In Files
- uri/rfc2396_parser.rb
Parent
Object
Included Modules
![[+]](../images/find.png "show/hide quicksearch"){kind=small}
URI::RFC2396_Parser
class that Parses String’s into URI’s
It contains a Hash set of patterns and Regexp’s that match and validate.
Attributes
Public Class Methods
new(opts = {})
Synopsis¶ ↑
URI::Parser.new([opts])
Args¶ ↑
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)
Examples¶ ↑
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:0xb78cf4f8 URL:http://example.jp/%uABCD> URI.parse(u.to_s) #=> raises URI::InvalidURIError s = "http://example.com/ABCD" u1 = p.parse(s) #=> #<URI::HTTP:0xb78c3220 URL:http://example.com/ABCD> u2 = URI.parse(s) #=> #<URI::HTTP:0xb78b6d54 URL:http://example.com/ABCD> u1 == u2 #=> true u1.eql?(u2) #=> false
# File uri/rfc2396_parser.rb, line 100
def initialize(opts = {})
@pattern = initialize_pattern(opts)
@pattern.each_value(&:freeze)
@pattern.freeze
@regexp = initialize_regexp(@pattern)
@regexp.each_value(&:freeze)
@regexp.freeze
end
Public Instance Methods
escape( str )
escape( str, unsafe )
Args¶ ↑
str-
String to make safe
unsafe-
Regexp to apply. Defaults to self.regexp
Description¶ ↑
constructs a safe String from str, removing unsafe characters,
replacing them with codes.
# File uri/rfc2396_parser.rb, line 300
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
extract( str )
extract( str, schemes )
extract( str, schemes ) {|item| block }
Args¶ ↑
str-
String to search
schemes-
Patterns to apply to
str
Description¶ ↑
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 262
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
make_regexp(schemes = nil)
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 275
def make_regexp(schemes = nil)
unless schemes
@regexp[:ABS_URI_REF]
else
/(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x
end
end
parse(uri)
Args¶ ↑
uri-
String
Description¶ ↑
parses uri and constructs either matching URI scheme object (FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic
Usage¶ ↑
p = URI::Parser.new p.parse("ldap://ldap.example.com/dc=example?user=john") #=> #<URI::LDAP:0x00000000b9e7e8 URL:ldap://ldap.example.com/dc=example?user=john>
# File uri/rfc2396_parser.rb, line 210
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
split(uri)
Returns a split URI against regexp
# File uri/rfc2396_parser.rb, line 121
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 = $~[1..-1]
if rel_segment && abs_path
path = rel_segment + abs_path
elsif rel_segment
path = rel_segment
elsif abs_path
path = abs_path
end
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
# net_path = "//" authority [ abs_path ]
# abs_path = "/" path_segments
# rel_path = rel_segment [ abs_path ]
# authority = server | reg_name
# server = [ [ userinfo "@" ] hostport ]
else
raise InvalidURIError, "bad URI(is not URI?): #{uri}"
end
path = '' if !path && !opaque # (see RFC2396 Section 5.2)
ret = [
scheme,
userinfo, host, port, # X
registry, # X
path, # Y
opaque, # Y
query,
fragment
]
return ret
end
unescape( str )
unescape( str, unsafe )
Args¶ ↑
str-
String to remove escapes from
unsafe-
Regexp to apply. Defaults to self.regexp
Description¶ ↑
Removes escapes from str
# File uri/rfc2396_parser.rb, line 331
def unescape(str, escaped = @regexp[:ESCAPED])
str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding)
end