json_escape 0.0.0 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 67b2fb0af20b092995334983baefd17b3682e65442bbddcbaf6c21cd54fc8cad
-  data.tar.gz: 4caebb4f7840f22477fc2b57ad10c7f44eb77a015221f689375ad5fd476d4436
+  metadata.gz: 5a389e1d0a7c064c39662f24a63d9b8d1e5fd2ee8020c79da2468dbd8a546bcd
+  data.tar.gz: ca09cd472d630efee98f0a7d4b0f7f66f970b8087c92bb8f3533ceefebace942
 SHA512:
-  metadata.gz: c3056572f2465c7f75d551c3de03e34dd366482dcee6a85bcc662bfe7c97fb9650e64a4d3d8d0b950652c022e9e07869946254ef167b6c958aaa384892e29ad8
-  data.tar.gz: 8bc9c230dc6f4c43e8253b3ce44dd547d8970e680d44f4e4d9a88c20e8b07cccca9faa7a7f60e52f5751a782965d9ed3d7950944863590b0a3433bed0c5b1e1c
+  metadata.gz: 8c31ed7c66c65cabe30cb10a1ce267fb39054e39e43f57a4e7213c8ee4b97f06dc23a56e1b6492f83c94f9f9acdf0bed6f998b5c0427e1da44281cbbcdd7b5b7
+  data.tar.gz: 1ffafad8b821031c3c5c73133a9f1cf1671bf3b5d69ff0b737526755c209cc727547943887ab6c2fa931b8f7e9ddaaabb6a12a77f37757009a230e82265277e4

data/README.md

@@ -1,24 +1,14 @@
 # JsonEscape
 
-TODO: Delete this and the text below, and describe your gem
+This is a proof of concept for implementing ActiveSupport's `escape_json` in C
+(and a pure-Ruby implemntation for platforms other than CRuby).
 
-Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/json_escape`. To experiment with that code, run `bin/console` for an interactive prompt.
-
-## Installation
-
-TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG` with your gem name right after releasing it to RubyGems.org. Please do not do it earlier due to security reasons. Alternatively, replace this section with instructions to install your gem from git if you don't plan to release to RubyGems.org.
-
-Install the gem and add to the application's Gemfile by executing:
-
-    $ bundle add UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
-
-If bundler is not being used to manage dependencies, install the gem by executing:
-
-    $ gem install UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
+This is to test, benchmark, and prove it's utility. I think this should be
+upstreamed into another library.
 
 ## Usage
 
-TODO: Write usage instructions here
+Don't.
 
 ## Development
 

data/Rakefile

@@ -1,4 +1,25 @@
 # frozen_string_literal: true
 
 require "bundler/gem_tasks"
-task default: %i[]
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/test_*.rb"]
+end
+
+if RUBY_ENGINE == "jruby"
+  task :clobber # noop
+  task :compile # noop
+
+  task default: %i[test]
+else
+  require "rake/extensiontask"
+
+  Rake::ExtensionTask.new("json_escape") do |ext|
+    ext.lib_dir = "lib/json_escape"
+  end
+
+  task default: %i[clobber compile test]
+end

data/benchmark.rb

@@ -0,0 +1,21 @@
+require "benchmark/ips"
+require "json_escape"
+
+benchmarks = [
+  "twitter.json",
+  "citm_catalog.json",
+  "canada.json"
+]
+
+Benchmark.ips do |x|
+  benchmarks.each do |benchmark|
+    data = File.read("#{__dir__}/test/benchmark_data/#{benchmark}")
+    x.report "JsonEscape.json_escape(#{benchmark})" do
+      JsonEscape.json_escape(data)
+    end
+
+    x.report "JsonEscape::Pure.json_escape(#{benchmark})" do
+      JsonEscape::Pure.json_escape(data)
+    end
+  end
+end

data/ext/json_escape/extconf.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+require "mkmf"
+
+create_makefile("json_escape/json_escape")

data/ext/json_escape/json_escape.c

@@ -0,0 +1,99 @@
+#include "ruby.h"
+#include "ruby/encoding.h"
+
+VALUE rb_mJsonEscape;
+
+/* strlen("\\u2029") == 6 */
+#define ESCAPE_JSON_MAX_LEN 6
+
+static inline long
+json_escaped_length(VALUE str)
+{
+    const long len = RSTRING_LEN(str);
+    if (len >= LONG_MAX / ESCAPE_JSON_MAX_LEN) {
+        ruby_malloc_size_overflow(len, ESCAPE_JSON_MAX_LEN);
+    }
+    return len * ESCAPE_JSON_MAX_LEN;
+}
+
+static VALUE
+escape_json(VALUE self, VALUE str)
+{
+    if (!RB_TYPE_P(str, T_STRING)) {
+        str = rb_convert_type(str, T_STRING, "String", "to_s");
+    }
+
+    rb_encoding *enc = rb_enc_get(str);
+    if (enc != rb_utf8_encoding() && enc != rb_usascii_encoding()) {
+        rb_raise(rb_eEncCompatError, "input string must be UTF-8 or ASCII");
+    }
+
+    const char *cstr = RSTRING_PTR(str);
+    const unsigned long str_len = RSTRING_LEN(str);
+    const char *end = cstr + RSTRING_LEN(str);
+
+    size_t initial_match = strcspn(cstr, "&<>\xe2");
+    if (initial_match == str_len) {
+        return str;
+    }
+
+    VALUE escaped = rb_str_buf_new(json_escaped_length(str));
+    rb_str_resize(escaped, json_escaped_length(str));
+    char *buf = RSTRING_PTR(escaped);
+    char *dest = buf;
+
+    memcpy(dest, cstr, initial_match);
+    cstr += initial_match;
+    dest += initial_match;
+
+    while (cstr < end) {
+        const char c = *cstr++;
+
+#define JSON_ESCAPE_CONCAT(s) do { \
+    memcpy(dest, ("\\u" s), strlen(s) + 2); \
+    dest += strlen(s) + 2; \
+} while (0)
+
+        if (0) {
+        }
+        else if (c == '&') {
+            JSON_ESCAPE_CONCAT("0026");
+        }
+        else if (c == '>') {
+            JSON_ESCAPE_CONCAT("003e");
+        }
+        else if (c == '<') {
+            JSON_ESCAPE_CONCAT("003c");
+        }
+        else if (c == '\xe2' && cstr[0] == '\x80' && cstr[1] == '\xa8') {
+            JSON_ESCAPE_CONCAT("2028");
+            cstr += 2;
+        }
+        else if (c == '\xe2' && cstr[0] == '\x80' && cstr[1] == '\xa9') {
+            JSON_ESCAPE_CONCAT("2029");
+            cstr += 2;
+        }
+        else {
+            *dest++ = c;
+        }
+
+        initial_match = strcspn(cstr, "&<>\xe2");
+        memcpy(dest, cstr, initial_match);
+        cstr += initial_match;
+        dest += initial_match;
+
+#undef JSON_ESCAPE_CONCAT
+    }
+
+    rb_str_resize(escaped, dest - buf);
+    rb_enc_associate(escaped, rb_enc_get(str));
+
+    return escaped;
+}
+
+void
+Init_json_escape(void)
+{
+    rb_mJsonEscape = rb_define_module("JsonEscape");
+    rb_define_method(rb_mJsonEscape, "json_escape", escape_json, 1);
+}

data/ext/json_escape/json_escape.h

@@ -0,0 +1,6 @@
+#ifndef JSON_ESCAPE_H
+#define JSON_ESCAPE_H 1
+
+#include "ruby.h"
+
+#endif /* JSON_ESCAPE_H */

data/lib/json_escape/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JsonEscape
-  VERSION = "0.0.0"
+  VERSION = "0.1.0"
 end

data/lib/json_escape.rb

@@ -3,6 +3,26 @@
 require_relative "json_escape/version"
 
 module JsonEscape
-  class Error < StandardError; end
-  # Your code goes here...
+  module Pure
+    JSON_ESCAPE = { "&" => '\u0026', ">" => '\u003e', "<" => '\u003c', "\u2028" => '\u2028', "\u2029" => '\u2029' }
+    JSON_ESCAPE_REGEXP = /[\u2028\u2029&><]/u
+    private_constant :JSON_ESCAPE, :JSON_ESCAPE_REGEXP
+
+    def json_escape(json)
+      json = json.to_s
+      if json.encoding != Encoding::UTF_8 && json.encoding != Encoding::ASCII
+        raise Encoding::CompatibilityError, "input string must be UTF-8 or ASCII"
+      end
+      json.gsub(JSON_ESCAPE_REGEXP, JSON_ESCAPE)
+    end
+    module_function :json_escape
+  end
+
+  begin
+    require_relative "json_escape/json_escape"
+  rescue LoadError
+    include Pure
+  end
+
+  module_function :json_escape
 end

metadata

@@ -1,20 +1,77 @@
 --- !ruby/object:Gem::Specification
 name: json_escape
 version: !ruby/object:Gem::Version
-  version: 0.0.0
+  version: 0.1.0
 platform: ruby
 authors:
 - John Hawthorn
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-06-23 00:00:00.000000000 Z
-dependencies: []
+date: 2023-06-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: benchmark-ips
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: JSON escape
 email:
 - john@hawthorn.email
 executables: []
-extensions: []
+extensions:
+- ext/json_escape/extconf.rb
 extra_rdoc_files: []
 files:
 - CODE_OF_CONDUCT.md
@@ -22,10 +79,12 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
-- json_escape.gemspec
+- benchmark.rb
+- ext/json_escape/extconf.rb
+- ext/json_escape/json_escape.c
+- ext/json_escape/json_escape.h
 - lib/json_escape.rb
 - lib/json_escape/version.rb
-- sig/json_escape.rbs
 homepage: https://github.com/jhawthorn/json_escape
 licenses:
 - MIT

data/json_escape.gemspec

@@ -1,37 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "lib/json_escape/version"
-
-Gem::Specification.new do |spec|
-  spec.name = "json_escape"
-  spec.version = JsonEscape::VERSION
-  spec.authors = ["John Hawthorn"]
-  spec.email = ["john@hawthorn.email"]
-
-  spec.summary = "JSON escape"
-  spec.description = "JSON escape"
-  spec.homepage = "https://github.com/jhawthorn/json_escape"
-  spec.license = "MIT"
-  spec.required_ruby_version = ">= 2.6.0"
-
-  spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = spec.homepage
-  spec.metadata["changelog_uri"] = spec.homepage
-
-  # Specify which files should be added to the gem when it is released.
-  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files = Dir.chdir(__dir__) do
-    `git ls-files -z`.split("\x0").reject do |f|
-      (File.expand_path(f) == __FILE__) || f.start_with?(*%w[bin/ test/ spec/ features/ .git .circleci appveyor])
-    end
-  end
-  spec.bindir = "exe"
-  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
-
-  # Uncomment to register a new dependency of your gem
-  # spec.add_dependency "example-gem", "~> 1.0"
-
-  # For more information and examples about making a new gem, check out our
-  # guide at: https://bundler.io/guides/creating_gem.html
-end

data/sig/json_escape.rbs

@@ -1,4 +0,0 @@
-module JsonEscape
-  VERSION: String
-  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
-end