Module: WEBrick::HTTPUtils

Defined in:
lib/webrick/httputils.rb

Overview

HTTPUtils provides utility methods for working with the HTTP protocol.

This module is generally used internally by WEBrick

Defined Under Namespace

Classes: CookieHeader, FormData, SplitHeader

Constant Summary collapse

DefaultMimeTypes =

Default mime types

{
  "ai"    => "application/postscript",
  "asc"   => "text/plain",
  "avi"   => "video/x-msvideo",
  "avif"  => "image/avif",
  "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",
  "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",
  "ico"   => "image/x-icon",
  "jpe"   => "image/jpeg",
  "jpeg"  => "image/jpeg",
  "jpg"   => "image/jpeg",
  "js"    => "application/javascript",
  "json"  => "application/json",
  "lha"   => "application/octet-stream",
  "lzh"   => "application/octet-stream",
  "mjs"   => "application/javascript",
  "mov"   => "video/quicktime",
  "mp4"   => "video/mp4",
  "mpe"   => "video/mpeg",
  "mpeg"  => "video/mpeg",
  "mpg"   => "video/mpeg",
  "otf"   => "font/otf",
  "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",
  "ttc"   => "font/collection",
  "ttf"   => "font/ttf",
  "txt"   => "text/plain",
  "wasm"  => "application/wasm",
  "webm"  => "video/webm",
  "webmanifest" => "application/manifest+json",
  "webp"  => "image/webp",
  "woff"  => "font/woff",
  "woff2" => "font/woff2",
  "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",
}
HEADER_CLASSES = 
Hash.new(SplitHeader).update({
  "cookie" => CookieHeader,
})
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+":@&=+$,")

Class Method Summary collapse

Class Method Details

._escape(str, regex) ⇒ Object 



474
475
476
477
478
479
 
# File 'lib/webrick/httputils.rb', line 474

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

._make_regex(str) ⇒ Object

:stopdoc:



472
 
# File 'lib/webrick/httputils.rb', line 472

def _make_regex(str) /([#{Regexp.escape(str)}])/n end

._make_regex!(str) ⇒ Object 



473
 
# File 'lib/webrick/httputils.rb', line 473

def _make_regex!(str) /([^#{Regexp.escape(str)}])/n end

._unescape(str, regex) ⇒ Object 



480
481
482
483
484
485
 
# File 'lib/webrick/httputils.rb', line 480

def _unescape(str, regex)
  str = str.b
  str.gsub!(regex) {$1.hex.chr}
  # encoding of %-unescaped string is unknown
  str
end

.dequote(str) ⇒ Object

Removes quotes and escapes from str



254
255
256
257
258
 
# File 'lib/webrick/httputils.rb', line 254

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

.escape(str) ⇒ Object

Escapes HTTP reserved and unwise characters in str



498
499
500
 
# File 'lib/webrick/httputils.rb', line 498

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

.escape8bit(str) ⇒ Object

Escapes 8 bit characters in str



539
540
541
 
# File 'lib/webrick/httputils.rb', line 539

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

.escape_form(str) ⇒ Object

Escapes form reserved characters in str



512
513
514
515
516
 
# File 'lib/webrick/httputils.rb', line 512

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

.escape_path(str) ⇒ Object

Escapes path str



528
529
530
531
532
533
534
 
# File 'lib/webrick/httputils.rb', line 528

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

.load_mime_types(file) ⇒ Object

Loads Apache-compatible mime.types in file.



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
 
# File 'lib/webrick/httputils.rb', line 122

def load_mime_types(file)
  # note: +file+ may be a "| command" for now; some people may
  # rely on this, but currently we do not use this method by default.
  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

.mime_type(filename, mime_tab) ⇒ Object

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



144
145
146
147
148
 
# File 'lib/webrick/httputils.rb', line 144

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

.normalize_path(path) ⇒ Object

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



31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/webrick/httputils.rb', line 31

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

.parse_form_data(io, boundary) ⇒ Object

Parses form data in io with the given boundary



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
 
# File 'lib/webrick/httputils.rb', line 426

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

.parse_header(raw) ⇒ Object 



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
 
# File 'lib/webrick/httputils.rb', line 171

def parse_header(raw)
  header = Hash.new([].freeze)
  field = nil
  raw.each_line{|line|
    case line
    when /^([A-Za-z0-9!\#$%&'*+\-.^_`|~]+):([^\r\n\0]*?)\r\n\z/om
      field, value = $1, $2
      field.downcase!
      header[field] = HEADER_CLASSES[field].new unless header.has_key?(field)
      header[field] << value
    when /^[ \t]+([^\r\n\0]*?)\r\n/om
      unless field
        raise HTTPStatus::BadRequest, "bad header '#{line}'."
      end
      value = line
      value.gsub!(/\A[ \t]+/, '')
      value.slice!(-2..-1)
      header[field][-1] << " " << value
    else
      raise HTTPStatus::BadRequest, "bad header '#{line}'."
    end
  }
  header.each{|key, values|
    values.each{|value|
      value.gsub!(/\A[ \t]+/, '')
      value.gsub!(/[ \t]+\z/, '')
    }
  }
  header
end

.parse_query(str) ⇒ Object

Parses the query component of a URI in str



402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
 
# File 'lib/webrick/httputils.rb', line 402

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

.parse_qvalues(value) ⇒ Object

Parses q values in value as used in Accept headers.



233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
 
# File 'lib/webrick/httputils.rb', line 233

def parse_qvalues(value)
  tmp = []
  if value
    parts = value.split(/,[ \t]*/)
    parts.each {|part|
      if m = %r{^([^ \t,]+?)(?:;[ \t]*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

.parse_range_header(ranges_specifier) ⇒ Object

Parses a Range header value ranges_specifier



215
216
217
218
219
220
221
222
223
224
225
226
227
 
# File 'lib/webrick/httputils.rb', line 215

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

.quote(str) ⇒ Object

Quotes and escapes quotes in str



264
265
266
 
# File 'lib/webrick/httputils.rb', line 264

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

.split_header_value(str) ⇒ Object

Splits a header value str according to HTTP specification.



206
207
208
209
 
# File 'lib/webrick/httputils.rb', line 206

def split_header_value(str)
  str.scan(%r'\G((?:"(?:\\.|[^"])+?"|[^",]++)+)
                (?:,[ \t]*|\Z)'xn).flatten
end

.unescape(str) ⇒ Object

Unescapes HTTP reserved and unwise characters in str



505
506
507
 
# File 'lib/webrick/httputils.rb', line 505

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

.unescape_form(str) ⇒ Object

Unescapes form reserved characters in str



521
522
523
 
# File 'lib/webrick/httputils.rb', line 521

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