mediaparse 0.2.0__tar.gz

mediaparse-0.2.0/.gitattributes

@@ -0,0 +1 @@
+* text=auto eol=lf

mediaparse-0.2.0/.github/FUNDING.yml

@@ -0,0 +1 @@
+buy_me_a_coffee: jlianesglrs

mediaparse-0.2.0/.gitignore

@@ -0,0 +1,16 @@
+__pycache__/
+*.py[cod]
+.venv/
+venv/
+build/
+dist/
+*.egg-info/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+
+# Third-party test files, fetched locally by scripts/fetch_upstream.py; only the manifest is tracked.
+tests/upstream/*
+!tests/upstream/MANIFEST.json

mediaparse-0.2.0/CHANGELOG.md

@@ -0,0 +1,49 @@
+# Changelog
+
+All notable changes to this project are documented here. The format follows
+[Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and the project uses
+[Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.2.0]
+
+### Added
+
+- `parse_media_type` and the frozen `MediaType` value: `essence`, the RFC 6838 `suffix`,
+  ordered `params`, `parameters`, `get()`, and `str()` with the WHATWG serialization.
+- `strict=True` on `parse`, `parse_media_type` and `normalize`: the RFC 9110 grammar
+  exactly, a repeated parameter is an error, and `MediaTypeError.position` points at the
+  first bad character.
+- `parse_accept`, `AcceptItem`, `quality` and `negotiate` for the Accept header (RFC 9110
+  sections 12.4.2 and 12.5.1), checked against the RFC examples.
+- `build(..., extended=True)` writes non-ASCII values as RFC 8187 / RFC 2231 extended
+  values, and `decode_extended` joins RFC 2231 continuations and decodes them.
+- Tests against the web-platform-tests MIME type corpus, fetched locally by
+  `scripts/fetch_upstream.py`, plus executed README examples, a typing check and an
+  installed-wheel test.
+
+### Changed
+
+- The default parser is the WHATWG MIME Sniffing algorithm: the first of a repeated
+  parameter wins (it was the last), a parameter with whitespace around `=` or a value
+  outside the quoted-string range is skipped, and HTTP whitespace (including CR and LF)
+  is trimmed.
+- Names are lower-cased in ASCII only.
+
+### Fixed
+
+- `build` no longer writes control characters such as CR and LF into a quoted value,
+  which let a parameter value split the header, nor characters a header cannot carry.
+  A duplicate name after lower-casing is refused instead of written twice.
+- Error messages show at most 80 characters of the input.
+
+## [0.1.0]
+
+- First release.
+- `parse` splits a Content-Type style header into a media type and its
+  parameters, unescaping quoted values and tolerating malformed input.
+- `build` renders a media type and parameters back, quoting only the values that
+  a token may not hold.
+- `normalize` and `matches` canonicalize and compare headers.
+- Fills the gap left by `cgi.parse_header`, removed in Python 3.13.

mediaparse-0.2.0/CONTRIBUTING.md

@@ -0,0 +1,23 @@
+# Contributing
+
+Thanks for taking the time. This project keeps a small, predictable shape.
+
+## Setup
+
+```
+pip install -r requirements-dev.txt
+```
+
+## Before you open a pull request
+
+- Keep public API in `src/mediaparse/__init__.py`; internals live in `_`-prefixed modules.
+- Add a test for the behaviour you change. Tests inject time, disk and network; they
+  never touch the real thing.
+- Run `python scripts/fetch_upstream.py` once: it downloads the web-platform-tests MIME
+  type files listed in `tests/upstream/MANIFEST.json`, which are not committed. Their
+  tests skip without them.
+- Run `scripts/check.ps1` (format, lint, types, tests) and make sure it passes. Set
+  `MEDIAPARSE_E2E=1` to also build the wheel and test the installed package.
+- One logical change per commit, imperative subject line.
+
+Open an issue first if the change is large or shifts the public API.

mediaparse-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Javier Lianes
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

mediaparse-0.2.0/PKG-INFO

@@ -0,0 +1,214 @@
+Metadata-Version: 2.5
+Name: mediaparse
+Version: 0.2.0
+Summary: Parse and build HTTP media types, Content-Type and Accept headers, exactly
+Project-URL: Homepage, https://lianes8studio.com
+Project-URL: Repository, https://github.com/JaviLianes8/mediaparse
+Project-URL: Issues, https://github.com/JaviLianes8/mediaparse/issues
+Project-URL: Changelog, https://github.com/JaviLianes8/mediaparse/blob/main/CHANGELOG.md
+Project-URL: LinkedIn, https://www.linkedin.com/in/jlianes/
+Project-URL: Funding, https://buymeacoffee.com/jlianesglrs
+Author-email: Javier Lianes <javier@lianes8studio.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: accept,cgi,content-negotiation,content-type,header,http,media-type,mime,rfc2231,rfc9110,whatwg
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+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: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Requires-Dist: twine; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# mediaparse
+
+Parse and build HTTP media types, `Content-Type` and `Accept` headers, exactly.
+
+## Install
+
+```
+pip install mediaparse
+```
+
+## Usage
+
+```python
+from mediaparse import build, matches, normalize, parse, parse_media_type
+
+# Read a Content-Type value the way a browser does.
+print(parse("text/html; charset=utf-8"))
+# ('text/html', {'charset': 'utf-8'})
+
+# Quoted values keep separators; text after the closing quote is skipped.
+print(parse('multipart/form-data; boundary="a; b=c"'))
+# ('multipart/form-data', {'boundary': 'a; b=c'})
+
+# A typed value with the essence, the +suffix and the browser serialization.
+media = parse_media_type("Application/Vnd.API+JSON; Charset=UTF-8")
+print(media.essence, media.suffix, media.get("charset"))
+# application/vnd.api+json json UTF-8
+print(media)
+# application/vnd.api+json;charset=UTF-8
+
+# Build a header, quoting only the values that need it.
+print(build("application/json", {"title": "a; b"}))
+# application/json; title="a; b"
+
+# Canonical form for display or comparison.
+print(normalize("TEXT/HTML; CharSet=UTF-8"))
+# text/html; charset=utf-8
+print(matches("Text/HTML; charset=UTF-8", "text/html;charset=utf-8"))
+# True
+```
+
+### Lenient or strict
+
+```python
+from mediaparse import MediaTypeError, parse
+
+# Default: the WHATWG algorithm. The first of a repeated parameter wins and a parameter
+# with whitespace before "=" is skipped, exactly as browsers do.
+print(parse("text/plain; charset=ascii; charset=utf-8; a =1"))
+# ('text/plain', {'charset': 'ascii'})
+
+# strict=True: the RFC 9110 grammar, with the position of the first bad character.
+try:
+    parse("text/plain; a =1", strict=True)
+except MediaTypeError as error:
+    print(error.position)
+# 13
+```
+
+### Building safely
+
+```python
+from mediaparse import MediaTypeError, build
+
+# No value can split the header: control characters are refused.
+try:
+    build("text/plain", {"name": "x\r\nSet-Cookie: a=b"})
+except MediaTypeError:
+    print("refused")
+# refused
+
+# Non-ASCII values travel as RFC 8187 / RFC 2231 extended values on request.
+print(build("text/plain", {"title": "caf\xe9"}, extended=True))
+# text/plain; title*=UTF-8''caf%C3%A9
+```
+
+### Accept and negotiation
+
+```python
+from mediaparse import negotiate, parse_accept, quality
+
+accept = "text/*;q=0.3, text/plain;q=0.7, text/plain;format=flowed, */*;q=0.5"
+
+# The weight comes from the most specific range that covers the offer.
+print(quality(accept, "text/plain;format=flowed"), quality(accept, "text/html"))
+# 1.0 0.3
+
+# Pick the best offer; ties go to the order you list them in.
+print(negotiate(accept, ["image/png", "text/html"]))
+# image/png
+
+print([(str(item.media_range), item.q) for item in parse_accept("text/html, */*;q=0.1")])
+# [('text/html', 1.0), ('*/*', 0.1)]
+```
+
+### RFC 2231 parameters
+
+```python
+from mediaparse import decode_extended, parse
+
+header = "application/x-stuff; title*0*=utf-8''r%C3%A9sum; title*1=\"e.pdf\""
+print(decode_extended(parse(header)[1]))
+# {'title': 'résume.pdf'}
+```
+
+## API
+
+| Name | What it does |
+| --- | --- |
+| `parse(header, *, strict=False)` | `(essence, params)` tuple. |
+| `parse_media_type(text, *, strict=False)` | A `MediaType`; raises `MediaTypeError` when there is no valid `type/subtype`. |
+| `MediaType` | Frozen value: `type`, `subtype`, `params` pairs, `essence`, `suffix`, `parameters`, `get()`, `str()`. |
+| `build(mimetype, params=None, *, extended=False)` | Header value with `"; "` between parts and minimal quoting. |
+| `normalize(header, *, strict=False)` | Lower-cased names, sorted parameters, lower-cased `charset`. |
+| `matches(first, second)` | Whether two headers normalize to the same text. |
+| `parse_accept(header, *, strict=False)` | List of `AcceptItem` in header order. |
+| `AcceptItem` | `media_range` (a `MediaType`), `q` (0 to 1), `specificity()`, `matches(media)`. |
+| `quality(accept, offer)` | Weight of an offer under an Accept header; `None` means no header. |
+| `negotiate(accept, offers)` | Best acceptable offer, returned as given, or `None`. |
+| `decode_extended(params)` | Joins RFC 2231 sections and decodes `charset'lang'` values. |
+| `MediaTypeError` | `ValueError` subclass with `position` (or `None`). Wrong argument types raise `TypeError`. |
+
+## Rules it follows
+
+- **Default parsing** is the WHATWG MIME Sniffing "parse a MIME type" algorithm, checked
+  against the web-platform-tests MIME type corpus. Whitespace (tab, LF, CR, space) is
+  trimmed, a parameter whose name is not a token or whose value has a character above
+  U+00FF or a control character is skipped, empty values are skipped and the first
+  duplicate wins. `str(MediaType)` is the WHATWG serialization.
+- **Strict parsing** is the RFC 9110 `media-type` grammar: no whitespace around `=`,
+  values are tokens or quoted strings with `qdtext` and `quoted-pair` only, and a repeated
+  parameter is an error (RFC 6838 section 4.3). Leading and trailing spaces or tabs are
+  allowed because a field parser removes them.
+- **Names** are lower-cased in ASCII only, so a character such as the Kelvin sign never
+  turns into a token. Values keep their case; `normalize` and `quality` treat `charset`
+  as case insensitive.
+- **Building** never writes a control character or a non-ASCII character into the
+  header: by default such a value raises, and with `extended=True` it is percent-encoded
+  as `name*=UTF-8''...` (names may not end in `*` then). Two parameters that would be
+  written under one name raise. The output is always one valid header field value.
+- **Accept**: elements split on commas outside quoted strings, empty elements are
+  ignored, `q` must match the `qvalue` grammar (up to three decimals, at most 1) and may
+  appear anywhere among the parameters. In the default mode an invalid element is
+  skipped, including one whose `q` is malformed (`q =0`, `q=`), so a broken weight never
+  counts as 1. In strict mode only spaces and tabs may surround an element. A missing field (`None`) accepts everything; an empty one accepts nothing; a
+  weight of 0 means not acceptable. On equally specific ranges the earliest one counts.
+- **RFC 2231**: sections start at 0 without gaps or leading zeros, encoded and plain
+  sections may mix, a character may span sections, and `name*` wins over `name`. The
+  language tag is dropped. Names compare in ASCII lower case. The charset must be a
+  charset name Python can decode as text; escape decoders, host code pages (`mbcs`,
+  `oem`), `idna` and `punycode` are refused.
+
+## Why
+
+Python 3.13 removed `cgi.parse_header` along with the rest of the `cgi` module. The
+documented replacement, the `email.message.Message` machinery, is parse-oriented with no
+clean builder and mishandles repeated parameters, so projects keep copying a parser by
+hand. `multipart.parse_options_header` is scoped to form data and parse-only, and
+`ietfparse` is a broad multi-RFC toolkit. `mediaparse` is a small, typed,
+zero-dependency library that parses the way browsers do, validates the way the RFC says,
+builds headers that cannot be split, and negotiates `Accept`.
+
+## Development
+
+`python scripts/fetch_upstream.py` downloads the web-platform-tests MIME type files listed
+in `tests/upstream/MANIFEST.json` (they are not part of the repository; their tests skip
+without them). `scripts/check.ps1` runs format, lint, types and tests. Set
+`MEDIAPARSE_E2E=1` to also build the wheel and test the installed package.
+
+## License
+
+MIT. See [LICENSE](LICENSE).
+
+## Links
+
+- Website: https://lianes8studio.com
+- GitHub: https://github.com/JaviLianes8
+- LinkedIn: https://www.linkedin.com/in/jlianes/

mediaparse-0.2.0/README.md

@@ -0,0 +1,178 @@
+# mediaparse
+
+Parse and build HTTP media types, `Content-Type` and `Accept` headers, exactly.
+
+## Install
+
+```
+pip install mediaparse
+```
+
+## Usage
+
+```python
+from mediaparse import build, matches, normalize, parse, parse_media_type
+
+# Read a Content-Type value the way a browser does.
+print(parse("text/html; charset=utf-8"))
+# ('text/html', {'charset': 'utf-8'})
+
+# Quoted values keep separators; text after the closing quote is skipped.
+print(parse('multipart/form-data; boundary="a; b=c"'))
+# ('multipart/form-data', {'boundary': 'a; b=c'})
+
+# A typed value with the essence, the +suffix and the browser serialization.
+media = parse_media_type("Application/Vnd.API+JSON; Charset=UTF-8")
+print(media.essence, media.suffix, media.get("charset"))
+# application/vnd.api+json json UTF-8
+print(media)
+# application/vnd.api+json;charset=UTF-8
+
+# Build a header, quoting only the values that need it.
+print(build("application/json", {"title": "a; b"}))
+# application/json; title="a; b"
+
+# Canonical form for display or comparison.
+print(normalize("TEXT/HTML; CharSet=UTF-8"))
+# text/html; charset=utf-8
+print(matches("Text/HTML; charset=UTF-8", "text/html;charset=utf-8"))
+# True
+```
+
+### Lenient or strict
+
+```python
+from mediaparse import MediaTypeError, parse
+
+# Default: the WHATWG algorithm. The first of a repeated parameter wins and a parameter
+# with whitespace before "=" is skipped, exactly as browsers do.
+print(parse("text/plain; charset=ascii; charset=utf-8; a =1"))
+# ('text/plain', {'charset': 'ascii'})
+
+# strict=True: the RFC 9110 grammar, with the position of the first bad character.
+try:
+    parse("text/plain; a =1", strict=True)
+except MediaTypeError as error:
+    print(error.position)
+# 13
+```
+
+### Building safely
+
+```python
+from mediaparse import MediaTypeError, build
+
+# No value can split the header: control characters are refused.
+try:
+    build("text/plain", {"name": "x\r\nSet-Cookie: a=b"})
+except MediaTypeError:
+    print("refused")
+# refused
+
+# Non-ASCII values travel as RFC 8187 / RFC 2231 extended values on request.
+print(build("text/plain", {"title": "caf\xe9"}, extended=True))
+# text/plain; title*=UTF-8''caf%C3%A9
+```
+
+### Accept and negotiation
+
+```python
+from mediaparse import negotiate, parse_accept, quality
+
+accept = "text/*;q=0.3, text/plain;q=0.7, text/plain;format=flowed, */*;q=0.5"
+
+# The weight comes from the most specific range that covers the offer.
+print(quality(accept, "text/plain;format=flowed"), quality(accept, "text/html"))
+# 1.0 0.3
+
+# Pick the best offer; ties go to the order you list them in.
+print(negotiate(accept, ["image/png", "text/html"]))
+# image/png
+
+print([(str(item.media_range), item.q) for item in parse_accept("text/html, */*;q=0.1")])
+# [('text/html', 1.0), ('*/*', 0.1)]
+```
+
+### RFC 2231 parameters
+
+```python
+from mediaparse import decode_extended, parse
+
+header = "application/x-stuff; title*0*=utf-8''r%C3%A9sum; title*1=\"e.pdf\""
+print(decode_extended(parse(header)[1]))
+# {'title': 'résume.pdf'}
+```
+
+## API
+
+| Name | What it does |
+| --- | --- |
+| `parse(header, *, strict=False)` | `(essence, params)` tuple. |
+| `parse_media_type(text, *, strict=False)` | A `MediaType`; raises `MediaTypeError` when there is no valid `type/subtype`. |
+| `MediaType` | Frozen value: `type`, `subtype`, `params` pairs, `essence`, `suffix`, `parameters`, `get()`, `str()`. |
+| `build(mimetype, params=None, *, extended=False)` | Header value with `"; "` between parts and minimal quoting. |
+| `normalize(header, *, strict=False)` | Lower-cased names, sorted parameters, lower-cased `charset`. |
+| `matches(first, second)` | Whether two headers normalize to the same text. |
+| `parse_accept(header, *, strict=False)` | List of `AcceptItem` in header order. |
+| `AcceptItem` | `media_range` (a `MediaType`), `q` (0 to 1), `specificity()`, `matches(media)`. |
+| `quality(accept, offer)` | Weight of an offer under an Accept header; `None` means no header. |
+| `negotiate(accept, offers)` | Best acceptable offer, returned as given, or `None`. |
+| `decode_extended(params)` | Joins RFC 2231 sections and decodes `charset'lang'` values. |
+| `MediaTypeError` | `ValueError` subclass with `position` (or `None`). Wrong argument types raise `TypeError`. |
+
+## Rules it follows
+
+- **Default parsing** is the WHATWG MIME Sniffing "parse a MIME type" algorithm, checked
+  against the web-platform-tests MIME type corpus. Whitespace (tab, LF, CR, space) is
+  trimmed, a parameter whose name is not a token or whose value has a character above
+  U+00FF or a control character is skipped, empty values are skipped and the first
+  duplicate wins. `str(MediaType)` is the WHATWG serialization.
+- **Strict parsing** is the RFC 9110 `media-type` grammar: no whitespace around `=`,
+  values are tokens or quoted strings with `qdtext` and `quoted-pair` only, and a repeated
+  parameter is an error (RFC 6838 section 4.3). Leading and trailing spaces or tabs are
+  allowed because a field parser removes them.
+- **Names** are lower-cased in ASCII only, so a character such as the Kelvin sign never
+  turns into a token. Values keep their case; `normalize` and `quality` treat `charset`
+  as case insensitive.
+- **Building** never writes a control character or a non-ASCII character into the
+  header: by default such a value raises, and with `extended=True` it is percent-encoded
+  as `name*=UTF-8''...` (names may not end in `*` then). Two parameters that would be
+  written under one name raise. The output is always one valid header field value.
+- **Accept**: elements split on commas outside quoted strings, empty elements are
+  ignored, `q` must match the `qvalue` grammar (up to three decimals, at most 1) and may
+  appear anywhere among the parameters. In the default mode an invalid element is
+  skipped, including one whose `q` is malformed (`q =0`, `q=`), so a broken weight never
+  counts as 1. In strict mode only spaces and tabs may surround an element. A missing field (`None`) accepts everything; an empty one accepts nothing; a
+  weight of 0 means not acceptable. On equally specific ranges the earliest one counts.
+- **RFC 2231**: sections start at 0 without gaps or leading zeros, encoded and plain
+  sections may mix, a character may span sections, and `name*` wins over `name`. The
+  language tag is dropped. Names compare in ASCII lower case. The charset must be a
+  charset name Python can decode as text; escape decoders, host code pages (`mbcs`,
+  `oem`), `idna` and `punycode` are refused.
+
+## Why
+
+Python 3.13 removed `cgi.parse_header` along with the rest of the `cgi` module. The
+documented replacement, the `email.message.Message` machinery, is parse-oriented with no
+clean builder and mishandles repeated parameters, so projects keep copying a parser by
+hand. `multipart.parse_options_header` is scoped to form data and parse-only, and
+`ietfparse` is a broad multi-RFC toolkit. `mediaparse` is a small, typed,
+zero-dependency library that parses the way browsers do, validates the way the RFC says,
+builds headers that cannot be split, and negotiates `Accept`.
+
+## Development
+
+`python scripts/fetch_upstream.py` downloads the web-platform-tests MIME type files listed
+in `tests/upstream/MANIFEST.json` (they are not part of the repository; their tests skip
+without them). `scripts/check.ps1` runs format, lint, types and tests. Set
+`MEDIAPARSE_E2E=1` to also build the wheel and test the installed package.
+
+## License
+
+MIT. See [LICENSE](LICENSE).
+
+## Links
+
+- Website: https://lianes8studio.com
+- GitHub: https://github.com/JaviLianes8
+- LinkedIn: https://www.linkedin.com/in/jlianes/

mediaparse-0.2.0/pyproject.toml

@@ -0,0 +1,64 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "mediaparse"
+version = "0.2.0"
+description = "Parse and build HTTP media types, Content-Type and Accept headers, exactly"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{ name = "Javier Lianes", email = "javier@lianes8studio.com" }]
+keywords = ["mime", "media-type", "content-type", "accept", "http", "header", "rfc9110", "whatwg", "rfc2231", "content-negotiation", "cgi"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "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",
+    "Topic :: Internet :: WWW/HTTP",
+    "Topic :: Software Development :: Libraries",
+    "Typing :: Typed",
+]
+dependencies = []
+
+[project.optional-dependencies]
+dev = ["ruff", "mypy", "pytest", "build", "twine"]
+
+[project.urls]
+Homepage = "https://lianes8studio.com"
+Repository = "https://github.com/JaviLianes8/mediaparse"
+Issues = "https://github.com/JaviLianes8/mediaparse/issues"
+Changelog = "https://github.com/JaviLianes8/mediaparse/blob/main/CHANGELOG.md"
+LinkedIn = "https://www.linkedin.com/in/jlianes/"
+Funding = "https://buymeacoffee.com/jlianesglrs"
+
+[tool.hatch.build.targets.sdist]
+# Third-party test files are fetched locally and never shipped; only their manifest is.
+exclude = ["IMPROVEMENTS-round*.md", "tests/upstream/wpt-*.json"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mediaparse"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "RUF"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-q"

mediaparse-0.2.0/requirements-dev.txt

@@ -0,0 +1,3 @@
+# Development dependencies: the package in editable mode plus its dev extras
+# (ruff, mypy, pytest, build, twine). Install with:  pip install -r requirements-dev.txt
+-e .[dev]

mediaparse-0.2.0/scripts/check.ps1

@@ -0,0 +1,16 @@
+# Local quality gate. Run before every commit. No CI runs in the cloud.
+# $ErrorActionPreference does NOT stop on a native command's non-zero exit, so each tool's
+# exit code is checked explicitly: a red gate must fail, never pass silently.
+$ErrorActionPreference = "Stop"
+
+function Invoke-Step($label, [scriptblock]$cmd) {
+    Write-Host "== $label =="
+    & $cmd
+    if ($LASTEXITCODE -ne 0) { Write-Host "FAILED: $label (exit $LASTEXITCODE)"; exit $LASTEXITCODE }
+}
+
+Invoke-Step "ruff format" { ruff format --check src tests }
+Invoke-Step "ruff lint"   { ruff check src tests }
+Invoke-Step "mypy"        { mypy src tests }
+Invoke-Step "pytest"      { pytest }
+Write-Host "gate green"

mediaparse-0.2.0/scripts/fetch_upstream.py

@@ -0,0 +1,37 @@
+"""Fetch the third-party test files listed in tests/upstream/MANIFEST.json.
+
+The files are not part of the repository. Their tests skip until this script has fetched
+them; each download is checked against the size and sha256 in the manifest.
+
+    python scripts/fetch_upstream.py
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import sys
+import urllib.request
+from pathlib import Path
+
+FOLDER = Path(__file__).resolve().parents[1] / "tests" / "upstream"
+
+
+def main() -> int:
+    manifest = json.loads((FOLDER / "MANIFEST.json").read_text(encoding="utf-8"))
+    failed = 0
+    for name, entry in manifest.items():
+        with urllib.request.urlopen(entry["url"], timeout=60) as response:
+            body = response.read()
+        digest = hashlib.sha256(body).hexdigest()
+        if len(body) != entry["size"] or digest != entry["sha256"]:
+            print(f"{name}: got {len(body)} bytes, sha256 {digest}; manifest differs")
+            failed += 1
+            continue
+        (FOLDER / name).write_bytes(body)
+        print(f"{name}: ok")
+    return 1 if failed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

mediaparse-0.2.0/scripts/release.ps1

@@ -0,0 +1,28 @@
+# Build and upload to PyPI. Run scripts/check.ps1 first.
+# The name must not already exist on PyPI; the token is read from a secret store, never git.
+$ErrorActionPreference = "Stop"
+
+# Works on both Windows PowerShell 5.1 and pwsh 7 (generic catch, no PS7-only types).
+$taken = $true
+try {
+    Invoke-WebRequest -UseBasicParsing "https://pypi.org/pypi/mediaparse/json" | Out-Null
+} catch {
+    if ($_.Exception.Response.StatusCode.value__ -eq 404) { $taken = $false } else { throw }
+}
+if ($taken) { throw "The name 'mediaparse' already exists on PyPI. Choose another before publishing." }
+
+$token = $env:PYPI_TOKEN
+if (-not $token -and (Test-Path "C:\secrets\pypi-token.txt")) {
+    $token = (Get-Content "C:\secrets\pypi-token.txt" -Raw).Trim()
+}
+if (-not $token) {
+    throw "No PyPI token. Set `$env:PYPI_TOKEN or save it to C:\secrets\pypi-token.txt (never commit it)."
+}
+
+Remove-Item -Recurse -Force dist -ErrorAction SilentlyContinue
+python -m build
+python -m twine check dist/*
+
+$env:TWINE_USERNAME = "__token__"
+$env:TWINE_PASSWORD = $token
+try { python -m twine upload dist/* } finally { Remove-Item Env:\TWINE_PASSWORD -ErrorAction SilentlyContinue }