regular_expression 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a27d72d3175c1d50948e9ea99493ccab342b9e7e9b84d87a109257b43c4eeec1
+  data.tar.gz: 3adc54f3f5f1a6adf830668d16d0938e5c7f6dc23c04992186fd53983fa53238
+SHA512:
+  metadata.gz: fa40e81edf71099e1101f8a4c5111556c41eafde41c1b2f541540dc23ef019b40cc56d332f64632f1b688a7147a5a4bccb87d89dc42de8f9cc9e6eacee5c23da
+  data.tar.gz: '08f9ad4a3857a9aeace3507d3c8108fc811baa6deb9484faae73d51a69d4ceabb1505c20b3ac3c6a971b2b278ef242bedbec5426084d8706445bba82f15a9dca'

data/.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "bundler"
+    directory: "/"
+    schedule:
+      interval: "daily"

data/.github/workflows/main.yml

@@ -0,0 +1,36 @@
+name: Main
+on:
+- push
+- pull_request_target
+jobs:
+  ci:
+    name: CI
+    runs-on: ubuntu-latest
+    env:
+      CI: true
+    steps:
+    - name: Install graphviz
+      run: sudo apt-get install graphviz
+    - uses: actions/checkout@master
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 3.0
+        bundler-cache: true
+    - name: Lint and test
+      run: |
+        bundle exec rake test
+        bundle exec rubocop --parallel
+  automerge:
+    name: AutoMerge
+    needs: ci
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request_target' && github.actor == 'dependabot[bot]'
+    steps:
+    - uses: actions/github-script@v3
+      with:
+        script: |
+          github.pulls.merge({
+            owner: context.payload.repository.owner.login,
+            repo: context.payload.repository.name,
+            pull_number: context.payload.pull_request.number
+          })

data/.gitignore

@@ -0,0 +1 @@
+coverage/

data/.rubocop.yml

@@ -0,0 +1,42 @@
+AllCops:
+  DisplayCopNames: true
+  DisplayStyleGuide: true
+  NewCops: enable
+  SuggestExtensions: false
+  TargetRubyVersion: 3.0
+  Exclude:
+  - "lib/regular_expression/parser.rb"
+  - "vendor/**/*"
+
+Gemspec/RequiredRubyVersion:
+  Enabled: false
+
+Metrics:
+  Enabled: false
+
+Style/AccessorGrouping:
+  Enabled: false
+
+Style/CombinableLoops:
+  Enabled: false
+
+Style/Documentation:
+  Enabled: false
+
+Style/HashEachMethods:
+  Enabled: false
+
+Style/IfUnlessModifier:
+  Enabled: false
+
+Style/PerlBackrefs:
+  Enabled: false
+
+Style/SpecialGlobalVars:
+  Enabled: false
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+Style/StructInheritance:
+  Enabled: false

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,76 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+- The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+- Trolling, insulting/derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at kddnewton@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq

data/CONTRIBUTING.md

@@ -0,0 +1,76 @@
+# Contributing
+
+Thanks for your interest in contributing to `regular_expression`! Here are a couple of ways that you can contribute:
+
+* A good place to start is looking at the existing [open issues](https://github.com/kddnewton/regular_expression/issues) on GitHub. Most of the time they will be labeled with an estimate of their size and scope.
+* We could always use help with better documentation both in code, in this document, and in the README.
+* If you've found a bug or other issue with the code, opening issues with reproduction steps is always appreciated!
+
+Below is some background information to get you up and running on what is happening in this gem.
+
+## Background
+
+In order to understand your regular expression patterns and compare them against input strings, the source string goes through a couple of transformations.
+
+### 1. Abstract syntax tree
+
+First, it passes through `RegularExpression::Parser`, which is a class that is generated using the [racc](https://github.com/ruby/racc) gem. It is a parser that will take your input string and convert it into an abstract syntax tree. The root of that tree is a `RegularExpression::AST::Root`, and each of its children are also within the `RegularExpression::AST` module. The grammar that the AST follows is loosely described below:
+
+```
+root: CARET? expression
+
+expression:
+  | item+ PIPE expression
+  | item+
+
+item: group | match | ANCHOR
+
+group: LPAREN expression RPAREN quantifier?
+
+match: match_item quantifier?
+
+match_item:
+  | LBRACKET CARET? character_group_item+ RBRACKET
+  | CHAR_CLASS
+  | CHAR
+  | PERIOD
+
+character_group_item:
+  | CHAR_CLASS
+  | CHAR DASH CHAR
+  | CHAR
+
+quantifier:
+  | LBRACE INTEGER COMMA INTEGER RBRACE
+  | LBRACE INTEGER COMMA RBRACE
+  | LBRACE INTEGER RBRACE
+  | STAR
+  | PLUS
+  | QMARK
+```
+
+### 2. State machine
+
+Second, we take the AST and transform it into a [nondeterministic finite automaton](https://en.wikipedia.org/wiki/Nondeterministic_finite_automaton) (which is an academic way of saying a state machine). Each transition between the states of the state machine consume either 0 or 1 characters from the input string. Everything regarding the state machine is defined under the `RegularExpression::NFA` module.
+
+### 3. Bytecode
+
+Third, we take the state machine and convert it into bytecode. This involves walking through each of the state machine's states and generating instructions that our interpreter understands. The various bytecode instructions are defined under the `RegularExpression::Bytecode::Insns` module. For the most part they consist of:
+
+* Instructions that push and pop the current string index from the stack to support backtracking.
+* Instructions that function as "guards" in that they assert that things are true (e.g., `\A` saying we're at the beginning of the string).
+* Instructions that conditionally jump (e.g., a pattern with a `[a-zA-Z]` range receiving an `x` character).
+* Instructions that succeed or fail the entire match.
+
+Once we have the bytecode in place, we can pass it to our interpreter to execute. At this point we have a functional matching algorithm that will work (albeit somewhat slowly).
+
+### 4. Control flow graph
+
+Fourth, if asked we will take the bytecode and convert it into a control flow graph. This graph creates a list of basic blocks (a set of instructions where the first instruction is a jump target). This graph makes it easier to compile our abstract representation of the regular expression pattern because the flow of the matching algorithm becomes explicit on the block boundaries. The code for generating and managing this control flow graph is defined under the `RegularExpression::CFG` module.
+
+### 5. Compilation
+
+Fifth, we can take the control flow graph and pass it to one of our compilers. These compilers are responsible for taking the control flow graph and transforming it into a proc that we can call with an input string. The compilers include:
+
+* `RegularExpression::Compiler::Ruby` - takes the control flow graph and converts it into a ruby string. To convert the string to a proc, the compiled object calls `eval`.
+* `RegularExpression::Compiler::X86` - takes the control flow graph and uses the `fisk` gem to generate `X86-64` assembly. The assembly returns a function pointer, and the compiled object knows how to convert that into a proc using the `Fiddle` library. The assembled code can be disassembled using the `crabstone` gem.

data/Gemfile

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gem "bundler"
+gem "crabstone"
+gem "graphviz"
+gem "minitest"
+gem "rake"
+gem "rubocop"
+gem "simplecov"
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,69 @@
+PATH
+  remote: .
+  specs:
+    regular_expression (0.1.0)
+      fisk
+      racc
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.2)
+    crabstone (4.0.3)
+      ffi
+    docile (1.4.0)
+    ffi (1.15.3)
+    fisk (2.0.0)
+    graphviz (1.2.1)
+      process-pipeline
+    minitest (5.14.4)
+    parallel (1.20.1)
+    parser (3.0.2.0)
+      ast (~> 2.4.1)
+    process-group (1.2.3)
+      process-terminal (~> 0.2.0)
+    process-pipeline (1.0.2)
+      process-group
+    process-terminal (0.2.0)
+      ffi
+    racc (1.5.2)
+    rainbow (3.0.0)
+    rake (13.0.6)
+    regexp_parser (2.1.1)
+    rexml (3.2.5)
+    rubocop (1.18.3)
+      parallel (~> 1.10)
+      parser (>= 3.0.0.0)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml
+      rubocop-ast (>= 1.7.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 3.0)
+    rubocop-ast (1.7.0)
+      parser (>= 3.0.1.1)
+    ruby-progressbar (1.11.0)
+    simplecov (0.21.2)
+      docile (~> 1.1)
+      simplecov-html (~> 0.11)
+      simplecov_json_formatter (~> 0.1)
+    simplecov-html (0.12.3)
+    simplecov_json_formatter (0.1.3)
+    unicode-display_width (2.0.0)
+
+PLATFORMS
+  x86_64-darwin-19
+  x86_64-linux
+
+DEPENDENCIES
+  bundler
+  crabstone
+  graphviz
+  minitest
+  rake
+  regular_expression!
+  rubocop
+  simplecov
+
+BUNDLED WITH
+   2.2.16

data/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021-present Kevin Newton
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,51 @@
+# RegularExpression
+
+[![Build Status](https://github.com/kddeisz/regular_expression/workflows/Main/badge.svg)](https://github.com/kddeisz/regular_expression/actions)
+
+A regular expression engine written in Ruby.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem "regular_expression"
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install regular_expression
+
+## Usage
+
+To create a regular expression pattern, use:
+
+```ruby
+pattern = RegularExpression::Pattern.new("ab?c")
+```
+
+Patterns can be queried for whether or not they match a test string, as in:
+
+```ruby
+pattern.match?("abc") # => true
+pattern.match?("ac") # => true
+pattern.match?("ab") # => false
+```
+
+## Development
+
+After checking out the repo, run `bundle install` to install dependencies. Then, run `bundle exec rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/kddeisz/regular_expression. For information about how to contribute to the development of this gem, see the [CONTRIBUTING.md](CONTRIBUTING.md) document.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+file "lib/regular_expression/parser.rb" => "lib/regular_expression/parser.y" do
+  `bundle exec racc lib/regular_expression/parser.y -o lib/regular_expression/parser.rb`
+end
+
+Rake::Task["test"].enhance(["lib/regular_expression/parser.rb"])
+
+task default: :test

data/bin/console

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+$:.unshift(File.expand_path("../lib", __dir__))
+require "regular_expression"
+
+require "irb"
+IRB.start