grex_ruby 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9eea98be32e92c0d87bc6675840278c2472767a7f57e48d01fde8bedb59b650d
-  data.tar.gz: 7bd0abf1026dbe6f9bb4e6c764952301c948da7b6647b9a2015b3a7553bb3e04
+  metadata.gz: 781efb31741fa9806bf76e010c0414b06bdd4dfaad5ef213ad4eba27d60ca976
+  data.tar.gz: d902f4f544a50bf54c71eb5ecbd2b743628ea195b13c282b1baef7aff54f7e69
 SHA512:
-  metadata.gz: 25bb8ab1dd9ac55dfdfcf1eb37841be34abd390cf2d27a4f541e1fb59735b780b5f4dabc0853b8463b2464cc0d7c222dfba91afa3c1f059196c5e7c0d4607f20
-  data.tar.gz: a45f66a23f259de711df1c84ce8e2df4335c2b568a493492cdddb4b7bce21f89fc072e29e88dff2ec2008cf43d824a6d45ebee51bf4ff0047a788823f08d66f2
+  metadata.gz: 06d66538fd78d54b19d8f4c79c4b57c9e50afe65dd225b866354a8b057e753703b388a5aa81003d2dbbfbc96f4dd497ef33183427abcd028f1e78a4e4e4ef554
+  data.tar.gz: 26d1802d580e715d89431471ea6744fad9290cc651cc8a9802b4704def599525c8bb6577f83c9e862b363773cf4bf70d6073d393e96fbe54bebe87643a119683

data/.gitattributes

@@ -0,0 +1 @@
+exe/* text eol=lf

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.3.0
+
+- Add `Grex.generate_from_file` with UTF-8 input, LF/CRLF line handling and keyword options.
+- Add the `grex-ruby` command with flags for every generation option.
+- Add command-line help, version output and readable errors with nonzero exit status.
+- Document file input and command-line usage, including local development commands.
+- Add integration tests for the CLI and file-based generation.
+
 ## 0.2.0
 
 - Expose the public API as `Grex`, keeping `GrexRuby` as a compatibility alias.

data/Cargo.lock

@@ -228,7 +228,7 @@ dependencies = [
 
 [[package]]
 name = "grex_ruby"
-version = "0.2.0"
+version = "0.3.0"
 dependencies = [
  "grex",
  "magnus",

data/README.md

@@ -401,6 +401,97 @@ An empty array raises `ArgumentError` with the message `samples must not be empt
 Passing a string instead of an array, or an array containing an integer, raises
 `TypeError`.
 
+## Reading examples from a file
+
+Starting with 0.3.0, `Grex.generate_from_file` reads a UTF-8 file with one example
+per line and accepts the same keyword options as `Grex.generate`:
+
+```ruby
+# samples.txt contains two lines: 123 and 234.
+Grex.generate_from_file('samples.txt', convert_digits: true)
+# => "^\\p{Nd}\\p{Nd}\\p{Nd}$"
+```
+
+LF and Windows CRLF line endings are removed; other whitespace is preserved.
+The last line does not need a newline. An empty file raises `ArgumentError`;
+a missing file raises `Errno::ENOENT`.
+
+## Command-line usage
+
+Version 0.3.0 adds the `grex-ruby` command. After installing the gem:
+
+```text
+grex-ruby --help
+grex-ruby --version
+grex-ruby samples.txt
+```
+
+Given a UTF-8 `samples.txt` containing:
+
+```text
+123
+234
+```
+
+Run:
+
+```text
+grex-ruby samples.txt --convert-digits
+```
+
+Output:
+
+```text
+^\p{Nd}\p{Nd}\p{Nd}$
+```
+
+Flags may appear before or after the file path, and can be combined:
+
+```text
+grex-ruby samples.txt --convert-digits --convert-repetitions --no-anchors
+```
+
+Output:
+
+```text
+\p{Nd}{3}
+```
+
+All generation options are available:
+
+| CLI flag | Ruby keyword |
+| --- | --- |
+| `--convert-digits` | `convert_digits: true` |
+| `--convert-non-digits` | `convert_non_digits: true` |
+| `--convert-whitespace` | `convert_whitespace: true` |
+| `--convert-non-whitespace` | `convert_non_whitespace: true` |
+| `--convert-words` | `convert_words: true` |
+| `--convert-non-words` | `convert_non_words: true` |
+| `--convert-repetitions` | `convert_repetitions: true` |
+| `--minimum-repetitions N` | `minimum_repetitions: N` |
+| `--minimum-substring-length N` | `minimum_substring_length: N` |
+| `--no-anchors` | `anchors: false` |
+| `--no-start-anchor` | `start_anchor: false` |
+| `--no-end-anchor` | `end_anchor: false` |
+| `-i`, `--ignore-case` | `ignore_case: true` |
+| `--capturing-groups` | `capturing_groups: true` |
+| `-x`, `--verbose` | `verbose: true` |
+| `--escape-non-ascii` | `escape_non_ascii: true` |
+
+Anchors are enabled by default. The positive forms `--anchors`, `--start-anchor`
+and `--end-anchor` are also accepted. As in the Ruby API, `--no-anchors` overrides
+the individual anchor settings. Numeric minimums must be positive 32-bit integers.
+
+The command accepts exactly one file path. Use `--` before a path that starts
+with `-`. Patterns are written to stdout; errors are written to stderr with exit
+status `1`. Successful generation, `--help`, and `--version` exit with status `0`.
+
+To run the CLI from a checkout before installing it:
+
+```bash
+bundle exec ruby -Ilib exe/grex-ruby samples.txt --convert-digits
+```
+
 ## Development
 
 ### Linux

data/exe/grex-ruby

@@ -0,0 +1,97 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'grex_ruby'
+require 'optparse'
+
+options = {}
+
+parser = OptionParser.new do |opts|
+  opts.banner = 'Usage: grex-ruby FILE [options]'
+
+  opts.on('--convert-digits', 'Convert digits to a Unicode digit class') do
+    options[:convert_digits] = true
+  end
+
+  opts.on('--convert-non-digits', 'Convert non-digits to a Unicode character class') do
+    options[:convert_non_digits] = true
+  end
+
+  opts.on('--convert-whitespace', 'Convert whitespace to a Unicode character class') do
+    options[:convert_whitespace] = true
+  end
+
+  opts.on('--convert-non-whitespace', 'Convert non-whitespace to a Unicode character class') do
+    options[:convert_non_whitespace] = true
+  end
+
+  opts.on('--convert-words', 'Convert Unicode word characters') do
+    options[:convert_words] = true
+  end
+
+  opts.on('--convert-non-words', 'Convert characters outside the Unicode word class') do
+    options[:convert_non_words] = true
+  end
+
+  opts.on('--convert-repetitions', 'Convert repeated substrings to quantifiers') do
+    options[:convert_repetitions] = true
+  end
+
+  opts.on('--minimum-repetitions N', Integer, 'Minimum repetitions after the first occurrence (default: 1)') do |value|
+    options[:minimum_repetitions] = value
+  end
+
+  opts.on('--minimum-substring-length N', Integer, 'Minimum repeated fragment length (default: 1)') do |value|
+    options[:minimum_substring_length] = value
+  end
+
+  opts.on('--[no-]anchors', 'Keep both line anchors (default: enabled)') do |value|
+    options[:anchors] = value
+  end
+
+  opts.on('--[no-]start-anchor', 'Keep the initial line anchor (default: enabled)') do |value|
+    options[:start_anchor] = value
+  end
+
+  opts.on('--[no-]end-anchor', 'Keep the final line anchor (default: enabled)') do |value|
+    options[:end_anchor] = value
+  end
+
+  opts.on('-i', '--ignore-case', 'Match without regard to letter case') do
+    options[:ignore_case] = true
+  end
+
+  opts.on('--capturing-groups', 'Use capturing groups') do
+    options[:capturing_groups] = true
+  end
+
+  opts.on('-x', '--verbose', 'Format the pattern across multiple lines') do
+    options[:verbose] = true
+  end
+
+  opts.on('--escape-non-ascii', 'Escape non-ASCII characters as Unicode code points') do
+    options[:escape_non_ascii] = true
+  end
+
+  opts.on('-V', '--version', 'Show version') do
+    puts Grex::VERSION
+    exit
+  end
+
+  opts.on('-h', '--help', 'Show help') do
+    puts opts
+    exit
+  end
+end
+
+begin
+  parser.parse!
+  raise OptionParser::MissingArgument, 'FILE' if ARGV.empty?
+  raise OptionParser::InvalidArgument, 'expected exactly one FILE' unless ARGV.length == 1
+
+  puts Grex.generate_from_file(ARGV.first, **options)
+rescue OptionParser::ParseError, ArgumentError, RangeError, SystemCallError, EncodingError => error
+  warn "grex-ruby: #{error.message}"
+  warn 'Run grex-ruby --help for usage.'
+  exit 1
+end

data/ext/grex_ruby/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "grex_ruby"
-version = "0.2.0"
+version = "0.3.0"
 edition = "2021"
 authors = ["Nelly Simkova <sk8high3r@ya.ru>"]
 publish = false

data/lib/grex_ruby/version.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module Grex
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end
 
 # Compatibility with the public module name used in version 0.1.0.

data/lib/grex_ruby.rb

@@ -1,66 +1,71 @@
-# frozen_string_literal: true
-
-require_relative 'grex_ruby/version'
-require 'grex_ruby/grex_ruby'
-
-module Grex
-  class Error < StandardError; end
-
-  def self.generate(samples,
-                    convert_digits: false,
-                    convert_repetitions: false,
-                    minimum_substring_length: 1,
-                    minimum_repetitions: 1,
-                    anchors: true,
-                    ignore_case: false,
-                    capturing_groups: false,
-                    verbose: false,
-                    convert_non_digits: false,
-                    convert_whitespace: false,
-                    convert_non_whitespace: false,
-                    convert_words: false,
-                    convert_non_words: false,
-                    start_anchor: true,
-                    end_anchor: true,
-                    escape_non_ascii: false)
-    pattern = generate_native(samples,
-                              { convert_digits:, convert_repetitions:, minimum_substring_length:, minimum_repetitions:,
-                                anchors:, ignore_case:, capturing_groups:, verbose:, convert_non_digits:, convert_whitespace:, convert_non_whitespace:, convert_words:, convert_non_words:, start_anchor:, end_anchor:, escape_non_ascii: })
-    adapt_pattern(pattern)
-  end
-
-  def self.adapt_pattern(pattern)
-    chars = pattern.chars
-    result = +''
-    index = 0
-
-    while index < chars.length
-      if chars[index] == '\\'
-        result << case chars[index + 1]
-                  when 'd'
-                    '\p{Nd}'
-                  when 'D'
-                    '\P{Nd}'
-                  when 's'
-                    '\p{Space}'
-                  when 'S'
-                    '\P{Space}'
-                  when 'w'
-                    '[\p{Alpha}\p{M}\p{Nd}\p{Pc}\p{Join_Control}]'
-                  when 'W'
-                    '[^\p{Alpha}\p{M}\p{Nd}\p{Pc}\p{Join_Control}]'
-                  else
-                    chars[index, 2].join
-                  end
-        index += 2
-      else
-        result << chars[index]
-        index += 1
-      end
-    end
-
-    result
-  end
-
-  private_class_method :generate_native, :adapt_pattern
-end
+# frozen_string_literal: true
+
+require_relative 'grex_ruby/version'
+require 'grex_ruby/grex_ruby'
+
+module Grex
+  class Error < StandardError; end
+
+  def self.generate(samples,
+                    convert_digits: false,
+                    convert_repetitions: false,
+                    minimum_substring_length: 1,
+                    minimum_repetitions: 1,
+                    anchors: true,
+                    ignore_case: false,
+                    capturing_groups: false,
+                    verbose: false,
+                    convert_non_digits: false,
+                    convert_whitespace: false,
+                    convert_non_whitespace: false,
+                    convert_words: false,
+                    convert_non_words: false,
+                    start_anchor: true,
+                    end_anchor: true,
+                    escape_non_ascii: false)
+    pattern = generate_native(samples,
+                              { convert_digits:, convert_repetitions:, minimum_substring_length:, minimum_repetitions:,
+                                anchors:, ignore_case:, capturing_groups:, verbose:, convert_non_digits:, convert_whitespace:, convert_non_whitespace:, convert_words:, convert_non_words:, start_anchor:, end_anchor:, escape_non_ascii: })
+    adapt_pattern(pattern)
+  end
+
+  def self.adapt_pattern(pattern)
+    chars = pattern.chars
+    result = +''
+    index = 0
+
+    while index < chars.length
+      if chars[index] == '\\'
+        result << case chars[index + 1]
+                  when 'd'
+                    '\p{Nd}'
+                  when 'D'
+                    '\P{Nd}'
+                  when 's'
+                    '\p{Space}'
+                  when 'S'
+                    '\P{Space}'
+                  when 'w'
+                    '[\p{Alpha}\p{M}\p{Nd}\p{Pc}\p{Join_Control}]'
+                  when 'W'
+                    '[^\p{Alpha}\p{M}\p{Nd}\p{Pc}\p{Join_Control}]'
+                  else
+                    chars[index, 2].join
+                  end
+        index += 2
+      else
+        result << chars[index]
+        index += 1
+      end
+    end
+
+    result
+  end
+
+  def self.generate_from_file(path, **options)
+    lines = File.readlines(path, encoding: 'UTF-8', chomp: true)
+    generate(lines, **options)
+  end
+
+  private_class_method :generate_native, :adapt_pattern
+end

data/sig/grex_ruby.rbs

@@ -20,6 +20,26 @@ module Grex
     ?end_anchor: bool,
     ?escape_non_ascii: bool,
   ) -> String
+
+  def self.generate_from_file: (
+    String,
+    ?convert_digits: bool,
+    ?convert_repetitions: bool,
+    ?minimum_substring_length: Integer,
+    ?minimum_repetitions: Integer,
+    ?anchors: bool,
+    ?ignore_case: bool,
+    ?capturing_groups: bool,
+    ?verbose: bool,
+    ?convert_non_digits: bool,
+    ?convert_whitespace: bool,
+    ?convert_non_whitespace: bool,
+    ?convert_words: bool,
+    ?convert_non_words: bool,
+    ?start_anchor: bool,
+    ?end_anchor: bool,
+    ?escape_non_ascii: bool,
+  ) -> String
 end
 
 module GrexRuby = Grex

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: grex_ruby
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Nelly Simkova
@@ -23,13 +23,35 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.9.128
+- !ruby/object:Gem::Dependency
+  name: optparse
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.3'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.3'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '1.0'
 email:
 - sk8high3r@ya.ru
-executables: []
+executables:
+- grex-ruby
 extensions:
 - ext/grex_ruby/extconf.rb
 extra_rdoc_files: []
 files:
+- ".gitattributes"
 - ".github/workflows/ci.yml"
 - CHANGELOG.md
 - Cargo.lock
@@ -38,6 +60,7 @@ files:
 - README.md
 - Rakefile
 - THIRD_PARTY_NOTICES.md
+- exe/grex-ruby
 - ext/grex_ruby/Cargo.toml
 - ext/grex_ruby/build.rs
 - ext/grex_ruby/extconf.rb