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: FormData

Constant Summary collapse

DefaultMimeTypes =

Default mime types

{
  "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",
  "json"  => "application/json",
  "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",
  "wasm"  => "application/wasm",
  "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",
}
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 



442
443
444
445
446
447
 
# File 'lib/webrick/httputils.rb', line 442

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:



440
 
# File 'lib/webrick/httputils.rb', line 440

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

._make_regex!(str) ⇒ Object 



441
 
# File 'lib/webrick/httputils.rb', line 441

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

._unescape(str, regex) ⇒ Object 



448
449
450
451
452
453
 
# File 'lib/webrick/httputils.rb', line 448

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



222
223
224
225
226
 
# File 'lib/webrick/httputils.rb', line 222

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



466
467
468
 
# File 'lib/webrick/httputils.rb', line 466

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

.escape8bit(str) ⇒ Object

Escapes 8 bit characters in str



507
508
509
 
# File 'lib/webrick/httputils.rb', line 507

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

.escape_form(str) ⇒ Object

Escapes form reserved characters in str



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

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

.escape_path(str) ⇒ Object

Escapes path str



496
497
498
499
500
501
502
 
# File 'lib/webrick/httputils.rb', line 496

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.



111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/webrick/httputils.rb', line 111

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.
  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.



133
134
135
136
137
 
# File 'lib/webrick/httputils.rb', line 133

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



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
 
# File 'lib/webrick/httputils.rb', line 394

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

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



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
 
# File 'lib/webrick/httputils.rb', line 144

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(&:strip!)
  }
  header
end

.parse_query(str) ⇒ Object

Parses the query component of a URI in str



370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
 
# File 'lib/webrick/httputils.rb', line 370

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.



201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
 
# File 'lib/webrick/httputils.rb', line 201

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

.parse_range_header(ranges_specifier) ⇒ Object

Parses a Range header value ranges_specifier



183
184
185
186
187
188
189
190
191
192
193
194
195
 
# File 'lib/webrick/httputils.rb', line 183

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



232
233
234
 
# File 'lib/webrick/httputils.rb', line 232

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

.split_header_value(str) ⇒ Object

Splits a header value str according to HTTP specification.



174
175
176
177
 
# File 'lib/webrick/httputils.rb', line 174

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

.unescape(str) ⇒ Object

Unescapes HTTP reserved and unwise characters in str



473
474
475
 
# File 'lib/webrick/httputils.rb', line 473

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

.unescape_form(str) ⇒ Object

Unescapes form reserved characters in str



489
490
491
 
# File 'lib/webrick/httputils.rb', line 489

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