smstools 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7df349a1fd0872910cc9f6d2c23992d33807419968cbc9d68547549ef16a18bd
-  data.tar.gz: a30dd9cbb8550e475a322317b0cecdcb67c13a09f95449bf392c67d8200eb11c
+  metadata.gz: f2cecee4608c47f5abf1cf0a980b3a3a646e358d50a72e6b0f1931f554f86c5f
+  data.tar.gz: 46eae0938780419f4672581f4b1105a8d51cc4fe7f6150b2e44fdc3c00f16c6e
 SHA512:
-  metadata.gz: edd17e186943ec7b89941e2eaba41279fadc39a27ee987cdb0efc3d4f8f4cbac85bb31a50afbe6d9df94fe7fd9f4498fe561861d9f60b97dd0bd39c49ed19ec8
-  data.tar.gz: b197d9070437eef8bf732134be1a9b3fcedcf71f71f95e0057d1ae214bde4c1b8d2f00769e58104df02acf776df71cf123bb34ead1d4a828c867a2ff1aae639c
+  metadata.gz: 6f40d959431dc1185a989b179c91858363978b5200bba7504e499b214ba8b1493c859eebb3308b343ac8000ec747db89ccfbc664692721315bb68c41f96000a0
+  data.tar.gz: 7670ac023de1612cd5e4573ad4879526e5f45e38c871416cef3466e4bbee6d1740d0b2ae760b907d57811f913670862e2907b3ed3c8f268b876085195bed2a61

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.2.2 (20 Jan 2021)
+
+* #9 Fix the way some complex Unicode characters (like composite emojis) are counted. Thanks to @bryanrite for the neat implementation. Note the fix could be **potentially backwards-incompatible** if you were relying on the incorrect behaviour previously. Technically it's still a bug fix.
+
 ## 0.2.1 (18 Aug 2020)
 
 * #7 Introduce `SmsTools.use_ascii_encoding` option (defaults to `true` for backwards-compatibility) that allows disabling the `:ascii` workaround encoding. See #6 and #7 for details. Thanks @kingsley-wang.

data/README.md

@@ -159,7 +159,7 @@ Check out the source code of the class to find out more.
 ### Client-side code
 
 If you're using the gem in Rails 3.1 or newer, you can gain access to the `SmsTools.Message` class.
-It's interface is similar to the one of `SmsTools::EncodingDetection`. Here is an example in
+Its interface is similar to the one of `SmsTools::EncodingDetection`. Here is an example in
 CoffeeScript:
 
 ```coffeescript
@@ -194,3 +194,9 @@ assumed. It might be possible to use it in other setups as well, but you're on y
 6. Push to the branch (`git push origin my-new-feature`)
 7. Send a pull request.
 
+## Publishing a new version
+
+1. Pick a version number according to Semantic Versioning.
+2. Update `CHANGELOG.md`, `version.rb` and potentially this readme.
+3. Commit the changes, tag them with `vX.Y.Z` (e.g. `v0.2.1`) and push all with `git push --tags`.
+4. Build and publish the new version of the gem with `gem build smstools.gemspec && gem push *.gem`.

data/lib/sms_tools.rb

@@ -1,6 +1,7 @@
 require 'sms_tools/version'
 require 'sms_tools/encoding_detection'
 require 'sms_tools/gsm_encoding'
+require 'sms_tools/unicode_encoding'
 
 if defined?(::Rails) and ::Rails.version >= '3.1'
   require 'sms_tools/rails/engine'

data/lib/sms_tools/encoding_detection.rb

@@ -68,8 +68,12 @@ module SmsTools
     # message, taking into account any double-space symbols in the GSM 03.38
     # encoding.
     def length
-      length = text.length
-      length += text.chars.count { |char| GsmEncoding.double_byte?(char) } if gsm?
+      if unicode?
+        length = text.chars.sum { |char| UnicodeEncoding.character_count(char) }
+      else
+        length = text.length
+        length += text.chars.count { |char| GsmEncoding.double_byte?(char) } if gsm?
+      end
 
       length
     end

data/lib/sms_tools/unicode_encoding.rb

@@ -0,0 +1,15 @@
+module SmsTools
+  module UnicodeEncoding
+    extend self
+
+    BASIC_PLANE = 0x0000..0xFFFF
+
+    # UCS-2/UTF-16 is used for unicode text messaging. UCS-2/UTF-16 represents characters in minimum
+    # 2-bytes, any characters in the basic plane are represented with 2-bytes, so each codepoint
+    # within the Basic Plane counts as a single character. Any codepoint outside the Basic Plane is
+    # encoded using 4-bytes and therefore counts as 2 characters in a text message.
+    def character_count(char)
+      char.each_codepoint.sum { |codepoint| BASIC_PLANE.include?(codepoint) ? 1 : 2 }
+    end
+  end
+end

data/lib/sms_tools/version.rb

@@ -1,3 +1,3 @@
 module SmsTools
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 end

data/spec/sms_tools/encoding_detection_spec.rb

@@ -118,6 +118,14 @@ describe SmsTools::EncodingDetection do
       detection_for('Уникод: Σ: €').length.must_equal 12
     end
 
+    it "counts ZWJ unicode characters correctly" do
+      detection_for('😴').length.must_equal 2
+      detection_for('🛌🏽').length.must_equal 4
+      detection_for('🤾🏽‍♀️').length.must_equal 7
+      detection_for('🇵🇵').length.must_equal 4
+      detection_for('👩‍❤️‍👩').length.must_equal 8
+    end
+
     describe 'with SmsTools.use_gsm_encoding = false' do
       before do
         SmsTools.use_gsm_encoding = false
@@ -166,11 +174,16 @@ describe SmsTools::EncodingDetection do
       concatenated_parts_for length: 135, encoding: :unicode, must_be: 3
     end
 
-    it "counts parts for actual GSM-encoded and Unicode messages" do
+    it "counts parts for actual GSM-encoded messages" do
       detection_for('').concatenated_parts.must_equal 1
-      detection_for('Я').concatenated_parts.must_equal 1
       detection_for('Σ' * 160).concatenated_parts.must_equal 1
       detection_for('Σ' * 159 + '~').concatenated_parts.must_equal 2
+    end
+
+    it "counts parts for actual Unicode-encoded messages" do
+      detection_for('Я').concatenated_parts.must_equal 1
+      detection_for('Я' * 70).concatenated_parts.must_equal 1
+      detection_for('Я' * 71).concatenated_parts.must_equal 2
       detection_for('Я' * 133 + '~').concatenated_parts.must_equal 2
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smstools
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Dimitar Dimitrov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-08-18 00:00:00.000000000 Z
+date: 2021-01-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -86,6 +86,7 @@ files:
 - lib/sms_tools/encoding_detection.rb
 - lib/sms_tools/gsm_encoding.rb
 - lib/sms_tools/rails/engine.rb
+- lib/sms_tools/unicode_encoding.rb
 - lib/sms_tools/version.rb
 - lib/smstools.rb
 - smstools.gemspec