philiprehberger-string_kit 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ffce546205ecc50ec2bcdadc79aa6c62808e4501144ba4379a62c1baacd35e43
-  data.tar.gz: 588a32c97d8bca9e364ba44e96cd7343641f43bc7dc31884f833914953c667b6
+  metadata.gz: 4a290f7b9aa5a9534b5f0f55086b416671e860b89bd58df4dae1558e8451f489
+  data.tar.gz: e4162f06038b8da1ad5f3b67249e3c1776fe9213014c2287a305addc163a978e
 SHA512:
-  metadata.gz: f58dd4dd8318d552374e7280f29a8b2864d8749dac9160ef22af88dbf3a58b7e4833fb14334dbb4b9ea82d4403302189b3d9188914c0bb787baf8d2e54c62710
-  data.tar.gz: 6af93996e58d274244114a6b82f804bb1e43ec9016b7a9e43c126ec3fff549a4e803242fc809f446eec61608286f1a8a838aadbc6475a6b45b413f42a53227eb
+  metadata.gz: df68e8c923b8ab6693894e01068317abbb4254ab10063d5859c81dbc2e1c585160e7ec4fa94189329b25ad86ae8b6b6728fa153c990fd74537b22653796abd51
+  data.tar.gz: d41749d919b01bff185fe0bd555b65a0b7c2989e27fb9cb7d0b33cd301fdeabb1491467637eee0ac09b5eb9d29c0d4481d47c73f0a9fbadc7c2fa2e93cf2f84e

data/CHANGELOG.md

@@ -7,6 +7,13 @@ and this gem adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
+## [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

@@ -75,6 +75,22 @@ 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
+```
+
 ## API
 
 | Method | Description |
@@ -99,6 +115,9 @@ 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 |
 
 ## Development
 

data/lib/philiprehberger/string_kit/version.rb

@@ -2,6 +2,6 @@
 
 module Philiprehberger
   module StringKit
-    VERSION = '0.2.1'
+    VERSION = '0.3.0'
   end
 end

data/lib/philiprehberger/string_kit.rb

@@ -278,6 +278,53 @@ 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
+
     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: 0.3.0
 platform: ruby
 authors:
 - Philip Rehberger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-15 00:00:00.000000000 Z
+date: 2026-04-26 00:00:00.000000000 Z
 dependencies: []
 description: String case conversion, slug generation, transliteration, padding, HTML
   stripping, whitespace normalization, word counting, reading time estimation, excerpt