pax_global_header00006660000000000000000000000064132134341120014504gustar00rootroot0000000000000052 comment=1963b428c08d74d3f60e4fe5fa50f4253506b47b scanf-1.0.0/000077500000000000000000000000001321343411200125745ustar00rootroot00000000000000scanf-1.0.0/.gitignore000066400000000000000000000001271321343411200145640ustar00rootroot00000000000000/.bundle/ /.yardoc /Gemfile.lock /_yardoc/ /coverage/ /doc/ /pkg/ /spec/reports/ /tmp/ scanf-1.0.0/.travis.yml000066400000000000000000000001461321343411200147060ustar00rootroot00000000000000sudo: false language: ruby rvm: - 2.3.5 - 2.4.2 - ruby-head before_install: gem install bundler scanf-1.0.0/Gemfile000066400000000000000000000001321321343411200140630ustar00rootroot00000000000000source 'https://rubygems.org' # Specify your gem's dependencies in scanf.gemspec gemspec scanf-1.0.0/LICENSE.txt000066400000000000000000000024021321343411200144150ustar00rootroot00000000000000Copyright (C) 1993-2013 Yukihiro Matsumoto. All rights reserved. Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met: 1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. 2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution. THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. scanf-1.0.0/README.md000066400000000000000000000054541321343411200140630ustar00rootroot00000000000000# scanf [![Build Status](https://travis-ci.org/ruby/scanf.svg?branch=master)](https://travis-ci.org/ruby/scanf) scanf is an implementation of the C function scanf(3), modified as necessary for Ruby compatibility. the methods provided are String#scanf, IO#scanf, and Kernel#scanf. Kernel#scanf is a wrapper around TDIN.scanf. IO#scanf can be used on any IO stream, including file handles and sockets. scanf can be called either with or without a block. Scanf scans an input string or stream according to a format, as described below in Conversions, and returns an array of matches between the format and the input. The format is defined in a string, and is similar (though not identical) to the formats used in Kernel#printf and Kernel#sprintf. The format may contain conversion specifiers, which tell scanf what form (type) each particular matched substring should be converted to (e.g., decimal integer, floating point number, literal string, etc.) The matches and conversions take place from left to right, and the conversions themselves are returned as an array. The format string may also contain characters other than those in the conversion specifiers. White space (blanks, tabs, or newlines) in the format string matches any amount of white space, including none, in the input. Everything else matches only itself. Scanning stops, and scanf returns, when any input character fails to match the specifications in the format string, or when input is exhausted, or when everything in the format string has been matched. All matches found up to the stopping point are returned in the return array (or yielded to the block, if a block was given). ## Installation Add this line to your application's Gemfile: ```ruby gem 'scanf' ``` And then execute: $ bundle Or install it yourself as: $ gem install scanf ## Usage ``` require 'scanf' # String#scanf and IO#scanf take a single argument, the format string array = a_string.scanf("%d%s") array = an_io.scanf("%d%s") # Kernel#scanf reads from STDIN array = scanf("%d%s") ``` ## Development After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment. To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org). ## Contributing Bug reports and pull requests are welcome on GitHub at https://github.com/ruby/scanf. ## License The gem is available as open source under the terms of the [2-Clause BSD License](https://opensource.org/licenses/BSD-2-Clause). scanf-1.0.0/Rakefile000066400000000000000000000003061321343411200142400ustar00rootroot00000000000000require "bundler/gem_tasks" require "rake/testtask" Rake::TestTask.new(:test) do |t| t.libs << "test" t.libs << "lib" t.test_files = FileList['test/**/test_*.rb'] end task :default => :test scanf-1.0.0/bin/000077500000000000000000000000001321343411200133445ustar00rootroot00000000000000scanf-1.0.0/bin/console000077500000000000000000000005241321343411200147350ustar00rootroot00000000000000#!/usr/bin/env ruby require "bundler/setup" require "scanf" # You can add fixtures and/or initialization code here to make experimenting # with your gem easier. You can also use a different console, if you like. # (If you use this, don't forget to add pry to your Gemfile!) # require "pry" # Pry.start require "irb" IRB.start(__FILE__) scanf-1.0.0/bin/setup000077500000000000000000000002031321343411200144250ustar00rootroot00000000000000#!/usr/bin/env bash set -euo pipefail IFS=$'\n\t' set -vx bundle install # Do any other automated setup that you need to do here scanf-1.0.0/lib/000077500000000000000000000000001321343411200133425ustar00rootroot00000000000000scanf-1.0.0/lib/scanf.rb000066400000000000000000000570001321343411200147630ustar00rootroot00000000000000# frozen_string_literal: false # scanf for Ruby # #-- # $Release Version: 1.1.2 $ # $Revision$ # $Id$ # $Author$ #++ # # == Description # # scanf is an implementation of the C function scanf(3), modified as necessary # for Ruby compatibility. # # the methods provided are String#scanf, IO#scanf, and # Kernel#scanf. Kernel#scanf is a wrapper around STDIN.scanf. IO#scanf # can be used on any IO stream, including file handles and sockets. # scanf can be called either with or without a block. # # Scanf scans an input string or stream according to a format, as # described below in Conversions, and returns an array of matches between # the format and the input. The format is defined in a string, and is # similar (though not identical) to the formats used in Kernel#printf and # Kernel#sprintf. # # The format may contain conversion specifiers, which tell scanf # what form (type) each particular matched substring should be converted # to (e.g., decimal integer, floating point number, literal string, # etc.) The matches and conversions take place from left to right, and # the conversions themselves are returned as an array. # # The format string may also contain characters other than those in the # conversion specifiers. White space (blanks, tabs, or newlines) in the # format string matches any amount of white space, including none, in # the input. Everything else matches only itself. # # Scanning stops, and scanf returns, when any input character fails to # match the specifications in the format string, or when input is # exhausted, or when everything in the format string has been # matched. All matches found up to the stopping point are returned in # the return array (or yielded to the block, if a block was given). # # # == Basic usage # # require 'scanf' # # # String#scanf and IO#scanf take a single argument, the format string # array = a_string.scanf("%d%s") # array = an_io.scanf("%d%s") # # # Kernel#scanf reads from STDIN # array = scanf("%d%s") # # == Block usage # # When called with a block, scanf keeps scanning the input, cycling back # to the beginning of the format string, and yields a new array of # conversions to the block every time the format string is matched # (including partial matches, but not including complete failures). The # actual return value of scanf when called with a block is an array # containing the results of all the executions of the block. # # str = "123 abc 456 def 789 ghi" # str.scanf("%d%s") { |num,str| [ num * 2, str.upcase ] } # # => [[246, "ABC"], [912, "DEF"], [1578, "GHI"]] # # == Conversions # # The single argument to scanf is a format string, which generally # includes one or more conversion specifiers. Conversion specifiers # begin with the percent character ('%') and include information about # what scanf should next scan for (string, decimal number, single # character, etc.). # # There may be an optional maximum field width, expressed as a decimal # integer, between the % and the conversion. If no width is given, a # default of `infinity' is used (with the exception of the %c specifier; # see below). Otherwise, given a field width of n for a given # conversion, at most n characters are scanned in processing # that conversion. Before conversion begins, most conversions skip # white space in the input string; this white space is not counted # against the field width. # # The following conversions are available. # # [%] # Matches a literal `%'. That is, `%%' in the format string matches a # single input `%' character. No conversion is done, and the resulting # '%' is not included in the return array. # # [d] # Matches an optionally signed decimal integer. # # [u] # Same as d. # # [i] # Matches an optionally signed integer. The integer is read in base # 16 if it begins with `0x' or `0X', in base 8 if it begins with `0', # and in base 10 other- wise. Only characters that correspond to the # base are recognized. # # [o] # Matches an optionally signed octal integer. # # [x, X] # Matches an optionally signed hexadecimal integer, # # [a, e, f, g, A, E, F, G] # Matches an optionally signed floating-point number. # # [s] # Matches a sequence of non-white-space character. The input string stops at # white space or at the maximum field width, whichever occurs first. # # [c] # Matches a single character, or a sequence of n characters if a # field width of n is specified. The usual skip of leading white # space is suppressed. To skip white space first, use an explicit space in # the format. # # [[] # Matches a nonempty sequence of characters from the specified set # of accepted characters. The usual skip of leading white space is # suppressed. This bracketed sub-expression is interpreted exactly like a # character class in a Ruby regular expression. (In fact, it is placed as-is # in a regular expression.) The matching against the input string ends with # the appearance of a character not in (or, with a circumflex, in) the set, # or when the field width runs out, whichever comes first. # # === Assignment suppression # # To require that a particular match occur, but without including the result # in the return array, place the assignment suppression flag, which is # the star character ('*'), immediately after the leading '%' of a format # specifier (just before the field width, if any). # # == scanf for Ruby compared with scanf in C # # scanf for Ruby is based on the C function scanf(3), but with modifications, # dictated mainly by the underlying differences between the languages. # # === Unimplemented flags and specifiers # # * The only flag implemented in scanf for Ruby is '*' (ignore # upcoming conversion). Many of the flags available in C versions of # scanf(3) have to do with the type of upcoming pointer arguments, and are # meaningless in Ruby. # # * The n specifier (store number of characters consumed so far in # next pointer) is not implemented. # # * The p specifier (match a pointer value) is not implemented. # # === Altered specifiers # # [o, u, x, X] # In scanf for Ruby, all of these specifiers scan for an optionally signed # integer, rather than for an unsigned integer like their C counterparts. # # === Return values # # scanf for Ruby returns an array of successful conversions, whereas # scanf(3) returns the number of conversions successfully # completed. (See below for more details on scanf for Ruby's return # values.) # # == Return values # # Without a block, scanf returns an array containing all the conversions # it has found. If none are found, scanf will return an empty array. An # unsuccessful match is never ignored, but rather always signals the end # of the scanning operation. If the first unsuccessful match takes place # after one or more successful matches have already taken place, the # returned array will contain the results of those successful matches. # # With a block scanf returns a 'map'-like array of transformations from # the block -- that is, an array reflecting what the block did with each # yielded result from the iterative scanf operation. (See "Block # usage", above.) # # == Current limitations and bugs # # When using IO#scanf under Windows, make sure you open your files in # binary mode: # # File.open("filename", "rb") # # so that scanf can keep track of characters correctly. # # Support for character classes is reasonably complete (since it # essentially piggy-backs on Ruby's regular expression handling of # character classes), but users are advised that character class testing # has not been exhaustive, and that they should exercise some caution # in using any of the more complex and/or arcane character class # idioms. # # == License and copyright # # Copyright:: (c) 2002-2003 David Alan Black # License:: Distributed on the same licensing terms as Ruby itself # # == Warranty disclaimer # # This software is provided "as is" and without any express or implied # warranties, including, without limitation, the implied warranties of # merchantability and fitness for a particular purpose. # # == Credits and acknowledgements # # scanf was developed as the major activity of the Austin Ruby Codefest # (Austin, Texas, August 2002). # # Principal author:: David Alan Black (mailto:dblack@superlink.net) # Co-author:: Hal Fulton (mailto:hal9000@hypermetrics.com) # Project contributors:: Nolan Darilek, Jason Johnston # # Thanks to Hal Fulton for hosting the Codefest. # # Thanks to Matz for suggestions about the class design. # # Thanks to Gavin Sinclair for some feedback on the documentation. # # The text for parts of this document, especially the Description and # Conversions sections, above, were adapted from the Linux Programmer's # Manual manpage for scanf(3), dated 1995-11-01. # # == Bugs and bug reports # # scanf for Ruby is based on something of an amalgam of C scanf # implementations and documentation, rather than on a single canonical # description. Suggestions for features and behaviors which appear in # other scanfs, and would be meaningful in Ruby, are welcome, as are # reports of suspicious behaviors and/or bugs. (Please see "Credits and # acknowledgements", above, for email addresses.) module Scanf # :stopdoc: # ==Technical notes # # ===Rationale behind scanf for Ruby # # The impetus for a scanf implementation in Ruby comes chiefly from the fact # that existing pattern matching operations, such as Regexp#match and # String#scan, return all results as strings, which have to be converted to # integers or floats explicitly in cases where what's ultimately wanted are # integer or float values. # # ===Design of scanf for Ruby # # scanf for Ruby is essentially a -to- converter. # # When scanf is called, a FormatString object is generated from the # format string ("%d%s...") argument. The FormatString object breaks the # format string down into atoms ("%d", "%5f", "blah", etc.), and from # each atom it creates a FormatSpecifier object, which it # saves. # # Each FormatSpecifier has a regular expression fragment and a "handler" # associated with it. For example, the regular expression fragment # associated with the format "%d" is "([-+]?\d+)", and the handler # associated with it is a wrapper around String#to_i. scanf itself calls # FormatString#match, passing in the input string. FormatString#match # iterates through its FormatSpecifiers; for each one, it matches the # corresponding regular expression fragment against the string. If # there's a match, it sends the matched string to the handler associated # with the FormatSpecifier. # # Thus, to follow up the "%d" example: if "123" occurs in the input # string when a FormatSpecifier consisting of "%d" is reached, the "123" # will be matched against "([-+]?\d+)", and the matched string will be # rendered into an integer by a call to to_i. # # The rendered match is then saved to an accumulator array, and the # input string is reduced to the post-match substring. Thus the string # is "eaten" from the left as the FormatSpecifiers are applied in # sequence. (This is done to a duplicate string; the original string is # not altered.) # # As soon as a regular expression fragment fails to match the string, or # when the FormatString object runs out of FormatSpecifiers, scanning # stops and results accumulated so far are returned in an array. class FormatSpecifier attr_reader :re_string, :matched_string, :conversion, :matched private def skip; /^\s*%\*/.match(@spec_string); end def extract_float(s) return nil unless s &&! skip if /\A(?[-+]?)0[xX](?\.\h+|\h+(?:\.\h*)?)[pP](?[-+]?\d+)/ =~ s f1, f2 = frac.split('.') f = f1.hex if f2 len = f2.length if len > 0 f += f2.hex / (16.0 ** len) end end (sign == ?- ? -1 : 1) * Math.ldexp(f, exp.to_i) elsif /\A([-+]?\d+)\.([eE][-+]\d+)/ =~ s ($1 << $2).to_f else s.to_f end end def extract_decimal(s); s.to_i if s &&! skip; end def extract_hex(s); s.hex if s &&! skip; end def extract_octal(s); s.oct if s &&! skip; end def extract_integer(s); Integer(s) if s &&! skip; end def extract_plain(s); s unless skip; end def nil_proc(s); nil; end public def to_s @spec_string end def count_space? /(?:\A|\S)%\*?\d*c|%\d*\[/.match(@spec_string) end def initialize(str) @spec_string = str h = '[A-Fa-f0-9]' @re_string, @handler = case @spec_string # %[[:...:]] when /%\*?(\[\[:[a-z]+:\]\])/ [ "(#{$1}+)", :extract_plain ] # %5[[:...:]] when /%\*?(\d+)(\[\[:[a-z]+:\]\])/ [ "(#{$2}{1,#{$1}})", :extract_plain ] # %[...] when /%\*?\[([^\]]*)\]/ yes = $1 if /^\^/.match(yes) then no = yes[1..-1] else no = '^' + yes end [ "([#{yes}]+)(?=[#{no}]|\\z)", :extract_plain ] # %5[...] when /%\*?(\d+)\[([^\]]*)\]/ yes = $2 w = $1 [ "([#{yes}]{1,#{w}})", :extract_plain ] # %i when /%\*?i/ [ "([-+]?(?:(?:0[0-7]+)|(?:0[Xx]#{h}+)|(?:[1-9]\\d*)))", :extract_integer ] # %5i when /%\*?(\d+)i/ n = $1.to_i s = "(" if n > 1 then s += "[1-9]\\d{1,#{n-1}}|" end if n > 1 then s += "0[0-7]{1,#{n-1}}|" end if n > 2 then s += "[-+]0[0-7]{1,#{n-2}}|" end if n > 2 then s += "[-+][1-9]\\d{1,#{n-2}}|" end if n > 2 then s += "0[Xx]#{h}{1,#{n-2}}|" end if n > 3 then s += "[-+]0[Xx]#{h}{1,#{n-3}}|" end s += "\\d" s += ")" [ s, :extract_integer ] # %d, %u when /%\*?[du]/ [ '([-+]?\d+)', :extract_decimal ] # %5d, %5u when /%\*?(\d+)[du]/ n = $1.to_i s = "(" if n > 1 then s += "[-+]\\d{1,#{n-1}}|" end s += "\\d{1,#{$1}})" [ s, :extract_decimal ] # %x when /%\*?[Xx]/ [ "([-+]?(?:0[Xx])?#{h}+)", :extract_hex ] # %5x when /%\*?(\d+)[Xx]/ n = $1.to_i s = "(" if n > 3 then s += "[-+]0[Xx]#{h}{1,#{n-3}}|" end if n > 2 then s += "0[Xx]#{h}{1,#{n-2}}|" end if n > 1 then s += "[-+]#{h}{1,#{n-1}}|" end s += "#{h}{1,#{n}}" s += ")" [ s, :extract_hex ] # %o when /%\*?o/ [ '([-+]?[0-7]+)', :extract_octal ] # %5o when /%\*?(\d+)o/ [ "([-+][0-7]{1,#{$1.to_i-1}}|[0-7]{1,#{$1}})", :extract_octal ] # %f when /%\*?[aefgAEFG]/ [ '([-+]?(?:0[xX](?:\.\h+|\h+(?:\.\h*)?)[pP][-+]?\d+|\d+(?![\d.])|\d*\.\d*(?:[eE][-+]?\d+)?))', :extract_float ] # %5f when /%\*?(\d+)[aefgAEFG]/ [ '(?=[-+]?(?:0[xX](?:\.\h+|\h+(?:\.\h*)?)[pP][-+]?\d+|\d+(?![\d.])|\d*\.\d*(?:[eE][-+]?\d+)?))' + "(\\S{1,#{$1}})", :extract_float ] # %5s when /%\*?(\d+)s/ [ "(\\S{1,#{$1}})", :extract_plain ] # %s when /%\*?s/ [ '(\S+)', :extract_plain ] # %c when /\s%\*?c/ [ "\\s*(.)", :extract_plain ] # %c when /%\*?c/ [ "(.)", :extract_plain ] # %5c (whitespace issues are handled by the count_*_space? methods) when /%\*?(\d+)c/ [ "(.{1,#{$1}})", :extract_plain ] # %% when /%%/ [ '(\s*%)', :nil_proc ] # literal characters else [ "(#{Regexp.escape(@spec_string)})", :nil_proc ] end @re_string = '\A' + @re_string end def to_re Regexp.new(@re_string,Regexp::MULTILINE) end def match(str) @matched = false s = str.dup s.sub!(/\A\s+/,'') unless count_space? res = to_re.match(s) if res @conversion = send(@handler, res[1]) @matched_string = @conversion.to_s @matched = true end res end def letter @spec_string[/%\*?\d*([a-z\[])/, 1] end def width @spec_string[/%\*?(\d+)/, 1]&.to_i end def mid_match? return false unless @matched cc_no_width = letter == '[' &&! width c_or_cc_width = (letter == 'c' || letter == '[') && width width_left = c_or_cc_width && (matched_string.size < width) return width_left || cc_no_width end end class FormatString attr_reader :string_left, :last_spec_tried, :last_match_tried, :matched_count, :space SPECIFIERS = 'diuXxofFeEgGscaA' REGEX = / # possible space, followed by... (?:\s* # percent sign, followed by... % # another percent sign, or... (?:%| # optional assignment suppression flag \*? # optional maximum field width \d* # named character class, ... (?:\[\[:\w+:\]\]| # traditional character class, or... \[[^\]]*\]| # specifier letter. [#{SPECIFIERS}])))| # or miscellaneous characters [^%\s]+/ix def initialize(str) @specs = [] @i = 1 s = str.to_s return unless /\S/.match(s) @space = true if /\s\z/.match(s) @specs.replace s.scan(REGEX).map {|spec| FormatSpecifier.new(spec) } end def to_s @specs.join('') end def prune(n=matched_count) n.times { @specs.shift } end def spec_count @specs.size end def last_spec @i == spec_count - 1 end def match(str) accum = [] @string_left = str @matched_count = 0 @specs.each_with_index do |spec,i| @i=i @last_spec_tried = spec @last_match_tried = spec.match(@string_left) break unless @last_match_tried @matched_count += 1 accum << spec.conversion @string_left = @last_match_tried.post_match break if @string_left.empty? end return accum.compact end end # :startdoc: end class IO #:stopdoc: # The trick here is doing a match where you grab one *line* # of input at a time. The linebreak may or may not occur # at the boundary where the string matches a format specifier. # And if it does, some rule about whitespace may or may not # be in effect... # # That's why this is much more elaborate than the string # version. # # For each line: # # Match succeeds (non-emptily) # and the last attempted spec/string sub-match succeeded: # # could the last spec keep matching? # yes: save interim results and continue (next line) # # The last attempted spec/string did not match: # # are we on the next-to-last spec in the string? # yes: # is fmt_string.string_left all spaces? # yes: does current spec care about input space? # yes: fatal failure # no: save interim results and continue # no: continue [this state could be analyzed further] # #:startdoc: # Scans the current string until the match is exhausted, # yielding each match as it is encountered in the string. # A block is not necessary though, as the results will simply # be aggregated into the final array. # # "123 456".block_scanf("%d") # # => [123, 456] # # If a block is given, the value from that is returned from # the yield is added to an output array. # # "123 456".block_scanf("%d") do |digit,| # the ',' unpacks the Array # digit + 100 # end # # => [223, 556] # # See Scanf for details on creating a format string. # # You will need to require 'scanf' to use IO#scanf. def scanf(str,&b) #:yield: current_match return block_scanf(str,&b) if b return [] unless str.size > 0 start_position = pos rescue 0 matched_so_far = 0 source_buffer = "" result_buffer = [] final_result = [] fstr = Scanf::FormatString.new(str) loop do if eof || (tty? &&! fstr.match(source_buffer)) final_result.concat(result_buffer) break end source_buffer << gets current_match = fstr.match(source_buffer) spec = fstr.last_spec_tried if spec.matched if spec.mid_match? result_buffer.replace(current_match) next end elsif (fstr.matched_count == fstr.spec_count - 1) if /\A\s*\z/.match(fstr.string_left) break if spec.count_space? result_buffer.replace(current_match) next end end final_result.concat(current_match) matched_so_far += source_buffer.size source_buffer.replace(fstr.string_left) matched_so_far -= source_buffer.size break if fstr.last_spec fstr.prune end begin seek(start_position + matched_so_far, IO::SEEK_SET) rescue Errno::ESPIPE end soak_up_spaces if fstr.last_spec && fstr.space return final_result end private def soak_up_spaces c = getc ungetc(c) if c until eof ||! c || /\S/.match(c.chr) c = getc end ungetc(c) if (c && /\S/.match(c.chr)) end def block_scanf(str) final = [] # Sub-ideal, since another FS gets created in scanf. # But used here to determine the number of specifiers. fstr = Scanf::FormatString.new(str) last_spec = fstr.last_spec begin current = scanf(str) break if current.empty? final.push(yield(current)) end until eof || fstr.last_spec_tried == last_spec return final end end class String # :section: scanf # # You will need to require 'scanf' to use these methods # Scans the current string. If a block is given, it # functions exactly like block_scanf. # # arr = "123 456".scanf("%d%d") # # => [123, 456] # # require 'pp' # # "this 123 read that 456 other".scanf("%s%d%s") {|m| pp m} # # # ["this", 123, "read"] # # ["that", 456, "other"] # # => [["this", 123, "read"], ["that", 456, "other"]] # # See Scanf for details on creating a format string. # # You will need to require 'scanf' to use String#scanf def scanf(fstr,&b) #:yield: current_match if b block_scanf(fstr,&b) else fs = if fstr.is_a? Scanf::FormatString fstr else Scanf::FormatString.new(fstr) end fs.match(self) end end # Scans the current string until the match is exhausted # yielding each match as it is encountered in the string. # A block is not necessary as the results will simply # be aggregated into the final array. # # "123 456".block_scanf("%d") # # => [123, 456] # # If a block is given, the value from that is returned from # the yield is added to an output array. # # "123 456".block_scanf("%d) do |digit,| # the ',' unpacks the Array # digit + 100 # end # # => [223, 556] # # See Scanf for details on creating a format string. # # You will need to require 'scanf' to use String#block_scanf def block_scanf(fstr) #:yield: current_match fs = Scanf::FormatString.new(fstr) str = self.dup final = [] begin current = str.scanf(fs) final.push(yield(current)) unless current.empty? str = fs.string_left end until current.empty? || str.empty? return final end end module Kernel private # Scans STDIN for data matching +format+. See IO#scanf for details. # # See Scanf for details on creating a format string. # # You will need to require 'scanf' to use Kernel#scanf. def scanf(format, &b) #:doc: STDIN.scanf(format ,&b) end end scanf-1.0.0/scanf.gemspec000066400000000000000000000016041321343411200152340ustar00rootroot00000000000000# coding: utf-8 # frozen_string_literal: true Gem::Specification.new do |spec| spec.name = "scanf" spec.version = "1.0.0" spec.date = '2017-12-11' spec.authors = ["David Alan Black"] spec.email = ['dblack@superlink.net'] spec.summary = "scanf is an implementation of the C function scanf(3)." spec.description = "scanf is an implementation of the C function scanf(3)." spec.homepage = "https://github.com/ruby/scanf" spec.license = "BSD-2-Clause" spec.files = ["lib/scanf.rb"] spec.bindir = "exe" spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) } spec.require_paths = ["lib"] spec.required_ruby_version = ">= 2.3.0" spec.add_development_dependency "bundler", "~> 1.14" spec.add_development_dependency "rake", "~> 10.0" spec.add_development_dependency "test-unit" end scanf-1.0.0/test/000077500000000000000000000000001321343411200135535ustar00rootroot00000000000000scanf-1.0.0/test/scanf/000077500000000000000000000000001321343411200146455ustar00rootroot00000000000000scanf-1.0.0/test/scanf/data.txt000066400000000000000000000000651321343411200163200ustar00rootroot00000000000000this is 33 a fun little input file with characters scanf-1.0.0/test/scanf/test_scanf.rb000066400000000000000000000274311321343411200173320ustar00rootroot00000000000000# frozen_string_literal: false # $Id$ # # scanf for Ruby # # Unit tests # require 'scanf.rb' require 'test/unit' require 'tempfile' # Comment out either of these lines to skip those tests. class TestStringScanf < Test::Unit::TestCase;end class TestIOScanf < Test::Unit::TestCase;end module ScanfTests def tests [ # Scratchpad [ "%2[a]", "nbc", []], [ "%*d %*3d %*s", "123 +456 abc", [] ], [ "%d%c", "123 x", [ 123, " " ] ], [ "%d%c", "123x", [ 123, "x" ] ], [ "%d %c", "123x", [ 123, "x" ] ], [ "%d %c", "123 x", [ 123, "x" ] ], # Testing failures [ "%x", "x", [] ], [ "%2x", "x", [] ], [ "%i", "x", [] ], # ]; end; def nothing; [ [ "%2i", "x", [] ], [ "%2o", "x", [] ], [ "%d", "x", [] ], [ "%2d", "x", [] ], [ "%3d", "+x3", [] ], [ "%d%[abc]", "eabc", [] ], [ "%d\n%[abc]", "\neabc", [] ], [ "%d%[^abc]", "ghiabc", [ ] ], [ "%d%[abc]", "abc", [] ], [ "%d%s", "", [] ], [ "%d%s", "blah 123 string", [] ], [ "%[\n]", "abc\n", [] ], [ "%f", "x", [] ], [ "%f", "z", [] ], [ "%f", "z3.2534", [] ], [ "", "", [] ], [ "", "abc 123", [] ], [ '%[^\\w]%c', "a...1", [] ], # Testing 'x' [ "%3x", "0xz", [0] ], # Testing 'i' [ "%3i", "097", [0] ], [ "%3i", "0xz", [0] ], [ "%1i", "3", [ 3 ] ], [ "%2i", "07", [ 7 ] ], [ "%2i", "0a", [ 0 ] ], # Testing 'c' [ "%3c", "abc", [ "abc" ] ], [ "%3c", "a\nb", [ "a\nb" ] ], [ "%3c", "a\nbcd", [ "a\nb" ] ], [ "%c\n\n", "x\n\n", [ "x" ] ], [ "%c", "\n", [ "\n" ] ], [ "%c", "x\n", [ "x" ] ], [ "%2c", " 123", [" 1"] ], [ " %c", " x", ["x"] ], [ "%c", " x", [" "] ], [ "%c", "123", ["1"] ], [ "%2c", "123", ["12"] ], [ "%5c", "a\nb\n\n", [ "a\nb\n\n" ] ], [ "%6c", "a\nb\n\nx", [ "a\nb\n\nx" ] ], [ "%5c", "ab\ncd", [ "ab\ncd" ] ], # Testing 'o' [ "%3o", "0xz", [0] ], # Testing 'd' [ "%d", "\n123", [ 123 ] ], [ "%d", "\n\n123", [ 123 ] ], [ "%1d", "2", [2] ], # Mixed tests # Includes: # whitespace/newline # mixed integer bases # various mixed specifiers [ "%[^\\w]%c", "...1", [ "...", "1"] ], [ "%[abc\n]%d", "a\n\nb\n\nc 123", [ "a\n\nb\n\nc", 123 ] ], [ "%[abc\n]%d", "a\n\nb\n\nc \t 123", [ "a\n\nb\n\nc", 123 ] ], [ "%[abc\t]%d", "a\t\tb\t\tc 123", [ "a\t\tb\t\tc", 123 ] ], [ "%d%3[abc\n]", "123a\nbeaab", [ 123, "a\nb" ] ], [ "%d%20c", "42 is the key", [ 42, " is the key" ] ], [ "%d %20c", "42 is the key", [ 42, "is the key" ] ], [ "%d%3[^abc\n]%d", "123de\nf123", [ 123, "de" ] ], [ "%d %4c", "3abc", [ 3, "abc" ] ], [ "%f%d\n%[abc]", "1\neabc", [1.0] ], [ "%d%3[abc]", "123aaab", [ 123, "aaa" ] ], [ "%d%3[abc]", "123 aaab", [ 123 ] ], [ "%d%3[abc]", "123aeaab", [ 123, "a" ] ], [ "%d%[^abc]", "123defabc", [123, "def" ] ], [ "%d%3[^abc]", "123defdef", [ 123, "def" ] ], [ "%d%3[^abc] ", "123defdef ", [ 123, "def" ] ], [ "%d%3[^abc]ghi", "123defghi", [ 123, "def" ] ], [ "%d%3[^abc]", "123adefdef", [ 123 ] ], [ "%d%3[^abc]", "123deafdef", [ 123, "de" ] ], [ "%d%3[^abc\n]", "123de\nf", [ 123, "de" ] ], [ "%s%c%c%s", "abc\n\ndef", ["abc", "\n","\n", "def" ] ], [ "%c%d", "\n\n123", [ "\n",123 ] ], [ "%s%c%d", "abc\n123", [ "abc", "\n", 123 ] ], [ "%s%c%d", "abc\n\n123", [ "abc", "\n", 123 ] ], [ "%c%d", "\t\n123", [ "\t",123 ] ], [ "%s%c%d", "abc\t\n123", [ "abc", "\t", 123 ] ], [ "%3c%d", "abc123", [ "abc", 123 ] ], [ "%3c\n%d", "abc123", [ "abc", 123 ] ], [ "%3c\n%d", "abc 123", [ "abc", 123 ] ], [ "%3c %d", "abc123", [ "abc", 123 ] ], [ "%3c\t%d", "abc \n 123", [ "abc", 123 ] ], [ "%3c\t%d", "abc \n 123 ", [ "abc", 123 ] ], [ "%3c%d", "a\nb123", [ "a\nb", 123 ] ], [ "%f%3c", "1.2x\ny", [ 1.2, "x\ny"] ], [ "%d\n%d\n%d", "123 456 789", [ 123,456,789 ] ], [ "%d\n%i%2d%x\n%d", "123 0718932", [ 123, 071, 89, 0x32] ], [ "%c\n%c", "x y", [ "x", "y" ] ], [ "%c\t%c", "x y", [ "x", "y" ] ], [ "%s\n%s", "x y", [ "x", "y" ] ], [ "%s%s\n", "x y", [ "x", "y" ] ], [ "%c\n\n%c", "x\n\ny", [ "x", "y" ] ], [ "%s%d%d", "abc\n123\n456", [ "abc", 123, 456 ] ], [ "%3s%c%3c%d", "1.2x\n\ny123", [ "1.2", "x", "\n\ny", 123 ] ], [ "%c\n%c", "x\n\ny", [ "x", "y" ] ], [ "%c %c", "x\n\ny", [ "x", "y" ] ], [ "%s\n\n%c", "x\n\ny", [ "x", "y" ] ], [ "%s\n\n%s", "x\n\ny", [ "x", "y" ] ], [ "%d\n\n%d", "23\n\n45", [ 23, 45 ] ], [ "%d\n%d", "23\n\n45", [ 23, 45 ] ], [ "%c\n\n%c", "x y", [ "x", "y" ] ], [ "%c%c", "x\n\ny", [ "x", "\n" ] ], [ "%c%c", "x\n", [ "x", "\n" ] ], [ "%d%c%c%d", "345 678", [ 345, " ", " ", 678] ], [ "%d %c%s", "123 x hello", [123, "x", "hello"] ], [ "%d%2c", "654 123", [654," 1"] ], [ "%5c%s", "a\nb\n\nxyz", [ "a\nb\n\n","xyz" ] ], [ "%s%[ xyz]%d", "hello x 32", ["hello", " x ", 32] ], [ "%5s%8[a-z]%d", "helloblahblah 32", ["hello", "blahblah", 32] ], [ '%s%[abcde\\s]%d', "hello badea 32", ["hello", " badea ", 32] ], [ '%d%[\\s]%c', "123 \n\t X", [ 123," \n\t ", "X"] ], [ "%4s%2c%c", "1.2x\n\ny", [ "1.2x", "\n\n","y"] ], [ "%f%c %3c%d", "1.2x\n\ny123", [ 1.2, "x", "y12", 3 ] ], [ "%s%5c", "abc ab\ncd", [ "abc", " ab\nc" ] ], [ "%5c%f", "ab\ncd1.2", [ "ab\ncd",1.2 ] ], [ "%5c%c", "ab\ncd1", [ "ab\ncd","1" ] ], [ "%f%c%2c%d", "1.2x\ny123", [ 1.2, "x", "\ny", 123 ] ], [ "%f%c%3c", "1.2x\ny123", [ 1.2, "x", "\ny1"] ], [ "%s\n%s", "blah\n\nand\nmore stuff", [ "blah", "and" ] ], [ "%o%d%x", "21912a3", [ "21".oct, 912, "a3".hex ] ], [ "%3o%4d%3x", "21912a3", [ "21".oct, 912, "a3".hex ] ], [ "%3o%4d%5x", "2191240xa3", [ "21".oct, 9124, "a3".hex ] ], [ "%3d%3x", "12abc", [12, "abc".hex] ], [ "%s%i%d", "hello +0xdef 123", [ "hello", "def".hex, 123] ], [ "%s%i%d", "hello -0xdef 123", [ "hello", -"def".hex, 123] ], [ "%s%i%i%i%i", "hello 012 -012 100 1", [ "hello", 10, -10, 100, 1 ] ], [ "%s%i%i%i%i", "hello 012 0x12 100 1", [ "hello", 10, 18, 100, 1 ] ], [ "%s%5i%3i%4i", "hello 0x123 123 0123", [ "hello", "0x123".hex, 123,"0123".oct] ], [ "%s%3i%4i", "hello 1230123", [ "hello", 123,"0123".oct] ], [ "%s%3i", "hello 1230", [ "hello", 123] ], [ "%s%5x%d", "hello 0xdef 123", [ "hello", "def".hex, 123] ], [ "%s%6x%d", "hello +0xdef 123", [ "hello", "def".hex, 123] ], [ "%s%6x%d", "hello -0xdef 123", [ "hello", -"def".hex, 123] ], [ "%s%4x%d", "hello -def 123", [ "hello", -"def".hex, 123] ], [ "%s%3x%d", "hello def 123", [ "hello", "def".hex, 123] ], [ "%s%x%d", "hello -def 123", [ "hello", -"def".hex, 123] ], [ "%s%x%d", "hello -0xdef 123", [ "hello", -"def".hex, 123] ], [ "%s%x%d", "hello 0xdef 123", [ "hello", "def".hex, 123] ], [ "%s%d%x%s", "hello 123 abc def", [ "hello", 123, "abc".hex, "def"] ], [ "%s%d%o%d", "hello 012 012 100", [ "hello", 12, 10, 100 ] ], [ "%s%d%o%d", "hello 012 -012 100", [ "hello", 12, -10, 100 ] ], [ "%s%o%x%d", "hello 012 0x12 100", [ "hello", 10, 18, 100 ] ], [ "%s%d%o%d", "hello 012 +01288", [ "hello", 12, 10, 88 ] ], [ "%f %d %s", "12.3e23 45 string", ["12.3e23".to_f, 45, "string"] ], [ "%f %d %s", "12.3e+23 45 string", ["12.3e23".to_f, 45, "string"] ], [ "%f %d %s", "12.3e-23 45 string", ["12.3e-23".to_f, 45, "string"] ], [ "%f %d %s", "-12.3e-23 45 string", ["-12.3e-23".to_f, 45, "string"] ], [ "%f %d %s", "12.e23 45 string", ["12.e23".to_f, 45, "string"] ], [ "%5f %d %s", "1.2e23 string", ["1.2e2".to_f, 3, "string"] ], [ "%5f%d %s", "1.2e23 string", ["1.2e2".to_f, 3, "string"] ], [ "%5f%d %d %s", "1.2e23 45 string", ["1.2e2".to_f, 3, 45, "string"] ], [ "%6f %d %d %s", "+1.2e23 45 string", ["1.2e2".to_f, 3, 45, "string"] ], [ "%d %d", "123 \n 345", [123, 345] ], [ "%d %*d", "123 \n 345", [123] ], [ "%d %3d789", "123 +45789", [123, 45] ], [ "%d %3d%d", "123 +456789", [123, 45, 6789] ], [ "%d %3dabc", "123 456abc", [123, 456] ], [ "%d %s", "123abc", [123, "abc"] ], [ "%d%s %s", "123 abc def", [123, "abc", "def"] ], [ "%s%s", "abc123 def", ["abc123", "def"] ], [ "%s%s %s", "123 abc def", ["123", "abc", "def"] ], [ "%s%%%s", "abc % def", ["abc", "def"] ], [ "%d %3d %s", "+123 456abc", [123, 456, "abc"] ], [ "%d %3d %s", "123 456abc", [123, 456, "abc"] ], [ "%d %3d %s", "123 +456 abc", [123, 45, "6"] ], [ "%d %3d %s", "-123-456abc", [-123, -45, "6abc"] ], [ "%dabc%d", "123abc345", [123, 345] ], [ "%d%5s%d", "123 abcde12", [123, "abcde", 12] ], [ "%5d%5s%5d", "12345abcde67890", [12345, "abcde", 67890] ], [ "%5d%*5s%5d", "12345abcde67890", [12345, 67890] ], [ " 12345%5s%5d", "12345abcde67890", [ "abcde", 67890] ], [ "%5dabcde%5d", "12345abcde67890", [ 12345, 67890] ], [ "%s%%%*s", "abc % def", ["abc"] ], [ "%*6s %d", "string 123", [123] ], [ "%d %*3d %s", "-123-456abc", [-123, "6abc"] ], [ "%d%s", "123", [123] ], [ "%s%d", "abc", ["abc"] ], [ "%f%x", "3.2e45x", ["3.2e45x".to_f] ], [ "%*5f%d %d %s", "1.2e23 45 string", [3, 45, "string"] ], [ "%5f%*d %d %s", "1.2e23 45 string", ["1.2e2".to_f, 45, "string"] ], [ "%*5f%*d %*d %s", "1.2e23 45 string", ["string"] ], [ "%f %*d %s", "12.e23 45 string", ["12.e23".to_f, "string"] ], [ "%s %f %s %d %x%c%c%c%c", "float: 1.2e23 dec/hex: 135a23 abc", ["float:", "1.2e23".to_f, "dec/hex:", 135, "a23".hex, " ", "a", "b", "c" ] ], # Testing 's' [ "%s\n", "blah\n\n\n", [ "blah" ] ], # Testing '[' [ "%[a\nb]", "a\nb", [ "a\nb" ] ], [ "%[abc]", "acb", [ "acb" ] ], [ "%[abc\n]", "a\nb", [ "a\nb" ] ], [ "%[^abc]", "defabc", [ "def" ] ], [ "%[-abc]", "abc-cba", [ "abc-cba" ] ], [ "%[\n]", "\n", [ "\n" ] ], [ "%[\n]", "\nabc", [ "\n" ] ], [ "%[\n\t]", "\t\n", [ "\t\n" ] ], [ "%[a-f]", "abczef", [ "abc" ] ], [ "%d%3[[:lower:]] %f", "123ade1.2", [ 123,"ade",1.2 ] ], [ "%d%3[[:lower:]] %f", "123ad1.2", [ 123,"ad",1.2 ] ], [ "%d%3[[:lower:]] %f", "123 ad1.2", [ 123 ] ], [ "%d%[[:lower:]]", "123abcdef1.2", [ 123, "abcdef" ] ], [ "%[[:lower:]]%d", "abcdef123", [ "abcdef", 123 ] ], [ "%[[:digit:]]%[[:alpha:]]", "123abcdef", [ "123", "abcdef" ] ], [ "%[[:digit:]]%d", "123 123", [ "123", 123 ] ], [ "%[[:upper:]]", "ABCdefGHI", [ "ABC" ] ], # Testing 'f' [ "%2f", "x", [] ], [ "%F", "1.23e45", [1.23e+45] ], [ "%e", "3.25ee", [3.25] ], [ "%E", "3..25", [3.0] ], [ "%g", "+3.25", [3.25] ], [ "%G", "+3.25e2", [325.0] ], [ "%f", "3.z", [3.0] ], [ "%a", "0X1P+10", [1024.0] ], [ "%a", "0X1P10", [1024.0] ], [ "%A", "0x1.deadbeefp+99", [1.1851510441583988e+30] ], # Testing embedded matches including literal '[' behavior [",%d,%f", ",10,1.1", [10,1.1] ], [" ,%d,%f", " ,10,1.1", [10,1.1] ], ["[%d,%f", "[10,1.1", [10,1.1] ], [" [%d,%f", " [10,1.1", [10,1.1] ], ] end def each_test self.tests.each do |test| format, string, = test yield test, "#{string.dump}(#{format.dump})" end end end class TestStringScanf include Scanf extend ScanfTests self.each_test do |test, i| define_method("test_#{i}") do || assert_equal(test[2], test[1].scanf(test[0])) end end end class TestIOScanf include Scanf extend ScanfTests self.each_test do |test, i| define_method("test_#{i}") do || Tempfile.create("iotest.dat") do |fh| fh.print test[1] fh.rewind assert_equal(test[2], fh.scanf(test[0])) end end end end scanf-1.0.0/test/scanf/test_scanfblocks.rb000066400000000000000000000033401321343411200205210ustar00rootroot00000000000000# frozen_string_literal: false # $Id$ # # scanf for Ruby # # Some not very comprehensive tests of block behavior. require 'test/unit' require 'scanf' require 'tmpdir' class TestScanfBlock < Test::Unit::TestCase def setup @str = <<-EOS Beethoven 1770 Bach 1685 Handel 1685 Scarlatti 1685 Brahms 1833 EOS end alias set_up setup def test_str1 res = @str.scanf("%s%d") { |name, year| "#{name} was born in #{year}." } assert_equal(res, [ "Beethoven was born in 1770.", "Bach was born in 1685.", "Handel was born in 1685.", "Scarlatti was born in 1685.", "Brahms was born in 1833." ]) end def test_str2 names = @str.scanf("%s%d") { |name, year| name.upcase } assert_equal(names, ["BEETHOVEN", "BACH", "HANDEL", "SCARLATTI", "BRAHMS"]) end def test_str3 assert_equal("".scanf("%d%f%s") {}, []) end def test_str4 assert_equal("abc".scanf("%d%f%s") {}, []) end def test_str5 assert_equal("abc".scanf("") {}, []) end def test_io1 fn = "#{Dir.tmpdir}/iotest.dat.#{$$}" File.open(fn, "w") { |fh| fh.puts(@str) } fh = File.open(fn, "rb") res = fh.scanf("%s%d") { |name, year| "#{name} was born in #{year}." } assert_equal( [ "Beethoven was born in 1770.", "Bach was born in 1685.", "Handel was born in 1685.", "Scarlatti was born in 1685.", "Brahms was born in 1833." ],res) fh.close ensure File.delete(fn) end def test_io2 fn = "#{Dir.tmpdir}/iotest.dat.#{$$}" File.open(fn, "w").close fh = File.open(fn,"rb") assert_equal(fh.scanf("") {}, []) fh.seek(0) assert_equal(fh.scanf("%d%f%s") {}, []) fh.close ensure File.delete(fn) end end scanf-1.0.0/test/scanf/test_scanfio.rb000066400000000000000000000006451321343411200176600ustar00rootroot00000000000000# frozen_string_literal: false # $Id$ # # scanf for Ruby # # Ad hoc tests of IO#scanf (needs to be expanded) require "scanf" class TestScanfIO < Test::Unit::TestCase def test_io fh = File.new(File.join(File.dirname(__FILE__), "data.txt"), "r") assert_equal(0, fh.pos) assert_equal(["this", "is"], fh.scanf("%s%s")) assert_equal([33, "little"], fh.scanf("%da fun%s")) ensure fh.close end end