ruby_parser 3.15.0 → 3.19.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b1172d3be0aa30a6d959bd6ab265a6e05b391923196ec30236705637f8b05cc0
-  data.tar.gz: bedbe7c23eb256413a34d9b5dc67d975c70a8757edea6b22cebfcb82fb42d412
+  metadata.gz: 82ff82f1d9693451e0d2f740f5e7a9cbeaa31034bee66ffa61486bc0f930d60b
+  data.tar.gz: 15d8b71b9533534ffaa4184e50f0e5a795e4a7f190bf13a55858f59b17c1ed99
 SHA512:
-  metadata.gz: 4e3174ada892182f6f60497feaa74668517e71bcffd44b10590f9c2fc153ba1744dbb8afd35493d1f7cb96598795e30505c922c2e53e441cbb1a7a646e9005ef
-  data.tar.gz: 2cab3beeefb45cba366c482e862bb2594169560f8920d39b28a7a86ad5c6c6582393fe91e082cd6387314f36ae5e660d8e18c2de8a4ddcefce9d40600593f795
+  metadata.gz: 78332be9c05d511d05f1c47977c74390658fcc00fc412009dba172d0e53c0e698b8e28c4803c4969720f2d2d29ed3fc891be2a990618098ae0cf04d00ad28e9f
+  data.tar.gz: 72f7e1c089bc80662ea2eb8c8056d7bb3bf84ff27224c2d450ffde94abd2fb5ba2317d1405a880bebb2c91ac34bcb7023685065f1a8b2e69f62ed8f6b0362e77

data/History.rdoc

@@ -1,3 +1,154 @@
+=== 3.19.2 / 2022-12-03
+
+* 5 bug fixes:
+
+  * Fixed bug parsing array patterns using %w, %i, etc.
+  * Fixed dedenting when heredoc has only empty line and interpolation. (mvz)
+  * Fixed dsym unescaping. (mvz)
+  * Fixed vars in pattern matching that should be lasgn, not lvar.
+  * find_pat mid-patterns are now splatted inline, not wrapped in an array_pat.
+
+=== 3.19.1 / 2022-04-05
+
+* 2 bug fixes:
+
+  * Added comments to endless defn and defs. (mvz)
+  * Fixed endless method bug handling attrset names.
+
+=== 3.19.0 / 2022-03-29
+
+* 1 major enhancement:
+
+  * Added tentative 3.1 support.
+
+* 7 minor enhancements:
+
+  * 3.1: bare RHS assoc: { y: } => s(:hash, s(:lit, :y), nil)
+  * 3.1: calls w/ unnamed block args (bare &)
+  * 3.1: endless defn/defs w/ paren-less calls (aka commands)
+  * 3.1: pattern capture to nonlocal vars, eg: ^@a, ^$b, ^@@c
+  * 3.1: pattern: ^(expr) => expr
+  * Improved steps for adding new versions.
+  * Improved steps for running gauntlets.
+
+* 2 bug fixes:
+
+  * Bumped 2.6+ cached versions for rake compare.
+  * Skip test_regexp_esc_C_slash on ruby 3.1.0 because of MRI bug.
+
+=== 3.18.1 / 2021-11-10
+
+* 1 minor enhancement:
+
+  * All parser tests are now explicitly testing line numbers at every level.
+
+* 3 bug fixes:
+
+  * Fixed endless method with noargs. (mitsuru)
+  * Fixed line numbers on some yield forms.
+  * Handle and clearly report if unifdef is missing.
+
+=== 3.18.0 / 2021-10-27
+
+Holy crap... 58 commits! 2.7 and 3.0 are feature complete. Strings
+& heredocs have been rewritten.
+
+* 9 major enhancements:
+
+  * !!! Rewrote lexer (and friends) for strings, heredocs, and %*[] constructs.
+  * Massive overhaul on line numbers.
+  * Freeze input! Finally!!! No more modifying the input string for heredocs.
+  * Overhauled RPStringScanner. Removed OLD compatibility methods!
+  * Removed Sexp methods: value, to_sym, add, add_all, node_type, values.
+    * value moved to sexp_processor.
+  * Removed String#grep monkey-patch.
+  * Removed String#lineno monkey-patch.
+  * Removed string_to_pos, charpos, etc hacks for ancient ruby versions.
+  * Removed unread_many... NO! NO EDITING THE INPUT STRING!
+
+* 31 minor enhancements:
+
+  * 2.7/3.0: many more pattern edge cases
+  * 2.7: Added `mlhs = rhs rescue expr`
+  * 2.7: refactored destructured args (`|(k,v)|`) and unfactored(?!) case_body/args.
+  * 3.0: excessed_comma
+  * 3.0: finished most everything: endless methods, patterns, etc.
+  * 3.0: refactored / added new pattern changes
+  * Added RubyLexer#in_heredoc? (ie, is there old_ss ?)
+  * Added RubyLexer#old_ss and old_lineno and removed much of SSStack(ish).
+  * Added Symbol#end_with? when necessary
+  * Added TALLY and DEBUG options for ss.getch and ss.scan
+  * Added ignore_body_comments to make parser productions more clear.
+  * Added support for no_kwarg (eg `def f(**nil)`).
+  * Added support for no_kwarg in blocks (eg `f { |**nil| }`).
+  * Augmented generated parser files to have frozen_string_literal comments and fixed tests.
+  * Broke out 3.0 parser into its own to ease development.
+  * Bumped dependencies on sexp_processor and oedipus_lex.
+  * Clean generated 3.x files.
+  * Extracted all string scanner methods to their own module.
+  * Fixed some precedence decls.
+  * Implemented most of pattern matching for 2.7+.
+  * Improve lex_state= to report location in verbose debug mode.
+  * Made it easier to debug with a particular version of ruby via rake.
+  * Make sure ripper uses the same version of ruby we specified.
+  * Moved all string/heredoc/etc code to ruby_lexer_strings.rb
+  * Remove warning from newer bisons.
+  * Sprinkled in some frozen_string_literal, but mostly helped by oedipus bump.
+  * Switch to comparing against ruby binary since ripper is buggy.
+  * bugs task should try both bug*.rb and bad*.rb.
+  * endless methods
+  * f_any_kwrest refactoring.
+  * refactored defn/defs
+
+* 15 bug fixes:
+
+  * Cleaned a bunch of old hacks. Initializing RubyLexer w/ Parser is cleaner now.
+  * Corrected some lex_state errors in process_token_keyword.
+  * Fixed ancient ruby2 change (use #lines) in ruby_parse_extract_error.
+  * Fixed bug where else without rescue only raises on 2.6+
+  * Fixed caller for getch and scan when DEBUG=1
+  * Fixed comments in the middle of message cascades.
+  * Fixed differences w/ symbol productions against ruby 2.7.
+  * Fixed dsym to use string_contents production.
+  * Fixed error in bdot2/3 in some edge cases. Fixed p_alt line.
+  * Fixed heredoc dedenting in the presence of empty lines. (mvz)
+  * Fixed some leading whitespace / comment processing
+  * Fixed up how class/module/defn/defs comments were collected.
+  * Overhauled ripper.rb to deal with buggy ripper w/ yydebug.
+  * Removed dsym from literal.
+  * Removed tUBANG lexeme but kept it distinct as a method name (eg: `def !@`).
+
+=== 3.17.0 / 2021-08-03
+
+* 1 minor enhancement:
+
+  * Added support for arg forwarding (eg `def f(...); m(...); end`) (presidentbeef)
+
+=== 3.16.0 / 2021-05-15
+
+* 1 major enhancement:
+
+  * Added tentative 3.0 support.
+
+* 3 minor enhancements:
+
+  * Added lexing for "beginless range" (bdots).
+  * Added parsing for bdots.
+  * Updated rake compare task to download xz files, bumped versions, etc
+
+* 4 bug fixes:
+
+  * Bump rake dependency to >= 10, < 15. (presidentbeef)
+  * Bump sexp_processor dependency to 4.15.1+. (pravi)
+  * Fixed minor state mismatch at the end of parsing to make diffing a little cleaner.
+  * Fixed normalizer to deal with new bison token syntax
+
+=== 3.15.1 / 2021-01-10
+
+* 1 bug fix:
+
+  * Bumped ruby version to include < 4 (trunk).
+
 === 3.15.0 / 2020-08-31
 
 * 1 major enhancement:

data/Manifest.txt

@@ -7,6 +7,7 @@ bin/ruby_parse
 bin/ruby_parse_extract_error
 compare/normalize.rb
 debugging.md
+gauntlet.md
 lib/.document
 lib/rp_extensions.rb
 lib/rp_stringscanner.rb
@@ -26,9 +27,15 @@ lib/ruby26_parser.rb
 lib/ruby26_parser.y
 lib/ruby27_parser.rb
 lib/ruby27_parser.y
+lib/ruby30_parser.rb
+lib/ruby30_parser.y
+lib/ruby31_parser.rb
+lib/ruby31_parser.y
+lib/ruby3_parser.yy
 lib/ruby_lexer.rb
 lib/ruby_lexer.rex
 lib/ruby_lexer.rex.rb
+lib/ruby_lexer_strings.rb
 lib/ruby_parser.rb
 lib/ruby_parser.yy
 lib/ruby_parser_extras.rb

data/README.rdoc

@@ -32,6 +32,10 @@ Tested against 801,039 files from the latest of all rubygems (as of 2013-05):
 * 1.8 parser is at 99.9739% accuracy, 3.651 sigma
 * 1.9 parser is at 99.9940% accuracy, 4.013 sigma
 * 2.0 parser is at 99.9939% accuracy, 4.008 sigma
+* 2.6 parser is at 99.9972% accuracy, 4.191 sigma
+* 3.0 parser has a 100% parse rate.
+  * Tested against 2,672,412 unique ruby files across 167k gems.
+  * As do all the others now, basically.
 
 == FEATURES/PROBLEMS:
 
@@ -61,15 +65,14 @@ You can also use Ruby19Parser, Ruby18Parser, or RubyParser.for_current_ruby:
 
 To add a new version:
 
-* New parser should be generated from lib/ruby_parser.yy.
-* Extend lib/ruby_parser.yy with new class name.
-* Add new version number to V2 in Rakefile for rule creation.
+* New parser should be generated from lib/ruby[3]_parser.yy.
+* Extend lib/ruby[3]_parser.yy with new class name.
+* Add new version number to V2/V3 in Rakefile for rule creation.
+* Add new (full) version to `ruby_parse` section of Rakefile for rake compare
 * Require generated parser in lib/ruby_parser.rb.
 * Add empty TestRubyParserShared##Plus module and TestRubyParserV## to test/test_ruby_parser.rb.
 * Extend Manifest.txt with generated file names.
-* Extend sexp_processor's pt_testcase.rb to match version
-  * add_19tests needs to have the version added
-  * VER_RE needs to have the regexp expanded
+* Add new version number to sexp_processor's pt_testcase.rb in all_versions
 
 Until all of these are done, you won't have a clean test run.
 

data/Rakefile

@@ -12,27 +12,40 @@ Hoe.add_include_dirs "lib"
 Hoe.add_include_dirs "../../sexp_processor/dev/lib"
 Hoe.add_include_dirs "../../minitest/dev/lib"
 Hoe.add_include_dirs "../../oedipus_lex/dev/lib"
+Hoe.add_include_dirs "../../ruby2ruby/dev/lib"
 
 V2   = %w[20 21 22 23 24 25 26 27]
-V2.replace [V2.last] if ENV["FAST"] # HACK
+V3   = %w[30 31]
+
+VERS = V2 + V3
+
+ENV["FAST"] = VERS.last if ENV["FAST"] && !VERS.include?(ENV["FAST"])
+VERS.replace [ENV["FAST"]] if ENV["FAST"]
 
 Hoe.spec "ruby_parser" do
   developer "Ryan Davis", "ryand-ruby@zenspider.com"
 
   license "MIT"
 
-  dependency "sexp_processor", "~> 4.9"
-  dependency "rake", "< 11", :developer
-  dependency "oedipus_lex", "~> 2.5", :developer
+  dependency "sexp_processor", "~> 4.16"
+  dependency "rake", [">= 10", "< 15"], :developer
+  dependency "oedipus_lex", "~> 2.6", :developer
+
+  # NOTE: Ryan!!! Stop trying to fix this dependency! Isolate just
+  # can't handle having a faux-gem half-installed! Stop! Just `gem
+  # install racc` and move on. Revisit this ONLY once racc-compiler
+  # gets split out.
 
-  require_ruby_version [">= 2.1", "< 3.1"]
+  dependency "racc", "~> 1.5", :developer
+
+  require_ruby_version [">= 2.1", "< 4"]
 
   if plugin? :perforce then     # generated files
-    V2.each do |n|
+    VERS.each do |n|
       self.perforce_ignore << "lib/ruby#{n}_parser.rb"
     end
 
-    V2.each do |n|
+    VERS.each do |n|
       self.perforce_ignore << "lib/ruby#{n}_parser.y"
     end
 
@@ -46,8 +59,44 @@ Hoe.spec "ruby_parser" do
   end
 end
 
+def maybe_add_to_top path, string
+  file = File.read path
+
+  return if file.start_with? string
+
+  warn "Altering top of #{path}"
+  tmp_path = "#{path}.tmp"
+  File.open(tmp_path, "w") do |f|
+    f.puts string
+    f.puts
+
+    f.write file
+    # TODO: make this deal with encoding comments properly?
+  end
+  File.rename tmp_path, path
+end
+
+def unifdef?
+  @unifdef ||= system("which unifdef") or abort <<~EOM
+    unifdef not found!
+
+    Please install 'unifdef' package on your system or `rake generate` on a mac.
+  EOM
+end
+
 V2.each do |n|
   file "lib/ruby#{n}_parser.y" => "lib/ruby_parser.yy" do |t|
+    unifdef?
+    cmd = 'unifdef -tk -DV=%s -UDEAD %s > %s || true' % [n, t.source, t.name]
+    sh cmd
+  end
+
+  file "lib/ruby#{n}_parser.rb" => "lib/ruby#{n}_parser.y"
+end
+
+V3.each do |n|
+  file "lib/ruby#{n}_parser.y" => "lib/ruby3_parser.yy" do |t|
+    unifdef?
     cmd = 'unifdef -tk -DV=%s -UDEAD %s > %s || true' % [n, t.source, t.name]
     sh cmd
   end
@@ -57,6 +106,12 @@ end
 
 file "lib/ruby_lexer.rex.rb" => "lib/ruby_lexer.rex"
 
+task :parser do |t|
+  t.prerequisite_tasks.grep(Rake::FileTask).select(&:already_invoked).each do |f|
+    maybe_add_to_top f.name, "# frozen_string_literal: true"
+  end
+end
+
 task :generate => [:lexer, :parser]
 
 task :clean do
@@ -65,6 +120,7 @@ task :clean do
         Dir["coverage.info"] +
         Dir["coverage"] +
         Dir["lib/ruby2*_parser.y"] +
+        Dir["lib/ruby3*_parser.y"] +
         Dir["lib/*.output"])
 end
 
@@ -92,7 +148,7 @@ end
 
 def dl v
   dir = v[/^\d+\.\d+/]
-  url = "https://cache.ruby-lang.org/pub/ruby/#{dir}/ruby-#{v}.tar.bz2"
+  url = "https://cache.ruby-lang.org/pub/ruby/#{dir}/ruby-#{v}.tar.xz"
   path = File.basename url
   unless File.exist? path then
     system "curl -O #{url}"
@@ -104,7 +160,7 @@ def ruby_parse version
   rp_txt    = "rp#{v}.txt"
   mri_txt   = "mri#{v}.txt"
   parse_y   = "parse#{v}.y"
-  tarball   = "ruby-#{version}.tar.bz2"
+  tarball   = "ruby-#{version}.tar.xz"
   ruby_dir  = "ruby-#{version}"
   diff      = "diff#{v}.diff"
   rp_out    = "lib/ruby#{v}_parser.output"
@@ -124,15 +180,18 @@ def ruby_parse version
     end
   end
 
+  desc "fetch all tarballs"
+  task :fetch => c_tarball
+
   file c_parse_y => c_tarball do
     in_compare do
-      extract_glob = case version
-                     when /2\.7/
+      extract_glob = case
+                     when version > "2.7" then
                        "{id.h,parse.y,tool/{id2token.rb,lib/vpath.rb}}"
                      else
                        "{id.h,parse.y,tool/{id2token.rb,vpath.rb}}"
                      end
-      system "tar yxf #{tarball} #{ruby_dir}/#{extract_glob}"
+      system "tar Jxf #{tarball} #{ruby_dir}/#{extract_glob}"
 
       Dir.chdir ruby_dir do
         if File.exist? "tool/id2token.rb" then
@@ -141,15 +200,20 @@ def ruby_parse version
           sh "expand parse.y > ../#{parse_y}"
         end
 
-        ruby "-pi", "-e", 'gsub(/^%define\s+api\.pure/, "%pure-parser")', "../#{parse_y}"
+        ruby "-pi", "-e", 'gsub(/^%pure-parser/, "%define api.pure")', "../#{parse_y}"
       end
       sh "rm -rf #{ruby_dir}"
     end
   end
 
+  bison = Dir["/opt/homebrew/opt/bison/bin/bison",
+              "/usr/local/opt/bison/bin/bison",
+              `which bison`.chomp,
+             ].first
+
   file c_mri_txt => [c_parse_y, normalize] do
     in_compare do
-      sh "bison -r all #{parse_y}"
+      sh "#{bison} -r all #{parse_y}"
       sh "./normalize.rb parse#{v}.output > #{mri_txt}"
       rm ["parse#{v}.output", "parse#{v}.tab.c"]
     end
@@ -190,17 +254,51 @@ def ruby_parse version
   end
 end
 
+task :versions do
+  require "open-uri"
+  require "net/http" # avoid require issues in threads
+  require "net/https"
+
+  versions = VERS.map { |s| s.split(//).join "." }
+
+  base_url = "https://cache.ruby-lang.org/pub/ruby"
+
+  class Array
+    def human_sort
+      sort_by { |item| item.to_s.split(/(\d+)/).map { |e| [e.to_i, e] } }
+    end
+  end
+
+  versions = versions.map { |ver|
+    Thread.new {
+      URI
+        .parse("#{base_url}/#{ver}/")
+        .read
+        .scan(/ruby-\d+\.\d+\.\d+[-\w.]*?.tar.gz/)
+        .reject { |s| s =~ /-(?:rc|preview)\d/ }
+        .human_sort
+        .last
+        .delete_prefix("ruby-")
+        .delete_suffix ".tar.gz"
+    }
+  }.map(&:value).sort
+
+  puts versions.map { |v| "ruby_parse %p" % [v] }
+end
+
 ruby_parse "2.0.0-p648"
-ruby_parse "2.1.9"
-ruby_parse "2.2.9"
+ruby_parse "2.1.10"
+ruby_parse "2.2.10"
 ruby_parse "2.3.8"
-ruby_parse "2.4.9"
-ruby_parse "2.5.8"
-ruby_parse "2.6.6"
-ruby_parse "2.7.1"
+ruby_parse "2.4.10"
+ruby_parse "2.5.9"
+ruby_parse "2.6.9"
+ruby_parse "2.7.5"
+ruby_parse "3.0.3"
+ruby_parse "3.1.1"
 
 task :debug => :isolate do
-  ENV["V"] ||= V2.last
+  ENV["V"] ||= VERS.last
   Rake.application[:parser].invoke # this way we can have DEBUG set
   Rake.application[:lexer].invoke # this way we can have DEBUG set
 
@@ -215,7 +313,7 @@ task :debug => :isolate do
   time = (ENV["RP_TIMEOUT"] || 10).to_i
 
   n = ENV["BUG"]
-  file = (n && "bug#{n}.rb") || ENV["F"] || ENV["FILE"] || "bug.rb"
+  file = (n && "bug#{n}.rb") || ENV["F"] || ENV["FILE"] || "debug.rb"
   ruby = ENV["R"] || ENV["RUBY"]
 
   if ruby then
@@ -238,19 +336,22 @@ task :debug => :isolate do
 end
 
 task :debug3 do
-  file    = ENV["F"] || "bug.rb"
-  verbose = ENV["V"] ? "-v" : ""
+  file    = ENV["F"] || "debug.rb"
+  version = ENV["V"] || ""
+  verbose = ENV["VERBOSE"] ? "-v" : ""
   munge    = "./tools/munge.rb #{verbose}"
 
   abort "Need a file to parse, via: F=path.rb" unless file
 
   ENV.delete "V"
 
-  sh "ruby -v"
-  sh "ruby -y #{file} 2>&1 | #{munge} > tmp/ruby"
-  sh "./tools/ripper.rb -d #{file} | #{munge} > tmp/rip"
+  ruby = "ruby#{version}"
+
+  sh "#{ruby} -v"
+  sh "#{ruby} -y #{file} 2>&1 | #{munge} > tmp/ruby"
+  sh "#{ruby} ./tools/ripper.rb -d #{file} | #{munge} > tmp/rip"
   sh "rake debug F=#{file} DEBUG=1 2>&1 | #{munge} > tmp/rp"
-  sh "diff -U 999 -d tmp/{rip,rp}"
+  sh "diff -U 999 -d tmp/{ruby,rp}"
 end
 
 task :cmp do
@@ -262,16 +363,25 @@ task :cmp3 do
 end
 
 task :extract => :isolate do
-  ENV["V"] ||= V2.last
+  ENV["V"] ||= VERS.last
   Rake.application[:parser].invoke # this way we can have DEBUG set
 
-  file = ENV["F"] || ENV["FILE"]
+  file = ENV["F"] || ENV["FILE"] || abort("Need to provide F=<path>")
 
   ruby "-Ilib", "bin/ruby_parse_extract_error", file
 end
 
+task :parse => :isolate do
+  ENV["V"] ||= VERS.last
+  Rake.application[:parser].invoke # this way we can have DEBUG set
+
+  file = ENV["F"] || ENV["FILE"] || abort("Need to provide F=<path>")
+
+  ruby "-Ilib", "bin/ruby_parse", file
+end
+
 task :bugs do
-  sh "for f in bug*.rb ; do #{Gem.ruby} -S rake debug F=$f && rm $f ; done"
+  sh "for f in bug*.rb bad*.rb ; do #{Gem.ruby} -S rake debug F=$f && rm $f ; done"
 end
 
 # vim: syntax=Ruby

data/bin/ruby_parse_extract_error

@@ -21,7 +21,7 @@ class RubyParser
     src = ss.string
     pre_error = src[0...ss.pos]
 
-    defs = pre_error.grep(/^ *(?:def|it)/)
+    defs = pre_error.lines.grep(/^ *(?:def|it)/)
 
     raise "can't figure out where the bad code starts" unless defs.last
 

data/compare/normalize.rb

@@ -84,6 +84,7 @@ def munge s
 
              "' '",             "tSPACE", # needs to be later to avoid bad hits
 
+             "%empty",          "none", # newer bison
              "/* empty */",     "none",
              /^\s*$/,           "none",
 
@@ -140,6 +141,7 @@ def munge s
              '"do for block"',     "kDO_BLOCK",
              '"do for condition"', "kDO_COND",
              '"do for lambda"',    "kDO_LAMBDA",
+             "tLABEL",             "kLABEL",
 
              # UGH
              "k_LINE__",       "k__LINE__",
@@ -155,7 +157,10 @@ def munge s
              /\"(\w+) \(?modifier\)?\"/, proc { |x| "k#{$1.upcase}_MOD" },
              /\"(\w+)\"/,                proc { |x| "k#{$1.upcase}" },
 
-             /@(\d+)(\s+|$)/,       "",
+             /\$?@(\d+)(\s+|$)/,    "", # newer bison
+
+             # TODO: remove for 3.0 work:
+             "lex_ctxt ", "" # 3.0 production that's mostly noise right now
             ]
 
   renames.each_slice(2) do |(a, b)|
@@ -174,7 +179,7 @@ ARGF.each_line do |line|
 
   case line.strip
   when /^$/ then
-  when /^(\d+) (\$?\w+): (.*)/ then    # yacc
+  when /^(\d+) (\$?[@\w]+): (.*)/ then    # yacc
     rule = $2
     order << rule unless rules.has_key? rule
     rules[rule] << munge($3)
@@ -199,7 +204,7 @@ ARGF.each_line do |line|
   when /^\cL/ then                     # byacc
     break
   else
-    warn "unparsed: #{$.}: #{line.chomp}"
+    warn "unparsed: #{$.}: #{line.strip.inspect}"
   end
 end