dmarcator 0.12.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b6c289ca56b406c5f591f414ada16407028e732310ad9b4c784e2f231469828a
-  data.tar.gz: 24f260da56f98e045d262bd5fcbe3ee9d3f8be1b1bdd310e26e8b9b4b74f1021
+  metadata.gz: 6f88c01ff39e839792769a66063bd78cd312f51d5fba6917acf6777d034e0269
+  data.tar.gz: 9b39f980958757f2a27718d157ad9925424a20da358a7100d3b87f9a3765af5f
 SHA512:
-  metadata.gz: f88871eab61d67fcccbe7ac0e6f0dfc8f97160592d97e69e58a69d9d99b069ec02e70b9126a0dc7ae114c9e50d599a0ca014ba9b02fc2514fab7db97c4bd4a08
-  data.tar.gz: 2d10f64bd4cd096f54ba2a6372a07c582dc3aad581fe556a3228be4378ba09bd9e3e5ba57c94a4cd98acc4b87899ded063ab9b886b73390267659754713297bb
+  metadata.gz: 4c5aa75a034fedffc21ad9100de83b82f049dc08416f66cdcf2056ec6f76a8f28415ccfee012ea6432d4cbbbd760279c5a0dbce32d614f0932a0d8e9cd9efa3e
+  data.tar.gz: c1351578b215094ca74bb710725f2b66ad49f8e1c24ba14862ee32bc11099163f0d0e8cbb0736f5d23a614b6d1b801ea4fa9cd52e0a3f521f13ffffa21959897

data/ChangeLog.md

@@ -1,3 +1,14 @@
+### 1.0.0 / 2026-10-30
+
+The public API is now frozen.
+
+* The contract spec added in 0.12.0 defines the supported surface: the module methods, constants and per-class public methods it asserts. Anything documented as `@api private` may still change in a minor release.
+* Deprecations are documentation-only, and removals happen only in a major release. `Report.max_report_bytes`, `Report.max_report_bytes=` and `Report::MAX_REPORT_BYTES` are deprecated in favour of `DMARCator.configure` and `Config::DEFAULT_MAX_REPORT_BYTES`, and will be removed in 2.0.
+* Supported Ruby is `>= 3.3.13`. Dropping a Ruby series is the one documented exception to the no-breaking-changes promise: it is announced in a minor release and removed in the next major.
+* Parsed report values are now frozen, not merely reader-only: the strings taken from the document and the arrays holding records, errors, reasons, auth results and the parsed record's `rua`/`ruf`/`fo` cannot be mutated in place. `Record` and the report value objects are therefore safe to share between threads.
+* The parser and XML helper moved to `DMARCator::Internal`, so the public constants are only documented API and the parser can be replaced in a minor release.
+* Parsing, lookup and transport behaviour are unchanged from 0.12.0; the differences above are the freeze itself.
+
 ### 0.12.0 / 2026-10-29
 
 Breaking changes, taken before 1.0:

data/README.md

@@ -312,6 +312,13 @@ A method is deprecated in a minor release by documentation only — no runtime
 warnings, so nothing is added to application logs. Deprecated methods are
 removed in the next major release.
 
+### Ruby support
+
+The minimum is Ruby 3.3.13, the first release in that series with the regular
+expression fixes the library requires. Dropping support for a Ruby series is
+the one documented exception to the no-breaking-changes promise: it is announced
+in a minor release and removed in the next major.
+
 ## Security
 
 DMARC records and XML reports are treated as untrusted input. See

data/lib/dmarcator/internal/parser.rb

@@ -0,0 +1,356 @@
+# frozen_string_literal: true
+
+require_relative '../exceptions'
+require_relative '../uri'
+
+require 'parslet'
+require 'uri'
+
+module DMARCator
+  #
+  # Implementation details of the library. Nothing here is covered by the
+  # 1.0 compatibility promise.
+  #
+  # @api private
+  #
+  module Internal
+    #
+    # DMARC parser.
+    #
+    # An implementation detail: use {Record.parse} rather than this class.
+    #
+    # @api private
+    #
+    # @see https://tools.ietf.org/html/rfc7489#section-6.4
+    #
+    class Parser < Parslet::Parser
+
+      # Maximum accepted DMARC record size in bytes. Real records are far
+      # smaller; the cap bounds parsing work on hostile input.
+      #
+      MAX_RECORD_BYTES = 4096
+
+      root :dmarc_record
+
+      rule(:dmarc_record) do
+        dmarc_version.repeat(1,1) >>
+        (dmarc_sep >> dmarc_tag).repeat >>
+        dmarc_sep.maybe >>
+        wsp?.maybe
+      end
+
+      rule(:dmarc_sep) { wsp? >> str(';') >> wsp? }
+
+      rule(:dmarc_version) do
+        str('v') >> wsp? >>
+        str('=') >> wsp? >>
+        str('DMARC1').as(:v)
+      end
+
+      rule(:dmarc_tag) do
+        dmarc_request   |
+        dmarc_srequest  |
+        dmarc_auri      |
+        dmarc_furi      |
+        dmarc_adkim     |
+        dmarc_aspf      |
+        dmarc_ainterval |
+        dmarc_fo        |
+        dmarc_rfmt      |
+        dmarc_percent   |
+        unknown_tag
+      end
+
+      #
+      # Defines a rule for a `tag=value` DMARC tag, capturing values that do not
+      # match the rule as `:invalid_tag` so strict mode can reject them.
+      #
+      # @param [Symbol] name
+      #   The rule name, used as `dmarc_<name>`.
+      #
+      # @param [String] tag
+      #   The DMARC tag name.
+      #
+      # @yieldreturn [Parslet::Atoms::Base]
+      #   The parslet matching the tag's value.
+      #
+      # @api private
+      #
+      def self.tag_rule(name,tag,&block)
+        rule(:"dmarc_#{name}") do
+          (
+            str(tag) >> wsp? >> str('=') >> wsp? >>
+            instance_eval(&block).as(tag.to_sym)
+          ) |
+          (
+            str(tag) >> wsp? >> str('=') >> wsp? >>
+            match["^; \t"].repeat(1)
+          ).as(:invalid_tag)
+        end
+      end
+
+      tag_rule(:request,'p') do
+        str('none') | str('quarantine') | str('reject')
+      end
+
+      tag_rule(:srequest,'sp') do
+        str('none') | str('quarantine') | str('reject')
+      end
+
+      tag_rule(:auri, 'rua') do
+        dmarc_uri >> (uri_list_sep.present? >> uri_list_sep).repeat >> (wsp? >> str(',')).absent?
+      end
+
+      tag_rule(:ainterval,'ri') { digit.repeat(1, 10) >> digit.absent? }
+
+      tag_rule(:furi,'ruf') do
+        dmarc_uri >> (uri_list_sep.present? >> uri_list_sep).repeat >> (wsp? >> str(',')).absent?
+      end
+
+      tag_rule(:fo,'fo') do
+        fo_opt >> (wsp? >> str(':') >> wsp? >> fo_opt).repeat
+      end
+
+      rule(:fo_opt) { match['01ds'].as(:fo_opt) }
+
+      tag_rule(:rfmt,'rf') { str('afrf') | str('iodef') }
+
+      tag_rule(:percent,'pct') { digit.repeat(1,3) >> digit.absent? }
+
+      tag_rule(:adkim, 'adkim') { match['rs'] }
+      tag_rule(:aspf, 'aspf')   { match['rs'] }
+
+      rule(:unknown_tag) { match["^; \t"].repeat(1).as(:unknown_tag) }
+
+      rule(:dmarc_uri) do
+        mailto_uri.as(:uri) >> (
+          str('!') >> digit.repeat(1, 10).as(:size) >> digit.absent? >> (
+            match['kmgt']
+          ).as(:unit).maybe
+        ).maybe >> str('!').absent?
+      end
+
+      rule(:uri_list_sep) { wsp? >> str(',') >> wsp? >> dmarc_uri }
+
+      rule(:mailto_uri) do
+        match['mM'] >> match['aA'] >> match['iI'] >> match['lL'] >> match['tT'] >> match['oO'] >>
+        str(':') >> mailto_address
+      end
+
+      rule(:mailto_address) do
+        mailto_local >> str('@') >> mailto_domain
+      end
+
+      rule(:mailto_local)  { mailto_char.repeat(1) }
+      rule(:mailto_domain) { mailto_char.repeat(1) }
+      rule(:mailto_char)   { match["A-Za-z0-9._%+-"] }
+
+      rule(:digit) { match('[0-9]') }
+      rule(:wsp) { str(' ') | str("\t") }
+      rule(:wsp?) { wsp.repeat }
+
+      #
+      # Converts the raw parse tree into tag attributes.
+      #
+      # @api private
+      #
+      class Transform < Parslet::Transform
+
+        rule(fo_opt: simple(:fo_opt)) { fo_opt }
+        rule(fo: simple(:fo_opt)) { {fo: [fo_opt]} }
+
+        rule(v: simple(:version)) { {v: version.to_sym} }
+        rule(p:  simple(:p))  { {p:  p.to_sym } }
+        rule(sp: simple(:sp)) { {sp: sp.to_sym} }
+        rule(rf: simple(:rf)) { {rf: rf.to_sym} }
+        rule(adkim: simple(:adkim)) { {adkim: adkim.to_sym} }
+        rule(aspf:  simple(:aspf))  { {aspf: aspf.to_sym} }
+
+        rule(pct: simple(:pct)) { {pct: pct.to_i} }
+        rule(ri:  simple(:ri))  { {ri:  ri.to_i}  }
+
+        rule(uri: simple(:uri), size: simple(:size), unit: simple(:unit)) do
+          Uri.new(
+            Transform.parse_uri(uri),
+            size.to_i,
+            unit.to_sym
+          )
+        end
+        rule(uri: simple(:uri), size: simple(:size)) do
+          Uri.new(
+            Transform.parse_uri(uri),
+            size.to_i
+          )
+        end
+        rule(uri: simple(:uri)) { Uri.new(Transform.parse_uri(uri)) }
+        rule(rua: subtree(:uris)) { {rua: Array(uris)} }
+        rule(ruf: subtree(:uris)) { {ruf: Array(uris)} }
+
+        # Maximum length of error messages echoed from untrusted input.
+        MAX_ERROR_MESSAGE_LENGTH = 300
+
+        #
+        # Parses a `mailto:` URI from a parse tree slice.
+        #
+        # @param [Parslet::Slice] value
+        #
+        # @return [URI::MailTo]
+        #
+        # @raise [InvalidRecord]
+        #   The URI is not a valid `mailto:` URI.
+        #
+        # @api private
+        #
+        def self.parse_uri(value)
+          uri = value.to_s
+
+          begin
+            parsed = URI.parse(uri)
+          rescue URI::Error => error
+            raise InvalidRecord, truncate(error.message)
+          end
+
+          unless parsed.is_a?(URI::MailTo)
+            raise InvalidRecord, "invalid DMARC report URI (expected mailto): #{truncate(uri)}"
+          end
+
+          parsed
+        end
+
+        #
+        # Truncates an error message to a bounded length.
+        #
+        # @param [String] message
+        #
+        # @return [String]
+        #
+        # @api private
+        #
+        def self.truncate(message)
+          message = message.to_s
+
+          if message.length > MAX_ERROR_MESSAGE_LENGTH
+            message[0, MAX_ERROR_MESSAGE_LENGTH] + "..."
+          else
+            message
+          end
+        end
+
+      end
+
+      #
+      # Parses a DMARC record.
+      #
+      # @param [String] record
+      #   The raw DMARC record to parse.
+      #
+      # @param [Boolean] strict (false)
+      #   When `true`, raise on unknown tags or invalid tag values instead of
+      #   silently ignoring them.
+      #
+      # @return [Hash{Symbol => Object}]
+      #   The Hash of tags within the record.
+      #
+      # @raise [InvalidRecord]
+      #   The record is not a String, is malformed, is too large, or (in strict
+      #   mode) contains an unknown tag or invalid tag value.
+      #
+      def self.parse(record, strict: false)
+        unless record.is_a?(String)
+          raise InvalidRecord, "DMARC record must be a String, got #{record.class}"
+        end
+
+        if record.bytesize > MAX_RECORD_BYTES
+          raise InvalidRecord, "DMARC record exceeds maximum size of #{MAX_RECORD_BYTES} bytes"
+        end
+
+        tree = parser.parse(record)
+
+        if strict
+          tree.each do |node|
+            next unless ignored?(node)
+
+            if node.key?(:unknown_tag)
+              raise InvalidRecord, "unknown DMARC tag: #{Transform.truncate(node[:unknown_tag].to_s).inspect}"
+            else
+              raise InvalidRecord, "invalid DMARC tag value: #{Transform.truncate(node[:invalid_tag].to_s).inspect}"
+            end
+          end
+        end
+
+        tags = transform.apply(tree.reject { |node| ignored?(node) })
+        hash = {}
+
+        tags.each do |tag|
+          tag.each_key do |key|
+            if hash.key?(key)
+              raise InvalidRecord, "duplicate DMARC tag: #{key}"
+            end
+          end
+
+          hash.merge!(tag)
+        end
+
+        validate!(hash)
+
+        return hash
+      end
+
+      #
+      # Determines whether a parse-tree node represents a tag that the lenient
+      # parser dropped because it was unknown or had an invalid value.
+      #
+      # @param [Object] node
+      #   The parse-tree node.
+      #
+      # @return [Boolean]
+      #
+      def self.ignored?(node)
+        node.is_a?(Hash) && (node.key?(:unknown_tag) || node.key?(:invalid_tag))
+      end
+
+      #
+      # The memoized parser instance. Parslet caches rules per instance, so
+      # reusing it avoids rebuilding the grammar on every call.
+      #
+      # @return [Parser]
+      #
+      # @api private
+      #
+      def self.parser
+        @parser ||= new
+      end
+
+      #
+      # The memoized transform instance.
+      #
+      # @return [Transform]
+      #
+      # @api private
+      #
+      def self.transform
+        @transform ||= Transform.new
+      end
+
+      #
+      # Validates the parsed tags.
+      #
+      # @param [Hash{Symbol => Object}] tags
+      #   The parsed tags.
+      #
+      # @raise [InvalidRecord]
+      #   One of the tags has an invalid value.
+      #
+      def self.validate!(tags)
+        if tags[:pct] && !(tags[:pct].is_a?(Integer) && tags[:pct].between?(0, 100))
+          raise InvalidRecord, "pct must be an integer between 0 and 100"
+        end
+
+        if tags[:ri] && !(tags[:ri].is_a?(Integer) && tags[:ri].between?(0, 2**32 - 1))
+          raise InvalidRecord, "ri must be an integer between 0 and 4294967295"
+        end
+      end
+
+    end
+  end
+end

data/lib/dmarcator/internal/xml_helper.rb

@@ -0,0 +1,69 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+
+module DMARCator
+  #
+  # Implementation details of the library. Nothing here is covered by the
+  # 1.0 compatibility promise.
+  #
+  # @api private
+  #
+  module Internal
+    #
+    # Internal helper for extracting values from parsed DMARC XML reports.
+    #
+    module XmlHelper
+      private
+
+      #
+      # Returns the text of the first node matching the XPath expression.
+      #
+      # @param [String] xpath
+      #   The XPath expression to match.
+      #
+      # @return [String, nil]
+      #   The node text, or `nil` if no node matched.
+      #
+      def get_text(xpath)
+        @node.at_xpath(xpath)&.text
+      end
+
+      #
+      # Parses a Unix timestamp from raw element text.
+      #
+      # @param [String, nil] value
+      #   The element text.
+      #
+      # @return [Time, nil]
+      #
+      # @api private
+      #
+      def parse_timestamp(value)
+        seconds = parse_integer(value)
+
+        Time.at(seconds) if seconds
+      end
+
+      #
+      # Parses an integer from raw element text, returning `nil` for values that
+      # are not plain decimal digits.
+      #
+      # @param [String, nil] value
+      #   The element text.
+      #
+      # @return [Integer, nil]
+      #
+      # @api private
+      #
+      def parse_integer(value)
+        return nil if value.nil? || value.empty?
+
+        digits = value.strip
+        return nil unless digits.match?(/\A\d+\z/)
+
+        digits.to_i
+      end
+    end
+  end
+end

data/lib/dmarcator/record.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 require 'dmarcator/query'
-require 'dmarcator/parser'
+require 'dmarcator/internal/parser'
 require 'dmarcator/exceptions'
 
 require 'resolv'
@@ -66,13 +66,13 @@ module DMARCator
       @v     = attributes.fetch(:v)
       @adkim = attributes[:adkim]
       @aspf  = attributes[:aspf]
-      @fo    = attributes[:fo]
+      @fo    = attributes[:fo]&.freeze
       @p     = attributes[:p]
       @pct   = attributes[:pct]
       @rf    = attributes[:rf]
       @ri    = attributes[:ri]
-      @rua   = attributes[:rua]
-      @ruf   = attributes[:ruf]
+      @rua   = attributes[:rua]&.freeze
+      @ruf   = attributes[:ruf]&.freeze
       @sp    = attributes[:sp]
     end
 
@@ -277,7 +277,7 @@ module DMARCator
     # @api public
     #
     def self.parse(record, strict: false)
-      attributes = Parser.parse(record, strict: strict)
+      attributes = Internal::Parser.parse(record, strict: strict)
 
       unless attributes[:p]
         raise InvalidRecord, "DMARC record is missing the required 'p' tag"

data/lib/dmarcator/report/auth_result.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative '../xml_helper'
+require_relative '../internal/xml_helper'
 
 module DMARCator
   class Report
@@ -8,7 +8,7 @@ module DMARCator
     # Represents an `auth_results` entry (DKIM/SPF) in a DMARC XML report.
     #
     class AuthResult
-      include XmlHelper
+      include Internal::XmlHelper
 
       # Attribute names exposed by this class.
       ATTRIBUTES = [:type, :domain, :result, :selector, :scope]
@@ -27,18 +27,18 @@ module DMARCator
 
       def initialize(node)
         @node = node
-        @type = node.name
+        @type = node.name.freeze
 
         node.element_children.each do |element|
           case element.name
           when 'domain'
-            @domain ||= element.text
+            @domain ||= element.text.freeze
           when 'result'
-            @result ||= element.text
+            @result ||= element.text.freeze
           when 'selector'
-            @selector ||= element.text
+            @selector ||= element.text.freeze
           when 'scope'
-            @scope ||= element.text
+            @scope ||= element.text.freeze
           end
         end
       end

data/lib/dmarcator/report/metadata.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative '../xml_helper'
+require_relative '../internal/xml_helper'
 
 module DMARCator
   class Report
@@ -8,7 +8,7 @@ module DMARCator
     # Represents the `report_metadata` element of a DMARC XML report.
     #
     class Metadata
-      include XmlHelper
+      include Internal::XmlHelper
 
       # Attribute names exposed by this class.
       ATTRIBUTES = [
@@ -37,24 +37,25 @@ module DMARCator
         @errors = []
 
         metadata = node.at_xpath('feedback/report_metadata')
-        return unless metadata
 
         metadata.element_children.each do |element|
           case element.name
           when 'org_name'
-            @org_name ||= element.text
+            @org_name ||= element.text.freeze
           when 'email'
-            @email ||= element.text
+            @email ||= element.text.freeze
           when 'extra_contact_info'
-            @extra_contact_info ||= element.text
+            @extra_contact_info ||= element.text.freeze
           when 'report_id'
-            @report_id ||= element.text
+            @report_id ||= element.text.freeze
           when 'error'
-            errors << element.text
+            errors << element.text.freeze
           when 'date_range'
             parse_date_range(element)
           end
         end
+      ensure
+        @errors.freeze
       end
 
       private
@@ -63,9 +64,9 @@ module DMARCator
         date_range.element_children.each do |element|
           case element.name
           when 'begin'
-            @begin_at ||= parse_timestamp(element.text)
+            @begin_at ||= parse_timestamp(element.text.freeze)
           when 'end'
-            @end_at ||= parse_timestamp(element.text)
+            @end_at ||= parse_timestamp(element.text.freeze)
           end
         end
       end

data/lib/dmarcator/report/policy.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative '../xml_helper'
+require_relative '../internal/xml_helper'
 
 module DMARCator
   class Report
@@ -8,7 +8,7 @@ module DMARCator
     # Represents the `policy_published` element of a DMARC XML report.
     #
     class Policy
-      include XmlHelper
+      include Internal::XmlHelper
 
       # Attribute names exposed by this class.
       ATTRIBUTES = [:domain, :adkim, :aspf, :p, :sp, :pct, :fo]
@@ -38,19 +38,19 @@ module DMARCator
         policy.element_children.each do |element|
           case element.name
           when 'pct'
-            @pct ||= parse_integer(element.text)
+            @pct ||= parse_integer(element.text.freeze)
           when 'domain'
-            @domain ||= element.text
+            @domain ||= element.text.freeze
           when 'adkim'
-            @adkim ||= element.text
+            @adkim ||= element.text.freeze
           when 'aspf'
-            @aspf ||= element.text
+            @aspf ||= element.text.freeze
           when 'p'
-            @p ||= element.text
+            @p ||= element.text.freeze
           when 'sp'
-            @sp ||= element.text
+            @sp ||= element.text.freeze
           when 'fo'
-            @fo ||= element.text
+            @fo ||= element.text.freeze
           end
         end
       end

data/lib/dmarcator/report/reason.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative '../xml_helper'
+require_relative '../internal/xml_helper'
 
 module DMARCator
   class Report
@@ -8,7 +8,7 @@ module DMARCator
     # Represents a `reason` element of a DMARC XML report record.
     #
     class Reason
-      include XmlHelper
+      include Internal::XmlHelper
 
       # Attribute names exposed by this class.
       ATTRIBUTES = [:type, :comment]
@@ -25,9 +25,9 @@ module DMARCator
         node.element_children.each do |element|
           case element.name
           when 'type'
-            @type ||= element.text
+            @type ||= element.text.freeze
           when 'comment'
-            @comment ||= element.text
+            @comment ||= element.text.freeze
           end
         end
       end

data/lib/dmarcator/report/row.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require_relative '../xml_helper'
+require_relative '../internal/xml_helper'
 require_relative 'auth_result'
 require_relative 'reason'
 
@@ -13,7 +13,7 @@ module DMARCator
     # DMARC TXT record.
     #
     class Row
-      include XmlHelper
+      include Internal::XmlHelper
 
       # Attribute names exposed by this class.
       ATTRIBUTES = [
@@ -64,7 +64,7 @@ module DMARCator
       def reasons
         return @reasons if defined?(@reasons)
 
-        @reasons = @reason_nodes.map { |reason_node| Reason.new(reason_node) }
+        @reasons = @reason_nodes.map { |reason_node| Reason.new(reason_node) }.freeze
       end
 
       #
@@ -77,7 +77,7 @@ module DMARCator
 
         @auth_results = @auth_result_nodes.map do |auth_result_node|
           AuthResult.new(auth_result_node)
-        end
+        end.freeze
       end
 
       private
@@ -86,9 +86,9 @@ module DMARCator
         row.element_children.each do |element|
           case element.name
           when 'source_ip'
-            @source_ip ||= element.text
+            @source_ip ||= element.text.freeze
           when 'count'
-            @count ||= parse_integer(element.text)
+            @count ||= parse_integer(element.text.freeze)
           when 'policy_evaluated'
             parse_policy_evaluated(element)
           end
@@ -99,11 +99,11 @@ module DMARCator
         policy_evaluated.element_children.each do |element|
           case element.name
           when 'disposition'
-            @disposition ||= element.text
+            @disposition ||= element.text.freeze
           when 'dkim'
-            @dkim ||= element.text
+            @dkim ||= element.text.freeze
           when 'spf'
-            @spf ||= element.text
+            @spf ||= element.text.freeze
           when 'reason'
             @reason_nodes << element
           end
@@ -114,11 +114,11 @@ module DMARCator
         identifiers.element_children.each do |element|
           case element.name
           when 'envelope_to'
-            @envelope_to ||= element.text
+            @envelope_to ||= element.text.freeze
           when 'envelope_from'
-            @envelope_from ||= element.text
+            @envelope_from ||= element.text.freeze
           when 'header_from'
-            @header_from ||= element.text
+            @header_from ||= element.text.freeze
           end
         end
       end

data/lib/dmarcator/report.rb

@@ -3,7 +3,7 @@
 require 'nokogiri'
 
 require_relative 'config'
-require_relative 'xml_helper'
+require_relative 'internal/xml_helper'
 require_relative 'exceptions'
 require_relative 'report/metadata'
 require_relative 'report/policy'
@@ -17,11 +17,11 @@ module DMARCator
   # resolved or fetched; treat report XML as untrusted input.
   #
   class Report
-    include XmlHelper
+    include Internal::XmlHelper
 
     # Default maximum accepted report size in bytes (25 MiB).
     #
-    # @deprecated Use {Config::DEFAULT_MAX_REPORT_BYTES}.
+    # @deprecated Use {Config::DEFAULT_MAX_REPORT_BYTES}. Removed in 2.0.
     #
     MAX_REPORT_BYTES = Config::DEFAULT_MAX_REPORT_BYTES
 
@@ -30,6 +30,7 @@ module DMARCator
       # The maximum accepted report size in bytes.
       #
       # @deprecated Use {DMARCator.configure} with `config.max_report_bytes`.
+      #   Removed in 2.0.
       #
       # @return [Integer]
       #
@@ -41,6 +42,7 @@ module DMARCator
       # Sets the maximum accepted report size in bytes.
       #
       # @deprecated Use {DMARCator.configure} with `config.max_report_bytes`.
+      #   Removed in 2.0.
       #
       # @param [Integer, nil] value
       #
@@ -100,7 +102,7 @@ module DMARCator
         value = get_text('feedback/version')
         value = value.strip if value
 
-        value if value && value.match?(/\A\d+(?:\.\d+)*\z/)
+        value.freeze if value && value.match?(/\A\d+(?:\.\d+)*\z/)
       end
     end
 
@@ -130,7 +132,7 @@ module DMARCator
     def records
       @records ||= @node.xpath('feedback/record').map do |node|
         Row.new(node)
-      end
+      end.freeze
     end
   end
 end

data/lib/dmarcator/version.rb

@@ -2,5 +2,5 @@
 
 module DMARCator
   # dmarcator version
-  VERSION = '0.12.0'
+  VERSION = '1.0.0'
 end

data/lib/dmarcator.rb

@@ -3,7 +3,7 @@
 require 'dmarcator/exceptions'
 require 'dmarcator/query'
 require 'dmarcator/record'
-require 'dmarcator/parser'
+require 'dmarcator/internal/parser'
 require 'dmarcator/report'
 require 'dmarcator/version'
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dmarcator
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Noah Berman
@@ -57,7 +57,8 @@ files:
 - lib/dmarcator.rb
 - lib/dmarcator/config.rb
 - lib/dmarcator/exceptions.rb
-- lib/dmarcator/parser.rb
+- lib/dmarcator/internal/parser.rb
+- lib/dmarcator/internal/xml_helper.rb
 - lib/dmarcator/query.rb
 - lib/dmarcator/record.rb
 - lib/dmarcator/report.rb
@@ -72,7 +73,6 @@ files:
 - lib/dmarcator/resolver/encrypted.rb
 - lib/dmarcator/uri.rb
 - lib/dmarcator/version.rb
-- lib/dmarcator/xml_helper.rb
 homepage: https://github.com/bermannoah/dmarcator
 licenses:
 - MIT

data/lib/dmarcator/parser.rb

@@ -1,348 +0,0 @@
-# frozen_string_literal: true
-
-require 'dmarcator/exceptions'
-require 'dmarcator/uri'
-
-require 'parslet'
-require 'uri'
-
-module DMARCator
-  #
-  # DMARC parser.
-  #
-  # An implementation detail: use {Record.parse} rather than this class.
-  #
-  # @api private
-  #
-  # @see https://tools.ietf.org/html/rfc7489#section-6.4
-  #
-  class Parser < Parslet::Parser
-
-    # Maximum accepted DMARC record size in bytes. Real records are far
-    # smaller; the cap bounds parsing work on hostile input.
-    #
-    MAX_RECORD_BYTES = 4096
-
-    root :dmarc_record
-
-    rule(:dmarc_record) do
-      dmarc_version.repeat(1,1) >>
-      (dmarc_sep >> dmarc_tag).repeat >>
-      dmarc_sep.maybe >>
-      wsp?.maybe
-    end
-
-    rule(:dmarc_sep) { wsp? >> str(';') >> wsp? }
-
-    rule(:dmarc_version) do
-      str('v') >> wsp? >>
-      str('=') >> wsp? >>
-      str('DMARC1').as(:v)
-    end
-
-    rule(:dmarc_tag) do
-      dmarc_request   |
-      dmarc_srequest  |
-      dmarc_auri      |
-      dmarc_furi      |
-      dmarc_adkim     |
-      dmarc_aspf      |
-      dmarc_ainterval |
-      dmarc_fo        |
-      dmarc_rfmt      |
-      dmarc_percent   |
-      unknown_tag
-    end
-
-    #
-    # Defines a rule for a `tag=value` DMARC tag, capturing values that do not
-    # match the rule as `:invalid_tag` so strict mode can reject them.
-    #
-    # @param [Symbol] name
-    #   The rule name, used as `dmarc_<name>`.
-    #
-    # @param [String] tag
-    #   The DMARC tag name.
-    #
-    # @yieldreturn [Parslet::Atoms::Base]
-    #   The parslet matching the tag's value.
-    #
-    # @api private
-    #
-    def self.tag_rule(name,tag,&block)
-      rule(:"dmarc_#{name}") do
-        (
-          str(tag) >> wsp? >> str('=') >> wsp? >>
-          instance_eval(&block).as(tag.to_sym)
-        ) |
-        (
-          str(tag) >> wsp? >> str('=') >> wsp? >>
-          match["^; \t"].repeat(1)
-        ).as(:invalid_tag)
-      end
-    end
-
-    tag_rule(:request,'p') do
-      str('none') | str('quarantine') | str('reject')
-    end
-
-    tag_rule(:srequest,'sp') do
-      str('none') | str('quarantine') | str('reject')
-    end
-
-    tag_rule(:auri, 'rua') do
-      dmarc_uri >> (uri_list_sep.present? >> uri_list_sep).repeat >> (wsp? >> str(',')).absent?
-    end
-
-    tag_rule(:ainterval,'ri') { digit.repeat(1, 10) >> digit.absent? }
-
-    tag_rule(:furi,'ruf') do
-      dmarc_uri >> (uri_list_sep.present? >> uri_list_sep).repeat >> (wsp? >> str(',')).absent?
-    end
-
-    tag_rule(:fo,'fo') do
-      fo_opt >> (wsp? >> str(':') >> wsp? >> fo_opt).repeat
-    end
-
-    rule(:fo_opt) { match['01ds'].as(:fo_opt) }
-
-    tag_rule(:rfmt,'rf') { str('afrf') | str('iodef') }
-
-    tag_rule(:percent,'pct') { digit.repeat(1,3) >> digit.absent? }
-
-    tag_rule(:adkim, 'adkim') { match['rs'] }
-    tag_rule(:aspf, 'aspf')   { match['rs'] }
-
-    rule(:unknown_tag) { match["^; \t"].repeat(1).as(:unknown_tag) }
-
-    rule(:dmarc_uri) do
-      mailto_uri.as(:uri) >> (
-        str('!') >> digit.repeat(1, 10).as(:size) >> digit.absent? >> (
-          match['kmgt']
-        ).as(:unit).maybe
-      ).maybe >> str('!').absent?
-    end
-
-    rule(:uri_list_sep) { wsp? >> str(',') >> wsp? >> dmarc_uri }
-
-    rule(:mailto_uri) do
-      match['mM'] >> match['aA'] >> match['iI'] >> match['lL'] >> match['tT'] >> match['oO'] >>
-      str(':') >> mailto_address
-    end
-
-    rule(:mailto_address) do
-      mailto_local >> str('@') >> mailto_domain
-    end
-
-    rule(:mailto_local)  { mailto_char.repeat(1) }
-    rule(:mailto_domain) { mailto_char.repeat(1) }
-    rule(:mailto_char)   { match["A-Za-z0-9._%+-"] }
-
-    rule(:digit) { match('[0-9]') }
-    rule(:wsp) { str(' ') | str("\t") }
-    rule(:wsp?) { wsp.repeat }
-
-    #
-    # Converts the raw parse tree into tag attributes.
-    #
-    # @api private
-    #
-    class Transform < Parslet::Transform
-
-      rule(fo_opt: simple(:fo_opt)) { fo_opt }
-      rule(fo: simple(:fo_opt)) { {fo: [fo_opt]} }
-
-      rule(v: simple(:version)) { {v: version.to_sym} }
-      rule(p:  simple(:p))  { {p:  p.to_sym } }
-      rule(sp: simple(:sp)) { {sp: sp.to_sym} }
-      rule(rf: simple(:rf)) { {rf: rf.to_sym} }
-      rule(adkim: simple(:adkim)) { {adkim: adkim.to_sym} }
-      rule(aspf:  simple(:aspf))  { {aspf: aspf.to_sym} }
-
-      rule(pct: simple(:pct)) { {pct: pct.to_i} }
-      rule(ri:  simple(:ri))  { {ri:  ri.to_i}  }
-
-      rule(uri: simple(:uri), size: simple(:size), unit: simple(:unit)) do
-        Uri.new(
-          Transform.parse_uri(uri),
-          size.to_i,
-          unit.to_sym
-        )
-      end
-      rule(uri: simple(:uri), size: simple(:size)) do
-        Uri.new(
-          Transform.parse_uri(uri),
-          size.to_i
-        )
-      end
-      rule(uri: simple(:uri)) { Uri.new(Transform.parse_uri(uri)) }
-      rule(rua: subtree(:uris)) { {rua: Array(uris)} }
-      rule(ruf: subtree(:uris)) { {ruf: Array(uris)} }
-
-      # Maximum length of error messages echoed from untrusted input.
-      MAX_ERROR_MESSAGE_LENGTH = 300
-
-      #
-      # Parses a `mailto:` URI from a parse tree slice.
-      #
-      # @param [Parslet::Slice] value
-      #
-      # @return [URI::MailTo]
-      #
-      # @raise [InvalidRecord]
-      #   The URI is not a valid `mailto:` URI.
-      #
-      # @api private
-      #
-      def self.parse_uri(value)
-        uri = value.to_s
-
-        begin
-          parsed = URI.parse(uri)
-        rescue URI::Error => error
-          raise InvalidRecord, truncate(error.message)
-        end
-
-        unless parsed.is_a?(URI::MailTo)
-          raise InvalidRecord, "invalid DMARC report URI (expected mailto): #{truncate(uri)}"
-        end
-
-        parsed
-      end
-
-      #
-      # Truncates an error message to a bounded length.
-      #
-      # @param [String] message
-      #
-      # @return [String]
-      #
-      # @api private
-      #
-      def self.truncate(message)
-        message = message.to_s
-
-        if message.length > MAX_ERROR_MESSAGE_LENGTH
-          message[0, MAX_ERROR_MESSAGE_LENGTH] + "..."
-        else
-          message
-        end
-      end
-
-    end
-
-    #
-    # Parses a DMARC record.
-    #
-    # @param [String] record
-    #   The raw DMARC record to parse.
-    #
-    # @param [Boolean] strict (false)
-    #   When `true`, raise on unknown tags or invalid tag values instead of
-    #   silently ignoring them.
-    #
-    # @return [Hash{Symbol => Object}]
-    #   The Hash of tags within the record.
-    #
-    # @raise [InvalidRecord]
-    #   The record is not a String, is malformed, is too large, or (in strict
-    #   mode) contains an unknown tag or invalid tag value.
-    #
-    def self.parse(record, strict: false)
-      unless record.is_a?(String)
-        raise InvalidRecord, "DMARC record must be a String, got #{record.class}"
-      end
-
-      if record.bytesize > MAX_RECORD_BYTES
-        raise InvalidRecord, "DMARC record exceeds maximum size of #{MAX_RECORD_BYTES} bytes"
-      end
-
-      tree = parser.parse(record)
-
-      if strict
-        tree.each do |node|
-          next unless ignored?(node)
-
-          if node.key?(:unknown_tag)
-            raise InvalidRecord, "unknown DMARC tag: #{Transform.truncate(node[:unknown_tag].to_s).inspect}"
-          else
-            raise InvalidRecord, "invalid DMARC tag value: #{Transform.truncate(node[:invalid_tag].to_s).inspect}"
-          end
-        end
-      end
-
-      tags = transform.apply(tree.reject { |node| ignored?(node) })
-      hash = {}
-
-      tags.each do |tag|
-        tag.each_key do |key|
-          if hash.key?(key)
-            raise InvalidRecord, "duplicate DMARC tag: #{key}"
-          end
-        end
-
-        hash.merge!(tag)
-      end
-
-      validate!(hash)
-
-      return hash
-    end
-
-    #
-    # Determines whether a parse-tree node represents a tag that the lenient
-    # parser dropped because it was unknown or had an invalid value.
-    #
-    # @param [Object] node
-    #   The parse-tree node.
-    #
-    # @return [Boolean]
-    #
-    def self.ignored?(node)
-      node.is_a?(Hash) && (node.key?(:unknown_tag) || node.key?(:invalid_tag))
-    end
-
-    #
-    # The memoized parser instance. Parslet caches rules per instance, so
-    # reusing it avoids rebuilding the grammar on every call.
-    #
-    # @return [Parser]
-    #
-    # @api private
-    #
-    def self.parser
-      @parser ||= new
-    end
-
-    #
-    # The memoized transform instance.
-    #
-    # @return [Transform]
-    #
-    # @api private
-    #
-    def self.transform
-      @transform ||= Transform.new
-    end
-
-    #
-    # Validates the parsed tags.
-    #
-    # @param [Hash{Symbol => Object}] tags
-    #   The parsed tags.
-    #
-    # @raise [InvalidRecord]
-    #   One of the tags has an invalid value.
-    #
-    def self.validate!(tags)
-      if tags[:pct] && !(tags[:pct].is_a?(Integer) && tags[:pct].between?(0, 100))
-        raise InvalidRecord, "pct must be an integer between 0 and 100"
-      end
-
-      if tags[:ri] && !(tags[:ri].is_a?(Integer) && tags[:ri].between?(0, 2**32 - 1))
-        raise InvalidRecord, "ri must be an integer between 0 and 4294967295"
-      end
-    end
-
-  end
-end

data/lib/dmarcator/xml_helper.rb

@@ -1,61 +0,0 @@
-# frozen_string_literal: true
-
-require 'nokogiri'
-
-module DMARCator
-  #
-  # Internal helper for extracting values from parsed DMARC XML reports.
-  #
-  module XmlHelper
-    private
-
-    #
-    # Returns the text of the first node matching the XPath expression.
-    #
-    # @param [String] xpath
-    #   The XPath expression to match.
-    #
-    # @return [String, nil]
-    #   The node text, or `nil` if no node matched.
-    #
-    def get_text(xpath)
-      @node.at_xpath(xpath)&.text
-    end
-
-    #
-    # Parses a Unix timestamp from raw element text.
-    #
-    # @param [String, nil] value
-    #   The element text.
-    #
-    # @return [Time, nil]
-    #
-    # @api private
-    #
-    def parse_timestamp(value)
-      seconds = parse_integer(value)
-
-      Time.at(seconds) if seconds
-    end
-
-    #
-    # Parses an integer from raw element text, returning `nil` for values that
-    # are not plain decimal digits.
-    #
-    # @param [String, nil] value
-    #   The element text.
-    #
-    # @return [Integer, nil]
-    #
-    # @api private
-    #
-    def parse_integer(value)
-      return nil if value.nil? || value.empty?
-
-      digits = value.strip
-      return nil unless digits.match?(/\A\d+\z/)
-
-      digits.to_i
-    end
-  end
-end