underlined.
* @param $instruction the characters to replace, ex. _
* @param $markup the markup to replace to, ex. "u" to get …
* @param &$text where to replace.
*/
function markupPreg($instruction, $markup, &$text) {
$output = $text;
# Replaces couples "__word__" into "word".
$output = mb_ereg_replace("${instruction}(.+?)${instruction}", "<{$markup}>\\1", $output);
# Replaces a remaining __ into "…" to the end of the line.
$output = mb_ereg_replace("${instruction}(.+)?", "<{$markup}>\\1", $output);
$text = $output;
}
/**
* Adds text attributes sucj as underline, bold, … to $line
* @param $line the line to process
*/
function addTextAttributes(&$line) {
markupPreg("__", "u", $line);
markupPreg("\*\*", "strong", $line);
markupPreg("//", "em", $line);
markupPreg("~~", "del", $line);
}
define("NARROW_NO_BREAK_SPACE", " ");
define("DASHES"
,"‒" # U+2012 Figure Dash
."–" # U+2013 En Dash
."—" # U+2014 Em Dash
."⸺" # U+2E3A Two-Em Dash
."⸻" # U+2E3B Three-Em Dash (Three times larger than a single char)
);
/**
* Prepares the raw text to be displayed in HTML environment:
* * Escapes the HTML entities yet contained in the Gemtext.
* * Puts thin unbrakable spaces before some characters.
* @param $text1, $text2 texts to process
*/
function htmlPrepare(&$text) {
$text = htmlspecialchars($text, ENT_HTML5|ENT_NOQUOTES, "UTF-8", false);
$text = mb_ereg_replace("\ ([?!:;»€$])", NARROW_NO_BREAK_SPACE."\\1", $text);
$text = mb_ereg_replace("([«])\ ", "\\1".NARROW_NO_BREAK_SPACE, $text); # Espace fine insécable
# Warning: using a monospace font editor may not display dashes as they should be!
# Adds no-break spaces to stick the (EM/EN dashes) to words : aaaaaa – bb – ccccc ==> aaaaaa –$bb$– ccccc
$text = mb_ereg_replace("([".DASHES."]) ([^".DASHES.".]+) ([".DASHES."])", "\\1".NARROW_NO_BREAK_SPACE."\\2".NARROW_NO_BREAK_SPACE."\\3", $text);
# Adds no-break space to stick the (EM/EN dashes) to words : aaaaaa – bb. ==> aaaaaa –$bb.
$text = mb_ereg_replace("([—–]) ([^.]+).", "\\1".NARROW_NO_BREAK_SPACE."\\2.", $text);
}
ob_start();
$mode = null;
$mode_textAttributes = true;
foreach ($fileLines as $line) {
$reDoCount = 0;
$mode_textAttributes_temp = false;
while (true) {
if ($reDoCount>2) {
error_log("HtmGem: Too many loops, mode == '$mode'");
$mode = null;
$reDoCount = 0;
break;
}
$reDoCount += 1;
$line1 = substr($line, 0, 1); // $line can be modified
$line2 = substr($line, 0, 2); // in the meantime.
$line3 = substr($line, 0, 3);
if (is_null($mode)) {
if (empty($line)) {
echo "
\n";
} elseif ('^^^' == $line3) {
if (preg_match("/^\^\^\^\s+(.*)$/", $line)) {
$mode_textAttributes = !$mode_textAttributes;
} else {
$mode = "raw";
continue;
}
} elseif ('^' == $line1 and !$mode_textAttributes_temp) {
preg_match("/^\^\s*(.*)$/", $line, $parts);
$line = $parts[1];
$mode_textAttributes_temp = true;
continue;
} elseif ("#" == $line1) {
preg_match("/^(#{1,3})\s*(.*)/", $line, $sharps);
$h_level = strlen($sharps[1]);
$text = $sharps[2];
htmlPrepare($text);
switch ($h_level) {
case 1: echo "".$text."
\n"; break;
case 2: echo "".$text."
\n"; break;
case 3: echo "".$text."
\n"; break;
}
} elseif ("=>" == $line2) {
if (preg_match("/^=>\s*([^\s]+)(?:\s+(.*))?$/", $line, $linkParts)) {
$url_link = $linkParts[1];
$url_label = @$linkParts[2];
if (empty(trim($url_label))) {
$url_label = $url_link;
} else {
// the label is humain-made, apply formatting
htmlPrepare($url_label);
}
echo "".$url_label."
\n";
} else {
$mode = "raw";
continue;
}
} elseif ("```" == $line3) {
$mode="pre";
echo "\n";
} elseif (">" == $line1) {
$mode = "quote";
preg_match("/^>\s*(.*)$/", $line, $quoteParts);
$quote = $quoteParts[1];
echo "\n";
if (empty($quote))
echo "
\n";
else
htmlPrepare($quote);
if ($mode_textAttributes xor $mode_textAttributes_temp) addTextAttributes($line);
echo "".$quote."
\n";
} elseif ("* " == $line2) {
echo "\n";
$mode = "ul";
continue;
} else {
$mode = "raw";
continue;
}
} else {
if ("raw"==$mode) {
htmlPrepare($line);
if ($mode_textAttributes xor $mode_textAttributes_temp) addTextAttributes($line);
if (empty($line)) $line = " ";
echo "$line
\n";
$mode = null;
} elseif ("pre"==$mode) {
if ("```" == $line3) {
echo "
\n";
$mode = null;
} else {
htmlPrepare($line);
echo $line."\n";
}
} elseif ("quote"==$mode) {
if (">" == $line1) {
preg_match("/^>\s*(.*)$/", $line, $quoteParts);
$quote = $quoteParts[1];
if (empty($quote))
echo "
\n";
else
htmlPrepare($quote);
echo "".$quote."
\n";
} else {
echo "\n";
$mode = null;
continue;
}
} elseif ("ul"==$mode) {
if ("* " == $line2) {
preg_match("/^\*\s*(.*)$/", $line, $ulParts);
$li = $ulParts[1];
if (empty($li)) {
echo " \n";
} else {
htmlPrepare($li);
if ($mode_textAttributes xor $mode_textAttributes_temp) addTextAttributes($li);
echo "".$li."\n";
}
} else {
echo "\n";
$mode = null;
continue;
}
} else {
die("Unexpected mode: $mode!");
}
}
break; // exits the while(true) as no continue occured
}
}
$body = ob_get_contents();
ob_clean();
# Gets the page title: the first occurrence with # at the line start
mb_ereg("#\s*([^\n]+)\n", $fileContents, $matches);
$page_title = @$matches[1];
#
echo <<
$page_title
EOL;
echo "\n".$body;
echo "\n\n";
ob_end_flush();
?>