#!/usr/local/bin/perl #This is a program to generate 53 html files open (READ, "data"); $line = ; $count = 0; while($line ne ""){ #The following if loop is to check the beginning of each html file if(($line eq "aa\n")||($line eq "aai\n")||($line eq "aau\n")||($line eq "aam\n")||($line eq "aan\n")||($line eq "aang\n")||($line eq "aap\n")||($line eq "aat\n")||($line eq "aak\n")||($line eq "ai\n")||($line eq "au\n")||($line eq "am\n")||($line eq "an\n")||($line eq "ang\n")||($line eq "ap\n")||($line eq "at\n")||($line eq "ak\n")||($line eq "ei\n")||($line eq "eng\n")||($line eq "ek\n")||($line eq "e\n")||($line eq "i\n")||($line eq "iu\n")||($line eq "im\n")||($line eq "in\n")||($line eq "ing\n")||($line eq "ip\n")||($line eq "it\n")||($line eq "ik\n")||($line eq "ou\n")||($line eq "o\n")||($line eq "oi\n")||($line eq "on\n")||($line eq "ong\n")||($line eq "ot\n")||($line eq "ok\n")||($line eq "oe\n")||($line eq "eoi\n")||($line eq "eon\n")||($line eq "oeng\n")||($line eq "eot\n")||($line eq "oek\n")||($line eq "u\n")||($line eq "ui\n")||($line eq "un\n")||($line eq "ung\n")||($line eq "ut\n")||($line eq "uk\n")||($line eq "yu\n")||($line eq "yun\n")||($line eq "yut\n")||($line eq "m\n")||($line eq "ng\n")){ #The followint if loop is to end the html files if ($count!=0){ print WRITE ("\n\n\n"); } chop($line); $name=$line; $line=$line.".html"; open (WRITE, ">/can/finals/$line"); print WRITE ("\n"); print WRITE ("\n"); print WRITE ("

\n"); print WRITE ("

$name\n"); print WRITE ("

\n"); print WRITE ("

\n"); print WRITE ("\n"); $count++; $line = ; } #The following else loop is to print out the content of each html file else{ chop($line); #The following statement is to split the line into 2 elements @array=split(/:/,$line); chop($array[1]); #The followint is to split the 2nd element into Chinese characters @word=split(/ +/,$array[1]); print WRITE ("\n"); $line = ; if ($line eq ""){ print WRITE ("
$array[0] \n"); print WRITE (" "); $number=1; while($word[$number] ne ""){ #The if loop is to cancel "," this can not be used in the last word in the "data" file if ($word[$number] ne "ó"){ chop($word[$number]); } #The following is to get the lower byte of Chinese character $sub2=substr($word[$number],1,1); #get the decimal of the ascii $char1=ord($word[$number]); $char2=ord($sub2); #get the heximal of the decimal number $hexa1=sprintf("%x", $char1); $hexa2=sprintf("%x", $char2); print WRITE ("$word[$number], \n"); $number++; } print WRITE ("
\n\n\n"); } } } close(READ); close(WRITE);