philiprehberger-encoding_kit 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 53d87e443eeb4c48893c09ab98662b29de9df96c6b6af0795a8fc3311a33ea3b
-  data.tar.gz: e1939f99e731ad8627ce581761850a0f6362a55e1a6b164bebe2ed951b0a6fc3
+  metadata.gz: f28c4abaf812bdda01287ea83ef2c48cdef622a082db01adb3f81899ae715809
+  data.tar.gz: 113cd2df4e35e9f49955209662d37aa091bb749fb819d7e1597d7c50c11cdb14
 SHA512:
-  metadata.gz: 21eb582de63768fc7c657b4d4e3f5d1a33b2b46f38dfc168b2e86f7be0816477a0c8fc74e55580fc33922205d30b343260d1ff655888997f26fbc38112b1e1ee
-  data.tar.gz: e2d6cf3dfa4a688e166ab790d00142bb1621a1ec205355a0cbfebc828b8008f8d52f08e783d4c64d5b1410cb24d2c2401abc7e9ccd5d5621bfa88427aaa590e2
+  metadata.gz: c9b0b01dbeb5e0362854c5a66b36e86a7d18c3b05949f70f5496cbe9c5ca784305dc61b9cd330b2f4e7549b0430381ab55ab2c387c24c28b64f9232a843f0c06
+  data.tar.gz: 1754851e434597696433549da529b471e2307da5c6282433c1b8fe5bf624cba3d3210c5e51d6d4f0656b561c5dea27336c9ce8ac8f09c9e53ac56165a848f536

data/CHANGELOG.md

@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.0] - 2026-03-28
+
+### Added
+
+- Confidence scores: `detect` returns a `DetectionResult` with `.encoding` and `.confidence` (1.0 for BOM, 0.5-0.9 for heuristics)
+- `DetectionResult` delegates to `Encoding` for backward compatibility (e.g., `result == Encoding::UTF_8` still works)
+- Streaming detection: `detect_stream(io, sample_size: 4096)` reads a sample from IO objects
+- Encoding analysis: `analyze(string)` returns byte distribution stats and ranked candidates
+- Windows codepage support: CP1252, CP1250, CP1251 detection via 0x80-0x9F byte patterns
+- Transcode alias: `transcode(string, to:, fallback:, replace:)` for simplified auto-detect-and-convert
+- Issue templates for bug reports and feature requests
+- Dependabot configuration for bundler and GitHub Actions
+- Pull request template
+
 ## [0.1.1] - 2026-03-26
 
 ### Added

data/README.md

@@ -2,7 +2,11 @@
 
 [![Tests](https://github.com/philiprehberger/rb-encoding-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/philiprehberger/rb-encoding-kit/actions/workflows/ci.yml)
 [![Gem Version](https://badge.fury.io/rb/philiprehberger-encoding_kit.svg)](https://rubygems.org/gems/philiprehberger-encoding_kit)
+[![GitHub release](https://img.shields.io/github/v/release/philiprehberger/rb-encoding-kit)](https://github.com/philiprehberger/rb-encoding-kit/releases)
+[![Last updated](https://img.shields.io/github/last-commit/philiprehberger/rb-encoding-kit)](https://github.com/philiprehberger/rb-encoding-kit/commits/main)
 [![License](https://img.shields.io/github/license/philiprehberger/rb-encoding-kit)](LICENSE)
+[![Bug Reports](https://img.shields.io/github/issues/philiprehberger/rb-encoding-kit/bug)](https://github.com/philiprehberger/rb-encoding-kit/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
+[![Feature Requests](https://img.shields.io/github/issues/philiprehberger/rb-encoding-kit/enhancement)](https://github.com/philiprehberger/rb-encoding-kit/issues?q=is%3Aissue+is%3Aopen+label%3Aenhancement)
 [![Sponsor](https://img.shields.io/badge/sponsor-GitHub%20Sponsors-ec6cb9)](https://github.com/sponsors/philiprehberger)
 
 Character encoding detection, conversion, and normalization
@@ -30,19 +34,68 @@ gem install philiprehberger-encoding_kit
 ```ruby
 require "philiprehberger/encoding_kit"
 
-encoding = Philiprehberger::EncodingKit.detect(raw_bytes)
+result = Philiprehberger::EncodingKit.detect(raw_bytes)
+result.encoding   # => Encoding::UTF_8
+result.confidence # => 0.9
 utf8 = Philiprehberger::EncodingKit.to_utf8(raw_bytes)
 ```
 
-### Encoding Detection
+### Encoding Detection with Confidence
 
 ```ruby
 require "philiprehberger/encoding_kit"
 
-# Detects via BOM first, then UTF-8 validity, ASCII, Latin-1 heuristics
-Philiprehberger::EncodingKit.detect("\xEF\xBB\xBFhello".b) # => Encoding::UTF_8
-Philiprehberger::EncodingKit.detect("caf\xC3\xA9".b)       # => Encoding::UTF_8
-Philiprehberger::EncodingKit.detect("caf\xE9".b)            # => Encoding::ISO_8859_1
+# Returns a DetectionResult that delegates to Encoding
+result = Philiprehberger::EncodingKit.detect("\xEF\xBB\xBFhello".b)
+result == Encoding::UTF_8  # => true (backward compatible)
+result.confidence          # => 1.0 (BOM detected)
+result.name                # => "UTF-8"
+result.to_h                # => {encoding: Encoding::UTF_8, confidence: 1.0}
+
+# Heuristic detection returns lower confidence
+result = Philiprehberger::EncodingKit.detect("caf\xC3\xA9".b)
+result.confidence # => 0.85-0.9
+```
+
+### Streaming Detection
+
+```ruby
+require "philiprehberger/encoding_kit"
+
+File.open("data.csv", "rb") do |file|
+  result = Philiprehberger::EncodingKit.detect_stream(file, sample_size: 8192)
+  result.encoding   # => Encoding::UTF_8
+  result.confidence # => 0.9
+end
+```
+
+### Encoding Analysis
+
+```ruby
+require "philiprehberger/encoding_kit"
+
+analysis = Philiprehberger::EncodingKit.analyze(raw_bytes)
+analysis[:encoding]       # => Encoding::UTF_8
+analysis[:confidence]     # => 0.9
+analysis[:printable_ratio] # => 0.95
+analysis[:ascii_ratio]    # => 0.8
+analysis[:high_bytes]     # => 12
+analysis[:candidates]     # => [{encoding: Encoding::UTF_8, confidence: 0.9}, ...]
+```
+
+### Transcode
+
+```ruby
+require "philiprehberger/encoding_kit"
+
+# Auto-detect source, convert to UTF-8
+utf8 = Philiprehberger::EncodingKit.transcode(raw_bytes)
+
+# Convert to a specific encoding
+latin1 = Philiprehberger::EncodingKit.transcode(utf8_string, to: Encoding::ISO_8859_1)
+
+# Custom fallback behavior
+result = Philiprehberger::EncodingKit.transcode(data, to: "UTF-8", fallback: :replace, replace: "?")
 ```
 
 ### Convert to UTF-8
@@ -97,7 +150,10 @@ Philiprehberger::EncodingKit.valid?("hello", encoding: Encoding::US_ASCII)  # =>
 
 | Method | Description |
 |--------|-------------|
-| `EncodingKit.detect(string)` | Detect encoding via BOM and heuristics, returns an `Encoding` object |
+| `EncodingKit.detect(string)` | Detect encoding via BOM and heuristics, returns a `DetectionResult` with `.encoding` and `.confidence` |
+| `EncodingKit.detect_stream(io, sample_size: 4096)` | Detect encoding from an IO stream by sampling bytes |
+| `EncodingKit.analyze(string)` | Analyze byte distribution and return encoding candidates with stats |
+| `EncodingKit.transcode(string, to:, fallback:, replace:)` | Auto-detect source and convert to target encoding |
 | `EncodingKit.to_utf8(string, from: nil)` | Convert to UTF-8, auto-detect source if `from` is nil |
 | `EncodingKit.normalize(string)` | Force to valid UTF-8, replacing bad bytes with U+FFFD |
 | `EncodingKit.valid?(string, encoding: nil)` | Check if string is valid in given or current encoding |
@@ -113,6 +169,13 @@ bundle exec rspec
 bundle exec rubocop
 ```
 
+## Support
+
+If you find this package useful, consider giving it a star on GitHub — it helps motivate continued maintenance and development.
+
+[![LinkedIn](https://img.shields.io/badge/Philip%20Rehberger-LinkedIn-0A66C2?logo=linkedin)](https://www.linkedin.com/in/philiprehberger)
+[![More packages](https://img.shields.io/badge/more-open%20source%20packages-blue)](https://philiprehberger.com/open-source-packages)
+
 ## License
 
 [MIT](LICENSE)

data/lib/philiprehberger/encoding_kit/converter.rb

@@ -35,7 +35,8 @@ module Philiprehberger
         # @param from [String, Encoding, nil] source encoding (auto-detect if nil)
         # @return [String] UTF-8 encoded string
         def to_utf8(string, from: nil)
-          source = from ? Encoding.find(from.to_s) : Detector.call(string)
+          detected = from ? Encoding.find(from.to_s) : Detector.call(string)
+          source = detected.is_a?(DetectionResult) ? detected.encoding : detected
           str = string.dup.force_encoding(source)
           str.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: "\uFFFD")
         end

data/lib/philiprehberger/encoding_kit/detection_result.rb

@@ -0,0 +1,85 @@
+# frozen_string_literal: true
+
+module Philiprehberger
+  module EncodingKit
+    # A detection result that wraps an Encoding with a confidence score.
+    # Delegates to the underlying Encoding so it can be used transparently
+    # wherever an Encoding object is expected (e.g., == Encoding::UTF_8).
+    class DetectionResult
+      attr_reader :encoding, :confidence
+
+      # @param encoding [Encoding] the detected encoding
+      # @param confidence [Float] confidence score between 0.0 and 1.0
+      def initialize(encoding, confidence)
+        @encoding = encoding
+        @confidence = confidence.to_f
+      end
+
+      # Equality check delegates to the underlying encoding so that
+      # `result == Encoding::UTF_8` works as expected.
+      #
+      # @param other [Object] the object to compare
+      # @return [Boolean]
+      def ==(other)
+        case other
+        when Encoding
+          @encoding == other
+        when DetectionResult
+          @encoding == other.encoding
+        else
+          super
+        end
+      end
+
+      # Support `eql?` for hash key usage.
+      #
+      # @param other [Object]
+      # @return [Boolean]
+      def eql?(other)
+        self == other
+      end
+
+      # Delegate hash to encoding for hash key consistency.
+      #
+      # @return [Integer]
+      def hash
+        @encoding.hash
+      end
+
+      # String representation shows the encoding name.
+      #
+      # @return [String]
+      def to_s
+        @encoding.to_s
+      end
+
+      # Inspect shows both encoding and confidence.
+      #
+      # @return [String]
+      def inspect
+        "#<#{self.class} encoding=#{@encoding} confidence=#{@confidence}>"
+      end
+
+      # Convert to a plain hash representation.
+      #
+      # @return [Hash]
+      def to_h
+        { encoding: @encoding, confidence: @confidence }
+      end
+
+      # Delegate unknown methods to the underlying Encoding object.
+      def method_missing(method, ...)
+        if @encoding.respond_to?(method)
+          @encoding.send(method, ...)
+        else
+          super
+        end
+      end
+
+      # Support respond_to? for delegated methods.
+      def respond_to_missing?(method, include_private = false)
+        @encoding.respond_to?(method, include_private) || super
+      end
+    end
+  end
+end

data/lib/philiprehberger/encoding_kit/detector.rb

@@ -13,29 +13,54 @@ module Philiprehberger
         ["\xFF\xFE".b,         Encoding::UTF_16LE]
       ].freeze
 
+      # Bytes in 0x80-0x9F that are defined in CP1252 but not in ISO-8859-1.
+      # These bytes are unmapped in ISO-8859-1, so their presence strongly
+      # suggests a Windows codepage.
+      CP1252_SPECIFIC = [
+        0x80, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88,
+        0x89, 0x8A, 0x8B, 0x8C, 0x8E, 0x91, 0x92, 0x93,
+        0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B,
+        0x9C, 0x9E, 0x9F
+      ].freeze
+
+      # CP1250 (Central European) has specific characters in 0x80-0x9F
+      # that differ from CP1252. Common: 0x8A (S-caron), 0x8E (Z-caron),
+      # 0x9A (s-caron), 0x9E (z-caron).
+      CP1250_MARKERS = [0x8A, 0x8E, 0x9A, 0x9E].freeze
+
+      # CP1251 (Cyrillic) maps 0x80-0xFF almost entirely to Cyrillic letters.
+      # Bytes 0xC0-0xFF are Cyrillic А-я in CP1251.
+      CP1251_RANGE = (0xC0..0xFF)
+
       class << self
-        # Detect the encoding of a byte string.
+        # Detect the encoding of a byte string, returning a DetectionResult
+        # with encoding and confidence score.
         #
         # Strategy:
-        #   1. Check for a byte order mark (BOM)
-        #   2. Try UTF-8 validity
-        #   3. Check pure ASCII
-        #   4. Apply Latin-1 heuristic
-        #   5. Fall back to BINARY
+        #   1. Check for a byte order mark (BOM) - confidence 1.0
+        #   2. Try UTF-8 validity - confidence 0.9
+        #   3. Check pure ASCII - confidence 0.9
+        #   4. Check Windows codepages (CP1252, CP1250, CP1251) - confidence 0.6-0.7
+        #   5. Apply Latin-1 heuristic - confidence 0.7
+        #   6. Fall back to BINARY - confidence 0.5
         #
         # @param string [String] the input string (ideally with BINARY/ASCII-8BIT encoding)
-        # @return [Encoding] the detected encoding
+        # @return [DetectionResult] the detected encoding with confidence
         def call(string)
           bytes = string.b
 
-          bom_encoding = detect_bom(bytes)
-          return bom_encoding if bom_encoding
+          bom_result = detect_bom_with_confidence(bytes)
+          return bom_result if bom_result
 
-          return Encoding::UTF_8 if valid_utf8?(bytes)
-          return Encoding::US_ASCII if ascii_only?(bytes)
-          return Encoding::ISO_8859_1 if latin1_heuristic?(bytes)
+          return DetectionResult.new(Encoding::UTF_8, utf8_confidence(bytes)) if valid_utf8?(bytes)
+          return DetectionResult.new(Encoding::US_ASCII, 0.9) if ascii_only?(bytes)
 
-          Encoding::BINARY
+          codepage_result = detect_windows_codepage(bytes)
+          return codepage_result if codepage_result
+
+          return DetectionResult.new(Encoding::ISO_8859_1, 0.7) if latin1_heuristic?(bytes)
+
+          DetectionResult.new(Encoding::BINARY, 0.5)
         end
 
         # Check whether the string starts with a known BOM.
@@ -51,6 +76,32 @@ module Philiprehberger
 
         private
 
+        # Detect BOM and return a DetectionResult with confidence 1.0.
+        #
+        # @param bytes [String] binary string
+        # @return [DetectionResult, nil]
+        def detect_bom_with_confidence(bytes)
+          BOMS.each do |bom, encoding|
+            return DetectionResult.new(encoding, 1.0) if bytes.start_with?(bom)
+          end
+          nil
+        end
+
+        # Calculate UTF-8 confidence based on the ratio of multibyte sequences.
+        #
+        # @param bytes [String] binary string
+        # @return [Float] confidence between 0.8 and 0.9
+        def utf8_confidence(bytes)
+          total = bytes.bytesize.to_f
+          return 0.9 if total.zero?
+
+          high_bytes = bytes.each_byte.count { |b| b >= 128 }
+          ratio = high_bytes / total
+
+          # More multibyte chars = higher confidence it's genuinely UTF-8
+          ratio > 0.1 ? 0.9 : 0.85
+        end
+
         # @param bytes [String] binary string
         # @return [Boolean]
         def valid_utf8?(bytes)
@@ -64,6 +115,38 @@ module Philiprehberger
           bytes.each_byte.all? { |b| b < 128 }
         end
 
+        # Detect Windows codepages by checking for bytes in the 0x80-0x9F range.
+        #
+        # @param bytes [String] binary string
+        # @return [DetectionResult, nil]
+        def detect_windows_codepage(bytes)
+          high_control = bytes.each_byte.grep(0x80..0x9F)
+          return nil if high_control.empty?
+
+          # Check for CP1251 (Cyrillic): high ratio of bytes in 0xC0-0xFF
+          cyrillic_count = bytes.each_byte.count { |b| CP1251_RANGE.cover?(b) }
+          total_high = bytes.each_byte.count { |b| b >= 0x80 }
+
+          if total_high.positive? && (cyrillic_count.to_f / total_high) > 0.6
+            return DetectionResult.new(Encoding::Windows_1251, 0.65)
+          end
+
+          # Check for CP1250 (Central European): presence of specific marker bytes
+          cp1250_markers = high_control.count { |b| CP1250_MARKERS.include?(b) }
+          if cp1250_markers >= 2
+            return DetectionResult.new(Encoding::Windows_1250, 0.6)
+          end
+
+          # Default to CP1252 (Western European) if bytes in 0x80-0x9F are present
+          cp1252_count = high_control.count { |b| CP1252_SPECIFIC.include?(b) }
+          if cp1252_count.positive?
+            confidence = cp1252_count > 3 ? 0.7 : 0.6
+            return DetectionResult.new(Encoding::Windows_1252, confidence)
+          end
+
+          nil
+        end
+
         # Simple heuristic: if every byte is in the ISO-8859-1 printable range
         # (0x20..0x7E or 0xA0..0xFF) or is a common control character, treat as Latin-1.
         #

data/lib/philiprehberger/encoding_kit/version.rb

@@ -2,6 +2,6 @@
 
 module Philiprehberger
   module EncodingKit
-    VERSION = '0.1.1'
+    VERSION = '0.2.0'
   end
 end

data/lib/philiprehberger/encoding_kit.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require_relative 'encoding_kit/version'
+require_relative 'encoding_kit/detection_result'
 require_relative 'encoding_kit/detector'
 require_relative 'encoding_kit/converter'
 
@@ -12,13 +13,79 @@ module Philiprehberger
     BOMS = Detector::BOMS
 
     # Detect the encoding of a string via BOM and heuristics.
+    # Returns a DetectionResult that delegates to the underlying Encoding,
+    # so it can be compared directly (e.g., result == Encoding::UTF_8)
+    # while also providing a confidence score via result.confidence.
     #
     # @param string [String] the input string
-    # @return [Encoding] the detected encoding
+    # @return [DetectionResult] the detected encoding with confidence score
     def self.detect(string)
       Detector.call(string)
     end
 
+    # Detect encoding from an IO stream by reading a sample of bytes.
+    # The IO position is restored after reading (if the IO supports seek).
+    #
+    # @param io [IO, StringIO] the IO object to read from
+    # @param sample_size [Integer] number of bytes to sample (default: 4096)
+    # @return [DetectionResult] the detected encoding with confidence score
+    def self.detect_stream(io, sample_size: 4096)
+      original_pos = io.respond_to?(:pos) ? io.pos : nil
+      sample = io.read(sample_size)
+
+      if original_pos && io.respond_to?(:seek)
+        io.seek(original_pos)
+      end
+
+      return DetectionResult.new(Encoding::BINARY, 0.5) if sample.nil? || sample.empty?
+
+      Detector.call(sample)
+    end
+
+    # Analyze a string and return detailed byte distribution statistics
+    # along with encoding candidates ranked by confidence.
+    #
+    # @param string [String] the input string
+    # @return [Hash] analysis results with keys :encoding, :confidence,
+    #   :printable_ratio, :ascii_ratio, :high_bytes, :candidates
+    def self.analyze(string)
+      bytes = string.b
+      total = bytes.bytesize.to_f
+
+      if total.zero?
+        return {
+          encoding: Encoding::BINARY,
+          confidence: 0.5,
+          printable_ratio: 0.0,
+          ascii_ratio: 0.0,
+          high_bytes: 0,
+          candidates: [{ encoding: Encoding::BINARY, confidence: 0.5 }]
+        }
+      end
+
+      ascii_count = 0
+      printable_count = 0
+      high_byte_count = 0
+
+      bytes.each_byte do |b|
+        ascii_count += 1 if b < 128
+        printable_count += 1 if (0x20..0x7E).cover?(b) || b == 0x09 || b == 0x0A || b == 0x0D
+        high_byte_count += 1 if b >= 128
+      end
+
+      primary = Detector.call(bytes)
+      candidates = build_candidates(bytes, primary)
+
+      {
+        encoding: primary.encoding,
+        confidence: primary.confidence,
+        printable_ratio: (printable_count / total).round(4),
+        ascii_ratio: (ascii_count / total).round(4),
+        high_bytes: high_byte_count,
+        candidates: candidates
+      }
+    end
+
     # Convert a string to UTF-8, auto-detecting source encoding if not specified.
     #
     # @param string [String] the input string
@@ -61,6 +128,23 @@ module Philiprehberger
       Converter.convert(string, from: from, to: to)
     end
 
+    # Transcode a string to the target encoding, auto-detecting the source.
+    # Simpler API for the most common conversion pattern.
+    #
+    # @param string [String] the input string
+    # @param to [String, Encoding] target encoding (default: UTF-8)
+    # @param fallback [Symbol] fallback strategy (:replace or :raise)
+    # @param replace [String] replacement character for invalid bytes
+    # @return [String] the transcoded string
+    # @raise [EncodingKit::Error] on conversion failure when fallback is :raise
+    def self.transcode(string, to: Encoding::UTF_8, fallback: :replace, replace: '?')
+      detected = Detector.call(string)
+      source = detected.encoding
+      target = to.is_a?(Encoding) ? to : Encoding.find(to.to_s)
+
+      Converter.convert(string, from: source, to: target, fallback: fallback, replace: replace)
+    end
+
     # Remove a byte order mark from the beginning of a string.
     #
     # @param string [String] the input string
@@ -84,5 +168,41 @@ module Philiprehberger
       bytes = string.b
       BOMS.any? { |bom, _encoding| bytes.start_with?(bom) }
     end
+
+    # Build a list of encoding candidates with confidence scores.
+    #
+    # @param bytes [String] binary string
+    # @param primary [DetectionResult] the primary detection result
+    # @return [Array<Hash>] candidates sorted by confidence (descending)
+    private_class_method def self.build_candidates(bytes, primary)
+      candidates = [{ encoding: primary.encoding, confidence: primary.confidence }]
+
+      # Check UTF-8 validity as a candidate
+      utf8_dup = bytes.dup.force_encoding(Encoding::UTF_8)
+      if utf8_dup.valid_encoding? && primary.encoding != Encoding::UTF_8
+        candidates << { encoding: Encoding::UTF_8, confidence: 0.6 }
+      end
+
+      # Check ASCII as a candidate
+      if bytes.each_byte.all? { |b| b < 128 } && primary.encoding != Encoding::US_ASCII
+        candidates << { encoding: Encoding::US_ASCII, confidence: 0.5 }
+      end
+
+      # Always consider Latin-1 for high-byte content
+      high_bytes = bytes.each_byte.any? { |b| b >= 128 }
+      if high_bytes && primary.encoding != Encoding::ISO_8859_1
+        candidates << { encoding: Encoding::ISO_8859_1, confidence: 0.5 }
+      end
+
+      # Consider Windows codepages for high-byte content
+      if high_bytes
+        has_control_high = bytes.each_byte.any? { |b| (0x80..0x9F).cover?(b) }
+        if has_control_high && primary.encoding != Encoding::Windows_1252
+          candidates << { encoding: Encoding::Windows_1252, confidence: 0.5 }
+        end
+      end
+
+      candidates.sort_by { |c| -c[:confidence] }
+    end
   end
 end

metadata

@@ -1,17 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: philiprehberger-encoding_kit
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Philip Rehberger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-03-27 00:00:00.000000000 Z
+date: 2026-03-29 00:00:00.000000000 Z
 dependencies: []
-description: Detect encoding from BOM and heuristics, convert between encodings, normalize
-  to UTF-8, and strip byte order marks. Zero dependencies.
+description: Detect encoding from BOM and heuristics with confidence scores, convert
+  between encodings, normalize to UTF-8, analyze byte distributions, and handle Windows
+  codepages. Zero dependencies.
 email:
 - me@philiprehberger.com
 executables: []
@@ -23,6 +24,7 @@ files:
 - README.md
 - lib/philiprehberger/encoding_kit.rb
 - lib/philiprehberger/encoding_kit/converter.rb
+- lib/philiprehberger/encoding_kit/detection_result.rb
 - lib/philiprehberger/encoding_kit/detector.rb
 - lib/philiprehberger/encoding_kit/version.rb
 homepage: https://github.com/philiprehberger/rb-encoding-kit