2024-06-02 15:14:25 +01:00
|
|
|
# typed: strict
|
2020-08-08 07:16:06 +05:30
|
|
|
# frozen_string_literal: true
|
|
|
|
|
2025-03-04 11:48:54 -08:00
|
|
|
require "livecheck/strategic"
|
|
|
|
|
2020-08-08 07:16:06 +05:30
|
|
|
module Homebrew
|
|
|
|
module Livecheck
|
|
|
|
module Strategy
|
2024-12-07 10:56:46 -05:00
|
|
|
# The {Pypi} strategy identifies the newest version of a PyPI package by
|
|
|
|
# checking the JSON API endpoint for the project and using the
|
|
|
|
# `info.version` field from the response.
|
2020-08-08 07:16:06 +05:30
|
|
|
#
|
2024-12-07 01:15:40 -05:00
|
|
|
# PyPI URLs have a standard format:
|
2024-12-07 10:56:46 -05:00
|
|
|
# `https://files.pythonhosted.org/packages/<hex>/<hex>/<long_hex>/example-1.2.3.tar.gz`
|
2020-11-05 17:17:03 -05:00
|
|
|
#
|
2024-12-07 10:56:46 -05:00
|
|
|
# Upstream documentation for the PyPI JSON API can be found at:
|
|
|
|
# https://docs.pypi.org/api/json/#get-a-project
|
2020-08-08 07:16:06 +05:30
|
|
|
#
|
|
|
|
# @api public
|
|
|
|
class Pypi
|
2025-02-22 21:51:41 -08:00
|
|
|
extend Strategic
|
|
|
|
|
2020-08-08 07:16:06 +05:30
|
|
|
NICE_NAME = "PyPI"
|
|
|
|
|
2024-12-07 10:56:46 -05:00
|
|
|
# The default `strategy` block used to extract version information when
|
|
|
|
# a `strategy` block isn't provided.
|
2024-12-08 12:47:50 -05:00
|
|
|
DEFAULT_BLOCK = T.let(proc do |json, regex|
|
|
|
|
version = json.dig("info", "version")
|
|
|
|
next if version.blank?
|
|
|
|
|
|
|
|
regex ? version[regex, 1] : version
|
2024-12-07 10:56:46 -05:00
|
|
|
end.freeze, T.proc.params(
|
2025-02-22 21:51:41 -08:00
|
|
|
json: T::Hash[String, T.anything],
|
2024-12-08 12:47:50 -05:00
|
|
|
regex: T.nilable(Regexp),
|
2024-12-07 10:56:46 -05:00
|
|
|
).returns(T.nilable(String)))
|
|
|
|
|
2023-09-08 14:46:15 -04:00
|
|
|
# The `Regexp` used to extract the package name and suffix (e.g. file
|
2020-12-21 00:48:31 -05:00
|
|
|
# extension) from the URL basename.
|
|
|
|
FILENAME_REGEX = /
|
|
|
|
(?<package_name>.+)- # The package name followed by a hyphen
|
|
|
|
.*? # The version string
|
|
|
|
(?<suffix>\.tar\.[a-z0-9]+|\.[a-z0-9]+)$ # Filename extension
|
2024-01-18 22:18:42 +00:00
|
|
|
/ix
|
2020-12-21 00:48:31 -05:00
|
|
|
|
2020-08-08 07:16:06 +05:30
|
|
|
# The `Regexp` used to determine if the strategy applies to the URL.
|
2020-12-21 00:48:31 -05:00
|
|
|
URL_MATCH_REGEX = %r{
|
|
|
|
^https?://files\.pythonhosted\.org
|
|
|
|
/packages
|
|
|
|
(?:/[^/]+)+ # The hexadecimal paths before the filename
|
|
|
|
/#{FILENAME_REGEX.source.strip} # The filename
|
2024-01-18 22:18:42 +00:00
|
|
|
}ix
|
2020-08-08 07:16:06 +05:30
|
|
|
|
|
|
|
# Whether the strategy can be applied to the provided URL.
|
2020-11-05 17:17:03 -05:00
|
|
|
#
|
2020-08-08 07:16:06 +05:30
|
|
|
# @param url [String] the URL to match against
|
|
|
|
# @return [Boolean]
|
2025-02-22 21:51:41 -08:00
|
|
|
sig { override.params(url: String).returns(T::Boolean) }
|
2020-08-08 07:16:06 +05:30
|
|
|
def self.match?(url)
|
|
|
|
URL_MATCH_REGEX.match?(url)
|
|
|
|
end
|
|
|
|
|
2024-12-07 10:56:46 -05:00
|
|
|
# Extracts the package name from the provided URL and uses it to
|
|
|
|
# generate the PyPI JSON API URL for the project.
|
2021-07-28 13:20:12 -04:00
|
|
|
#
|
|
|
|
# @param url [String] the URL used to generate values
|
|
|
|
# @return [Hash]
|
|
|
|
sig { params(url: String).returns(T::Hash[Symbol, T.untyped]) }
|
|
|
|
def self.generate_input_values(url)
|
|
|
|
values = {}
|
|
|
|
|
|
|
|
match = File.basename(url).match(FILENAME_REGEX)
|
|
|
|
return values if match.blank?
|
|
|
|
|
2024-12-07 10:56:46 -05:00
|
|
|
values[:url] = "https://pypi.org/pypi/#{T.must(match[:package_name]).gsub(/%20|_/, "-")}/json"
|
2021-07-28 13:20:12 -04:00
|
|
|
|
|
|
|
values
|
|
|
|
end
|
|
|
|
|
2024-12-07 10:56:46 -05:00
|
|
|
# Generates a PyPI JSON API URL for the project and identifies new
|
|
|
|
# versions using {Json#find_versions} with a block.
|
2020-11-05 17:17:03 -05:00
|
|
|
#
|
2020-08-08 07:16:06 +05:30
|
|
|
# @param url [String] the URL of the content to check
|
2024-12-07 10:56:46 -05:00
|
|
|
# @param regex [Regexp] a regex used for matching versions in content
|
|
|
|
# @param provided_content [String, nil] content to check instead of
|
|
|
|
# fetching
|
livecheck: Add Options class
This adds a `Livecheck::Options` class, which is intended to house
various configuration options that are set in `livecheck` blocks,
conditionally set by livecheck at runtime, etc. The general idea is
that when we add features involving configurations options (e.g., for
livecheck, strategies, curl, etc.), we can make changes to `Options`
without needing to modify parameters for strategy `find_versions`
methods, `Strategy` methods like `page_headers` and `page_content`,
etc. This is something that I've been trying to improve over the years
and `Options` should help to reduce maintenance overhead in this area
while also strengthening type signatures.
`Options` replaces the existing `homebrew_curl` option (which related
strategies pass to `Strategy` methods and on to `curl_args`) and the
new `url_options` (which contains `post_form` or `post_json` values
that are used to make `POST` requests). I recently added `url_options`
as a temporary way of enabling `POST` support without `Options` but
this restores the original `Options`-based implementation.
Along the way, I added a `homebrew_curl` parameter to the `url` DSL
method, allowing us to set an explicit value in `livecheck` blocks.
This is something that we've needed in some cases but I also intend
to replace implicit/inferred `homebrew_curl` usage with explicit
values in `livecheck` blocks once this is available for use. My
intention is to eventually remove the implicit behavior and only rely
on explicit values. That will align with how `homebrew_curl` options
work for other URLs and makes the behavior clear just from looking at
the `livecheck` block.
Lastly, this removes the `unused` rest parameter from `find_versions`
methods. I originally added `unused` as a way of handling parameters
that some `find_versions` methods have but others don't (e.g., `cask`
in `ExtractPlist`), as this allowed us to pass various arguments to
`find_versions` methods without worrying about whether a particular
parameter is available. This isn't an ideal solution and I originally
wanted to handle this situation by only passing expected arguments to
`find_versions` methods but there was a technical issue standing in
the way. I recently found an answer to the issue, so this also
replaces the existing `ExtractPlist` special case with generic logic
that checks the parameters for a strategy's `find_versions` method
and only passes expected arguments.
Replacing the aforementioned `find_versions` parameters with `Options`
ensures that the remaining parameters are fairly consistent across
strategies and any differences are handled by the aforementioned
logic. Outside of `ExtractPlist`, the only other difference is that
some `find_versions` methods have a `provided_content` parameter but
that's currently only used by tests (though it's intended for caching
support in the future). I will be renaming that parameter to `content`
in an upcoming PR and expanding it to the other strategies, which
should make them all consistent outside of `ExtractPlist`.
2025-02-11 18:04:38 -05:00
|
|
|
# @param options [Options] options to modify behavior
|
2020-08-08 07:16:06 +05:30
|
|
|
# @return [Hash]
|
2021-04-04 03:00:34 +02:00
|
|
|
sig {
|
2025-02-22 21:51:41 -08:00
|
|
|
override.params(
|
2024-12-07 10:56:46 -05:00
|
|
|
url: String,
|
|
|
|
regex: T.nilable(Regexp),
|
|
|
|
provided_content: T.nilable(String),
|
livecheck: Add Options class
This adds a `Livecheck::Options` class, which is intended to house
various configuration options that are set in `livecheck` blocks,
conditionally set by livecheck at runtime, etc. The general idea is
that when we add features involving configurations options (e.g., for
livecheck, strategies, curl, etc.), we can make changes to `Options`
without needing to modify parameters for strategy `find_versions`
methods, `Strategy` methods like `page_headers` and `page_content`,
etc. This is something that I've been trying to improve over the years
and `Options` should help to reduce maintenance overhead in this area
while also strengthening type signatures.
`Options` replaces the existing `homebrew_curl` option (which related
strategies pass to `Strategy` methods and on to `curl_args`) and the
new `url_options` (which contains `post_form` or `post_json` values
that are used to make `POST` requests). I recently added `url_options`
as a temporary way of enabling `POST` support without `Options` but
this restores the original `Options`-based implementation.
Along the way, I added a `homebrew_curl` parameter to the `url` DSL
method, allowing us to set an explicit value in `livecheck` blocks.
This is something that we've needed in some cases but I also intend
to replace implicit/inferred `homebrew_curl` usage with explicit
values in `livecheck` blocks once this is available for use. My
intention is to eventually remove the implicit behavior and only rely
on explicit values. That will align with how `homebrew_curl` options
work for other URLs and makes the behavior clear just from looking at
the `livecheck` block.
Lastly, this removes the `unused` rest parameter from `find_versions`
methods. I originally added `unused` as a way of handling parameters
that some `find_versions` methods have but others don't (e.g., `cask`
in `ExtractPlist`), as this allowed us to pass various arguments to
`find_versions` methods without worrying about whether a particular
parameter is available. This isn't an ideal solution and I originally
wanted to handle this situation by only passing expected arguments to
`find_versions` methods but there was a technical issue standing in
the way. I recently found an answer to the issue, so this also
replaces the existing `ExtractPlist` special case with generic logic
that checks the parameters for a strategy's `find_versions` method
and only passes expected arguments.
Replacing the aforementioned `find_versions` parameters with `Options`
ensures that the remaining parameters are fairly consistent across
strategies and any differences are handled by the aforementioned
logic. Outside of `ExtractPlist`, the only other difference is that
some `find_versions` methods have a `provided_content` parameter but
that's currently only used by tests (though it's intended for caching
support in the future). I will be renaming that parameter to `content`
in an upcoming PR and expanding it to the other strategies, which
should make them all consistent outside of `ExtractPlist`.
2025-02-11 18:04:38 -05:00
|
|
|
options: Options,
|
2024-12-07 10:56:46 -05:00
|
|
|
block: T.nilable(Proc),
|
2025-02-22 21:51:41 -08:00
|
|
|
).returns(T::Hash[Symbol, T.anything])
|
2021-04-04 03:00:34 +02:00
|
|
|
}
|
livecheck: Add Options class
This adds a `Livecheck::Options` class, which is intended to house
various configuration options that are set in `livecheck` blocks,
conditionally set by livecheck at runtime, etc. The general idea is
that when we add features involving configurations options (e.g., for
livecheck, strategies, curl, etc.), we can make changes to `Options`
without needing to modify parameters for strategy `find_versions`
methods, `Strategy` methods like `page_headers` and `page_content`,
etc. This is something that I've been trying to improve over the years
and `Options` should help to reduce maintenance overhead in this area
while also strengthening type signatures.
`Options` replaces the existing `homebrew_curl` option (which related
strategies pass to `Strategy` methods and on to `curl_args`) and the
new `url_options` (which contains `post_form` or `post_json` values
that are used to make `POST` requests). I recently added `url_options`
as a temporary way of enabling `POST` support without `Options` but
this restores the original `Options`-based implementation.
Along the way, I added a `homebrew_curl` parameter to the `url` DSL
method, allowing us to set an explicit value in `livecheck` blocks.
This is something that we've needed in some cases but I also intend
to replace implicit/inferred `homebrew_curl` usage with explicit
values in `livecheck` blocks once this is available for use. My
intention is to eventually remove the implicit behavior and only rely
on explicit values. That will align with how `homebrew_curl` options
work for other URLs and makes the behavior clear just from looking at
the `livecheck` block.
Lastly, this removes the `unused` rest parameter from `find_versions`
methods. I originally added `unused` as a way of handling parameters
that some `find_versions` methods have but others don't (e.g., `cask`
in `ExtractPlist`), as this allowed us to pass various arguments to
`find_versions` methods without worrying about whether a particular
parameter is available. This isn't an ideal solution and I originally
wanted to handle this situation by only passing expected arguments to
`find_versions` methods but there was a technical issue standing in
the way. I recently found an answer to the issue, so this also
replaces the existing `ExtractPlist` special case with generic logic
that checks the parameters for a strategy's `find_versions` method
and only passes expected arguments.
Replacing the aforementioned `find_versions` parameters with `Options`
ensures that the remaining parameters are fairly consistent across
strategies and any differences are handled by the aforementioned
logic. Outside of `ExtractPlist`, the only other difference is that
some `find_versions` methods have a `provided_content` parameter but
that's currently only used by tests (though it's intended for caching
support in the future). I will be renaming that parameter to `content`
in an upcoming PR and expanding it to the other strategies, which
should make them all consistent outside of `ExtractPlist`.
2025-02-11 18:04:38 -05:00
|
|
|
def self.find_versions(url:, regex: nil, provided_content: nil, options: Options.new, &block)
|
2024-12-07 01:15:40 -05:00
|
|
|
match_data = { matches: {}, regex:, url: }
|
|
|
|
|
2021-07-28 13:20:12 -04:00
|
|
|
generated = generate_input_values(url)
|
2024-12-07 01:15:40 -05:00
|
|
|
return match_data if generated.blank?
|
|
|
|
|
2024-12-07 10:56:46 -05:00
|
|
|
Json.find_versions(
|
|
|
|
url: generated[:url],
|
|
|
|
regex:,
|
|
|
|
provided_content:,
|
livecheck: Add Options class
This adds a `Livecheck::Options` class, which is intended to house
various configuration options that are set in `livecheck` blocks,
conditionally set by livecheck at runtime, etc. The general idea is
that when we add features involving configurations options (e.g., for
livecheck, strategies, curl, etc.), we can make changes to `Options`
without needing to modify parameters for strategy `find_versions`
methods, `Strategy` methods like `page_headers` and `page_content`,
etc. This is something that I've been trying to improve over the years
and `Options` should help to reduce maintenance overhead in this area
while also strengthening type signatures.
`Options` replaces the existing `homebrew_curl` option (which related
strategies pass to `Strategy` methods and on to `curl_args`) and the
new `url_options` (which contains `post_form` or `post_json` values
that are used to make `POST` requests). I recently added `url_options`
as a temporary way of enabling `POST` support without `Options` but
this restores the original `Options`-based implementation.
Along the way, I added a `homebrew_curl` parameter to the `url` DSL
method, allowing us to set an explicit value in `livecheck` blocks.
This is something that we've needed in some cases but I also intend
to replace implicit/inferred `homebrew_curl` usage with explicit
values in `livecheck` blocks once this is available for use. My
intention is to eventually remove the implicit behavior and only rely
on explicit values. That will align with how `homebrew_curl` options
work for other URLs and makes the behavior clear just from looking at
the `livecheck` block.
Lastly, this removes the `unused` rest parameter from `find_versions`
methods. I originally added `unused` as a way of handling parameters
that some `find_versions` methods have but others don't (e.g., `cask`
in `ExtractPlist`), as this allowed us to pass various arguments to
`find_versions` methods without worrying about whether a particular
parameter is available. This isn't an ideal solution and I originally
wanted to handle this situation by only passing expected arguments to
`find_versions` methods but there was a technical issue standing in
the way. I recently found an answer to the issue, so this also
replaces the existing `ExtractPlist` special case with generic logic
that checks the parameters for a strategy's `find_versions` method
and only passes expected arguments.
Replacing the aforementioned `find_versions` parameters with `Options`
ensures that the remaining parameters are fairly consistent across
strategies and any differences are handled by the aforementioned
logic. Outside of `ExtractPlist`, the only other difference is that
some `find_versions` methods have a `provided_content` parameter but
that's currently only used by tests (though it's intended for caching
support in the future). I will be renaming that parameter to `content`
in an upcoming PR and expanding it to the other strategies, which
should make them all consistent outside of `ExtractPlist`.
2025-02-11 18:04:38 -05:00
|
|
|
options:,
|
2024-12-07 10:56:46 -05:00
|
|
|
&block || DEFAULT_BLOCK
|
|
|
|
)
|
2020-08-08 07:16:06 +05:30
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|