metadata-utils 0.2.0__tar.gz → 1.0.0__tar.gz

metadata_utils-1.0.0/CHANGES.txt

@@ -0,0 +1,36 @@
+1.0.0
+    * Add helper examples and test entity round trips and compatibility normalization.
+    * Consolidate packaging and tox configuration and add coverage reporting.
+    * Extend the test matrix through Python 3.15 while retaining Python 3.6+.
+    * Document the quoted HTML attribute context and tighten type annotations.
+    * Use the official Black pre-commit mirror.
+
+0.2.1
+    * minor formatting
+0.2.0
+    * typing support
+    * drop PY2
+    * drop PY3.5
+0.1.3
+	packaging fixes
+
+0.1.2
+	* black
+	* upgraded black; 20.8b1
+	* integrated with pre-commit
+	* tox and github actions
+
+0.1.1
+	* reverted aggressive 2to3 change
+
+0.1.0
+	* python 3 support
+	* tests
+
+0.0.2
+	* added `force_clean_ascii_NFKD`
+	* added `force_clean_ascii_NFKC`
+	* flake8
+
+0.0.1
+	* initial import

{metadata_utils-0.2.0 → metadata_utils-1.0.0}/MANIFEST.in

@@ -2,7 +2,6 @@ graft src
 graft tests
 
 include setup.cfg pyproject.toml
-include tox.ini
 include CHANGES.txt
 include LICENSE
 include README.md

metadata_utils-1.0.0/PKG-INFO

@@ -0,0 +1,69 @@
+Metadata-Version: 2.4
+Name: metadata_utils
+Version: 1.0.0
+Summary: Lightweight Metadata Support
+Home-page: https://github.com/jvanasco/metadata_utils
+Author: Jonathan Vanasco
+Author-email: jvanasco@2xlp.com
+License: MIT
+Keywords: web
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: testing
+Requires-Dist: pytest; extra == "testing"
+Requires-Dist: mypy; extra == "testing"
+Dynamic: license-file
+
+![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
+
+metadata_utils
+==============
+
+This package offers lightweight tools for dealing with metadata in HTML.
+
+## Quoted HTML attributes
+
+Use `html_attribute_escape` on text before inserting it into a quoted HTML
+attribute.
+
+```python
+from metadata_utils import html_attribute_escape, html_attribute_unescape
+
+title = 'Fish & "Chips"'
+escaped = html_attribute_escape(title)
+assert f'<span title="{escaped}"></span>' == (
+    '<span title="Fish &amp; &quot;Chips&quot;"></span>'
+)
+assert html_attribute_unescape(escaped) == title
+```
+
+`html_attribute_unescape` decodes one layer of the five named entities emitted
+by the escape function (`&amp;`, `&lt;`, `&gt;`, `&quot;`, and `&apos;`).
+Other named and numeric references pass through unchanged.
+
+## ASCII normalization
+
+Both helpers apply Unicode normalization, drop any remaining non-ASCII
+characters, and return `bytes`. Both expand the `fi` ligature into `fi`.
+NFKD decomposes `é` so the ASCII `e` survives. NFKC keeps the composed
+`é`, which is dropped during ASCII encoding.
+
+```python
+from metadata_utils import force_clean_ascii_NFKC, force_clean_ascii_NFKD
+
+assert force_clean_ascii_NFKD("fi café") == b"fi cafe"
+assert force_clean_ascii_NFKC("fi café") == b"fi caf"
+```

metadata_utils-1.0.0/README.md

@@ -0,0 +1,40 @@
+![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
+
+metadata_utils
+==============
+
+This package offers lightweight tools for dealing with metadata in HTML.
+
+## Quoted HTML attributes
+
+Use `html_attribute_escape` on text before inserting it into a quoted HTML
+attribute.
+
+```python
+from metadata_utils import html_attribute_escape, html_attribute_unescape
+
+title = 'Fish & "Chips"'
+escaped = html_attribute_escape(title)
+assert f'<span title="{escaped}"></span>' == (
+    '<span title="Fish &amp; &quot;Chips&quot;"></span>'
+)
+assert html_attribute_unescape(escaped) == title
+```
+
+`html_attribute_unescape` decodes one layer of the five named entities emitted
+by the escape function (`&amp;`, `&lt;`, `&gt;`, `&quot;`, and `&apos;`).
+Other named and numeric references pass through unchanged.
+
+## ASCII normalization
+
+Both helpers apply Unicode normalization, drop any remaining non-ASCII
+characters, and return `bytes`. Both expand the `fi` ligature into `fi`.
+NFKD decomposes `é` so the ASCII `e` survives. NFKC keeps the composed
+`é`, which is dropped during ASCII encoding.
+
+```python
+from metadata_utils import force_clean_ascii_NFKC, force_clean_ascii_NFKD
+
+assert force_clean_ascii_NFKD("fi café") == b"fi cafe"
+assert force_clean_ascii_NFKC("fi café") == b"fi caf"
+```

metadata_utils-1.0.0/pyproject.toml

@@ -0,0 +1,10 @@
+[build-system]
+requires = ["setuptools>=61; python_version >= '3.7'", "setuptools>=59.6,<60; python_version < '3.7'", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.black]
+target-version = ['py36']
+
+[tool.mypy]
+disallow_untyped_defs = true
+disallow_any_generics = true

metadata_utils-1.0.0/setup.cfg

@@ -0,0 +1,74 @@
+[metadata]
+name = metadata_utils
+version = attr: metadata_utils.__VERSION__
+description = Lightweight Metadata Support
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/jvanasco/metadata_utils
+author = Jonathan Vanasco
+author_email = jvanasco@2xlp.com
+keywords = web
+license = MIT
+license_file = LICENSE
+classifiers = 
+	Intended Audience :: Developers
+	Programming Language :: Python :: 3
+	Programming Language :: Python :: 3.6
+	Programming Language :: Python :: 3.7
+	Programming Language :: Python :: 3.8
+	Programming Language :: Python :: 3.9
+	Programming Language :: Python :: 3.10
+	Programming Language :: Python :: 3.11
+	Programming Language :: Python :: 3.12
+	Programming Language :: Python :: 3.13
+	Programming Language :: Python :: 3.14
+	Programming Language :: Python :: 3.15
+
+[options]
+python_requires = >=3.6
+package_dir = 
+	= src
+packages = find:
+include_package_data = true
+zip_safe = false
+
+[options.packages.find]
+where = src
+
+[options.package_data]
+metadata_utils = py.typed
+
+[options.extras_require]
+testing = 
+	pytest
+	mypy
+
+[flake8]
+exclude = .eggs/*, .pytest_cache/*, .tox/*, build/*, dist/*
+application_import_names = metadata_utils
+import_order_style = appnexus
+
+[tox:tox]
+envlist = py36, py37, py38, py39, py310, py311, py312, py313, py314, py315, mypy
+isolated_build = true
+
+[testenv]
+package = wheel
+deps = 
+	pytest
+	coverage
+setenv = 
+	COVERAGE_FILE = {envtmpdir}{/}.coverage
+commands = 
+	python -m coverage run --source=metadata_utils -m pytest {posargs}
+	python -m coverage html -d htmlcov/{envname}
+
+[testenv:mypy]
+basepython = python3.14
+deps = mypy
+commands = python -m mypy src tests
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

{metadata_utils-0.2.0 → metadata_utils-1.0.0}/src/metadata_utils/__init__.py

@@ -1,8 +1,10 @@
 # stdlib
 import unicodedata
-from xml.sax.saxutils import escape, unescape
+from typing import Dict
+from xml.sax.saxutils import escape
+from xml.sax.saxutils import unescape
 
-__VERSION__ = "0.2.0"
+__VERSION__ = "1.0.0"
 
 
 # ==============================================================================
@@ -11,23 +13,27 @@ __VERSION__ = "0.2.0"
 # https://wiki.python.org/moin/EscapingHtml
 # escape() and unescape() takes care of "&" , "<" and ">"
 # we need to handle quotes, so we don't break things
-html_attribute_escape_table: dict = {'"': "&quot;", "'": "&apos;"}
-html_attribute_unescape_table: dict = {
+html_attribute_escape_table: Dict[str, str] = {'"': "&quot;", "'": "&apos;"}
+html_attribute_unescape_table: Dict[str, str] = {
     v: k for (k, v) in html_attribute_escape_table.items()
 }
 
 
 def html_attribute_escape(text: str) -> str:
+    """Escape text for insertion into a quoted HTML attribute."""
     return escape(text, html_attribute_escape_table)
 
 
 def html_attribute_unescape(text: str) -> str:
+    """Decode the five named entities emitted by html_attribute_escape."""
     return unescape(text, html_attribute_unescape_table)
 
 
 def force_clean_ascii_NFKD(text: str) -> bytes:
+    """Apply NFKD, then return ASCII bytes, dropping non-ASCII characters."""
     return unicodedata.normalize("NFKD", text).encode("ascii", "ignore")
 
 
 def force_clean_ascii_NFKC(text: str) -> bytes:
+    """Apply NFKC, then return ASCII bytes, dropping non-ASCII characters."""
     return unicodedata.normalize("NFKC", text).encode("ascii", "ignore")

metadata_utils-1.0.0/src/metadata_utils.egg-info/PKG-INFO

@@ -0,0 +1,69 @@
+Metadata-Version: 2.4
+Name: metadata_utils
+Version: 1.0.0
+Summary: Lightweight Metadata Support
+Home-page: https://github.com/jvanasco/metadata_utils
+Author: Jonathan Vanasco
+Author-email: jvanasco@2xlp.com
+License: MIT
+Keywords: web
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: testing
+Requires-Dist: pytest; extra == "testing"
+Requires-Dist: mypy; extra == "testing"
+Dynamic: license-file
+
+![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
+
+metadata_utils
+==============
+
+This package offers lightweight tools for dealing with metadata in HTML.
+
+## Quoted HTML attributes
+
+Use `html_attribute_escape` on text before inserting it into a quoted HTML
+attribute.
+
+```python
+from metadata_utils import html_attribute_escape, html_attribute_unescape
+
+title = 'Fish & "Chips"'
+escaped = html_attribute_escape(title)
+assert f'<span title="{escaped}"></span>' == (
+    '<span title="Fish &amp; &quot;Chips&quot;"></span>'
+)
+assert html_attribute_unescape(escaped) == title
+```
+
+`html_attribute_unescape` decodes one layer of the five named entities emitted
+by the escape function (`&amp;`, `&lt;`, `&gt;`, `&quot;`, and `&apos;`).
+Other named and numeric references pass through unchanged.
+
+## ASCII normalization
+
+Both helpers apply Unicode normalization, drop any remaining non-ASCII
+characters, and return `bytes`. Both expand the `fi` ligature into `fi`.
+NFKD decomposes `é` so the ASCII `e` survives. NFKC keeps the composed
+`é`, which is dropped during ASCII encoding.
+
+```python
+from metadata_utils import force_clean_ascii_NFKC, force_clean_ascii_NFKD
+
+assert force_clean_ascii_NFKD("fi café") == b"fi cafe"
+assert force_clean_ascii_NFKC("fi café") == b"fi caf"
+```

{metadata_utils-0.2.0 → metadata_utils-1.0.0}/src/metadata_utils.egg-info/SOURCES.txt

@@ -4,9 +4,8 @@ MANIFEST.in
 README.md
 pyproject.toml
 setup.cfg
-setup.py
-tox.ini
 src/metadata_utils/__init__.py
+src/metadata_utils/py.typed
 src/metadata_utils.egg-info/PKG-INFO
 src/metadata_utils.egg-info/SOURCES.txt
 src/metadata_utils.egg-info/dependency_links.txt

{metadata_utils-0.2.0 → metadata_utils-1.0.0}/src/metadata_utils.egg-info/requires.txt

@@ -1,3 +1,4 @@
 
 [testing]
 pytest
+mypy

{metadata_utils-0.2.0 → metadata_utils-1.0.0}/tests/test_core.py

@@ -1,6 +1,8 @@
+# stdlib
 import unittest
-import metadata_utils
 
+# local
+import metadata_utils
 
 # ==============================================================================
 
@@ -10,37 +12,47 @@ class TestEscaping(unittest.TestCase):
     text_escaped = "foo "' bar"
     text_escaped_twice = "foo "' bar"
 
-    def test_escape(self):
+    def test_escape(self) -> None:
         escaped = metadata_utils.html_attribute_escape(self.text_raw)
         self.assertEqual(escaped, self.text_escaped)
 
-    def test_escape_twice(self):
+    def test_escape_twice(self) -> None:
         # we don't parse we, just escape, so this will change
         escaped_twice = metadata_utils.html_attribute_escape(self.text_escaped)
         self.assertEqual(escaped_twice, self.text_escaped_twice)
 
-    def test_unescape(self):
+    def test_unescape(self) -> None:
         unescaped = metadata_utils.html_attribute_unescape(self.text_escaped)
         self.assertEqual(unescaped, self.text_raw)
 
-    def test_roundtrip(self):
+    def test_roundtrip(self) -> None:
         escaped = metadata_utils.html_attribute_escape(self.text_raw)
         self.assertEqual(escaped, self.text_escaped)
         unescaped = metadata_utils.html_attribute_unescape(escaped)
         self.assertEqual(unescaped, self.text_raw)
 
+    def test_roundtrip_preserves_literal_entity(self) -> None:
+        escaped = metadata_utils.html_attribute_escape(""")
+        self.assertEqual(escaped, """)
+        self.assertEqual(metadata_utils.html_attribute_unescape(escaped), """)
+
 
 class TestCleanAscii(unittest.TestCase):
-    def test_NFKD(self):
+    def test_NFKD(self) -> None:
         text_unicode = "El Ni\xf1o"
         text_clean_a = "El Nino"  # downgrades
         escaped = metadata_utils.force_clean_ascii_NFKD(text_unicode)
         # py3 is a bytes
         self.assertEqual(escaped, text_clean_a.encode())
 
-    def test_NFKC(self):
+    def test_NFKC(self) -> None:
         text_unicode = "El Ni\xf1o"
         text_clean_a = "El Nio"  # strips
         escaped = metadata_utils.force_clean_ascii_NFKC(text_unicode)
         # py3 is a bytes
         self.assertEqual(escaped, text_clean_a.encode())
+
+    def test_compatibility_ligature(self) -> None:
+        text = "\ufb01 caf\xe9"
+        self.assertEqual(metadata_utils.force_clean_ascii_NFKD(text), b"fi cafe")
+        self.assertEqual(metadata_utils.force_clean_ascii_NFKC(text), b"fi caf")

metadata_utils-0.2.0/CHANGES.txt

@@ -1,27 +0,0 @@
-0.2.0
-    * typing support
-    * drop PY2
-    * drop PY3.5
-0.1.3
-	packaging fixes
-
-0.1.2
-	* black
-	* upgraded black; 20.8b1
-	* integrated with pre-commit
-	* tox and github actions
-
-0.1.1
-	* reverted aggressive 2to3 change
-
-0.1.0
-	* python 3 support
-	* tests
-
-0.0.2
-	* added `force_clean_ascii_NFKD`
-	* added `force_clean_ascii_NFKC`
-	* flake8
-
-0.0.1
-	* initial import

metadata_utils-0.2.0/PKG-INFO

@@ -1,37 +0,0 @@
-Metadata-Version: 2.1
-Name: metadata_utils
-Version: 0.2.0
-Summary: Lightweight Metadata Support
-Home-page: https://github.com/jvanasco/metadata_utils
-Author: Jonathan Vanasco
-Author-email: jonathan@findmeon.com
-License: MIT
-Keywords: web
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-Provides-Extra: testing
-License-File: LICENSE
-
-![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
-
-metadata_utils
-==============
-
-This package offers lightweight tools for dealing with metadata in HTML.
-
-The following functions are made available to streamline dealing with html encodings:
-
-* `html_attribute_escape`
-* `html_attribute_unescape`
-* `force_clean_ascii_NFKD`
-* `force_clean_ascii_NFKC`

metadata_utils-0.2.0/README.md

@@ -1,13 +0,0 @@
-![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
-
-metadata_utils
-==============
-
-This package offers lightweight tools for dealing with metadata in HTML.
-
-The following functions are made available to streamline dealing with html encodings:
-
-* `html_attribute_escape`
-* `html_attribute_unescape`
-* `force_clean_ascii_NFKD`
-* `force_clean_ascii_NFKC`

metadata_utils-0.2.0/pyproject.toml

@@ -1,3 +0,0 @@
-[tool.black]
-target-version = ['py38']
-

metadata_utils-0.2.0/setup.cfg

@@ -1,7 +0,0 @@
-[easy_install]
-zip_ok = false
-
-[egg_info]
-tag_build = 
-tag_date = 0
-

metadata_utils-0.2.0/setup.py

@@ -1,61 +0,0 @@
-"""metadata_utils installation script.
-"""
-import os
-import re
-from setuptools import setup
-from setuptools import find_packages
-
-HERE = os.path.abspath(os.path.dirname(__file__))
-
-long_description = description = "Lightweight Metadata Support"
-with open(os.path.join(HERE, "README.md")) as fp:
-    long_description = fp.read()
-
-# store version in the init.py
-with open(os.path.join(HERE, "src", "metadata_utils", "__init__.py")) as v_file:
-    VERSION = re.compile(r'.*__VERSION__ = "(.*?)"', re.S).match(v_file.read()).group(1)
-
-requires = []
-tests_require = [
-    "pytest",
-]
-testing_extras = tests_require + []
-
-setup(
-    name="metadata_utils",
-    description="Lightweight Metadata Support",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    version=VERSION,
-    url="https://github.com/jvanasco/metadata_utils",
-    author="Jonathan Vanasco",
-    author_email="jonathan@findmeon.com",
-    zip_safe=False,
-    python_requires=">=3.6",
-    keywords="web",
-    install_requires=requires,
-    tests_require=tests_require,
-    extras_require={
-        "testing": testing_extras,
-    },
-    test_suite="tests",
-    packages=find_packages(
-        where="src",
-    ),
-    package_dir={"": "src"},
-    package_data={"metadata_utils": ["py.typed"]},
-    include_package_data=True,
-    classifiers=[
-        "Intended Audience :: Developers",
-        "Programming Language :: Python",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.6",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-        "License :: OSI Approved :: MIT License",
-    ],
-    license="MIT",
-)

metadata_utils-0.2.0/src/metadata_utils.egg-info/PKG-INFO

@@ -1,37 +0,0 @@
-Metadata-Version: 2.1
-Name: metadata-utils
-Version: 0.2.0
-Summary: Lightweight Metadata Support
-Home-page: https://github.com/jvanasco/metadata_utils
-Author: Jonathan Vanasco
-Author-email: jonathan@findmeon.com
-License: MIT
-Keywords: web
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-Provides-Extra: testing
-License-File: LICENSE
-
-![Python package](https://github.com/jvanasco/metadata_utils/workflows/Python%20package/badge.svg)
-
-metadata_utils
-==============
-
-This package offers lightweight tools for dealing with metadata in HTML.
-
-The following functions are made available to streamline dealing with html encodings:
-
-* `html_attribute_escape`
-* `html_attribute_unescape`
-* `force_clean_ascii_NFKD`
-* `force_clean_ascii_NFKC`

metadata_utils-0.2.0/tox.ini

@@ -1,12 +0,0 @@
-[tox]
-envlist =
-	lint,
-	mypy,
-	py36,py37,py38,py39,py310,py311
-
-[testenv]
-commands =
-    python --version
-    pytest {posargs:}
-extras =
-    testing