philiprehberger-encoding_kit 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3e69668037179f14b92560b58c816a29a14134560bd32568775fd321325b4644
-  data.tar.gz: 3ad9997b697ca6cecca1d8e63955512eb860a86c48007a5138777167da9c4d13
+  metadata.gz: 47de974b9f87b11740744bced13177a6afe17de3ac74a589246b67604241085c
+  data.tar.gz: 3ee29c6b81b51166858bb9e051ae5652f2da84d242f80c8baa6ba45017ecbaa8
 SHA512:
-  metadata.gz: af626ca49ad283a08574162ed45b81fabdccf7aca6d978d78d9367df150234e28d7cd563a1c212145c3a399a7b431b65cd1508fbba67a784517344b124a85a38
-  data.tar.gz: ffd8620298177f0a689411d49bdadbcc61c0a93c0fb0c5afc6cd9e5f72ef77f627ec14aea5819ca898f4aeb774cbdef02957c1777d640712cab360c7eb6622e6
+  metadata.gz: ba8d01eda47ece58ac39d5c494fa82a5a4fa761087cf7c97da6fda3188b1e060afe50dc90e1228a0dfd3a8ab21384255ba862d027fee98407d33ebfd5f9466ca
+  data.tar.gz: 2b5e70cb2767541713c59733e858a6b5f751bd838df739811308e7773a3383aea0955bcd24d161921fec1c1526b92e60b9e0734bafeaed3713f7f379ade00ece

data/CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.6.0] - 2026-05-20
+
+### Added
+- `strip_bom:` option on `EncodingKit.to_utf8` and `EncodingKit.read_as_utf8` to drop a leading UTF BOM after transcoding
+- Card image reference in the README for registry-side rendering
+
 ## [0.5.0] - 2026-04-30
 
 ### Added

data/README.md

@@ -4,6 +4,8 @@
 [![Gem Version](https://badge.fury.io/rb/philiprehberger-encoding_kit.svg)](https://rubygems.org/gems/philiprehberger-encoding_kit)
 [![Last updated](https://img.shields.io/github/last-commit/philiprehberger/rb-encoding-kit)](https://github.com/philiprehberger/rb-encoding-kit/commits/main)
 
+![philiprehberger-encoding_kit](https://raw.githubusercontent.com/philiprehberger/rb-encoding-kit/main/package-card.webp)
+
 Character encoding detection, conversion, and normalization
 
 ## Requirements
@@ -103,6 +105,10 @@ utf8 = Philiprehberger::EncodingKit.to_utf8(raw_bytes)
 
 # Specify source encoding
 utf8 = Philiprehberger::EncodingKit.to_utf8(latin1_string, from: Encoding::ISO_8859_1)
+
+# Strip a leading BOM after transcoding
+clean = Philiprehberger::EncodingKit.to_utf8("\xEF\xBB\xBFhello".b, strip_bom: true)
+# => "hello"
 ```
 
 ### Normalize
@@ -195,7 +201,7 @@ Philiprehberger::EncodingKit.valid?("hello", encoding: Encoding::US_ASCII)  # =>
 | `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.to_utf8(string, from: nil, strip_bom: false)` | Convert to UTF-8, auto-detect source if `from` is nil; pass `strip_bom: true` to drop a leading UTF BOM |
 | `EncodingKit.normalize(string)` | Force to valid UTF-8, replacing bad bytes with U+FFFD |
 | `EncodingKit.scrub(string)` | Force to valid UTF-8 by removing invalid bytes entirely |
 | `EncodingKit.normalize_line_endings(string, to: :lf)` | Convert mixed CRLF/CR/LF to a single canonical form (`:lf`, `:crlf`, `:cr`) |
@@ -204,7 +210,7 @@ Philiprehberger::EncodingKit.valid?("hello", encoding: Encoding::US_ASCII)  # =>
 | `EncodingKit.strip_bom(string)` | Remove byte order mark if present |
 | `EncodingKit.bom?(string)` | Check if string starts with a BOM |
 | `EncodingKit.detect_file(path, sample_size: 4096)` | Detect encoding of a file by reading a byte sample |
-| `EncodingKit.read_as_utf8(path, from: nil)` | Read a file and return its content as UTF-8 |
+| `EncodingKit.read_as_utf8(path, from: nil, strip_bom: false)` | Read a file and return its content as UTF-8; pass `strip_bom: true` to drop a leading UTF BOM |
 | `EncodingKit.file_valid?(path, encoding: nil)` | Check if a file's content is valid in the given encoding |
 | `EncodingKit.guess_from_filename(path)` | Guess `Encoding` from filename suffixes (e.g. `.utf8`, `.latin1`), `nil` if unknown |
 

data/lib/philiprehberger/encoding_kit/converter.rb

@@ -33,12 +33,14 @@ module Philiprehberger
         #
         # @param string [String] the input string
         # @param from [String, Encoding, nil] source encoding (auto-detect if nil)
+        # @param strip_bom [Boolean] remove any leading UTF BOM from the result (default: false)
         # @return [String] UTF-8 encoded string
-        def to_utf8(string, from: nil)
+        def to_utf8(string, from: nil, strip_bom: false)
           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")
+          encoded = str.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: "\uFFFD")
+          strip_bom ? encoded.delete_prefix("\uFEFF") : encoded
         end
 
         # Force a string to valid UTF-8 by replacing invalid and undefined bytes.

data/lib/philiprehberger/encoding_kit/version.rb

@@ -2,6 +2,6 @@
 
 module Philiprehberger
   module EncodingKit
-    VERSION = '0.5.0'
+    VERSION = '0.6.0'
   end
 end

data/lib/philiprehberger/encoding_kit.rb

@@ -90,9 +90,10 @@ module Philiprehberger
     #
     # @param string [String] the input string
     # @param from [String, Encoding, nil] source encoding (auto-detect if nil)
+    # @param strip_bom [Boolean] remove any leading UTF BOM from the result (default: false)
     # @return [String] UTF-8 encoded string
-    def self.to_utf8(string, from: nil)
-      Converter.to_utf8(string, from: from)
+    def self.to_utf8(string, from: nil, strip_bom: false)
+      Converter.to_utf8(string, from: from, strip_bom: strip_bom)
     end
 
     # Normalize a string to valid UTF-8, replacing invalid/undefined bytes
@@ -210,10 +211,11 @@ module Philiprehberger
     #
     # @param path [String] path to the file
     # @param from [String, Encoding, nil] source encoding (auto-detect if nil)
+    # @param strip_bom [Boolean] remove any leading UTF BOM from the result (default: false)
     # @return [String] UTF-8 encoded file content
-    def self.read_as_utf8(path, from: nil)
+    def self.read_as_utf8(path, from: nil, strip_bom: false)
       raw = File.binread(path)
-      to_utf8(raw, from: from)
+      to_utf8(raw, from: from, strip_bom: strip_bom)
     end
 
     # Check if a file's content is valid in the detected or specified encoding.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: philiprehberger-encoding_kit
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Philip Rehberger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-05-01 00:00:00.000000000 Z
+date: 2026-05-20 00:00:00.000000000 Z
 dependencies: []
 description: Detect encoding from BOM and heuristics with confidence scores, convert
   between encodings, normalize to UTF-8, analyze byte distributions, and handle Windows