Merge pull request #267 from kjd/housekeeping

Housekeeping

Author: kjd

.github/workflows/deploy.yml

@@ -50,8 +50,7 @@ jobs:
         path: dist/
 
   publish-to-pypi:
-    name: >-
-      Publish to PyPI
+    name: Publish to PyPI
     if: startsWith(github.ref, 'refs/tags/v')  # only publish to PyPI on version tag pushes
     needs:
     - build

.github/workflows/python-package.yml

@@ -1,6 +1,3 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
 name: Python package
 
 on:
@@ -16,6 +13,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+      - name: Check the license copyright year is current
+        run: |
+          year="$(date -u +%Y)"
+          license_year="$(grep -m1 '^Copyright' LICENSE.md | grep -oE '[0-9]{4}' | tail -1)"
+          if [ "$license_year" != "$year" ]; then
+            echo "::error file=LICENSE.md::Copyright year $license_year is not the current year $year; update LICENSE.md" >&2
+            exit 1
+          fi
       - name: Set up Python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
@@ -75,7 +80,7 @@ jobs:
             gil: '0'
           - python-version: '3.15t-dev'
             gil: '0'
-    runs-on: ${{ matrix.os || 'ubuntu-latest' }}
+    runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
     - name: Set up Python ${{ matrix.python-version }}

.gitignore

@@ -1,21 +1,18 @@
 *.py[cod]
 *.so
 *.egg
-*.egg-info
-dist
-build
-eggs
-parts
-bin
-var
-sdist
-develop-eggs
-.installed.cfg
-lib
-lib64
-.idea
+*.egg-info/
+dist/
+build/
+sdist/
+.idea/
 *.swp
 
 .hypothesis/
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
 .coverage
 htmlcov/
+.DS_Store
+uv.lock

README.md

@@ -40,7 +40,7 @@ specification to be a local user-interface issue distinct from IDNA
 conversion functionality.
 
 For example, "Königsgäßchen" is not a permissible label as capital letters
-are not allowed. UTS 46 will convert this into lower case prior to applying
+are not allowed. UTS #46 will convert this into lower case prior to applying
 the IDNA conversion.
 
 ```pycon
@@ -78,7 +78,7 @@ Exceptions carry machine-readable attributes so that applications
 do not need to parse the message: `code` is a short, stable identifier
 for the rule that failed (listed below); and, when the failure can be
 attributed to a particular character, `text` (the label, or domain for
-UTS 46 processing, being validated), `codepoint` (the offending
+UTS #46 processing, being validated), `codepoint` (the offending
 codepoint as an integer) and `position` (its 1-based index within
 `text`, as quoted in the message) are set. Each is `None` when it does
 not apply. Message wording is not part of the API and may change.
@@ -112,8 +112,8 @@ disallowed_codepoint 75 1 Königsgäßchen
 | `non_canonical_alabel` | An `xn--` label is not the canonical Punycode encoding of its U-label (a "fake A-label") |
 | `invalid_ascii` | Byte input is not ASCII |
 | `invalid_utf8` | Byte input is not UTF-8 |
-| `uts46_disallowed` | A codepoint is disallowed by the UTS 46 mapping table |
-| `uts46_std3` | An ASCII character is rejected by the UTS 46 STD3 rules |
+| `uts46_disallowed` | A codepoint is disallowed by the UTS #46 mapping table |
+| `uts46_std3` | An ASCII character is rejected by the UTS #46 STD3 rules |
 | `unsupported_errors` | The codec was given an `errors` handler other than `strict` |
 
 
@@ -146,32 +146,24 @@ the tool exits with a non-zero status if any conversion failed.
 
 ## Additional Notes
 
-* **Version support**. This library supports Python 3.9 and higher.
+* **Python version support**. This library supports Python 3.9 and higher.
   As this library serves as a low-level toolkit for a variety of
   applications, we strive to support all versions of Python that are
-  not beyond end-of-life.
+  not beyond end-of-life. Free-threaded Python is also supported,
+  as the library holds no mutable global state the functions can be
+  called concurrently from multiple threads.
 
 * **Unicode version**. The IDNA and UTS #46 lookup tables are generated
-  from a specific Unicode release, available as `idna.unicode_version`
-  (and shown by `idna --version`). Some checks — NFC normalisation,
-  bidirectional classes and combining classes — still come from the
+  from a specific Unicode release. Some Unicode data depends on the
   running Python's `unicodedata` module, so on an older Python a
-  character new to Unicode may be rejected (typically with the
-  `unknown_codepoint` or `bidi_unknown_direction` error codes) even
-  though the tables know about it.
-
-* **Thread safety and free-threaded Python**. The library holds no
-  mutable global state — the lookup tables are read-only — so all
-  functions may be called concurrently from multiple threads, and the
-  incremental codec classes keep their state per instance. The test
-  suite runs on free-threaded CPython builds (`3.14t`) with the GIL
-  disabled and includes a concurrency test.
+  character new to Unicode may be rejected as unknown even if this
+  library knows about it.
 
 * **Emoji**. It is an occasional request to support emoji domains in
   this library. Encoding of symbols like emoji is expressly prohibited by
   the IDNA technical standard, and emoji domains are broadly phased
   out across the domain industry due to associated security risks.
 
-* **Regenerating lookup tables**. The IDNA and UTS 46 functionality
+* **Regenerating lookup tables**. The IDNA and UTS #46 functionality
   relies upon pre-calculated lookup tables, generated using the
   `idna-data` script in [`tools/`](tools/README.md).

SECURITY.md

@@ -15,5 +15,5 @@ Please disclose your issue through Github's
 [security advisory facility](https://github.com/kjd/idna/security/advisories/new).
 
 We will endeavor to prioritize review, remediation and disclosure of
-vulnerabilites. However, be mindful that this project is maintained by a
+vulnerabilities. However, be mindful that this project is maintained by a
 team of volunteers who work on a best effort basis.

idna/codec.py

@@ -75,7 +75,6 @@ def _buffer_encode(self, data: str, errors: str, final: bool) -> tuple[bytes, in
                 size += 1
             size += len(label)
 
-        # Join with U+002E
         result_bytes = b".".join(result) + trailing_dot
         size += len(trailing_dot)
         return result_bytes, size

idna/core.py

@@ -466,8 +466,9 @@ def check_label(label: str | bytes | bytearray) -> None:
     if len(label) == 0:
         raise IDNAError("Empty Label", code="empty_label")
 
-    # Reject on domain length rather than label length so support some UTS 46
-    # use cases, still reducing processing of label contextual rules
+    # Check against the domain length rather than the label length to
+    # support some UTS #46 use cases, while still bounding the work done
+    # by the label contextual rules below.
     if not valid_string_length(label, trailing_dot=True):
         raise IDNAError("Label too long", code="label_too_long")
 
@@ -662,31 +663,27 @@ def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False
     if len(domain) > _max_input_length:
         raise IDNAError("Domain too long", code="input_too_long")
     if domain.isascii():
-        # The only ASCII mapping in UTS #46 is upper- to lowercase; every
-        # other ASCII codepoint has status V (tests pin this against the
-        # table). ASCII is invariant under NFC, so this is the whole job.
+        # The only ASCII mapping in UTS #46 is upper- to lowercase, and
+        # ASCII is invariant under NFC, so lowercasing is the whole job.
         result = domain.lower()
         if std3_rules:
             _check_std3(result, domain, 0)
         return result
 
     from .uts46data import uts46_replacements, uts46_starts, uts46_statuses
 
-    # Characters that pass through unchanged are not copied one at a time:
-    # ``start`` marks the beginning of the current run of unchanged input,
-    # and a run is only sliced out when a character has to be replaced or
-    # dropped. For the common case where nothing changes no copy is made.
-    # The STD3 check is applied to each piece of output as it is produced,
-    # so that a violation is reported at its position in the input.
+    # ``start`` marks the run of unchanged input not yet copied; a run is
+    # only sliced out when a character must be replaced or dropped, so the
+    # common no-change case makes no copy. STD3 is checked per output piece
+    # to report a violation at its input position.
     output: list[str] = []
     start = 0
     for pos, char in enumerate(domain):
         code_point = ord(char)
         i = code_point if code_point < 256 else bisect.bisect_right(uts46_starts, code_point) - 1
         status = uts46_statuses[i]
-        # UTS #46 §4: V is always valid, D is deviation (kept: transitional
-        # processing, which mapped it, is deprecated), M is mapped, I is
-        # ignored, anything else is disallowed.
+        # UTS #46 §4: V valid, D deviation (kept), M mapped, I ignored,
+        # anything else disallowed.
         if status == _STATUS_VALID:
             continue
         if status == _STATUS_MAPPED:
@@ -773,8 +770,6 @@ def encode(
     if uts46:
         s = uts46_remap(s, std3_rules)
 
-    # Reject inputs that exceed the maximum DNS domain length up-front
-    # to avoid expensive computation on long inputs.
     if not valid_string_length(s, trailing_dot=True):
         raise IDNAError("Domain too long", code="domain_too_long")
 
@@ -840,8 +835,6 @@ def decode(
         raise IDNAError("Domain too long", code="input_too_long")
     if uts46:
         s = uts46_remap(s, std3_rules, False)
-    # Reject inputs that exceed the maximum DNS domain length up-front
-    # to avoid expensive computation on long inputs.
     if not valid_string_length(s, trailing_dot=True):
         raise IDNAError("Domain too long", code="domain_too_long")
     trailing_dot = False

pyproject.toml

@@ -53,6 +53,7 @@ all = [
     "ty >= 0.0.37",
     "pytest >= 8.3.2",
     "hypothesis >= 6.141.1",
+    "coverage >= 7.10.0",
 ]
 
 [tool.coverage.run]

tests/test_idna.py

@@ -138,7 +138,6 @@ def test_check_bidi(self):
 
         # RFC 5893 Rule 2
         self.assertTrue(idna.check_bidi(r + al))
-        self.assertTrue(idna.check_bidi(r + al))
         self.assertTrue(idna.check_bidi(r + an))
         self.assertTrue(idna.check_bidi(r + en))
         self.assertTrue(idna.check_bidi(r + es + al))

tests/test_idna_codec.py

@@ -6,6 +6,14 @@
 
 CODEC_NAME = "idna2008"
 
+# (decoded, encoded) pairs derived from CPython's Lib/test/test_codecs.py
+INCREMENTAL_TESTS = (
+    ("python.org", b"python.org"),
+    ("python.org.", b"python.org."),
+    ("pyth\xf6n.org", b"xn--pythn-mua.org"),
+    ("pyth\xf6n.org.", b"xn--pythn-mua.org."),
+)
+
 
 class IDNACodecTests(unittest.TestCase):
     def setUp(self):
@@ -58,16 +66,7 @@ def encode(obj):
         return self.idnatests.test_encode(encode=encode)
 
     def testIncrementalDecoder(self):
-        # Tests derived from Python standard library test/test_codecs.py
-
-        incremental_tests = (
-            ("python.org", b"python.org"),
-            ("python.org.", b"python.org."),
-            ("pyth\xf6n.org", b"xn--pythn-mua.org"),
-            ("pyth\xf6n.org.", b"xn--pythn-mua.org."),
-        )
-
-        for decoded, encoded in incremental_tests:
+        for decoded, encoded in INCREMENTAL_TESTS:
             self.assertEqual(
                 "".join(codecs.iterdecode((bytes([c]) for c in encoded), CODEC_NAME)),
                 decoded,
@@ -106,15 +105,7 @@ def testIncrementalDecoder(self):
         self.assertEqual(decoder.decode(b"", True), "")
 
     def testIncrementalEncoder(self):
-        # Tests derived from Python standard library test/test_codecs.py
-
-        incremental_tests = (
-            ("python.org", b"python.org"),
-            ("python.org.", b"python.org."),
-            ("pyth\xf6n.org", b"xn--pythn-mua.org"),
-            ("pyth\xf6n.org.", b"xn--pythn-mua.org."),
-        )
-        for decoded, encoded in incremental_tests:
+        for decoded, encoded in INCREMENTAL_TESTS:
             self.assertEqual(b"".join(codecs.iterencode(decoded, CODEC_NAME)), encoded)
 
         encoder = codecs.getincrementalencoder(CODEC_NAME)()