我正在尝试将javascript的源代码转换为类似逻辑的php源代码。因此，功能的功能保持不变，但是php代码可以直接在php中使用，而无需使用任何开销代码。
function convert_to_unicode(text) {
const array_one = new Array(
// "(",")",
"ñ", "Q+Z", "sas", "aa", ")Z", "ZZ", "‘", "’", "“", "”",
"å", "ƒ", "„", "…", "†", "‡", "ˆ", "‰", "Š", "‹",
"¶+", "d+", "[+k", "[+", "x+", "T+", "t+", "M+", "<+", "Q+", ";+", "j+", "u+",
"Ùk", "Ù", "ä", "–", "—", "é", "™", "=kk", "f=k",
"à", "á", "â", "ã", "ºz", "º", "í", "{k", "{", "=", "«",
"Nî", "Vî", "Bî", "Mî", "<î", "|", "K", "}",
"J", "Vª", "Mª", "<ªª", "Nª", "Ø", "Ý", "nzZ", "æ", "ç", "Á", "xz", "#", ":",
"v‚", "vks", "vkS", "vk", "v", "b±", "Ã", "bZ", "b", "m", "Å", ",s", ",", "_",
"ô", "d", "Dk", "D", "[k", "[", "x", "Xk", "X", "Ä", "?k", "?", "³",
"pkS", "p", "Pk", "P", "N", "t", "Tk", "T", ">", "÷", "¥",
"ê", "ë", "V", "B", "ì", "ï", "M+", "<+", "M", "<", ".k", ".",
"r", "Rk", "R", "Fk", "F", ")", "n", "/k", "èk", "/", "Ë", "è", "u", "Uk", "U",
"i", "Ik", "I", "Q", "¶", "c", "Ck", "C", "Hk", "H", "e", "Ek", "E",
";", "¸", "j", "y", "Yk", "Y", "G", "o", "Ok", "O",
"'k", "'", "\"k", "\"", "l", "Lk", "L", "g",
"È", "z",
"Ì", "Í", "Î", "Ï", "Ñ", "Ò", "Ó", "Ô", "Ö", "Ø", "Ù", "Ük", "Ü",
"‚", "ks", "kS", "k", "h", "q", "w", "`", "s", "S",
"a", "¡", "%", "W", "•", "·", "∙", "·", "~j", "~", "\\", "+", " ः",
"^", "*", "Þ", "ß", "(", "¼", "½", "¿", "À", "¾", "A", "-", "&", "&", "Œ", "]", "~ ", "@");
const array_two = new Array(
//"¼","½",
"॰", "QZ+", "sa", "a", "र्द्ध", "Z", "\"", "\"", "'", "'",
"०", "१", "२", "३", "४", "५", "६", "७", "८", "९",
"फ़्", "क़", "ख़", "ख़्", "ग़", "ज़्", "ज़", "ड़", "ढ़", "फ़", "य़", "ऱ", "ऩ", // one-byte nukta varNas
"त्त", "त्त्", "क्त", "दृ", "कृ", "न्न", "न्न्", "=k", "f=",
"ह्न", "ह्य", "हृ", "ह्म", "ह्र", "ह्", "द्द", "क्ष", "क्ष्", "त्र", "त्र्",
"छ्य", "ट्य", "ठ्य", "ड्य", "ढ्य", "द्य", "ज्ञ", "द्व",
"श्र", "ट्र", "ड्र", "ढ्र", "छ्र", "क्र", "फ्र", "र्द्र", "द्र", "प्र", "प्र", "ग्र", "रु", "रू",
"ऑ", "ओ", "औ", "आ", "अ", "ईं", "ई", "ई", "इ", "उ", "ऊ", "ऐ", "ए", "ऋ",
"क्क", "क", "क", "क्", "ख", "ख्", "ग", "ग", "ग्", "घ", "घ", "घ्", "ङ",
"चै", "च", "च", "च्", "छ", "ज", "ज", "ज्", "झ", "झ्", "ञ",
"ट्ट", "ट्ठ", "ट", "ठ", "ड्ड", "ड्ढ", "ड़", "ढ़", "ड", "ढ", "ण", "ण्",
"त", "त", "त्", "थ", "थ्", "द्ध", "द", "ध", "ध", "ध्", "ध्", "ध्", "न", "न", "न्",
"प", "प", "प्", "फ", "फ्", "ब", "ब", "ब्", "भ", "भ्", "म", "म", "म्",
"य", "य्", "र", "ल", "ल", "ल्", "ळ", "व", "व", "व्",
"श", "श्", "ष", "ष्", "स", "स", "स्", "ह",
"ीं", "्र",
"द्द", "ट्ट", "ट्ठ", "ड्ड", "कृ", "भ", "्य", "ड्ढ", "झ्", "क्र", "त्त्", "श", "श्",
"ॉ", "ो", "ौ", "ा", "ी", "ु", "ू", "ृ", "े", "ै",
"ं", "ँ", "ः", "ॅ", "ऽ", "ऽ", "ऽ", "ऽ", "्र", "्", "?", "़", ":",
"‘", "’", "“", "”", ";", "(", ")", "{", "}", "=", "।", ".", "-", "µ", "॰", ",", "् ", "/");
var array_one_length = array_one.length;
var modified_substring = text;
//****************************************************************************************
// Break the long text into small bunches of max. max_text_size characters each.
//****************************************************************************************
var text_size = modified_substring.length;
var processed_text = ''; //blank
var sthiti1 = 0; var sthiti2 = 0; var chale_chalo = 1;
var max_text_size = 6000;
while (chale_chalo == 1) {
sthiti1 = sthiti2;
if (sthiti2 < (text_size - max_text_size)) {
sthiti2 += max_text_size;
while (modified_substring.charAt(sthiti2) != ' ') { sthiti2--; }
}
else { sthiti2 = text_size; chale_chalo = 0 }
var modified_substring = modified_substring.substring(sthiti1, sthiti2);
Replace_Symbols();
processed_text += modified_substring;
}
function Replace_Symbols() {
if (modified_substring != "")
{
for (input_symbol_idx = 0; input_symbol_idx < array_one_length; input_symbol_idx++)
{
idx = 0;
while (idx != -1)
{
modified_substring = modified_substring.replace(array_one[input_symbol_idx], array_two[input_symbol_idx])
idx = modified_substring.indexOf(array_one[input_symbol_idx])
}
}
modified_substring = modified_substring.replace(/±/g, "Zं"); // at some places ì is used eg in "कर्कंधु,पूर्णांक".
modified_substring = modified_substring.replace(/Æ/g, "र्f"); // at some places Æ is used eg in "धार्मिक".
var position_of_i = modified_substring.indexOf("f")
while (position_of_i != -1) //while-02
{
var charecter_next_to_i = modified_substring.charAt(position_of_i + 1)
var charecter_to_be_replaced = "f" + charecter_next_to_i
modified_substring = modified_substring.replace(charecter_to_be_replaced, charecter_next_to_i + "ि")
position_of_i = modified_substring.search(/f/, position_of_i + 1) // search for i ahead of the current position.
}
modified_substring = modified_substring.replace(/Ç/g, "fa"); // at some places Ç is used eg in "किंकर".
modified_substring = modified_substring.replace(/É/g, "र्fa"); // at some places É is used eg in "शर्मिंदा"
var position_of_i = modified_substring.indexOf("fa")
while (position_of_i != -1) //while-02
{
var charecter_next_to_ip2 = modified_substring.charAt(position_of_i + 2)
var charecter_to_be_replaced = "fa" + charecter_next_to_ip2
modified_substring = modified_substring.replace(charecter_to_be_replaced, charecter_next_to_ip2 + "िं")
position_of_i = modified_substring.search(/fa/, position_of_i + 2) // search for i ahead of the current position.
}
;
modified_substring = modified_substring.replace(/Ê/g, "ीZ"); // at some places Ê is used eg in "किंकर".
var position_of_wrong_ee = modified_substring.indexOf("ि्")
while (position_of_wrong_ee != -1) //while-03
{
var consonent_next_to_wrong_ee = modified_substring.charAt(position_of_wrong_ee + 2)
var charecter_to_be_replaced = "ि्" + consonent_next_to_wrong_ee
modified_substring = modified_substring.replace(charecter_to_be_replaced, "्" + consonent_next_to_wrong_ee + "ि")
position_of_wrong_ee = modified_substring.search(/ि्/, position_of_wrong_ee + 2) // search for 'wrong ee' ahead of the current position.
}
set_of_matras = "अ आ इ ई उ ऊ ए ऐ ओ औ ा ि ी ु ू ृ े ै ो ौ ं : ँ ॅ"
var position_of_R = modified_substring.indexOf("Z")
while (position_of_R > 0) // while-04
{
probable_position_of_half_r = position_of_R - 1;
var charecter_at_probable_position_of_half_r = modified_substring.charAt(probable_position_of_half_r)
while (set_of_matras.match(charecter_at_probable_position_of_half_r) != null) // while-05
{
probable_position_of_half_r = probable_position_of_half_r - 1;
charecter_at_probable_position_of_half_r = modified_substring.charAt(probable_position_of_half_r);
}
charecter_to_be_replaced = modified_substring.substr(probable_position_of_half_r, (position_of_R - probable_position_of_half_r));
new_replacement_string = "र्" + charecter_to_be_replaced;
charecter_to_be_replaced = charecter_to_be_replaced + "Z";
modified_substring = modified_substring.replace(charecter_to_be_replaced, new_replacement_string);
position_of_R = modified_substring.indexOf("Z");
}
}
}
return processed_text;
}
我已经转换了部分代码，但其工作原理类似于javascript
<?php
function charAt($str,$pos) {
return (substr($str,$pos,1) !== false) ? substr($str,$pos,1) : -1;
}
function convert_to_unicode($text)
{
$array_one = array(
// "(",")",
"ñ","Q+Z","sas","aa",")Z","ZZ","‘","’","“","”",
"å", "ƒ", "„", "…", "†", "‡", "ˆ", "‰", "Š", "‹",
"¶+", "d+", "[+k","[+", "x+", "T+", "t+", "M+", "<+", "Q+", ";+", "j+", "u+",
"Ùk", "Ù", "ä", "–", "—","é","™","=kk","f=k",
"à", "á", "â", "ã", "ºz", "º", "í", "{k", "{", "=", "«",
"Nî", "Vî", "Bî", "Mî", "<î", "|", "K", "}",
"J", "Vª", "Mª", "<ªª", "Nª", "Ø", "Ý", "nzZ", "æ", "ç", "Á", "xz", "#", ":",
"v‚","vks", "vkS", "vk", "v", "b±", "Ã", "bZ", "b", "m", "Å", ",s", ",", "_",
"ô", "d", "Dk", "D", "[k", "[", "x","Xk", "X", "Ä", "?k", "?", "³",
"pkS", "p", "Pk", "P", "N", "t", "Tk", "T", ">", "÷", "¥",
"ê", "ë", "V", "B", "ì", "ï", "M+", "<+", "M", "<", ".k", ".",
"r", "Rk", "R", "Fk", "F", ")", "n", "/k", "èk", "/", "Ë", "è", "u", "Uk", "U",
"i", "Ik", "I", "Q", "¶", "c", "Ck", "C", "Hk", "H", "e", "Ek", "E",
";", "¸", "j", "y", "Yk", "Y", "G", "o", "Ok", "O",
"'k", "'", "\"k", "\"", "l", "Lk", "L", "g",
"È", "z",
"Ì", "Í", "Î", "Ï", "Ñ", "Ò", "Ó", "Ô", "Ö", "Ø", "Ù","Ük", "Ü",
"‚", "ks", "kS", "k", "h", "q", "w", "`", "s", "S",
"a", "¡", "%", "W", "•", "·", "∙", "·", "~j", "~", "\\","+"," ः",
"^", "*", "Þ", "ß", "(", "¼", "½", "¿", "À", "¾", "A", "-", "&", "&", "Œ", "]","~ ","@");
$array_two = array(
//"¼","½",
"॰","QZ+","sa","a","र्द्ध","Z","\"","\"","'","'",
"०", "१", "२", "३", "४", "५", "६", "७", "८", "९",
"फ़्", "क़", "ख़", "ख़्", "ग़", "ज़्", "ज़", "ड़", "ढ़", "फ़", "य़", "ऱ", "ऩ", // one-byte nukta varNas
"त्त", "त्त्", "क्त", "दृ", "कृ","न्न","न्न्","=k","f=",
"ह्न", "ह्य", "हृ", "ह्म", "ह्र", "ह्", "द्द", "क्ष", "क्ष्", "त्र", "त्र्",
"छ्य", "ट्य", "ठ्य", "ड्य", "ढ्य", "द्य", "ज्ञ", "द्व",
"श्र", "ट्र", "ड्र", "ढ्र", "छ्र", "क्र", "फ्र", "र्द्र", "द्र", "प्र", "प्र", "ग्र", "रु", "रू",
"ऑ", "ओ", "औ", "आ", "अ", "ईं", "ई", "ई", "इ", "उ", "ऊ", "ऐ", "ए", "ऋ",
"क्क", "क", "क", "क्", "ख", "ख्", "ग", "ग", "ग्", "घ", "घ", "घ्", "ङ",
"चै", "च", "च", "च्", "छ", "ज", "ज", "ज्", "झ", "झ्", "ञ",
"ट्ट", "ट्ठ", "ट", "ठ", "ड्ड", "ड्ढ", "ड़", "ढ़", "ड", "ढ", "ण", "ण्",
"त", "त", "त्", "थ", "थ्", "द्ध", "द", "ध", "ध", "ध्", "ध्", "ध्", "न", "न", "न्",
"प", "प", "प्", "फ", "फ्", "ब", "ब", "ब्", "भ", "भ्", "म", "म", "म्",
"य", "य्", "र", "ल", "ल", "ल्", "ळ", "व", "व", "व्",
"श", "श्", "ष", "ष्", "स", "स", "स्", "ह",
"ीं", "्र",
"द्द", "ट्ट","ट्ठ","ड्ड","कृ","भ","्य","ड्ढ","झ्","क्र","त्त्","श","श्",
"ॉ", "ो", "ौ", "ा", "ी", "ु", "ू", "ृ", "े", "ै",
"ं", "ँ", "ः", "ॅ", "ऽ", "ऽ", "ऽ", "ऽ", "्र", "्", "?", "़",":",
"‘", "’", "“", "”", ";", "(", ")", "{", "}", "=", "।", ".", "-", "µ", "॰", ",","् ","/");
$array_one_length = sizeof($array_one);
$modified_substring = $text;
$text_size = strlen($modified_substring);
$processed_text = '' ; //blank
$sthiti1 = 0 ;
$sthiti2 = 0 ;
$chale_chalo = 1 ;
$max_text_size = 6000;
while ( $chale_chalo == 1 )
{
$sthiti1 = $sthiti2 ;
if ( $sthiti2 < ( $text_size - $max_text_size ) )
{
$sthiti2 += $max_text_size ;
while (charAt($modified_substring,$sthiti2) != ' ')
{
$sthiti2--;
}
}
else
{
$sthiti2 = $text_size ;
$chale_chalo = 0;
}
$modified_substring = substr($modified_substring,$sthiti1, $sthiti2);
$modified_substring = Replace_Symbols($modified_substring,$array_one_length,$array_one,$array_two,$text);
}
return $modified_substring;
}
function Replace_Symbols($modified_substring,$array_one_length,$array_one,$array_two,$text)
{
if( $modified_substring != "" ) // if stringto be converted is non-blank then no need of any processing.
{
for ($input_symbol_idx = 0; $input_symbol_idx < $array_one_length; $input_symbol_idx++ )
{
$idx = true ;
while ($idx != false)
{
$modified_substring = str_replace($array_one[$input_symbol_idx],$array_two[$input_symbol_idx],$modified_substring);
$idx = strpos($modified_substring,$array_one[$input_symbol_idx]);
}
}
//$position_of_i = strpos(utf8_decode($modified_substring),"f");
$set_of_matras = "अ आ इ ई उ ऊ ए ऐ ओ औ ा ि ी ु ू ृ े ै ो ौ ं : ँ ॅ";
$position_of_R = strpos(utf8_decode($modified_substring), "Z");
while ($position_of_R > 0 ) // while-04
{
$probable_position_of_half_r = $position_of_R - 1;
$charecter_at_probable_position_of_half_r = $array_two[array_search($text{$probable_position_of_half_r}, $array_one)];
var_dump(preg_match($charecter_at_probable_position_of_half_r,$set_of_matras) != false);
while(preg_match($charecter_at_probable_position_of_half_r,$set_of_matras)){
$probable_position_of_half_r = $probable_position_of_half_r - 1;
echo $probable_position_of_half_r;
$charecter_at_probable_position_of_half_r = $modified_substring{$probable_position_of_half_r};
}
$charecter_to_be_replaced = $array_two[array_search(substr($text, $probable_position_of_half_r, $position_of_R - $probable_position_of_half_r), $array_one)];
$new_replacement_string = "र्".$charecter_to_be_replaced;
$charecter_to_be_replaced = $charecter_to_be_replaced."Z";
$modified_substring = str_replace($charecter_to_be_replaced,$new_replacement_string,$modified_substring);
$position_of_R = strpos(utf8_decode($modified_substring), "Z");
$position_of_R--;
}
}
return $modified_substring;
}
?>
PHP
preg_match($charecter_at_probable_position_of_half_r,$set_of_matras) != false;
返回假，
与
相同JavaScript
console.log(set_of_matras.match(charecter_at_probable_position_of_half_r) != null);
它返回true;