Just been doing some heavy translation from German to English. Which lead to writing a simple command line tool for translating via Google – waste time to save time in other words. Getting a prototype up from scratch took about 15 minutes (which sheds a light on blog spam I guess). Have cleaned it up a bit and dropping it here in case anyone can use it.

Two major things that still need doing;

- validation of the language pair CLI option, to keep users sane

- character set conversion – right now getting UFT8 from Google so XML_HTMLSax can parse correctly (it relies on the str_ functions) but not doing anything clever after that.

…and there’s probably a bug or three.


#!/usr/local/bin/php
/**
* License: http://www.php.net/license/3_0.txt
*/
//------------------------------------------------------------------------------
require_once 'Console/Getopt.php';
require_once 'HTTP/Request.php';
require_once 'XML/HTMLSax3.php';

//------------------------------------------------------------------------------
class Google_Translate {

var $langpair;
var $proxy = null;

function Google_Translate($langpair, $proxy = null) {

$this->langpair = $langpair;
$this->proxy = $proxy;

}

function query($text) {
$R = & new HTTP_Request('http://translate.google.com/translate_t');
$R->setMethod('POST');

if ( !is_null($this->proxy) ) {
$pxy = parse_url($this->proxy);
$R->setProxy($pxy['host'],$pxy['port'],$pxy['user'],$pxy['pass']);
}

$R->addPostData('text', utf8_encode($text));
$R->addPostData('langpair', $this->langpair);
$R->addPostData('ie','UTF8');
$R->addPostData('oe','UTF8');

$res = $R->sendRequest();

if ( PEAR::isError($res) ) {
fwrite(STDERR, "Connection problem: ".$res->toString()."\n");
exit(1);
}

if ($R->getResponseCode() != '200') {
fwrite(STDOUT, "Invalid HTTP Status: ".$R->getResponseCode()."\n");
exit(1);
}

return $R->getResponseBody();
}

function translate($text) {
$P = & new Google_Translate_Parser();
return $P->parse($this->query($text));
}
}

//------------------------------------------------------------------------------
class Google_Translate_Parser {

var $inResult = FALSE;
var $result = '';

function open($p, $tag, $attrs) {
if ( $tag == 'textarea' && isset($attrs['name']) && $attrs['name'] == 'q' ) {
$this->inResult = TRUE;
}
}

function close($p, $tag) {
if ( $this->inResult && $tag == 'textarea' ) {
$this->inResult = FALSE;
}
}

function data($p, $data) {
if ( $this->inResult ) {
$this->result .= $data;
}
}

function parse($html) {

$P = & new XML_HTMLSax3();
$P->set_object($this);
$P->set_element_handler('open','close');
$P->set_data_handler('data');
$P->parse($html);

return utf8_decode($this->result);
}
}

//------------------------------------------------------------------------------
function usage() {
$usage = << Usage: ./gtrans.php [ OPTIONS ] [ Text to tranlate ]

Translates input string via Google's language tools.

-l=LANGPAIR Language to-from e.g. de-en
-p=PROXY Proxy server URL (optional)
-h Display usage

EOD;
fwrite(STDOUT,$usage);
exit(0);
}

//------------------------------------------------------------------------------
$args = Console_Getopt::readPHPArgv();

if ( PEAR::isError($args) ) {
fwrite(STDERR,$args->getMessage()."\n");
exit(1);
}

if ( realpath($_SERVER['argv'][0]) == __FILE__ ) {
$options = Console_Getopt::getOpt($args,'hl:p:');
} else {
$options = Console_Getopt::getOpt2($args,'hl:p:');
}

if ( PEAR::isError($options) ) {
fwrite(STDERR,$options->getMessage()."\n");
usage();
}

$proxy = null;

foreach ( $options[0] as $option ) {
switch ( $option[0] ) {
case 'h':
usage();
break;

case 'l':
$lang = str_replace('-','|',$option[1]);
break;

case 'p':
$proxy = $option[1];
break;
}
}

$G = & new Google_Translate($lang, $proxy);
echo $G->translate($options[1][0])."\n";
exit(0);

Get Started with
Ruby on Rails

Github, Twitter and Hulu. All huge. All successful. All Rails.

Learn the web development framework of the moment with our newest book and course.

Learn Rails

Harry Fuecks

More Posts