From fcbf63e62c627deae76c1b8cb8c0876c536ed811 Mon Sep 17 00:00:00 2001 From: Jari Vetoniemi Date: Mon, 16 Mar 2020 18:49:26 +0900 Subject: Fresh start --- jni/ruby/ext/ripper/lib/ripper.rb | 73 ++++++++++++ jni/ruby/ext/ripper/lib/ripper/core.rb | 70 ++++++++++++ jni/ruby/ext/ripper/lib/ripper/filter.rb | 77 +++++++++++++ jni/ruby/ext/ripper/lib/ripper/lexer.rb | 186 +++++++++++++++++++++++++++++++ jni/ruby/ext/ripper/lib/ripper/sexp.rb | 118 ++++++++++++++++++++ 5 files changed, 524 insertions(+) create mode 100644 jni/ruby/ext/ripper/lib/ripper.rb create mode 100644 jni/ruby/ext/ripper/lib/ripper/core.rb create mode 100644 jni/ruby/ext/ripper/lib/ripper/filter.rb create mode 100644 jni/ruby/ext/ripper/lib/ripper/lexer.rb create mode 100644 jni/ruby/ext/ripper/lib/ripper/sexp.rb (limited to 'jni/ruby/ext/ripper/lib') diff --git a/jni/ruby/ext/ripper/lib/ripper.rb b/jni/ruby/ext/ripper/lib/ripper.rb new file mode 100644 index 0000000..542bd40 --- /dev/null +++ b/jni/ruby/ext/ripper/lib/ripper.rb @@ -0,0 +1,73 @@ +require 'ripper/core' +require 'ripper/lexer' +require 'ripper/filter' +require 'ripper/sexp' + +# Ripper is a Ruby script parser. +# +# You can get information from the parser with event-based style. +# Information such as abstract syntax trees or simple lexical analysis of the +# Ruby program. +# +# == Usage +# +# Ripper provides an easy interface for parsing your program into a symbolic +# expression tree (or S-expression). +# +# Understanding the output of the parser may come as a challenge, it's +# recommended you use PP to format the output for legibility. +# +# require 'ripper' +# require 'pp' +# +# pp Ripper.sexp('def hello(world) "Hello, #{world}!"; end') +# #=> [:program, +# [[:def, +# [:@ident, "hello", [1, 4]], +# [:paren, +# [:params, [[:@ident, "world", [1, 10]]], nil, nil, nil, nil, nil, nil]], +# [:bodystmt, +# [[:string_literal, +# [:string_content, +# [:@tstring_content, "Hello, ", [1, 18]], +# [:string_embexpr, [[:var_ref, [:@ident, "world", [1, 27]]]]], +# [:@tstring_content, "!", [1, 33]]]]], +# nil, +# nil, +# nil]]]] +# +# You can see in the example above, the expression starts with +:program+. +# +# From here, a method definition at +:def+, followed by the method's identifier +# :@ident. After the method's identifier comes the parentheses +# +:paren+ and the method parameters under +:params+. +# +# Next is the method body, starting at +:bodystmt+ (+stmt+ meaning statement), +# which contains the full definition of the method. +# +# In our case, we're simply returning a String, so next we have the +# +:string_literal+ expression. +# +# Within our +:string_literal+ you'll notice two @tstring_content, +# this is the literal part for Hello, and !. Between +# the two @tstring_content statements is a +:string_embexpr+, +# where _embexpr_ is an embedded expression. Our expression consists of a local +# variable, or +var_ref+, with the identifier (@ident) of +world+. +# +# == Resources +# +# * {Ruby Inside}[http://www.rubyinside.com/using-ripper-to-see-how-ruby-is-parsing-your-code-5270.html] +# +# == Requirements +# +# * ruby 1.9 (support CVS HEAD only) +# * bison 1.28 or later (Other yaccs do not work) +# +# == License +# +# Ruby License. +# +# Minero Aoki +# aamine@loveruby.net +# http://i.loveruby.net +class Ripper; end diff --git a/jni/ruby/ext/ripper/lib/ripper/core.rb b/jni/ruby/ext/ripper/lib/ripper/core.rb new file mode 100644 index 0000000..008ec53 --- /dev/null +++ b/jni/ruby/ext/ripper/lib/ripper/core.rb @@ -0,0 +1,70 @@ +# +# $Id: core.rb 36954 2012-09-12 23:04:41Z zzak $ +# +# Copyright (c) 2003-2005 Minero Aoki +# +# This program is free software. +# You can distribute and/or modify this program under the Ruby License. +# For details of Ruby License, see ruby/COPYING. +# + +require 'ripper.so' + +class Ripper + + # Parses the given Ruby program read from +src+. + # +src+ must be a String or an IO or a object with a #gets method. + def Ripper.parse(src, filename = '(ripper)', lineno = 1) + new(src, filename, lineno).parse + end + + # This array contains name of parser events. + PARSER_EVENTS = PARSER_EVENT_TABLE.keys + + # This array contains name of scanner events. + SCANNER_EVENTS = SCANNER_EVENT_TABLE.keys + + # This array contains name of all ripper events. + EVENTS = PARSER_EVENTS + SCANNER_EVENTS + + private + + # + # Parser Events + # + + PARSER_EVENT_TABLE.each do |id, arity| + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{id}(#{ ('a'..'z').to_a[0, arity].join(', ') }) + #{arity == 0 ? 'nil' : 'a'} + end + End + end + + # This method is called when weak warning is produced by the parser. + # +fmt+ and +args+ is printf style. + def warn(fmt, *args) + end + + # This method is called when strong warning is produced by the parser. + # +fmt+ and +args+ is printf style. + def warning(fmt, *args) + end + + # This method is called when the parser found syntax error. + def compile_error(msg) + end + + # + # Scanner Events + # + + SCANNER_EVENTS.each do |id| + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{id}(token) + token + end + End + end + +end diff --git a/jni/ruby/ext/ripper/lib/ripper/filter.rb b/jni/ruby/ext/ripper/lib/ripper/filter.rb new file mode 100644 index 0000000..b30b085 --- /dev/null +++ b/jni/ruby/ext/ripper/lib/ripper/filter.rb @@ -0,0 +1,77 @@ +# +# $Id: filter.rb 36954 2012-09-12 23:04:41Z zzak $ +# +# Copyright (c) 2004,2005 Minero Aoki +# +# This program is free software. +# You can distribute and/or modify this program under the Ruby License. +# For details of Ruby License, see ruby/COPYING. +# + +require 'ripper/lexer' + +class Ripper + + # This class handles only scanner events, + # which are dispatched in the 'right' order (same with input). + class Filter + + # Creates a new Ripper::Filter instance, passes parameters +src+, + # +filename+, and +lineno+ to Ripper::Lexer.new + # + # The lexer is for internal use only. + def initialize(src, filename = '-', lineno = 1) + @__lexer = Lexer.new(src, filename, lineno) + @__line = nil + @__col = nil + end + + # The file name of the input. + def filename + @__lexer.filename + end + + # The line number of the current token. + # This value starts from 1. + # This method is valid only in event handlers. + def lineno + @__line + end + + # The column number of the current token. + # This value starts from 0. + # This method is valid only in event handlers. + def column + @__col + end + + # Starts the parser. + # +init+ is a data accumulator and is passed to the next event handler (as + # of Enumerable#inject). + def parse(init = nil) + data = init + @__lexer.lex.each do |pos, event, tok| + @__line, @__col = *pos + data = if respond_to?(event, true) + then __send__(event, tok, data) + else on_default(event, tok, data) + end + end + data + end + + private + + # This method is called when some event handler is undefined. + # +event+ is :on_XXX, +token+ is the scanned token, and +data+ is a data + # accumulator. + # + # The return value of this method is passed to the next event handler (as + # of Enumerable#inject). + def on_default(event, token, data) + data + end + + end + +end diff --git a/jni/ruby/ext/ripper/lib/ripper/lexer.rb b/jni/ruby/ext/ripper/lib/ripper/lexer.rb new file mode 100644 index 0000000..38b2087 --- /dev/null +++ b/jni/ruby/ext/ripper/lib/ripper/lexer.rb @@ -0,0 +1,186 @@ +# +# $Id: lexer.rb 44878 2014-02-07 12:57:44Z zzak $ +# +# Copyright (c) 2004,2005 Minero Aoki +# +# This program is free software. +# You can distribute and/or modify this program under the Ruby License. +# For details of Ruby License, see ruby/COPYING. +# + +require 'ripper/core' + +class Ripper + + # Tokenizes the Ruby program and returns an array of strings. + # + # p Ripper.tokenize("def m(a) nil end") + # # => ["def", " ", "m", "(", "a", ")", " ", "nil", " ", "end"] + # + def Ripper.tokenize(src, filename = '-', lineno = 1) + Lexer.new(src, filename, lineno).tokenize + end + + # Tokenizes the Ruby program and returns an array of an array, + # which is formatted like [[lineno, column], type, token]. + # + # require 'ripper' + # require 'pp' + # + # pp Ripper.lex("def m(a) nil end") + # #=> [[[1, 0], :on_kw, "def"], + # [[1, 3], :on_sp, " " ], + # [[1, 4], :on_ident, "m" ], + # [[1, 5], :on_lparen, "(" ], + # [[1, 6], :on_ident, "a" ], + # [[1, 7], :on_rparen, ")" ], + # [[1, 8], :on_sp, " " ], + # [[1, 9], :on_kw, "nil"], + # [[1, 12], :on_sp, " " ], + # [[1, 13], :on_kw, "end"]] + # + def Ripper.lex(src, filename = '-', lineno = 1) + Lexer.new(src, filename, lineno).lex + end + + class Lexer < ::Ripper #:nodoc: internal use only + def tokenize + lex().map {|pos, event, tok| tok } + end + + def lex + parse().sort_by {|pos, event, tok| pos } + end + + def parse + @buf = [] + super + @buf + end + + private + + SCANNER_EVENTS.each do |event| + module_eval(<<-End, __FILE__+'/module_eval', __LINE__ + 1) + def on_#{event}(tok) + @buf.push [[lineno(), column()], :on_#{event}, tok] + end + End + end + end + + # [EXPERIMENTAL] + # Parses +src+ and return a string which was matched to +pattern+. + # +pattern+ should be described as Regexp. + # + # require 'ripper' + # + # p Ripper.slice('def m(a) nil end', 'ident') #=> "m" + # p Ripper.slice('def m(a) nil end', '[ident lparen rparen]+') #=> "m(a)" + # p Ripper.slice("< "string\n" + # + def Ripper.slice(src, pattern, n = 0) + if m = token_match(src, pattern) + then m.string(n) + else nil + end + end + + def Ripper.token_match(src, pattern) #:nodoc: + TokenPattern.compile(pattern).match(src) + end + + class TokenPattern #:nodoc: + + class Error < ::StandardError # :nodoc: + end + class CompileError < Error # :nodoc: + end + class MatchError < Error # :nodoc: + end + + class << self + alias compile new + end + + def initialize(pattern) + @source = pattern + @re = compile(pattern) + end + + def match(str) + match_list(::Ripper.lex(str)) + end + + def match_list(tokens) + if m = @re.match(map_tokens(tokens)) + then MatchData.new(tokens, m) + else nil + end + end + + private + + def compile(pattern) + if m = /[^\w\s$()\[\]{}?*+\.]/.match(pattern) + raise CompileError, "invalid char in pattern: #{m[0].inspect}" + end + buf = '' + pattern.scan(/(?:\w+|\$\(|[()\[\]\{\}?*+\.]+)/) do |tok| + case tok + when /\w/ + buf.concat map_token(tok) + when '$(' + buf.concat '(' + when '(' + buf.concat '(?:' + when /[?*\[\])\.]/ + buf.concat tok + else + raise 'must not happen' + end + end + Regexp.compile(buf) + rescue RegexpError => err + raise CompileError, err.message + end + + def map_tokens(tokens) + tokens.map {|pos,type,str| map_token(type.to_s.sub(/\Aon_/,'')) }.join + end + + MAP = {} + seed = ('a'..'z').to_a + ('A'..'Z').to_a + ('0'..'9').to_a + SCANNER_EVENT_TABLE.each do |ev, | + raise CompileError, "[RIPPER FATAL] too many system token" if seed.empty? + MAP[ev.to_s.sub(/\Aon_/,'')] = seed.shift + end + + def map_token(tok) + MAP[tok] or raise CompileError, "unknown token: #{tok}" + end + + class MatchData # :nodoc: + def initialize(tokens, match) + @tokens = tokens + @match = match + end + + def string(n = 0) + return nil unless @match + match(n).join + end + + private + + def match(n = 0) + return [] unless @match + @tokens[@match.begin(n)...@match.end(n)].map {|pos,type,str| str } + end + end + + end + +end diff --git a/jni/ruby/ext/ripper/lib/ripper/sexp.rb b/jni/ruby/ext/ripper/lib/ripper/sexp.rb new file mode 100644 index 0000000..514a585 --- /dev/null +++ b/jni/ruby/ext/ripper/lib/ripper/sexp.rb @@ -0,0 +1,118 @@ +# +# $Id: sexp.rb 48144 2014-10-26 03:24:18Z nobu $ +# +# Copyright (c) 2004,2005 Minero Aoki +# +# This program is free software. +# You can distribute and/or modify this program under the Ruby License. +# For details of Ruby License, see ruby/COPYING. +# + +require 'ripper/core' + +class Ripper + + # [EXPERIMENTAL] + # Parses +src+ and create S-exp tree. + # Returns more readable tree rather than Ripper.sexp_raw. + # This method is mainly for developer use. + # + # require 'ripper' + # require 'pp' + # + # pp Ripper.sexp("def m(a) nil end") + # #=> [:program, + # [[:def, + # [:@ident, "m", [1, 4]], + # [:paren, [:params, [[:@ident, "a", [1, 6]]], nil, nil, nil, nil]], + # [:bodystmt, [[:var_ref, [:@kw, "nil", [1, 9]]]], nil, nil, nil]]]] + # + def Ripper.sexp(src, filename = '-', lineno = 1) + builder = SexpBuilderPP.new(src, filename, lineno) + sexp = builder.parse + sexp unless builder.error? + end + + # [EXPERIMENTAL] + # Parses +src+ and create S-exp tree. + # This method is mainly for developer use. + # + # require 'ripper' + # require 'pp' + # + # pp Ripper.sexp_raw("def m(a) nil end") + # #=> [:program, + # [:stmts_add, + # [:stmts_new], + # [:def, + # [:@ident, "m", [1, 4]], + # [:paren, [:params, [[:@ident, "a", [1, 6]]], nil, nil, nil]], + # [:bodystmt, + # [:stmts_add, [:stmts_new], [:var_ref, [:@kw, "nil", [1, 9]]]], + # nil, + # nil, + # nil]]]] + # + def Ripper.sexp_raw(src, filename = '-', lineno = 1) + builder = SexpBuilder.new(src, filename, lineno) + sexp = builder.parse + sexp unless builder.error? + end + + class SexpBuilderPP < ::Ripper #:nodoc: + private + + PARSER_EVENT_TABLE.each do |event, arity| + if /_new\z/ =~ event.to_s and arity == 0 + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event} + [] + end + End + elsif /_add\z/ =~ event.to_s + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event}(list, item) + list.push item + list + end + End + else + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event}(*args) + [:#{event}, *args] + end + End + end + end + + SCANNER_EVENTS.each do |event| + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event}(tok) + [:@#{event}, tok, [lineno(), column()]] + end + End + end + end + + class SexpBuilder < ::Ripper #:nodoc: + private + + PARSER_EVENTS.each do |event| + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event}(*args) + args.unshift :#{event} + args + end + End + end + + SCANNER_EVENTS.each do |event| + module_eval(<<-End, __FILE__, __LINE__ + 1) + def on_#{event}(tok) + [:@#{event}, tok, [lineno(), column()]] + end + End + end + end + +end -- cgit v1.2.3-70-g09d2