Merge pull request #14845 from samford/livecheck/add-xml-strategy

livecheck: Add Xml strategy

Library/Homebrew/.rubocop.yml

@@ -52,6 +52,7 @@ Style/Documentation:
     - livecheck/strategy/pypi.rb
     - livecheck/strategy/sourceforge.rb
     - livecheck/strategy/sparkle.rb
+    - livecheck/strategy/xml.rb
     - livecheck/strategy/xorg.rb
     - os.rb
     - resource.rb

Library/Homebrew/livecheck/strategy.rb

@@ -156,7 +156,7 @@ module Homebrew
             # Only treat the strategy as usable if the `livecheck` block
             # contains a regex and/or `strategy` block
             next if !regex_provided && !block_provided
-          elsif strategy == Json
+          elsif [Json, Xml].include?(strategy)
             # Only treat the strategy as usable if the `livecheck` block
             # specifies the strategy and contains a `strategy` block
             next if (livecheck_strategy != strategy_symbol) || !block_provided
@@ -284,4 +284,5 @@ require_relative "strategy/page_match"
 require_relative "strategy/pypi"
 require_relative "strategy/sourceforge"
 require_relative "strategy/sparkle"
+require_relative "strategy/xml"
 require_relative "strategy/xorg"

Library/Homebrew/livecheck/strategy/sparkle.rb

@@ -66,25 +66,8 @@ module Homebrew
         # @return [Item, nil]
         sig { params(content: String).returns(T::Array[Item]) }
         def self.items_from_content(content)
-          require "rexml/document"
+          xml = Xml.parse_xml(content)
-
+          return [] if xml.blank?
-          parsing_tries = 0
-          xml = begin
-            REXML::Document.new(content)
-          rescue REXML::UndefinedNamespaceException => e
-            undefined_prefix = e.to_s[/Undefined prefix ([^ ]+) found/i, 1]
-            raise if undefined_prefix.blank?
-
-            # Only retry parsing once after removing prefix from content
-            parsing_tries += 1
-            raise if parsing_tries > 1
-
-            # When an XML document contains a prefix without a corresponding
-            # namespace, it's necessary to remove the prefix from the content
-            # to be able to successfully parse it using REXML
-            content = content.gsub(%r{(</?| )#{Regexp.escape(undefined_prefix)}:}, '\1')
-            retry
-          end
 
           # Remove prefixes, so we can reliably identify elements and attributes
           xml.root&.each_recursive do |node|

Library/Homebrew/livecheck/strategy/xml.rb

@@ -0,0 +1,153 @@
+# typed: true
+# frozen_string_literal: true
+
+module Homebrew
+  module Livecheck
+    module Strategy
+      # The {Xml} strategy fetches content at a URL, parses it as XML using
+      # `REXML`, and provides the `REXML::Document` to a `strategy` block.
+      # If a regex is present in the `livecheck` block, it should be passed
+      # as the second argument to the `strategy` block.
+      #
+      # This is a generic strategy that doesn't contain any logic for finding
+      # versions, as the structure of XML data varies. Instead, a `strategy`
+      # block must be used to extract version information from the XML data.
+      # For more information on how to work with an `REXML::Document` object,
+      # please refer to the [`REXML::Document`](https://ruby.github.io/rexml/REXML/Document.html)
+      # and [`REXML::Element`](https://ruby.github.io/rexml/REXML/Element.html)
+      # documentation.
+      #
+      # This strategy is not applied automatically and it is necessary to use
+      # `strategy :xml` in a `livecheck` block (in conjunction with a
+      # `strategy` block) to use it.
+      #
+      # This strategy's {find_versions} method can be used in other strategies
+      # that work with XML content, so it should only be necessary to write
+      # the version-finding logic that works with the parsed XML data.
+      #
+      # @api public
+      class Xml
+        extend T::Sig
+
+        NICE_NAME = "XML"
+
+        # A priority of zero causes livecheck to skip the strategy. We do this
+        # for {Xml} so we can selectively apply it only when a strategy block
+        # is provided in a `livecheck` block.
+        PRIORITY = 0
+
+        # The `Regexp` used to determine if the strategy applies to the URL.
+        URL_MATCH_REGEX = %r{^https?://}i.freeze
+
+        # Whether the strategy can be applied to the provided URL.
+        # {Xml} will technically match any HTTP URL but is only usable with
+        # a `livecheck` block containing a `strategy` block.
+        #
+        # @param url [String] the URL to match against
+        # @return [Boolean]
+        sig { params(url: String).returns(T::Boolean) }
+        def self.match?(url)
+          URL_MATCH_REGEX.match?(url)
+        end
+
+        # Parses XML text and returns an `REXML::Document` object.
+        # @param content [String] the XML text to parse
+        # @return [REXML::Document, nil]
+        sig { params(content: String).returns(T.nilable(REXML::Document)) }
+        def self.parse_xml(content)
+          require "rexml/document"
+
+          parsing_tries = 0
+          begin
+            REXML::Document.new(content)
+          rescue REXML::UndefinedNamespaceException => e
+            undefined_prefix = e.to_s[/Undefined prefix ([^ ]+) found/i, 1]
+            raise "Could not identify undefined prefix." if undefined_prefix.blank?
+
+            # Only retry parsing once after removing prefix from content
+            parsing_tries += 1
+            raise "Could not parse XML after removing undefined prefix." if parsing_tries > 1
+
+            # When an XML document contains a prefix without a corresponding
+            # namespace, it's necessary to remove the prefix from the content
+            # to be able to successfully parse it using REXML
+            content = content.gsub(%r{(</?| )#{Regexp.escape(undefined_prefix)}:}, '\1')
+            retry
+          end
+        end
+
+        # Parses XML text and identifies versions using a `strategy` block.
+        # If a regex is provided, it will be passed as the second argument to
+        # the  `strategy` block (after the parsed XML data).
+        # @param content [String] the XML text to parse and check
+        # @param regex [Regexp, nil] a regex used for matching versions in the
+        #   content
+        # @return [Array]
+        sig {
+          params(
+            content: String,
+            regex:   T.nilable(Regexp),
+            block:   T.untyped,
+          ).returns(T::Array[String])
+        }
+        def self.versions_from_content(content, regex = nil, &block)
+          return [] if content.blank? || block.blank?
+
+          require "rexml"
+          xml = parse_xml(content)
+          return [] if xml.blank?
+
+          block_return_value = if regex.present?
+            yield(xml, regex)
+          elsif block.arity == 2
+            raise "Two arguments found in `strategy` block but no regex provided."
+          else
+            yield(xml)
+          end
+          Strategy.handle_block_return(block_return_value)
+        end
+
+        # Checks the XML content at the URL for versions, using the provided
+        # `strategy` block to extract version information.
+        #
+        # @param url [String] the URL of the content to check
+        # @param regex [Regexp, nil] a regex used for matching versions
+        # @param provided_content [String, nil] page content to use in place of
+        #   fetching via `Strategy#page_content`
+        # @param homebrew_curl [Boolean] whether to use brewed curl with the URL
+        # @return [Hash]
+        sig {
+          params(
+            url:              String,
+            regex:            T.nilable(Regexp),
+            provided_content: T.nilable(String),
+            homebrew_curl:    T::Boolean,
+            _unused:          T.nilable(T::Hash[Symbol, T.untyped]),
+            block:            T.untyped,
+          ).returns(T::Hash[Symbol, T.untyped])
+        }
+        def self.find_versions(url:, regex: nil, provided_content: nil, homebrew_curl: false, **_unused, &block)
+          raise ArgumentError, "#{Utils.demodulize(T.must(name))} requires a `strategy` block" if block.blank?
+
+          match_data = { matches: {}, regex: regex, url: url }
+          return match_data if url.blank? || block.blank?
+
+          content = if provided_content.is_a?(String)
+            match_data[:cached] = true
+            provided_content
+          else
+            match_data.merge!(Strategy.page_content(url, homebrew_curl: homebrew_curl))
+            match_data[:content]
+          end
+          return match_data if content.blank?
+
+          versions_from_content(content, regex, &block).each do |match_text|
+            match_data[:matches][match_text] = Version.new(match_text)
+          end
+
+          match_data
+        end
+      end
+    end
+  end
+end

Library/Homebrew/test/livecheck/strategy/xml_spec.rb

@@ -0,0 +1,205 @@
+# typed: false
+# frozen_string_literal: true
+
+require "livecheck/strategy"
+require "rexml/document"
+
+describe Homebrew::Livecheck::Strategy::Xml do
+  subject(:xml) { described_class }
+
+  let(:http_url) { "https://brew.sh/blog/" }
+  let(:non_http_url) { "ftp://brew.sh/" }
+
+  let(:regex) { /^v?(\d+(?:\.\d+)+)$/i }
+
+  let(:content_version_text) {
+    <<~EOS
+      <?xml version="1.0" encoding="utf-8"?>
+      <versions>
+        <version>1.1.2</version>
+        <version>1.1.2b</version>
+        <version>1.1.2a</version>
+        <version>1.1.1</version>
+        <version>1.1.0</version>
+        <version>1.1.0-rc3</version>
+        <version>1.1.0-rc2</version>
+        <version>1.1.0-rc1</version>
+        <version>1.0.x-last</version>
+        <version>1.0.3</version>
+        <version>1.0.3-rc3</version>
+        <version>1.0.3-rc2</version>
+        <version>1.0.3-rc1</version>
+        <version>1.0.2</version>
+        <version>1.0.2-rc1</version>
+        <version>1.0.1</version>
+        <version>1.0.1-rc1</version>
+        <version>1.0.0</version>
+        <version>1.0.0-rc1</version>
+      </versions>
+    EOS
+  }
+
+  let(:content_version_attr) {
+    <<~EOS
+      <?xml version="1.0" encoding="utf-8"?>
+      <items>
+        <item version="1.1.2" />
+        <item version="1.1.2b" />
+        <item version="1.1.2a" />
+        <item version="1.1.1" />
+        <item version="1.1.0" />
+        <item version="1.1.0-rc3" />
+        <item version="1.1.0-rc2" />
+        <item version="1.1.0-rc1" />
+        <item version="1.0.x-last" />
+        <item version="1.0.3" />
+        <item version="1.0.3-rc3" />
+        <item version="1.0.3-rc2" />
+        <item version="1.0.3-rc1" />
+        <item version="1.0.2" />
+        <item version="1.0.2-rc1" />
+        <item version="1.0.1" />
+        <item version="1.0.1-rc1" />
+        <item version="1.0.0" />
+        <item version="1.0.0-rc1" />
+      </items>
+    EOS
+  }
+
+  let(:content_simple) {
+    <<~EOS
+      <?xml version="1.0" encoding="utf-8"?>
+      <version>1.2.3</version>
+    EOS
+  }
+
+  let(:content_undefined_namespace) {
+    <<~EOS
+      <?xml version="1.0" encoding="utf-8"?>
+      <something:version>1.2.3</something:version>
+    EOS
+  }
+
+  let(:content_matches) { ["1.1.2", "1.1.1", "1.1.0", "1.0.3", "1.0.2", "1.0.1", "1.0.0"] }
+  let(:content_simple_matches) { ["1.2.3"] }
+
+  let(:find_versions_return_hash) {
+    {
+      matches: {
+        "1.1.2" => Version.new("1.1.2"),
+        "1.1.1" => Version.new("1.1.1"),
+        "1.1.0" => Version.new("1.1.0"),
+        "1.0.3" => Version.new("1.0.3"),
+        "1.0.2" => Version.new("1.0.2"),
+        "1.0.1" => Version.new("1.0.1"),
+        "1.0.0" => Version.new("1.0.0"),
+      },
+      regex:   regex,
+      url:     http_url,
+    }
+  }
+
+  let(:find_versions_cached_return_hash) {
+    find_versions_return_hash.merge({ cached: true })
+  }
+
+  describe "::match?" do
+    it "returns true for an HTTP URL" do
+      expect(xml.match?(http_url)).to be true
+    end
+
+    it "returns false for a non-HTTP URL" do
+      expect(xml.match?(non_http_url)).to be false
+    end
+  end
+
+  describe "::parse_xml" do
+    # TODO: Should we be comparing against an actual REXML::Document object?
+    it "returns an REXML::Document when given XML content" do
+      expect(xml.parse_xml(content_version_text)).to be_an_instance_of(REXML::Document)
+    end
+
+    it "returns an REXML::Document when given XML content with an undefined namespace" do
+      expect(xml.parse_xml(content_undefined_namespace)).to be_an_instance_of(REXML::Document)
+    end
+  end
+
+  describe "::versions_from_content" do
+    it "returns an empty array when given a block but content is blank" do
+      expect(xml.versions_from_content("", regex) { "1.2.3" }).to eq([])
+    end
+
+    it "returns an array of version strings when given content and a block" do
+      # Returning a string from block
+      expect(xml.versions_from_content(content_simple) do |xml|
+        xml.elements["version"]&.text
+      end).to eq(content_simple_matches)
+      expect(xml.versions_from_content(content_simple, regex) do |xml|
+        version = xml.elements["version"]&.text
+        next if version.blank?
+
+        version[regex, 1]
+      end).to eq(content_simple_matches)
+
+      # Returning an array of strings from block
+      expect(xml.versions_from_content(content_version_text, regex) do |xml, regex|
+        xml.get_elements("versions//version").map { |item| item.text[regex, 1] }
+      end).to eq(content_matches)
+
+      expect(xml.versions_from_content(content_version_attr, regex) do |xml, regex|
+        xml.get_elements("items//item").map do |item|
+          version = item["version"]
+          next if version.blank?
+
+          version[regex, 1]
+        end
+      end).to eq(content_matches)
+    end
+
+    it "allows a nil return from a block" do
+      expect(xml.versions_from_content(content_simple, regex) { next }).to eq([])
+    end
+
+    it "errors if a block uses two arguments but a regex is not given" do
+      expect { xml.versions_from_content(content_simple) { |xml, regex| xml["version"][regex, 1] } }
+        .to raise_error("Two arguments found in `strategy` block but no regex provided.")
+    end
+
+    it "errors on an invalid return type from a block" do
+      expect { xml.versions_from_content(content_simple, regex) { 123 } }
+        .to raise_error(TypeError, Homebrew::Livecheck::Strategy::INVALID_BLOCK_RETURN_VALUE_MSG)
+    end
+  end
+
+  describe "::find_versions?" do
+    it "finds versions in provided_content using a block" do
+      expect(xml.find_versions(url: http_url, regex: regex, provided_content: content_version_text) do |xml, regex|
+        xml.get_elements("versions//version").map { |item| item.text[regex, 1] }
+      end).to eq(find_versions_cached_return_hash)
+
+      # NOTE: A regex should be provided using the `#regex` method in a
+      # `livecheck` block but we're using a regex literal in the `strategy`
+      # block here simply to ensure this method works as expected when a
+      # regex isn't provided.
+      expect(xml.find_versions(url: http_url, provided_content: content_version_text) do |xml|
+        regex = /^v?(\d+(?:\.\d+)+)$/i.freeze
+        xml.get_elements("versions//version").map { |item| item.text[regex, 1] }
+      end).to eq(find_versions_cached_return_hash.merge({ regex: nil }))
+    end
+
+    it "errors if a block is not provided" do
+      expect { xml.find_versions(url: http_url, provided_content: content_simple) }
+        .to raise_error(ArgumentError, "Xml requires a `strategy` block")
+    end
+
+    it "returns default match_data when url is blank" do
+      expect(xml.find_versions(url: "") { "1.2.3" })
+        .to eq({ matches: {}, regex: nil, url: "" })
+    end
+
+    it "returns default match_data when content is blank" do
+      expect(xml.find_versions(url: http_url, provided_content: "") { "1.2.3" })
+        .to eq({ matches: {}, regex: nil, url: http_url, cached: true })
+    end
+  end
+end

docs/Brew-Livecheck.md

@@ -171,6 +171,22 @@ livecheck do
 end
 ```
 
+#### `Xml` `strategy` block
+
+A `strategy` block for `Xml` receives an `REXML::Document` object and, if provided, a regex. For example, if the XML contains a `versions` element with nested `version` elements and their inner text contains the version string, we could extract it using a regex as follows:
+
+```ruby
+livecheck do
+  url "https://www.example.com/example.xml"
+  regex(/v?(\d+(?:\.\d+)+)/i)
+  strategy :xml do |xml, regex|
+    xml.get_elements("versions//version").map { |item| item.text[regex, 1] }
+  end
+end
+```
+
+For more information on how to work with an `REXML::Document` object, please refer to the [`REXML::Document`](https://ruby.github.io/rexml/REXML/Document.html) and [`REXML::Element`](https://ruby.github.io/rexml/REXML/Element.html) documentation.
+
 ### `skip`
 
 Livecheck automatically skips some formulae/casks for a number of reasons (deprecated, disabled, discontinued, etc.). However, on rare occasions we need to use a `livecheck` block to do a manual skip. The `skip` method takes a string containing a very brief reason for skipping.