regexp_property_values 1.5.1 → 1.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c3b4e58dbefa036bfca55b36da86baa96e1ba6c56483167279c9ce971823b8ba
-  data.tar.gz: 5e5ed54fef70679475b4abaf35abe7e65a8d28940cde6f07398378b5eedf3e03
+  metadata.gz: '0588e959f6bc0ad3ef9612a495cbd3485b079b45ed9c4a485a3bd533e3ee9c7a'
+  data.tar.gz: abf53c421d3c895e436e0a992236d1daccda73d1da15b73ca5a3f8a8b7f94724
 SHA512:
-  metadata.gz: d650720818f1e427b0cb4532e8e93cc348d7680c5a3c0c11e5cfba273802c32889567b0e2aff6e84247c98e60dc97022a47cb4987ed812a3d787bbf9ca98a3a0
-  data.tar.gz: 10232496849f607db55974e99a998fd6b9f4b2efe459e0fabe03db46ccfe9f41414f1b3028f39ba27101cc17eb0afdb32cb7326d87f262c7739222a958c7e327
+  metadata.gz: 769d89728bcf42382782b0b42d946de6af689108b0d0b6101092eacc209f2bf50787fb1290f90545a406677bfc4da270a846de8a0dab0ab5fe4f694b53d423c9
+  data.tar.gz: 982ee2f8811bf1989f3789b0a52b83c89610aa7a2d00d190e36a16d16eff2a47f2ba38881373b36ac771f3f294c235207ce460d8a26ac9aee120442a3e7fe07b

data/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [1.5.2] - 2024-05-20
+
+### Fixed
+- fixed `#matched_characters` for properties containing surrogates
+- improved speed of `#matched_codepoints`
+
 ## [1.5.1] - 2024-01-06
 
 ### Fixed

data/Gemfile

@@ -5,7 +5,7 @@ git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
 # Specify your gem's dependencies in regexp_property_values.gemspec
 gemspec
 
-gem 'character_set', '~> 1.4.0'
+gem 'character_set', '~> 1.8.0'
 gem 'rake', '~> 13.0'
 gem 'rake-compiler', '~> 1.0'
 gem 'range_compressor', '~> 1.0'

data/README.md

@@ -34,6 +34,8 @@ PV['foobar'].supported_by_current_ruby? # => false
 PV['AHex'].matched_characters # => %w[0 1 2 3 4 5 6 7 8 9 A B C ...]
 PV['AHex'].matched_codepoints # => [48, 49, 50, ...]
 PV['AHex'].matched_ranges # => [48..57, 65..70, 97..102]
+# Note: #matched_characters is slow for large properties and you
+# may not want to use it in time-critical code. It also omits surrogates.
 
 PV['foobar'].matched_ranges # => RegexpPropertyValues::Error
 ```

data/bin/console

@@ -2,6 +2,7 @@
 
 require "bundler/setup"
 require "regexp_property_values"
+require "benchmark"
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.

data/ext/regexp_property_values/regexp_property_values.c

@@ -2,11 +2,13 @@
 #include "ruby/encoding.h"
 #include "ruby/oniguruma.h" // still in recent rubies f. backwards compatibility
 
-static int prop_name_to_ctype(char *name, rb_encoding *enc)
+static int prop_name_to_ctype(VALUE arg, rb_encoding *enc)
 {
+  char *name;
   UChar *uname;
   int ctype;
 
+  name = StringValueCStr(arg);
   uname = (UChar *)name;
   ctype = ONIGENC_PROPERTY_NAME_TO_CTYPE(enc, uname, uname + strlen(name));
   if (ctype < 0)
@@ -15,13 +17,26 @@ static int prop_name_to_ctype(char *name, rb_encoding *enc)
   return ctype;
 }
 
-VALUE onig_ranges_to_rb(const OnigCodePoint *onig_ranges)
+const OnigCodePoint *get_onig_ranges(VALUE prop_name)
+{
+  int ctype;
+  const OnigCodePoint *ranges;
+  OnigCodePoint sb_out;
+  rb_encoding *enc;
+
+  enc = rb_utf8_encoding();
+  ctype = prop_name_to_ctype(prop_name, enc);
+  ONIGENC_GET_CTYPE_CODE_RANGE(enc, ctype, &sb_out, &ranges);
+  return ranges;
+}
+
+VALUE onig_ranges_to_rb_ranges(const OnigCodePoint *onig_ranges)
 {
   unsigned int range_count, i;
   VALUE result, sub_range;
 
   range_count = onig_ranges[0];
-  result = rb_ary_new2(range_count); // rb_ary_new_capa not avail. in Ruby 2.0
+  result = rb_ary_new_capa(range_count);
 
   for (i = 0; i < range_count; i++)
   {
@@ -34,24 +49,35 @@ VALUE onig_ranges_to_rb(const OnigCodePoint *onig_ranges)
   return result;
 }
 
-VALUE rb_prop_ranges(char *name)
+VALUE onig_ranges_to_rb_integers(const OnigCodePoint *onig_ranges)
 {
-  int ctype;
-  const OnigCodePoint *onig_ranges;
-  OnigCodePoint sb_out;
-  rb_encoding *enc;
-  enc = rb_utf8_encoding();
+  unsigned int range_count, i, beg, end, j;
+  VALUE result;
+
+  range_count = onig_ranges[0];
+  result = rb_ary_new();
 
-  ctype = prop_name_to_ctype(name, enc);
-  ONIGENC_GET_CTYPE_CODE_RANGE(enc, ctype, &sb_out, &onig_ranges);
-  return onig_ranges_to_rb(onig_ranges);
+  for (i = 0; i < range_count; i++)
+  {
+    beg = onig_ranges[(i * 2) + 1];
+    end = onig_ranges[(i * 2) + 2];
+    for (j = beg; j <= end; j++)
+    {
+      rb_ary_push(result, INT2FIX(j));
+    }
+  }
+
+  return result;
 }
 
 VALUE method_matched_ranges(VALUE self, VALUE arg)
 {
-  char *prop_name;
-  prop_name = StringValueCStr(arg);
-  return rb_prop_ranges(prop_name);
+  return onig_ranges_to_rb_ranges(get_onig_ranges(arg));
+}
+
+VALUE method_matched_codepoints(VALUE self, VALUE arg)
+{
+  return onig_ranges_to_rb_integers(get_onig_ranges(arg));
 }
 
 void Init_regexp_property_values()
@@ -63,4 +89,5 @@ void Init_regexp_property_values()
   VALUE module;
   module = rb_define_module("OnigRegexpPropertyHelper");
   rb_define_singleton_method(module, "matched_ranges", method_matched_ranges, 1);
+  rb_define_singleton_method(module, "matched_codepoints", method_matched_codepoints, 1);
 }

data/lib/regexp_property_values/value/ext_adapter.rb

@@ -2,11 +2,17 @@ module RegexpPropertyValues
   class Value
     module ExtAdapter
       def matched_characters
-        matched_codepoints.map { |cp| cp.chr('utf-8') }
+        acc = []
+        matched_codepoints.each do |cp|
+          acc << cp.chr('utf-8') if cp < 0xD800 || cp > 0xDFFF
+        end
+        acc
       end
 
       def matched_codepoints
-        matched_ranges.flat_map(&:to_a)
+        OnigRegexpPropertyHelper.matched_codepoints(name)
+      rescue ArgumentError
+        raise_unsupported_or_unknown_error
       end
 
       def matched_ranges

data/lib/regexp_property_values/version.rb

@@ -1,3 +1,3 @@
 module RegexpPropertyValues
-  VERSION = '1.5.1'
+  VERSION = '1.5.2'
 end

data/regexp_property_values.gemspec

@@ -22,5 +22,5 @@ Gem::Specification.new do |s|
 
   s.extensions = %w[ext/regexp_property_values/extconf.rb]
 
-  s.required_ruby_version = '>= 2.0.0'
+  s.required_ruby_version = '>= 2.1.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_property_values
 version: !ruby/object:Gem::Version
-  version: 1.5.1
+  version: 1.5.2
 platform: ruby
 authors:
 - Janosch Müller
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-01-06 00:00:00.000000000 Z
+date: 2024-05-22 00:00:00.000000000 Z
 dependencies: []
 description: This small library lets you see which property values are supported by
   the regular expression engine of the Ruby version you are running, and what they
@@ -54,14 +54,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.0.0
+      version: 2.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.0.dev
+rubygems_version: 3.5.3
 signing_key:
 specification_version: 4
 summary: Inspect property values supported by Ruby's regex engine