Skip to content

deps: update dependencies and align tables with Unicode 18 #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
DevExzh merged 4 commits into from
Nov 12, 2026
Merged

deps: update dependencies and align tables with Unicode 18 #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b42291a
deps(deps): bump unicode-normalization
dependabot[bot] Oct 26, 2026
c6f04e5
deps: refresh dependencies and Unicode 18 tables
DevExzh Nov 12, 2026
ad70091
Merge remote-tracking branch 'origin/main' into dependabot/cargo/patc…
DevExzh Nov 12, 2026
7e4aab8
Merge remote-tracking branch 'origin/main' into dependabot/cargo/patc…
DevExzh Nov 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
543 changes: 180 additions & 363 deletions Cargo.lock
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,10 +40,10 @@ quick_check_oracle = []

[dev-dependencies]
proptest = "1.12"
unicode-normalization = "0.1"
unicode-normalization = "0.1.26"
icu_normalizer = "2.4"
simdutf8 = "0.1"
criterion = { version = "0.8", features = ["html_reports"] }
simdutf8 = "0.1.5"
criterion = { version = "0.8.2", features = ["html_reports"] }
simd-normalizer = { path = ".", features = ["internal-test-api"] }

[[bench]]
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ Provides NFC, NFD, NFKC, and NFKD normalization with a single-pass,
SIMD-guided architecture that scans 64-byte chunks to skip ASCII and
passthrough regions in bulk. Non-passthrough bytes are handled with scalar
decode, decompose, CCC sort, and optional recomposition. Tables are generated
from Unicode 17.0 data.
from Unicode 18.0 data.

## Features

Expand Down
75 changes: 25 additions & 50 deletions fuzz/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions fuzz/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,9 @@ publish = false
cargo-fuzz = true

[dependencies]
libfuzzer-sys = "0.4"
libfuzzer-sys = "0.4.13"
simd-normalizer = { path = ".." }
unicode-normalization = "0.1"
unicode-normalization = "0.1.26"

[[bin]]
name = "fuzz_nfc"
Expand Down
17 changes: 12 additions & 5 deletions scripts/generate_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
Usage:
python3 scripts/generate_tables.py

Downloads UCD files for Unicode 17.0 and generates:
Downloads UCD files for Unicode 18.0 and generates:
src/tables/decomposition.rs
src/tables/composition.rs
src/tables/ccc.rs
Expand All @@ -19,7 +19,7 @@
from pathlib import Path
from collections import defaultdict

UNICODE_VERSION = "17.0.0"
UNICODE_VERSION = "18.0.0"
UCD_BASE_URL = f"https://www.unicode.org/Public/{UNICODE_VERSION}/ucd"

UCD_FILES = {
Expand All @@ -30,13 +30,13 @@
"CaseFolding.txt": f"{UCD_BASE_URL}/CaseFolding.txt",
}

SECURITY_BASE_URL = "https://www.unicode.org/Public/security/latest"
SECURITY_BASE_URL = f"https://www.unicode.org/Public/{UNICODE_VERSION}/security"
SECURITY_FILES = {
"confusables.txt": f"{SECURITY_BASE_URL}/confusables.txt",
}

SCRIPT_DIR = Path(__file__).resolve().parent
CACHE_DIR = SCRIPT_DIR / "ucd_cache"
CACHE_DIR = SCRIPT_DIR / "ucd_cache" / UNICODE_VERSION
PROJECT_ROOT = SCRIPT_DIR.parent
OUTPUT_DIR = PROJECT_ROOT / "src" / "tables"
TEST_DATA_DIR = PROJECT_ROOT / "tests" / "data"
Expand Down Expand Up @@ -901,6 +901,7 @@ def write_normalization_tests_rs(tests):
f.write(f"// Test cases: {len(tests)}\n\n")
f.write("#![cfg_attr(rustfmt, rustfmt::skip)]\n\n")
f.write("#[derive(Debug)]\n")
f.write("#[allow(dead_code)]\n")
f.write("pub struct NormalizationTest {\n")
f.write(" pub source: &'static str,\n")
f.write(" pub nfc: &'static str,\n")
Expand All @@ -915,7 +916,13 @@ def write_normalization_tests_rs(tests):
nfd_lit = codepoints_to_rust_str(nfd)
nfkc_lit = codepoints_to_rust_str(nfkc)
nfkd_lit = codepoints_to_rust_str(nfkd)
f.write(f" NormalizationTest {{ source: {src_lit}, nfc: {nfc_lit}, nfd: {nfd_lit}, nfkc: {nfkc_lit}, nfkd: {nfkd_lit} }},\n")
f.write(" NormalizationTest {\n")
f.write(f" source: {src_lit},\n")
f.write(f" nfc: {nfc_lit},\n")
f.write(f" nfd: {nfd_lit},\n")
f.write(f" nfkc: {nfkc_lit},\n")
f.write(f" nfkd: {nfkd_lit},\n")
f.write(" },\n")
f.write("];\n")
print(f" Wrote {path} ({path.stat().st_size} bytes, {len(tests)} test cases)")

Expand Down
Loading
Loading