flemming-it
a66d49f5c4
Brings module.yaml in line with F∆I 0.12.0's capability naming convention. The legacy schema_version 1 (with implicit provider) still loads in 0.12.0 via the grace-period default, but this bump makes the publisher identity explicit and unblocks storage-layout migration via 'fai migrate'. See fai/platform docs/reference/capability-namespaces.yaml + docs/operations/migration-to-0.12.md. Signed-off-by: flemming-it <sf@flemming.it>
54 lines
1.9 KiB
YAML
54 lines
1.9 KiB
YAML
schema_version: 2
|
|
provider: fai
|
|
name: text-anonymize
|
|
version: 0.1.0
|
|
|
|
# Capability provided by this module.
|
|
provides:
|
|
- capability: text.anonymize
|
|
version: 0.1.0
|
|
|
|
# Inputs the invoke function accepts.
|
|
inputs:
|
|
# The text to anonymize. Plain UTF-8, any length the host
|
|
# tolerates as a Payload::Text (operator policy caps).
|
|
text: text
|
|
# Optional newline-separated list of additional bare terms
|
|
# (operator-supplied — names of people, organisations, or
|
|
# places that the regex patterns won't catch) to redact in
|
|
# addition to the built-in categories. Empty string disables
|
|
# this extension. Each line is matched whole-word
|
|
# (case-insensitive).
|
|
custom_terms: text
|
|
|
|
# Outputs produced.
|
|
outputs:
|
|
# The anonymized text. Each detected entity is replaced
|
|
# with a token of the shape ⟦TYPE_N⟧ where TYPE is the
|
|
# category (EMAIL, PHONE, IBAN, BIC, IPV4, GERMAN_TAX_ID,
|
|
# NAME, CUSTOM) and N is a stable counter starting at 1
|
|
# per category, in order of first occurrence. The opening
|
|
# / closing characters are U+27E6 / U+27E7 (mathematical
|
|
# white square brackets) so the token never collides with
|
|
# plain `[…]` already present in the source.
|
|
anonymized: text
|
|
# JSON report describing each redaction:
|
|
# {
|
|
# "redactions": [
|
|
# { "type": "EMAIL", "token": "⟦EMAIL_1⟧",
|
|
# "original": "foo@bar.de", "offset": 42 }
|
|
# ],
|
|
# "counts": { "EMAIL": 3, "PHONE": 1, ... }
|
|
# }
|
|
# The full `original` text is included so the operator can
|
|
# run a verify-pass against the redacted file (compliance:
|
|
# GDPR Art. 32(1)(a) "ability to undo" requirement). Hub
|
|
# operators that want a pseudo-anonymisation-only flow can
|
|
# discard this output downstream.
|
|
report: json
|
|
|
|
# Permissions required.
|
|
#
|
|
# Pure-Rust, regex-only, in-WASM. No filesystem, no network,
|
|
# no LLM. The empty list makes that explicit.
|
|
permissions: []
|