Author: grothoff
Date: 2005-04-03 19:54:54 -0700 (Sun, 03 Apr 2005)
New Revision: 584
Modified:
i18nHTML/src/commitTranslation.php
i18nHTML/src/i18nhtml.inc
i18nHTML/src/translate.php
i18nHTML/src/vote.php
Log:
bugfixes
Modified: i18nHTML/src/commitTranslation.php
===================================================================
--- i18nHTML/src/commitTranslation.php 2005-04-04 02:02:32 UTC (rev 583)
+++ i18nHTML/src/commitTranslation.php 2005-04-04 02:54:54 UTC (rev 584)
@@ -18,7 +18,7 @@
Boston, MA 02111-1307, USA.
*/
include("i18nhtml.inc");
-$text = $_REQUEST['text'];
+$text = mysql_real_escape_string($_REQUEST['text']);
$translation = $_REQUEST['translation'];
$back = $_REQUEST['back'];
if (!$connection) {
@@ -47,7 +47,9 @@
generateFooter();
echo "</body></html>";
} else {
- if (array_count_values($text)['%'] != array_count_values($t)['%']) {
+ $txtCnt = count_chars($text, 1);
+ $tCnt = count_chars($text, 1);
+ if ($txtCnt['%'] != $tCnt['%']) {
echo "<html><head>";
TITLE("Commit failed.");
echo "</head><body>";
@@ -55,7 +57,7 @@
W("The number of percent signs in source text and translation do not
match.");
W("Note that you must preserve all %%s expressions unchanged.");
W("Also, a single displayed %% sign must be translated into two (%%%%)
such signs.");
- echo "</body></html>"
+ echo "</body></html>";
} else {
$query = "INSERT INTO map VALUES(\"$text\", \"$lang\", \"$t\", 1, \"" .
$_SERVER['REMOTE_ADDR'] . "\");";
$result = mysql_query($query, $connection);
Modified: i18nHTML/src/i18nhtml.inc
===================================================================
--- i18nHTML/src/i18nhtml.inc 2005-04-04 02:02:32 UTC (rev 583)
+++ i18nHTML/src/i18nhtml.inc 2005-04-04 02:54:54 UTC (rev 584)
@@ -305,7 +305,299 @@
return $text;
}
+
/**
+ * transcode unicode entities to/from HTML entities
+ *
+ * Also, this function transforms HTML entities into their equivalent Unicode
entities.
+ * For example, w.bloggar posts pages using HTML entities.
+ * If you have to modify these pages using web forms, you would like to get
UTF-8 instead.
+ *
+ * @link
http://www.evolt.org/article/A_Simple_Character_Entity_Chart/17/21234/ A Simple
Character Entity Chart
+ *
+ * @param string the string to be transcoded
+ * @param boolean TRUE to transcode to Unicode, FALSE to transcode to HTML
+ * @return a transcoded string
+ */
+function transcode($input, $to_unicode=TRUE) {
+
+ // initialize tables only once
+ static $html_entities, $unicode_entities;
+ if(!is_array($html_entities)) {
+
+
+ // numerical order
+ $codes = array(
+ ' ' => ' ', // non-breaking space
+ '¡' => '¡', // inverted exclamation mark
+ '¢' => '¢', // cent sign
+ '£' => '£', // pound sign
+ '¤' => '¤', // currency sign
+ '¥' => '¥', // yen sign
+ '¦' => '¦', // broken bar
+ '§' => '§', // section sign
+ '¨' => '¨', // diaeresis
+ '©' => '©', // copyright sign
+ 'ª' => 'ª', // feminine ordinal indicator
+ '«' => '«', // left-pointing double angle
quotation mark
+ '¬' => '¬', // not sign
+ '­' => '­', // soft hyphen
+ '®' => '®', // registered sign
+ '¯' => '¯', // macron
+ '°' => '°', // degree sign
+ '±' => '±', // plus-minus sign
+ '²' => '²', // superscript two
+ '³' => '³', // superscript three
+ '´' => '´', // acute accent
+ 'µ' => 'µ', // micro sign
+ '¶' => '¶', // pilcrow sign
+ '·' => '·', // middle dot
+ '¸' => '¸', // cedilla
+ '¹' => '¹', // superscript one
+ 'º' => 'º', // masculine ordinal indicator
+ '»' => '»', // right-pointing double angle
quotation mark
+ '¼' => '¼', // vulgar fraction one quarter
+ '½' => '½', // vulgar fraction one half
+ '¾' => '¾', // vulgar fraction three
quarters
+ '¿' => '¿', // inverted question mark
+ 'À' => 'À', // latin capital letter A with
grave
+ 'Á' => 'Á', // latin capital letter A with
acute
+ 'Â' => 'Â', // latin capital letter A with
circumflex
+ 'Ã' => 'Ã', // latin capital letter A with
tilde
+ 'Ä' => 'Ä', // latin capital letter A with
diaeresis
+ 'Å' => 'Å', // latin capital letter A with
ring above
+ 'Æ' => 'Æ', // latin capital letter AE
+ 'Ç' => 'Ç', // latin capital letter C with
cedilla
+ 'È' => 'È', // latin capital letter E with
grave
+ 'É' => 'É', // latin capital letter E with
acute
+ 'Ê' => 'Ê', // latin capital letter E with
circumflex
+ 'Ë' => 'Ë', // latin capital letter E with
diaeresis
+ 'Ì' => 'Ì', // latin capital letter I with
grave
+ 'Í' => 'Í', // latin capital letter I with
acute
+ 'Î' => 'Î', // latin capital letter I with
circumflex
+ 'Ï' => 'Ï', // latin capital letter I with
diaeresis
+ 'Ð' => 'Ð', // latin capital letter
ETH
+ 'Ñ' => 'Ñ', // latin capital letter N with
tilde
+ 'Ò' => 'Ò', // latin capital letter O with
grave
+ 'Ó' => 'Ó', // latin capital letter O with
acute
+ 'Ô' => 'Ô', // latin capital letter O with
circumflex
+ 'Õ' => 'Õ', // latin capital letter O with
tilde
+ 'Ö' => 'Ö', // latin capital letter O with
diaeresis
+ '×' => '×', // multiplication sign
+ 'Ø' => 'Ø', // latin capital letter O with
stroke
+ 'Ù' => 'Ù', // latin capital letter U with
grave
+ 'Ú' => 'Ú', // latin capital letter U with
acute
+ 'Û' => 'Û', // latin capital letter U with
circumflex
+ 'Ü' => 'Ü', // latin capital letter U with
diaeresis
+ 'Ý' => 'Ý', // latin capital letter Y with
acute
+ 'Þ' => 'Þ', // latin capital letter THORN
+ 'ß' => 'ß', // latin small letter sharp s
+ 'à' => 'à', // latin small letter a with
grave
+ 'á' => 'á', // latin small letter a with
acute
+ 'â' => 'â', // latin small letter a with
circumflex
+ 'ã' => 'ã', // latin small letter a with
tilde
+ 'ä' => 'ä', // latin small letter a with
diaeresis
+ 'å' => 'å', // latin small letter a with
ring above
+ 'æ' => 'æ', // latin small letter ae
+ 'ç' => 'ç', // latin small letter c with
cedilla
+ 'è' => 'è', // latin small letter e with
grave
+ 'é' => 'é', // latin small letter e with
acute
+ 'ê' => 'ê', // latin small letter e with
circumflex
+ 'ë' => 'ë', // latin small letter e with
diaeresis
+ 'ì' => 'ì', // latin small letter i with
grave
+ 'í' => 'í', // latin small letter i with
acute
+ 'î' => 'î', // latin small letter i with
circumflex
+ 'ï' => 'ï', // latin small letter i with
diaeresis
+ 'ð' => 'ð', // latin small letter
eth
+ 'ñ' => 'ñ', // latin small letter n with
tilde
+ 'ò' => 'ò', // latin small letter o with
grave
+ 'ó' => 'ó', // latin small letter o with
acute
+ 'ô' => 'ô', // latin small letter o with
circumflex
+ 'õ' => 'õ', // latin small letter o with
tilde
+ 'ö' => 'ö', // latin small letter o with
diaeresis
+ '÷' => '÷', // division sign
+ 'ø' => 'ø', // latin small letter o with
stroke
+ 'ù' => 'ù', // latin small letter u with
grave
+ 'ú' => 'ú', // latin small letter u with
acute
+ 'û' => 'û', // latin small letter u with
circumflex
+ 'ü' => 'ü', // latin small letter u with
diaeresis
+ 'ý' => 'ý', // latin small letter y with
acute
+ 'þ' => 'þ', // latin small letter thorn
+ 'ÿ' => 'ÿ', //
+ 'Œ' => 'Œ', // latin capital ligature OE
+ 'œ' => 'œ', // latin small ligature oe
+ 'Š' => 'Š', // latin capital letter S with
caron
+ 'š' => 'š', // latin small letter s with
caron
+ 'Ÿ' => 'Ÿ', // latin capital letter Y with
diaeresis
+ 'ƒ' => 'ƒ' , // latin small f with hook
+ 'ˆ' => 'ˆ', // modifier letter circumflex
accent
+ '˜' => '˜', // small tilde
+ 'Α' => 'Α', // greek capital letter alpha
+ 'Β' => 'Β', // greek capital letter beta
+ 'Γ' => 'Γ', // greek capital letter gamma
+ 'Δ' => 'Δ', // greek capital letter delta
+ 'Ε' => 'Ε', // greek capital letter epsilon
+ 'Ζ' => 'Ζ', // greek capital letter zeta
+ 'Η' => 'Η', // greek capital letter
eta
+ 'Θ' => 'Θ', // greek capital letter theta
+ 'Ι' => 'Ι', // greek capital letter iota
+ 'Κ' => 'Κ', // greek capital letter kappa
+ 'Λ' => 'Λ', // greek capital letter lambda
+ 'Μ' => 'Μ', // greek capital letter
mu
+ 'Ν' => 'Ν', // greek capital letter
nu
+ 'Ξ' => 'Ξ', // greek capital letter
xi
+ 'Ο' => 'Ο', // greek capital letter omicron
+ 'Π' => 'Π', // greek capital letter
pi
+ 'Ρ' => 'Ρ', // greek capital letter
rho
+ 'Σ' => 'Σ', // greek capital letter sigma
+ 'Τ' => 'Τ', // greek capital letter
tau
+ 'Υ' => 'Υ', // greek capital letter upsilon
+ 'Φ' => 'Φ', // greek capital letter
phi
+ 'Χ' => 'Χ', // greek capital letter
chi
+ 'Ψ' => 'Ψ', // greek capital letter
psi
+ 'Ω' => 'Ω', // greek capital letter omega
+ 'α' => 'α', // greek small letter alpha
+ 'β' => 'β', // greek small letter beta
+ 'γ' => 'γ', // greek small letter gamma
+ 'δ' => 'δ', // greek small letter delta
+ 'ε' => 'ε', // greek small letter epsilon
+ 'ζ' => 'ζ', // greek small letter zeta
+ 'η' => 'η', // greek small letter
eta
+ 'θ' => 'θ', // greek small letter theta
+ 'ι' => 'ι', // greek small letter iota
+ 'κ' => 'κ', // greek small letter kappa
+ 'λ' => 'λ', // greek small letter lambda
+ 'μ' => 'μ', // greek small letter mu
+ 'ν' => 'ν', // greek small letter nu
+ 'ξ' => 'ξ', // greek small letter xi
+ 'ο' => 'ο', // greek small letter omicron
+ 'π' => 'π', // greek small letter pi
+ 'ρ' => 'ρ', // greek small letter
rho
+ 'ς' => 'ς', // greek small letter final
sigma
+ 'σ' => 'σ', // greek small letter sigma
+ 'τ' => 'τ', // greek small letter
tau
+ 'υ' => 'υ', // greek small letter upsilon
+ 'φ' => 'φ', // greek small letter
phi
+ 'χ' => 'χ', // greek small letter
chi
+ 'ψ' => 'ψ', // greek small letter
psi
+ 'ω' => 'ω', // greek small letter omega
+ 'ϑ' => 'ϑ', // greek small letter
theta symbol
+ 'ϒ' => 'ϒ', // greek upsilon with hook
symbol
+ 'ϖ' => 'ϖ', // greek pi symbol
+ ' ' => ' ', // en space
+ ' ' => ' ', // em space
+ ' ' => ' ', // thin space
+ '‌' => '‌', // zero width non-joiner
+ '‍' => '‍', // zero width joiner
+ '‎' => '‎', // left-to-right mark
+ '‏' => '‏', // right-to-left mark
+ '–' => '–', // en dash
+ '—' => '—', // em dash
+ '‘' => '‘', // left single quotation mark
+ '’' => '’', // right single quotation mark
+ '‚' => '‚', // single low-9 quotation mark
+ '“' => '“', // left double quotation mark
+ '”' => '”', // right double quotation mark
+ '„' => '„', // double low-9 quotation mark
+ '†' => '†', // dagger
+ '‡' => '‡', // double dagger
+ '•' => '•', // bullet
+ '…' => '…', // horizontal ellipsis
+ '‰' => '‰', // per mille sign
+ '′' => '′', // primeminutes
+ '″' => '″', // double prime
+ '‹' => '‹', // single left-pointing angle
quotation mark
+ '›' => '›', // single right-pointing angle
quotation mark
+ '‾' => '‾', // overline
+ '⁄' => '⁄', // fraction slash
+ '€' => '€', // euro sign
+ 'ℑ' => 'ℑ', // blackletter capital I
+ '℘' => '℘', // script capital P
+ 'ℜ' => 'ℜ', // blackletter capital R
+ '™' => '™', // trade mark sign
+ 'ℵ' => 'ℵ', // alef symbol
+ '←' => '←', // leftwards arrow
+ '↑' => '↑', // upwards arrow
+ '→' => '→', // rightwards arrow
+ '↓' => '↓', // downwards arrow
+ '↔' => '↔', // left right arrow
+ '↵' => '↵', // downwards arrow with corner
leftwards
+ '⇐' => '⇐', // leftwards double arrow
+ '⇑' => '⇑', // upwards double arrow
+ '⇒' => '⇒', // rightwards double arrow
+ '⇓' => '⇓', // downwards double arrow
+ '⇔' => '⇔', // left right double arrow
+ '∀' => '∀', // for all
+ '∂' => '∂', // partial differential
+ '∃' => '∃', // there exists
+ '∅' => '∅', // empty set
+ '∇' => '∇', // nabla
+ '∈' => '∈', // element of
+ '∉' => '∉', // not an element of
+ '∋' => '∋', // contains as member
+ '∏' => '∏', // n-ary product
+ '∑' => '∑', // n-ary sumation
+ '−' => '−', // minus sign
+ '∗' => '∗', // asterisk operator
+ '√' => '√', // square root
+ '∝' => '∝', // proportional to
+ '∞' => '∞', // infinity
+ '∠' => '∠', // angle
+ '∧' => '∧', // logical and
+ '∨' => '∨', // logical or
+ '∩' => '∩', // intersection
+ '∪' => '∪', // union
+ '∫' => '∫', // integral
+ '∴' => '∴', // therefore
+ '∼' => '∼', // tilde operator
+ '≅' => '≅', // approximately equal to
+ '≈' => '≈', // almost equal to
+ '≠' => '≠', // not equal to
+ '≡' => '≡', // identical to
+ '≤' => '≤', // less-than or equal to
+ '≥' => '≥', // greater-than or
equal to
+ '⊂' => '⊂', // subset of
+ '⊃' => '⊃', // superset of
+ '⊄' => '⊄', // not a subset of
+ '⊆' => '⊆', // subset of or equal to
+ '⊇' => '⊇', // superset of or equal to
+ '⊕' => '⊕', // circled plus
+ '⊗' => '⊗', // circled times
+ '⊥' => '⊥', // up tack
+ '⋅' => '⋅', // dot operator
+ '⌈' => '⌈', // left ceiling
+ '⌉' => '⌉', // right ceiling
+ '⌊' => '⌊', // left floor
+ '⌋' => '⌋', // right floor
+ '〈' => '⟨', // left-pointing angle bracket
+ '〉' => '⟩', // right-pointing angle bracket
+ '◊' => '◊', // lozenge
+ '♠' => '♠', // black spade suit
+ '♣' => '♣', // black club suit
+ '♥' => '♥', // black heart suit
+ '♦' => '♦' // black diam suit
+ );
+
+ // split entities for use in str_replace()
+ foreach($codes as $unicode_entity => $html_entity) {
+ $unicode_entities[] = $unicode_entity;
+ $html_entities[] = $html_entity;
+ }
+ }
+
+ // transcode HTML entities to Unicode
+ if($to_unicode)
+ return str_replace($html_entities, $unicode_entities, $input);
+
+ // transcode Unicode entities to HTML entities
+ else
+ return str_replace($unicode_entities, $html_entities, $input);
+}
+
+
+
+
+/**
* transcode multi-byte characters to HTML representations for Unicode
*
* This function is aiming to preserve Unicode characters through storage in a
ISO-8859-1 compliant system.
@@ -329,7 +621,7 @@
function to_unicode($input) {
// transcode HTML entities to Unicode entities
- $input = utf8::transcode($input);
+ $input = transcode($input);
// scan the whole string
$output = '';
@@ -533,7 +825,7 @@
global $lang;
global $languagecodes;
echo "<meta http-equiv=\"Content-Type\" content=\"text/html;charset=utf-8\"
>";
- echo "<title>" . W_($a,$b) . "</title>\n";
+ echo "<title>" . TRANSLATE_($a,$b) . "</title>\n";
if (isset($languagecodes[$lang])) {
echo "<meta name=\"content-language\" content=\"" .
$languagecodes[$lang] . "\">";
Modified: i18nHTML/src/translate.php
===================================================================
--- i18nHTML/src/translate.php 2005-04-04 02:02:32 UTC (rev 583)
+++ i18nHTML/src/translate.php 2005-04-04 02:54:54 UTC (rev 584)
@@ -43,7 +43,7 @@
W("Destination language: ");
W($lang);
P();
-echo "<form method="POST" action=\"" . $i18nHTMLbase .
"commitTranslation.php\">\n";
+echo "<form method=\"POST\" action=\"" . $i18nHTMLbase .
"commitTranslation.php\">\n";
echo "<input type=hidden name=\"text\" value=\"" . urlencode($text) . "\">\n";
echo "<input type=hidden name=\"xlang\" value=\"$xlang\">\n";
echo "<input type=hidden name=\"back\" value=\"$back\">\n";
Modified: i18nHTML/src/vote.php
===================================================================
--- i18nHTML/src/vote.php 2005-04-04 02:02:32 UTC (rev 583)
+++ i18nHTML/src/vote.php 2005-04-04 02:54:54 UTC (rev 584)
@@ -31,8 +31,8 @@
}
$text = $_REQUEST['text'];
$translation = $_REQUEST['translation'];
-$u = urlencode($text);
-$t = urlencode($translation);
+$u = mysql_real_escape_string($text);
+$t = mysql_real_escape_string(to_unicode($translation));
echo "text = " . $text . "<br>\n";
echo "translation = " . $translation . "<br>\n";
_______________________________________________
GNUnet-SVN mailing list
GNUnet-SVN@gnu.org
http://lists.gnu.org/mailman/listinfo/gnunet-svn
