#!/usr/bin/tclsh8.3
###############################################################################
# 
# Abfrageprozessor für Mr.Check (Fremdwörterlexikon)
#  Erik Buchmann, August '01
# 

regsub {[ ]+} $argv {+} search

set header ""
set content ""

global header content

################################
# Funktionen
proc getServer {client_request server} {
	global header content

	regsub -all -lineanchor "^\[\t \n\]+" [string trim $client_request] "" client_request

	# Socket aufmachen und Daten holen
	if {[catch {set server_channel [socket $server 80]}]} {
		puts "Got Error: Server not found"
		exit
	}

	fconfigure $server_channel -translation crlf -blocking true
	puts $server_channel "$client_request\n"
	flush $server_channel

	#Header holen
	set line "foo"
	set header ""
	while {$line!="" } {
		set line [gets $server_channel]
		set header "$header\n$line"
	}

	# Daten holen 
	fconfigure $server_channel -translation binary -blocking true
	set content [read $server_channel]

	close $server_channel
}

################################
# Anfrage nach Location aufbauen

set client_request "\
	GET /v2.0/Mrcheck.php?CID=MrcheckDGFW&SB=$search HTTP/1.0
	Connection: close
	User-Agent: lex.tcl
	Host: mr-check.xipolis.net
	Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, image/png, */*
	Accept-Language: en
	Accept-Charset: iso-8859-1,*,utf-8"

getServer $client_request "mr-check.xipolis.net"

######################
# Location extrahieren
regexp -lineanchor {(Location: http://)([^/]+)([^
 ]*)} $header nix nix server location

# Location umformen
regsub {Mrcheck.php.*$} $location "main.php" location

################################
# Anfrage nach Inhalt aufbauen

set client_request "\
	GET $location HTTP/1.0
	Connection: close
	User-Agent: lex.tcl
	Host: $server
	Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, image/png, */*
	Accept-Language: en
	Accept-Charset: iso-8859-1,*,utf-8"

getServer $client_request $server

#Anfang und Ende abschneiden
regsub {^.*?(\</select\>)} $content {} content
regsub {^.*?(\</table\>)} $content {} content
regsub {(\<img src=).*$} $content {} content

#alle HTML-Tags entfernen
regsub -all -nocase {\<.*?\>} $content {} content

#Umlaute
regsub -all {(&auml;|&#228;)} $content {ä} content
regsub -all {(&Auml;|&#196;)} $content {Ä} content
regsub -all {(&ouml;|&#246;)} $content {ö} content
regsub -all {(&Ouml;|&#214;)} $content {Ö} content
regsub -all {(&uuml;|&#252;)} $content {ü} content
regsub -all {(&Uuml;|&#220;)} $content {Ü} content
regsub -all {(&szlig;|&#223;)} $content {ß} content
regsub -all {&lt;} $content {<} content
regsub -all {&gt;} $content {>} content
regsub -all {(&laquo;|&#171;)} $content {«} content
regsub -all {(&raquo;|&#187;)} $content {»} content
regsub -all {(&oslash;|&#248;)} $content {ø} content
regsub -all {(&eacute;|&#233;|&#113;|&#x113;)} $content {é} content
regsub -all {(&aacute;|&#225;|&#224;)} $content {á} content
regsub -all {(&oacute;|&#243;)} $content {ó} content
regsub -all {(&yacute;|&#253;)} $content {ý} content

#Whitespace
regsub -all {[ 	]+} $content { } content
regsub -all -lineanchor {^[ ]+} $content {} content

set clist [split $content "\n"]

puts "------------------------------------------------------------"

foreach x $clist {
  
	if {[string length [string trim $x]]>0} {
		if {[regexp {^(Quelle:)} $x]} {
			puts " "
		} elseif {[regexp {^(Hilfe \| schlie.en)} $x ]} {
			puts "keine weiteren Ergebnisse gefunden!"
		} else {
		  	puts "$x"
		}
	}
}

puts "------------------------------------------------------------"