Lingvistica's Taalhulp
Tekstsegmentatie
Semanta verdeelt teksten in analyseerbare zinsdelen om grammaticale en taalkundige segmenten mogelijk te maken. "; $ontl_strt = microtime(true); $userip=$_SERVER['REMOTE_ADDR']; $vg=0; $ial_sw=0; set_time_limit(0); session_start(); $sess_idnt=session_id(); // echo "
SESSION ID ".$sess_idnt." SERVER ".$srvr; include ("conv.php"); // $invr_bzv1=urldecode($invr_bzv1); // echo "
INVR BZV1".$invr_bzv1; $mb_rslt=preg_split('/(?"; foreach($mb_rslt as $mb_key => $mb_val) { $mb_lowr=mb_strtolower($mb_val,'UTF-8'); $mb_text=$mb_text.$mb_lowr; } // echo "
MB TEXT ".$mb_text; $mb_dtls=explode(" ",$mb_text); foreach($mb_dtls as $mb_key => $mb_val) { // echo "
KEY ".$mb_key." VAL ".$mb_val; } // echo "
MB TEXT ".$mb_text; $invr_bzv1=$mb_text; // echo "
EERSTE INDRUK INVR TAAL ".$invr_taal." BZV1 ".$invr_bzv1." BZV2 ".$invr_bzv2." LNKS ".$invr_lnks."RCHS ".$invr_rchs." CHBT ".$invr_chbt." DOMN ".$invr_domn." CHBT ".$invr_chbt;$sinvr_domn=str_replace(" ","+",$invr_domn); $plus_itms=explode("+",$invr_domn); // print_r ($plus_itms); $invr_domn=$plus_itms[0]; $sinvr_bzv1=str_replace(" ","+",$invr_bzv1); $uinvr_bzv1=urlencode($invr_bzv1); $invr_bzv1=str_replace("+"," ",$invr_bzv1); $uinvr_domn=urlencode($invr_domn); $invr_domn=str_replace("+"," ",$invr_domn); $invr_chbt=str_replace("+"," ",$invr_chbt); $invr_bzv1=str_replace("+"," ",$invr_bzv1); $uinvr_bzv1=str_replace("%E3%80%82",".",$uinvr_bzv1); $invr_domn=str_replace("_"," ",$invr_domn); $invr_bzv1=str_replace("_"," ",$invr_bzv1); if ($invr_domn[0] == " ") { str_replace(" ","",$invr_domn[0]); } if ($invr_chbt[0] == " ") { str_replace(" ","",$invr_chbt[0]); } $sinvr_domn=str_replace(" ","+",$invr_domn); $sinvr_chbt=str_replace(" ","+",$invr_chbt); $chbt_imge="semanta.png"; if ($invr_chbt == "tineke") { $chbt_imge="tineke.png"; $invr_domn="Tineke wordt 65 en nu"; } if ($invr_chbt == "bol") { $chbt_imge="bol.png"; // $invr_domn="U gaat toch ook bestellen bij BOL"; } // echo "
TWEEDE INDRUK TEXT TAAL ".$text_taal."CHBT ".$invr_chbt." BZV1 ".$sinvr_bzv1." BZV2 ".$invr_bzv2." LNKS ".$invr_lnks."RCHS ".$invr_rchs." LGRM ".$invr_lgrm." DOMN ".$invr_domn." SESS ". $fnal_domn=$invr_domn; $fnal_bzv1=$invr_bzv1; $fnal_taal=$invr_taal; $fnal_chbt=$invr_chbt; include ("config.php"); include ("bwrk-bzv1-func.php"); include ("bepl-taal-func.php"); include ("text-isrt-func.php"); include ("bwrk-bzkr-func.php"); include ("smta-tlkd-func-0017.php"); ////////////////// bepaal de datumeigenschappen ////////////// $datm=date("Y-m-d H:i:s", time()); $datm_itms=explode(" ",$datm); // print_r($datm_itms); $datm_datm=$datm_itms[0]; $datm_time=$datm_itms[1]; echo "
".$datm_datm; $sql_gw27="SELECT * FROM cldr where `datm` = '$datm_datm' order by `lnks` desc"; mysql_query("SET CHARACTER SET utf8"); mysql_query("SET NAMES utf8"); $gw27_result = mysql_query($sql_gw27, $link); $gw27_mtch = mysql_num_rows($gw27_result); // echo "
CLDR SQL Aantal entries ".$gw27_mtch." for ".$sql_gw27." and DOMN ".$rbzv1_domn; // echo "
domn ".$invr_domn. "BZV1 ". $invr_bzv1." BZV2 ".$invr_bzv2; if ($gw27_mtch > 0 ) { // echo "
rule SQL Aantal entries ".$gw27_mtch." for ".$sql_gw27; // echo "
domn ".$invr_domn. "BZV1 ". $invr_bzv1." BZV2 ".$invr_bzv2; while ($row = mysql_fetch_assoc($gw27_result)) { $grule=$gram_rule; $gw27_ipad=$row['ipad']; $gw27_taal=$row['taal']; $gw27_domn=$row['domn']; // echo "
GW27 RCHS ".$gw27_rchs; $gw27_lnks=$row['lnks']; $gw27_rchs=$row['rchs']; $gw27_datm=$row['datm']; $bzdt_dag=$gw27_rchs; // echo "
SHRT 0001 GW27 DOMN ".$gw27_domn." LNKS ".$gw27_lnks." RCHS ".$gw27_rchs." PROCES ".$gw27_domn." lnks ".$invr_lnks." RCHS ".$invr_rchs; } } $versie="SEMANTA alpha versie 15.01.03"; $modl="tlkd-domndotphp"; $bzkr_array=bwrk_bzkr("stat@".$userip); // print_r($bzkr_array); if (count($bzkr_array) < 1) { echo "
Nog geen volledige toegangsgegevens."; echo "
Er was nog niet eerder een bezoeker bij ons vanaf dit IP adres: ".$userip." Bent u bewust bij mij op bezoek of is het een toevalligheid"; echo '
'; echo "
Please continue here"; } // print_r($bzkr_array); foreach($bzkr_array as $bzkr_key => $bzkr_val) { $bzkr_itms=explode("=",$bzkr_key); $bzkr_bzkr=$bzkr_itms[0]; $bzkr_name=$bzkr_itms[1]; $bzkr_domn=$bzkr_itms[2]; $bzkr_levl=$bzkr_itms[3]+1; $bzkr_datm=$bzkr_itms[4]; $datm_itms=explode(" ",$bzkr_datm); // echo "
BZKR DATM ".$bzkr_datm; $bzdt_datm=$datm_itms[0]; $bzdt_time=$datm_itms[1]; // echo "
Hallo ".$bzkr_bzkr; // echo $bzdt_dag; // echo "
".$bzdt_dag; } /////////////////////////////////////////// $encd_string=urlencode($invr_bzv1); $encd_string=str_replace("%0A","xdotx",$encd_string); $encd_string=str_replace("%A0","xdotx",$encd_string); $encd_string=str_replace("%09","xdotx",$encd_string); $encd_string=str_replace("%0D","xdotx",$encd_string); $encd_string=str_replace("%00"," ",$encd_string); $encd_string=str_replace("%91"," ",$encd_string); $encd_string=str_replace("%92"," ",$encd_string); echo "
ENCD STRING ".$encd_string; $invr_bzv1=urldecode($encd_string); $sent_itms=explode("xdotx",$invr_bzv1); // echo "
SENT ITMS
"; // print_r($sent_itms); if ($invr_domn == null) { $invr_domn=$sent_itms[0]; $domn_itms=explode(". ",$invr_domn); } // print_r($sent_itms); if (count($sent_itms) == 1) { $tlkd_rslt=smta_tlkd($invr_bzv1."@tlkd"); // include ("conv-tlkd.php"); // print_r($gram_array); // krsort($gram_array); foreach($gram_array as $gram_key => $gram_val) { $gram_dtls=explode("@",$gram_key); $gram_lnks=$gram_dtls[0]; $gram_rchs=$gram_dtls[2]; if ($hrelt != $gram_lnks) { // echo "
GRAM LNKS".$gram_lnks; $hrelt=$gram_lnks; } // echo " ".$gram_rchs; } // echo "FORM ".$wrds_form." GRAM ".$wrds_gram; } if ($invr_domn != null and count($sent_itms) > 1) { $sent_itms[count($sent_itms)+1]=$invr_domn; } $pinvr_domn=$sent_itms[0]; if ($invr_domn != null) { $pinvr_domn=$invr_domn; } echo ""; $sent_text= "Voor het gespreksonderwerp ".$pinvr_domn." bestaat de tekst uit ".strlen($invr_bzv1)." tekens en ".count($sent_itms)." zinnen, u kunt per zin de analyse uitvoeren."; $sinvr_domn=str_replace(" ","+",$pinvr_domn); echo "
".$sent_text; $last_val=""; $cntr_sent=0; // print_r($sent_itms); ///////////////////////////////////////// foreach ($sent_itms as $sent_key => $sent_val) { // echo "
SENT VAL ".$sent_val; // $string = str_replace(' ', '-', $sent_val); // Replaces all spaces with hyphens. // $string = str_replace('/', '-', $string); // Replaces all spaces with hyphens. // $string = preg_replace('/[^A-Za-z0-9\-]/', '', $string); // Removes special chars. //////////////////////////////// // echo "
INVR BZV1 ".$invr_bzv1." STRING ".$string; // $sent_val=str_replace("-"," ",$string); $ssent_val=str_replace(" ","+",$sent_val); $usent_val=urlencode($sent_val); if (strlen($sent_val) > 2) { if ($last_val == null) { $last_val=$invr_bzv1; } $cmds_ipad=$userip; $rshrt_key=str_replace(" ","_",$invr_bzv2); $cntr_sent=$cntr_sent+1; $taal_itms=bepl_taal($invr_bzv1); // echo "
INVR TAAL ".$invr_taal." TEXT "; // print_r($taal_itms); asort($taal_itms); $sw_taal=0; foreach($taal_itms as $taal_key => $taal_val) { // echo " ".$taal_key; if ($taal_key == $invr_taal) { $sw_taal=1; } } if ($sw_taal == 1 ) { // echo "
Er is een teksttaal gevonden die gelijk is aan invoertaal ".$taal_key; $rslt_taal=$invr_taal; $prslt_taal=text_isrt($taal_key."@".$taal_key); $prslt_taal="".$rslt_taal.""; } if ($sw_taal != 1) { // echo "
Er is geen teksttaal gevonden die gelijk is aan invoertaal ".$taal_key; $rslt_taal=$taal_key; $prslt_taal=text_isrt($taal_key."@".$taal_key); $prslt_taal="".$rslt_taal.""; // echo "
RSLT TAAL ".$rslt_taal; } $cmds_bzv2=$sent_val."[tref[".$rslt_taal."[".$sent_itms[0]."[".$last_val."[".$cntr_sent; $last_val=$sent_val; echo "
CMDS BZV2 ".$cmds_bzv2; include ("chbt-cmds-code-2.php"); $cmds_bzv2=$sent_val."[tref[".$rslt_taal."[".$invr_domn."[".$invr_corp."[".$cntr_sent; echo "
NAAR TREF CMDS BZV2 ".$cmds_bzv2; include ("chbt-cmds-code-2.php"); $sinvr_chbt=str_replace(" ","+",$invr_chbt); // echo "
LGRM domn ".$invr_domn. "BZV1 ". $invr_bzv1." BZV2 ".$invr_bzv2." INVR CHBT ".$invr_chbt; echo ""; } } echo "
CONVERSATIE ".$rslt_taal." ".$taal_val."".substr($sent_val,0,64).".....
"; /////////////////////// $geen_antwoord=text_isrt($invr_taal."@Helaas heb ik hier nog geen antwoord voor"); $invr_domn=str_replace("+"," ",$invr_domn); $uinvr_domn=urlencode($invr_domn); $sinvr_domn=str_replace(" ","+",$invr_domn); $bzv1_itms=explode(" ",$invr_bzv1); // echo "
COUNT ITEMS ".count($bzv1_itms); $cntr_itms=count($bzv1_itms); $rbzv1_domn=str_replace(" ","_",$invr_domn); $rinvr_bzv1=str_replace(" ","_",$invr_bzv1); $sinvr_bzv1=str_replace(" ","+",$invr_bzv1); $sinvr_chbt=str_replace(" ","+",$invr_chbt); if ($cntr_itms < 128 and $cntr_itms > 0 ) { // echo "
Hier gaan we mee aan de slag ".$invr_domn." BZV1 ".$invr_bzv1; $sql_gw27="SELECT * FROM rule where `lnks` = '$rinvr_bzv1' order by `lnks` desc"; mysql_query("SET CHARACTER SET utf8"); mysql_query("SET NAMES utf8"); $gw27_result = mysql_query($sql_gw27, $link); $gw27_mtch = mysql_num_rows($gw27_result); // echo "
GRAM rule SQL Aantal entries ".$gw27_mtch." for ".$sql_gw27." and DOMN ".$rbzv1_domn; // echo "
domn ".$invr_domn. "BZV1 ". $invr_bzv1." BZV2 ".$invr_bzv2; if ($gw27_mtch == 0) { // echo "
".$geen_antwoord.""; $invr_bzv1=$invr_domn; // echo "

".substr($invr_bzv1,0,256).""; // include ("word-rule.php"); include ("tlkd-rslt.php"); // print_r($vrag_array); } ////////////////////////////////////////////////////////////////////// if ($gw27_mtch > 0 ) { // echo "
rule SQL Aantal entries ".$gw27_mtch." for ".$sql_gw27; // echo "
domn ".$invr_domn. "BZV1 ". $invr_bzv1." BZV2 ".$invr_bzv2; // echo "Als er meerdere zinnen in het antwoord zitten, kunt u de tekst verder verwerken door er op te klikken."; // echo "
Gesprekspartner ".$gw27_ipad; if ($gw27_ipad== $userip) { // $invr_chbt=$bzkr_bzkr; } // echo "
Gesprekspartner ".$invr_chbt; $gw27_taal=$row['taal']; $gw27_domn=$row['domn']; $invr_domn=$gw27_domn; include ("tlkd-rslt.php"); // echo "
GW27 RCHS ".$gw27_rchs; $gw27_lnks=$row['lnks']; $gw27_rchs=$row['rchs']; include ("tlkd-rslt.php"); $sgw27_lnks=str_replace("_"," ",$gw27_lnks); $sgw27_rchs=str_replace(" ","+",$gw27_rchs); $ugw27_rchs=urlencode($sgw27_rchs); $gw27_itms=explode(".",$gw27_rchs); // print_r($gw27_itms); if (count($gw27_itms) > 1) { // echo "

".substr($gw27_rchs,0,64)."
"; } if (count($gw27_itms) == 1) { // echo "
".$gw27_rchs.""; $sinvr_bzv2=str_replace(" ","+",$gw27_rchs); $sinvr_domn=str_replace(" ","+",$invr_domn); // echo "

".substr($gw27_rchs,0,64)."
"; } } } } $invr_domn=str_replace("+"," ",$invr_domn); $datum=text_isrt($invr_taal."@datum"); $beschrijving=text_isrt($invr_taal."@beschrijving"); $chatbot=text_isrt($invr_taal."@chatbot"); $chatbotkarakter=text_isrt($invr_taal."@chatbotkarakter"); $uw_bezoek=text_isrt($invr_taal."@U bezoekt ons vanuit IP Adres"); $kennisdomeinen=text_isrt($invr_taal."@kennisdomeinen"); $bezoeker=text_isrt($invr_taal."@bezoeker"); $uw_antwoord=text_isrt($invr_taal."@Wat zou uw antwoord zijn?"); $uw_vraag=text_isrt($invr_taal."@Uw vraag"); $suw_antwoord=str_replace(" ","_",$uw_antwoord); $gebruikersteksten=text_isrt($invr_taal."@gebruikersteksten"); $onderwerpen=text_isrt($invr_taal."@onderwerpen"); $woordonderhoud=text_isrt($invr_taal."@woordonderhoud"); $chatbotleraar=text_isrt($invr_taal."@Chatbotleraar"); $opleiding=text_isrt($invr_taal."@opleiding"); $we_spreken_nu=text_isrt($invr_taal."@we spreken nu")." ".text_isrt($invr_taal."@".$invr_taal); $taal=text_isrt($invr_taal."@".$invr_taal); $wat_wij_al_weten=text_isrt($invr_taal."@wat wij al weten van u"); $swat_wij_al_weten=''.$wat_wij_al_weten.''; $geen_antwoord=text_isrt($invr_taal."@Helaas heb ik hier nog geen antwoord voor"); // echo "
".$onderwerpen.""; if ($invr_taal == "nederlands") { // echo "
".$taal."=".$chatbotkarakter."<>".$opleiding.""; } // echo "
DERDE INDRUK TEXT TAAL ".$text_taal." BZV1 ".$invr_bzv1." BZV2 ".$invr_bzv2." LNKS ".$invr_lnks."RCHS ".$invr_rchs." LGRM ".$invr_lgrm." DOMN ".$invr_domn." CHBT "; echo "