Kevin Veen-BirkenbachandClaude Opus 5.5
c035373518
Requirement 001 phase 6, S0: - Speech: the security class shows as "Sécurité" and is spoken as in maritime radio, "say-cure-ee-tay" three times. A hex run of 7 or more characters with a letter and a digit (commit, session, message ids) is spelled in the NATO alphabet; every other digit is spoken on its own in ICAO pronunciation (42305: four two tree zero fife). The spelling runs inside clip() before the length cut, so a phrase still fits SPEECH_LIMIT; the displayed text keeps its digits and hashes. - English: every orchestrator label, tooltip, message, error, script output, document and test string is English (Regeln -> Firewall, Hierarchie -> Hierarchy, Steuerung -> Controls, Ausführen -> Run, ...); the page declares lang="en" and formats dates as en-GB. Task filter ids are English. German stays only in the skill trigger phrases that quote the operator, and as identifiers: the view keys (view=) and the leitstand id. - tests/test_english.py scans every tracked text file for umlauts and German words, with an allowlist of the quoted trigger phrases. BREAKING CHANGE: the Stream search tokens art: and seit: are now kind: and since:; an old art: or seit: token counts as a plain word. Evidence: make test 657 OK, ruff and markdownlint clean (/tmp/s0-make-test-1.log); e2e 17 OK, none skipped (/tmp/s0-e2e-1.log); MEDUSA 86 files, 24 findings on reworded strings accepted after an independent skeptic (21 path:line, 0 rejected, no behaviour change in signing, approving, rules, denying, offices, events), rescan 0 open. 🎯 Fix: 93 % 💥 Break: 4 % 💸 Cost: 100 % ⏱️ Time: – 🛡️ Security: 100 % 🏆 Score: 89 🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
81 lines
3.0 KiB
Python
81 lines
3.0 KiB
Python
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
from .fields import LINE
|
|
|
|
SPEECH_LIMIT = 1000
|
|
SPOKEN_TEXT = 500
|
|
SPOKEN_NAME = 60
|
|
SPOKEN_GROUP = 120
|
|
ALARM_WORDS = {"pan-pan": "PAN-PAN", "security": "say-cure-ee-tay"}
|
|
ADDRESSED = ("post", "call", "receipt")
|
|
CALLS = re.compile(r"^(?:(?:MAYDAY|PAN[ -]?PAN|SECURIT[EÉY])\b[\s:,.;!-]*)+", re.IGNORECASE)
|
|
HUB_MARK = re.compile(r"\[kvb-orchestrator msg [0-9a-f]{16}\]")
|
|
HUB_FILE = re.compile(r"\s+file: /\S*$")
|
|
SPOKEN_LINE = re.compile(LINE.format(SPEECH_LIMIT))
|
|
HASH = re.compile(r"\b(?=[0-9a-f]*[a-f])(?=[0-9a-f]*[0-9])[0-9a-f]{7,}\b|[0-9]", re.IGNORECASE)
|
|
NATO = dict(zip("abcdef", ("alfa", "bravo", "charlie", "delta", "echo", "foxtrot")))
|
|
ICAO = dict(zip("0123456789", ("zero", "one", "two", "tree", "four", "fife", "six", "seven", "eight", "niner")))
|
|
|
|
|
|
def pronounced(text: str) -> str:
|
|
"""Args:
|
|
text: a radio text as displayed.
|
|
|
|
Returns:
|
|
The text with each hex run of 7 or more characters holding a letter
|
|
and a digit spelled in the NATO alphabet and every other digit
|
|
spoken on its own in ICAO pronunciation.
|
|
"""
|
|
return HASH.sub(spelled, text)
|
|
|
|
|
|
def spelled(found: re.Match) -> str:
|
|
start, end = found.span()
|
|
before = " " if start and found.string[start - 1].isalnum() else ""
|
|
after = " " if end < len(found.string) and found.string[end].isalnum() else ""
|
|
return before + " ".join(NATO.get(char) or ICAO[char] for char in found[0].lower()) + after
|
|
|
|
|
|
def clip(text: str, limit: int) -> str:
|
|
words = " ".join(pronounced(text).split())
|
|
if len(words) <= limit:
|
|
return words
|
|
return words[:limit].rsplit(" ", 1)[0] or words[:limit]
|
|
|
|
|
|
def spoken_text(cls: str, text: str) -> str:
|
|
body = HUB_MARK.sub("", text)
|
|
if body != text:
|
|
body = HUB_FILE.sub("", body)
|
|
if cls in ("mayday", *ALARM_WORDS):
|
|
body = CALLS.sub("", body.strip())
|
|
body = clip(body, SPOKEN_TEXT)
|
|
return "" if body == "-" else body
|
|
|
|
|
|
def phrase(cls: str, sender: str, called: list[str], text: str) -> str:
|
|
"""Args:
|
|
cls: the radio class of the row, one of council.CLASSES or receipt.
|
|
sender: the sender's name valid at the row's time.
|
|
called: the names of the called stations valid at the row's time.
|
|
text: the radio text.
|
|
|
|
Returns:
|
|
The row in maritime radio phraseology (SMCP style), one line of at
|
|
most SPEECH_LIMIT characters.
|
|
"""
|
|
station = clip(sender, SPOKEN_NAME) or "unknown station"
|
|
if cls == "mayday":
|
|
head, end = f"MAYDAY MAYDAY MAYDAY, this is {station} {station} {station}", "over"
|
|
elif cls in ALARM_WORDS:
|
|
word = ALARM_WORDS[cls]
|
|
head, end = f"{word} {word} {word}, all stations, this is {station}", "over"
|
|
elif cls in ADDRESSED and called:
|
|
group = clip(" and ".join(clip(name, SPOKEN_NAME) for name in called), SPOKEN_GROUP)
|
|
head, end = f"{group}, {group}, this is {station}", "over"
|
|
else:
|
|
head, end = f"all stations, this is {station}", "out"
|
|
return ", ".join(part for part in (head, spoken_text(cls, text), end) if part)
|