rack-url-canonicalizer 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 416209bee17b49fe10d7cad5c88885750a91006ab9692e37ecf115655303fa3c
-  data.tar.gz: 354611a1a288bfbeb65c504cf5f910b483d50028b4ab8ae7b52f0d5fc68672b2
+  metadata.gz: 0cc0592b66830e51b4f791b9b7c9503fa98ca0c20f25fb4fe92ae9379af404ed
+  data.tar.gz: 572708d83ec547c190e93d78dd900db96af8de7cca0c3760122a132fef8282c6
 SHA512:
-  metadata.gz: babc20af66280225ed938bd8f19ee0ce412552b4d39dd79d62101476c3e0526c998103f3cbdde53301057a4268f41b3bde05e6390011ad70d74ec1dd484dc902
-  data.tar.gz: a8717237099c617244a9136e5b28c7a28b3452b6a281d0f38522c3b374c6adb9b8b96dd299870ffc639c36d24b1e35b8359b1e506b8369ce5f61418305370230
+  metadata.gz: 1e1b05c26326297a9b6cd425433face278ebeae8d9ca9deddf34f637d092b3f8875d64591cf5b59a0265187933cfcbe88822ef5c0d52a7c30f08b6010c19f0d8
+  data.tar.gz: ffc8f3651b5a9bd64a50365dd86e9a5f9129903bfd4e998d44da3a3a8a024f30a60673bfd4e6aea365954cb12299985de08c95bf12df3e0daa04ad9c59c6989e

data/README.md

@@ -6,7 +6,8 @@ It automatically canonicalizes incoming request URLs to prevent search engine **
 1. Stripping `www.` or enforcing `www.` sub-domain prefix.
 2. Collapsing duplicate slashes (`//path//to` ➔ `/path/to`).
 3. Stripping trailing slashes from paths (`/path/` ➔ `/path`).
-4. Validating `locale` GET query parameters against an allowed list and stripping invalid locales.
+4. Canonicalizing URL paths to lowercase (`/About-Us` ➔ `/about-us`), globally or selectively.
+5. Validating `locale` GET query parameters against an allowed list and stripping invalid locales.
 
 ---
 
@@ -16,7 +17,7 @@ Search engines (Google, Yandex, Bing) treat every unique URL string as a distinc
 
 This gem is essential when:
 - **Protecting SEO & Domain Authority**: You need to prevent index cannibalization caused by variations like `example.com/item` vs. `www.example.com/item`, `example.com/item/`, or `example.com//item`.
-- **Enforcing Single Canonical URLs**: You want incoming traffic from user typos or legacy backlinks to be redirected with an HTTP 301 (Moved Permanently) status to a single canonical address before reaching your application logic.
+- **Enforcing Single Canonical URLs**: You want incoming traffic from user typos, mobile keyboard auto-capitalization, or legacy backlinks to be redirected with an HTTP 301 (Moved Permanently) status to a single canonical address before reaching your application logic.
 - **Handling Multi-Locale Query Parameters**: Your app supports localization (e.g. `?locale=en`) and you want to sanitize or discard invalid/malformed locale parameters (e.g. `?locale=xyz`) that would otherwise generate infinite duplicate URL variants.
 - **High-Performance Early Redirects**: You want URL normalization to happen at the lightweight Rack middleware layer—avoiding unnecessary Rails controller instantiations, routing checks, or database queries.
 - **Simplified Deployment with Kamal & Modern Stacks**: Ideal for containerized setups deployed with **Kamal**, **Thruster**, or Docker, where configuring and maintaining separate Nginx/Caddy redirect rules or complex DNS edge layers adds unnecessary overhead. This gem handles canonicalization directly inside your application stack for fast, zero-config deployments.
@@ -48,6 +49,9 @@ bundle install
 | `enforce_www` | `Boolean` | `false` | Prepends `www.` to requests lacking it (aliased as `prefer_www`). Automatically skips localhost and IP addresses. |
 | `collapse_slashes` | `Boolean` | `true` | Replaces multiple slashes `//` with `/`. |
 | `strip_trailing_slash` | `Boolean` | `true` | Removes trailing slash from path (except root `/`). |
+| `downcase_path` | `Boolean` | `false` | Converts path to lowercase (e.g. `/About-Us` ➔ `/about-us`). Query string casing is preserved. |
+| `downcase_paths` | `Array<String \| Regexp \| Proc> \| Boolean` | `nil` | Selective allowlist: only paths matching these prefixes or patterns are downcased. |
+| `downcase_exclude_paths` | `Array<String \| Regexp \| Proc>` | `[]` | Array of path prefixes, patterns, or procs to bypass from downcasing (preserves casing for tokens/IDs). |
 | `exclude_paths` | `Array<String>` | `[]` | Array of path prefixes to bypass (e.g. `%w[/api /assets]`). |
 | `exclude_hosts` | `Array<String \| Regexp \| Proc>` | `[]` | Array of hosts or patterns to bypass from host redirection. |
 | `locale_param` | `String` | `"locale"` | GET parameter key for locale. |
@@ -64,14 +68,27 @@ bundle install
 In `config/application.rb`:
 
 ```ruby
-# Strip www (default):
+# Strip www, normalize paths, and enforce lowercase:
 config.middleware.use Rack::UrlCanonicalizer,
   strip_www: true,
   collapse_slashes: true,
   strip_trailing_slash: true,
+  downcase_path: true,
   exclude_paths: %w[/api /assets /up],
   allowed_locales: -> { I18n.available_locales }
 
+# Or selective downcasing for specific marketing / content routes:
+config.middleware.use Rack::UrlCanonicalizer,
+  downcase_paths: [
+    "/about",
+    "/contribution",
+    "/pricing",
+    %r{\A/(docs|faq)/}i
+  ],
+  downcase_exclude_paths: [
+    %r{\A/invites/[A-Za-z0-9_-]+}
+  ]
+
 # Or enforce www (example.com -> www.example.com):
 config.middleware.use Rack::UrlCanonicalizer,
   enforce_www: true,
@@ -86,6 +103,7 @@ In `config.ru`:
 require "rack/url_canonicalizer"
 
 use Rack::UrlCanonicalizer,
+  downcase_path: true,
   enforce_www: true,
   exclude_paths: ["/api"]
 
@@ -100,6 +118,7 @@ Alternatively, set global defaults:
 Rack::UrlCanonicalizer.configure do |config|
   config.enforce_www = true
   config.collapse_slashes = true
+  config.downcase_path = true
   config.allowed_locales = %w[en ru es]
 end
 

data/lib/rack/url_canonicalizer/configuration.rb

@@ -5,6 +5,9 @@ module Rack
     class Configuration
       attr_accessor :collapse_slashes,
                     :strip_trailing_slash,
+                    :downcase_path,
+                    :downcase_paths,
+                    :downcase_exclude_paths,
                     :exclude_paths,
                     :exclude_hosts,
                     :locale_param,
@@ -18,6 +21,9 @@ module Rack
         @enforce_www = false
         @collapse_slashes = true
         @strip_trailing_slash = true
+        @downcase_path = false
+        @downcase_paths = nil
+        @downcase_exclude_paths = []
         @exclude_paths = []
         @exclude_hosts = []
         @locale_param = 'locale'

data/lib/rack/url_canonicalizer/version.rb

@@ -2,6 +2,6 @@
 
 module Rack
   class UrlCanonicalizer
-    VERSION = '0.2.0'
+    VERSION = '0.3.0'
   end
 end

data/lib/rack/url_canonicalizer.rb

@@ -118,9 +118,41 @@ module Rack
     def normalize_path(path)
       path = path.gsub(%r{/{2,}}, '/') if @config.collapse_slashes
       path = path.chomp('/') if @config.strip_trailing_slash && path.length > 1 && path.end_with?('/')
+      path = path.downcase if should_downcase_path?(path)
       path
     end
 
+    def should_downcase_path?(path)
+      return false if downcase_excluded?(path)
+
+      if @config.downcase_paths == true
+        true
+      elsif @config.downcase_paths
+        match_path_patterns?(@config.downcase_paths, path)
+      else
+        @config.downcase_path
+      end
+    end
+
+    def downcase_excluded?(path)
+      return false if @config.downcase_exclude_paths.nil? || @config.downcase_exclude_paths.empty?
+
+      match_path_patterns?(@config.downcase_exclude_paths, path)
+    end
+
+    def match_path_patterns?(patterns, path)
+      Array(patterns).any? do |pattern|
+        case pattern
+        when Regexp then pattern.match?(path) || pattern.match?(path.downcase)
+        when Proc then pattern.call(path)
+        else
+          prefix = pattern.to_s.downcase
+          prefix = "/#{prefix}" unless prefix.start_with?('/')
+          path.downcase.start_with?(prefix)
+        end
+      end
+    end
+
     def locale_redirect?(query_params)
       key = @config.locale_param
       return false unless key && query_params.key?(key)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rack-url-canonicalizer
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Alex Abramov
@@ -141,7 +141,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.18
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Rack middleware for URL normalization and SEO canonicalization
 test_files: []