| 1 |
#!/usr/local/bin/php
|
| 2 |
<?php
|
| 3 |
// $Id: extractor.php,v 1.7 2005/01/08 19:17:33 goba Exp $
|
| 4 |
|
| 5 |
/*
|
| 6 |
Extracts translatable strings from t(), t(,array()) and format_plural()
|
| 7 |
function calls, plus adds some file specific strings. Only literal strings
|
| 8 |
with no embedded variables can be extracted. Outputs a POT file on
|
| 9 |
STDOUT, errors on STDERR
|
| 10 |
|
| 11 |
Copyright (c) 2003, 2004 Alfa21 Outsourcing
|
| 12 |
Created by Jacobo Tarrio <jtarrio [at] alfa21.com>
|
| 13 |
with contributions from Gabor Hojtsy <goba [at] php.net>
|
| 14 |
Licensed under the terms of the GNU General Public License
|
| 15 |
*/
|
| 16 |
|
| 17 |
set_time_limit(0);
|
| 18 |
if (!defined("STDERR")) {
|
| 19 |
define("STDERR", fopen("php://stderr", "w"));
|
| 20 |
}
|
| 21 |
|
| 22 |
$argv = $GLOBALS['argv'];
|
| 23 |
array_shift ($argv);
|
| 24 |
if (!count($argv)) {
|
| 25 |
print "Usage: extractor.php file1 [file2 [...]]\n\n";
|
| 26 |
return 1;
|
| 27 |
}
|
| 28 |
|
| 29 |
|
| 30 |
$strings = $file_versions = array();
|
| 31 |
|
| 32 |
foreach ($argv as $file) {
|
| 33 |
$code = file_get_contents($file);
|
| 34 |
|
| 35 |
// Extract raw tokens
|
| 36 |
$raw_tokens = token_get_all($code);
|
| 37 |
|
| 38 |
// Remove whitespace and HTML
|
| 39 |
$tokens = array();
|
| 40 |
$lineno = 1;
|
| 41 |
foreach ($raw_tokens as $tok) {
|
| 42 |
if ((!is_array($tok)) || (($tok[0] != T_WHITESPACE) && ($tok[0] != T_INLINE_HTML))) {
|
| 43 |
if (is_array($tok)) {
|
| 44 |
$tok[] = $lineno;
|
| 45 |
}
|
| 46 |
$tokens[] = $tok;
|
| 47 |
}
|
| 48 |
if (is_array($tok)) {
|
| 49 |
$lineno += count(split("\n", $tok[1])) - 1;
|
| 50 |
} else {
|
| 51 |
$lineno += count(split("\n", $tok)) - 1;
|
| 52 |
}
|
| 53 |
}
|
| 54 |
|
| 55 |
find_t_calls($tokens, $file);
|
| 56 |
find_watchdog_calls($tokens, $file);
|
| 57 |
find_format_plural_calls($tokens, $file);
|
| 58 |
|
| 59 |
find_perm_hook($code, $file);
|
| 60 |
find_node_types_hook($code, $file);
|
| 61 |
find_module_name($code, $file);
|
| 62 |
find_language_names($code, $file);
|
| 63 |
find_version_number($code, $file);
|
| 64 |
|
| 65 |
add_date_strings($file);
|
| 66 |
add_format_interval_strings($file);
|
| 67 |
}
|
| 68 |
|
| 69 |
|
| 70 |
foreach ($strings as $str => $fileinfo) {
|
| 71 |
$occured = $filelist = array();
|
| 72 |
foreach ($fileinfo as $file => $lines) {
|
| 73 |
$occured[] = "$file:" . join(";", $lines);
|
| 74 |
if (isset($file_versions[$file])) {
|
| 75 |
$filelist[] = $file_versions[$file];
|
| 76 |
}
|
| 77 |
}
|
| 78 |
|
| 79 |
$output = "#: " . join(" ", $occured) . "\n";
|
| 80 |
$filename = ((count($occured) > 1) ? 'general' : $file);
|
| 81 |
|
| 82 |
if (strpos($str, "\0") === FALSE) {
|
| 83 |
$output .= "msgid \"$str\"\n";
|
| 84 |
$output .= "msgstr \"\"\n";
|
| 85 |
}
|
| 86 |
else {
|
| 87 |
list ($singular, $plural) = explode("\0", $str);
|
| 88 |
$output .= "msgid \"$singular\"\n";
|
| 89 |
$output .= "msgid_plural \"$plural\"\n";
|
| 90 |
$output .= "msgstr[0] \"\"\n";
|
| 91 |
$output .= "msgstr[1] \"\"\n";
|
| 92 |
}
|
| 93 |
$output .= "\n";
|
| 94 |
|
| 95 |
store($filename, $output, $filelist);
|
| 96 |
}
|
| 97 |
|
| 98 |
write_files();
|
| 99 |
|
| 100 |
function write_files() {
|
| 101 |
$output = store(0, 0, array(), 1);
|
| 102 |
foreach ($output as $file => $content) {
|
| 103 |
if (count($content) <= 11 && $file != 'general') {
|
| 104 |
@$output['general'][1] = array_unique(array_merge($output['general'][1], $content[1]));
|
| 105 |
if (!isset($output['general'][0])) {
|
| 106 |
$output['general'][0] = $content[0];
|
| 107 |
}
|
| 108 |
unset($content[0]);
|
| 109 |
unset($content[1]);
|
| 110 |
foreach ($content as $msgid) {
|
| 111 |
$output['general'][] = $msgid;
|
| 112 |
}
|
| 113 |
unset($output[$file]);
|
| 114 |
}
|
| 115 |
}
|
| 116 |
foreach ($output as $file => $content) {
|
| 117 |
$tmp = preg_replace('<[/]?([a-z]*/)*>', '', $file);
|
| 118 |
$file = str_replace('.', '-', $tmp) .'.pot';
|
| 119 |
$filelist = $content[1]; unset($content[1]);
|
| 120 |
if (count($filelist) > 1) {
|
| 121 |
$filelist = "Generated from files:\n# " . join("\n# ", $filelist);
|
| 122 |
}
|
| 123 |
elseif (count($filelist) == 1) {
|
| 124 |
$filelist = "Generated from file: " . join("", $filelist);
|
| 125 |
}
|
| 126 |
else {
|
| 127 |
$filelist = "No version information was available in the source files.";
|
| 128 |
}
|
| 129 |
$fp = fopen($file, 'w');
|
| 130 |
fwrite($fp, str_replace("--VERSIONS--", $filelist, join("", $content)));
|
| 131 |
fclose($fp);
|
| 132 |
}
|
| 133 |
}
|
| 134 |
|
| 135 |
function store($file = 0, $input = 0, $filelist = array(), $get = 0) {
|
| 136 |
static $storage = array();
|
| 137 |
if (!$get) {
|
| 138 |
if (isset($storage[$file])) {
|
| 139 |
$storage[$file][1] = array_unique(array_merge($storage[$file][1], $filelist));
|
| 140 |
$storage[$file][] = $input;
|
| 141 |
}
|
| 142 |
else {
|
| 143 |
$storage[$file] = array();
|
| 144 |
$storage[$file][0] = write_header($file);
|
| 145 |
$storage[$file][1] = $filelist;
|
| 146 |
$storage[$file][2] = $input;
|
| 147 |
}
|
| 148 |
}
|
| 149 |
else {
|
| 150 |
return $storage;
|
| 151 |
}
|
| 152 |
}
|
| 153 |
|
| 154 |
function write_header($file) {
|
| 155 |
$output = "# LANGUAGE translation of Drupal (". $file .")\n";
|
| 156 |
$output .= "# Copyright YEAR NAME <EMAIL@ADDRESS>\n";
|
| 157 |
$output .= "# --VERSIONS--\n";
|
| 158 |
$output .= "#\n";
|
| 159 |
$output .= "#, fuzzy\n";
|
| 160 |
$output .= "msgid \"\"\n";
|
| 161 |
$output .= "msgstr \"\"\n";
|
| 162 |
$output .= "\"Project-Id-Version: PROJECT VERSION\\n\"\n";
|
| 163 |
$output .= "\"POT-Creation-Date: " . date("Y-m-d H:iO") . "\\n\"\n";
|
| 164 |
$output .= "\"PO-Revision-Date: YYYY-mm-DD HH:MM+ZZZZ\\n\"\n";
|
| 165 |
$output .= "\"Last-Translator: NAME <EMAIL@ADDRESS>\\n\"\n";
|
| 166 |
$output .= "\"Language-Team: LANGUAGE <EMAIL@ADDRESS>\\n\"\n";
|
| 167 |
$output .= "\"MIME-Version: 1.0\\n\"\n";
|
| 168 |
$output .= "\"Content-Type: text/plain; charset=utf-8\\n\"\n";
|
| 169 |
$output .= "\"Content-Transfer-Encoding: 8bit\\n\"\n";
|
| 170 |
$output .= "\"Plural-Forms: nplurals=INTEGER; plural=EXPRESSION;\\n\"\n\n";
|
| 171 |
|
| 172 |
return $output;
|
| 173 |
}
|
| 174 |
|
| 175 |
function format_quoted_string($str) {
|
| 176 |
$quo = substr($str, 0, 1);
|
| 177 |
$str = substr($str, 1, -1);
|
| 178 |
if ($quo == '"') {
|
| 179 |
$str = stripcslashes($str);
|
| 180 |
} else {
|
| 181 |
$str = strtr($str, array("\\'" => "'", "\\\\" => "\\"));
|
| 182 |
}
|
| 183 |
return addcslashes($str, "\0..\37\\\"");
|
| 184 |
}
|
| 185 |
|
| 186 |
function marker_error($file, $line, $marker, $tokens) {
|
| 187 |
fwrite(STDERR, "Invalid marker content in $file:$line\n* $marker(");
|
| 188 |
array_shift($tokens); array_shift($tokens);
|
| 189 |
$par = 1;
|
| 190 |
while (count($tokens) && $par) {
|
| 191 |
if (is_array($tokens[0])) {
|
| 192 |
fwrite(STDERR, $tokens[0][1]);
|
| 193 |
} else {
|
| 194 |
fwrite(STDERR, $tokens[0]);
|
| 195 |
if ($tokens[0] == "(") {
|
| 196 |
$par++;
|
| 197 |
}
|
| 198 |
if ($tokens[0] == ")") {
|
| 199 |
$par--;
|
| 200 |
}
|
| 201 |
}
|
| 202 |
array_shift($tokens);
|
| 203 |
}
|
| 204 |
fwrite(STDERR, "\n\n");
|
| 205 |
}
|
| 206 |
|
| 207 |
/*
|
| 208 |
Detect all occurances of one of these sequences:
|
| 209 |
T_STRING("t") + "(" + T_CONSTANT_ENCAPSED_STRING + ")"
|
| 210 |
T_STRING("t") + "(" + T_CONSTANT_ENCAPSED_STRING + ","
|
| 211 |
*/
|
| 212 |
function find_t_calls($tokens, $file) {
|
| 213 |
global $strings;
|
| 214 |
|
| 215 |
while (count($tokens) > 3) {
|
| 216 |
|
| 217 |
list($ctok, $par, $mid, $rig) = $tokens;
|
| 218 |
if (!is_array($ctok)) {
|
| 219 |
array_shift($tokens);
|
| 220 |
continue;
|
| 221 |
}
|
| 222 |
list($type, $string, $line) = $ctok;
|
| 223 |
|
| 224 |
if (($type == T_STRING) && ($string == "t") && ($par == "(")) {
|
| 225 |
|
| 226 |
if (in_array($rig, array(")", ","))
|
| 227 |
&& (is_array($mid) && ($mid[0] == T_CONSTANT_ENCAPSED_STRING))) {
|
| 228 |
|
| 229 |
$strings[format_quoted_string($mid[1])][$file][] = $line;
|
| 230 |
}
|
| 231 |
|
| 232 |
// t() found, but inside is something which is not a string literal
|
| 233 |
else {
|
| 234 |
marker_error($file, $line, "t", $tokens);
|
| 235 |
}
|
| 236 |
}
|
| 237 |
array_shift($tokens);
|
| 238 |
}
|
| 239 |
}
|
| 240 |
|
| 241 |
/*
|
| 242 |
Detect all occurances this sequence:
|
| 243 |
T_STRING("format_plural") + "(" + ..anything (might be more tokens).. +
|
| 244 |
"," + T_CONSTANT_ENCAPSED_STRING +
|
| 245 |
"," + T_CONSTANT_ENCAPSED_STRING + ")"
|
| 246 |
*/
|
| 247 |
function find_format_plural_calls($tokens, $file) {
|
| 248 |
global $strings;
|
| 249 |
|
| 250 |
while (count($tokens) > 7) {
|
| 251 |
|
| 252 |
list($ctok, $par1) = $tokens;
|
| 253 |
if (!is_array($ctok)) {
|
| 254 |
array_shift($tokens);
|
| 255 |
continue;
|
| 256 |
}
|
| 257 |
list($type, $string, $line) = $ctok;
|
| 258 |
|
| 259 |
if (($type == T_STRING) && ($string == "format_plural") && ($par1 == "(")) {
|
| 260 |
|
| 261 |
// Eat up everything that is used as the first parameter
|
| 262 |
$nt = $tokens;
|
| 263 |
array_shift($nt); array_shift($nt);
|
| 264 |
$depth = 0;
|
| 265 |
while (!($nt[0] == "," && $depth == 0)) {
|
| 266 |
if ($nt[0] == "(") {
|
| 267 |
$depth++;
|
| 268 |
}
|
| 269 |
elseif ($nt[0] == ")") {
|
| 270 |
$depth--;
|
| 271 |
}
|
| 272 |
array_shift($nt);
|
| 273 |
}
|
| 274 |
|
| 275 |
// Get further parameters
|
| 276 |
list($comma1, $singular, $comma2, $plural, $par2) = $nt;
|
| 277 |
|
| 278 |
if (($comma2 == ",") && ($par2 == ")") &&
|
| 279 |
(is_array($singular) && ($singular[0] == T_CONSTANT_ENCAPSED_STRING)) &&
|
| 280 |
(is_array($plural) && ($plural[0] == T_CONSTANT_ENCAPSED_STRING))) {
|
| 281 |
|
| 282 |
$strings[format_quoted_string($singular[1]) .
|
| 283 |
"\0" .
|
| 284 |
format_quoted_string($plural[1])][$file][] = $line;
|
| 285 |
}
|
| 286 |
|
| 287 |
// format_plural() found, but the parameters are not correct
|
| 288 |
else {
|
| 289 |
marker_error($file, $line, "format_plural", $tokens);
|
| 290 |
}
|
| 291 |
}
|
| 292 |
array_shift($tokens);
|
| 293 |
}
|
| 294 |
}
|
| 295 |
|
| 296 |
/*
|
| 297 |
Detect all occurances of this sequence:
|
| 298 |
T_STRING("watchdog") + "(" + T_CONSTANT_ENCAPSED_STRING + ","
|
| 299 |
*/
|
| 300 |
function find_watchdog_calls($tokens, $file) {
|
| 301 |
global $strings;
|
| 302 |
|
| 303 |
while (count($tokens) > 3) {
|
| 304 |
|
| 305 |
list($ctok, $par, $mid, $rig) = $tokens;
|
| 306 |
if (!is_array($ctok)) {
|
| 307 |
array_shift($tokens);
|
| 308 |
continue;
|
| 309 |
}
|
| 310 |
list($type, $string, $line) = $ctok;
|
| 311 |
|
| 312 |
if (($type == T_STRING) && ($string == "watchdog") && ($par == "(")) {
|
| 313 |
|
| 314 |
if (($rig == ",")
|
| 315 |
&& (is_array($mid) && ($mid[0] == T_CONSTANT_ENCAPSED_STRING))) {
|
| 316 |
|
| 317 |
$strings[format_quoted_string($mid[1])][$file][] = $line;
|
| 318 |
}
|
| 319 |
|
| 320 |
// watchdog() found, but inside is something which is not a string literal
|
| 321 |
else {
|
| 322 |
marker_error($file, $line, "watchdog", $tokens);
|
| 323 |
}
|
| 324 |
}
|
| 325 |
array_shift($tokens);
|
| 326 |
}
|
| 327 |
}
|
| 328 |
|
| 329 |
// This will get confused if a similar pattern is found in a comment...
|
| 330 |
function find_perm_hook($code, $file) {
|
| 331 |
global $strings;
|
| 332 |
|
| 333 |
if (preg_match('!^(.+function \\w+_perm\\(\\) \\{\s+return)([^\\}]+)\\}!Us', $code, $hook_code)) {
|
| 334 |
$lines = substr_count($hook_code[1], "\n") + 1;
|
| 335 |
preg_match_all('!(["\'])([a-z ]+)\1!', $hook_code[2], $items, PREG_PATTERN_ORDER);
|
| 336 |
foreach ($items[2] as $item) {
|
| 337 |
$strings[$item][$file][] = $lines;
|
| 338 |
}
|
| 339 |
}
|
| 340 |
}
|
| 341 |
|
| 342 |
// This will also get confused if a similar pattern is found in a comment...
|
| 343 |
function find_node_types_hook($code, $file) {
|
| 344 |
global $strings;
|
| 345 |
|
| 346 |
if (preg_match('!^(.+function \\w+_node_types\\(\\) \\{\s+return)([^\\}]+)\\}!Us', $code, $hook_code)) {
|
| 347 |
$lines = substr_count($hook_code[1], "\n") + 1;
|
| 348 |
preg_match_all('!(["\'])([0-9a-z-]+)\1!', $hook_code[2], $items, PREG_PATTERN_ORDER);
|
| 349 |
foreach ($items[2] as $item) {
|
| 350 |
$strings[$item][$file][] = $lines;
|
| 351 |
}
|
| 352 |
}
|
| 353 |
}
|
| 354 |
|
| 355 |
// This will get confused if a similar pattern is found in a comment...
|
| 356 |
function find_module_name($code, $file) {
|
| 357 |
global $strings;
|
| 358 |
|
| 359 |
if (preg_match('!function (\\w+)_help\\(!', $code, $module_name) &&
|
| 360 |
$module_name[1] != 'menu_get_active') {
|
| 361 |
$strings[$module_name[1]][$file][] = 0;
|
| 362 |
}
|
| 363 |
}
|
| 364 |
|
| 365 |
function find_language_names($code, $file) {
|
| 366 |
global $strings;
|
| 367 |
|
| 368 |
if (preg_match("!locale\\.inc$!", $file) &&
|
| 369 |
preg_match("!^(.+function _locale_get_iso639_list\\(\\) {)([^\\}]+)\\}!Us", $code, $langcodes)) {
|
| 370 |
$lines = substr_count($langcodes[1], "\n") + 1;
|
| 371 |
preg_match_all('!array\\((["\'])([^\'"]+)\1!', $langcodes[2], $items, PREG_PATTERN_ORDER);
|
| 372 |
foreach ($items[2] as $item) {
|
| 373 |
$strings[$item][$file][] = $lines;
|
| 374 |
}
|
| 375 |
}
|
| 376 |
}
|
| 377 |
|
| 378 |
// Get the exact version number from the file, so we can push that into the pot
|
| 379 |
function find_version_number($code, $file) {
|
| 380 |
global $file_versions;
|
| 381 |
|
| 382 |
// Prevent CVS from replacing this pattern with actual info
|
| 383 |
if (preg_match('!\\$I' . 'd: ([^\\$]+) Exp \\$!', $code, $version_info)) {
|
| 384 |
$file_versions[$file] = $version_info[1];
|
| 385 |
}
|
| 386 |
}
|
| 387 |
|
| 388 |
// Add date strings if locale.module is parsed
|
| 389 |
function add_date_strings($file) {
|
| 390 |
global $strings;
|
| 391 |
|
| 392 |
if (preg_match('!(^|/)locale.module$!', $file)) {
|
| 393 |
for ($i = 1; $i <= 12; $i++) {
|
| 394 |
$stamp = mktime(0, 0, 0, $i, 1, 1971);
|
| 395 |
$strings[date("F", $stamp)][$file][] = 0;
|
| 396 |
$strings[date("M", $stamp)][$file][] = 0;
|
| 397 |
}
|
| 398 |
|
| 399 |
for ($i = 0; $i <= 7; $i++) {
|
| 400 |
$stamp = $i * 86400;
|
| 401 |
$strings[date("D", $stamp)][$file][] = 0;
|
| 402 |
$strings[date("l", $stamp)][$file][] = 0;
|
| 403 |
}
|
| 404 |
}
|
| 405 |
}
|
| 406 |
|
| 407 |
// Add format_interval special strings if common.inc is parsed
|
| 408 |
function add_format_interval_strings($file) {
|
| 409 |
global $strings;
|
| 410 |
|
| 411 |
if (preg_match('!(^|/)common.inc$!', $file)) {
|
| 412 |
$components = array(
|
| 413 |
'1 year' => '%count years',
|
| 414 |
'1 week' => '%count weeks',
|
| 415 |
'1 day' => '%count days',
|
| 416 |
'1 hour' => '%count hours',
|
| 417 |
'1 min' => '%count min',
|
| 418 |
'1 sec' => '%count sec');
|
| 419 |
|
| 420 |
foreach($components as $singular => $plural) {
|
| 421 |
$strings[$singular."\0".$plural][$file][] = 0;
|
| 422 |
}
|
| 423 |
}
|
| 424 |
}
|
| 425 |
|
| 426 |
return;
|
| 427 |
|
| 428 |
// These are never executed, you can run extractor.php on itself to test it
|
| 429 |
$a = t("Test string 1" );
|
| 430 |
$b = t("Test string 2 %string", array("%string" => "how do you do"));
|
| 431 |
$c = t('Test string 3');
|
| 432 |
$d = t("Special\ncharacters");
|
| 433 |
$e = t('Special\ncharacters');
|
| 434 |
$f = t("Embedded $variable");
|
| 435 |
$g = t('Embedded $variable');
|
| 436 |
$h = t("more \$special characters");
|
| 437 |
$i = t('even more \$special characters');
|
| 438 |
$j = t("Mixed 'quote' \"marks\"");
|
| 439 |
$k = t('Mixed "quote" \'marks\'');
|
| 440 |
$l = t('This is some repeating text');
|
| 441 |
$m = t("This is some repeating text");
|
| 442 |
$n = t(embedded_function_call());
|
| 443 |
$o = format_plural($days, "one day", "%count days");
|
| 444 |
$p = format_plural(embedded_function_call($count), "one day", "%count days");
|
| 445 |
|
| 446 |
function embedded_function_call() { return 12; }
|
| 447 |
|
| 448 |
function extractor_perm() {
|
| 449 |
return array("access extrator data", 'administer extractor data');
|
| 450 |
}
|
| 451 |
|
| 452 |
function extractor_help($section = 'default') {
|
| 453 |
watchdog('help', t('Help called'));
|
| 454 |
return t('This is some help');
|
| 455 |
}
|
| 456 |
|
| 457 |
function extractor_node_types() {
|
| 458 |
return array("extractor-cooltype", "extractor-evencooler");
|
| 459 |
}
|
| 460 |
|
| 461 |
?>
|
Parent Directory
| 
Revision Log
| 
Revision Graph