File: escape.rb

package info (click to toggle)
libescape-ruby 0.2-1
  • links: PTS
  • area: main
  • in suites: lenny, squeeze, wheezy
  • size: 344 kB
  • ctags: 109
  • sloc: ruby: 288; makefile: 54
file content (302 lines) | stat: -rw-r--r-- 10,497 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
# escape.rb - escape/unescape library for several formats
#
# Copyright (C) 2006,2007 Tanaka Akira  <akr@fsij.org>
# 
# 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.
#  3. The name of the author may not be used to endorse or promote products
#     derived from this software without specific prior written permission.
# 
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 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.

# Escape module provides several escape functions.
# * URI
# * HTML
# * shell command
module Escape
  module_function

  class StringWrapper
    class << self
      alias new_no_dup new
      def new(str)
        new_no_dup(str.dup)
      end
    end

    def initialize(str)
      @str = str
    end

    def to_s
      @str.dup
    end

    def inspect
      "\#<#{self.class}: #{@str}>"
    end

    def ==(other)
      other.class == self.class && @str == other.instance_variable_get(:@str)
    end
    alias eql? ==

    def hash
      @str.hash
    end
  end

  class ShellEscaped < StringWrapper
  end

  # Escape.shell_command composes
  # a sequence of words to
  # a single shell command line.
  # All shell meta characters are quoted and
  # the words are concatenated with interleaving space.
  # It returns an instance of ShellEscaped.
  #
  #  Escape.shell_command(["ls", "/"]) #=> #<Escape::ShellEscaped: ls />
  #  Escape.shell_command(["echo", "*"]) #=> #<Escape::ShellEscaped: echo '*'>
  #
  # Note that system(*command) and
  # system(Escape.shell_command(command)) is roughly same.
  # There are two exception as follows.
  # * The first is that the later may invokes /bin/sh.
  # * The second is an interpretation of an array with only one element: 
  #   the element is parsed by the shell with the former but
  #   it is recognized as single word with the later.
  #   For example, system(*["echo foo"]) invokes echo command with an argument "foo".
  #   But system(Escape.shell_command(["echo foo"])) invokes "echo foo" command without arguments (and it probably fails).
  def shell_command(command)
    s = command.map {|word| shell_single_word(word) }.join(' ')
    ShellEscaped.new_no_dup(s)
  end

  # Escape.shell_single_word quotes shell meta characters.
  # It returns an instance of ShellEscaped.
  #
  # The result string is always single shell word, even if
  # the argument is "".
  # Escape.shell_single_word("") returns #<Escape::ShellEscaped: ''>.
  #
  #  Escape.shell_single_word("") #=> #<Escape::ShellEscaped: ''>
  #  Escape.shell_single_word("foo") #=> #<Escape::ShellEscaped: foo>
  #  Escape.shell_single_word("*") #=> #<Escape::ShellEscaped: '*'>
  def shell_single_word(str)
    if str.empty?
      ShellEscaped.new_no_dup("''")
    elsif %r{\A[0-9A-Za-z+,./:=@_-]+\z} =~ str
      ShellEscaped.new(str)
    else
      result = ''
      str.scan(/('+)|[^']+/) {
        if $1
          result << %q{\'} * $1.length
        else
          result << "'#{$&}'"
        end
      }
      ShellEscaped.new_no_dup(result)
    end
  end

  class PercentEncoded < StringWrapper
  end

  # Escape.uri_segment escapes URI segment using percent-encoding.
  # It returns an instance of PercentEncoded.
  #
  #  Escape.uri_segment("a/b") #=> #<Escape::PercentEncoded: a%2Fb>
  #
  # The segment is "/"-splitted element after authority before query in URI, as follows.
  #
  #   scheme://authority/segment1/segment2/.../segmentN?query#fragment
  #
  # See RFC 3986 for details of URI.
  def uri_segment(str)
    # pchar - pct-encoded = unreserved / sub-delims / ":" / "@"
    # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
    # sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
    s = str.gsub(%r{[^A-Za-z0-9\-._~!$&'()*+,;=:@]}n) {
      '%' + $&.unpack("H2")[0].upcase
    }
    PercentEncoded.new_no_dup(s)
  end

  # Escape.uri_path escapes URI path using percent-encoding.
  # The given path should be a sequence of (non-escaped) segments separated by "/".
  # The segments cannot contains "/".
  # It returns an instance of PercentEncoded.
  #
  #  Escape.uri_path("a/b/c") #=> #<Escape::PercentEncoded: a/b/c>
  #  Escape.uri_path("a?b/c?d/e?f") #=> #<Escape::PercentEncoded: a%3Fb/c%3Fd/e%3Ff>
  #
  # The path is the part after authority before query in URI, as follows.
  #
  #   scheme://authority/path#fragment
  #
  # See RFC 3986 for details of URI.
  #
  # Note that this function is not appropriate to convert OS path to URI.
  def uri_path(str)
    s = str.gsub(%r{[^/]+}n) { uri_segment($&) }
    PercentEncoded.new_no_dup(s)
  end

  # :stopdoc:
  def html_form_fast(pairs, sep='&')
    s = pairs.map {|k, v|
      # query-chars - pct-encoded - x-www-form-urlencoded-delimiters =
      #   unreserved / "!" / "$" / "'" / "(" / ")" / "*" / "," / ":" / "@" / "/" / "?"
      # query-char - pct-encoded = unreserved / sub-delims / ":" / "@" / "/" / "?"
      # query-char = pchar / "/" / "?" = unreserved / pct-encoded / sub-delims / ":" / "@" / "/" / "?"
      # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
      # sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
      # x-www-form-urlencoded-delimiters = "&" / "+" / ";" / "="
      k = k.gsub(%r{[^0-9A-Za-z\-\._~:/?@!\$'()*,]}n) {
        '%' + $&.unpack("H2")[0].upcase
      }
      v = v.gsub(%r{[^0-9A-Za-z\-\._~:/?@!\$'()*,]}n) {
        '%' + $&.unpack("H2")[0].upcase
      }
      "#{k}=#{v}"
    }.join(sep)
    PercentEncoded.new_no_dup(s)
  end
  # :startdoc:

  # Escape.html_form composes HTML form key-value pairs as a x-www-form-urlencoded encoded string.
  # It returns an instance of PercentEncoded.
  #
  # Escape.html_form takes an array of pair of strings or
  # an hash from string to string.
  #
  #  Escape.html_form([["a","b"], ["c","d"]]) #=> #<Escape::PercentEncoded: a=b&c=d>
  #  Escape.html_form({"a"=>"b", "c"=>"d"}) #=> #<Escape::PercentEncoded: a=b&c=d>
  #
  # In the array form, it is possible to use same key more than once.
  # (It is required for a HTML form which contains
  # checkboxes and select element with multiple attribute.)
  #
  #  Escape.html_form([["k","1"], ["k","2"]]) #=> #<Escape::PercentEncoded: k=1&k=2>
  #
  # If the strings contains characters which must be escaped in x-www-form-urlencoded,
  # they are escaped using %-encoding.
  #
  #  Escape.html_form([["k=","&;="]]) #=> #<Escape::PercentEncoded: k%3D=%26%3B%3D>
  #
  # The separator can be specified by the optional second argument.
  #
  #  Escape.html_form([["a","b"], ["c","d"]], ";") #=> #<Escape::PercentEncoded: a=b;c=d>
  #
  # See HTML 4.01 for details.
  def html_form(pairs, sep='&')
    r = ''
    first = true
    pairs.each {|k, v|
      # query-chars - pct-encoded - x-www-form-urlencoded-delimiters =
      #   unreserved / "!" / "$" / "'" / "(" / ")" / "*" / "," / ":" / "@" / "/" / "?"
      # query-char - pct-encoded = unreserved / sub-delims / ":" / "@" / "/" / "?"
      # query-char = pchar / "/" / "?" = unreserved / pct-encoded / sub-delims / ":" / "@" / "/" / "?"
      # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
      # sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
      # x-www-form-urlencoded-delimiters = "&" / "+" / ";" / "="
      r << sep if !first
      first = false
      k.each_byte {|byte|
        ch = byte.chr
        if %r{[^0-9A-Za-z\-\._~:/?@!\$'()*,]}n =~ ch
          r << "%" << ch.unpack("H2")[0].upcase
        else
          r << ch
        end
      }
      r << '='
      v.each_byte {|byte|
        ch = byte.chr
        if %r{[^0-9A-Za-z\-\._~:/?@!\$'()*,]}n =~ ch
          r << "%" << ch.unpack("H2")[0].upcase
        else
          r << ch
        end
      }
    }
    PercentEncoded.new_no_dup(r)
  end

  class HTMLEscaped < StringWrapper
  end

  # :stopdoc:
  HTML_TEXT_ESCAPE_HASH = {
    '&' => '&amp;',
    '<' => '&lt;',
    '>' => '&gt;',
  }
  # :startdoc:

  # Escape.html_text escapes a string appropriate for HTML text using character references.
  # It returns an instance of HTMLEscaped.
  #
  # It escapes 3 characters:
  # * '&' to '&amp;'
  # * '<' to '&lt;'
  # * '>' to '&gt;'
  #
  #  Escape.html_text("abc") #=> #<Escape::HTMLEscaped: abc>
  #  Escape.html_text("a & b < c > d") #=> #<Escape::HTMLEscaped: a &amp; b &lt; c &gt; d>
  #
  # This function is not appropriate for escaping HTML element attribute
  # because quotes are not escaped.
  def html_text(str)
    s = str.gsub(/[&<>]/) {|ch| HTML_TEXT_ESCAPE_HASH[ch] }
    HTMLEscaped.new_no_dup(s)
  end

  # :stopdoc:
  HTML_ATTR_ESCAPE_HASH = {
    '&' => '&amp;',
    '<' => '&lt;',
    '>' => '&gt;',
    '"' => '&quot;',
  }
  # :startdoc:

  class HTMLAttrValue < StringWrapper
  end

  # Escape.html_attr_value encodes a string as a double-quoted HTML attribute using character references.
  # It returns an instance of HTMLAttrValue.
  #
  #  Escape.html_attr_value("abc") #=> #<Escape::HTMLAttrValue: "abc">
  #  Escape.html_attr_value("a&b") #=> #<Escape::HTMLAttrValue: "a&amp;b">
  #  Escape.html_attr_value("ab&<>\"c") #=> #<Escape::HTMLAttrValue: "ab&amp;&lt;&gt;&quot;c">
  #  Escape.html_attr_value("a'c") #=> #<Escape::HTMLAttrValue: "a'c">
  #
  # It escapes 4 characters:
  # * '&' to '&amp;'
  # * '<' to '&lt;'
  # * '>' to '&gt;'
  # * '"' to '&quot;'
  #
  def html_attr_value(str)
    s = '"' + str.gsub(/[&<>"]/) {|ch| HTML_ATTR_ESCAPE_HASH[ch] } + '"'
    HTMLAttrValue.new_no_dup(s)
  end
end