mirror of
https://github.com/vitorpamplona/amethyst.git
synced 2026-10-05 19:28:25 +00:00
Claude
0a48ddab5d
Linux native's UnicodeNormalizer returned its input unchanged, so NIP-49 keys encrypted under a non-ASCII password (normalized by every other client) could not be decrypted there. Add a pure-Kotlin UAX #15 NFKC normalizer with tables generated from the Unicode 17.0 UCD by tools/unicode-nfkc/generate.py, and use it on Linux. It passes all 20,034 lines of Unicode's NormalizationTest.txt and matches java.text.Normalizer for every code point the JDK defines (NfkcNormalizerJdkParityTest). NostrSignerRemote.decryptZapEvent and deriveKey were TODO(), whose NotImplementedError is an Error that escapes DecryptCache's handlers. A private zap's anon payload is AES-CBC under the NIP-04 shared secret, so the recipient now decrypts it through the bunker's nip04_decrypt. The sender's copy and deriveKey need the raw private key, which a bunker never exposes, so they now throw CouldNotPerformException and UnsupportedMethodException. An end-to-end test runs the remote signer against Quartz's own bunker over an in-process relay. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QytMdt3MPxvmmWrAX3bJYS
25 lines
1.1 KiB
Markdown
25 lines
1.1 KiB
Markdown
# unicode-nfkc
|
|
|
|
Generates `NfkcData.kt`, the tables behind Quartz's pure-Kotlin NFKC normalizer
|
|
(`quartz/.../utils/unicode/NfkcNormalizer.kt`). Linux native uses it because it
|
|
has no platform normalizer. JVM/Android use `java.text.Normalizer` and Apple
|
|
uses `NSString`. NIP-49 NFKC-normalizes passwords before scrypt, so a wrong
|
|
normalizer silently breaks key decryption.
|
|
|
|
```bash
|
|
V=17.0.0
|
|
mkdir -p /tmp/ucd && for f in UnicodeData.txt DerivedNormalizationProps.txt; do
|
|
curl -sSfo /tmp/ucd/$f https://www.unicode.org/Public/$V/ucd/$f
|
|
done
|
|
tools/unicode-nfkc/generate.py /tmp/ucd \
|
|
quartz/src/commonMain/kotlin/com/vitorpamplona/quartz/utils/unicode/NfkcData.kt
|
|
```
|
|
|
|
Commit the regenerated file. `NfkcNormalizerJdkParityTest` (jvmTest) checks the
|
|
result against the JDK for every code point the JDK knows. To check a new
|
|
Unicode version fully, run the normalizer over that version's
|
|
`NormalizationTest.txt` (column 4 is the NFKC of columns 1-5).
|
|
|
|
The data is derived from the Unicode Character Database, distributed under the
|
|
permissive [Unicode License v3](https://www.unicode.org/license.txt).
|