Skip to content

Conflictive "Ã" #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
georgik merged 5 commits into from
Apr 24, 2019
Merged

Conflictive "Ã" #1

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5684c41
One character per line
juanruitina Apr 23, 2019
316a61b
Put "”" down the array to avoid conflicts with longer errors
juanruitina Apr 23, 2019
7da59f3
Add some characters from https://www.i18nqa.com/debug/utf8-debug.html
juanruitina Apr 23, 2019
44026ad
Add null character to array
juanruitina Apr 23, 2019
b1e7601
Add selector of preferred character to replace conflictive "Ã"
juanruitina Apr 23, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
247 changes: 218 additions & 29 deletions repair.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,56 +1,245 @@
<!DOCTYPE html>
<html>
<head>
<!-- Inspired by https://gist.github.com/xijo/d4bad3953f7b9979dd91 written by Xijo -->
<!-- Inspired by https://gist.github.com/xijo/d4bad3953f7b9979dd91 written by Xijo.
Some characters also from https://www.i18nqa.com/debug/utf8-debug.html -->
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<script type="text/javascript">
var REPLACEMENTS = {
"€" : "€", "‚" : "‚", "„" : "„", "…" : "…", "ˆ" : "ˆ",
"‹" : "‹", "‘" : "‘", "’" : "’", "“" : "“", "â€" : "”",
"•" : "•", "–" : "–", "—" : "—", "Ëœ" : "˜", "â„¢" : "™",
"›" : "›", "Å“" : "œ", "Å’" : "Œ", "ž" : "ž", "Ÿ" : "Ÿ",
"Å¡" : "š", "Ž" : "Ž", "¡" : "¡", "¢" : "¢", "£" : "£",
"¤" : "¤", "Â¥" : "¥", "¦" : "¦", "§" : "§", "¨" : "¨",
"©" : "©", "ª" : "ª", "«" : "«", "¬" : "¬", "®" : "®",
"¯" : "¯", "°" : "°", "±" : "±", "²" : "²", "³" : "³",
"´" : "´", "µ" : "µ", "¶" : "¶", "·" : "·", "¸" : "¸",
"¹" : "¹", "º" : "º", "»" : "»", "¼" : "¼", "½" : "½",
"¾" : "¾", "¿" : "¿", "À" : "À", "Â" : "Â", "Ã" : "Ã",
"Ä" : "Ä", "Ã…" : "Å", "Æ" : "Æ", "Ç" : "Ç", "È" : "È",
"É" : "É", "Ê" : "Ê", "Ë" : "Ë", "ÃŒ" : "Ì", "ÃŽ" : "Î",
"Ñ" : "Ñ", "Ã’" : "Ò", "Ó" : "Ó", "Ô" : "Ô", "Õ" : "Õ",
"Ö" : "Ö", "×" : "×", "Ø" : "Ø", "Ù" : "Ù", "Ú" : "Ú",
"Û" : "Û", "Ãœ" : "Ü", "Þ" : "Þ", "ß" : "ß", "á" : "á",
"â" : "â", "ã" : "ã", "ä" : "ä", "Ã¥" : "å", "æ" : "æ",
"ç" : "ç", "è" : "è", "é" : "é", "ê" : "ê", "ë" : "ë",
"ì" : "ì", "í" : "í", "î" : "î", "ï" : "ï", "ð" : "ð",
"ñ" : "ñ", "ò" : "ò", "ó" : "ó", "ô" : "ô", "õ" : "õ",
"ö" : "ö", "÷" : "÷", "ø" : "ø", "ù" : "ù", "ú" : "ú",
"û" : "û", "ü" : "ü", "ý" : "ý", "þ" : "þ", "ÿ" : "ÿ",
"Ä›" : "ě", "Å™" : "ř"
}

"€" : "€",
"‚" : "‚",
"„" : "„",
"…" : "…",
"‡" : "‡",
"ˆ" : "ˆ",
"‰" : "‰",
"‹" : "‹",
"‘" : "‘",
"’" : "’",
"“" : "“",
"•" : "•",
"–" : "–",
"—" : "—",
"Ëœ" : "˜",
"â„¢" : "™",
"›" : "›",
"â€" : "”",
// "â€" : "†", --> conflictive with "”"
"Å“" : "œ",
"Å’" : "Œ",
"ž" : "ž",
"Ÿ" : "Ÿ",
"Å¡" : "š",
"Ž" : "Ž",
"Å" : "Š",
"¡" : "¡",
"¢" : "¢",
"£" : "£",
"¤" : "¤",
"Â¥" : "¥",
"¦" : "¦",
"§" : "§",
"¨" : "¨",
"©" : "©",
"ª" : "ª",
"«" : "«",
"¬" : "¬",
"®" : "®",
"¯" : "¯",
"°" : "°",
"±" : "±",
"²" : "²",
"³" : "³",
"´" : "´",
"µ" : "µ",
"¶" : "¶",
"·" : "·",
"¸" : "¸",
"¹" : "¹",
"º" : "º",
"»" : "»",
"¼" : "¼",
"½" : "½",
"¾" : "¾",
"¿" : "¿",
"À" : "À",
"Â" : "Â",
"Ã" : "Ã",
"Ä" : "Ä",
"Ã…" : "Å",
"Æ" : "Æ",
"Ç" : "Ç",
"È" : "È",
"É" : "É",
"Ê" : "Ê",
"Ë" : "Ë",
"ÃŒ" : "Ì",
"ÃŽ" : "Î",
"Ñ" : "Ñ",
"Ã’" : "Ò",
"Ó" : "Ó",
"Ô" : "Ô",
"Õ" : "Õ",
"Ö" : "Ö",
"×" : "×",
"Ø" : "Ø",
"Ù" : "Ù",
"Ú" : "Ú",
"Û" : "Û",
"Ãœ" : "Ü",
"Þ" : "Þ",
"ß" : "ß",
"á" : "á",
"â" : "â",
"ã" : "ã",
"ä" : "ä",
"Ã¥" : "å",
"æ" : "æ",
"ç" : "ç",
"è" : "è",
"é" : "é",
"ê" : "ê",
"ë" : "ë",
"ì" : "ì",
"í" : "í",
"î" : "î",
"ï" : "ï",
"ð" : "ð",
"ñ" : "ñ",
"ò" : "ò",
"ó" : "ó",
"ô" : "ô",
"õ" : "õ",
"ö" : "ö",
"÷" : "÷",
"ø" : "ø",
"ù" : "ù",
"ú" : "ú",
"û" : "û",
"ü" : "ü",
"ý" : "ý",
"þ" : "þ",
"ÿ" : "ÿ",
"Ä›" : "ě",
"Å™" : "ř",
"" : "" // null character
}

// "Ã" is the error for many characters. Here are those grouped by languages. In Spanish and French, the expected most common character has been chosen, the rest being commented. Please be aware this characters might not be replaced properly.
var CONFLICTIVE_REPLACEMENTS = [
{ "Ã" : "Ã" },
{ "Ã" : "Ý" },
{ "Ã" : "Á" },
{ "Ã" : "Í" },
{ "Ã" : "à" },
{ "Ã" : "Ï" },
{ "Ã" : "Ð" }
];

var choice = 0;

function encodeText() {
var sourceElement = document.getElementById("source");
var targetElement = document.getElementById("target");
var targetValue = sourceElement.value;

for (var key in REPLACEMENTS) {
for (var key in REPLACEMENTS) {
targetValue = targetValue.split(key).join(REPLACEMENTS[key]);
}

for (i = 0; i < CONFLICTIVE_REPLACEMENTS.length; i++) {
if ( choice == i ) {
for (var key in CONFLICTIVE_REPLACEMENTS[i]) {
targetValue = targetValue.split(key).join(CONFLICTIVE_REPLACEMENTS[i][key]);
}
}
}

targetElement.value = targetValue;
}
document.addEventListener("DOMContentLoaded", encodeText);

function selector() {
function selectorOut() {
var radioValue = document.querySelector('input[name="choice"]:checked').value;
choice = radioValue;
encodeText();
}
document.getElementById("choice0").addEventListener("click", selectorOut);
document.getElementById("choice1").addEventListener("click", selectorOut);
document.getElementById("choice2").addEventListener("click", selectorOut);
document.getElementById("choice3").addEventListener("click", selectorOut);
document.getElementById("choice4").addEventListener("click", selectorOut);
document.getElementById("choice5").addEventListener("click", selectorOut);
document.getElementById("choice6").addEventListener("click", selectorOut);

function infoBoxToggle() {
var x = document.getElementById("info-box");
if (x.style.display === "none") {
x.style.display = "block";
} else {
x.style.display = "none";
}
}
}
document.addEventListener("DOMContentLoaded", selector);

document.addEventListener("DOMContentLoaded", encodeText);
</script>

</script>
<style>
body { font-family: sans-serif; }
</style>
</head>
<body>



<p>
<textarea id="source" cols="60" rows="5" onkeyup="encodeText()">Dobrý den</textarea>
</p>
<p>
<textarea id="target" cols="60" rows="5"></textarea>
</p>

<div id="info-box">
<p>"Ã" is the error returned for several characters. Choose which one you would like to replace "Ã" with. Please, keep in mind <i>all</i> "Ã" will be replaced with the same chosen character.</p>
</div>

<div>
<div>
<input type="radio" class="choice" id="choice0" name="choice" value="0" checked>
<label for="choice0">Keep as à (Portuguese, Vietnamese, Guarani <a href="https://en.wikipedia.org/wiki/%C3%83">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice1" name="choice" value="1">
<label for="choice1">Ý (Czech, Slovak, Icelandic, Kazakh <a href="https://en.wikipedia.org/wiki/%C3%9D">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice2" name="choice" value="2">
<label for="choice2">Á (Spanish, Portuguese, Czech, Dutch, Hungarian, Irish, Slovak <a href="https://en.wikipedia.org/wiki/%C3%81">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice3" name="choice" value="3">
<label for="choice3">Í (Spanish, Portuguese, Vietnamese, Hungarian, Czech, Slovak, Italian <a href="https://en.wikipedia.org/wiki/%C3%8D">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice4" name="choice" value="4">
<label for="choice4">à (French, Portuguese, Dutch, Catalan, Galician, Italian, Hungarian, Vietnamese, Welsh <a href="https://en.wikipedia.org/wiki/%C3%80">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice5" name="choice" value="5">
<label for="choice5">Ï (French, Dutch, Catalan, Galician, Welsh, English <a href="https://en.wikipedia.org/wiki/%C3%8F">and more</a>)</label>
</div>

<div>
<input type="radio" class="choice" id="choice6" name="choice" value="6">
<label for="choice6">Ð (Icelandic and Faroese)</label>
</div>
</div>
</body>
</html>