//include "verb_forms.php4";
include_once "utf8/utf8.class.php";
$xfst_path = "/spd25/htdocs/hyperlex2/nahuatl/xfst_dir/xfst -utf8 -q -e 'loadd SurfaceForms.fsm' -e 'regex GlSR;'";
$in = file("Burroh.html");
unset($words);
$verbs = array();
$commands = $xfst_path;
$verbStem;
foreach($in as $line) {
$line = strtolower($line);
$line = utf8_encode($line);
$line = ereg_replace("[.?,;']","",$line);
$line = explode(" ",$line);
foreach($line as $word) {
$word = trim($word);
if(($word != "") && !ereg("=|[0-9]|Roman",$word)){
$word = ereg_replace("<.*>","",$word);
$word = ereg_replace("[<>|{]","",$word);
$commands .= " -e 'apply up $word'";
}
}
}
$commands .= " -stop";
unset($parsable);
exec($commands,$parsable);
$commands = $xfst_path;
foreach($parsable as $p) {
$commands .= " -e 'apply down $p'";
}
$commands .= " -stop";
unset($verbs);
exec($commands,$verbs);
sort($verbs);
$verbs = array_unique($verbs);
/*
foreach($verbs as $v) {
echo "$v
";
}
*/
$in = file("Burroh.html");
$s = "";
foreach($in as $line) {
$s .= $line;
}
$newLink = "";
$other="";
foreach($verbs as $v) {
$v = utf8_decode($v);
//$s = ereg_replace($v,"$v",$s);
//$newLink = " $v";
//$other = getVerbSenses($v);
$s = ereg_replace($v,$newLink,$s);
}
//" " and $
$out = fopen("Burroh_with_links_lg.html","w");
fwrite($out,$s);
fclose($out);
//echo ";
function GetSenses($word){
global $verbStem;
$urltoSenses = "http://hyperlex2.ldc.upenn.edu/nahuatl/search_results.php4?user_lang=english&condition=word_search&word=".$verbStem."&entry_template=englishwordsense.html&bg_template=english%senses_template.html";
$strIframe = htmlentities (" |
");
return $strIframe;
}
function GetVerbSenses($word){
{
global $verbStem;
$table = "";
$word = strtolower($word);
//$word = utf8_encode($word);
$utfConverter = new utf8();
$word = $utfConverter->strToUtf8($word);
$xfst_path = "/spd25/htdocs/hyperlex2/nahuatl/xfst_dir/xfst -utf8 -e 'loadd SurfaceForms.fsm' -e 'regex GlSR;'";
$command = $xfst_path." -e 'apply up $word' -stop";
unset($parse);
exec($command,$parse);
//$result = utf8_decode(trim($parse[3]));
$result = $utfConverter->utf8ToStr(trim($parse[3]));
if($result != "") {
$command = "/spd25/htdocs/hyperlex2/nahuatl/xfst_dir/xfst -utf8 -e 'loadd SurfaceForms.fsm'";
//$command = "xfst -utf8 -e 'loadd SurfaceForms.fsm'";
$command .= " -e 'regex GlUR;' -e 'apply down $result' -stop";
unset($parse);
$foo = exec($command,$parse);
$temp = $parse[3];
/*
foreach($parse2 as $p) {
echo utf8_decode($p)."
";
}
*/
if($temp != "") {
$table = "
";
$table = $table . "Parse: | $temp ";
$table = $table . " |
";
}
$table = $table . "";
$table = $table . "Gloss: | $result ";
$table = $table . " |
";
$parts = explode("-",$result);
$index = count($parts)-2;
$results[0] = $parts[$index];
$verbStem = $results[0];
$table = $table . "";
$table = $table . "Verb stem: | ";
$table = $table . "".$results[0]."";
$table = $table . " |
";
if($index == 1) {
$table = $table . "";
$results[1] = "intrans";
$table = $table . "Part of speech: | Intransitive Oapan verb";
$table = $table . " |
";
}
else if($index == 2) {
$table = $table . "";
$results[1] = "trans";
$table = $table . "Part of speech: | Transitive Oapan verb";
//$table = $table . " |
";
$table = $table . "";
}
return $table;
}
return "";
}
}
?>