diff options
Diffstat (limited to 'lib/shellwords.rb')
| -rw-r--r-- | lib/shellwords.rb | 107 |
1 files changed, 73 insertions, 34 deletions
diff --git a/lib/shellwords.rb b/lib/shellwords.rb index c3586d29fa..20a85ed9d2 100644 --- a/lib/shellwords.rb +++ b/lib/shellwords.rb @@ -1,15 +1,17 @@ +# frozen-string-literal: true ## # == Manipulates strings like the UNIX Bourne shell # # This module manipulates strings according to the word parsing rules # of the UNIX Bourne shell. # -# The shellwords() function was originally a port of shellwords.pl, -# but modified to conform to POSIX / SUSv3 (IEEE Std 1003.1-2001 [1]). +# The <tt>shellwords()</tt> function was originally a port of shellwords.pl, but +# modified to conform to {the Shell & Utilities volume of the IEEE Std 1003.1-2008, 2016 +# Edition}[http://pubs.opengroup.org/onlinepubs/9699919799/utilities/contents.html] # # === Usage # -# You can use shellwords to parse a string into a Bourne shell friendly Array. +# You can use Shellwords to parse a string into a Bourne shell friendly Array. # # require 'shellwords' # @@ -22,28 +24,37 @@ # argv = "see how they run".shellsplit # argv #=> ["see", "how", "they", "run"] # -# Be careful you don't leave a quote unmatched. +# They treat quotes as special characters, so an unmatched quote will +# cause an ArgumentError. # # argv = "they all ran after the farmer's wife".shellsplit -# #=> ArgumentError: Unmatched double quote: ... +# #=> ArgumentError: Unmatched quote: ... # -# In this case, you might want to use Shellwords.escape, or it's alias -# String#shellescape. +# Shellwords also provides methods that do the opposite. +# Shellwords.escape, or its alias, String#shellescape, escapes +# shell metacharacters in a string for use in a command line. # -# This method will escape the String for you to safely use with a Bourne shell. +# filename = "special's.txt" # -# argv = Shellwords.escape("special's.txt") -# argv #=> "special\\s.txt" -# system("cat " + argv) +# system("cat -- #{filename.shellescape}") +# # runs "cat -- special\\'s.txt" +# +# Note the '--'. Without it, cat(1) will treat the following argument +# as a command line option if it starts with '-'. It is guaranteed +# that Shellwords.escape converts a string to a form that a Bourne +# shell will parse back to the original string, but it is the +# programmer's responsibility to make sure that passing an arbitrary +# argument to a command does no harm. # # Shellwords also comes with a core extension for Array, Array#shelljoin. # -# argv = %w{ls -lta lib} -# system(argv.shelljoin) +# dir = "Funny GIFs" +# argv = %W[ls -lta -- #{dir}] +# system(argv.shelljoin + " | less") +# # runs "ls -lta -- Funny\\ GIFs | less" # -# You can use this method to create an escaped string out of an array of tokens -# separated by a space. In this example we'll use the literal shortcut for -# Array.new. +# You can use this method to build a complete command line out of an +# array of arguments. # # === Authors # * Wakou Aoyama @@ -51,32 +62,53 @@ # # === Contact # * Akinori MUSHA <knu@iDaemons.org> (current maintainer) -# -# === Resources -# -# 1: {IEEE Std 1003.1-2004}[http://pubs.opengroup.org/onlinepubs/009695399/toc.htm] module Shellwords + # The version number string. + VERSION = "0.2.2" + # Splits a string into an array of tokens in the same way the UNIX # Bourne shell does. # # argv = Shellwords.split('here are "two words"') # argv #=> ["here", "are", "two words"] # + # +line+ must not contain NUL characters because of nature of + # +exec+ system call. + # + # Note, however, that this is not a command line parser. Shell + # metacharacters except for the single and double quotes and + # backslash are not treated as such. + # + # argv = Shellwords.split('ruby my_prog.rb | less') + # argv #=> ["ruby", "my_prog.rb", "|", "less"] + # # String#shellsplit is a shortcut for this function. # # argv = 'here are "two words"'.shellsplit # argv #=> ["here", "are", "two words"] def shellsplit(line) words = [] - field = '' - line.scan(/\G\s*(?>([^\s\\\'\"]+)|'([^\']*)'|"((?:[^\"\\]|\\.)*)"|(\\.?)|(\S))(\s|\z)?/m) do + field = String.new + line.scan(/\G\s*(?>([^\0\s\\\'\"]+)|'([^\0\']*)'|"((?:[^\0\"\\]|\\[^\0])*)"|(\\[^\0]?)|(\S))(\s|\z)?/m) do |word, sq, dq, esc, garbage, sep| - raise ArgumentError, "Unmatched double quote: #{line.inspect}" if garbage - field << (word || sq || (dq || esc).gsub(/\\(.)/, '\\1')) + if garbage + b = $~.begin(0) + line = $~[0] + line = "..." + line if b > 0 + raise ArgumentError, "#{garbage == "\0" ? 'Nul character' : 'Unmatched quote'} at #{b}: #{line}" + end + # 2.2.3 Double-Quotes: + # + # The <backslash> shall retain its special meaning as an + # escape character only when followed by one of the following + # characters when considered special: + # + # $ ` " \ <newline> + field << (word || sq || (dq && dq.gsub(/\\([$`"\\\n])/, '\\1')) || esc.gsub(/\\(.)/, '\\1')) if sep words << field - field = '' + field = String.new end end words @@ -94,6 +126,9 @@ module Shellwords # command line. +str+ can be a non-string object that responds to # +to_s+. # + # +str+ must not contain NUL characters because of nature of +exec+ + # system call. + # # Note that a resulted string should be used unquoted and is not # intended for use in double quotes nor in single quotes. # @@ -107,7 +142,7 @@ module Shellwords # # # Search files in lib for method definitions # pattern = "^[ \t]*def " - # open("| grep -Ern #{pattern.shellescape} lib") { |grep| + # open("| grep -Ern -e #{pattern.shellescape} lib") { |grep| # grep.each_line { |line| # file, lineno, matched_line = line.split(':', 3) # # ... @@ -117,24 +152,27 @@ module Shellwords # It is the caller's responsibility to encode the string in the right # encoding for the shell environment where this string is used. # - # Multibyte characters are treated as multibyte characters, not bytes. + # Multibyte characters are treated as multibyte characters, not as bytes. # # Returns an empty quoted String if +str+ has a length of zero. def shellescape(str) str = str.to_s # An empty argument will be skipped, so return empty quotes. - return "''" if str.empty? + return "''".dup if str.empty? + + # Shellwords cannot contain NUL characters. + raise ArgumentError, "NUL character" if str.index("\0") str = str.dup - # Treat multibyte characters as is. It is caller's responsibility + # Treat multibyte characters as is. It is the caller's responsibility # to encode the string in the right encoding for the shell # environment. - str.gsub!(/([^A-Za-z0-9_\-.,:\/@\n])/, "\\\\\\1") + str.gsub!(/[^A-Za-z0-9_\-.,:+\/@\n]/, "\\\\\\&") # A LF cannot be escaped with a backslash because a backslash + LF - # combo is regarded as line continuation and simply ignored. + # combo is regarded as a line continuation and simply ignored. str.gsub!(/\n/, "'\n'") return str @@ -149,8 +187,9 @@ module Shellwords # Builds a command line string from an argument list, +array+. # # All elements are joined into a single string with fields separated by a - # space, where each element is escaped for Bourne shell and stringified using - # +to_s+. + # space, where each element is escaped for the Bourne shell and stringified + # using +to_s+. + # See also Shellwords.shellescape. # # ary = ["There's", "a", "time", "and", "place", "for", "everything"] # argv = Shellwords.join(ary) @@ -206,7 +245,7 @@ class Array # array.shelljoin => string # # Builds a command line string from an argument list +array+ joining - # all elements escaped for Bourne shell and separated by a space. + # all elements escaped for the Bourne shell and separated by a space. # # See Shellwords.shelljoin for details. def shelljoin |