summaryrefslogtreecommitdiff
path: root/lib/webrick/httputils.rb
blob: a5f0632b86377b80ca28537ba6b0c3928d81aaf5 (plain)
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
#
# httputils.rb -- HTTPUtils Module
#
# Author: IPR -- Internet Programming with Ruby -- writers
# Copyright (c) 2000, 2001 TAKAHASHI Masayoshi, GOTOU Yuuzou
# Copyright (c) 2002 Internet Programming with Ruby writers. All rights
# reserved.
#
# $IPR: httputils.rb,v 1.34 2003/06/05 21:34:08 gotoyuzo Exp $

require 'socket'
require 'tempfile'

module WEBrick
  CR   = "\x0d"     # :nodoc:
  LF   = "\x0a"     # :nodoc:
  CRLF = "\x0d\x0a" # :nodoc:

  ##
  # HTTPUtils provides utility methods for working with the HTTP protocol.
  #
  # This module is generally used internally by WEBrick

  module HTTPUtils

    ##
    # Normalizes a request path.  Raises an exception if the path cannot be
    # normalized.

    def normalize_path(path)
      raise "abnormal path `#{path}'" if path[0] != ?/
      ret = path.dup

      ret.gsub!(%r{/+}o, '/')                    # //      => /
      while ret.sub!(%r'/\.(?:/|\Z)', '/'); end  # /.      => /
      while ret.sub!(%r'/(?!\.\./)[^/]+/\.\.(?:/|\Z)', '/'); end # /foo/.. => /foo

      raise "abnormal path `#{path}'" if %r{/\.\.(/|\Z)} =~ ret
      ret
    end
    module_function :normalize_path

    ##
    # Default mime types

    DefaultMimeTypes = {
      "ai"    => "application/postscript",
      "asc"   => "text/plain",
      "avi"   => "video/x-msvideo",
      "bin"   => "application/octet-stream",
      "bmp"   => "image/bmp",
      "class" => "application/octet-stream",
      "cer"   => "application/pkix-cert",
      "crl"   => "application/pkix-crl",
      "crt"   => "application/x-x509-ca-cert",
     #"crl"   => "application/x-pkcs7-crl",
      "css"   => "text/css",
      "dms"   => "application/octet-stream",
      "doc"   => "application/msword",
      "dvi"   => "application/x-dvi",
      "eps"   => "application/postscript",
      "etx"   => "text/x-setext",
      "exe"   => "application/octet-stream",
      "gif"   => "image/gif",
      "htm"   => "text/html",
      "html"  => "text/html",
      "jpe"   => "image/jpeg",
      "jpeg"  => "image/jpeg",
      "jpg"   => "image/jpeg",
      "js"    => "application/javascript",
      "lha"   => "application/octet-stream",
      "lzh"   => "application/octet-stream",
      "mov"   => "video/quicktime",
      "mpe"   => "video/mpeg",
      "mpeg"  => "video/mpeg",
      "mpg"   => "video/mpeg",
      "pbm"   => "image/x-portable-bitmap",
      "pdf"   => "application/pdf",
      "pgm"   => "image/x-portable-graymap",
      "png"   => "image/png",
      "pnm"   => "image/x-portable-anymap",
      "ppm"   => "image/x-portable-pixmap",
      "ppt"   => "application/vnd.ms-powerpoint",
      "ps"    => "application/postscript",
      "qt"    => "video/quicktime",
      "ras"   => "image/x-cmu-raster",
      "rb"    => "text/plain",
      "rd"    => "text/plain",
      "rtf"   => "application/rtf",
      "sgm"   => "text/sgml",
      "sgml"  => "text/sgml",
      "svg"   => "image/svg+xml",
      "tif"   => "image/tiff",
      "tiff"  => "image/tiff",
      "txt"   => "text/plain",
      "xbm"   => "image/x-xbitmap",
      "xhtml" => "text/html",
      "xls"   => "application/vnd.ms-excel",
      "xml"   => "text/xml",
      "xpm"   => "image/x-xpixmap",
      "xwd"   => "image/x-xwindowdump",
      "zip"   => "application/zip",
    }

    ##
    # Loads Apache-compatible mime.types in +file+.

    def load_mime_types(file)
      open(file){ |io|
        hash = Hash.new
        io.each{ |line|
          next if /^#/ =~ line
          line.chomp!
          mimetype, ext0 = line.split(/\s+/, 2)
          next unless ext0
          next if ext0.empty?
          ext0.split(/\s+/).each{ |ext| hash[ext] = mimetype }
        }
        hash
      }
    end
    module_function :load_mime_types

    ##
    # Returns the mime type of +filename+ from the list in +mime_tab+.  If no
    # mime type was found application/octet-stream is returned.

    def mime_type(filename, mime_tab)
      suffix1 = (/\.(\w+)$/ =~ filename && $1.downcase)
      suffix2 = (/\.(\w+)\.[\w\-]+$/ =~ filename && $1.downcase)
      mime_tab[suffix1] || mime_tab[suffix2] || "application/octet-stream"
    end
    module_function :mime_type

    ##
    # Parses an HTTP header +raw+ into a hash of header fields with an Array
    # of values.

    def parse_header(raw)
      header = Hash.new([].freeze)
      field = nil
      raw.each_line{|line|
        case line
        when /^([A-Za-z0-9!\#$%&'*+\-.^_`|~]+):\s*(.*?)\s*\z/om
          field, value = $1, $2
          field.downcase!
          header[field] = [] unless header.has_key?(field)
          header[field] << value
        when /^\s+(.*?)\s*\z/om
          value = $1
          unless field
            raise HTTPStatus::BadRequest, "bad header '#{line}'."
          end
          header[field][-1] << " " << value
        else
          raise HTTPStatus::BadRequest, "bad header '#{line}'."
        end
      }
      header.each{|key, values|
        values.each{|value|
          value.strip!
          value.gsub!(/\s+/, " ")
        }
      }
      header
    end
    module_function :parse_header

    ##
    # Splits a header value +str+ according to HTTP specification.

    def split_header_value(str)
      str.scan(%r'\G((?:"(?:\\.|[^"])+?"|[^",]+)+)
                    (?:,\s*|\Z)'xn).flatten
    end
    module_function :split_header_value

    ##
    # Parses a Range header value +ranges_specifier+

    def parse_range_header(ranges_specifier)
      if /^bytes=(.*)/ =~ ranges_specifier
        byte_range_set = split_header_value($1)
        byte_range_set.collect{|range_spec|
          case range_spec
          when /^(\d+)-(\d+)/ then $1.to_i .. $2.to_i
          when /^(\d+)-/      then $1.to_i .. -1
          when /^-(\d+)/      then -($1.to_i) .. -1
          else return nil
          end
        }
      end
    end
    module_function :parse_range_header

    ##
    # Parses q values in +value+ as used in Accept headers.

    def parse_qvalues(value)
      tmp = []
      if value
        parts = value.split(/,\s*/)
        parts.each {|part|
          if m = %r{^([^\s,]+?)(?:;\s*q=(\d+(?:\.\d+)?))?$}.match(part)
            val = m[1]
            q = (m[2] or 1).to_f
            tmp.push([val, q])
          end
        }
        tmp = tmp.sort_by{|val, q| -q}
        tmp.collect!{|val, q| val}
      end
      return tmp
    end
    module_function :parse_qvalues

    ##
    # Removes quotes and escapes from +str+

    def dequote(str)
      ret = (/\A"(.*)"\Z/ =~ str) ? $1 : str.dup
      ret.gsub!(/\\(.)/, "\\1")
      ret
    end
    module_function :dequote

    ##
    # Quotes and escapes quotes in +str+

    def quote(str)
      '"' << str.gsub(/[\\\"]/o, "\\\1") << '"'
    end
    module_function :quote

    ##
    # Stores multipart form data.  FormData objects are created when
    # WEBrick::HTTPUtils.parse_form_data is called.

    class FormData < String
      EmptyRawHeader = [].freeze # :nodoc:
      EmptyHeader = {}.freeze # :nodoc:

      ##
      # The name of the form data part

      attr_accessor :name

      ##
      # The filename of the form data part

      attr_accessor :filename

      attr_accessor :next_data # :nodoc:
      protected :next_data

      ##
      # Creates a new FormData object.
      #
      # +args+ is an Array of form data entries.  One FormData will be created
      # for each entry.
      #
      # This is called by WEBrick::HTTPUtils.parse_form_data for you

      def initialize(*args)
        @name = @filename = @next_data = nil
        if args.empty?
          @raw_header = []
          @header = nil
          super("")
        else
          @raw_header = EmptyRawHeader
          @header = EmptyHeader
          super(args.shift)
          unless args.empty?
            @next_data = self.class.new(*args)
          end
        end
      end

      ##
      # Retrieves the header at the first entry in +key+

      def [](*key)
        begin
          @header[key[0].downcase].join(", ")
        rescue StandardError, NameError
          super
        end
      end

      ##
      # Adds +str+ to this FormData which may be the body, a header or a
      # header entry.
      #
      # This is called by WEBrick::HTTPUtils.parse_form_data for you

      def <<(str)
        if @header
          super
        elsif str == CRLF
          @header = HTTPUtils::parse_header(@raw_header.join)
          if cd = self['content-disposition']
            if /\s+name="(.*?)"/ =~ cd then @name = $1 end
            if /\s+filename="(.*?)"/ =~ cd then @filename = $1 end
          end
        else
          @raw_header << str
        end
        self
      end

      ##
      # Adds +data+ at the end of the chain of entries
      #
      # This is called by WEBrick::HTTPUtils.parse_form_data for you.

      def append_data(data)
        tmp = self
        while tmp
          unless tmp.next_data
            tmp.next_data = data
            break
          end
          tmp = tmp.next_data
        end
        self
      end

      ##
      # Yields each entry in this FormData

      def each_data
        tmp = self
        while tmp
          next_data = tmp.next_data
          yield(tmp)
          tmp = next_data
        end
      end

      ##
      # Returns all the FormData as an Array

      def list
        ret = []
        each_data{|data|
          ret << data.to_s
        }
        ret
      end

      ##
      # A FormData will behave like an Array

      alias :to_ary :list

      ##
      # This FormData's body

      def to_s
        String.new(self)
      end
    end

    ##
    # Parses the query component of a URI in +str+

    def parse_query(str)
      query = Hash.new
      if str
        str.split(/[&;]/).each{|x|
          next if x.empty?
          key, val = x.split(/=/,2)
          key = unescape_form(key)
          val = unescape_form(val.to_s)
          val = FormData.new(val)
          val.name = key
          if query.has_key?(key)
            query[key].append_data(val)
            next
          end
          query[key] = val
        }
      end
      query
    end
    module_function :parse_query

    ##
    # Parses form data in +io+ with the given +boundary+

    def parse_form_data(io, boundary)
      boundary_regexp = /\A--#{Regexp.quote(boundary)}(--)?#{CRLF}\z/
      form_data = Hash.new
      return form_data unless io
      data = nil
      io.each_line{|line|
        if boundary_regexp =~ line
          if data
            data.chop!
            key = data.name
            if form_data.has_key?(key)
              form_data[key].append_data(data)
            else
              form_data[key] = data
            end
          end
          data = FormData.new
          next
        else
          if data
            data << line
          end
        end
      }
      return form_data
    end
    module_function :parse_form_data

    #####

    reserved = ';/?:@&=+$,'
    num      = '0123456789'
    lowalpha = 'abcdefghijklmnopqrstuvwxyz'
    upalpha  = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
    mark     = '-_.!~*\'()'
    unreserved = num + lowalpha + upalpha + mark
    control  = (0x0..0x1f).collect{|c| c.chr }.join + "\x7f"
    space    = " "
    delims   = '<>#%"'
    unwise   = '{}|\\^[]`'
    nonascii = (0x80..0xff).collect{|c| c.chr }.join

    module_function

    # :stopdoc:

    def _make_regex(str) /([#{Regexp.escape(str)}])/n end
    def _make_regex!(str) /([^#{Regexp.escape(str)}])/n end
    def _escape(str, regex)
      str = str.b
      str.gsub!(regex) {"%%%02X" % $1.ord}
      # %-escaped string should contain US-ASCII only
      str.force_encoding(Encoding::US_ASCII)
    end
    def _unescape(str, regex)
      str = str.b
      str.gsub!(regex) {$1.hex.chr}
      # encoding of %-unescaped string is unknown
      str
    end

    UNESCAPED = _make_regex(control+space+delims+unwise+nonascii)
    UNESCAPED_FORM = _make_regex(reserved+control+delims+unwise+nonascii)
    NONASCII  = _make_regex(nonascii)
    ESCAPED   = /%([0-9a-fA-F]{2})/
    UNESCAPED_PCHAR = _make_regex!(unreserved+":@&=+$,")

    # :startdoc:

    ##
    # Escapes HTTP reserved and unwise characters in +str+

    def escape(str)
      _escape(str, UNESCAPED)
    end

    ##
    # Unescapes HTTP reserved and unwise characters in +str+

    def unescape(str)
      _unescape(str, ESCAPED)
    end

    ##
    # Escapes form reserved characters in +str+

    def escape_form(str)
      ret = _escape(str, UNESCAPED_FORM)
      ret.gsub!(/ /, "+")
      ret
    end

    ##
    # Unescapes form reserved characters in +str+

    def unescape_form(str)
      _unescape(str.gsub(/\+/, " "), ESCAPED)
    end

    ##
    # Escapes path +str+

    def escape_path(str)
      result = ""
      str.scan(%r{/([^/]*)}).each{|i|
        result << "/" << _escape(i[0], UNESCAPED_PCHAR)
      }
      return result
    end

    ##
    # Escapes 8 bit characters in +str+

    def escape8bit(str)
      _escape(str, NONASCII)
    end
  end
end