Object
Class that parses String's into URI's.
It contains a Hash set of patterns and Regexp's that match and validate.
URI::Parser.new([opts])
The constructor accepts a hash as options for parser. Keys of options are pattern names of URI components and values of options are pattern strings. The constructor generates set of regexps for parsing URIs.
You can use the following keys:
* :ESCAPED (URI::PATTERN::ESCAPED in default) * :UNRESERVED (URI::PATTERN::UNRESERVED in default) * :DOMLABEL (URI::PATTERN::DOMLABEL in default) * :TOPLABEL (URI::PATTERN::TOPLABEL in default) * :HOSTNAME (URI::PATTERN::HOSTNAME in default)
p = URI::Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})") u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP http://example.jp/%uABCD> URI.parse(u.to_s) #=> raises URI::InvalidURIError s = "http://example.com/ABCD" u1 = p.parse(s) #=> #<URI::HTTP http://example.com/ABCD> u2 = URI.parse(s) #=> #<URI::HTTP http://example.com/ABCD> u1 == u2 #=> true u1.eql?(u2) #=> false
# File uri/rfc2396_parser.rb, line 99 def initialize(opts = {}) @pattern = initialize_pattern(opts) @pattern.each_value(&:freeze) @pattern.freeze @regexp = initialize_regexp(@pattern) @regexp.each_value(&:freeze) @regexp.freeze end
str
String to make safe
unsafe
Regexp to apply. Defaults to self.regexp
Constructs a safe String from str
, removing unsafe characters,
replacing them with codes.
# File uri/rfc2396_parser.rb, line 299 def escape(str, unsafe = @regexp[:UNSAFE]) unless unsafe.kind_of?(Regexp) # perhaps unsafe is String object unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false) end str.gsub(unsafe) do us = $& tmp = '' us.each_byte do |uc| tmp << sprintf('%%%02X', uc) end tmp end.force_encoding(Encoding::US_ASCII) end
str
String to search
schemes
Patterns to apply to str
Attempts to parse and merge a set of URIs. If no block
given,
then returns the result, else it calls block
for each element
in result.
See also URI::Parser.make_regexp.
# File uri/rfc2396_parser.rb, line 261 def extract(str, schemes = nil) if block_given? str.scan(make_regexp(schemes)) { yield $& } nil else result = [] str.scan(make_regexp(schemes)) { result.push $& } result end end
# File uri/rfc2396_parser.rb, line 337 def inspect @@to_s.bind(self).call end
Returns Regexp that is default self.regexp,
unless schemes
is provided. Then it is a Regexp.union with self.pattern.
# File uri/rfc2396_parser.rb, line 274 def make_regexp(schemes = nil) unless schemes @regexp[:ABS_URI_REF] else /(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x end end
uri
String
Parses uri
and constructs either matching URI scheme object (File, FTP,
HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic.
p = URI::Parser.new p.parse("ldap://ldap.example.com/dc=example?user=john") #=> #<URI::LDAP ldap://ldap.example.com/dc=example?user=john>
# File uri/rfc2396_parser.rb, line 209 def parse(uri) scheme, userinfo, host, port, registry, path, opaque, query, fragment = self.split(uri) if scheme && URI.scheme_list.include?(scheme.upcase) URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port, registry, path, opaque, query, fragment, self) else Generic.new(scheme, userinfo, host, port, registry, path, opaque, query, fragment, self) end end
Returns a split URI against regexp.
# File uri/rfc2396_parser.rb, line 120 def split(uri) case uri when '' # null uri when @regexp[:ABS_URI] scheme, opaque, userinfo, host, port, registry, path, query, fragment = $~[1..-1] # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] # absoluteURI = scheme ":" ( hier_part | opaque_part ) # hier_part = ( net_path | abs_path ) [ "?" query ] # opaque_part = uric_no_slash *uric # abs_path = "/" path_segments # net_path = "//" authority [ abs_path ] # authority = server | reg_name # server = [ [ userinfo "@" ] hostport ] if !scheme raise InvalidURIError, "bad URI(absolute but no scheme): #{uri}" end if !opaque && (!path && (!host && !registry)) raise InvalidURIError, "bad URI(absolute but no path): #{uri}" end when @regexp[:REL_URI] scheme = nil opaque = nil userinfo, host, port, registry, rel_segment, abs_path, query, fragment = $~[1..-1] if rel_segment && abs_path path = rel_segment + abs_path elsif rel_segment path = rel_segment elsif abs_path path = abs_path end # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ] # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ] # net_path = "//" authority [ abs_path ] # abs_path = "/" path_segments # rel_path = rel_segment [ abs_path ] # authority = server | reg_name # server = [ [ userinfo "@" ] hostport ] else raise InvalidURIError, "bad URI(is not URI?): #{uri}" end path = '' if !path && !opaque # (see RFC2396 Section 5.2) ret = [ scheme, userinfo, host, port, # X registry, # X path, # Y opaque, # Y query, fragment ] return ret end
str
String to remove escapes from
escaped
Regexp to apply. Defaults to self.regexp
Removes escapes from str
.
# File uri/rfc2396_parser.rb, line 330 def unescape(str, escaped = @regexp[:ESCAPED]) enc = str.encoding enc = Encoding::UTF_8 if enc == Encoding::US_ASCII str.gsub(escaped) { [$&[1, 2]].pack('H2').force_encoding(enc) } end