philiprehberger-string_kit 0.2.1 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ffce546205ecc50ec2bcdadc79aa6c62808e4501144ba4379a62c1baacd35e43
-  data.tar.gz: 588a32c97d8bca9e364ba44e96cd7343641f43bc7dc31884f833914953c667b6
+  metadata.gz: f38ef0d79a14fb2d1ee763b52cd9e01ade47d478944f766676f6e32ac1d89eda
+  data.tar.gz: b7f0c00dee4c9fd5d7287a16b41b9e7bd5f701068d7c2d52a878a6991cc261ef
 SHA512:
-  metadata.gz: f58dd4dd8318d552374e7280f29a8b2864d8749dac9160ef22af88dbf3a58b7e4833fb14334dbb4b9ea82d4403302189b3d9188914c0bb787baf8d2e54c62710
-  data.tar.gz: 6af93996e58d274244114a6b82f804bb1e43ec9016b7a9e43c126ec3fff549a4e803242fc809f446eec61608286f1a8a838aadbc6475a6b45b413f42a53227eb
+  metadata.gz: ddb00275a54597ae4a4b0b9265acdf50360ce8b537787d7c7fef89705dbc9173e73dfb67ded292672151ddde4dac6798bb027d0806b6fdf270df68b52489f715
+  data.tar.gz: 9652f8595c23648bfe3a42b633e04f758c16d49db5c912237b669d80e8053a28db67ddf7b7758cf08d32be4e0a4ef7a858dcf9ea15b0439b9207223b091dca0a

data/CHANGELOG.md

@@ -7,6 +7,23 @@ and this gem adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
+## [0.4.0] - 2026-05-30
+
+### Added
+- `StringKit.mask(str, show_first:, show_last:, mask_char:)` for partial string obfuscation
+- `StringKit.between(str, left, right)` to extract text between delimiters
+- `StringKit.truncate_words(str, max_words, omission:)` for word-aware truncation
+
+### Fixed
+- README now includes the standard package card image after the badges
+
+## [0.3.0] - 2026-04-25
+
+### Added
+- `StringKit.strip_zero_width` removes zero-width and invisible Unicode characters
+- `StringKit.levenshtein` returns Levenshtein edit distance between two strings
+- `StringKit.similarity` returns a 0.0–1.0 similarity score derived from Levenshtein distance
+
 ## [0.2.1] - 2026-04-15
 
 ### Fixed

data/README.md

@@ -4,6 +4,8 @@
 [![Gem Version](https://badge.fury.io/rb/philiprehberger-string_kit.svg)](https://rubygems.org/gems/philiprehberger-string_kit)
 [![Last updated](https://img.shields.io/github/last-commit/philiprehberger/rb-string-kit)](https://github.com/philiprehberger/rb-string-kit/commits/main)
 
+![philiprehberger-string_kit](https://raw.githubusercontent.com/philiprehberger/rb-string-kit/main/package-card.webp)
+
 Comprehensive string utilities without ActiveSupport dependency
 
 ## Requirements
@@ -75,6 +77,46 @@ Philiprehberger::StringKit.indent("hello\nworld", 2)           # => "  hello\n
 Philiprehberger::StringKit.dedent("    hello\n    world")      # => "hello\nworld"
 ```
 
+### Zero-Width Characters
+
+```ruby
+require "philiprehberger/string_kit"
+
+raw = "hello​world"
+Philiprehberger::StringKit.strip_zero_width(raw)  # => "helloworld"
+```
+
+### String Similarity
+
+```ruby
+Philiprehberger::StringKit.levenshtein('kitten', 'sitting')  # => 3
+Philiprehberger::StringKit.similarity('kitten', 'sitting')   # => ~0.571
+```
+
+### Masking
+
+```ruby
+Philiprehberger::StringKit.mask('4242424242424242', show_last: 4)                  # => "************4242"
+Philiprehberger::StringKit.mask('alice@example.com', show_first: 2, show_last: 4)  # => "al***********.com"
+Philiprehberger::StringKit.mask('password123', show_last: 3, mask_char: '#')       # => "########123"
+```
+
+### Between Delimiters
+
+```ruby
+Philiprehberger::StringKit.between('hello [world] there', '[', ']')  # => "world"
+Philiprehberger::StringKit.between('a(b)c(d)', '(', ')')             # => "b"
+Philiprehberger::StringKit.between('no brackets here', '[', ']')     # => nil
+```
+
+### Word-Aware Truncation
+
+```ruby
+Philiprehberger::StringKit.truncate_words('The quick brown fox jumps', 3)                  # => "The quick brown…"
+Philiprehberger::StringKit.truncate_words('Two words', 5)                                  # => "Two words"
+Philiprehberger::StringKit.truncate_words('a b c d e', 2, omission: '...')                 # => "a b..."
+```
+
 ## API
 
 | Method | Description |
@@ -99,6 +141,12 @@ Philiprehberger::StringKit.dedent("    hello\n    world")      # => "hello\nworl
 | `StringKit.squeeze(str)` | Remove consecutive duplicate characters |
 | `StringKit.indent(str, n)` | Indent each line by n spaces |
 | `StringKit.dedent(str)` | Remove common leading whitespace |
+| `.strip_zero_width(str)` | Remove zero-width and invisible Unicode characters |
+| `.levenshtein(a, b)` | Edit distance between two strings |
+| `.similarity(a, b)` | 0.0–1.0 similarity derived from Levenshtein distance |
+| `StringKit.mask(str, show_first:, show_last:, mask_char:)` | Mask the middle of a string for partial obfuscation |
+| `StringKit.between(str, left, right)` | Extract text between the first occurrence of two delimiters |
+| `StringKit.truncate_words(str, max_words, omission:)` | Truncate to the first `max_words` words with an omission marker |
 
 ## Development
 

data/lib/philiprehberger/string_kit/version.rb

@@ -2,6 +2,6 @@
 
 module Philiprehberger
   module StringKit
-    VERSION = '0.2.1'
+    VERSION = '0.4.0'
   end
 end

data/lib/philiprehberger/string_kit.rb

@@ -278,6 +278,109 @@ module Philiprehberger
       str.swapcase
     end
 
+    # Removes zero-width and invisible Unicode characters from `str`.
+    # Useful when ingesting content copied from web pages.
+    #
+    # @param str [String]
+    # @return [String]
+    def self.strip_zero_width(str)
+      str.gsub(/[​‌‍⁠؜]/, '')
+    end
+
+    # Levenshtein edit distance between `a` and `b`.
+    #
+    # @param a [String]
+    # @param b [String]
+    # @return [Integer]
+    def self.levenshtein(a, b)
+      return b.length if a.empty?
+      return a.length if b.empty?
+
+      prev = (0..b.length).to_a
+      curr = Array.new(b.length + 1)
+
+      a.each_char.with_index do |ac, i|
+        curr[0] = i + 1
+        b.each_char.with_index do |bc, j|
+          cost = ac == bc ? 0 : 1
+          curr[j + 1] = [curr[j] + 1, prev[j + 1] + 1, prev[j] + cost].min
+        end
+        prev = curr.dup
+      end
+
+      prev[b.length]
+    end
+
+    # Similarity score between 0.0 and 1.0 derived from Levenshtein distance.
+    # Returns 1.0 for identical strings, 1.0 for two empty strings, and
+    # `1 - distance / max_length` otherwise.
+    #
+    # @param a [String]
+    # @param b [String]
+    # @return [Float]
+    def self.similarity(a, b)
+      max = [a.length, b.length].max
+      return 1.0 if max.zero?
+
+      1.0 - (levenshtein(a, b).to_f / max)
+    end
+
+    # Mask a string by replacing its middle portion with `mask_char`,
+    # leaving `show_first` characters at the start and `show_last` at the end.
+    # Returns `str` unchanged when there is not enough room to mask at least
+    # two characters in the middle.
+    #
+    # @param str [String]
+    # @param show_first [Integer] number of characters to leave visible at the start
+    # @param show_last [Integer] number of characters to leave visible at the end
+    # @param mask_char [String] character used to mask the hidden portion (default: '*')
+    # @return [String]
+    def self.mask(str, show_first: 0, show_last: 0, mask_char: '*')
+      validate!(str)
+      return str if show_first + show_last >= str.length - 1
+
+      masked_length = str.length - show_first - show_last
+      str[0, show_first] + (mask_char * masked_length) + str[str.length - show_last, show_last].to_s
+    end
+
+    # Returns the substring strictly between the first occurrence of `left`
+    # and the first occurrence of `right` after `left`. Returns `nil` when
+    # either delimiter is missing.
+    #
+    # @param str [String]
+    # @param left [String]
+    # @param right [String]
+    # @return [String, nil]
+    def self.between(str, left, right)
+      validate!(str)
+      left_index = str.index(left)
+      return nil if left_index.nil?
+
+      start_pos = left_index + left.length
+      right_index = str.index(right, start_pos)
+      return nil if right_index.nil?
+
+      str[start_pos...right_index]
+    end
+
+    # Truncate a string to the first `max_words` words. When truncation
+    # happens, append `omission` to the result. The string is unchanged
+    # when the word count is less than or equal to `max_words`.
+    #
+    # @param str [String]
+    # @param max_words [Integer] maximum number of words to keep (must be positive)
+    # @param omission [String] string appended when truncation occurs (default: '…')
+    # @return [String]
+    def self.truncate_words(str, max_words, omission: '…')
+      validate!(str)
+      raise Error, 'max_words must be a positive Integer' unless max_words.is_a?(Integer) && max_words.positive?
+
+      words = str.split(/\s+/).reject(&:empty?)
+      return str if words.length <= max_words
+
+      "#{words.first(max_words).join(' ')}#{omission}"
+    end
+
     class << self
       private
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: philiprehberger-string_kit
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.4.0
 platform: ruby
 authors:
 - Philip Rehberger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-15 00:00:00.000000000 Z
+date: 2026-05-31 00:00:00.000000000 Z
 dependencies: []
 description: String case conversion, slug generation, transliteration, padding, HTML
   stripping, whitespace normalization, word counting, reading time estimation, excerpt