# -*- coding: utf-8 -*-
"""customer_copy_vocab — THE ONE list of customer-copy vocabulary, shared by both repos.

WHY THIS FILE EXISTS AT ALL. Two guards need the same words: the controller's
`retrieval_promise_gate.py` (which scans the box's own screens) and this repo's `hub_copy_gate.py`
(which scans the hub's e-mails and binding pages). Two copies of a word list is not a theoretical
risk here — it is the R-299 defect exactly: a guard asserted one inflection of a Hungarian verb and
the plural, one paragraph above, walked straight past it. A second list drifts the same way.

So the list lives HERE, in `felhom.eu/scripts/`, which is already the established home for gates both
repos consume without copying (`reuse_refs_check.py`, `instructions_gate.py` — the controller's own
`controller_gates.py` runs them from this directory and FAILS when the sibling clone is absent, which
is the fail-CLOSED shape a shared gate needs).

⚠ ADOPTION IS HALF DONE, AND SAYING SO IS THE POINT. `hub_copy_gate.py` imports this module.
`felhom-controller/controller/scripts/retrieval_promise_gate.py` still carries its own `STEMS`
literal, because the session that wrote this module was under a hard end-state requirement to leave
felhom-controller untouched (its target box was being re-deployed the same evening). Until that gate
imports this file, `hub_copy_gate.py` DRIFT-CHECKS it: it reads the controller gate's `STEMS` and
fails if the two lists disagree. That gives single-source semantics tonight without a cross-repo
edit — but it is a scaffold, not the destination. Register row: R-325.
"""

# ── The retired names ────────────────────────────────────────────────────────────────────────────
#
# A name here is BANNED from customer-facing copy outright. Unlike the stems below, these are not
# claims that might be true in context — they are names for a secret that a different secret now
# owns, and a customer meeting one is being told two things have the same name.
#
# Each entry is a SUBSTRING, deliberately shorn of its leading capital and its ending, so a
# possessive or accusative form cannot slip past a check written against the nominative:
# „visszaállító jelszavadat" must convict as surely as „Visszaállító jelszó". That is the R-299
# lesson applied to nouns instead of verbs.
RETIRED_NAMES = {
    "isszaállító kód": (
        "R-295 (2026-08-10 box side, 2026-08-13 hub side). The THREE-word code that takes control of "
        "the dashboard is „Beállító kód”. „Visszaállító kód” was a near-homograph of the escrow "
        "„Helyreállítási kód” and the collision cost a real code."),
    "isszaállító jelsz": (
        "R-323 (2026-08-13). The FIVE-word phrase that proves the account owns the box being bound is "
        "„Tulajdonosi jelmondat”. „Visszaállító jelszó” was one word from the name retired above, and "
        "it was false besides — the phrase restores nothing."),
}

# ── The retrieval-promise stems ──────────────────────────────────────────────────────────────────
#
# These are NOT banned. Each carries the claim "your old backups can be got back", which is sometimes
# TRUE and must then be sayable. An occurrence must be REGISTERED with a reason in the consuming
# gate's allowlist; an unregistered one fails.
#
# The docstring of the controller gate is the long version and is worth reading before adding a stem:
# five instances of this claim surfaced ONE AT A TIME, and the obvious guard (ban the sentence) was
# tried twice and failed twice.
RETRIEVAL_STEMS = ["visszaállíthat", "visszaszerezhet", "visszahozhat", "visszanyit"]

# ── The same claim, in English (R-558, hub v0.118.0) ─────────────────────────────────────────────
#
# Localisation slice 3 gave the hub an English bundle, so every sentence these guards exist for can
# now be written twice. A guard that reads only the Hungarian half would be HALF A GUARD, and the
# English half is the one nobody has years of habit reading carefully.
#
# ⚠ THESE ARE REGEXES, AND THEY MATCH A CAPABILITY CLAIM — NOT A WORD.
#
# The first attempt at this list was the bare stems "restor" and "recover", and it convicted 141
# sentences on its first run: „node_recovered" („Your server can be reached again"), „Disaster
# recovery has started", the Restore PAGE NAME. That is not a near miss, it is the wrong instrument:
# in Hungarian the stems ARE the claim, because „visszaállíthat" is a single word meaning *can
# restore*. English splits the modal from the verb, so the English form of the claim is a PHRASE, and
# matching the verb alone matches every honest use of a perfectly ordinary word.
#
# A guard that cries wolf 141 times is worse than no guard: it gets an allowlist entry per sentence
# and then nobody reads it. So each pattern below carries the modal.
#
# ⚠ EVERY PATTERN ALLOWS AN ADVERB BETWEEN THE MODAL AND THE VERB, and that is not defensive
# padding — the decoy suite caught its absence. The first version read `can\s+(?:be\s+)?restor`
# and a planted "Your earlier backups can STILL be restored with your old recovery code" walked
# straight through it. One adverb. That is R-299 again, in English: a guard written for one surface
# form of a claim, and the claim wearing another.
_ADV = r"(?:\s+\w+ly|\s+still|\s+always|\s+then)?"      # an optional adverb, e.g. "can STILL be"
RETRIEVAL_STEMS_EN = [
    # can [still] [be] restored / recover / retrieve
    r"\b(?:can|could|will\s+be\s+able\s+to|are\s+able\s+to|is\s+able\s+to)" + _ADV +
    r"(?:\s+be)?" + _ADV + r"\s+(?:restor|recover|retriev|un-?seal|open)",
    # can [still] get/bring <it> back
    r"\b(?:can|could|will)" + _ADV + r"(?:\s+be\s+able\s+to)?" + _ADV +
    r"\s+(?:get|bring|have)\s+\w+\s+back",
    # the adjectives, which carry the claim on their own
    r"\b(?:restorable|recoverable|retrievable)\b",
    # "are [still] recoverable / restorable"
    r"\b(?:are|is|remain|remains|stay|stays)" + _ADV + r"\s+(?:restor|recover|retriev)able",
]

# The retired names have no English twin, and that is a FACT rather than an omission: „Beállító kód",
# „Helyreállítási kód" and „Tulajdonosi jelmondat" are translated in the bundle (setup code, recovery
# code, owner passphrase) and the retired ones were never written in English at all — there is no
# English form of „Visszaállító kód" that has ever shipped. If one is ever coined, it belongs here.
RETIRED_NAMES_EN = {}

# ── The three secrets, so a reviewer can check a name against the THING ───────────────────────────
#
# Not consumed by any check — it is here because every argument about these names has had to be
# reconstructed from register rows, and the table is the argument.
THE_THREE_SECRETS = [
    ("three words", "takes control of the dashboard", "Beállító kód"),
    ("ten words", "opens the sealed off-site backups", "Helyreállítási kód"),
    ("five words", "proves the account owns the box being bound", "Tulajdonosi jelmondat"),
]