# Author:: Tom Gilbert <tom@linuxbrit.co.uk>
# Author:: Giuseppe "Oblomov" Bilotta <giuseppe.bilotta@gmail.com>
# Author:: Dmitry "jsn" Kim <dmitry point kim at gmail point com>
-#
-# Copyright:: (C) 2002-2005 Tom Gilbert
-# Copyright:: (C) 2006 Tom Gilbert, Giuseppe Bilotta
-# Copyright:: (C) 2007 Giuseppe Bilotta, Dmitry Kim
require 'resolv'
require 'net/http'
end
when 'deflate'
debug "inflating body"
- # From http://www.koders.com/ruby/fid927B4382397E5115AC0ABE21181AB5C1CBDD5C17.aspx?s=thread:
+ # From http://www.koders.com/ruby/fid927B4382397E5115AC0ABE21181AB5C1CBDD5C17.aspx?s=thread:
# -MAX_WBITS stops zlib from looking for a zlib header
inflater = Zlib::Inflate.new(-Zlib::MAX_WBITS)
begin
# TODO
# debug "full inflation failed (#{e}), trying to recover as much as possible"
end
+ when /^(?:iso-8859-\d+|windows-\d+|utf-8|utf8)$/i
+ # B0rked servers (Freshmeat being one of them) sometimes return the charset
+ # in the content-encoding; in this case we assume that the document has
+ # a standarc content-encoding
+ old_hsh = self.to_hash
+ self['content-type']= self['content-type']+"; charset="+method.downcase
+ warning "Charset vs content-encoding confusion, trying to recover: from\n#{old_hsh.pretty_inspect}to\n#{self.to_hash.pretty_inspect}"
+ return str
else
+ debug self.to_hash
raise "Unhandled content encoding #{method}"
end
end
# the partial text at each chunk. Return the partial body.
def partial_body(size=0, &block)
- self.no_cache = true
partial = String.new
- self.read_body { |chunk|
- partial << chunk
+ if @read
+ debug "using body() as partial"
+ partial = self.body
yield self.body_to_utf(self.decompress_body(partial)) if block_given?
- break if size and size > 0 and partial.length >= size
- }
+ else
+ debug "disabling cache"
+ self.no_cache = true
+ self.read_body { |chunk|
+ partial << chunk
+ yield self.body_to_utf(self.decompress_body(partial)) if block_given?
+ break if size and size > 0 and partial.length >= size
+ }
+ end
return self.body_to_utf(self.decompress_body(partial))
end
#
def get_response(uri_or_s, options = {}, &block) # :yields: resp
uri = uri_or_s.kind_of?(URI) ? uri_or_s : URI.parse(uri_or_s.to_s)
+ unless URI::HTTP === uri
+ if uri.scheme
+ raise "#{uri.scheme.inspect} URI scheme is not supported"
+ else
+ raise "don't know what to do with #{uri.to_s.inspect}"
+ end
+ end
+
opts = {
:max_redir => @bot.config['http.max_redir'],
:yield => :final,
}.merge(options)
resp = nil
- cached = nil
req_class = case opts[:method].to_s.downcase.intern
when :head, :"net::http::head"
debug "get_response(#{uri}, #{opts.inspect})"
- if opts[:cache] && cached = @cache[cache_key]
+ cached = @cache[cache_key]
+
+ if opts[:cache] && cached
debug "got cached"
if !cached.expired?
debug "using cached"
headers['Range'] = opts[:range] if opts[:range]
headers['Authorization'] = opts[:auth_head] if opts[:auth_head]
- cached.setup_headers(headers) if cached && (req_class == Net::HTTP::Get)
+ if opts[:cache] && cached && (req_class == Net::HTTP::Get)
+ cached.setup_headers headers
+ end
+
req = req_class.new(uri.request_uri, headers)
if uri.user && uri.password
req.basic_auth(uri.user, uri.password)
debug "prepared request: #{req.to_hash.inspect}"
begin
- get_proxy(uri, opts).start do |http|
- http.request(req) do |resp|
- resp['x-rbot-location'] = uri.to_s
- if Net::HTTPNotModified === resp
- debug "not modified"
- begin
- cached.revalidate(resp)
- rescue Exception => e
- error e
+ get_proxy(uri, opts).start do |http|
+ http.request(req) do |resp|
+ resp['x-rbot-location'] = uri.to_s
+ if Net::HTTPNotModified === resp
+ debug "not modified"
+ begin
+ cached.revalidate(resp)
+ rescue Exception => e
+ error e
+ end
+ debug "reusing cached"
+ resp = cached.response
+ elsif Net::HTTPServerError === resp || Net::HTTPClientError === resp
+ debug "http error, deleting cached obj" if cached
+ @cache.delete(cache_key)
end
- debug "reusing cached"
- resp = cached.response
- elsif Net::HTTPServerError === resp || Net::HTTPClientError === resp
- debug "http error, deleting cached obj" if cached
- @cache.delete(cache_key)
- elsif opts[:cache]
+
begin
return handle_response(uri, resp, opts, &block)
ensure
@cache[cache_key] = cached
end
end
- return ret
end
- return handle_response(uri, resp, opts, &block)
end
- end
rescue Exception => e
error e
raise e.message
opts = {:method => :head}.merge(options)
begin
resp = get_response(uri, opts, &block)
- raise "http error #{resp}" if Net::HTTPClientError === resp ||
- Net::HTTPServerError == resp
+ # raise "http error #{resp}" if Net::HTTPClientError === resp ||
+ # Net::HTTPServerError == resp
return resp
rescue Exception => e
error e
# _uri_:: uri to query (URI object or String)
# _nbytes_:: number of bytes to get
#
- # Partia GET request, returns (if possible) the first _nbytes_ bytes of the
+ # Partial GET request, returns (if possible) the first _nbytes_ bytes of the
# response body, following redirs and caching if requested, yielding the
# actual response(s) to the optional block. See get_response for details on
# the supported _options_