diff options
Diffstat (limited to 'misc')
34 files changed, 3007 insertions, 2608 deletions
diff --git a/misc/.vscode/launch.json b/misc/.vscode/launch.json new file mode 100644 index 0000000000..51bfef09d7 --- /dev/null +++ b/misc/.vscode/launch.json @@ -0,0 +1,13 @@ +{ + "version": "0.2.0", + "configurations": [ + { + "type": "lldb", + "name": "Run ruby", + "request": "launch", + "program": "${workspaceFolder}/ruby", + "args": ["test.rb"], + "preLaunchTask": "${defaultBuildTask}" + } + ] +} diff --git a/misc/.vscode/settings.json b/misc/.vscode/settings.json new file mode 100644 index 0000000000..a2e4e1ec69 --- /dev/null +++ b/misc/.vscode/settings.json @@ -0,0 +1,10 @@ +{ + "rust-analyzer.cargo.features": [ + "disasm", + ], + "rust-analyzer.cfg.setTest": false, + // rust-analyzer bundled in the VSCode extension may only support Rust newer than 1.85.0. + // To avoid warnings, install rust-analyzer with `rustup component add rust-analyzer` and + // use `~/.cargo/bin/rust-analyzer` with the following config. + "rust-analyzer.server.path": "rust-analyzer", +} diff --git a/misc/.vscode/tasks.json b/misc/.vscode/tasks.json new file mode 100644 index 0000000000..045fe7e5c0 --- /dev/null +++ b/misc/.vscode/tasks.json @@ -0,0 +1,14 @@ +{ + "version": "2.0.0", + "tasks": [ + { + "label": "build", + "type": "shell", + "command": "make -j", + "group": { + "kind": "build", + "isDefault": true + } + } + ] +} diff --git a/misc/README b/misc/README index 93d1de90b2..86b680e724 100644 --- a/misc/README +++ b/misc/README @@ -1,12 +1,7 @@ -README this file -inf-ruby.el program to run ruby under emacs -rb_optparse.bash bash completion script -rb_optparse.zsh zsh completion script -rdoc-mode.el RDoc mode for emacs -ruby-mode.el ruby mode for emacs -ruby-style.el Ruby's C/C++ mode style for emacs -rubydb2x.el ruby debugger support for emacs 19.2x or before -rubydb3x.el ruby debugger support for emacs 19.3x or later -ruby-electric.el emacs minor mode providing electric commands - -Check out http://rubyforge.org/projects/ruby-debug/ also. +README this file +rb_optparse.bash bash completion script +rb_optparse.zsh zsh completion script +ruby-style.el Ruby's C/C++ mode style for emacs +lldb_cruby.py LLDB port of debug utility +test_lldb_cruby.rb test file for LLDB port +.vscode example VSCode config to debug Ruby diff --git a/misc/call_fuzzer.rb b/misc/call_fuzzer.rb new file mode 100644 index 0000000000..c3f9f90490 --- /dev/null +++ b/misc/call_fuzzer.rb @@ -0,0 +1,372 @@ +require 'optparse' +require 'set' + +# Number of iterations to test +num_iters = 10_000 + +# Parse the command-line options +OptionParser.new do |opts| + opts.on("--num-iters=N") do |n| + num_iters = n.to_i + end +end.parse! + +# Format large numbers with comma separators for readability +def format_number(pad, number) + s = number.to_s + i = s.index('.') || s.size + s.insert(i -= 3, ',') while i > 3 + s.rjust(pad, ' ') +end + +# Wrap an integer to pass as argument +# We use this so we can have some object arguments +class IntWrapper + def initialize(v) + # Force the object to have a random shape + if rand() < 50 + @v0 = 1 + end + if rand() < 50 + @v1 = 1 + end + if rand() < 50 + @v2 = 1 + end + if rand() < 50 + @v3 = 1 + end + if rand() < 50 + @v4 = 1 + end + if rand() < 50 + @v5 = 1 + end + if rand() < 50 + @v6 = 1 + end + + @value = v + end + + attr_reader :value +end + +# Generate a random argument value, integer or string or object +def sample_arg() + c = ['int', 'string', 'object'].sample() + + if c == 'int' + return rand(0...100) + end + + if c == 'string' + return 'f' * rand(0...100) + end + + if c == 'object' + return IntWrapper.new(rand(0...100)) + end + + raise "should not get here" +end + +# Evaluate the value of an argument with respect to the checksum +def arg_val(arg) + if arg.kind_of? Integer + return arg + end + + if arg.kind_of? String + return arg.length + end + + if arg.kind_of? Object + return arg.value + end + + raise "unknown arg type" +end + +# List of parameters/arguments for a method +class ParamList + def initialize() + self.sample_params() + self.sample_args() + end + + # Sample/generate a random set of parameters for a method + def sample_params() + # Choose how many positional arguments to use, and how many are optional + num_pargs = rand(10) + @opt_parg_idx = rand(num_pargs) + @num_opt_pargs = rand(num_pargs + 1 - @opt_parg_idx) + @num_pargs_req = num_pargs - @num_opt_pargs + @pargs = (0...num_pargs).map do |i| + { + :name => "p#{i}", + :optional => (i >= @opt_parg_idx && i < @opt_parg_idx + @num_opt_pargs) + } + end + + # Choose how many kwargs to use, and how many are optional + num_kwargs = rand(10) + @kwargs = (0...num_kwargs).map do |i| + { + :name => "k#{i}", + :optional => rand() < 0.5 + } + end + + # Choose whether to have rest parameters or not + @has_rest = @num_opt_pargs == 0 && rand() < 0.5 + @has_kwrest = rand() < 0.25 + + # Choose whether to have a named block parameter or not + @has_block_param = rand() < 0.25 + end + + # Sample/generate a random set of arguments corresponding to the parameters + def sample_args() + # Choose how many positional args to pass + num_pargs_passed = rand(@num_pargs_req..@pargs.size) + + # How many optional arguments will be filled + opt_pargs_filled = num_pargs_passed - @num_pargs_req + + @pargs.each_with_index do |parg, i| + if parg[:optional] + parg[:default] = rand(100) + end + + if !parg[:optional] || i < @opt_parg_idx + opt_pargs_filled + parg[:argval] = rand(100) + end + end + + @kwargs.each_with_index do |kwarg, i| + if kwarg[:optional] + kwarg[:default] = rand(100) + end + + if !kwarg[:optional] || rand() < 0.5 + kwarg[:argval] = rand(100) + end + end + + # Randomly pass a block or not + @block_arg = nil + if rand() < 0.5 + @block_arg = rand(100) + end + end + + # Compute the expected checksum of arguments ahead of time + def compute_checksum() + checksum = 0 + + @pargs.each_with_index do |arg, i| + value = (arg.key? :argval)? arg[:argval]:arg[:default] + checksum += (i+1) * arg_val(value) + end + + @kwargs.each_with_index do |arg, i| + value = (arg.key? :argval)? arg[:argval]:arg[:default] + checksum += (i+1) * arg_val(value) + end + + if @block_arg + if @has_block_param + checksum += arg_val(@block_arg) + end + + checksum += arg_val(@block_arg) + end + + checksum + end + + # Generate code for the method signature and method body + def gen_method_str() + m_str = "def m(" + + @pargs.each do |arg| + if !m_str.end_with?("(") + m_str += ", " + end + + m_str += arg[:name] + + # If this has a default value + if arg[:optional] + m_str += " = #{arg[:default]}" + end + end + + if @has_rest + if !m_str.end_with?("(") + m_str += ", " + end + m_str += "*rest" + end + + @kwargs.each do |arg| + if !m_str.end_with?("(") + m_str += ", " + end + + m_str += "#{arg[:name]}:" + + # If this has a default value + if arg[:optional] + m_str += " #{arg[:default]}" + end + end + + if @has_kwrest + if !m_str.end_with?("(") + m_str += ", " + end + m_str += "**kwrest" + end + + if @has_block_param + if !m_str.end_with?("(") + m_str += ", " + end + + m_str += "&block" + end + + m_str += ")\n" + + # Add some useless locals + rand(0...16).times do |i| + m_str += "local#{i} = #{i}\n" + end + + # Add some useless if statements + @pargs.each_with_index do |arg, i| + if rand() < 50 + m_str += "if #{arg[:name]} > 4; end\n" + end + end + + m_str += "checksum = 0\n" + + @pargs.each_with_index do |arg, i| + m_str += "checksum += #{i+1} * arg_val(#{arg[:name]})\n" + end + + @kwargs.each_with_index do |arg, i| + m_str += "checksum += #{i+1} * arg_val(#{arg[:name]})\n" + end + + if @has_block_param + m_str += "if block; r = block.call; checksum += arg_val(r); end\n" + end + + m_str += "if block_given?; r = yield; checksum += arg_val(r); end\n" + + if @has_rest + m_str += "raise 'rest is not array' unless rest.kind_of?(Array)\n" + m_str += "raise 'rest size not integer' unless rest.size.kind_of?(Integer)\n" + end + + if @has_kwrest + m_str += "raise 'kwrest is not a hash' unless kwrest.kind_of?(Hash)\n" + m_str += "raise 'kwrest size not integer' unless kwrest.size.kind_of?(Integer)\n" + end + + m_str += "checksum\n" + m_str += "end" + + m_str + end + + # Generate code to call into the method and pass the arguments + def gen_call_str() + c_str = "m(" + + @pargs.each_with_index do |arg, i| + if !arg.key? :argval + next + end + + if !c_str.end_with?("(") + c_str += ", " + end + + c_str += "#{arg[:argval]}" + end + + @kwargs.each_with_index do |arg, i| + if !arg.key? :argval + next + end + + if !c_str.end_with?("(") + c_str += ", " + end + + c_str += "#{arg[:name]}: #{arg[:argval]}" + end + + c_str += ")" + + # Randomly pass a block or not + if @block_arg + c_str += " { #{@block_arg} }" + end + + c_str + end +end + +iseqs_compiled_start = RubyVM::YJIT.runtime_stats[:compiled_iseq_entry] +start_time = Time.now.to_f + +num_iters.times do |i| + puts "Iteration #{i}" + + lst = ParamList.new() + m_str = lst.gen_method_str() + c_str = lst.gen_call_str() + checksum = lst.compute_checksum() + + f = Object.new + + # Define the method on f + puts "Defining" + p m_str + f.instance_eval(m_str) + #puts RubyVM::InstructionSequence.disasm(f.method(:m)) + #exit 0 + + puts "Calling" + c_str = "f.#{c_str}" + p c_str + r = eval(c_str) + puts "checksum=#{r}" + + if r != checksum + raise "return value #{r} doesn't match checksum #{checksum}" + end + + puts "" +end + +# Make sure that YJIT actually compiled the tests we ran +# Should be run with --yjit-call-threshold=1 +iseqs_compiled_end = RubyVM::YJIT.runtime_stats[:compiled_iseq_entry] +if iseqs_compiled_end - iseqs_compiled_start < num_iters + raise "YJIT did not compile enough ISEQs" +end + +puts "Code region size: #{ format_number(0, RubyVM::YJIT.runtime_stats[:code_region_size]) }" + +end_time = Time.now.to_f +itrs_per_sec = num_iters / (end_time - start_time) +itrs_per_hour = 3600 * itrs_per_sec +puts "#{'%.1f' % itrs_per_sec} iterations/s" +puts "#{format_number(0, itrs_per_hour.round)} iterations/hour" diff --git a/misc/call_fuzzer.sh b/misc/call_fuzzer.sh new file mode 100755 index 0000000000..cf4ec76fe8 --- /dev/null +++ b/misc/call_fuzzer.sh @@ -0,0 +1,13 @@ +# Stop at first error +set -e + +# TODO +# TODO: boost --num-iters to 1M+ for actual test +# TODO +export NUM_ITERS=25000 + +# Enable code GC so we don't stop compiling when we hit the code size limit +ruby --yjit-call-threshold=1 --yjit-code-gc misc/call_fuzzer.rb --num-iters=$NUM_ITERS + +# Do another pass with --verify-ctx +ruby --yjit-call-threshold=1 --yjit-code-gc --yjit-verify-ctx misc/call_fuzzer.rb --num-iters=$NUM_ITERS diff --git a/misc/expand_tabs.rb b/misc/expand_tabs.rb new file mode 100755 index 0000000000..d26568eefc --- /dev/null +++ b/misc/expand_tabs.rb @@ -0,0 +1,178 @@ +#!/usr/bin/env ruby --disable-gems +# Add the following line to your `.git/hooks/pre-commit`: +# +# $ ruby --disable-gems misc/expand_tabs.rb +# + +require 'shellwords' +require 'tmpdir' +ENV['LC_ALL'] = 'C' + +class Git + def initialize(oldrev, newrev) + @oldrev = oldrev + @newrev = newrev + end + + # ["foo/bar.c", "baz.h", ...] + def updated_paths + with_clean_env do + IO.popen(['git', 'diff', '--cached', '--name-only', @newrev], &:readlines).each(&:chomp!) + end + end + + # [0, 1, 4, ...] + def updated_lines(file) + lines = [] + revs_pattern = ("0"*40) + " " + with_clean_env { IO.popen(['git', 'blame', '-l', '--', file], &:readlines) }.each_with_index do |line, index| + if line.b.start_with?(revs_pattern) + lines << index + end + end + lines + end + + def add(file) + git('add', file) + end + + def toplevel + IO.popen(['git', 'rev-parse', '--show-toplevel'], &:read).chomp + end + + private + + def git(*args) + cmd = ['git', *args].shelljoin + unless with_clean_env { system(cmd) } + abort "Failed to run: #{cmd}" + end + end + + def with_clean_env + git_dir = ENV.delete('GIT_DIR') # this overcomes '-C' or pwd + yield + ensure + ENV['GIT_DIR'] = git_dir if git_dir + end +end + +DEFAULT_GEM_LIBS = %w[ + bundler + delegate + did_you_mean + english + erb + error_highlight + fileutils + find + forwardable + ipaddr + net-http + net-protocol + open3 + open-uri + optparse + ostruct + pp + prettyprint + prism + resolv + rubygems + securerandom + shellwords + singleton + tempfile + time + timeout + tmpdir + un + tsort + uri + weakref + yaml +] + +DEFAULT_GEM_EXTS = %w[ + date + digest + etc + fcntl + io-console + io-nonblock + io-wait + json + openssl + pathname + psych + stringio + strscan + zlib +] + +EXPANDTAB_IGNORED_FILES = [ + # default gems whose master is GitHub + %r{\Abin/(?!erb)\w+\z}, + *DEFAULT_GEM_LIBS.flat_map { |lib| + [ + %r{\Alib/#{lib}/}, + %r{\Alib/#{lib}\.gemspec\z}, + %r{\Alib/#{lib}\.rb\z}, + %r{\Atest/#{lib}/}, + ] + }, + *DEFAULT_GEM_EXTS.flat_map { |ext| + [ + %r{\Aext/#{ext}/}, + %r{\Atest/#{ext}/}, + ] + }, + + # vendoring (ccan) + %r{\Accan/}, + + # vendoring (onigmo) + %r{\Aenc/}, + %r{\Ainclude/ruby/onigmo\.h\z}, + %r{\Areg.+\.(c|h)\z}, + + # explicit or implicit `c-file-style: "linux"` + %r{\Aaddr2line\.c\z}, + %r{\Amissing/}, + %r{\Astrftime\.c\z}, + %r{\Avsnprintf\.c\z}, +] + +git = Git.new('HEAD^', 'HEAD') + +Dir.chdir(git.toplevel) do + paths = git.updated_paths + paths.select! {|f| + (f.end_with?('.c') || f.end_with?('.h') || f == 'insns.def') && EXPANDTAB_IGNORED_FILES.all? { |re| !f.match(re) } + } + files = paths.select {|n| File.file?(n)} + exit if files.empty? + + files.each do |f| + src = File.binread(f) rescue next + + expanded = false + updated_lines = git.updated_lines(f) + unless updated_lines.empty? + src.gsub!(/^.*$/).with_index do |line, lineno| + if updated_lines.include?(lineno) && line.start_with?("\t") # last-committed line with hard tabs + expanded = true + line.sub(/\A\t+/) { |tabs| ' ' * (8 * tabs.length) } + else + line + end + end + end + + if expanded + File.binwrite(f, src) + git.add(f) + end + end +end diff --git a/misc/gdb.py b/misc/gdb.py new file mode 100644 index 0000000000..6034a389bb --- /dev/null +++ b/misc/gdb.py @@ -0,0 +1,181 @@ +import argparse +import textwrap + +# usage: [-h] [-a | --all | --no-all] [-s STACK_SIZE] [uplevel] +# +# Dump a control frame +# +# positional arguments: +# uplevel CFP offset from the stack top +# +# options: +# -h, --help show this help message and exit +# -a, --all, --no-all dump all frames +# -s STACK_SIZE, --stack-size STACK_SIZE +# override stack_size (useful for JIT frames) +class CFP(gdb.Command): + FRAME_MAGICS = [ + # frame types + 'VM_FRAME_MAGIC_METHOD', + 'VM_FRAME_MAGIC_BLOCK', + 'VM_FRAME_MAGIC_CLASS', + 'VM_FRAME_MAGIC_TOP', + 'VM_FRAME_MAGIC_CFUNC', + 'VM_FRAME_MAGIC_IFUNC', + 'VM_FRAME_MAGIC_EVAL', + 'VM_FRAME_MAGIC_RESCUE', + 'VM_FRAME_MAGIC_DUMMY', + ] + FRAME_FLAGS = [ + # frame flag + 'VM_FRAME_FLAG_FINISH', + 'VM_FRAME_FLAG_BMETHOD', + 'VM_FRAME_FLAG_CFRAME', + 'VM_FRAME_FLAG_LAMBDA', + 'VM_FRAME_FLAG_MODIFIED_BLOCK_PARAM', + 'VM_FRAME_FLAG_CFRAME_KW', + 'VM_FRAME_FLAG_PASSED', + # env flag + 'VM_ENV_FLAG_LOCAL', + 'VM_ENV_FLAG_ESCAPED', + 'VM_ENV_FLAG_WB_REQUIRED', + 'VM_ENV_FLAG_ISOLATED', + ] + + def __init__(self): + super(CFP, self).__init__('cfp', gdb.COMMAND_USER) + + self.parser = argparse.ArgumentParser(description='Dump a control frame') + self.parser.add_argument('uplevel', type=int, nargs='?', default=0, help='CFP offset from the stack top') + self.parser.add_argument('-a', '--all', action=argparse.BooleanOptionalAction, help='dump all frames') + self.parser.add_argument('-s', '--stack-size', type=int, help='override stack_size (useful for JIT frames)') + + def invoke(self, args, from_tty): + try: + args = self.parser.parse_args(args.split()) + except SystemExit: + return + cfp = f'(ruby_current_ec->cfp + ({args.uplevel}))' + end_cfp = self.get_int('ruby_current_ec->vm_stack + ruby_current_ec->vm_stack_size') + cfp_index = int((end_cfp - self.get_int(cfp) - 1) / self.get_int('sizeof(rb_control_frame_t)')) + + if args.all: + cfp_count = int((end_cfp - self.get_int('ruby_current_ec->cfp')) / self.get_int('sizeof(rb_control_frame_t)')) - 1 # exclude dummy CFP + for i in range(cfp_count): + print('-' * 80) + self.invoke(str(cfp_count - i - 1), from_tty) + return + + print('CFP (addr=0x{:x}, index={}):'.format(self.get_int(cfp), cfp_index)) + gdb.execute(f'p *({cfp})') + print() + + if self.get_int(f'{cfp}->iseq'): + local_size = self.get_int(f'{cfp}->iseq->body->local_table_size - {cfp}->iseq->body->param.size') + param_size = self.get_int(f'{cfp}->iseq->body->param.size') + + if local_size: + print(f'Params (size={param_size}):') + for i in range(-3 - local_size - param_size, -3 - local_size): + self.print_stack(cfp, i, self.rp(cfp, i)) + print() + + if param_size: + print(f'Locals (size={local_size}):') + for i in range(-3 - local_size, -3): + self.print_stack(cfp, i, self.rp(cfp, i)) + print() + + print('Env:') + self.print_env(cfp, -3, self.rp_env(cfp, -3)) + self.print_env(cfp, -2, self.specval(cfp, -2)) + self.print_env(cfp, -1, self.frame_types(cfp, -1)) + print() + + # We can't calculate BP for the first frame. + # vm_base_ptr doesn't work for C frames either. + if cfp_index > 0 and self.get_int(f'{cfp}->iseq'): + if args.stack_size is not None: + stack_size = args.stack_size + else: + stack_size = int((self.get_int(f'{cfp}->sp') - self.get_int(f'vm_base_ptr({cfp})')) / 8) + print(f'Stack (size={stack_size}):') + for i in range(0, stack_size): + self.print_stack(cfp, i, self.rp(cfp, i)) + print(self.regs(cfp, stack_size)) + + def print_env(self, cfp, bp_index, content): + ep_index = bp_index + 1 + address = self.get_int(f'((rb_control_frame_t *){cfp})->ep + {ep_index}') + value = self.get_env(cfp, bp_index) + regs = self.regs(cfp, bp_index) + if content: + content = textwrap.indent(content, ' ' * 3).lstrip() # Leave the regs column empty + content = f'{content} ' + print('{:2} 0x{:x} [{}] {}(0x{:x})'.format(regs, address, bp_index, content, value)) + + def print_stack(self, cfp, bp_index, content): + address = self.get_int(f'vm_base_ptr({cfp}) + {bp_index}') + value = self.get_value(cfp, bp_index) + regs = self.regs(cfp, bp_index) + if content: + content = textwrap.indent(content, ' ' * 3).lstrip() # Leave the regs column empty + content = f'{content} ' + print('{:2} 0x{:x} [{}] {}(0x{:x})'.format(regs, address, bp_index, content, value)) + + def regs(self, cfp, bp_index): + address = self.get_int(f'vm_base_ptr({cfp}) + {bp_index}') + regs = [] + for reg, field in { 'EP': 'ep', 'SP': 'sp' }.items(): + if address == self.get_int(f'{cfp}->{field}'): + regs.append(reg) + return ' '.join(regs) + + def rp(self, cfp, bp_index): + value = self.get_value(cfp, bp_index) + return self.get_string(f'rp {value}').rstrip() + + def rp_env(self, cfp, bp_index): + value = self.get_env(cfp, bp_index) + return self.get_string(f'rp {value}').rstrip() + + # specval: block_handler or previous EP + def specval(self, cfp, bp_index): + value = self.get_env(cfp, bp_index) + if value == 0: + return 'VM_BLOCK_HANDLER_NONE' + if value == self.get_int('rb_block_param_proxy'): + return 'rb_block_param_proxy' + return '' + + def frame_types(self, cfp, bp_index): + types = [] + value = self.get_env(cfp, bp_index) + + magic_mask = self.get_int('VM_FRAME_MAGIC_MASK') + for magic in self.FRAME_MAGICS: + magic_value = self.get_int(magic) + if value & magic_mask == magic_value: + types.append(magic) + + for flag in self.FRAME_FLAGS: + flag_value = self.get_int(flag) + if value & flag_value: + types.append(flag) + + return ' | '.join(types) + + def get_env(self, cfp, bp_index): + ep_index = bp_index + 1 + return self.get_int(f'((rb_control_frame_t *){cfp})->ep[{ep_index}]') + + def get_value(self, cfp, bp_index): + return self.get_int(f'vm_base_ptr({cfp})[{bp_index}]') + + def get_int(self, expr): + return int(self.get_string(f'printf "%ld", ({expr})')) + + def get_string(self, expr): + return gdb.execute(expr, to_string=True) + +CFP() diff --git a/misc/inf-ruby.el b/misc/inf-ruby.el deleted file mode 100644 index ea03eee23d..0000000000 --- a/misc/inf-ruby.el +++ /dev/null @@ -1,416 +0,0 @@ -;;; -*-Emacs-Lisp-*- -;;; -;;; $Id$ -;;; $Author$ -;;; -;;; Inferior Ruby Mode - ruby process in a buffer. -;;; adapted from cmuscheme.el -;;; -;;; Usage: -;;; -;;; (0) check ruby-program-name variable that can run your environment. -;;; -;;; (1) modify .emacs to use ruby-mode -;;; for example : -;;; -;;; (autoload 'ruby-mode "ruby-mode" -;;; "Mode for editing ruby source files" t) -;;; (setq auto-mode-alist -;;; (append '(("\\.rb$" . ruby-mode)) auto-mode-alist)) -;;; (setq interpreter-mode-alist (append '(("ruby" . ruby-mode)) -;;; interpreter-mode-alist)) -;;; -;;; (2) set to load inf-ruby and set inf-ruby key definition in ruby-mode. -;;; -;;; (autoload 'run-ruby "inf-ruby" -;;; "Run an inferior Ruby process") -;;; (autoload 'inf-ruby-keys "inf-ruby" -;;; "Set local key defs for inf-ruby in ruby-mode") -;;; (add-hook 'ruby-mode-hook -;;; '(lambda () -;;; (inf-ruby-keys) -;;; )) -;;; -;;; HISTORY -;;; senda - 8 Apr 1998: Created. -;;; $Log$ -;;; Revision 1.7 2004/07/27 08:11:36 matz -;;; * eval.c (rb_eval): copy on write for argument local variable -;;; assignment. -;;; -;;; * eval.c (assign): ditto. -;;; -;;; * eval.c (rb_call0): update ruby_frame->argv with the default -;;; value used for the optional arguments. -;;; -;;; * object.c (Init_Object): "===" calls rb_obj_equal() directly. -;;; [ruby-list:39937] -;;; -;;; Revision 1.6 2002/09/07 14:35:46 nobu -;;; * misc/inf-ruby.el (inferior-ruby-error-regexp-alist): regexp -;;; alist for error message from ruby. -;;; -;;; * misc/inf-ruby.el (inferior-ruby-mode): fixed for Emacs. -;;; -;;; * misc/inf-ruby.el (ruby-send-region): compilation-parse-errors -;;; doesn't parse first line, so insert separators before each -;;; evaluations. -;;; -;;; Revision 1.5 2002/08/19 10:05:47 nobu -;;; * misc/inf-ruby.el (inf-ruby-keys): ruby-send-definition -;;; conflicted with ruby-insert-end. -;;; -;;; * misc/inf-ruby.el (inferior-ruby-mode): compilation-minor-mode. -;;; -;;; * misc/inf-ruby.el (ruby-send-region): send as here document to -;;; adjust source file/line. [ruby-talk:47113], [ruby-dev:17965] -;;; -;;; * misc/inf-ruby.el (ruby-send-terminator): added to make unique -;;; terminator. -;;; -;;; Revision 1.4 2002/01/29 07:16:09 matz -;;; * file.c (rb_stat_rdev_major): added. [new] -;;; -;;; * file.c (rb_stat_rdev_minor): added. [new] -;;; -;;; * file.c (rb_stat_inspect): print mode in octal. -;;; -;;; Revision 1.3 1999/12/01 09:24:18 matz -;;; 19991201 -;;; -;;; Revision 1.2 1999/08/13 05:45:18 matz -;;; 1.4.0 -;;; -;;; Revision 1.1.1.1.2.1 1999/07/15 07:59:59 matz -;;; 990715 -;;; -;;; Revision 1.1.1.1 1999/01/20 04:59:36 matz -;;; ruby 1.3 cycle -;;; -;;; Revision 1.1.2.1 1998/12/16 07:30:36 matz -;;; first public release of 1.1d (pre1.2) series -;;; -;;; Revision 1.4 1998/05/20 02:45:58 senda -;;; default program to irb -;;; -;;; Revision 1.3 1998/04/10 04:11:30 senda -;;; modification by Matsumoto san (1.1b9_09) -;;; remove-in-string defined -;;; global variable : -;;; inferior-ruby-first-prompt-pattern -;;; inferior-ruby-prompt-pattern -;;; defined -;;; -;;; Revision 1.2 1998/04/09 07:53:42 senda -;;; remove M-C-x in inferior-ruby-mode -;;; -;;; Revision 1.1 1998/04/09 07:28:36 senda -;;; Initial revision -;;; -;;; - -(require 'comint) -(require 'compile) -(require 'ruby-mode) - -;; -;; you may change these variables -;; -;(defvar ruby-program-name "rbc --noreadline" -; "*Program invoked by the run-ruby command") -; -;(defvar inferior-ruby-first-prompt-pattern "^rbc0> *" -; "first prompt regex pattern of ruby interpreter.") -; -;(defvar inferior-ruby-prompt-pattern "^\\(rbc.[>*\"'] *\\)+" -; "prompt regex pattern of ruby interpreter.") - -;;;; for irb -(defvar ruby-program-name "irb --inf-ruby-mode" - "*Program invoked by the run-ruby command") - -(defvar inferior-ruby-first-prompt-pattern "^irb(.*)[0-9:]+0> *" - "first prompt regex pattern of ruby interpreter.") - -(defvar inferior-ruby-prompt-pattern "^\\(irb(.*)[0-9:]+[>*\"'] *\\)+" - "prompt regex pattern of ruby interpreter.") - -;; -;; mode variables -;; -(defvar inferior-ruby-mode-hook nil - "*Hook for customising inferior-ruby mode.") -(defvar inferior-ruby-mode-map nil - "*Mode map for inferior-ruby-mode") - -(defconst inferior-ruby-error-regexp-alist - '(("SyntaxError: compile error\n^\\([^\(].*\\):\\([1-9][0-9]*\\):" 1 2) - ("^\tfrom \\([^\(].*\\):\\([1-9][0-9]*\\)\\(:in `.*'\\)?$" 1 2))) - -(cond ((not inferior-ruby-mode-map) - (setq inferior-ruby-mode-map - (copy-keymap comint-mode-map)) -; (define-key inferior-ruby-mode-map "\M-\C-x" ;gnu convention -; 'ruby-send-definition) -; (define-key inferior-ruby-mode-map "\C-x\C-e" 'ruby-send-last-sexp) - (define-key inferior-ruby-mode-map "\C-c\C-l" 'ruby-load-file) -)) - -(defun inf-ruby-keys () - "Set local key defs for inf-ruby in ruby-mode" - (define-key ruby-mode-map "\M-\C-x" 'ruby-send-definition) -; (define-key ruby-mode-map "\C-x\C-e" 'ruby-send-last-sexp) - (define-key ruby-mode-map "\C-c\C-b" 'ruby-send-block) - (define-key ruby-mode-map "\C-c\M-b" 'ruby-send-block-and-go) - (define-key ruby-mode-map "\C-c\C-x" 'ruby-send-definition) - (define-key ruby-mode-map "\C-c\M-x" 'ruby-send-definition-and-go) - (define-key ruby-mode-map "\C-c\C-r" 'ruby-send-region) - (define-key ruby-mode-map "\C-c\M-r" 'ruby-send-region-and-go) - (define-key ruby-mode-map "\C-c\C-z" 'switch-to-ruby) - (define-key ruby-mode-map "\C-c\C-l" 'ruby-load-file) - (define-key ruby-mode-map "\C-c\C-s" 'run-ruby) -) - -(defvar ruby-buffer nil "current ruby (actually irb) process buffer.") - -(defun inferior-ruby-mode () - "Major mode for interacting with an inferior ruby (irb) process. - -The following commands are available: -\\{inferior-ruby-mode-map} - -A ruby process can be fired up with M-x run-ruby. - -Customisation: Entry to this mode runs the hooks on comint-mode-hook and -inferior-ruby-mode-hook (in that order). - -You can send text to the inferior ruby process from other buffers containing -Ruby source. - switch-to-ruby switches the current buffer to the ruby process buffer. - ruby-send-definition sends the current definition to the ruby process. - ruby-send-region sends the current region to the ruby process. - - ruby-send-definition-and-go, ruby-send-region-and-go, - switch to the ruby process buffer after sending their text. -For information on running multiple processes in multiple buffers, see -documentation for variable ruby-buffer. - -Commands: -Return after the end of the process' output sends the text from the - end of process to point. -Return before the end of the process' output copies the sexp ending at point - to the end of the process' output, and sends it. -Delete converts tabs to spaces as it moves back. -Tab indents for ruby; with argument, shifts rest - of expression rigidly with the current line. -C-M-q does Tab on each line starting within following expression. -Paragraphs are separated only by blank lines. # start comments. -If you accidentally suspend your process, use \\[comint-continue-subjob] -to continue it." - (interactive) - (comint-mode) - ;; Customise in inferior-ruby-mode-hook - ;(setq comint-prompt-regexp "^[^>\n]*>+ *") - (setq comint-prompt-regexp inferior-ruby-prompt-pattern) - ;;(scheme-mode-variables) - (ruby-mode-variables) - (setq major-mode 'inferior-ruby-mode) - (setq mode-name "Inferior Ruby") - (setq mode-line-process '(":%s")) - (use-local-map inferior-ruby-mode-map) - (setq comint-input-filter (function ruby-input-filter)) - (setq comint-get-old-input (function ruby-get-old-input)) - (make-local-variable 'compilation-error-regexp-alist) - (setq compilation-error-regexp-alist inferior-ruby-error-regexp-alist) - (compilation-shell-minor-mode t) - (run-hooks 'inferior-ruby-mode-hook)) - -(defvar inferior-ruby-filter-regexp "\\`\\s *\\S ?\\S ?\\s *\\'" - "*Input matching this regexp are not saved on the history list. -Defaults to a regexp ignoring all inputs of 0, 1, or 2 letters.") - -(defun ruby-input-filter (str) - "Don't save anything matching inferior-ruby-filter-regexp" - (not (string-match inferior-ruby-filter-regexp str))) - -;; adapted from replace-in-string in XEmacs (subr.el) -(defun remove-in-string (str regexp) - "Remove all matches in STR for REGEXP and returns the new string." - (let ((rtn-str "") (start 0) match prev-start) - (while (setq match (string-match regexp str start)) - (setq prev-start start - start (match-end 0) - rtn-str (concat rtn-str (substring str prev-start match)))) - (concat rtn-str (substring str start)))) - -(defun ruby-get-old-input () - "Snarf the sexp ending at point" - (save-excursion - (let ((end (point))) - (re-search-backward inferior-ruby-first-prompt-pattern) - (remove-in-string (buffer-substring (point) end) - inferior-ruby-prompt-pattern) - ))) - -(defun ruby-args-to-list (string) - (let ((where (string-match "[ \t]" string))) - (cond ((null where) (list string)) - ((not (= where 0)) - (cons (substring string 0 where) - (ruby-args-to-list (substring string (+ 1 where) - (length string))))) - (t (let ((pos (string-match "[^ \t]" string))) - (if (null pos) - nil - (ruby-args-to-list (substring string pos - (length string))))))))) - -(defun run-ruby (cmd) - "Run an inferior Ruby process, input and output via buffer *ruby*. -If there is a process already running in `*ruby*', switch to that buffer. -With argument, allows you to edit the command line (default is value -of `ruby-program-name'). Runs the hooks `inferior-ruby-mode-hook' -\(after the `comint-mode-hook' is run). -\(Type \\[describe-mode] in the process buffer for a list of commands.)" - - (interactive (list (if current-prefix-arg - (read-string "Run Ruby: " ruby-program-name) - ruby-program-name))) - (if (not (comint-check-proc "*ruby*")) - (let ((cmdlist (ruby-args-to-list cmd))) - (set-buffer (apply 'make-comint "ruby" (car cmdlist) - nil (cdr cmdlist))) - (inferior-ruby-mode))) - (setq ruby-program-name cmd) - (setq ruby-buffer "*ruby*") - (pop-to-buffer "*ruby*")) - -(defconst ruby-send-terminator "--inf-ruby-%x-%d-%d-%d--" - "Template for irb here document terminator. -Must not contain ruby meta characters.") - -(defconst ruby-eval-separator "") - -(defun ruby-send-region (start end) - "Send the current region to the inferior Ruby process." - (interactive "r") - (let (term (file (buffer-file-name)) line) - (save-excursion - (save-restriction - (widen) - (goto-char start) - (setq line (+ start (forward-line (- start)) 1)) - (goto-char start) - (while (progn - (setq term (apply 'format ruby-send-terminator (random) (current-time))) - (re-search-forward (concat "^" (regexp-quote term) "$") end t))))) - ;; compilation-parse-errors parses from second line. - (save-excursion - (let ((m (process-mark (ruby-proc)))) - (set-buffer (marker-buffer m)) - (goto-char m) - (insert ruby-eval-separator "\n") - (set-marker m (point)))) - (comint-send-string (ruby-proc) (format "eval <<'%s', nil, %S, %d\n" term file line)) - (comint-send-region (ruby-proc) start end) - (comint-send-string (ruby-proc) (concat "\n" term "\n")))) - -(defun ruby-send-definition () - "Send the current definition to the inferior Ruby process." - (interactive) - (save-excursion - (ruby-end-of-defun) - (let ((end (point))) - (ruby-beginning-of-defun) - (ruby-send-region (point) end)))) - -;(defun ruby-send-last-sexp () -; "Send the previous sexp to the inferior Ruby process." -; (interactive) -; (ruby-send-region (save-excursion (backward-sexp) (point)) (point))) - -(defun ruby-send-block () - "Send the current block to the inferior Ruby process." - (interactive) - (save-excursion - (ruby-end-of-block) - (end-of-line) - (let ((end (point))) - (ruby-beginning-of-block) - (ruby-send-region (point) end)))) - -(defun switch-to-ruby (eob-p) - "Switch to the ruby process buffer. -With argument, positions cursor at end of buffer." - (interactive "P") - (if (get-buffer ruby-buffer) - (pop-to-buffer ruby-buffer) - (error "No current process buffer. See variable ruby-buffer.")) - (cond (eob-p - (push-mark) - (goto-char (point-max))))) - -(defun ruby-send-region-and-go (start end) - "Send the current region to the inferior Ruby process. -Then switch to the process buffer." - (interactive "r") - (ruby-send-region start end) - (switch-to-ruby t)) - -(defun ruby-send-definition-and-go () - "Send the current definition to the inferior Ruby. -Then switch to the process buffer." - (interactive) - (ruby-send-definition) - (switch-to-ruby t)) - -(defun ruby-send-block-and-go () - "Send the current block to the inferior Ruby. -Then switch to the process buffer." - (interactive) - (ruby-send-block) - (switch-to-ruby t)) - -(defvar ruby-source-modes '(ruby-mode) - "*Used to determine if a buffer contains Ruby source code. -If it's loaded into a buffer that is in one of these major modes, it's -considered a ruby source file by ruby-load-file. -Used by these commands to determine defaults.") - -(defvar ruby-prev-l/c-dir/file nil - "Caches the last (directory . file) pair. -Caches the last pair used in the last ruby-load-file command. -Used for determining the default in the -next one.") - -(defun ruby-load-file (file-name) - "Load a Ruby file into the inferior Ruby process." - (interactive (comint-get-source "Load Ruby file: " ruby-prev-l/c-dir/file - ruby-source-modes t)) ; T because LOAD - ; needs an exact name - (comint-check-source file-name) ; Check to see if buffer needs saved. - (setq ruby-prev-l/c-dir/file (cons (file-name-directory file-name) - (file-name-nondirectory file-name))) - (comint-send-string (ruby-proc) (concat "(load \"" - file-name - "\"\)\n"))) - -(defun ruby-proc () - "Returns the current ruby process. See variable ruby-buffer." - (let ((proc (get-buffer-process (if (eq major-mode 'inferior-ruby-mode) - (current-buffer) - ruby-buffer)))) - (or proc - (error "No current process. See variable ruby-buffer")))) - -;;; Do the user's customisation... - -(defvar inf-ruby-load-hook nil - "This hook is run when inf-ruby is loaded in. -This is a good place to put keybindings.") - -(run-hooks 'inf-ruby-load-hook) - -(provide 'inf-ruby) - -;;; inf-ruby.el ends here diff --git a/misc/lldb_cruby.py b/misc/lldb_cruby.py new file mode 100644 index 0000000000..b3d4fb509a --- /dev/null +++ b/misc/lldb_cruby.py @@ -0,0 +1,747 @@ +#coding: utf-8 +# +# Usage: run `command script import -r misc/lldb_cruby.py` on LLDB +# +# Test: misc/test_lldb_cruby.rb +# + +from __future__ import print_function +import lldb +import os +import inspect +import sys +import shlex +import platform +import glob +import math + +from lldb_rb.constants import * + +# BEGIN FUNCTION STYLE DECLS +# This will be refactored to use class style decls in the misc/commands dir +class BackTrace: + VM_FRAME_MAGIC_METHOD = 0x11110001 + VM_FRAME_MAGIC_BLOCK = 0x22220001 + VM_FRAME_MAGIC_CLASS = 0x33330001 + VM_FRAME_MAGIC_TOP = 0x44440001 + VM_FRAME_MAGIC_CFUNC = 0x55550001 + VM_FRAME_MAGIC_IFUNC = 0x66660001 + VM_FRAME_MAGIC_EVAL = 0x77770001 + VM_FRAME_MAGIC_RESCUE = 0x78880001 + VM_FRAME_MAGIC_DUMMY = 0x79990001 + + VM_FRAME_MAGIC_MASK = 0x7fff0001 + + VM_FRAME_MAGIC_NAME = { + VM_FRAME_MAGIC_TOP: "TOP", + VM_FRAME_MAGIC_METHOD: "METHOD", + VM_FRAME_MAGIC_CLASS: "CLASS", + VM_FRAME_MAGIC_BLOCK: "BLOCK", + VM_FRAME_MAGIC_CFUNC: "CFUNC", + VM_FRAME_MAGIC_IFUNC: "IFUNC", + VM_FRAME_MAGIC_EVAL: "EVAL", + VM_FRAME_MAGIC_RESCUE: "RESCUE", + 0: "-----" + } + + def __init__(self, debugger, command, result, internal_dict): + self.debugger = debugger + self.command = command + self.result = result + + self.target = debugger.GetSelectedTarget() + self.process = self.target.GetProcess() + self.thread = self.process.GetSelectedThread() + self.frame = self.thread.GetSelectedFrame() + self.tRString = self.target.FindFirstType("struct RString").GetPointerType() + self.tRArray = self.target.FindFirstType("struct RArray").GetPointerType() + + rb_cft_len = len("rb_control_frame_t") + method_type_length = sorted(map(len, self.VM_FRAME_MAGIC_NAME.values()), reverse=True)[0] + # cfp address, method type, function name + self.fmt = "%%-%ds %%-%ds %%s" % (rb_cft_len, method_type_length) + + def vm_frame_magic(self, cfp): + ep = cfp.GetValueForExpressionPath("->ep") + frame_type = ep.GetChildAtIndex(0).GetValueAsUnsigned() & self.VM_FRAME_MAGIC_MASK + return self.VM_FRAME_MAGIC_NAME.get(frame_type, "(none)") + + def rb_iseq_path_str(self, iseq): + tRBasic = self.target.FindFirstType("::RBasic").GetPointerType() + + pathobj = iseq.GetValueForExpressionPath("->body->location.pathobj") + pathobj = pathobj.Cast(tRBasic) + flags = pathobj.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + flType = flags & RUBY_T_MASK + + if flType == RUBY_T_ARRAY: + pathobj = pathobj.Cast(self.tRArray) + + if flags & RUBY_FL_USER1: + len = ((flags & (RUBY_FL_USER3|RUBY_FL_USER4|RUBY_FL_USER5|RUBY_FL_USER6|RUBY_FL_USER7|RUBY_FL_USER8|RUBY_FL_USER9)) >> (RUBY_FL_USHIFT+3)) + ptr = pathobj.GetValueForExpressionPath("->as.ary") + else: + len = pathobj.GetValueForExpressionPath("->as.heap.len").GetValueAsSigned() + ptr = pathobj.GetValueForExpressionPath("->as.heap.ptr") + + pathobj = ptr.GetChildAtIndex(0) + + pathobj = pathobj.Cast(self.tRString) + ptr, len = string2cstr(pathobj) + err = lldb.SBError() + path = self.target.process.ReadMemory(ptr, len, err) + if err.Success(): + return path.decode("utf-8") + else: + return "unknown" + + def dump_iseq_frame(self, cfp, iseq): + m = self.vm_frame_magic(cfp) + + if iseq.GetValueAsUnsigned(): + iseq_label = iseq.GetValueForExpressionPath("->body->location.label") + path = self.rb_iseq_path_str(iseq) + ptr, len = string2cstr(iseq_label.Cast(self.tRString)) + + err = lldb.SBError() + iseq_name = self.target.process.ReadMemory(ptr, len, err) + if err.Success(): + iseq_name = iseq_name.decode("utf-8") + else: + iseq_name = "error!!" + + else: + print("No iseq", file=self.result) + + print(self.fmt % (("%0#12x" % cfp.GetAddress().GetLoadAddress(self.target)), m, "%s %s" % (path, iseq_name)), file=self.result) + + def dump_cfunc_frame(self, cfp): + print(self.fmt % ("%0#12x" % (cfp.GetAddress().GetLoadAddress(self.target)), "CFUNC", ""), file=self.result) + + def print_bt(self, ec): + tRbExecutionContext_t = self.target.FindFirstType("rb_execution_context_t") + ec = ec.Cast(tRbExecutionContext_t.GetPointerType()) + vm_stack = ec.GetValueForExpressionPath("->vm_stack") + vm_stack_size = ec.GetValueForExpressionPath("->vm_stack_size") + + last_cfp_frame = ec.GetValueForExpressionPath("->cfp") + cfp_type_p = last_cfp_frame.GetType() + + stack_top = vm_stack.GetValueAsUnsigned() + ( + vm_stack_size.GetValueAsUnsigned() * vm_stack.GetType().GetByteSize()) + + cfp_frame_size = cfp_type_p.GetPointeeType().GetByteSize() + + start_cfp = stack_top + # Skip dummy frames + start_cfp -= cfp_frame_size + start_cfp -= cfp_frame_size + + last_cfp = last_cfp_frame.GetValueAsUnsigned() + + size = ((start_cfp - last_cfp) / cfp_frame_size) + 1 + + print(self.fmt % ("rb_control_frame_t", "TYPE", ""), file=self.result) + + curr_addr = start_cfp + + while curr_addr >= last_cfp: + cfp = self.target.CreateValueFromAddress("cfp", lldb.SBAddress(curr_addr, self.target), cfp_type_p.GetPointeeType()) + ep = cfp.GetValueForExpressionPath("->ep") + iseq = cfp.GetValueForExpressionPath("->iseq") + + frame_type = ep.GetChildAtIndex(0).GetValueAsUnsigned() & self.VM_FRAME_MAGIC_MASK + + if iseq.GetValueAsUnsigned(): + pc = cfp.GetValueForExpressionPath("->pc") + if pc.GetValueAsUnsigned(): + self.dump_iseq_frame(cfp, iseq) + else: + if frame_type == self.VM_FRAME_MAGIC_CFUNC: + self.dump_cfunc_frame(cfp) + + curr_addr -= cfp_frame_size + +def lldb_init(debugger): + target = debugger.GetSelectedTarget() + global SIZEOF_VALUE + SIZEOF_VALUE = target.FindFirstType("VALUE").GetByteSize() + + value_types = [] + g = globals() + + imemo_types = target.FindFirstType('enum imemo_type') + enum_members = imemo_types.GetEnumMembers() + + for i in range(enum_members.GetSize()): + member = enum_members.GetTypeEnumMemberAtIndex(i) + g[member.GetName()] = member.GetValueAsUnsigned() + + for enum in target.FindFirstGlobalVariable('ruby_dummy_gdb_enums'): + enum = enum.GetType() + members = enum.GetEnumMembers() + for i in range(0, members.GetSize()): + member = members.GetTypeEnumMemberAtIndex(i) + name = member.GetName() + value = member.GetValueAsUnsigned() + g[name] = value + + if name.startswith('RUBY_T_'): + value_types.append(name) + g['value_types'] = value_types + +def string2cstr(rstring): + """Returns the pointer to the C-string in the given String object""" + if rstring.TypeIsPointerType(): + rstring = rstring.Dereference() + flags = rstring.GetValueForExpressionPath(".basic->flags").unsigned + if flags & RUBY_T_MASK != RUBY_T_STRING: + raise TypeError("not a string") + clen = int(rstring.GetValueForExpressionPath(".len").value, 0) + if flags & RUBY_FL_USER1: + cptr = int(rstring.GetValueForExpressionPath(".as.heap.ptr").value, 0) + else: + cptr = int(rstring.GetValueForExpressionPath(".as.embed.ary").location, 0) + return cptr, clen + +def output_string(debugger, result, rstring): + cptr, clen = string2cstr(rstring) + append_expression(debugger, "*(const char (*)[%d])%0#x" % (clen, cptr), result) + +def fixnum_p(x): + return x & RUBY_FIXNUM_FLAG != 0 + +def flonum_p(x): + return (x&RUBY_FLONUM_MASK) == RUBY_FLONUM_FLAG + +def static_sym_p(x): + return (x&~(~0<<RUBY_SPECIAL_SHIFT)) == RUBY_SYMBOL_FLAG + +def append_command_output(debugger, command, result): + output1 = result.GetOutput() + debugger.GetCommandInterpreter().HandleCommand(command, result) + output2 = result.GetOutput() + result.Clear() + result.write(output1) + result.write(output2) + +def append_expression(debugger, expression, result): + append_command_output(debugger, "expression " + expression, result) + +def lldb_rp(debugger, command, result, internal_dict): + if not ('RUBY_Qfalse' in globals()): + lldb_init(debugger) + + target = debugger.GetSelectedTarget() + process = target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + if frame.IsValid(): + val = frame.EvaluateExpression(command) + else: + val = target.EvaluateExpression(command) + error = val.GetError() + if error.Fail(): + print(error, file=result) + return + lldb_inspect(debugger, target, result, val) + +def lldb_inspect(debugger, target, result, val): + num = val.GetValueAsSigned() + if num == RUBY_Qfalse: + print('false', file=result) + elif num == RUBY_Qtrue: + print('true', file=result) + elif num == RUBY_Qnil: + print('nil', file=result) + elif num == RUBY_Qundef: + print('undef', file=result) + elif fixnum_p(num): + print(num >> 1, file=result) + elif flonum_p(num): + append_expression(debugger, "rb_float_value(%0#x)" % val.GetValueAsUnsigned(), result) + elif static_sym_p(num): + if num < 128: + print("T_SYMBOL: %c" % num, file=result) + else: + print("T_SYMBOL: (%x)" % num, file=result) + append_expression(debugger, "rb_id2name(%0#x)" % (num >> 8), result) + elif num & RUBY_IMMEDIATE_MASK: + print('immediate(%x)' % num, file=result) + else: + tRBasic = target.FindFirstType("::RBasic").GetPointerType() + + val = val.Cast(tRBasic) + flags = val.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + flaginfo = "" + + page = get_page(lldb, target, val) + page_type = target.FindFirstType("struct heap_page").GetPointerType() + page.Cast(page_type) + + dump_bits(target, result, page, val.GetValueAsUnsigned()) + + if (flags & RUBY_FL_PROMOTED) == RUBY_FL_PROMOTED: + flaginfo += "[PROMOTED] " + if (flags & RUBY_FL_FREEZE) == RUBY_FL_FREEZE: + flaginfo += "[FROZEN] " + flType = flags & RUBY_T_MASK + if flType == RUBY_T_NONE: + print('T_NONE: %s%s' % (flaginfo, val.Dereference()), file=result) + elif flType == RUBY_T_NIL: + print('T_NIL: %s%s' % (flaginfo, val.Dereference()), file=result) + elif flType == RUBY_T_OBJECT: + result.write('T_OBJECT: %s' % flaginfo) + append_expression(debugger, "*(struct RObject*)%0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_CLASS or flType == RUBY_T_MODULE or flType == RUBY_T_ICLASS: + result.write('T_%s: %s' % ('CLASS' if flType == RUBY_T_CLASS else 'MODULE' if flType == RUBY_T_MODULE else 'ICLASS', flaginfo)) + append_expression(debugger, "*(struct RClass*)%0#x" % val.GetValueAsUnsigned(), result) + tRClass = target.FindFirstType("struct RClass") + if not val.Cast(tRClass).GetChildMemberWithName("ptr").IsValid(): + append_expression(debugger, "*(struct rb_classext_struct*)%0#x" % (val.GetValueAsUnsigned() + tRClass.GetByteSize()), result) + elif flType == RUBY_T_STRING: + result.write('T_STRING: %s' % flaginfo) + encidx = ((flags & RUBY_ENCODING_MASK)>>RUBY_ENCODING_SHIFT) + encname = target.FindFirstType("enum ruby_preserved_encindex").GetEnumMembers().GetTypeEnumMemberAtIndex(encidx).GetName() + if encname is not None: + result.write('[%s] ' % encname[14:]) + else: + result.write('[enc=%d] ' % encidx) + tRString = target.FindFirstType("struct RString").GetPointerType() + ptr, len = string2cstr(val.Cast(tRString)) + if len == 0: + result.write("(empty)\n") + else: + append_expression(debugger, "*(const char (*)[%d])%0#x" % (len, ptr), result) + elif flType == RUBY_T_SYMBOL: + result.write('T_SYMBOL: %s' % flaginfo) + tRSymbol = target.FindFirstType("struct RSymbol").GetPointerType() + val = val.Cast(tRSymbol) + append_expression(debugger, '(ID)%0#x ' % val.GetValueForExpressionPath("->id").GetValueAsUnsigned(), result) + tRString = target.FindFirstType("struct RString").GetPointerType() + output_string(debugger, result, val.GetValueForExpressionPath("->fstr").Cast(tRString)) + elif flType == RUBY_T_ARRAY: + tRArray = target.FindFirstType("struct RArray").GetPointerType() + val = val.Cast(tRArray) + if flags & RUBY_FL_USER1: + len = ((flags & (RUBY_FL_USER3|RUBY_FL_USER4|RUBY_FL_USER5|RUBY_FL_USER6|RUBY_FL_USER7|RUBY_FL_USER8|RUBY_FL_USER9)) >> (RUBY_FL_USHIFT+3)) + ptr = val.GetValueForExpressionPath("->as.ary") + else: + len = val.GetValueForExpressionPath("->as.heap.len").GetValueAsSigned() + ptr = val.GetValueForExpressionPath("->as.heap.ptr") + result.write("T_ARRAY: %slen=%d" % (flaginfo, len)) + if flags & RUBY_FL_USER1: + result.write(" (embed)") + elif flags & RUBY_FL_USER2: + shared = val.GetValueForExpressionPath("->as.heap.aux.shared").GetValueAsUnsigned() + result.write(" (shared) shared=%016x" % shared) + else: + capa = val.GetValueForExpressionPath("->as.heap.aux.capa").GetValueAsSigned() + result.write(" (ownership) capa=%d" % capa) + if len == 0: + result.write(" {(empty)}\n") + else: + result.write("\n") + if ptr.GetValueAsSigned() == 0: + append_expression(debugger, "-fx -- ((struct RArray*)%0#x)->as.ary" % val.GetValueAsUnsigned(), result) + else: + append_expression(debugger, "-Z %d -fx -- (const VALUE*)%0#x" % (len, ptr.GetValueAsUnsigned()), result) + elif flType == RUBY_T_HASH: + result.write("T_HASH: %s" % flaginfo) + append_expression(debugger, "*(struct RHash *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_BIGNUM: + tRBignum = target.FindFirstType("struct RBignum").GetPointerType() + val = val.Cast(tRBignum) + sign = '+' if (flags & RUBY_FL_USER1) != 0 else '-' + if flags & RUBY_FL_USER2: + len = ((flags & (RUBY_FL_USER3|RUBY_FL_USER4|RUBY_FL_USER5)) >> (RUBY_FL_USHIFT+3)) + print("T_BIGNUM: sign=%s len=%d (embed)" % (sign, len), file=result) + append_expression(debugger, "((struct RBignum *) %0#x)->as.ary" % val.GetValueAsUnsigned(), result) + else: + len = val.GetValueForExpressionPath("->as.heap.len").GetValueAsSigned() + print("T_BIGNUM: sign=%s len=%d" % (sign, len), file=result) + print(val.Dereference(), file=result) + append_expression(debugger, "-Z %x -fx -- (const BDIGIT*)((struct RBignum*)%d)->as.heap.digits" % (len, val.GetValueAsUnsigned()), result) + # append_expression(debugger, "((struct RBignum *) %0#x)->as.heap.digits / %d" % (val.GetValueAsUnsigned(), len), result) + elif flType == RUBY_T_FLOAT: + append_expression(debugger, "((struct RFloat *)%d)->float_value" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_RATIONAL: + tRRational = target.FindFirstType("struct RRational").GetPointerType() + val = val.Cast(tRRational) + lldb_inspect(debugger, target, result, val.GetValueForExpressionPath("->num")) + output = result.GetOutput() + result.Clear() + result.write("(Rational) " + output.rstrip() + " / ") + lldb_inspect(debugger, target, result, val.GetValueForExpressionPath("->den")) + elif flType == RUBY_T_COMPLEX: + tRComplex = target.FindFirstType("struct RComplex").GetPointerType() + val = val.Cast(tRComplex) + lldb_inspect(debugger, target, result, val.GetValueForExpressionPath("->real")) + real = result.GetOutput().rstrip() + result.Clear() + lldb_inspect(debugger, target, result, val.GetValueForExpressionPath("->imag")) + imag = result.GetOutput().rstrip() + result.Clear() + if not imag.startswith("-"): + imag = "+" + imag + print("(Complex) " + real + imag + "i", file=result) + elif flType == RUBY_T_REGEXP: + tRRegex = target.FindFirstType("struct RRegexp").GetPointerType() + val = val.Cast(tRRegex) + print("(Regex) ->src {", file=result) + lldb_inspect(debugger, target, result, val.GetValueForExpressionPath("->src")) + print("}", file=result) + elif flType == RUBY_T_DATA: + tRTypedData = target.FindFirstType("struct RTypedData").GetPointerType() + val = val.Cast(tRTypedData) + flag = val.GetValueForExpressionPath("->typed_flag") + if flag.GetValueAsUnsigned() == 1: + print("T_DATA: %s" % val.GetValueForExpressionPath("->type->wrap_struct_name"), file=result) + append_expression(debugger, "*(struct RTypedData *) %0#x" % val.GetValueAsUnsigned(), result) + else: + print("T_DATA:", file=result) + append_expression(debugger, "*(struct RData *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_NODE: + tRTypedData = target.FindFirstType("struct RNode").GetPointerType() + nd_type = (flags & RUBY_NODE_TYPEMASK) >> RUBY_NODE_TYPESHIFT + append_expression(debugger, "(node_type) %d" % nd_type, result) + val = val.Cast(tRTypedData) + append_expression(debugger, "*(struct RNode *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_MOVED: + tRTypedData = target.FindFirstType("struct RMoved").GetPointerType() + val = val.Cast(tRTypedData) + append_expression(debugger, "*(struct RMoved *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_MATCH: + tRTypedData = target.FindFirstType("struct RMatch").GetPointerType() + val = val.Cast(tRTypedData) + append_expression(debugger, "*(struct RMatch *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_IMEMO: + # I'm not sure how to get IMEMO_MASK out of lldb. It's not in globals() + imemo_type = (flags >> RUBY_FL_USHIFT) & 0x0F # IMEMO_MASK + + print("T_IMEMO: ", file=result) + append_expression(debugger, "(enum imemo_type) %d" % imemo_type, result) + append_expression(debugger, "*(struct MEMO *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_STRUCT: + tRTypedData = target.FindFirstType("struct RStruct").GetPointerType() + val = val.Cast(tRTypedData) + append_expression(debugger, "*(struct RStruct *) %0#x" % val.GetValueAsUnsigned(), result) + elif flType == RUBY_T_ZOMBIE: + tRZombie = target.FindFirstType("struct RZombie").GetPointerType() + val = val.Cast(tRZombie) + append_expression(debugger, "*(struct RZombie *) %0#x" % val.GetValueAsUnsigned(), result) + else: + print("Not-handled type %0#x" % flType, file=result) + print(val, file=result) + +def count_objects(debugger, command, ctx, result, internal_dict): + objspace = ctx.frame.EvaluateExpression("ruby_current_vm->objspace") + num_pages = objspace.GetValueForExpressionPath(".heap_pages.allocated_pages").unsigned + + counts = {} + total = 0 + for t in range(0x00, RUBY_T_MASK+1): + counts[t] = 0 + + for i in range(0, num_pages): + print("\rcounting... %d/%d" % (i, num_pages), end="") + page = objspace.GetValueForExpressionPath('.heap_pages.sorted[%d]' % i) + p = page.GetChildMemberWithName('start') + num_slots = page.GetChildMemberWithName('total_slots').unsigned + for j in range(0, num_slots): + obj = p.GetValueForExpressionPath('[%d]' % j) + flags = obj.GetValueForExpressionPath('.as.basic.flags').unsigned + obj_type = flags & RUBY_T_MASK + counts[obj_type] += 1 + total += num_slots + + print("\rTOTAL: %d, FREE: %d" % (total, counts[0x00])) + for sym in value_types: + print("%s: %d" % (sym, counts[globals()[sym]])) + +def stack_dump_raw(debugger, command, ctx, result, internal_dict): + ctx.frame.EvaluateExpression("rb_vmdebug_stack_dump_raw_current()") + +def check_bits(page, bitmap_name, bitmap_index, bitmap_bit, v): + bits = page.GetChildMemberWithName(bitmap_name) + plane = bits.GetChildAtIndex(bitmap_index).GetValueAsUnsigned() + if (plane & bitmap_bit) != 0: + return v + else: + return ' ' + +def heap_page_body(debugger, command, ctx, result, internal_dict): + target = debugger.GetSelectedTarget() + process = target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + + val = frame.EvaluateExpression(command) + page = get_page_body(lldb, target, val) + print("Page body address: ", page.GetAddress(), file=result) + print(page, file=result) + +def get_page_body(lldb, target, val): + tHeapPageBody = target.FindFirstType("struct heap_page_body") + addr = val.GetValueAsUnsigned() + page_addr = addr & ~(HEAP_PAGE_ALIGN_MASK) + address = lldb.SBAddress(page_addr, target) + return target.CreateValueFromAddress("page", address, tHeapPageBody) + +def get_page(lldb, target, val): + body = get_page_body(lldb, target, val) + return body.GetValueForExpressionPath("->header.page") + +def dump_node(debugger, command, ctx, result, internal_dict): + args = shlex.split(command) + if not args: + return + node = args[0] + + dump = ctx.frame.EvaluateExpression("(struct RString*)rb_parser_dump_tree((NODE*)(%s), 0)" % node) + output_string(ctx, result, dump) + +def rb_backtrace(debugger, command, result, internal_dict): + if not ('RUBY_Qfalse' in globals()): + lldb_init(debugger) + bt = BackTrace(debugger, command, result, internal_dict) + frame = bt.frame + + if command: + if frame.IsValid(): + val = frame.EvaluateExpression(command) + else: + val = target.EvaluateExpression(command) + + error = val.GetError() + if error.Fail(): + print >> result, error + return + else: + print("Need an EC for now") + + bt.print_bt(val) + +def dump_bits(target, result, page, object_address, end = "\n"): + slot_size = page.GetChildMemberWithName("heap").GetChildMemberWithName("slot_size").unsigned + byte_size = 40 ** math.floor(math.log(slot_size, 40)) + tUintPtr = target.FindFirstType("uintptr_t") # bits_t + + num_in_page = (object_address & HEAP_PAGE_ALIGN_MASK) // byte_size; + bits_bitlength = tUintPtr.GetByteSize() * 8 + bitmap_index = num_in_page // bits_bitlength + bitmap_offset = num_in_page & (bits_bitlength - 1) + bitmap_bit = 1 << bitmap_offset + + print("bits: [%s%s%s%s%s]" % ( + check_bits(page, "uncollectible_bits", bitmap_index, bitmap_bit, "L"), + check_bits(page, "mark_bits", bitmap_index, bitmap_bit, "M"), + check_bits(page, "pinned_bits", bitmap_index, bitmap_bit, "P"), + check_bits(page, "marking_bits", bitmap_index, bitmap_bit, "R"), + check_bits(page, "wb_unprotected_bits", bitmap_index, bitmap_bit, "U"), + ), end=end, file=result) + +class HeapPageIter: + def __init__(self, page, target): + self.page = page + self.target = target + self.start = page.GetChildMemberWithName('start').GetValueAsUnsigned(); + self.num_slots = page.GetChildMemberWithName('total_slots').unsigned + self.slot_size = page.GetChildMemberWithName('heap').GetChildMemberWithName('slot_size').unsigned + self.counter = 0 + self.tRBasic = target.FindFirstType("::RBasic") + + def is_valid(self): + heap_page_header_size = self.target.FindFirstType("struct heap_page_header").GetByteSize() + rvalue_size = self.slot_size + heap_page_obj_limit = int((HEAP_PAGE_SIZE - heap_page_header_size) / self.slot_size) + + return (heap_page_obj_limit - 1) <= self.num_slots <= heap_page_obj_limit + + def __iter__(self): + return self + + def __next__(self): + if self.counter < self.num_slots: + obj_addr_i = self.start + (self.counter * self.slot_size) + obj_addr = lldb.SBAddress(obj_addr_i, self.target) + slot_info = (self.counter, obj_addr_i, self.target.CreateValueFromAddress("object", obj_addr, self.tRBasic)) + self.counter += 1 + + return slot_info + else: + raise StopIteration + + +def dump_page_internal(page, target, process, thread, frame, result, debugger, highlight=None): + if not ('RUBY_Qfalse' in globals()): + lldb_init(debugger) + + ruby_type_map = ruby_types(debugger) + + freelist = [] + fl_start = page.GetChildMemberWithName('freelist').GetValueAsUnsigned() + free_slot = target.FindFirstType("struct free_slot") + + while fl_start > 0: + freelist.append(fl_start) + obj_addr = lldb.SBAddress(fl_start, target) + obj = target.CreateValueFromAddress("object", obj_addr, free_slot) + fl_start = obj.GetChildMemberWithName("next").GetValueAsUnsigned() + + page_iter = HeapPageIter(page, target) + if page_iter.is_valid(): + for (page_index, obj_addr, obj) in page_iter: + dump_bits(target, result, page, obj_addr, end= " ") + flags = obj.GetChildMemberWithName('flags').GetValueAsUnsigned() + flType = flags & RUBY_T_MASK + + flidx = ' ' + if flType == RUBY_T_NONE: + try: + flidx = "%3d" % freelist.index(obj_addr) + except ValueError: + flidx = ' -1' + + if flType == RUBY_T_NONE: + klass = obj.GetChildMemberWithName('klass').GetValueAsUnsigned() + result_str = "%s idx: [%3d] freelist_idx: {%s} Addr: %0#x (flags: %0#x, next: %0#x)" % (rb_type(flags, ruby_type_map), page_index, flidx, obj_addr, flags, klass) + else: + result_str = "%s idx: [%3d] freelist_idx: {%s} Addr: %0#x (flags: %0#x)" % (rb_type(flags, ruby_type_map), page_index, flidx, obj_addr, flags) + + if highlight == obj_addr: + result_str = ' '.join([result_str, "<<<<<"]) + + print(result_str, file=result) + else: + print("%s is not a valid heap page" % page, file=result) + + + +def dump_page(debugger, command, result, internal_dict): + target = debugger.GetSelectedTarget() + process = target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + + tHeapPageP = target.FindFirstType("struct heap_page").GetPointerType() + page = frame.EvaluateExpression(command) + page = page.Cast(tHeapPageP) + + dump_page_internal(page, target, process, thread, frame, result, debugger) + + +def dump_page_rvalue(debugger, command, result, internal_dict): + target = debugger.GetSelectedTarget() + process = target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + + val = frame.EvaluateExpression(command) + page = get_page(lldb, target, val) + page_type = target.FindFirstType("struct heap_page").GetPointerType() + page.Cast(page_type) + + dump_page_internal(page, target, process, thread, frame, result, debugger, highlight=val.GetValueAsUnsigned()) + + + +def rb_type(flags, ruby_types): + flType = flags & RUBY_T_MASK + return "%-10s" % (ruby_types.get(flType, ("%0#x" % flType))) + +def ruby_types(debugger): + target = debugger.GetSelectedTarget() + + types = {} + for enum in target.FindFirstGlobalVariable('ruby_dummy_gdb_enums'): + enum = enum.GetType() + members = enum.GetEnumMembers() + for i in range(0, members.GetSize()): + member = members.GetTypeEnumMemberAtIndex(i) + name = member.GetName() + value = member.GetValueAsUnsigned() + + if name.startswith('RUBY_T_'): + types[value] = name.replace('RUBY_', '') + + return types + +def rb_ary_entry(target, ary, idx, result): + tRArray = target.FindFirstType("struct RArray").GetPointerType() + ary = ary.Cast(tRArray) + flags = ary.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + + if flags & RUBY_FL_USER1: + ptr = ary.GetValueForExpressionPath("->as.ary") + else: + ptr = ary.GetValueForExpressionPath("->as.heap.ptr") + + ptr_addr = ptr.GetValueAsUnsigned() + (idx * ptr.GetType().GetByteSize()) + return target.CreateValueFromAddress("ary_entry[%d]" % idx, lldb.SBAddress(ptr_addr, target), ptr.GetType().GetPointeeType()) + +def rb_id_to_serial(id_val): + if id_val > tLAST_OP_ID: + return id_val >> RUBY_ID_SCOPE_SHIFT + else: + return id_val + +def rb_id2str(debugger, command, result, internal_dict): + if not ('RUBY_Qfalse' in globals()): + lldb_init(debugger) + + target = debugger.GetSelectedTarget() + process = target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + global_symbols = target.FindFirstGlobalVariable("ruby_global_symbols") + + id_val = frame.EvaluateExpression(command).GetValueAsUnsigned() + num = rb_id_to_serial(id_val) + + last_id = global_symbols.GetChildMemberWithName("last_id").GetValueAsUnsigned() + ID_ENTRY_SIZE = 2 + ID_ENTRY_UNIT = int(target.FindFirstGlobalVariable("ID_ENTRY_UNIT").GetValue()) + + ids = global_symbols.GetChildMemberWithName("ids") + + if (num <= last_id): + idx = num // ID_ENTRY_UNIT + ary = rb_ary_entry(target, ids, idx, result) + pos = (num % ID_ENTRY_UNIT) * ID_ENTRY_SIZE + id_str = rb_ary_entry(target, ary, pos, result) + lldb_inspect(debugger, target, result, id_str) +# END FUNCTION STYLE DECLS + + +load_dir, _ = os.path.split(os.path.realpath(__file__)) + +for fname in glob.glob(f"{load_dir}/lldb_rb/commands/*_command.py"): + _, basename = os.path.split(fname) + mname, _ = os.path.splitext(basename) + + exec(f"import lldb_rb.commands.{mname}") + +def __lldb_init_module(debugger, internal_dict): + # Register all classes that subclass RbBaseCommand + + for memname, mem in inspect.getmembers(sys.modules["lldb_rb.rb_base_command"]): + if memname == "RbBaseCommand": + for sclass in mem.__subclasses__(): + sclass.register_lldb_command(debugger, f"{__name__}.{sclass.__module__}") + + + ## FUNCTION INITS - These should be removed when converted to class commands + debugger.HandleCommand("command script add -f lldb_cruby.lldb_rp old_rp") + debugger.HandleCommand("command script add -f lldb_cruby.count_objects rb_count_objects") + debugger.HandleCommand("command script add -f lldb_cruby.stack_dump_raw SDR") + debugger.HandleCommand("command script add -f lldb_cruby.dump_node dump_node") + debugger.HandleCommand("command script add -f lldb_cruby.heap_page_body heap_page_body") + debugger.HandleCommand("command script add -f lldb_cruby.rb_backtrace rbbt") + debugger.HandleCommand("command script add -f lldb_cruby.dump_page dump_page") + debugger.HandleCommand("command script add -f lldb_cruby.dump_page_rvalue dump_page_rvalue") + debugger.HandleCommand("command script add -f lldb_cruby.rb_id2str old_rb_id2str") + + lldb_rb.rb_base_command.RbBaseCommand.lldb_init(debugger) + + print("lldb scripts for ruby has been installed.") diff --git a/misc/lldb_disasm.py b/misc/lldb_disasm.py new file mode 100644 index 0000000000..ab759f009a --- /dev/null +++ b/misc/lldb_disasm.py @@ -0,0 +1,250 @@ +#!/usr/bin/env python +#coding: utf-8 +# +# Usage: run `command script import -r misc/lldb_disasm.py` on LLDB +# +# +# (lldb) p iseq +# (rb_iseq_t *) $147 = 0x0000000101068400 +# (lldb) rbdisasm iseq +# 0000 putspecialobject( 3 ) +# 0002 putnil +# 0003 defineclass( ID: 0x560b, (rb_iseq_t *)0x1010681d0, 2 ) +# 0007 pop +# 0008 putspecialobject( 3 ) +# 0010 putnil +# 0011 defineclass( ID: 0x56eb, (rb_iseq_t *)0x101063b58, 2 ) +# 0015 leave + + +import lldb +import os +import shlex + +class IseqDisassembler: + TS_VARIABLE = b'.'[0] + TS_CALLDATA = b'C'[0] + TS_CDHASH = b'H'[0] + TS_IC = b'K'[0] + TS_IVC = b'A'[0] + TS_ICVARC = b'J'[0] + TS_ID = b'I'[0] + TS_ISE = b'T'[0] + TS_ISEQ = b'S'[0] + TS_OFFSET = b'O'[0] + TS_VALUE = b'V'[0] + TS_LINDEX = b'L'[0] + TS_FUNCPTR = b'F'[0] + TS_NUM = b'N'[0] + TS_BUILTIN = b'R'[0] + + ISEQ_OPT_DISPATCH = { + TS_BUILTIN: "(rb_builtin_function *)%0#x", + TS_NUM: "%d", + TS_FUNCPTR: "(rb_insn_func_t) %0#x", + TS_LINDEX: "%d", + TS_VALUE: "(VALUE)%0#x", + TS_OFFSET: "%d", + TS_ISEQ: "(rb_iseq_t *)%0#x", + TS_ISE: "(iseq_inline_storage_entry *)%0#x", + TS_ID: "ID: %0#x", + TS_IVC: "(struct iseq_inline_iv_cache_entry *)%0#x", + TS_ICVARC: "(struct iseq_inline_cvar_cache_entry *)%0#x", + TS_IC: "(struct iseq_inline_cache_entry *)%0#x", + TS_CDHASH: "CDHASH (VALUE)%0#x", + TS_CALLDATA: "(struct rb_call_data *)%0#x", + TS_VARIABLE: "VARIABLE %0#x", + } + + def __init__(self, debugger, command, result, internal_dict): + self.debugger = debugger + self.command = command + self.result = result + self.internal_dict = internal_dict + + self.target = debugger.GetSelectedTarget() + self.insns_address_table = self.__get_insns_address_table() + self.process = self.target.GetProcess() + self.thread = self.process.GetSelectedThread() + self.frame = self.thread.GetSelectedFrame() + self.addr2insn = self.build_addr2insn(self.target) + self.tChar = self.target.FindFirstType("char") + + def disasm(self, val): + tRbISeq = self.target.FindFirstType("struct rb_iseq_struct").GetPointerType() + val = val.Cast(tRbISeq) + iseq_size = val.GetValueForExpressionPath("->body->iseq_size").GetValueAsUnsigned() + iseqs = val.GetValueForExpressionPath("->body->iseq_encoded") + idx = 0 + print("PC IDX insn_name(operands) ", file=self.result) + while idx < iseq_size: + m = self.iseq_extract_values(self.debugger, self.target, self.process, self.result, iseqs, idx) + if m < 1: + print("Error decoding", file=self.result) + return + else: + idx += m + + def build_addr2insn(self, target): + tIntPtr = target.FindFirstType("intptr_t") + size = target.EvaluateExpression('ruby_vminsn_type::VM_INSTRUCTION_SIZE').unsigned + sizeOfIntPtr = tIntPtr.GetByteSize() + addr_of_table = self.insns_address_table.GetStartAddress().GetLoadAddress(target) + + my_dict = {} + + for insn in range(size): + addr_in_table = addr_of_table + (insn * sizeOfIntPtr) + addr = lldb.SBAddress(addr_in_table, target) + machine_insn = target.CreateValueFromAddress("insn", addr, tIntPtr).GetValueAsUnsigned() + my_dict[machine_insn] = insn + + return my_dict + + def rb_vm_insn_addr2insn2(self, target, result, wanted_addr): + return self.addr2insn.get(wanted_addr) + + def iseq_extract_values(self, debugger, target, process, result, iseqs, n): + tValueP = target.FindFirstType("VALUE") + sizeofValueP = tValueP.GetByteSize() + pc = iseqs.unsigned + (n * sizeofValueP) + insn = target.CreateValueFromAddress("i", lldb.SBAddress(pc, target), tValueP) + addr = insn.GetValueAsUnsigned() + orig_insn = self.rb_vm_insn_addr2insn2(target, result, addr) + + name = self.insn_name(target, process, result, orig_insn) + length = self.insn_len(target, orig_insn) + op_str = self.insn_op_types(target, process, result, orig_insn) + op_types = bytes(op_str, 'utf-8') + + if length != (len(op_types) + 1): + print("error decoding iseqs", file=result) + return -1 + + print("%0#14x %04d %s" % (pc, n, name), file=result, end="") + + if length == 1: + print("", file=result) + return length + + print("(", end="", file=result) + for idx, op_type in enumerate(op_types): + if idx == 0: + print(" ", end="", file=result) + else: + print(", ", end="", file=result) + + opAddr = lldb.SBAddress(iseqs.unsigned + ((n + idx + 1) * sizeofValueP), target) + opValue = target.CreateValueFromAddress("op", opAddr, tValueP) + op = opValue.GetValueAsUnsigned() + print(self.ISEQ_OPT_DISPATCH.get(op_type) % op, end="", file=result) + + print(" )", file=result) + return length + + def insn_len(self, target, offset): + size_of_char = self.tChar.GetByteSize() + + symbol = target.FindSymbols("rb_vm_insn_len_info")[0].GetSymbol() + section = symbol.GetStartAddress().GetSection() + addr_of_table = symbol.GetStartAddress().GetOffset() + + error = lldb.SBError() + length = section.GetSectionData().GetUnsignedInt8(error, addr_of_table + (offset * size_of_char)) + + if error.Success(): + return length + else: + print("error getting length: ", error) + + def insn_op_types(self, target, process, result, insn): + tUShort = target.FindFirstType("unsigned short") + + size_of_short = tUShort.GetByteSize() + size_of_char = self.tChar.GetByteSize() + + symbol = target.FindSymbols("rb_vm_insn_op_offset")[0].GetSymbol() + section = symbol.GetStartAddress().GetSection() + addr_of_table = symbol.GetStartAddress().GetOffset() + + addr_in_table = addr_of_table + (insn * size_of_short) + + error = lldb.SBError() + offset = section.GetSectionData().GetUnsignedInt16(error, addr_in_table) + + if not error.Success(): + print("error getting op type offset: ", error) + + symbol = target.FindSymbols("rb_vm_insn_op_base")[0].GetSymbol() + section = symbol.GetStartAddress().GetSection() + addr_of_table = symbol.GetStartAddress().GetOffset() + addr_in_name_table = addr_of_table + (offset * size_of_char) + + error = lldb.SBError() + types = section.GetSectionData().GetString(error, addr_in_name_table) + if error.Success(): + return types + else: + print("error getting op types: ", error) + + def insn_name_table_offset(self, target, offset): + tUShort = target.FindFirstType("unsigned short") + size_of_short = tUShort.GetByteSize() + + symbol = target.FindSymbols("rb_vm_insn_name_offset")[0].GetSymbol() + section = symbol.GetStartAddress().GetSection() + table_offset = symbol.GetStartAddress().GetOffset() + + table_offset = table_offset + (offset * size_of_short) + + error = lldb.SBError() + offset = section.GetSectionData().GetUnsignedInt16(error, table_offset) + + if error.Success(): + return offset + else: + print("error getting insn name table offset: ", error) + + def insn_name(self, target, process, result, offset): + symbol = target.FindSymbols("rb_vm_insn_name_base")[0].GetSymbol() + section = symbol.GetStartAddress().GetSection() + addr_of_table = symbol.GetStartAddress().GetOffset() + + name_table_offset = self.insn_name_table_offset(target, offset) + addr_in_name_table = addr_of_table + name_table_offset + + error = lldb.SBError() + name = section.GetSectionData().GetString(error, addr_in_name_table) + + if error.Success(): + return name + else: + print('error getting insn name', error) + + def __get_insns_address_table(self): + module = self.target.FindSymbols("vm_exec_core")[0].GetModule() + + for symbol in module: + if "insns_address_table" in symbol.name and symbol.GetType() == lldb.eSymbolTypeData: + print(f"found symbol {symbol.name}") + return symbol + + +def disasm(debugger, command, result, internal_dict): + disassembler = IseqDisassembler(debugger, command, result, internal_dict) + frame = disassembler.frame + + if frame.IsValid(): + val = frame.EvaluateExpression(command) + else: + val = target.EvaluateExpression(command) + error = val.GetError() + if error.Fail(): + print >> result, error + return + + disassembler.disasm(val); + +def __lldb_init_module(debugger, internal_dict): + debugger.HandleCommand("command script add -f lldb_disasm.disasm rbdisasm") + print("lldb Ruby disasm installed.") diff --git a/misc/lldb_rb/commands/command_template.py b/misc/lldb_rb/commands/command_template.py new file mode 100644 index 0000000000..21014a993e --- /dev/null +++ b/misc/lldb_rb/commands/command_template.py @@ -0,0 +1,30 @@ +# This is a command template for implementing a helper function inside LLDB. To +# use this file +# 1. Copy it and rename the copy so it ends with `_command.py`. +# 2. Rename the class to something descriptive that ends with Command. +# 3. Change the program variable to be a descriptive command name +# 4. Ensure you are inheriting from RbBaseCommand or another command that +# implements the same interface + +import lldb + +from lldb_rb.constants import * +from lldb_rb.rb_base_command import RbBaseCommand + +# This test command inherits from RbBaseCommand which provides access to Ruby +# globals and utility helpers +class TestCommand(RbBaseCommand): + # program is the keyword the user will type in lldb to execute this command + program = "test" + + # help_string will be displayed in lldb when the user uses the help functions + help_string = "This is a test command to show how to implement lldb commands" + + # call is where our command logic will be implemented + def call(self, debugger, command, exe_ctx, result): + # This method will be called once the LLDB environment has been setup. + # You will have access to self.target, self.process, self.frame, and + # self.thread + # + # This is where we should implement our command logic + pass diff --git a/misc/lldb_rb/commands/heap_page_command.py b/misc/lldb_rb/commands/heap_page_command.py new file mode 100644 index 0000000000..2eed3c3bee --- /dev/null +++ b/misc/lldb_rb/commands/heap_page_command.py @@ -0,0 +1,27 @@ +import lldb + +from lldb_rb.constants import * +from lldb_rb.rb_base_command import RbBaseCommand + +class HeapPageCommand(RbBaseCommand): + program = "heap_page" + help_string = "prints out 'struct heap_page' for a VALUE pointer in the page" + + def call(self, debugger, command, exe_ctx, result): + self.result = result + self.t_heap_page_body = self.target.FindFirstType("struct heap_page_body") + self.t_heap_page_ptr = self.target.FindFirstType("struct heap_page").GetPointerType() + + page = self._get_page(self.frame.EvaluateExpression(command)) + page.Cast(self.t_heap_page_ptr) + + self._append_expression("(struct heap_page *) %0#x" % page.GetValueAsUnsigned()) + self._append_expression("*(struct heap_page *) %0#x" % page.GetValueAsUnsigned()) + + def _get_page(self, val): + addr = val.GetValueAsUnsigned() + page_addr = addr & ~(HEAP_PAGE_ALIGN_MASK) + address = lldb.SBAddress(page_addr, self.target) + body = self.target.CreateValueFromAddress("page", address, self.t_heap_page_body) + + return body.GetValueForExpressionPath("->header.page") diff --git a/misc/lldb_rb/commands/print_flags_command.py b/misc/lldb_rb/commands/print_flags_command.py new file mode 100644 index 0000000000..bc494ae01a --- /dev/null +++ b/misc/lldb_rb/commands/print_flags_command.py @@ -0,0 +1,31 @@ +import lldb +import re + +from lldb_rb.constants import * +from lldb_rb.rb_base_command import RbBaseCommand + +class PrintFlagsCommand(RbBaseCommand): + program = "print_flags" + + help_string = "Print out the individial flags of an RVALUE object in human readable format" + + # call is where our command logic will be implemented + def call(self, debugger, command, exe_ctx, result): + rclass_t = self.target.FindFirstType("::RBasic") + rcass_ptr = self.target.EvaluateExpression(command).Cast(rclass_t.GetPointerType()) + obj_flags = rcass_ptr.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + + flags = [ + "RUBY_FL_WB_PROTECTED", "RUBY_FL_PROMOTED", "RUBY_FL_FINALIZE", + "RUBY_FL_SHAREABLE", "RUBY_FL_FREEZE", + "RUBY_FL_USER0", "RUBY_FL_USER1", "RUBY_FL_USER2", "RUBY_FL_USER3", "RUBY_FL_USER4", + "RUBY_FL_USER5", "RUBY_FL_USER6", "RUBY_FL_USER7", "RUBY_FL_USER8", "RUBY_FL_USER9", + "RUBY_FL_USER10", "RUBY_FL_USER11", "RUBY_FL_USER12", "RUBY_FL_USER13", "RUBY_FL_USER14", + "RUBY_FL_USER15", "RUBY_FL_USER16", "RUBY_FL_USER17", "RUBY_FL_USER18" + ] + + types_index = {v: k for k, v in self.ruby_globals.items() if re.match(r'RUBY_T_', k)} + print("TYPE: {}".format(types_index[obj_flags & self.ruby_globals["RUBY_T_MASK"]])) + for flag in flags: + output = "{} : {}".format(flag, "1" if (obj_flags & self.ruby_globals[flag]) else "0") + print(output, file=result) diff --git a/misc/lldb_rb/commands/rb_id2str_command.py b/misc/lldb_rb/commands/rb_id2str_command.py new file mode 100644 index 0000000000..6ee859ebf6 --- /dev/null +++ b/misc/lldb_rb/commands/rb_id2str_command.py @@ -0,0 +1,49 @@ +import lldb + +from lldb_rb.constants import * +from lldb_rb.utils import * +from lldb_rb.rb_base_command import RbBaseCommand + +class RbID2StrCommand(RbBaseCommand): + program = "rb_id2str" + + help_string = "convert and print a Ruby ID to a C string and print it to the LLDB console" + + def call(self, debugger, command, exe_ctx, result): + global_symbols = self.target.FindFirstGlobalVariable("ruby_global_symbols") + + id_val = self.frame.EvaluateExpression(command).GetValueAsUnsigned() + num = self.rb_id_to_serial(id_val) + + last_id = global_symbols.GetChildMemberWithName("last_id").GetValueAsUnsigned() + ID_ENTRY_SIZE = 2 + ID_ENTRY_UNIT = int(self.target.FindFirstGlobalVariable("ID_ENTRY_UNIT").GetValue()) + + ids = global_symbols.GetChildMemberWithName("ids") + + if num <= last_id: + idx = num // ID_ENTRY_UNIT + ary = self.rb_ary_entry(ids, idx, result) + pos = (num % ID_ENTRY_UNIT) * ID_ENTRY_SIZE + id_str = self.rb_ary_entry(ary, pos, result) + + RbInspector(debugger, result, self.ruby_globals).inspect(id_str) + + def rb_id_to_serial(self, id_val): + if id_val > self.ruby_globals["tLAST_OP_ID"]: + return id_val >> self.ruby_globals["RUBY_ID_SCOPE_SHIFT"] + else: + return id_val + + def rb_ary_entry(self, ary, idx, result): + tRArray = self.target.FindFirstType("struct RArray").GetPointerType() + ary = ary.Cast(tRArray) + flags = ary.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + + if flags & self.ruby_globals["RUBY_FL_USER1"]: + ptr = ary.GetValueForExpressionPath("->as.ary") + else: + ptr = ary.GetValueForExpressionPath("->as.heap.ptr") + + ptr_addr = ptr.GetValueAsUnsigned() + (idx * ptr.GetType().GetByteSize()) + return self.target.CreateValueFromAddress("ary_entry[%d]" % idx, lldb.SBAddress(ptr_addr, self.target), ptr.GetType().GetPointeeType()) diff --git a/misc/lldb_rb/commands/rclass_ext_command.py b/misc/lldb_rb/commands/rclass_ext_command.py new file mode 100644 index 0000000000..8bae911457 --- /dev/null +++ b/misc/lldb_rb/commands/rclass_ext_command.py @@ -0,0 +1,14 @@ +from lldb_rb.rb_base_command import RbBaseCommand + +class RclassExtCommand(RbBaseCommand): + program = "rclass_ext" + help_string = "retrieves and prints the rb_classext_struct for the VALUE pointer passed in" + + def call(self, debugger, command, exe_ctx, result): + uintptr_t = self.target.FindFirstType("uintptr_t") + rclass_t = self.target.FindFirstType("struct RClass") + rclass_ext_t = self.target.FindFirstType("rb_classext_t") + + rclass_addr = self.target.EvaluateExpression(command).Cast(uintptr_t) + rclass_ext_addr = (rclass_addr.GetValueAsUnsigned() + rclass_t.GetByteSize()) + debugger.HandleCommand("p *(rb_classext_t *)%0#x" % rclass_ext_addr) diff --git a/misc/lldb_rb/commands/rp_command.py b/misc/lldb_rb/commands/rp_command.py new file mode 100644 index 0000000000..06b2516d50 --- /dev/null +++ b/misc/lldb_rb/commands/rp_command.py @@ -0,0 +1,15 @@ +import lldb + +from lldb_rb.constants import * +from lldb_rb.utils import * +from lldb_rb.rb_base_command import RbBaseCommand + +class RbID2StrCommand(RbBaseCommand): + program = "rp" + + help_string = "convert and print a Ruby ID to a C string and print it to the LLDB console" + + def call(self, debugger, command, exe_ctx, result): + val = self.frame.EvaluateExpression(command) + inspector = RbInspector(debugger, result, self.ruby_globals) + inspector.inspect(val) diff --git a/misc/lldb_rb/constants.py b/misc/lldb_rb/constants.py new file mode 100644 index 0000000000..9cd56eccb0 --- /dev/null +++ b/misc/lldb_rb/constants.py @@ -0,0 +1,6 @@ +HEAP_PAGE_ALIGN_LOG = 16 +HEAP_PAGE_ALIGN_MASK = (~(~0 << HEAP_PAGE_ALIGN_LOG)) +HEAP_PAGE_ALIGN = (1 << HEAP_PAGE_ALIGN_LOG) +HEAP_PAGE_SIZE = HEAP_PAGE_ALIGN + +IMEMO_MASK = 0x0F diff --git a/misc/lldb_rb/lldb_interface.py b/misc/lldb_rb/lldb_interface.py new file mode 100644 index 0000000000..25930b2e16 --- /dev/null +++ b/misc/lldb_rb/lldb_interface.py @@ -0,0 +1,18 @@ +class LLDBInterface: + def build_environment(self, debugger): + self.debugger = debugger + self.target = debugger.GetSelectedTarget() + self.process = self.target.GetProcess() + self.thread = self.process.GetSelectedThread() + self.frame = self.thread.GetSelectedFrame() + + def _append_command_output(self, command): + output1 = self.result.GetOutput() + self.debugger.GetCommandInterpreter().HandleCommand(command, self.result) + output2 = self.result.GetOutput() + self.result.Clear() + self.result.write(output1) + self.result.write(output2) + + def _append_expression(self, expression): + self._append_command_output("expression " + expression) diff --git a/misc/lldb_rb/rb_base_command.py b/misc/lldb_rb/rb_base_command.py new file mode 100644 index 0000000000..70a5addd6d --- /dev/null +++ b/misc/lldb_rb/rb_base_command.py @@ -0,0 +1,57 @@ +import lldb +from pydoc import locate +from lldb_rb.constants import * +from lldb_rb.utils import * + +class RbBaseCommand(LLDBInterface): + @classmethod + def register_lldb_command(cls, debugger, module_name): + # Add any commands contained in this module to LLDB + command = f"command script add -c {module_name}.{cls.__name__} {cls.program}" + debugger.HandleCommand(command) + + @classmethod + def lldb_init(cls, debugger): + target = debugger.GetSelectedTarget() + global SIZEOF_VALUE + SIZEOF_VALUE = target.FindFirstType("VALUE").GetByteSize() + + value_types = [] + g = globals() + + imemo_types = target.FindFirstType("enum imemo_type") + + #for member in imemo_types.GetEnumMembers(): + # g[member.GetName()] = member.GetValueAsUnsigned() + + for enum in target.FindFirstGlobalVariable("ruby_dummy_gdb_enums"): + enum = enum.GetType() + members = enum.GetEnumMembers() + for i in range(0, members.GetSize()): + member = members.GetTypeEnumMemberAtIndex(i) + name = member.GetName() + value = member.GetValueAsUnsigned() + g[name] = value + + if name.startswith("RUBY_T_"): + value_types.append(name) + g["value_types"] = value_types + return g + + def __init__(self, debugger, _internal_dict): + self.ruby_globals = RbBaseCommand.lldb_init(debugger) + self.internal_dict = _internal_dict + + def __call__(self, debugger, command, exe_ctx, result): + self.ruby_globals = RbBaseCommand.lldb_init(debugger) + self.build_environment(debugger) + self.call(debugger, command, exe_ctx, result) + + def call(self, debugger, command, exe_ctx, result): + raise NotImplementedError("subclasses must implement call") + + def get_short_help(self): + return self.__class__.help_string + + def get_long_help(self): + return self.__class__.help_string diff --git a/misc/lldb_rb/rb_heap_structs.py b/misc/lldb_rb/rb_heap_structs.py new file mode 100644 index 0000000000..798b838080 --- /dev/null +++ b/misc/lldb_rb/rb_heap_structs.py @@ -0,0 +1,152 @@ +import lldb +import math +from lldb_rb.lldb_interface import LLDBInterface +from lldb_rb.constants import * + +class HeapPage(LLDBInterface): + def __init__(self, debugger, val): + self.build_environment(debugger) + self.page_type = self.target.FindFirstType("struct heap_page").GetPointerType() + self.val = val + + def heap_page_body(self, command, ctx, result, internal_dict): + process = self.target.GetProcess() + thread = process.GetSelectedThread() + frame = thread.GetSelectedFrame() + + val = frame.EvaluateExpression(command) + page = self.get_page_body(val) + print("Page body address: ", page.GetAddress(), file=result) + print(page, file=result) + + def get_page_body(self, val): + tHeapPageBody = self.target.FindFirstType("struct heap_page_body") + addr = val.GetValueAsUnsigned() + page_addr = addr & ~(HEAP_PAGE_ALIGN_MASK) + address = lldb.SBAddress(page_addr, self.target) + return self.target.CreateValueFromAddress("page", address, tHeapPageBody) + + def get_page_raw(self, val): + body = self.get_page_body(val) + return body.GetValueForExpressionPath("->header.page") + + def to_heap_page_struct(self): + pagePtr = self.get_page_raw(self.val) + return pagePtr.Cast(self.page_type) + + +class RbObject(LLDBInterface): + def __init__(self, ptr, debugger, ruby_globals): + self.build_environment(debugger) + self.ruby_globals = ruby_globals + + self.flUser1 = self.ruby_globals["RUBY_FL_USER1"] + self.flUser2 = self.ruby_globals["RUBY_FL_USER2"] + self.flUser3 = self.ruby_globals["RUBY_FL_USER3"] + self.flUser4 = self.ruby_globals["RUBY_FL_USER4"] + self.flUser5 = self.ruby_globals["RUBY_FL_USER5"] + self.flUser6 = self.ruby_globals["RUBY_FL_USER6"] + self.flUser7 = self.ruby_globals["RUBY_FL_USER7"] + self.flUser8 = self.ruby_globals["RUBY_FL_USER8"] + self.flUser9 = self.ruby_globals["RUBY_FL_USER9"] + self.flUshift = self.ruby_globals["RUBY_FL_USHIFT"] + + self.tRBasic = self.target.FindFirstType("::RBasic").GetPointerType() + + self.val = ptr.Cast(self.tRBasic) + self.page = HeapPage(self.debugger, self.val) + self.flags = self.val.GetValueForExpressionPath("->flags").GetValueAsUnsigned() + + self.type = None + self.type_name = "" + + def check_bits(self, bitmap_name, bitmap_index, bitmap_bit, v): + page = self.page.to_heap_page_struct() + bits = page.GetChildMemberWithName(bitmap_name) + plane = bits.GetChildAtIndex(bitmap_index).GetValueAsUnsigned() + if (plane & bitmap_bit) != 0: + return v + else: + return ' ' + + def dump_bits(self, result, end = "\n"): + tUintPtr = self.target.FindFirstType("uintptr_t") # bits_t + + slot_size = self.page.to_heap_page_struct().GetChildMemberWithName("heap").GetChildMemberWithName("slot_size").unsigned + byte_size = 40 ** math.floor(math.log(slot_size, 40)) + + num_in_page = (self.val.GetValueAsUnsigned() & HEAP_PAGE_ALIGN_MASK) // byte_size; + bits_bitlength = tUintPtr.GetByteSize() * 8 + bitmap_index = num_in_page // bits_bitlength + bitmap_offset = num_in_page & (bits_bitlength - 1) + bitmap_bit = 1 << bitmap_offset + + page = self.page.to_heap_page_struct() + print("bits: [%s%s%s%s%s]" % ( + self.check_bits("uncollectible_bits", bitmap_index, bitmap_bit, "L"), + self.check_bits("mark_bits", bitmap_index, bitmap_bit, "M"), + self.check_bits("pinned_bits", bitmap_index, bitmap_bit, "P"), + self.check_bits("marking_bits", bitmap_index, bitmap_bit, "R"), + self.check_bits("wb_unprotected_bits", bitmap_index, bitmap_bit, "U"), + ), end=end, file=result) + + def promoted_p(self): + rbFlPromoted = self.ruby_globals["RUBY_FL_PROMOTED"] + return (self.flags & rbFlPromoted) == rbFlPromoted + + def frozen_p(self): + rbFlFreeze = self.ruby_globals["RUBY_FL_FREEZE"] + return (self.flags & rbFlFreeze) == rbFlFreeze + + def is_type(self, type_name): + if self.type is None: + flTMask = self.ruby_globals["RUBY_T_MASK"] + flType = self.flags & flTMask + self.type = flType + + if self.type == self.ruby_globals[type_name]: + self.type_name = type_name + return True + else: + return False + + def as_type(self, type_name): + if type_name == "array": + tRarray = self.target.FindFirstType("struct RArray") + return self.val.Cast(tRarray.GetPointerType()) + elif type_name == "bignum": + tRbignum = self.target.FindFirstType("struct RBignum") + return self.val.Cast(tRbignum.GetPointerType()) + else: + print("as_type is not implemented for:", type_name) + + def ary_ptr(self): + rval = self.as_type("array") + if self.flags & self.ruby_globals["RUBY_FL_USER1"]: + ptr = rval.GetValueForExpressionPath("->as.ary") + else: + ptr = rval.GetValueForExpressionPath("->as.heap.ptr") + return ptr + + def ary_len(self): + if self.flags & self.flUser1: + len = ((self.flags & + (self.flUser3 | self.flUser4 | self.flUser5 | self.flUser6 | + self.flUser7 | self.flUser8 | self.flUser9) + ) >> (self.flUshift + 3)) + else: + rval = self.as_type("array") + len = rval.GetValueForExpressionPath("->as.heap.len").GetValueAsSigned() + + return len + + def bignum_len(self): + if self.flags & self.flUser2: + len = ((self.flags & + (self.flUser3 | self.flUser4 | self.flUser5) + ) >> (self.flUshift + 3)) + else: + len = (self.as_type("bignum").GetValueForExpressionPath("->as.heap.len"). + GetValueAsUnsigned()) + + return len diff --git a/misc/lldb_rb/utils.py b/misc/lldb_rb/utils.py new file mode 100644 index 0000000000..1415dd3f33 --- /dev/null +++ b/misc/lldb_rb/utils.py @@ -0,0 +1,515 @@ +from lldb_rb.lldb_interface import LLDBInterface +from lldb_rb.rb_heap_structs import HeapPage, RbObject +from lldb_rb.constants import * + +class RbInspector(LLDBInterface): + def __init__(self, debugger, result, ruby_globals): + self.build_environment(debugger) + self.result = result + self.ruby_globals = ruby_globals + + def string2cstr(self, rstring): + """Returns the pointer to the C-string in the given String object""" + if rstring.TypeIsPointerType(): + rstring = rstring.Dereference() + + flags = rstring.GetValueForExpressionPath(".basic->flags").unsigned + clen = int(rstring.GetValueForExpressionPath(".len").value, 0) + if flags & self.ruby_globals["RUBY_FL_USER1"]: + cptr = int(rstring.GetValueForExpressionPath(".as.heap.ptr").value, 0) + else: + cptr = int(rstring.GetValueForExpressionPath(".as.embed.ary").location, 0) + + return cptr, clen + + def output_string(self, rstring): + cptr, clen = self.string2cstr(rstring) + self._append_expression("*(const char (*)[%d])%0#x" % (clen, cptr)) + + def fixnum_p(self, x): + return x & self.ruby_globals["RUBY_FIXNUM_FLAG"] != 0 + + def flonum_p(self, x): + return (x & self.ruby_globals["RUBY_FLONUM_MASK"]) == self.ruby_globals["RUBY_FLONUM_FLAG"] + + def static_sym_p(self, x): + special_shift = self.ruby_globals["RUBY_SPECIAL_SHIFT"] + symbol_flag = self.ruby_globals["RUBY_SYMBOL_FLAG"] + return (x & ~(~0 << special_shift)) == symbol_flag + + def generic_inspect(self, val, rtype): + tRType = self.target.FindFirstType("struct %s" % rtype).GetPointerType() + val = val.Cast(tRType) + self._append_expression("*(struct %s *) %0#x" % (rtype, val.GetValueAsUnsigned())) + + def inspect(self, val): + rbTrue = self.ruby_globals["RUBY_Qtrue"] + rbFalse = self.ruby_globals["RUBY_Qfalse"] + rbNil = self.ruby_globals["RUBY_Qnil"] + rbUndef = self.ruby_globals["RUBY_Qundef"] + rbImmediateMask = self.ruby_globals["RUBY_IMMEDIATE_MASK"] + + if self.inspect_node(val): + return + + num = val.GetValueAsSigned() + if num == rbFalse: + print('false', file=self.result) + elif num == rbTrue: + print('true', file=self.result) + elif num == rbNil: + print('nil', file=self.result) + elif num == rbUndef: + print('undef', file=self.result) + elif self.fixnum_p(num): + print(num >> 1, file=self.result) + elif self.flonum_p(num): + self._append_expression("rb_float_value(%0#x)" % val.GetValueAsUnsigned()) + elif self.static_sym_p(num): + if num < 128: + print("T_SYMBOL: %c" % num, file=self.result) + else: + print("T_SYMBOL: (%x)" % num, file=self.result) + self._append_expression("rb_id2name(%0#x)" % (num >> 8)) + + elif num & rbImmediateMask: + print('immediate(%x)' % num, file=self.result) + else: + rval = RbObject(val, self.debugger, self.ruby_globals) + rval.dump_bits(self.result) + + flaginfo = "" + if rval.promoted_p(): + flaginfo += "[PROMOTED] " + if rval.frozen_p(): + flaginfo += "[FROZEN] " + + if rval.is_type("RUBY_T_NONE"): + print('T_NONE: %s%s' % (flaginfo, val.Dereference()), file=self.result) + + elif rval.is_type("RUBY_T_NIL"): + print('T_NIL: %s%s' % (flaginfo, val.Dereference()), file=self.result) + + elif rval.is_type("RUBY_T_OBJECT"): + self.result.write('T_OBJECT: %s' % flaginfo) + self._append_expression("*(struct RObject*)%0#x" % val.GetValueAsUnsigned()) + + elif (rval.is_type("RUBY_T_CLASS") or + rval.is_type("RUBY_T_MODULE") or + rval.is_type("RUBY_T_ICLASS")): + self.result.write('T_%s: %s' % (rval.type_name.split('_')[-1], flaginfo)) + tRClass = self.target.FindFirstType("struct RClass") + + self._append_expression("*(struct RClass*)%0#x" % val.GetValueAsUnsigned()) + if not val.Cast(tRClass).GetChildMemberWithName("ptr").IsValid(): + self._append_expression( + "*(struct rb_classext_struct*)%0#x" % + (val.GetValueAsUnsigned() + tRClass.GetByteSize()) + ) + + elif rval.is_type("RUBY_T_STRING"): + self.result.write('T_STRING: %s' % flaginfo) + tRString = self.target.FindFirstType("struct RString").GetPointerType() + + chilled = self.ruby_globals["RUBY_FL_USER3"] + if (rval.flags & chilled) != 0: + self.result.write("[CHILLED] ") + + rb_enc_mask = self.ruby_globals["RUBY_ENCODING_MASK"] + rb_enc_shift = self.ruby_globals["RUBY_ENCODING_SHIFT"] + encidx = ((rval.flags & rb_enc_mask) >> rb_enc_shift) + encname = self.target.FindFirstType("enum ruby_preserved_encindex") \ + .GetEnumMembers().GetTypeEnumMemberAtIndex(encidx) \ + .GetName() + + if encname is not None: + self.result.write('[%s] ' % encname[14:]) + else: + self.result.write('[enc=%d] ' % encidx) + + coderange = rval.flags & self.ruby_globals["RUBY_ENC_CODERANGE_MASK"] + if coderange == self.ruby_globals["RUBY_ENC_CODERANGE_7BIT"]: + self.result.write('[7BIT] ') + elif coderange == self.ruby_globals["RUBY_ENC_CODERANGE_VALID"]: + self.result.write('[VALID] ') + elif coderange == self.ruby_globals["RUBY_ENC_CODERANGE_BROKEN"]: + self.result.write('[BROKEN] ') + else: + self.result.write('[UNKNOWN] ') + + ptr, len = self.string2cstr(val.Cast(tRString)) + if len == 0: + self.result.write("(empty)\n") + else: + self._append_expression("*(const char (*)[%d])%0#x" % (len, ptr)) + + elif rval.is_type("RUBY_T_SYMBOL"): + self.result.write('T_SYMBOL: %s' % flaginfo) + tRSymbol = self.target.FindFirstType("struct RSymbol").GetPointerType() + tRString = self.target.FindFirstType("struct RString").GetPointerType() + + val = val.Cast(tRSymbol) + self._append_expression('(ID)%0#x ' % val.GetValueForExpressionPath("->id").GetValueAsUnsigned()) + self.output_string(val.GetValueForExpressionPath("->fstr").Cast(tRString)) + + elif rval.is_type("RUBY_T_ARRAY"): + len = rval.ary_len() + ptr = rval.ary_ptr() + + self.result.write("T_ARRAY: %slen=%d" % (flaginfo, len)) + + if rval.flags & self.ruby_globals["RUBY_FL_USER1"]: + self.result.write(" (embed)") + elif rval.flags & self.ruby_globals["RUBY_FL_USER2"]: + shared = val.GetValueForExpressionPath("->as.heap.aux.shared").GetValueAsUnsigned() + self.result.write(" (shared) shared=%016x" % shared) + else: + capa = val.GetValueForExpressionPath("->as.heap.aux.capa").GetValueAsSigned() + self.result.write(" (ownership) capa=%d" % capa) + if len == 0: + self.result.write(" {(empty)}\n") + else: + self.result.write("\n") + if ptr.GetValueAsSigned() == 0: + self._append_expression("-fx -- ((struct RArray*)%0#x)->as.ary" % val.GetValueAsUnsigned()) + else: + self._append_expression("-Z %d -fx -- (const VALUE*)%0#x" % (len, ptr.GetValueAsUnsigned())) + + elif rval.is_type("RUBY_T_HASH"): + self.result.write("T_HASH: %s" % flaginfo) + ptr = val.GetValueAsUnsigned() + self._append_expression("*(struct RHash *) %0#x" % ptr) + if rval.flags & self.ruby_globals["RUBY_FL_USER3"]: + self._append_expression("*(struct st_table *) (%0#x + sizeof(struct RHash))" % ptr) + else: + self._append_expression("*(struct ar_table *) (%0#x + sizeof(struct RHash))" % ptr) + + elif rval.is_type("RUBY_T_BIGNUM"): + sign = '-' + if (rval.flags & self.ruby_globals["RUBY_FL_USER1"]) != 0: + sign = '+' + len = rval.bignum_len() + + if rval.flags & self.ruby_globals["RUBY_FL_USER2"]: + print("T_BIGNUM: sign=%s len=%d (embed)" % (sign, len), file=self.result) + self._append_expression("((struct RBignum *) %0#x)->as.ary" + % val.GetValueAsUnsigned()) + else: + print("T_BIGNUM: sign=%s len=%d" % (sign, len), file=self.result) + print(rval.as_type("bignum"), file=self.result) + self._append_expression("-Z %d -fx -- ((struct RBignum*)%d)->as.heap.digits" % + (len, val.GetValueAsUnsigned())) + + elif rval.is_type("RUBY_T_FLOAT"): + self._append_expression("((struct RFloat *)%d)->float_value" + % val.GetValueAsUnsigned()) + + elif rval.is_type("RUBY_T_RATIONAL"): + tRRational = self.target.FindFirstType("struct RRational").GetPointerType() + val = val.Cast(tRRational) + self.inspect(val.GetValueForExpressionPath("->num")) + output = self.result.GetOutput() + self.result.Clear() + self.result.write("(Rational) " + output.rstrip() + " / ") + self.inspect(val.GetValueForExpressionPath("->den")) + + elif rval.is_type("RUBY_T_COMPLEX"): + tRComplex = self.target.FindFirstType("struct RComplex").GetPointerType() + val = val.Cast(tRComplex) + self.inspect(val.GetValueForExpressionPath("->real")) + real = self.result.GetOutput().rstrip() + self.result.Clear() + self.inspect(val.GetValueForExpressionPath("->imag")) + imag = self.result.GetOutput().rstrip() + self.result.Clear() + if not imag.startswith("-"): + imag = "+" + imag + print("(Complex) " + real + imag + "i", file=self.result) + + elif rval.is_type("RUBY_T_REGEXP"): + tRRegex = self.target.FindFirstType("struct RRegexp").GetPointerType() + val = val.Cast(tRRegex) + print("(Regex) ->src {", file=self.result) + self.inspect(val.GetValueForExpressionPath("->src")) + print("}", file=self.result) + + elif rval.is_type("RUBY_T_DATA"): + tRTypedData = self.target.FindFirstType("struct RTypedData").GetPointerType() + val = val.Cast(tRTypedData) + is_typed_data = self.ruby_globals.get("RUBY_TYPED_FL_IS_TYPED_DATA", None) + if is_typed_data: + typed = rval.flags & is_typed_data + else: + typed = val.GetValueForExpressionPath("->typed_flag").GetValueAsUnsigned() == 1 + + if typed: + type = val.GetValueForExpressionPath("->type").GetValueAsUnsigned() + embed = (type & 1) + if embed: + flaginfo += "[EMBED] " + type = self.frame.EvaluateExpression("(rb_data_type_t *)%0#x" % (type & ~1)) + print("T_DATA: %s%s" % + (flaginfo, type.GetValueForExpressionPath("->wrap_struct_name")), + file=self.result) + print("%s", type.Dereference(), file=self.result) + ptr = val.GetValueForExpressionPath("->data") + if embed: + ptr = ptr.AddressOf() + self._append_expression("(void *)%0#x" % ptr.GetValueAsUnsigned()) + else: + print("T_DATA:", file=self.result) + self._append_expression("*(struct RData *) %0#x" % val.GetValueAsUnsigned()) + + elif rval.is_type("RUBY_T_IMEMO"): + imemo_type = ((rval.flags >> self.ruby_globals["RUBY_FL_USHIFT"]) + & IMEMO_MASK) + print("T_IMEMO: ", file=self.result) + + self._append_expression("(enum imemo_type) %d" % imemo_type) + self._append_expression("*(struct MEMO *) %0#x" % val.GetValueAsUnsigned()) + + elif rval.is_type("RUBY_T_FILE"): + self.generic_inspect(val, "RFile") + + elif rval.is_type("RUBY_T_MOVED"): + self.generic_inspect(val, "RMoved") + + elif rval.is_type("RUBY_T_MATCH"): + self.generic_inspect(val, "RMatch") + + elif rval.is_type("RUBY_T_STRUCT"): + self.generic_inspect(val, "RStruct") + + elif rval.is_type("RUBY_T_ZOMBIE"): + self.generic_inspect(val, "RZombie") + + else: + print("Not-handled type %0#x" % rval.type, file=self.result) + print(val, file=self.result) + + def inspect_node(self, val): + tRNode = self.target.FindFirstType("struct RNode").GetPointerType() + + # if val.GetType() != tRNode: does not work for unknown reason + + if val.GetType().GetPointeeType().name != "NODE": + return False + + rbNodeTypeMask = self.ruby_globals["RUBY_NODE_TYPEMASK"] + rbNodeTypeShift = self.ruby_globals["RUBY_NODE_TYPESHIFT"] + flags = val.Cast(tRNode).GetChildMemberWithName("flags").GetValueAsUnsigned() + nd_type = (flags & rbNodeTypeMask) >> rbNodeTypeShift + + self._append_expression("(node_type) %d" % nd_type) + + if nd_type == self.ruby_globals["NODE_SCOPE"]: + self._append_expression("*(rb_node_scope_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_BLOCK"]: + self._append_expression("*(rb_node_block_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_IF"]: + self._append_expression("*(rb_node_if_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_UNLESS"]: + self._append_expression("*(rb_node_unless_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CASE"]: + self._append_expression("*(rb_node_case_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CASE2"]: + self._append_expression("*(rb_node_case2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CASE3"]: + self._append_expression("*(rb_node_case3_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_WHEN"]: + self._append_expression("*(rb_node_when_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_IN"]: + self._append_expression("*(rb_node_in_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_WHILE"]: + self._append_expression("*(rb_node_while_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_UNTIL"]: + self._append_expression("*(rb_node_until_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ITER"]: + self._append_expression("*(rb_node_iter_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FOR"]: + self._append_expression("*(rb_node_for_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FOR_MASGN"]: + self._append_expression("*(rb_node_for_masgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_BREAK"]: + self._append_expression("*(rb_node_break_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_NEXT"]: + self._append_expression("*(rb_node_next_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_REDO"]: + self._append_expression("*(rb_node_redo_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_RETRY"]: + self._append_expression("*(rb_node_retry_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_BEGIN"]: + self._append_expression("*(rb_node_begin_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_RESCUE"]: + self._append_expression("*(rb_node_rescue_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_RESBODY"]: + self._append_expression("*(rb_node_resbody_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ENSURE"]: + self._append_expression("*(rb_node_ensure_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_AND"]: + self._append_expression("*(rb_node_and_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OR"]: + self._append_expression("*(rb_node_or_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_MASGN"]: + self._append_expression("*(rb_node_masgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_LASGN"]: + self._append_expression("*(rb_node_lasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DASGN"]: + self._append_expression("*(rb_node_dasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_GASGN"]: + self._append_expression("*(rb_node_gasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_IASGN"]: + self._append_expression("*(rb_node_iasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CDECL"]: + self._append_expression("*(rb_node_cdecl_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CVASGN"]: + self._append_expression("*(rb_node_cvasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OP_ASGN1"]: + self._append_expression("*(rb_node_op_asgn1_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OP_ASGN2"]: + self._append_expression("*(rb_node_op_asgn2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OP_ASGN_AND"]: + self._append_expression("*(rb_node_op_asgn_and_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OP_ASGN_OR"]: + self._append_expression("*(rb_node_op_asgn_or_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OP_CDECL"]: + self._append_expression("*(rb_node_op_cdecl_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CALL"]: + self._append_expression("*(rb_node_call_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OPCALL"]: + self._append_expression("*(rb_node_opcall_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FCALL"]: + self._append_expression("*(rb_node_fcall_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_VCALL"]: + self._append_expression("*(rb_node_vcall_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_QCALL"]: + self._append_expression("*(rb_node_qcall_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_SUPER"]: + self._append_expression("*(rb_node_super_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ZSUPER"]: + self._append_expression("*(rb_node_zsuper_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_LIST"]: + self._append_expression("*(rb_node_list_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ZLIST"]: + self._append_expression("*(rb_node_zlist_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_HASH"]: + self._append_expression("*(rb_node_hash_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_RETURN"]: + self._append_expression("*(rb_node_return_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_YIELD"]: + self._append_expression("*(rb_node_yield_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_LVAR"]: + self._append_expression("*(rb_node_lvar_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DVAR"]: + self._append_expression("*(rb_node_dvar_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_GVAR"]: + self._append_expression("*(rb_node_gvar_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CONST"]: + self._append_expression("*(rb_node_const_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CVAR"]: + self._append_expression("*(rb_node_cvar_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_NTH_REF"]: + self._append_expression("*(rb_node_nth_ref_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_BACK_REF"]: + self._append_expression("*(rb_node_back_ref_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_MATCH"]: + self._append_expression("*(rb_node_match_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_MATCH2"]: + self._append_expression("*(rb_node_match2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_MATCH3"]: + self._append_expression("*(rb_node_match3_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_STR"]: + self._append_expression("*(rb_node_str_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DSTR"]: + self._append_expression("*(rb_node_dstr_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_XSTR"]: + self._append_expression("*(rb_node_xstr_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DXSTR"]: + self._append_expression("*(rb_node_dxstr_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_EVSTR"]: + self._append_expression("*(rb_node_evstr_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_REGX"]: + self._append_expression("*(rb_node_regx_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DREGX"]: + self._append_expression("*(rb_node_dregx_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ONCE"]: + self._append_expression("*(rb_node_once_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ARGS"]: + self._append_expression("*(rb_node_args_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ARGS_AUX"]: + self._append_expression("*(rb_node_args_aux_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_OPT_ARG"]: + self._append_expression("*(rb_node_opt_arg_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_KW_ARG"]: + self._append_expression("*(rb_node_kw_arg_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_POSTARG"]: + self._append_expression("*(rb_node_postarg_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ARGSCAT"]: + self._append_expression("*(rb_node_argscat_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ARGSPUSH"]: + self._append_expression("*(rb_node_argspush_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_SPLAT"]: + self._append_expression("*(rb_node_splat_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DEFN"]: + self._append_expression("*(rb_node_defn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DEFS"]: + self._append_expression("*(rb_node_defs_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ALIAS"]: + self._append_expression("*(rb_node_alias_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_VALIAS"]: + self._append_expression("*(rb_node_valias_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_UNDEF"]: + self._append_expression("*(rb_node_undef_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_CLASS"]: + self._append_expression("*(rb_node_class_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_MODULE"]: + self._append_expression("*(rb_node_module_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_SCLASS"]: + self._append_expression("*(rb_node_sclass_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_COLON2"]: + self._append_expression("*(rb_node_colon2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_COLON3"]: + self._append_expression("*(rb_node_colon3_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DOT2"]: + self._append_expression("*(rb_node_dot2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DOT3"]: + self._append_expression("*(rb_node_dot3_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FLIP2"]: + self._append_expression("*(rb_node_flip2_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FLIP3"]: + self._append_expression("*(rb_node_flip3_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_SELF"]: + self._append_expression("*(rb_node_self_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_NIL"]: + self._append_expression("*(rb_node_nil_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_TRUE"]: + self._append_expression("*(rb_node_true_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FALSE"]: + self._append_expression("*(rb_node_false_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ERRINFO"]: + self._append_expression("*(rb_node_errinfo_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DEFINED"]: + self._append_expression("*(rb_node_defined_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_POSTEXE"]: + self._append_expression("*(rb_node_postexe_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_DSYM"]: + self._append_expression("*(rb_node_dsym_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ATTRASGN"]: + self._append_expression("*(rb_node_attrasgn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_LAMBDA"]: + self._append_expression("*(rb_node_lambda_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ARYPTN"]: + self._append_expression("*(rb_node_aryptn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_HSHPTN"]: + self._append_expression("*(rb_node_hshptn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FNDPTN"]: + self._append_expression("*(rb_node_fndptn_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_ERROR"]: + self._append_expression("*(rb_node_error_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_LINE"]: + self._append_expression("*(rb_node_line_t *) %0#x" % val.GetValueAsUnsigned()) + elif nd_type == self.ruby_globals["NODE_FILE"]: + self._append_expression("*(rb_node_file_t *) %0#x" % val.GetValueAsUnsigned()) + else: + self._append_expression("*(NODE *) %0#x" % val.GetValueAsUnsigned()) + return True diff --git a/misc/rb_optparse.bash b/misc/rb_optparse.bash index 8a59ec2dda..f77d937c87 100644 --- a/misc/rb_optparse.bash +++ b/misc/rb_optparse.bash @@ -1,4 +1,5 @@ -#! /bin/bash +# -*- bash -*- +# # Completion for bash: # # (1) install this file, @@ -16,5 +17,5 @@ _rb_optparse() { } rb_optparse () { - [ $# = 0 ] || complete -o default -F _rb_optparse "$@" + [ $# = 0 ] || complete -o default -F _rb_optparse "$@" } diff --git a/misc/rb_optparse.zsh b/misc/rb_optparse.zsh index d53170c5f7..258d4f856c 100755..100644 --- a/misc/rb_optparse.zsh +++ b/misc/rb_optparse.zsh @@ -1,4 +1,5 @@ -#!/bin/zsh +# -*- zsh -*- +# # Completion for zsh: # (based on <http://d.hatena.ne.jp/rubikitch/20071002/zshcomplete>) # @@ -7,13 +8,13 @@ # cp rb_optparse.zsh ~/.zsh.d/rb_optparse.zsh # # (2) load the script, and add a directory to fpath before compinit. -# echo '. ~/.zsh.d/rb_optparse.zsh' >> ~/.zshrc -# echo 'fpath=(~/.zsh.d/Completion $fpath)' >> ~/.zshrc -# echo 'autoload -U compinit; compinit' >> ~/.zshrc +# echo '. ~/.zsh.d/rb_optparse.zsh' >> "${ZDOTDIR:-~}/.zshrc" +# echo 'fpath=(~/.zsh.d/Completion $fpath)' >> "${ZDOTDIR:-~}/.zshrc" +# echo 'autoload -U compinit; compinit' >> "${ZDOTDIR:-~}/.zshrc" # # (3) restart zsh. # -# (4) geneate completion files once. +# (4) generate completion files once. # generate-complete-function/ruby/optparse COMMAND1 # generate-complete-function/ruby/optparse COMMAND2 # @@ -24,8 +25,8 @@ generate-complete-function/ruby/optparse () mkdir -p "${ZSH_COMPLETION_DIR-$HOME/.zsh.d/Completion}" $1 "--*-completion-zsh=${1:t}" >! "${ZSH_COMPLETION_DIR-$HOME/.zsh.d/Completion}/$cmpl" if [[ $(type -w "$cmpl") == "${cmpl}: function" ]]; then - unfunction "$cmpl" - autoload -U "$cmpl" + unfunction "$cmpl" + autoload -U "$cmpl" else compinit "$cmpl" fi diff --git a/misc/rdoc-mode.el b/misc/rdoc-mode.el deleted file mode 100644 index ec715798ae..0000000000 --- a/misc/rdoc-mode.el +++ /dev/null @@ -1,130 +0,0 @@ -;; -;; rdoc-mode.el -;; Major mode for RDoc editing -;; - -;; Created: Fri Sep 18 09:04:49 JST 2009 - -;; License: Ruby's - -(require 'derived) -(define-derived-mode rdoc-mode text-mode "RDoc" - "Major mode for RD editing. -\\{rdoc-mode-map}" - (make-local-variable 'paragraph-separate) - (setq paragraph-separate "^\\(=+\\|\\*+\\)[ \t\v\f]*\\|^\\s *$") - (make-local-variable 'paragraph-start) - (setq paragraph-start paragraph-separate) - (make-local-variable 'require-final-newline) - (setq require-final-newline t) - (make-local-variable 'font-lock-defaults) - (setq font-lock-defaults '((rdoc-font-lock-keywords) t nil)) - (make-local-variable 'font-lock-keywords) - (setq font-lock-keywords rdoc-font-lock-keywords) - (make-local-variable 'outline-regexp) - (setq outline-regexp "^\\(=+\\)[ \t\v\f]*") - (outline-minor-mode t) - (setq show-trailing-whitespace t) - (rdoc-setup-keys) - (setq indent-tabs-mode nil) - (run-hooks 'rdoc-mode-hook) - ) - -(defun rdoc-fill-paragraph (&rest args) - "Fills paragraph, except for cited region" - (interactive (progn - (barf-if-buffer-read-only) - (list (if current-prefix-arg 'full)))) - (save-excursion - (beginning-of-line) - (unless (looking-at "^ +") - (apply 'fill-paragraph args)))) - -(defun rdoc-setup-keys () - (interactive) - (define-key rdoc-mode-map "\M-q" 'rdoc-fill-paragraph) - ) - -(defvar rdoc-heading1-face 'font-lock-keywordoc-face) -(defvar rdoc-heading2-face 'font-lock-type-face) -(defvar rdoc-heading3-face 'font-lock-variable-name-face) -(defvar rdoc-heading4-face 'font-lock-comment-face) -(defvar rdoc-bold-face 'font-lock-function-name-face) -(defvar rdoc-emphasis-face 'font-lock-function-name-face) -(defvar rdoc-code-face 'font-lock-keyword-face) -(defvar rdoc-description-face 'font-lock-constant-face) - -(defvar rdoc-font-lock-keywords - (list - (list "^=([^=\r\n].*)?$" - 0 rdoc-heading1-face) - (list "^==([^=\r\n].*)?$" - 0 rdoc-heading2-face) - (list "^===([^=\r\n].*)?$" - 0 rdoc-heading3-face) - (list "^====+.*$" - 0 rdoc-heading4-face) - (list "\\(^\\|[ \t\v\f]\\)\\(\\*\\(\\sw\\|[-_:]\\)+\\*\\)\\($\\|[ \t\v\f]\\)" - 2 rdoc-bold-face) ; *bold* - (list "\\(^\\|[ \t\v\f]\\)\\(_\\(\\sw\\|[-_:]\\)+_\\)\\($\\|[ \t\v\f]\\)" - 2 rdoc-emphasis-face) ; _emphasis_ - (list "\\(^\\|[ \t\v\f]\\)\\(\\+\\(\\sw\\|[-_:]\\)+\\+\\)\\($\\|[ \t\v\f]\\)" - 2 rdoc-code-face) ; +code+ - (list "<em>[^<>]*</em>" 0 rdoc-emphasis-face) - (list "<i>[^<>]*</i>" 0 rdoc-emphasis-face) - (list "<b>[^<>]*</b>" 0 rdoc-bold-face) - (list "<tt>[^<>]*</tt>" 0 rdoc-code-face) - (list "<code>[^<>]*</code>" 0 rdoc-code-face) - (list "^\\([-*]\\|[0-9]+\\.\\|[A-Za-z]\\.\\)\\s " - 1 rdoc-description-face) ; bullet | numbered | alphabetically numbered - (list "^\\[[^\]]*\\]\\|\\S .*::\\)\\([ \t\v\f]\\|$\\)" - 1 rdoc-description-face) ; labeled | node - ;(list "^[ \t\v\f]+\\(.*\\)" 1 rdoc-verbatim-face) - )) - -(defun rdoc-imenu-create-index () - (let ((root '(nil . nil)) - cur-alist - (cur-level 0) - (pattern (concat outline-regexp "\\(.*?\\)[ \t\v\f]*$")) - (empty-heading "-") - (self-heading ".") - pos level heading alist) - (save-excursion - (goto-char (point-min)) - (while (re-search-forward pattern (point-max) t) - (setq heading (match-string-no-properties 2) - level (min 6 (length (match-string-no-properties 1))) - pos (match-beginning 1)) - (if (= (length heading) 0) - (setq heading empty-heading)) - (setq alist (list (cons heading pos))) - (cond - ((= cur-level level) ; new sibling - (setcdr cur-alist alist) - (setq cur-alist alist)) - ((< cur-level level) ; first child - (dotimes (i (- level cur-level 1)) - (setq alist (list (cons empty-heading alist)))) - (if cur-alist - (let* ((parent (car cur-alist)) - (self-pos (cdr parent))) - (setcdr parent (cons (cons self-heading self-pos) alist))) - (setcdr root alist)) ; primogenitor - (setq cur-alist alist - cur-level level)) - (t ; new sibling of an ancestor - (let ((sibling-alist (last (cdr root)))) - (dotimes (i (1- level)) - (setq sibling-alist (last (cdar sibling-alist)))) - (setcdr sibling-alist alist) - (setq cur-alist alist - cur-level level)))))) - (cdr root))) - -(defun rdoc-set-imenu-create-index-function () - (setq imenu-create-index-function 'rdoc-imenu-create-index)) - -(add-hook 'rdoc-mode-hook 'rdoc-set-imenu-create-index-function) - -(provide 'rdoc-mode) diff --git a/misc/ruby-additional.el b/misc/ruby-additional.el deleted file mode 100644 index 152067e48e..0000000000 --- a/misc/ruby-additional.el +++ /dev/null @@ -1,100 +0,0 @@ -;; missing functions in Emacs 24. - -(eval-after-load "\\(\\`\\|/\\)ruby-mode\\.elc?\\(\\.gz\\)?\\'" - (progn - (define-key ruby-mode-map "\C-c\C-e" 'ruby-insert-end) - (define-key ruby-mode-map "\C-c{" 'ruby-toggle-block) - - (defun ruby-insert-end () - (interactive) - (if (eq (char-syntax (char-before)) ?w) - (insert " ")) - (insert "end") - (save-excursion - (if (eq (char-syntax (char-after)) ?w) - (insert " ")) - (ruby-indent-line t) - (end-of-line))) - - (defun ruby-brace-to-do-end () - (when (looking-at "{") - (let ((orig (point)) (end (progn (ruby-forward-sexp) (point)))) - (when (eq (char-before) ?\}) - (delete-char -1) - (if (eq (char-syntax (char-before)) ?w) - (insert " ")) - (insert "end") - (if (eq (char-syntax (char-after)) ?w) - (insert " ")) - (goto-char orig) - (delete-char 1) - (if (eq (char-syntax (char-before)) ?w) - (insert " ")) - (insert "do") - (when (looking-at "\\sw\\||") - (insert " ") - (backward-char)) - t)))) - - (defun ruby-do-end-to-brace () - (when (and (or (bolp) - (not (memq (char-syntax (char-before)) '(?w ?_)))) - (looking-at "\\<do\\(\\s \\|$\\)")) - (let ((orig (point)) (end (progn (ruby-forward-sexp) (point)))) - (backward-char 3) - (when (looking-at ruby-block-end-re) - (delete-char 3) - (insert "}") - (goto-char orig) - (delete-char 2) - (insert "{") - (if (looking-at "\\s +|") - (delete-char (- (match-end 0) (match-beginning 0) 1))) - t)))) - - (defun ruby-toggle-block () - (interactive) - (or (ruby-brace-to-do-end) - (ruby-do-end-to-brace))) - - (defun ruby-mode-set-encoding () - "Insert a magic comment header with the proper encoding always. -Now encoding needs to be set always explicitly actually." - (save-excursion - (let ((coding-system)) - (widen) - (goto-char (point-min)) - (if (re-search-forward "[^\0-\177]" nil t) - (progn - (goto-char (point-min)) - (setq coding-system - (or coding-system-for-write - buffer-file-coding-system)) - (if coding-system - (setq coding-system - (or (coding-system-get coding-system 'mime-charset) - (coding-system-change-eol-conversion coding-system nil)))) - (setq coding-system - (if coding-system - (symbol-name - (or (and ruby-use-encoding-map - (cdr (assq coding-system ruby-encoding-map))) - coding-system)) - "ascii-8bit"))) - (setq coding-system "us-ascii")) - (if (looking-at "^#!") (beginning-of-line 2)) - (cond ((looking-at "\\s *#.*-\*-\\s *\\(en\\)?coding\\s *:\\s *\\([-a-z0-9_]*\\)\\s *\\(;\\|-\*-\\)") - (unless (string= (match-string 2) coding-system) - (goto-char (match-beginning 2)) - (delete-region (point) (match-end 2)) - (and (looking-at "-\*-") - (let ((n (skip-chars-backward " "))) - (cond ((= n 0) (insert " ") (backward-char)) - ((= n -1) (insert " ")) - ((forward-char))))) - (insert coding-system))) - ((looking-at "\\s *#.*coding\\s *[:=]")) - (t (when ruby-insert-encoding-magic-comment - (insert "# -*- coding: " coding-system " -*-\n"))))))) - - )) diff --git a/misc/ruby-electric.el b/misc/ruby-electric.el deleted file mode 100644 index 95644e24cd..0000000000 --- a/misc/ruby-electric.el +++ /dev/null @@ -1,205 +0,0 @@ -;; -*-Emacs-Lisp-*- -;; -;; ruby-electric.el --- electric editing commands for ruby files -;; -;; Copyright (C) 2005 by Dee Zsombor <dee dot zsombor at gmail dot com>. -;; Released under same license terms as Ruby. -;; -;; Due credit: this work was inspired by a code snippet posted by -;; Frederick Ros at http://rubygarden.org/ruby?EmacsExtensions. -;; -;; Following improvements where added: -;; -;; - handling of strings of type 'here document' -;; - more keywords, with special handling for 'do' -;; - packaged into a minor mode -;; -;; Usage: -;; -;; 0) copy ruby-electric.el into directory where emacs can find it. -;; -;; 1) modify your startup file (.emacs or whatever) by adding -;; following line: -;; -;; (require 'ruby-electric) -;; -;; note that you need to have font lock enabled beforehand. -;; -;; 2) toggle Ruby Electric Mode on/off with ruby-electric-mode. -;; -;; Changelog: -;; -;; 2005/Jan/14: inserts matching pair delimiters like {, [, (, ', ", -;; ' and | . -;; -;; 2005/Jan/14: added basic Custom support for configuring keywords -;; with electric closing. -;; -;; 2005/Jan/18: more Custom support for configuring characters for -;; which matching expansion should occur. -;; -;; 2005/Jan/18: no longer uses 'looking-back' or regexp character -;; classes like [:space:] since they are not implemented on XEmacs. -;; -;; 2005/Feb/01: explicitly provide default argument of 1 to -;; 'backward-word' as it requires it on Emacs 21.3 -;; -;; 2005/Mar/06: now stored inside ruby CVS; customize pages now have -;; ruby as parent; cosmetic fixes. - - -(require 'ruby-mode) - -(defgroup ruby-electric nil - "Minor mode providing electric editing commands for ruby files" - :group 'ruby) - -(defconst ruby-electric-expandable-do-re - "do\\s-$") - -(defconst ruby-electric-expandable-bar - "\\s-\\(do\\|{\\)\\s-+|") - -(defvar ruby-electric-matching-delimeter-alist - '((?\[ . ?\]) - (?\( . ?\)) - (?\' . ?\') - (?\` . ?\`) - (?\" . ?\"))) - -(defcustom ruby-electric-simple-keywords-re - (regexp-opt '("def" "if" "class" "module" "unless" "case" "while" "do" "until" "for" "begin") t) - "*Regular expresion matching keywords for which closing 'end' -is to be inserted." - :type 'regexp :group 'ruby-electric) - -(defcustom ruby-electric-expand-delimiters-list '(all) - "*List of contexts where matching delimiter should be -inserted. The word 'all' will do all insertions." - :type '(set :extra-offset 8 - (const :tag "Everything" all ) - (const :tag "Curly brace" ?\{ ) - (const :tag "Square brace" ?\[ ) - (const :tag "Round brace" ?\( ) - (const :tag "Quote" ?\' ) - (const :tag "Double quote" ?\" ) - (const :tag "Back quote" ?\` ) - (const :tag "Vertical bar" ?\| )) - :group 'ruby-electric) - -(defcustom ruby-electric-newline-before-closing-bracket nil - "*Controls whether a newline should be inserted before the -closing bracket or not." - :type 'boolean :group 'ruby-electric) - -(define-minor-mode ruby-electric-mode - "Toggle Ruby Electric minor mode. -With no argument, this command toggles the mode. Non-null prefix -argument turns on the mode. Null prefix argument turns off the -mode. - -When Ruby Electric mode is enabled, an indented 'end' is -heuristicaly inserted whenever typing a word like 'module', -'class', 'def', 'if', 'unless', 'case', 'until', 'for', 'begin', -'do'. Simple, double and back quotes as well as braces are paired -auto-magically. Expansion does not occur inside comments and -strings. Note that you must have Font Lock enabled." - ;; initial value. - nil - ;;indicator for the mode line. - " REl" - ;;keymap - ruby-mode-map - (ruby-electric-setup-keymap)) - -(defun ruby-electric-setup-keymap() - (define-key ruby-mode-map " " 'ruby-electric-space) - (define-key ruby-mode-map "{" 'ruby-electric-curlies) - (define-key ruby-mode-map "(" 'ruby-electric-matching-char) - (define-key ruby-mode-map "[" 'ruby-electric-matching-char) - (define-key ruby-mode-map "\"" 'ruby-electric-matching-char) - (define-key ruby-mode-map "\'" 'ruby-electric-matching-char) - (define-key ruby-mode-map "|" 'ruby-electric-bar)) - -(defun ruby-electric-space (arg) - (interactive "P") - (self-insert-command (prefix-numeric-value arg)) - (if (ruby-electric-space-can-be-expanded-p) - (save-excursion - (ruby-indent-line t) - (newline) - (ruby-insert-end)))) - -(defun ruby-electric-code-at-point-p() - (and ruby-electric-mode - (let* ((properties (text-properties-at (point)))) - (and (null (memq 'font-lock-string-face properties)) - (null (memq 'font-lock-comment-face properties)))))) - -(defun ruby-electric-string-at-point-p() - (and ruby-electric-mode - (consp (memq 'font-lock-string-face (text-properties-at (point)))))) - -(defun ruby-electric-is-last-command-char-expandable-punct-p() - (or (memq 'all ruby-electric-expand-delimiters-list) - (memq last-command-event ruby-electric-expand-delimiters-list))) - -(defun ruby-electric-space-can-be-expanded-p() - (if (ruby-electric-code-at-point-p) - (let* ((ruby-electric-keywords-re - (concat ruby-electric-simple-keywords-re "\\s-$")) - (ruby-electric-single-keyword-in-line-re - (concat "\\s-*" ruby-electric-keywords-re))) - (save-excursion - (backward-word 1) - (or (looking-at ruby-electric-expandable-do-re) - (and (looking-at ruby-electric-keywords-re) - (not (string= "do" (match-string 1))) - (progn - (beginning-of-line) - (looking-at ruby-electric-single-keyword-in-line-re)))))))) - - -(defun ruby-electric-curlies(arg) - (interactive "P") - (self-insert-command (prefix-numeric-value arg)) - (if (ruby-electric-is-last-command-char-expandable-punct-p) - (cond ((ruby-electric-code-at-point-p) - (insert " ") - (save-excursion - (if ruby-electric-newline-before-closing-bracket - (progn - (newline) - (insert "}") - (ruby-indent-line t)) - (insert "}")))) - ((ruby-electric-string-at-point-p) - (if (eq last-command-event ?{) - (save-excursion - (backward-char 1) - (or (char-equal ?\# (preceding-char)) - (insert "#")) - (forward-char 1) - (insert "}"))))))) - -(defun ruby-electric-matching-char(arg) - (interactive "P") - (self-insert-command (prefix-numeric-value arg)) - (and (ruby-electric-is-last-command-char-expandable-punct-p) - (ruby-electric-code-at-point-p) - (save-excursion - (insert (cdr (assoc last-command-event - ruby-electric-matching-delimeter-alist)))))) - -(defun ruby-electric-bar(arg) - (interactive "P") - (self-insert-command (prefix-numeric-value arg)) - (and (ruby-electric-is-last-command-char-expandable-punct-p) - (ruby-electric-code-at-point-p) - (and (save-excursion (re-search-backward ruby-electric-expandable-bar nil t)) - (= (point) (match-end 0))) ;looking-back is missing on XEmacs - (save-excursion - (insert "|")))) - - -(provide 'ruby-electric) diff --git a/misc/ruby-mode.el b/misc/ruby-mode.el deleted file mode 100644 index dcaa396a2e..0000000000 --- a/misc/ruby-mode.el +++ /dev/null @@ -1,1514 +0,0 @@ -;;; ruby-mode.el --- Major mode for editing Ruby files - -;; Copyright (C) 1994, 1995, 1996 1997, 1998, 1999, 2000, 2001, -;; 2002,2003, 2004, 2005, 2006, 2007, 2008 -;; Free Software Foundation, Inc. - -;; Authors: Yukihiro Matsumoto, Nobuyoshi Nakada -;; URL: http://www.emacswiki.org/cgi-bin/wiki/RubyMode -;; Created: Fri Feb 4 14:49:13 JST 1994 -;; Keywords: languages ruby -;; Version: 0.9 - -;; This file is not part of GNU Emacs. However, a newer version of -;; ruby-mode is included in recent releases of GNU Emacs (version 23 -;; and up), but the new version is not guaranteed to be compatible -;; with older versions of Emacs or XEmacs. This file is the last -;; version that aims to keep this compatibility. - -;; You can also get the latest version from the Emacs Lisp Package -;; Archive: http://tromey.com/elpa - -;; This file is free software: you can redistribute it and/or modify -;; it under the terms of the GNU General Public License as published by -;; the Free Software Foundation, either version 3 of the License, or -;; (at your option) any later version. - -;; It is distributed in the hope that it will be useful, but WITHOUT -;; ANY WARRANTY; without even the implied warranty of MERCHANTABILITY -;; or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public -;; License for more details. - -;; You should have received a copy of the GNU General Public License -;; along with it. If not, see <http://www.gnu.org/licenses/>. - -;;; Commentary: - -;; Provides font-locking, indentation support, and navigation for Ruby code. -;; -;; If you're installing manually, you should add this to your .emacs -;; file after putting it on your load path: -;; -;; (autoload 'ruby-mode "ruby-mode" "Major mode for ruby files" t) -;; (add-to-list 'auto-mode-alist '("\\.rb$" . ruby-mode)) -;; (add-to-list 'interpreter-mode-alist '("ruby" . ruby-mode)) -;; - -;;; Code: - -(defconst ruby-mode-revision "$Revision$" - "Ruby mode revision string.") - -(defconst ruby-mode-version - (and (string-match "[0-9.]+" ruby-mode-revision) - (substring ruby-mode-revision (match-beginning 0) (match-end 0))) - "Ruby mode version number.") - -(defconst ruby-keyword-end-re - (if (string-match "\\_>" "ruby") - "\\_>" - "\\>")) - -(defconst ruby-block-beg-keywords - '("class" "module" "def" "if" "unless" "case" "while" "until" "for" "begin" "do") - "Keywords at the beginning of blocks.") - -(defconst ruby-block-beg-re - (regexp-opt ruby-block-beg-keywords) - "Regexp to match the beginning of blocks.") - -(defconst ruby-non-block-do-re - (concat (regexp-opt '("while" "until" "for" "rescue") t) ruby-keyword-end-re) - "Regexp to match") - -(defconst ruby-indent-beg-re - (concat "\\(\\s *" (regexp-opt '("class" "module" "def") t) "\\)\\|" - (regexp-opt '("if" "unless" "case" "while" "until" "for" "begin"))) - "Regexp to match where the indentation gets deeper.") - -(defconst ruby-modifier-beg-keywords - '("if" "unless" "while" "until") - "Modifiers that are the same as the beginning of blocks.") - -(defconst ruby-modifier-beg-re - (regexp-opt ruby-modifier-beg-keywords) - "Regexp to match modifiers same as the beginning of blocks.") - -(defconst ruby-modifier-re - (regexp-opt (cons "rescue" ruby-modifier-beg-keywords)) - "Regexp to match modifiers.") - -(defconst ruby-block-mid-keywords - '("then" "else" "elsif" "when" "rescue" "ensure") - "Keywords where the indentation gets shallower in middle of block statements.") - -(defconst ruby-block-mid-re - (regexp-opt ruby-block-mid-keywords) - "Regexp to match where the indentation gets shallower in middle of block statements.") - -(defconst ruby-block-op-keywords - '("and" "or" "not") - "Block operators.") - -(defconst ruby-block-hanging-re - (regexp-opt (append ruby-modifier-beg-keywords ruby-block-op-keywords)) - "Regexp to match hanging block modifiers.") - -(defconst ruby-block-end-re "\\_<end\\_>") - -(defconst ruby-here-doc-beg-re - "\\(<\\)<\\(-\\)?\\(\\([a-zA-Z0-9_]+\\)\\|[\"]\\([^\"]+\\)[\"]\\|[']\\([^']+\\)[']\\)") - -(defconst ruby-here-doc-end-re - "^\\([ \t]+\\)?\\(.*\\)\\(.\\)$") - -(defun ruby-here-doc-end-match () - (concat "^" - (if (match-string 2) "[ \t]*" nil) - (regexp-quote - (or (match-string 4) - (match-string 5) - (match-string 6))))) - -(defun ruby-here-doc-beg-match () - (let ((contents (concat - (regexp-quote (concat (match-string 2) (match-string 3))) - (if (string= (match-string 3) "_") "\\B" "\\b")))) - (concat "<<" - (let ((match (match-string 1))) - (if (and match (> (length match) 0)) - (concat "\\(?:-\\([\"']?\\)\\|\\([\"']\\)" (match-string 1) "\\)" - contents "\\(\\1\\|\\2\\)") - (concat "-?\\([\"']\\|\\)" contents "\\1")))))) - -(defconst ruby-delimiter - (concat "[?$/%(){}#\"'`.:]\\|<<\\|\\[\\|\\]\\|\\_<\\(" - ruby-block-beg-re - "\\)\\_>\\|" ruby-block-end-re - "\\|^=begin\\|" ruby-here-doc-beg-re) - ) - -(defconst ruby-negative - (concat "^[ \t]*\\(\\(" ruby-block-mid-re "\\)\\>\\|" - ruby-block-end-re "\\|}\\|\\]\\)") - "Regexp to match where the indentation gets shallower.") - -(defconst ruby-operator-chars "-,.+*/%&|^~=<>:") -(defconst ruby-operator-re (concat "[" ruby-operator-chars "]")) - -(defconst ruby-symbol-chars "a-zA-Z0-9_") -(defconst ruby-symbol-re (concat "[" ruby-symbol-chars "]")) - -(defvar ruby-mode-abbrev-table nil - "Abbrev table in use in ruby-mode buffers.") - -(define-abbrev-table 'ruby-mode-abbrev-table ()) - -(defvar ruby-mode-map nil "Keymap used in ruby mode.") - -(if ruby-mode-map - nil - (setq ruby-mode-map (make-sparse-keymap)) - (define-key ruby-mode-map "{" 'ruby-electric-brace) - (define-key ruby-mode-map "}" 'ruby-electric-brace) - (define-key ruby-mode-map "\e\C-a" 'ruby-beginning-of-defun) - (define-key ruby-mode-map "\e\C-e" 'ruby-end-of-defun) - (define-key ruby-mode-map "\e\C-b" 'ruby-backward-sexp) - (define-key ruby-mode-map "\e\C-f" 'ruby-forward-sexp) - (define-key ruby-mode-map "\e\C-p" 'ruby-beginning-of-block) - (define-key ruby-mode-map "\e\C-n" 'ruby-end-of-block) - (define-key ruby-mode-map "\e\C-h" 'ruby-mark-defun) - (define-key ruby-mode-map "\e\C-q" 'ruby-indent-exp) - (define-key ruby-mode-map "\t" 'ruby-indent-command) - (define-key ruby-mode-map "\C-c\C-e" 'ruby-insert-end) - (define-key ruby-mode-map "\C-j" 'ruby-reindent-then-newline-and-indent) - (define-key ruby-mode-map "\C-c{" 'ruby-toggle-block) - (define-key ruby-mode-map "\C-c\C-u" 'uncomment-region)) - -(defvar ruby-mode-syntax-table nil - "Syntax table in use in ruby-mode buffers.") - -(if ruby-mode-syntax-table - () - (setq ruby-mode-syntax-table (make-syntax-table)) - (modify-syntax-entry ?\' "\"" ruby-mode-syntax-table) - (modify-syntax-entry ?\" "\"" ruby-mode-syntax-table) - (modify-syntax-entry ?\` "\"" ruby-mode-syntax-table) - (modify-syntax-entry ?# "<" ruby-mode-syntax-table) - (modify-syntax-entry ?\n ">" ruby-mode-syntax-table) - (modify-syntax-entry ?\\ "\\" ruby-mode-syntax-table) - (modify-syntax-entry ?$ "." ruby-mode-syntax-table) - (modify-syntax-entry ?? "_" ruby-mode-syntax-table) - (modify-syntax-entry ?_ "_" ruby-mode-syntax-table) - (modify-syntax-entry ?: "_" ruby-mode-syntax-table) - (modify-syntax-entry ?< "." ruby-mode-syntax-table) - (modify-syntax-entry ?> "." ruby-mode-syntax-table) - (modify-syntax-entry ?& "." ruby-mode-syntax-table) - (modify-syntax-entry ?| "." ruby-mode-syntax-table) - (modify-syntax-entry ?% "." ruby-mode-syntax-table) - (modify-syntax-entry ?= "." ruby-mode-syntax-table) - (modify-syntax-entry ?/ "." ruby-mode-syntax-table) - (modify-syntax-entry ?+ "." ruby-mode-syntax-table) - (modify-syntax-entry ?* "." ruby-mode-syntax-table) - (modify-syntax-entry ?- "." ruby-mode-syntax-table) - (modify-syntax-entry ?\; "." ruby-mode-syntax-table) - (modify-syntax-entry ?\( "()" ruby-mode-syntax-table) - (modify-syntax-entry ?\) ")(" ruby-mode-syntax-table) - (modify-syntax-entry ?\{ "(}" ruby-mode-syntax-table) - (modify-syntax-entry ?\} "){" ruby-mode-syntax-table) - (modify-syntax-entry ?\[ "(]" ruby-mode-syntax-table) - (modify-syntax-entry ?\] ")[" ruby-mode-syntax-table) - ) - -(defcustom ruby-indent-tabs-mode nil - "*Indentation can insert tabs in ruby mode if this is non-nil." - :type 'boolean :group 'ruby) -(put 'ruby-indent-tabs-mode 'safe-local-variable 'booleanp) - -(defcustom ruby-indent-level 2 - "*Indentation of ruby statements." - :type 'integer :group 'ruby) -(put 'ruby-indent-level 'safe-local-variable 'integerp) - -(defcustom ruby-comment-column 32 - "*Indentation column of comments." - :type 'integer :group 'ruby) -(put 'ruby-comment-column 'safe-local-variable 'integerp) - -(defcustom ruby-deep-arglist t - "*Deep indent lists in parenthesis when non-nil. -Also ignores spaces after parenthesis when 'space." - :group 'ruby) -(put 'ruby-deep-arglist 'safe-local-variable 'booleanp) - -(defcustom ruby-deep-indent-paren '(?\( ?\[ ?\] t) - "*Deep indent lists in parenthesis when non-nil. t means continuous line. -Also ignores spaces after parenthesis when 'space." - :group 'ruby) - -(defcustom ruby-deep-indent-paren-style 'space - "Default deep indent style." - :options '(t nil space) :group 'ruby) - -(defcustom ruby-encoding-map '((shift_jis . cp932) (shift-jis . cp932)) - "Alist to map encoding name from emacs to ruby." - :group 'ruby) - -(defcustom ruby-use-encoding-map t - "*Use `ruby-encoding-map' to set encoding magic comment if this is non-nil." - :type 'boolean :group 'ruby) - -(defvar ruby-indent-point nil "internal variable") - -(eval-when-compile (require 'cl)) -(defun ruby-imenu-create-index-in-block (prefix beg end) - (let ((index-alist '()) (case-fold-search nil) - name next pos decl sing) - (goto-char beg) - (while (re-search-forward "^\\s *\\(\\(class\\s +\\|\\(class\\s *<<\\s *\\)\\|module\\s +\\)\\([^\(<\n ]+\\)\\|\\(def\\|alias\\)\\s +\\([^\(\n ]+\\)\\)" end t) - (setq sing (match-beginning 3)) - (setq decl (match-string 5)) - (setq next (match-end 0)) - (setq name (or (match-string 4) (match-string 6))) - (setq pos (match-beginning 0)) - (cond - ((string= "alias" decl) - (if prefix (setq name (concat prefix name))) - (push (cons name pos) index-alist)) - ((string= "def" decl) - (if prefix - (setq name - (cond - ((string-match "^self\." name) - (concat (substring prefix 0 -1) (substring name 4))) - (t (concat prefix name))))) - (push (cons name pos) index-alist) - (ruby-accurate-end-of-block end)) - (t - (if (string= "self" name) - (if prefix (setq name (substring prefix 0 -1))) - (if prefix (setq name (concat (substring prefix 0 -1) "::" name))) - (push (cons name pos) index-alist)) - (ruby-accurate-end-of-block end) - (setq beg (point)) - (setq index-alist - (nconc (ruby-imenu-create-index-in-block - (concat name (if sing "." "#")) - next beg) index-alist)) - (goto-char beg)))) - index-alist)) - -(defun ruby-imenu-create-index () - (nreverse (ruby-imenu-create-index-in-block nil (point-min) nil))) - -(defun ruby-accurate-end-of-block (&optional end) - (let (state) - (or end (setq end (point-max))) - (while (and (setq state (apply 'ruby-parse-partial end state)) - (>= (nth 2 state) 0) (< (point) end))))) - -(defun ruby-mode-variables () - (set-syntax-table ruby-mode-syntax-table) - (setq show-trailing-whitespace t) - (setq local-abbrev-table ruby-mode-abbrev-table) - (make-local-variable 'indent-line-function) - (setq indent-line-function 'ruby-indent-line) - (make-local-variable 'require-final-newline) - (setq require-final-newline t) - (make-local-variable 'comment-start) - (setq comment-start "# ") - (make-local-variable 'comment-end) - (setq comment-end "") - (make-local-variable 'comment-column) - (setq comment-column ruby-comment-column) - (make-local-variable 'comment-start-skip) - (setq comment-start-skip "#+ *") - (setq indent-tabs-mode ruby-indent-tabs-mode) - (make-local-variable 'parse-sexp-ignore-comments) - (setq parse-sexp-ignore-comments t) - (make-local-variable 'parse-sexp-lookup-properties) - (setq parse-sexp-lookup-properties t) - (make-local-variable 'paragraph-start) - (setq paragraph-start (concat "$\\|" page-delimiter)) - (make-local-variable 'paragraph-separate) - (setq paragraph-separate paragraph-start) - (make-local-variable 'paragraph-ignore-fill-prefix) - (setq paragraph-ignore-fill-prefix t)) - -(defun ruby-mode-set-encoding () - (save-excursion - (widen) - (goto-char (point-min)) - (when (re-search-forward "[^\0-\177]" nil t) - (goto-char (point-min)) - (let ((coding-system - (or coding-system-for-write - buffer-file-coding-system))) - (if coding-system - (setq coding-system - (or (coding-system-get coding-system 'mime-charset) - (coding-system-change-eol-conversion coding-system nil)))) - (setq coding-system - (if coding-system - (symbol-name - (or (and ruby-use-encoding-map - (cdr (assq coding-system ruby-encoding-map))) - coding-system)) - "ascii-8bit")) - (if (looking-at "^#!") (beginning-of-line 2)) - (cond ((looking-at "\\s *#.*-\*-\\s *\\(en\\)?coding\\s *:\\s *\\([-a-z0-9_]*\\)\\s *\\(;\\|-\*-\\)") - (unless (string= (match-string 2) coding-system) - (goto-char (match-beginning 2)) - (delete-region (point) (match-end 2)) - (and (looking-at "-\*-") - (let ((n (skip-chars-backward " "))) - (cond ((= n 0) (insert " ") (backward-char)) - ((= n -1) (insert " ")) - ((forward-char))))) - (insert coding-system))) - ((looking-at "\\s *#.*coding\\s *[:=]")) - (t (insert "# -*- coding: " coding-system " -*-\n")) - ))))) - -(defun ruby-current-indentation () - (save-excursion - (beginning-of-line) - (back-to-indentation) - (current-column))) - -(defun ruby-indent-line (&optional flag) - "Correct indentation of the current ruby line." - (ruby-indent-to (ruby-calculate-indent))) - -(defun ruby-indent-command () - (interactive) - (ruby-indent-line t)) - -(defun ruby-indent-to (x) - (if x - (let (shift top beg) - (and (< x 0) (error "invalid nest")) - (setq shift (current-column)) - (beginning-of-line) - (setq beg (point)) - (back-to-indentation) - (setq top (current-column)) - (skip-chars-backward " \t") - (if (>= shift top) (setq shift (- shift top)) - (setq shift 0)) - (if (and (bolp) - (= x top)) - (move-to-column (+ x shift)) - (move-to-column top) - (delete-region beg (point)) - (beginning-of-line) - (indent-to x) - (move-to-column (+ x shift)))))) - -(defun ruby-special-char-p (&optional pnt) - (setq pnt (or pnt (point))) - (let ((c (char-before pnt)) (b (and (< (point-min) pnt) (char-before (1- pnt))))) - (cond ((or (eq c ??) (eq c ?$))) - ((and (eq c ?:) (or (not b) (eq (char-syntax b) ? )))) - ((eq c ?\\) (eq b ??))))) - -(defun ruby-singleton-class-p () - (save-excursion - (forward-word -1) - (and (or (bolp) (not (eq (char-before (point)) ?_))) - (looking-at "class\\s *<<")))) - -(defun ruby-expr-beg (&optional option) - (save-excursion - (store-match-data nil) - (let ((space (skip-chars-backward " \t")) - (start (point))) - (cond - ((bolp) t) - ((progn - (forward-char -1) - (and (looking-at "\\?") - (or (eq (char-syntax (char-before (point))) ?w) - (ruby-special-char-p)))) - nil) - ((and (eq option 'heredoc) (< space 0)) - (not (progn (goto-char start) (ruby-singleton-class-p)))) - ((or (looking-at ruby-operator-re) - (looking-at "[\\[({,;]") - (and (looking-at "[!?]") - (or (not (eq option 'modifier)) - (bolp) - (save-excursion (forward-char -1) (looking-at "\\Sw$")))) - (and (looking-at ruby-symbol-re) - (skip-chars-backward ruby-symbol-chars) - (cond - ((looking-at (regexp-opt - (append ruby-block-beg-keywords - ruby-block-op-keywords - ruby-block-mid-keywords) - 'words)) - (goto-char (match-end 0)) - (not (looking-at "\\s_\\|[!?:]"))) - ((eq option 'expr-qstr) - (looking-at "[a-zA-Z][a-zA-z0-9_]* +%[^ \t]")) - ((eq option 'expr-re) - (looking-at "[a-zA-Z][a-zA-z0-9_]* +/[^ \t]")) - (t nil))))))))) - -(defun ruby-forward-string (term &optional end no-error expand) - (let ((n 1) (c (string-to-char term)) - (re (if expand - (concat "[^\\]\\(\\\\\\\\\\)*\\([" term "]\\|\\(#{\\)\\)") - (concat "[^\\]\\(\\\\\\\\\\)*[" term "]")))) - (while (and (re-search-forward re end no-error) - (if (match-beginning 3) - (ruby-forward-string "}{" end no-error nil) - (> (setq n (if (eq (char-before (point)) c) - (1- n) (1+ n))) 0))) - (forward-char -1)) - (cond ((zerop n)) - (no-error nil) - ((error "unterminated string"))))) - -(defun ruby-deep-indent-paren-p (c &optional pos) - (cond ((save-excursion - (if pos (goto-char pos)) - (ruby-expr-beg)) - nil) - ((listp ruby-deep-indent-paren) - (let ((deep (assoc c ruby-deep-indent-paren))) - (cond (deep - (or (cdr deep) ruby-deep-indent-paren-style)) - ((memq c ruby-deep-indent-paren) - ruby-deep-indent-paren-style)))) - ((eq c ruby-deep-indent-paren) ruby-deep-indent-paren-style) - ((eq c ?\( ) ruby-deep-arglist))) - -(defun ruby-parse-partial (&optional end in-string nest depth pcol indent) - (or depth (setq depth 0)) - (or indent (setq indent 0)) - (when (re-search-forward ruby-delimiter end 'move) - (let ((pnt (point)) w re expand) - (goto-char (match-beginning 0)) - (cond - ((and (memq (char-before) '(?@ ?$)) (looking-at "\\sw")) - (goto-char pnt)) - ((looking-at "[\"`]") ;skip string - (cond - ((and (not (eobp)) - (ruby-forward-string (buffer-substring (point) (1+ (point))) end t t)) - nil) - (t - (setq in-string (point)) - (goto-char end)))) - ((looking-at "'") - (cond - ((and (not (eobp)) - (re-search-forward "[^\\]\\(\\\\\\\\\\)*'" end t)) - nil) - (t - (setq in-string (point)) - (goto-char end)))) - ((looking-at "/=") - (goto-char pnt)) - ((looking-at "/") - (cond - ((and (not (eobp)) (ruby-expr-beg 'expr-re)) - (if (ruby-forward-string "/" end t t) - nil - (setq in-string (point)) - (goto-char end))) - (t - (goto-char pnt)))) - ((looking-at "%") - (cond - ((and (not (eobp)) - (ruby-expr-beg 'expr-qstr) - (not (looking-at "%=")) - (looking-at "%[QqrxWw]?\\([^a-zA-Z0-9 \t\n]\\)")) - (goto-char (match-beginning 1)) - (setq expand (not (memq (char-before) '(?q ?w)))) - (setq w (match-string 1)) - (cond - ((string= w "[") (setq re "][")) - ((string= w "{") (setq re "}{")) - ((string= w "(") (setq re ")(")) - ((string= w "<") (setq re "><")) - ((and expand (string= w "\\")) - (setq w (concat "\\" w)))) - (unless (cond (re (ruby-forward-string re end t expand)) - (expand (ruby-forward-string w end t t)) - (t (re-search-forward - (if (string= w "\\") - "\\\\[^\\]*\\\\" - (concat "[^\\]\\(\\\\\\\\\\)*" w)) - end t))) - (setq in-string (point)) - (goto-char end))) - (t - (goto-char pnt)))) - ((looking-at "\\?") ;skip ?char - (cond - ((and (ruby-expr-beg) - (looking-at "?\\(\\\\C-\\|\\\\M-\\)*\\\\?.")) - (goto-char (match-end 0))) - (t - (goto-char pnt)))) - ((looking-at "\\$") ;skip $char - (goto-char pnt) - (forward-char 1)) - ((looking-at "#") ;skip comment - (forward-line 1) - (goto-char (point)) - ) - ((looking-at "[\\[{(]") - (let ((deep (ruby-deep-indent-paren-p (char-after)))) - (if (and deep (or (not (eq (char-after) ?\{)) (ruby-expr-beg))) - (progn - (and (eq deep 'space) (looking-at ".\\s +[^# \t\n]") - (setq pnt (1- (match-end 0)))) - (setq nest (cons (cons (char-after (point)) (point)) nest)) - (setq pcol (cons (cons pnt depth) pcol)) - (setq depth 0)) - (setq nest (cons (cons (char-after (point)) pnt) nest)) - (setq depth (1+ depth)))) - (goto-char pnt) - ) - ((looking-at "[])}]") - (if (ruby-deep-indent-paren-p (matching-paren (char-after)) - (if nest - (cdr (nth 0 nest)) - (save-excursion - (forward-char) - (ruby-backward-sexp) - (point)))) - (setq depth (cdr (car pcol)) pcol (cdr pcol)) - (setq depth (1- depth))) - (setq nest (cdr nest)) - (goto-char pnt)) - ((looking-at ruby-block-end-re) - (if (or (and (not (bolp)) - (progn - (forward-char -1) - (setq w (char-after (point))) - (or (eq ?_ w) - (eq ?. w)))) - (progn - (goto-char pnt) - (setq w (char-after (point))) - (or (eq ?_ w) - (eq ?! w) - (eq ?? w)))) - nil - (setq nest (cdr nest)) - (setq depth (1- depth))) - (goto-char pnt)) - ((looking-at "def\\s +[^(\n;]*") - (if (or (bolp) - (progn - (forward-char -1) - (not (eq ?_ (char-after (point)))))) - (progn - (setq nest (cons (cons nil pnt) nest)) - (setq depth (1+ depth)))) - (goto-char (match-end 0))) - ((looking-at (concat "\\_<\\(" ruby-block-beg-re "\\)\\_>")) - (and - (save-match-data - (or (not (looking-at (concat "do" ruby-keyword-end-re))) - (save-excursion - (back-to-indentation) - (not (looking-at ruby-non-block-do-re))))) - (or (bolp) - (progn - (forward-char -1) - (setq w (char-after (point))) - (not (or (eq ?_ w) - (eq ?. w))))) - (goto-char pnt) - (setq w (char-after (point))) - (not (eq ?_ w)) - (not (eq ?! w)) - (not (eq ?? w)) - (not (eq ?: w)) - (skip-chars-forward " \t") - (goto-char (match-beginning 0)) - (or (not (looking-at ruby-modifier-re)) - (ruby-expr-beg 'modifier)) - (goto-char pnt) - (setq nest (cons (cons nil pnt) nest)) - (setq depth (1+ depth))) - (goto-char pnt)) - ((looking-at ":\\(['\"]\\)") - (goto-char (match-beginning 1)) - (ruby-forward-string (buffer-substring (match-beginning 1) (match-end 1)) end)) - ((looking-at ":\\([-,.+*/%&|^~<>]=?\\|===?\\|<=>\\|![~=]?\\)") - (goto-char (match-end 0))) - ((looking-at ":\\([a-zA-Z_][a-zA-Z_0-9]*[!?=]?\\)?") - (goto-char (match-end 0))) - ((or (looking-at "\\.\\.\\.?") - (looking-at "\\.[0-9]+") - (looking-at "\\.[a-zA-Z_0-9]+") - (looking-at "\\.")) - (goto-char (match-end 0))) - ((looking-at "^=begin") - (if (re-search-forward "^=end" end t) - (forward-line 1) - (setq in-string (match-end 0)) - (goto-char end))) - ((looking-at "<<") - (cond - ((and (ruby-expr-beg 'heredoc) - (looking-at "<<\\(-\\)?\\(\\([\"'`]\\)\\([^\n]+?\\)\\3\\|\\(?:\\sw\\|\\s_\\)+\\)")) - (setq re (regexp-quote (or (match-string 4) (match-string 2)))) - (if (match-beginning 1) (setq re (concat "\\s *" re))) - (let* ((id-end (goto-char (match-end 0))) - (line-end-position (save-excursion (end-of-line) (point))) - (state (list in-string nest depth pcol indent))) - ;; parse the rest of the line - (while (and (> line-end-position (point)) - (setq state (apply 'ruby-parse-partial - line-end-position state)))) - (setq in-string (car state) - nest (nth 1 state) - depth (nth 2 state) - pcol (nth 3 state) - indent (nth 4 state)) - ;; skip heredoc section - (if (re-search-forward (concat "^" re "$") end 'move) - (forward-line 1) - (setq in-string id-end) - (goto-char end)))) - (t - (goto-char pnt)))) - ((looking-at "^__END__$") - (goto-char pnt)) - ((looking-at ruby-here-doc-beg-re) - (if (re-search-forward (ruby-here-doc-end-match) - ruby-indent-point t) - (forward-line 1) - (setq in-string (match-end 0)) - (goto-char ruby-indent-point))) - (t - (error (format "bad string %s" - (buffer-substring (point) pnt) - )))))) - (list in-string nest depth pcol)) - -(defun ruby-parse-region (start end) - (let (state) - (save-excursion - (if start - (goto-char start) - (ruby-beginning-of-indent)) - (save-restriction - (narrow-to-region (point) end) - (while (and (> end (point)) - (setq state (apply 'ruby-parse-partial end state)))))) - (list (nth 0 state) ; in-string - (car (nth 1 state)) ; nest - (nth 2 state) ; depth - (car (car (nth 3 state))) ; pcol - ;(car (nth 5 state)) ; indent - ))) - -(defun ruby-indent-size (pos nest) - (+ pos (* (or nest 1) ruby-indent-level))) - -(defun ruby-calculate-indent (&optional parse-start) - (save-excursion - (beginning-of-line) - (let ((ruby-indent-point (point)) - (case-fold-search nil) - state bol eol begin op-end - (paren (progn (skip-syntax-forward " ") - (and (char-after) (matching-paren (char-after))))) - (indent 0)) - (if parse-start - (goto-char parse-start) - (ruby-beginning-of-indent) - (setq parse-start (point))) - (back-to-indentation) - (setq indent (current-column)) - (setq state (ruby-parse-region parse-start ruby-indent-point)) - (cond - ((nth 0 state) ; within string - (setq indent nil)) ; do nothing - ((car (nth 1 state)) ; in paren - (goto-char (setq begin (cdr (nth 1 state)))) - (let ((deep (ruby-deep-indent-paren-p (car (nth 1 state)) - (1- (cdr (nth 1 state)))))) - (if deep - (cond ((and (eq deep t) (eq (car (nth 1 state)) paren)) - (skip-syntax-backward " ") - (setq indent (1- (current-column)))) - ((eq deep 'space) - (goto-char (cdr (nth 1 state))) - (setq indent (1+ (current-column)))) - ((let ((s (ruby-parse-region (point) ruby-indent-point))) - (and (nth 2 s) (> (nth 2 s) 0) - (or (goto-char (cdr (nth 1 s))) t))) - (forward-word -1) - (setq indent (ruby-indent-size (current-column) (nth 2 state)))) - (t - (setq indent (current-column)) - (cond ((eq deep 'space)) - (paren (setq indent (1- indent))) - (t (setq indent (ruby-indent-size (1- indent) 1)))))) - (if (nth 3 state) (goto-char (nth 3 state)) - (goto-char parse-start) (back-to-indentation)) - (setq indent (ruby-indent-size (current-column) (nth 2 state)))) - (and (eq (car (nth 1 state)) paren) - (ruby-deep-indent-paren-p (matching-paren paren) - (1- (cdr (nth 1 state)))) - (search-backward (char-to-string paren)) - (setq indent (current-column))))) - ((and (nth 2 state) (> (nth 2 state) 0)) ; in nest - (if (null (cdr (nth 1 state))) - (error "invalid nest")) - (goto-char (cdr (nth 1 state))) - (forward-word -1) ; skip back a keyword - (setq begin (point)) - (cond - ((looking-at "do\\>[^_]") ; iter block is a special case - (if (nth 3 state) (goto-char (nth 3 state)) - (goto-char parse-start) (back-to-indentation)) - (setq indent (ruby-indent-size (current-column) (nth 2 state)))) - (t - (setq indent (+ (current-column) ruby-indent-level))))) - - ((and (nth 2 state) (< (nth 2 state) 0)) ; in negative nest - (setq indent (ruby-indent-size (current-column) (nth 2 state))))) - (when indent - (goto-char ruby-indent-point) - (end-of-line) - (setq eol (point)) - (beginning-of-line) - (cond - ((and (not (ruby-deep-indent-paren-p paren - (and (cdr (nth 1 state)) - (1- (cdr (nth 1 state)))))) - (re-search-forward ruby-negative eol t)) - (and (not (eq ?_ (char-after (match-end 0)))) - (setq indent (- indent ruby-indent-level)))) - ((and - (save-excursion - (beginning-of-line) - (not (bobp))) - (or (ruby-deep-indent-paren-p t) - (null (car (nth 1 state))))) - ;; goto beginning of non-empty no-comment line - (let (end done) - (while (not done) - (skip-chars-backward " \t\n") - (setq end (point)) - (beginning-of-line) - (if (re-search-forward "^\\s *#" end t) - (beginning-of-line) - (setq done t)))) - (setq bol (point)) - (end-of-line) - ;; skip the comment at the end - (skip-chars-backward " \t") - (let (end (pos (point))) - (beginning-of-line) - (while (and (re-search-forward "#" pos t) - (setq end (1- (point))) - (or (ruby-special-char-p end) - (and (setq state (ruby-parse-region parse-start end)) - (nth 0 state)))) - (setq end nil)) - (goto-char (or end pos)) - (skip-chars-backward " \t") - (setq begin (if (and end (nth 0 state)) pos (cdr (nth 1 state)))) - (setq state (ruby-parse-region parse-start (point)))) - (or (bobp) (forward-char -1)) - (and - (or (and (looking-at ruby-symbol-re) - (skip-chars-backward ruby-symbol-chars) - (looking-at (concat "\\<\\(" ruby-block-hanging-re "\\)\\>")) - (not (eq (point) (nth 3 state))) - (save-excursion - (goto-char (match-end 0)) - (not (looking-at "[a-z_]")))) - (and (looking-at ruby-operator-re) - (not (ruby-special-char-p)) - ;; operator at the end of line - (let ((c (char-after (point)))) - (and -;; (or (null begin) -;; (save-excursion -;; (goto-char begin) -;; (skip-chars-forward " \t") -;; (not (or (eolp) (looking-at "#") -;; (and (eq (car (nth 1 state)) ?{) -;; (looking-at "|")))))) - (or (not (eq ?/ c)) - (null (nth 0 (ruby-parse-region (or begin parse-start) (point))))) - (or (not (eq ?| (char-after (point)))) - (save-excursion - (or (eolp) (forward-char -1)) - (cond - ((search-backward "|" nil t) - (skip-chars-backward " \t\n") - (and (not (eolp)) - (progn - (forward-char -1) - (not (looking-at "{"))) - (progn - (forward-word -1) - (not (looking-at "do\\>[^_]"))))) - (t t)))) - (not (eq ?, c)) - (setq op-end t))))) - (setq indent - (cond - ((and - (null op-end) - (not (looking-at (concat "\\<\\(" ruby-block-hanging-re "\\)\\>"))) - (eq (ruby-deep-indent-paren-p t) 'space) - (not (bobp))) - (widen) - (goto-char (or begin parse-start)) - (skip-syntax-forward " ") - (current-column)) - ((car (nth 1 state)) indent) - (t - (+ indent ruby-indent-level)))))))) - (goto-char ruby-indent-point) - (beginning-of-line) - (skip-syntax-forward " ") - (if (looking-at "\\.[^.]") - (+ indent ruby-indent-level) - indent)))) - -(defun ruby-electric-brace (arg) - (interactive "P") - (insert-char last-command-char 1) - (ruby-indent-line t) - (delete-char -1) - (self-insert-command (prefix-numeric-value arg))) - -(eval-when-compile - (defmacro defun-region-command (func args &rest body) - (let ((intr (car body))) - (when (featurep 'xemacs) - (if (stringp intr) (setq intr (cadr body))) - (and (eq (car intr) 'interactive) - (setq intr (cdr intr)) - (setcar intr (concat "_" (car intr))))) - (cons 'defun (cons func (cons args body)))))) - -(defun-region-command ruby-beginning-of-defun (&optional arg) - "Move backward to next beginning-of-defun. -With argument, do this that many times. -Returns t unless search stops due to end of buffer." - (interactive "p") - (and (re-search-backward (concat "^\\(" ruby-block-beg-re "\\)\\_>") - nil 'move (or arg 1)) - (progn (beginning-of-line) t))) - -(defun ruby-beginning-of-indent () - (and (re-search-backward (concat "^\\(" ruby-indent-beg-re "\\)\\_>") - nil 'move) - (progn - (beginning-of-line) - t))) - -(defun-region-command ruby-end-of-defun (&optional arg) - "Move forward to next end of defun. -An end of a defun is found by moving forward from the beginning of one." - (interactive "p") - (and (re-search-forward (concat "^\\(" ruby-block-end-re "\\)\\($\\|\\b[^_]\\)") - nil 'move (or arg 1)) - (progn (beginning-of-line) t)) - (forward-line 1)) - -(defun ruby-move-to-block (n) - (let (start pos done down (orig (point))) - (setq start (ruby-calculate-indent)) - (setq down (looking-at (if (< n 0) ruby-block-end-re - (concat "\\<\\(" ruby-block-beg-re "\\)\\>")))) - (while (and (not done) (not (if (< n 0) (bobp) (eobp)))) - (forward-line n) - (cond - ((looking-at "^\\s *$")) - ((looking-at "^\\s *#")) - ((and (> n 0) (looking-at "^=begin\\>")) - (re-search-forward "^=end\\>")) - ((and (< n 0) (looking-at "^=end\\>")) - (re-search-backward "^=begin\\>")) - (t - (setq pos (current-indentation)) - (cond - ((< start pos) - (setq down t)) - ((and down (= pos start)) - (setq done t)) - ((> start pos) - (setq done t))))) - (if done - (save-excursion - (back-to-indentation) - (if (looking-at (concat "\\<\\(" ruby-block-mid-re "\\)\\>")) - (setq done nil))))) - (back-to-indentation) - (when (< n 0) - (let ((eol (point-at-eol)) state next) - (if (< orig eol) (setq eol orig)) - (setq orig (point)) - (while (and (setq next (apply 'ruby-parse-partial eol state)) - (< (point) eol)) - (setq state next)) - (when (cdaadr state) - (goto-char (cdaadr state))) - (backward-word))))) - -(defun-region-command ruby-beginning-of-block (&optional arg) - "Move backward to next beginning-of-block" - (interactive "p") - (ruby-move-to-block (- (or arg 1)))) - -(defun-region-command ruby-end-of-block (&optional arg) - "Move forward to next beginning-of-block" - (interactive "p") - (ruby-move-to-block (or arg 1))) - -(defun-region-command ruby-forward-sexp (&optional cnt) - (interactive "p") - (if (and (numberp cnt) (< cnt 0)) - (ruby-backward-sexp (- cnt)) - (let ((i (or cnt 1))) - (condition-case nil - (while (> i 0) - (skip-syntax-forward " ") - (if (looking-at ",\\s *") (goto-char (match-end 0))) - (cond ((looking-at "\\?\\(\\\\[CM]-\\)*\\\\?\\S ") - (goto-char (match-end 0))) - ((progn - (skip-chars-forward ",.:;|&^~=!?\\+\\-\\*") - (looking-at "\\s(")) - (goto-char (scan-sexps (point) 1))) - ((and (looking-at (concat "\\<\\(" ruby-block-beg-re "\\)\\>")) - (not (eq (char-before (point)) ?.)) - (not (eq (char-before (point)) ?:))) - (ruby-end-of-block) - (forward-word 1)) - ((looking-at "\\(\\$\\|@@?\\)?\\sw") - (while (progn - (while (progn (forward-word 1) (looking-at "_"))) - (cond ((looking-at "::") (forward-char 2) t) - ((> (skip-chars-forward ".") 0)) - ((looking-at "\\?\\|!\\(=[~=>]\\|[^~=]\\)") - (forward-char 1) nil))))) - ((let (state expr) - (while - (progn - (setq expr (or expr (ruby-expr-beg) - (looking-at "%\\sw?\\Sw\\|[\"'`/]"))) - (nth 1 (setq state (apply 'ruby-parse-partial nil state)))) - (setq expr t) - (skip-chars-forward "<")) - (not expr)))) - (setq i (1- i))) - ((error) (forward-word 1))) - i))) - -(defun-region-command ruby-backward-sexp (&optional cnt) - (interactive "p") - (if (and (numberp cnt) (< cnt 0)) - (ruby-forward-sexp (- cnt)) - (let ((i (or cnt 1))) - (condition-case nil - (while (> i 0) - (skip-chars-backward " \t\n,.:;|&^~=!?\\+\\-\\*") - (forward-char -1) - (cond ((looking-at "\\s)") - (goto-char (scan-sexps (1+ (point)) -1)) - (case (char-before) - (?% (forward-char -1)) - ('(?q ?Q ?w ?W ?r ?x) - (if (eq (char-before (1- (point))) ?%) (forward-char -2)))) - nil) - ((looking-at "\\s\"\\|\\\\\\S_") - (let ((c (char-to-string (char-before (match-end 0))))) - (while (and (search-backward c) - (oddp (skip-chars-backward "\\"))))) - nil) - ((looking-at "\\s.\\|\\s\\") - (if (ruby-special-char-p) (forward-char -1))) - ((looking-at "\\s(") nil) - (t - (forward-char 1) - (while (progn (forward-word -1) - (case (char-before) - (?_ t) - (?. (forward-char -1) t) - ((?$ ?@) - (forward-char -1) - (and (eq (char-before) (char-after)) (forward-char -1))) - (?: - (forward-char -1) - (eq (char-before) :))))) - (if (looking-at ruby-block-end-re) - (ruby-beginning-of-block)) - nil)) - (setq i (1- i))) - ((error))) - i))) - -(defun ruby-reindent-then-newline-and-indent () - (interactive "*") - (newline) - (save-excursion - (end-of-line 0) - (indent-according-to-mode) - (delete-region (point) (progn (skip-chars-backward " \t") (point)))) - (indent-according-to-mode)) - -(fset 'ruby-encomment-region (symbol-function 'comment-region)) - -(defun ruby-decomment-region (beg end) - (interactive "r") - (save-excursion - (goto-char beg) - (while (re-search-forward "^\\([ \t]*\\)#" end t) - (replace-match "\\1" nil nil) - (save-excursion - (ruby-indent-line))))) - -(defun ruby-insert-end () - (interactive) - (insert "end") - (ruby-indent-line t) - (end-of-line)) - -(defun ruby-mark-defun () - "Put mark at end of this Ruby function, point at beginning." - (interactive) - (push-mark (point)) - (ruby-end-of-defun) - (push-mark (point) nil t) - (ruby-beginning-of-defun) - (re-search-backward "^\n" (- (point) 1) t)) - -(defun ruby-indent-exp (&optional shutup-p) - "Indent each line in the balanced expression following point syntactically. -If optional SHUTUP-P is non-nil, no errors are signalled if no -balanced expression is found." - (interactive "*P") - (let ((here (point-marker)) start top column (nest t)) - (set-marker-insertion-type here t) - (unwind-protect - (progn - (beginning-of-line) - (setq start (point) top (current-indentation)) - (while (and (not (eobp)) - (progn - (setq column (ruby-calculate-indent start)) - (cond ((> column top) - (setq nest t)) - ((and (= column top) nest) - (setq nest nil) t)))) - (ruby-indent-to column) - (beginning-of-line 2))) - (goto-char here) - (set-marker here nil)))) - -(defun ruby-add-log-current-method () - "Return current method string." - (condition-case nil - (save-excursion - (let (mname mlist (indent 0)) - ;; get current method (or class/module) - (if (re-search-backward - (concat "^[ \t]*\\(def\\|class\\|module\\)[ \t]+" - "\\(" - ;; \\. and :: for class method - "\\([A-Za-z_]" ruby-symbol-re "*\\|\\.\\|::" "\\)" - "+\\)") - nil t) - (progn - (setq mname (match-string 2)) - (unless (string-equal "def" (match-string 1)) - (setq mlist (list mname) mname nil)) - (goto-char (match-beginning 1)) - (setq indent (current-column)) - (beginning-of-line))) - ;; nest class/module - (while (and (> indent 0) - (re-search-backward - (concat - "^[ \t]*\\(class\\|module\\)[ \t]+" - "\\([A-Z]" ruby-symbol-re "*\\)") - nil t)) - (goto-char (match-beginning 1)) - (if (< (current-column) indent) - (progn - (setq mlist (cons (match-string 2) mlist)) - (setq indent (current-column)) - (beginning-of-line)))) - (when mname - (let ((mn (split-string mname "\\.\\|::"))) - (if (cdr mn) - (progn - (cond - ((string-equal "" (car mn)) - (setq mn (cdr mn) mlist nil)) - ((string-equal "self" (car mn)) - (setq mn (cdr mn))) - ((let ((ml (nreverse mlist))) - (while ml - (if (string-equal (car ml) (car mn)) - (setq mlist (nreverse (cdr ml)) ml nil)) - (or (setq ml (cdr ml)) (nreverse mlist)))))) - (if mlist - (setcdr (last mlist) mn) - (setq mlist mn)) - (setq mn (last mn 2)) - (setq mname (concat "." (cadr mn))) - (setcdr mn nil)) - (setq mname (concat "#" mname))))) - ;; generate string - (if (consp mlist) - (setq mlist (mapconcat (function identity) mlist "::"))) - (if mname - (if mlist (concat mlist mname) mname) - mlist))))) - -(defun ruby-brace-to-do-end () - (when (looking-at "{") - (let ((orig (point)) (end (progn (ruby-forward-sexp) (point)))) - (when (eq (char-before) ?\}) - (delete-char -1) - (if (eq (char-syntax (char-before)) ?w) - (insert " ")) - (insert "end") - (if (eq (char-syntax (char-after)) ?w) - (insert " ")) - (goto-char orig) - (delete-char 1) - (if (eq (char-syntax (char-before)) ?w) - (insert " ")) - (insert "do") - (when (looking-at "\\sw\\||") - (insert " ") - (backward-char)) - t)))) - -(defun ruby-do-end-to-brace () - (when (and (or (bolp) - (not (memq (char-syntax (char-before)) '(?w ?_)))) - (looking-at "\\<do\\(\\s \\|$\\)")) - (let ((orig (point)) (end (progn (ruby-forward-sexp) (point)))) - (backward-char 3) - (when (looking-at ruby-block-end-re) - (delete-char 3) - (insert "}") - (goto-char orig) - (delete-char 2) - (insert "{") - (if (looking-at "\\s +|") - (delete-char (- (match-end 0) (match-beginning 0) 1))) - t)))) - -(defun ruby-toggle-block () - (interactive) - (or (ruby-brace-to-do-end) - (ruby-do-end-to-brace))) - -(eval-when-compile - (if (featurep 'font-lock) - (defmacro eval-when-font-lock-available (&rest args) (cons 'progn args)) - (defmacro eval-when-font-lock-available (&rest args)))) - -(eval-when-compile - (if (featurep 'hilit19) - (defmacro eval-when-hilit19-available (&rest args) (cons 'progn args)) - (defmacro eval-when-hilit19-available (&rest args)))) - -(eval-when-font-lock-available - (or (boundp 'font-lock-variable-name-face) - (setq font-lock-variable-name-face font-lock-type-face)) - - (defconst ruby-font-lock-syntactic-keywords - `( - ;; #{ }, #$hoge, #@foo are not comments - ("\\(#\\)[{$@]" 1 (1 . nil)) - ;; the last $', $", $` in the respective string is not variable - ;; the last ?', ?", ?` in the respective string is not ascii code - ("\\(^\\|[\[ \t\n<+\(,=]\\)\\(['\"`]\\)\\(\\\\.\\|\\2\\|[^'\"`\n\\\\]\\)*?\\\\?[?$]\\(\\2\\)" - (2 (7 . nil)) - (4 (7 . nil))) - ;; $' $" $` .... are variables - ;; ?' ?" ?` are ascii codes - ("\\(^\\|[^\\\\]\\)\\(\\\\\\\\\\)*[?$]\\([#\"'`]\\)" 3 (1 . nil)) - ;; regexps - ("\\(^\\|[[=(,~?:;<>]\\|\\(^\\|\\s \\)\\(if\\|elsif\\|unless\\|while\\|until\\|when\\|and\\|or\\|&&\\|||\\)\\|g?sub!?\\|scan\\|split!?\\)\\s *\\(/\\)[^/\n\\\\]*\\(\\\\.[^/\n\\\\]*\\)*\\(/\\)" - (4 (7 . ?/)) - (6 (7 . ?/))) - ("^\\(=\\)begin\\(\\s \\|$\\)" 1 (7 . nil)) - ("^\\(=\\)end\\(\\s \\|$\\)" 1 (7 . nil)) - (,(concat ruby-here-doc-beg-re ".*\\(\n\\)") - ,(+ 1 (regexp-opt-depth ruby-here-doc-beg-re)) - (ruby-here-doc-beg-syntax)) - (,ruby-here-doc-end-re 3 (ruby-here-doc-end-syntax)))) - - (unless (functionp 'syntax-ppss) - (defun syntax-ppss (&optional pos) - (parse-partial-sexp (point-min) (or pos (point))))) - - (defun ruby-in-ppss-context-p (context &optional ppss) - (let ((ppss (or ppss (syntax-ppss (point))))) - (if (cond - ((eq context 'anything) - (or (nth 3 ppss) - (nth 4 ppss))) - ((eq context 'string) - (nth 3 ppss)) - ((eq context 'heredoc) - (and (nth 3 ppss) - ;; If it's generic string, it's a heredoc and we don't care - ;; See `parse-partial-sexp' - (not (numberp (nth 3 ppss))))) - ((eq context 'non-heredoc) - (and (ruby-in-ppss-context-p 'anything) - (not (ruby-in-ppss-context-p 'heredoc)))) - ((eq context 'comment) - (nth 4 ppss)) - (t - (error (concat - "Internal error on `ruby-in-ppss-context-p': " - "context name `" (symbol-name context) "' is unknown")))) - t))) - - (defun ruby-in-here-doc-p () - (save-excursion - (let ((old-point (point)) (case-fold-search nil)) - (beginning-of-line) - (catch 'found-beg - (while (and (re-search-backward ruby-here-doc-beg-re nil t) - (not (ruby-singleton-class-p))) - (if (not (or (ruby-in-ppss-context-p 'anything) - (ruby-here-doc-find-end old-point))) - (throw 'found-beg t))))))) - - (defun ruby-here-doc-find-end (&optional limit) - "Expects the point to be on a line with one or more heredoc -openers. Returns the buffer position at which all heredocs on the -line are terminated, or nil if they aren't terminated before the -buffer position `limit' or the end of the buffer." - (save-excursion - (beginning-of-line) - (catch 'done - (let ((eol (save-excursion (end-of-line) (point))) - (case-fold-search nil) - ;; Fake match data such that (match-end 0) is at eol - (end-match-data (progn (looking-at ".*$") (match-data))) - beg-match-data end-re) - (while (re-search-forward ruby-here-doc-beg-re eol t) - (setq beg-match-data (match-data)) - (setq end-re (ruby-here-doc-end-match)) - - (set-match-data end-match-data) - (goto-char (match-end 0)) - (unless (re-search-forward end-re limit t) (throw 'done nil)) - (setq end-match-data (match-data)) - - (set-match-data beg-match-data) - (goto-char (match-end 0))) - (set-match-data end-match-data) - (goto-char (match-end 0)) - (point))))) - - (defun ruby-here-doc-beg-syntax () - (save-excursion - (goto-char (match-beginning 0)) - (unless (or (ruby-in-ppss-context-p 'non-heredoc) - (ruby-in-here-doc-p)) - (string-to-syntax "|")))) - - (defun ruby-here-doc-end-syntax () - (let ((pss (syntax-ppss)) (case-fold-search nil)) - (when (ruby-in-ppss-context-p 'heredoc pss) - (save-excursion - (goto-char (nth 8 pss)) ; Go to the beginning of heredoc. - (let ((eol (point))) - (beginning-of-line) - (if (and (re-search-forward (ruby-here-doc-beg-match) eol t) ; If there is a heredoc that matches this line... - (not (ruby-in-ppss-context-p 'anything)) ; And that's not inside a heredoc/string/comment... - (progn (goto-char (match-end 0)) ; And it's the last heredoc on its line... - (not (re-search-forward ruby-here-doc-beg-re eol t)))) - (string-to-syntax "|"))))))) - - (eval-when-compile - (put 'ruby-mode 'font-lock-defaults - '((ruby-font-lock-keywords) - nil nil nil - beginning-of-line - (font-lock-syntactic-keywords - . ruby-font-lock-syntactic-keywords)))) - - (defun ruby-font-lock-docs (limit) - (if (re-search-forward "^=begin\\(\\s \\|$\\)" limit t) - (let (beg) - (beginning-of-line) - (setq beg (point)) - (forward-line 1) - (if (re-search-forward "^=end\\(\\s \\|$\\)" limit t) - (progn - (set-match-data (list beg (point))) - t))))) - - (defun ruby-font-lock-maybe-docs (limit) - (let (beg) - (save-excursion - (if (and (re-search-backward "^=\\(begin\\|end\\)\\(\\s \\|$\\)" nil t) - (string= (match-string 1) "begin")) - (progn - (beginning-of-line) - (setq beg (point))))) - (if (and beg (and (re-search-forward "^=\\(begin\\|end\\)\\(\\s \\|$\\)" nil t) - (string= (match-string 1) "end"))) - (progn - (set-match-data (list beg (point))) - t) - nil))) - - (defvar ruby-font-lock-syntax-table - (let* ((tbl (copy-syntax-table ruby-mode-syntax-table))) - (modify-syntax-entry ?_ "w" tbl) - tbl)) - - (defconst ruby-font-lock-keywords - (list - ;; functions - '("^\\s *def\\s +\\([^( \t\n]+\\)" - 1 font-lock-function-name-face) - ;; keywords - (cons (concat - "\\(^\\|[^_:.@$]\\|\\.\\.\\)\\_<\\(defined\\?\\|" - (regexp-opt - '("alias" - "and" - "begin" - "break" - "case" - "catch" - "class" - "def" - "do" - "elsif" - "else" - "fail" - "ensure" - "for" - "end" - "if" - "in" - "module" - "next" - "not" - "or" - "raise" - "redo" - "rescue" - "retry" - "return" - "then" - "throw" - "super" - "unless" - "undef" - "until" - "when" - "while" - "yield" - ) - t) - "\\)" - ruby-keyword-end-re) - 2) - ;; here-doc beginnings - (list ruby-here-doc-beg-re 0 'font-lock-string-face) - ;; variables - '("\\(^\\|[^_:.@$]\\|\\.\\.\\)\\_<\\(nil\\|self\\|true\\|false\\)\\>" - 2 font-lock-variable-name-face) - ;; variables - '("\\(\\$\\([^a-zA-Z0-9 \n]\\|[0-9]\\)\\)\\W" - 1 font-lock-variable-name-face) - '("\\(\\$\\|@\\|@@\\)\\(\\w\\|_\\)+" - 0 font-lock-variable-name-face) - ;; embedded document - '(ruby-font-lock-docs - 0 font-lock-comment-face t) - '(ruby-font-lock-maybe-docs - 0 font-lock-comment-face t) - ;; general delimited string - '("\\(^\\|[[ \t\n<+(,=]\\)\\(%[xrqQwW]?\\([^<[{(a-zA-Z0-9 \n]\\)[^\n\\\\]*\\(\\\\.[^\n\\\\]*\\)*\\(\\3\\)\\)" - (2 font-lock-string-face)) - ;; constants - '("\\(^\\|[^_]\\)\\_<\\([A-Z]+\\(\\w\\|_\\)*\\)" - 2 font-lock-type-face) - ;; symbols - '("\\(^\\|[^:]\\)\\(:\\([-+~]@?\\|[/%&|^`]\\|\\*\\*?\\|<\\(<\\|=>?\\)?\\|>[>=]?\\|===?\\|=~\\|![~=]?\\|\\[\\]=?\\|\\(\\w\\|_\\)+\\([!?=]\\|\\b_*\\)\\|#{[^}\n\\\\]*\\(\\\\.[^}\n\\\\]*\\)*}\\)\\)" - 2 font-lock-reference-face) - '("\\(^\\s *\\|[\[\{\(,]\\s *\\|\\sw\\s +\\)\\(\\(\\sw\\|_\\)+\\):[^:]" 2 font-lock-reference-face) - ;; expression expansion - '("#\\({[^}\n\\\\]*\\(\\\\.[^}\n\\\\]*\\)*}\\|\\(\\$\\|@\\|@@\\)\\(\\w\\|_\\)+\\)" - 0 font-lock-variable-name-face t) - ;; warn lower camel case - ;'("\\<[a-z]+[a-z0-9]*[A-Z][A-Za-z0-9]*\\([!?]?\\|\\>\\)" - ; 0 font-lock-warning-face) - ) - "*Additional expressions to highlight in ruby mode.")) - -(eval-when-hilit19-available - (hilit-set-mode-patterns - 'ruby-mode - '(("[^$\\?]\\(\"[^\\\"]*\\(\\\\\\(.\\|\n\\)[^\\\"]*\\)*\"\\)" 1 string) - ("[^$\\?]\\('[^\\']*\\(\\\\\\(.\\|\n\\)[^\\']*\\)*'\\)" 1 string) - ("[^$\\?]\\(`[^\\`]*\\(\\\\\\(.\\|\n\\)[^\\`]*\\)*`\\)" 1 string) - ("^\\s *#.*$" nil comment) - ("[^$@?\\]\\(#[^$@{\n].*$\\)" 1 comment) - ("[^a-zA-Z_]\\(\\?\\(\\\\[CM]-\\)*.\\)" 1 string) - ("^\\s *\\(require\\|load\\).*$" nil include) - ("^\\s *\\(include\\|alias\\|undef\\).*$" nil decl) - ("^\\s *\\<\\(class\\|def\\|module\\)\\>" "[)\n;]" defun) - ("[^_]\\<\\(begin\\|case\\|else\\|elsif\\|end\\|ensure\\|for\\|if\\|unless\\|rescue\\|then\\|when\\|while\\|until\\|do\\|yield\\)\\>\\([^_]\\|$\\)" 1 defun) - ("[^_]\\<\\(and\\|break\\|next\\|raise\\|fail\\|in\\|not\\|or\\|redo\\|retry\\|return\\|super\\|yield\\|catch\\|throw\\|self\\|nil\\)\\>\\([^_]\\|$\\)" 1 keyword) - ("\\$\\(.\\|\\sw+\\)" nil type) - ("[$@].[a-zA-Z_0-9]*" nil struct) - ("^__END__" nil label)))) - - -;;;###autoload -(defun ruby-mode () - "Major mode for editing ruby scripts. -\\[ruby-indent-command] properly indents subexpressions of multi-line -class, module, def, if, while, for, do, and case statements, taking -nesting into account. - -The variable ruby-indent-level controls the amount of indentation. -\\{ruby-mode-map}" - (interactive) - (kill-all-local-variables) - (use-local-map ruby-mode-map) - (setq mode-name "Ruby") - (setq major-mode 'ruby-mode) - (ruby-mode-variables) - - (make-local-variable 'imenu-create-index-function) - (setq imenu-create-index-function 'ruby-imenu-create-index) - - (make-local-variable 'add-log-current-defun-function) - (setq add-log-current-defun-function 'ruby-add-log-current-method) - - (add-hook - (cond ((boundp 'before-save-hook) - (make-local-variable 'before-save-hook) - 'before-save-hook) - ((boundp 'write-contents-functions) 'write-contents-functions) - ((boundp 'write-contents-hooks) 'write-contents-hooks)) - 'ruby-mode-set-encoding) - - (set (make-local-variable 'font-lock-defaults) '((ruby-font-lock-keywords) nil nil)) - (set (make-local-variable 'font-lock-keywords) ruby-font-lock-keywords) - (set (make-local-variable 'font-lock-syntax-table) ruby-font-lock-syntax-table) - (set (make-local-variable 'font-lock-syntactic-keywords) ruby-font-lock-syntactic-keywords) - - (if (fboundp 'run-mode-hooks) - (run-mode-hooks 'ruby-mode-hook) - (run-hooks 'ruby-mode-hook))) - -(provide 'ruby-mode) diff --git a/misc/ruby-style.el b/misc/ruby-style.el index 3ce55cd1ab..03d0830d3a 100644 --- a/misc/ruby-style.el +++ b/misc/ruby-style.el @@ -7,6 +7,8 @@ ;;; $Author$ ;;; created at: Thu Apr 26 13:54:01 JST 2007 ;;; +;;; Put this file under a directory contained in ``load-path'', and +;;; then load it. ;;; To switch to the "ruby" style automatically if it looks like a ;;; source file of ruby, add ruby-style-c-mode to c-mode-hook: ;;; @@ -53,8 +55,10 @@ '("bsd" (c-basic-offset . 4) (tab-width . 8) - (indent-tabs-mode . t) - (setq show-trailing-whitespace t) + (indent-tabs-mode . nil) + (show-trailing-whitespace . t) + (c-backslash-column . 1) + (c-backslash-max-column . 1) (c-offsets-alist (case-label . *) (label . (ruby-style-label-indent *)) @@ -64,6 +68,18 @@ (access-label /) ))) +(c-add-style + "prism" + '("bsd" + (c-basic-offset . 4) + (tab-width . 8) + (indent-tabs-mode . nil) + (show-trailing-whitespace . t) + (c-offsets-alist + (case-label . +) + ))) + +;;;###autoload (defun ruby-style-c-mode () (interactive) (if (or (let ((name (buffer-file-name))) (and name (string-match "/ruby\\>" name))) @@ -72,7 +88,20 @@ (let ((head (progn (forward-line 100) (point))) (case-fold-search nil)) (goto-char (point-min)) - (re-search-forward "Copyright (C) .* Yukihiro Matsumoto" head t)))) + (re-search-forward "Copyright (C) .* Yukihiro Matsumoto" head t))) + (condition-case () + (with-temp-buffer + (when (= 0 (call-process "git" nil t nil "remote" "get-url" "origin")) + (goto-char (point-min)) + (looking-at ".*/ruby\\(\\.git\\)?$"))) + (error)) + (condition-case () + (with-temp-buffer + (when (= 0 (call-process "svn" nil t nil "info" "--xml")) + (goto-char (point-min)) + (search-forward-regexp "<root>.*/ruby</root>" nil))) + (error)) + nil) (c-set-style "ruby"))) (provide 'ruby-style) diff --git a/misc/rubydb2x.el b/misc/rubydb2x.el deleted file mode 100644 index a74265fb0e..0000000000 --- a/misc/rubydb2x.el +++ /dev/null @@ -1,104 +0,0 @@ -(require 'gud) -(provide 'rubydb) - -;; ====================================================================== -;; rubydb functions - -;;; History of argument lists passed to rubydb. -(defvar gud-rubydb-history nil) - -(defun gud-rubydb-massage-args (file args) - (cons "-I" (cons "." (cons "-r" (cons "debug" (cons file args)))))) - -;; There's no guarantee that Emacs will hand the filter the entire -;; marker at once; it could be broken up across several strings. We -;; might even receive a big chunk with several markers in it. If we -;; receive a chunk of text which looks like it might contain the -;; beginning of a marker, we save it here between calls to the -;; filter. -(defvar gud-rubydb-marker-acc "") - -(defun gud-rubydb-marker-filter (string) - (save-match-data - (setq gud-marker-acc (concat gud-marker-acc string)) - (let ((output "")) - - ;; Process all the complete markers in this chunk. - (while (string-match "\032\032\\([^:\n]*\\):\\([0-9]*\\):.*\n" - gud-marker-acc) - (setq - - ;; Extract the frame position from the marker. - gud-last-frame - (cons (substring gud-marker-acc (match-beginning 1) (match-end 1)) - (string-to-int (substring gud-marker-acc - (match-beginning 2) - (match-end 2)))) - - ;; Append any text before the marker to the output we're going - ;; to return - we don't include the marker in this text. - output (concat output - (substring gud-marker-acc 0 (match-beginning 0))) - - ;; Set the accumulator to the remaining text. - gud-marker-acc (substring gud-marker-acc (match-end 0)))) - - ;; Does the remaining text look like it might end with the - ;; beginning of another marker? If it does, then keep it in - ;; gud-marker-acc until we receive the rest of it. Since we - ;; know the full marker regexp above failed, it's pretty simple to - ;; test for marker starts. - (if (string-match "\032.*\\'" gud-marker-acc) - (progn - ;; Everything before the potential marker start can be output. - (setq output (concat output (substring gud-marker-acc - 0 (match-beginning 0)))) - - ;; Everything after, we save, to combine with later input. - (setq gud-marker-acc - (substring gud-marker-acc (match-beginning 0)))) - - (setq output (concat output gud-marker-acc) - gud-marker-acc "")) - - output))) - -(defun gud-rubydb-find-file (f) - (find-file-noselect f)) - -(defvar rubydb-command-name "ruby" - "File name for executing ruby.") - -;;;###autoload -(defun rubydb (command-line) - "Run rubydb on program FILE in buffer *gud-FILE*. -The directory containing FILE becomes the initial working directory -and source-file directory for your debugger." - (interactive - (list (read-from-minibuffer "Run rubydb (like this): " - (if (consp gud-rubydb-history) - (car gud-rubydb-history) - (concat rubydb-command-name " ")) - nil nil - '(gud-rubydb-history . 1)))) - - (gud-overload-functions '((gud-massage-args . gud-rubydb-massage-args) - (gud-marker-filter . gud-rubydb-marker-filter) - (gud-find-file . gud-rubydb-find-file) - )) - (gud-common-init command-line) - - (gud-def gud-break "b %l" "\C-b" "Set breakpoint at current line.") -; (gud-def gud-remove "clear %l" "\C-d" "Remove breakpoint at current line") - (gud-def gud-step "s" "\C-s" "Step one source line with display.") - (gud-def gud-next "n" "\C-n" "Step one line (skip functions).") - (gud-def gud-cont "c" "\C-r" "Continue with display.") - (gud-def gud-finish "finish" "\C-f" "Finish executing current function.") - (gud-def gud-up "up %p" "<" "Up N stack frames (numeric arg).") - (gud-def gud-down "down %p" ">" "Down N stack frames (numeric arg).") - (gud-def gud-print "p %e" "\C-p" "Evaluate ruby expression at point.") - - (setq comint-prompt-regexp "^(rdb:-) ") - (setq paragraph-start comint-prompt-regexp) - (run-hooks 'rubydb-mode-hook) - ) diff --git a/misc/rubydb3x.el b/misc/rubydb3x.el deleted file mode 100644 index 9d6bc57d5a..0000000000 --- a/misc/rubydb3x.el +++ /dev/null @@ -1,115 +0,0 @@ -(require 'gud) -(provide 'rubydb) - -;; ====================================================================== -;; rubydb functions - -;;; History of argument lists passed to rubydb. -(defvar gud-rubydb-history nil) - -(if (fboundp 'gud-overload-functions) - (defun gud-rubydb-massage-args (file args) - (cons "-r" (cons "debug" (cons file args)))) - (defun gud-rubydb-massage-args (file args) - (cons "-r" (cons "debug" args)))) - -;; There's no guarantee that Emacs will hand the filter the entire -;; marker at once; it could be broken up across several strings. We -;; might even receive a big chunk with several markers in it. If we -;; receive a chunk of text which looks like it might contain the -;; beginning of a marker, we save it here between calls to the -;; filter. -(defvar gud-rubydb-marker-acc "") -(make-variable-buffer-local 'gud-rubydb-marker-acc) - -(defun gud-rubydb-marker-filter (string) - (setq gud-rubydb-marker-acc (concat gud-rubydb-marker-acc string)) - (let ((output "")) - - ;; Process all the complete markers in this chunk. - (while (string-match "\032\032\\([^:\n]*\\):\\([0-9]*\\):.*\n" - gud-rubydb-marker-acc) - (setq - - ;; Extract the frame position from the marker. - gud-last-frame - (cons (substring gud-rubydb-marker-acc (match-beginning 1) (match-end 1)) - (string-to-int (substring gud-rubydb-marker-acc - (match-beginning 2) - (match-end 2)))) - - ;; Append any text before the marker to the output we're going - ;; to return - we don't include the marker in this text. - output (concat output - (substring gud-rubydb-marker-acc 0 (match-beginning 0))) - - ;; Set the accumulator to the remaining text. - gud-rubydb-marker-acc (substring gud-rubydb-marker-acc (match-end 0)))) - - ;; Does the remaining text look like it might end with the - ;; beginning of another marker? If it does, then keep it in - ;; gud-rubydb-marker-acc until we receive the rest of it. Since we - ;; know the full marker regexp above failed, it's pretty simple to - ;; test for marker starts. - (if (string-match "\032.*\\'" gud-rubydb-marker-acc) - (progn - ;; Everything before the potential marker start can be output. - (setq output (concat output (substring gud-rubydb-marker-acc - 0 (match-beginning 0)))) - - ;; Everything after, we save, to combine with later input. - (setq gud-rubydb-marker-acc - (substring gud-rubydb-marker-acc (match-beginning 0)))) - - (setq output (concat output gud-rubydb-marker-acc) - gud-rubydb-marker-acc "")) - - output)) - -(defun gud-rubydb-find-file (f) - (save-excursion - (let ((buf (find-file-noselect f))) - (set-buffer buf) -;; (gud-make-debug-menu) - buf))) - -(defvar rubydb-command-name "ruby" - "File name for executing ruby.") - -;;;###autoload -(defun rubydb (command-line) - "Run rubydb on program FILE in buffer *gud-FILE*. -The directory containing FILE becomes the initial working directory -and source-file directory for your debugger." - (interactive - (list (read-from-minibuffer "Run rubydb (like this): " - (if (consp gud-rubydb-history) - (car gud-rubydb-history) - (concat rubydb-command-name " ")) - nil nil - '(gud-rubydb-history . 1)))) - - (if (not (fboundp 'gud-overload-functions)) - (gud-common-init command-line 'gud-rubydb-massage-args - 'gud-rubydb-marker-filter 'gud-rubydb-find-file) - (gud-overload-functions '((gud-massage-args . gud-rubydb-massage-args) - (gud-marker-filter . gud-rubydb-marker-filter) - (gud-find-file . gud-rubydb-find-file))) - (gud-common-init command-line rubydb-command-name)) - - (gud-def gud-break "b %l" "\C-b" "Set breakpoint at current line.") -; (gud-def gud-remove "clear %l" "\C-d" "Remove breakpoint at current line") - (gud-def gud-step "s" "\C-s" "Step one source line with display.") - (gud-def gud-next "n" "\C-n" "Step one line (skip functions).") - (gud-def gud-cont "c" "\C-r" "Continue with display.") - (gud-def gud-finish "finish" "\C-f" "Finish executing current function.") - (gud-def gud-up "up %p" "<" "Up N stack frames (numeric arg).") - (gud-def gud-down "down %p" ">" "Down N stack frames (numeric arg).") - (gud-def gud-print "p %e" "\C-p" "Evaluate ruby expression at point.") - - (setq comint-prompt-regexp "^(rdb:-) ") - (if (boundp 'comint-last-output-start) - (set-marker comint-last-output-start (point))) - (set (make-local-variable 'paragraph-start) comint-prompt-regexp) - (run-hooks 'rubydb-mode-hook) - ) diff --git a/misc/test_lldb_cruby.rb b/misc/test_lldb_cruby.rb new file mode 100644 index 0000000000..bd58619ac2 --- /dev/null +++ b/misc/test_lldb_cruby.rb @@ -0,0 +1,40 @@ +#!/usr/bin/env ruby +require 'open3' +require 'tempfile' +require 'test/unit' + +class TestLLDBInit < Test::Unit::TestCase + def assert_rp(expr, pattern, message=nil) + Tempfile.create('lldb') do |tf| + tf.puts <<eom +target create ./miniruby +command script import -r misc/lldb_cruby.py +b rb_inspect +run -e'p #{expr}' +rp obj +eom + tf.flush + o, s = Open3.capture2('lldb', '-b', '-s', tf.path) + assert_true s.success?, message + assert_match /^\(lldb\) rp obj\n#{pattern}/, o, message + end + end + + def test_rp_object + assert_rp 'Object.new', 'T_OBJECT' + end + + def test_rp_regex + assert_rp '/foo/', '[(]Regex' + end + + def test_rp_symbol + assert_rp ':abcde', /T_SYMBOL: \(\h+\)/ + end + + def test_rp_string + assert_rp '"abc"', /\(char \[\d+\]\) ary = "abc"/ + assert_rp "\"\u3042\"", /\(char \[\d+\]\) ary = "\u3042"/ + assert_rp '"' + "\u3042"*10 + '"', /\(RString::\(anonymous struct\)\) heap = \{/ + end +end diff --git a/misc/tsan_suppressions.txt b/misc/tsan_suppressions.txt new file mode 100644 index 0000000000..5492500e7f --- /dev/null +++ b/misc/tsan_suppressions.txt @@ -0,0 +1,109 @@ +# TSan: ThreadSanitizer +# https://github.com/google/sanitizers/wiki/threadsanitizersuppressions +# +# This file describes a number of places where TSAN detects problems in CRuby. +# Many of these indicate bugs. Others are benign (ex. data races that can be +# replaced with relaxed atomic loads) +# +# Usage: +# Configure with: +# ./configure cflags='-fsanitize=thread' CC=clang +# Build and run with: +# TSAN_OPTIONS="suppressions=$(pwd)/misc/tsan_suppressions.txt:die_after_fork=0" +# +# Other useful TSAN_OPTIONS: +# * halt_on_error=1 +# * strip_path_prefix=$(pwd)/ + +# Namespaces +race_top:push_subclass_entry_to_list + +# sub_nounderflow includes non-atomic read, possibly other issue +race:objspace_malloc_increase_body + +# Signals and ubf +race:unregister_ubf_list + +# It's already crashing. We're doing our best +signal:rb_vm_bugreport +race:check_reserved_signal_ + +race_top:rb_check_deadlock + +# vm->ractor.sched.grq_cnt++ +race_top:ractor_sched_enq +race_top:ractor_sched_deq + +# Race between vm_remove_ractor writing ractor count and +# native_thread_check_and_create_shared reading it during thread creation. +# The write happens when a ractor thread exits, the read happens when +# checking if new shared threads need to be created. +race:vm_remove_ractor + +# th->sched.finished at end of co_start +race_top:rb_thread_sched_mark_zombies + +# Races against timer thread setting th->sched.waiting_reason.flags +race_top:thread_sched_wait_events + +# At thread start +race_top:rb_ractor_set_current_ec_ + +# TSan reports a lock-order-inversion between thread_sched_lock_ and this lock. +# It's unclear if that can cause a deadlock since the lock is on self +deadlock:ractor_lock_self + +# TSan reports a deadlock when reacquiring the this lock after a barrier, but +# we know the other threads have been stopped +deadlock:rb_ractor_sched_barrier_start + +# RVALUE_AGE_SET manipulates flag bits on objects which may be accessed in Ractors +race_top:RVALUE_AGE_SET + +# Inline caches and call cache updates +# Multiple threads can race when updating shared call caches during method lookups +# and argument forwarding. These races involve reading/writing cd->cc fields. +race_top:vm_cc_call_set +race_top:vm_cc_class_check +race_top:vm_search_cc +race_top:vm_search_method_slowpath0 +race_top:rb_vm_opt_getconstant_path +race_top:vm_ic_attr_index_set +race:vm_ic_update +race:vm_caller_setup_fwd_args + +# Race in shape_get_next where multiple threads simultaneously access and modify +# RCLASS_MAX_IV_COUNT and RCLASS_VARIATION_COUNT fields in class objects. +# One thread reads the field while another thread calls RCLASS_SET_MAX_IV_COUNT. +# This happens during instance variable shape transitions in multi-threaded code. +race:shape_get_next + +# Non-atomic reads/writes +race:gccct_method_search + +# Ignore exit for now +race:rb_ec_finalize +race:rb_ec_cleanup + +# TSan doesn't work well post-fork, this raises errors when creating the new +# timer thread +race:after_fork_ruby + +# Sets objspace->flags.dont_incremental while writebarrier may be running +race_top:objspace_each_exec +race_top:objspace_each_objects_ensure + +# Non-atomic lazy initialized static variable +race_top:rbimpl_intern_const + +# Setting def->aliased bitfield non-atomically +race_top:method_definition_addref + +# Switching to setting up tracing. Likely other ractors should be stopped for this. +race_top:encoded_iseq_trace_instrument +race:rb_iseq_trace_set_all +race:rb_tracepoint_enable + +# GC enable/disable flag modifications race with object allocation flag reads +race_top:rb_gc_impl_gc_disable +race_top:rb_gc_impl_gc_enable diff --git a/misc/yjit_perf.py b/misc/yjit_perf.py new file mode 100755 index 0000000000..61434e5eb4 --- /dev/null +++ b/misc/yjit_perf.py @@ -0,0 +1,116 @@ +#!/usr/bin/env python3 +import os +import sys +from collections import Counter, defaultdict +import os.path + +# Aggregating cycles per symbol and dso +total_cycles = 0 +category_cycles = Counter() +detailed_category_cycles = defaultdict(Counter) +categories = set() + +def truncate_symbol(symbol, max_length=50): + """ Truncate the symbol name to a maximum length """ + return symbol if len(symbol) <= max_length else symbol[:max_length-3] + '...' + +def categorize_symbol(dso, symbol): + """ Categorize the symbol based on the defined criteria """ + if dso == 'sqlite3_native.so': + return '[sqlite3]' + elif 'SHA256' in symbol: + return '[sha256]' + elif symbol.startswith('[JIT] gen_send'): + return '[JIT send]' + elif symbol.startswith('[JIT]'): + return '[JIT code]' + elif '::' in symbol or symbol.startswith('yjit::') or symbol.startswith('_ZN4yjit'): + return '[YJIT compile]' + elif symbol.startswith('rb_vm_') or symbol.startswith('vm_') or symbol in { + "rb_call0", "callable_method_entry_or_negative", "invoke_block_from_c_bh", + "rb_funcallv_scope", "setup_parameters_complex", "rb_yield"}: + return '[interpreter]' + elif symbol.startswith('rb_hash_') or symbol.startswith('hash_'): + return '[rb_hash_*]' + elif symbol.startswith('rb_ary_') or symbol.startswith('ary_'): + return '[rb_ary_*]' + elif symbol.startswith('rb_str_') or symbol.startswith('str_'): + return '[rb_str_*]' + elif symbol.startswith('rb_sym') or symbol.startswith('sym_'): + return '[rb_sym_*]' + elif symbol.startswith('rb_st_') or symbol.startswith('st_'): + return '[rb_st_*]' + elif symbol.startswith('rb_ivar_') or 'shape' in symbol: + return '[ivars]' + elif 'match' in symbol or symbol.startswith('rb_reg') or symbol.startswith('onig'): + return '[regexp]' + elif 'alloc' in symbol or 'free' in symbol or 'gc' in symbol: + return '[GC]' + elif 'pthread' in symbol and 'lock' in symbol: + return '[pthread lock]' + else: + return symbol # Return the symbol itself for uncategorized symbols + +def process_event(event): + global total_cycles, category_cycles, detailed_category_cycles, categories + + full_dso = event.get("dso", "Unknown_dso") + dso = os.path.basename(full_dso) + symbol = event.get("symbol", "[unknown]") + cycles = event["sample"]["period"] + total_cycles += cycles + + category = categorize_symbol(dso, symbol) + category_cycles[category] += cycles + detailed_category_cycles[category][(dso, symbol)] += cycles + + if category.startswith('[') and category.endswith(']'): + categories.add(category) + +def trace_end(): + if total_cycles == 0: + return + + print("Aggregated Event Data:") + print("{:<20} {:<50} {:>20} {:>15}".format("[dso]", "[symbol or category]", "[top-most cycle ratio]", "[num cycles]")) + + for category, cycles in category_cycles.most_common(): + ratio = (cycles / total_cycles) * 100 + dsos = {dso for dso, _ in detailed_category_cycles[category]} + dso_display = next(iter(dsos)) if len(dsos) == 1 else "Multiple DSOs" + print("{:<20} {:<50} {:>20.2f}% {:>15}".format(dso_display, truncate_symbol(category), ratio, cycles)) + + # Category breakdown + for category in categories: + symbols = detailed_category_cycles[category] + category_total = sum(symbols.values()) + category_ratio = (category_total / total_cycles) * 100 + print(f"\nCategory: {category} ({category_ratio:.2f}%)") + print("{:<20} {:<50} {:>20} {:>15}".format("[dso]", "[symbol]", "[top-most cycle ratio]", "[num cycles]")) + for (dso, symbol), cycles in symbols.most_common(): + symbol_ratio = (cycles / category_total) * 100 + print("{:<20} {:<50} {:>20.2f}% {:>15}".format(dso, truncate_symbol(symbol), symbol_ratio, cycles)) + +# There are two ways to use this script: +# 1) perf script -s misc/yjit_perf.py -- native interface +# 2) perf script > perf.txt && misc/yjit_perf.py perf.txt -- hack, which doesn't require perf with Python support +# +# In both cases, __name__ is "__main__". The following code implements (2) when sys.argv is 2. +if __name__ == "__main__" and len(sys.argv) == 2: + if len(sys.argv) != 2: + print("Usage: yjit_perf.py <filename>") + sys.exit(1) + + with open(sys.argv[1], "r") as file: + for line in file: + # [Example] + # ruby 78207 3482.848465: 1212775 cpu_core/cycles:P/: 5c0333f682e1 [JIT] getlocal_WC_0+0x0 (/tmp/perf-78207.map) + row = line.split(maxsplit=6) + + period = row[3] # "1212775" + symbol, dso = row[6].split(" (") # "[JIT] getlocal_WC_0+0x0", "/tmp/perf-78207.map)\n" + symbol = symbol.split("+")[0] # "[JIT] getlocal_WC_0" + dso = dso.split(")")[0] # "/tmp/perf-78207.map" + + process_event({"dso": dso, "symbol": symbol, "sample": {"period": int(period)}}) + trace_end() |