
<select value={draft.status} disabled={!canAdmin || busy} onChange={(event) => setDraft({ ...draft, status: event.target.value as ConnectorConfigurationDraft["status"] })}>
<option value="draft">Draft</option>
<option value="active">Active</option>
<option value="disabled">Disabled</option>
</select>
</FormField>
<FormField label="Endpoint URL" hint="Credentials are rejected in URLs.">
<input value={draft.endpoint_url} disabled={!canAdmin || busy} placeholder="https://provider.example/api" onChange={(event) => setDraft({ ...draft, endpoint_url: event.target.value })} />
</FormField>
<FormField label="Credential reference" hint="Reference an approved secret; do not paste a secret.">
<input value={draft.credential_ref} disabled={!canAdmin || busy} placeholder="vault://connectors/provider" onChange={(event) => setDraft({ ...draft, credential_ref: event.target.value })} />
</FormField>
<FormField label="Ambiguous-result policy">
<select value={draft.ambiguity_policy} disabled={!canAdmin || busy} onChange={(event) => setDraft({ ...draft, ambiguity_policy: event.target.value as ConnectorConfigurationDraft["ambiguity_policy"] })}>
<option value="manual_review">Manual review</option>
<option value="quarantine">Quarantine</option>
<option value="reject">Reject</option>
</select>
</FormField>
<FormField label="Protected local overrides" hint="JSON object leaf paths remain protected when package revisions are adopted.">
<textarea rows={8} value={draft.local_overrides} disabled={!canAdmin || busy} onChange={(event) => setDraft({ ...draft, local_overrides: event.target.value })} />
</FormField>
</FormGrid>
<p className="muted">
Protected paths: {selected.protected_paths.length ? selected.protected_paths.join(", ") : "none"}
</p>
</Card>
<Card title="Dry-run and simulation">
<p className="muted">Runs never apply changes. They retain redacted, revision-pinned evidence for review.</p>
<FormGrid columns={2} collapseAt="standard" className="">
<FormField label="Sample input rows" hint="JSON array, bounded by the definition's maximum.">
<textarea rows={9} value={sampleJson} disabled={!canExecute || busy} onChange={(event) => setSampleJson(event.target.value)} />
</FormField>
<FormField label="External revision" hint="Optional provider ETag, cursor, or snapshot revision.">
<input value={externalRevision} disabled={!canExecute || busy} onChange={(event) => setExternalRevision(event.target.value)} />
</FormField>
</FormGrid>
<div className="connector-run-actions">
<Button onClick={() => void run("dry-runs")} disabled={!canExecute || busy || dirty}>Run dry-run</Button>
<Button variant="primary" onClick={() => void run("simulations")} disabled={!canExecute || busy || dirty}>Run simulation</Button>
{dirty ? <span className="muted">Save or discard configuration changes before running.</span> : null}
</div>
</Card>
<Card title="Simulation evidence">
<DataGrid
id="connector-simulation-runs"
rows={runs}
columns={runColumns}
getRowKey={(row) => row.id}
initialFit="container"
emptyText="No dry-runs or simulations have been recorded."
/>
</Card>
<Card title="Effective governed definition">
<pre className="connector-json-preview">{JSON.stringify(selected.effective_configuration, null, 2)}</pre>
</Card>
</div>}
</WorkspaceLayout>
<Dialog
open={definitionOpen}
title="Create or revise connector definition"
onClose={() => !busy && setDefinitionOpen(false)}
closeDisabled={busy}
footer={<>
<Button onClick={() => setDefinitionOpen(false)} disabled={busy}>Cancel</Button>
<Button variant="primary" onClick={() => void createDefinition()} disabled={!canAdmin || busy}>Save definition revision</Button>
</>}
>
<p className="muted">The definition is schema-validated and every changed specification creates an immutable revision. Package definitions must name their package reference.</p>
<FormField label="Governed definition JSON">
<textarea className="connector-definition-editor" rows={24} value={definitionJson} disabled={busy} onChange={(event) => setDefinitionJson(event.target.value)} />
</FormField>
</Dialog>
<Dialog
open={configurationOpen}
title="Create connector configuration"
onClose={() => !busy && setConfigurationOpen(false)}
closeDisabled={busy}
footer={<>
<Button onClick={() => setConfigurationOpen(false)} disabled={busy}>Cancel</Button>
<Button variant="primary" onClick={() => void createConfiguration()} disabled={busy || !newDefinitionId || !newDraft.name.trim()}>Create configuration</Button>
</>}
>
<FormGrid columns={2} collapseAt="standard" className="">
<FormField label="Definition">
<select value={newDefinitionId} disabled={busy} onChange={(event) => setNewDefinitionId(event.target.value)}>
{definitions.map((item) => <option key={item.id} value={item.id}>{item.name} · revision {item.current_revision}</option>)}
</select>
</FormField>
<FormField label="Name">
<input value={newDraft.name} disabled={busy} onChange={(event) => setNewDraft({ ...newDraft, name: event.target.value })} />
</FormField>
<FormField label="Endpoint URL">
<input value={newDraft.endpoint_url} disabled={busy} onChange={(event) => setNewDraft({ ...newDraft, endpoint_url: event.target.value })} />
</FormField>
<FormField label="Credential reference">
<input value={newDraft.credential_ref} disabled={busy} onChange={(event) => setNewDraft({ ...newDraft, credential_ref: event.target.value })} />
</FormField>
<FormField label="Ambiguous-result policy">
<select value={newDraft.ambiguity_policy} disabled={busy} onChange={(event) => setNewDraft({ ...newDraft, ambiguity_policy: event.target.value as ConnectorConfigurationDraft["ambiguity_policy"] })}>
<option value="manual_review">Manual review</option>
<option value="quarantine">Quarantine</option>
<option value="reject">Reject</option>
</select>
</FormField>
<FormField label="Local overrides">
<textarea rows={7} value={newDraft.local_overrides} disabled={busy} onChange={(event) => setNewDraft({ ...newDraft, local_overrides: event.target.value })} />
</FormField>
</FormGrid>
</Dialog>
<Dialog
open={Boolean(reviewRun)}
title="Review ambiguous connector result"
onClose={() => !busy && setReviewRun(null)}
closeDisabled={busy}
footer={<>
<Button onClick={() => setReviewRun(null)} disabled={busy}>Cancel</Button>
<Button variant="danger" onClick={() => void decideReview("rejected")} disabled={busy || reviewReason.trim().length < 5}>Reject</Button>
<Button variant="primary" onClick={() => void decideReview("approved")} disabled={busy || reviewReason.trim().length < 5}>Approve</Button>
</>}
>
<p>Review {reviewRun?.summary.ambiguous ?? 0} ambiguous effects against the retained input and configuration hashes before deciding.</p>
<FormField label="Decision reason">
<textarea rows={4} value={reviewReason} disabled={busy} onChange={(event) => setReviewReason(event.target.value)} />
</FormField>
<pre className="connector-json-preview">{JSON.stringify(reviewRun?.diagnostics ?? [], null, 2)}</pre>
</Dialog>
</AdminPageLayout>;
}
function draftFromConfiguration(item: ConnectorConfiguration): ConnectorConfigurationDraft {
return {
name: item.name,
status: item.status,
endpoint_url: item.endpoint_url ?? "",
credential_ref: item.credential_ref ?? "",
local_overrides: JSON.stringify(item.local_overrides, null, 2),
ambiguity_policy: item.ambiguity_policy
};
}
function draftKey(value: ConnectorConfigurationDraft): string {
return JSON.stringify({
name: value.name.trim(),
status: value.status,
endpoint_url: value.endpoint_url.trim(),
credential_ref: value.credential_ref.trim(),
local_overrides: normalizeJson(value.local_overrides),
ambiguity_policy: value.ambiguity_policy
});
}
function normalizeJson(value: string): unknown {
try {
return JSON.parse(value);
} catch {
return value.trim();
}
}
function parseObject(value: string, label: string): Record<string, unknown> {
const parsed: unknown = JSON.parse(value);
if (!parsed || Array.isArray(parsed) || typeof parsed !== "object") {
throw new Error(`${label} must be a JSON object.`);
}
return parsed as Record<string, unknown>;
}
function parseRows(value: string): Array<Record<string, unknown>> {
const parsed: unknown = JSON.parse(value);
if (!Array.isArray(parsed) || parsed.some((item) => !item || Array.isArray(item) || typeof item !== "object")) {
throw new Error("Sample input must be a JSON array of objects.");
}
return parsed as Array<Record<string, unknown>>;
}
function errorMessage(error: unknown): string {
return error instanceof Error ? error.message : String(error);
}
+1
View File
@@ -0,0 +1 @@
export { connectorsModule as default, connectorsModule } from "./module";
+62
View File
@@ -0,0 +1,62 @@
import { createElement, lazy } from "react";
import type {
AdminSectionsUiCapability,
PlatformWebModule
} from "@govoplan/core-webui";
import "./styles/connectors.css";
const ConnectorGovernancePage = lazy(
() => import("./features/ConnectorGovernancePage")
);
const readScopes = [
"connectors:source:read",
"connectors:source:admin"
];
const adminSections: AdminSectionsUiCapability = {
sections: [
{
id: "connector-governance",
moduleId: "connectors",
kind: "management",
surfaceId: "connectors.admin.governed-configurations",
label: "Connector governance",
group: "SYSTEM",
order: 45,
anyOf: readScopes,
render: ({ settings, auth }) =>
createElement(ConnectorGovernancePage, { settings, auth })
}
]
};
export const connectorsModule: PlatformWebModule = {
id: "connectors",
label: "Connectors",
version: "0.1.18",
dependencies: [],
optionalDependencies: ["access", "audit", "policy", "ops"],
viewSurfaces: [
{
id: "connectors.admin.governed-configurations",
moduleId: "connectors",
kind: "section",
label: "Connector governance",
order: 45
},
{
id: "connectors.admin.simulation-review",
moduleId: "connectors",
kind: "section",
label: "Connector simulation review",
parentId: "connectors.admin.governed-configurations",
order: 20
}
],
uiCapabilities: {
"admin.sections": adminSections
}
};
export default connectorsModule;
+32
View File
@@ -0,0 +1,32 @@
.connector-governance-page .connector-governance-list,
.connector-governance-page .connector-governance-detail {
display: grid;
gap: var(--space-4, 1rem);
}
.connector-governance-page .connector-revision-line,
.connector-governance-page .connector-run-actions {
align-items: center;
display: flex;
flex-wrap: wrap;
gap: var(--space-3, 0.75rem);
margin-bottom: var(--space-4, 1rem);
}
.connector-governance-page textarea {
font-family: var(--font-family-mono, ui-monospace, monospace);
resize: vertical;
}
.connector-governance-page .connector-definition-editor,
.connector-governance-page .connector-json-preview {
max-height: 34rem;
overflow: auto;
white-space: pre-wrap;
}
.connector-governance-page .connector-json-preview {
background: var(--surface-subtle);
border-radius: var(--radius-md, 0.5rem);
padding: var(--space-4, 1rem);
}
@@ -0,0 +1,25 @@
import assert from "node:assert/strict";
import { readFileSync } from "node:fs";
const moduleSource = readFileSync("src/module.ts", "utf8");
const page = readFileSync("src/features/ConnectorGovernancePage.tsx", "utf8");
const api = readFileSync("src/api/governedConnectors.ts", "utf8");
assert.match(moduleSource, /"admin.sections": adminSections/);
assert.match(moduleSource, /connectors\.admin\.governed-configurations/);
assert.match(page, /<AdminPageLayout/);
assert.match(page, /<PageActionBar/);
assert.match(page, /refreshable/);
assert.match(page, /saveAction=/);
assert.match(page, /useUnsavedDraftGuard/);
assert.match(page, /<WorkspaceLayout/);
assert.match(page, /Adopt package revision/);
assert.match(page, /Protected paths/);
assert.match(page, /manual_review/);
assert.match(page, /quarantine/);
assert.match(page, /Run simulation/);
assert.match(page, /Review ambiguous connector result/);
assert.match(api, /idempotency_key/);
assert.match(api, /credential_ref/);
console.log("Connector governance UI structural contract passed.");