From 859b0aad811d730377f48abe90169b1603f95966 Mon Sep 17 00:00:00 2001 From: Christophe HENRY Date: Tue, 16 Mar 2021 20:54:10 +0100 Subject: [PATCH] Deep refactoring: parsing, translating, classes * Removes "^" to disable text decoration line-wise. * Split HTML generation in two: parsing and translating. * Create class to handle gemtext parsing. * Create class to translate to HTML. * Create class to generate back gemtext (for future test cases). * Uses generators to parse then translate. * Fix: 404 doesn't occur for an empty file. * Page 404 fully generated by HtmGem itself. * CSS is no longer incorporated in the HTML page. * Handle CSS inclusion by addCss() calls. --- index.gmi | 3 +- index.php | 147 ++++++--------- lib-htmgem.php | 467 +++++++++++++++++++++++++++++++----------------- tutogemtext.gmi | 4 +- 4 files changed, 353 insertions(+), 268 deletions(-) diff --git a/index.gmi b/index.gmi index ba08644..5be4e06 100644 --- a/index.gmi +++ b/index.gmi @@ -118,8 +118,7 @@ La décoration du texte, qui interprête le **gras** par exemple, ne fait pas pa ### Désactiver la décoration du texte On peut : -* commencer la ligne par **^**, -* faire un bloc non décoré avec **^^^**, +* désactiver et activer la décoration du texte avec une ligne **^^^**, * ajouter ce qui suit à la **réécriture** d’URL : > &textDecoration=0 diff --git a/index.php b/index.php index cac10d5..5832956 100644 --- a/index.php +++ b/index.php @@ -1,91 +1,61 @@ "); } -?> - - - -Installation de HtmGem - - - - -\n\n"; - die(); + $t = new \htmgem\GemTextTranslate_html(@file_get_contents("index.gmi")); + echo $t->getFullHtml(); + exit(); } -######################################## /Installation page + + +# to false only if textDecoration=0 in the URL +$textDecoration = "0" != @$_REQUEST['textDecoration']; # Removes the headling and trailling slashes, to be sure there's not any. $filePath = rtrim($_SERVER['DOCUMENT_ROOT'], "/")."/".ltrim($url, "/"); -$fileContents = @file_get_contents($filePath); - - -######################################## 404 page -if (empty($fileContents)) { +/* 404 page + */ +if (!file_exists($filePath)) { error_log("HtmGem: 404 $url $filePath"); - http_response_code(404); ?> - - - - - - - - $url Recharger 🔄 - => / EOF; -echo translateGemToHtml($text404); -echo "\n"; -die(); + $t = new \htmgem\GemTextTranslate_html($page404); + echo $t->getFullHtml(); + exit(); } -######################################## /404 page + +$fileContents = @file_get_contents($filePath); # Removes the Byte Order Mark $fileContents = preg_replace("/\xEF\xBB\xBF/", "", $fileContents); -# Gets the page title: the first occurrence with # at the line start -mb_ereg("#\s*([^\n]+)\n", $fileContents, $matches); -$page_title = @$matches[1]; -###################################### CSS Management -/** -* if &style=source displays the source directly and stops. -* if there's a filename.css besides filename.gmi, use the css and stops. -* if &style= then embbed the default style, and stops. -* if &style= then use htmgem/word.css -* if &style=/… then use the … as as stylesheet. -**/ +/* CSS and special style management + */ +$style = @$_REQUEST['style']; if ("source" == $style) { $basename = basename($filePath); header("Cache-Control: public"); @@ -93,9 +63,12 @@ if ("source" == $style) { header("Content-Type: text/plain"); header("Content-Transfer-Encoding: binary"); header('Content-Length: ' . filesize($filePath)); - readfile($filePath); + echo $fileContents; exit(); } elseif ("pre" == $style) { + # Gets the page title: the first occurrence with # at the line start + mb_ereg("#\s*([^\n]+)\n", $fileContents, $matches); + $page_title = @$matches[1]; $fileContents = htmlspecialchars($fileContents, ENT_HTML5|ENT_NOQUOTES, "UTF-8", false); echo << @@ -104,52 +77,32 @@ if ("source" == $style) { $page_title -
$fileContents
+
+$fileContents
EOL; + exit(); } else { - $parts = pathinfo($filePath); - $localCss = $parts["filename"].".css"; - $localCssFilePath = $parts["dirname"]."/".$localCss; - if (file_exists($localCssFilePath)) { - # Warning, using htmhem.php?url=… will make $localCss not found - # as the path is relative to htmgem.php and not / ! - $cssContent = ""; - } else { - if (empty($style)) { - $cssContent = - "\n"; - } else { - if ("none" == $style) { - $cssContent = ""; - } else { - if ("/" == $style[0]) - $href = $style; - else - $href = "/htmgem/css/$style.css"; - $cssContent = ""; - } + $t = new \htmgem\GemTextTranslate_html($fileContents); + if ("none" == $style) { + $t->addCss(""); + } elseif ("/" == @$style[0]) { + $t->addCss($style); + } elseif (empty($style)) { + $parts = pathinfo($filePath); + $localCss = $parts["filename"].".css"; + $localCssFilePath = $parts["dirname"]."/".$localCss; + if (file_exists($localCssFilePath)) { + # Warning, using htmhem.php?url=… will make $localCss not found + # as the path is relative to htmgem.php and not / ! + $t->addCss($localCss); } + } else { #TODO: regex check for $style + $t->addCss("/htmgem/css/$style.css"); } - echo << - - -$page_title - -$cssContent - - -EOL; - - echo "\n".translateGemToHtml($fileContents); - echo "\n\n"; } - -ob_end_flush(); +echo $t->getFullHtml(); ?> diff --git a/lib-htmgem.php b/lib-htmgem.php index 0711a93..1b40b39 100644 --- a/lib-htmgem.php +++ b/lib-htmgem.php @@ -5,203 +5,78 @@ namespace htmgem; mb_internal_encoding("UTF-8"); mb_regex_encoding("UTF-8"); -$style = @$_REQUEST['style']; - -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) -); - /** - * Replaces markups things like __underlined__ to underlined. - * @param $instruction the characters to replace, ex. _ - * @param $markup the markup to replace to, ex. "u" to get … - * @param &$text where to replace. + * Parses the gemtext and generates the internal format version + * @param str $fileContents the gemtext to parse */ -function markupPreg($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) { - global $textDecoration; - if (!$textDecoration) return; - markupPreg("__", "u", $line); - markupPreg("\*\*", "strong", $line); - markupPreg("//", "em", $line); - markupPreg("~~", "del", $line); -} - -/** - * 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.", $text); -} - -function translateGemToHtml($fileContents) { - $fileLines = preg_split("/\n/", $fileContents); - if (empty($fileLines[-1])) array_pop($fileLines); # Don't output a last empty line - ob_start(); +function gemtextParser($fileContents) { + $fileLines = explode("\n", $fileContents); $mode = null; - $mode_textAttributes = true; + $current = array(); foreach ($fileLines as $line) { $reDoCount = 0; $mode_textAttributes_temp = false; while (true) { - if ($reDoCount>2) { - error_log("HtmGem: Too many loops, mode == '$mode'"); - $mode = null; - $reDoCount = 0; - break; + /* The continue instruction is used to make another turn when there is a transition + * between two modes. */ + if ($reDoCount>1) { + die("HtmGem: Too many loops, mode == '$mode'"); } $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) { - $mode_textAttributes = !$mode_textAttributes; - } elseif ('^' == $line1 and !$mode_textAttributes_temp) { - if (preg_match("/^\^\s*(.+)$/", $line, $parts)) { - $line = $parts[1]; - $mode_textAttributes_temp = true; - } else { - $mode = "raw"; - } - continue; + if ('^^^' == $line3) { + yield array("mode" => "^^^"); } elseif ("#" == $line1) { - if (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; - } - } else { - $mode = "raw"; - continue; - } + preg_match("/^(#{1,3})\s*(.+)/", $line, $matches); + yield array("mode" => $matches[1], "title" => trim($matches[2])); } elseif ("=>" == $line2) { - if (preg_match("/^=>\s*([^\s]+)(?:\s+(.*))?$/", $line, $linkParts)) { - $url_link = $linkParts[1]; - $url_label = @$linkParts[2]; - preg_match("/^([^:]+):/", $url_link, $matches); - $url_protocol = @$matches[1]; - if (empty($url_protocol)) $url_protocol = "local"; - if (empty(trim($url_label))) { - $url_label = $url_link; - } else { - // the label is humain-made, apply formatting - htmlPrepare($url_label); - if ($mode_textAttributes xor $mode_textAttributes_temp) addTextAttributes($url_label); - } - echo "

$url_label

\n"; - } else { - $mode = "raw"; - continue; - } + preg_match("/^=>\s*([^\s]+)(?:\s+(.*))?$/", $line, $matches); + yield array("mode" => "=>", "link" => trim($matches[1]), "text" => trim(@$matches[2])); } elseif ("```" == $line3) { preg_match("/^```\s*(.*)$/", $line, $matches); - $alt_text = trim($matches[1]); - if (empty($alt_text)) { - echo "
\n";
-                    } else {
-                        echo "
\n";
-                    }
-                    $mode="pre";
+                    $current = array("mode" => "```", "alt" => trim($matches[1]), "texts" => array());
+                    $mode="```";
                 } elseif (">" == $line1) {
-                    echo "
\n";
-                    $mode = "quote";
-                    continue;
+                    preg_match("/^>\s*(.*)$/", $line, $matches);
+                    $current = array("mode" => ">", "texts" => array(trim($matches[1])));
+                    $mode = ">";
                 } elseif ("*" == $line1) {
-                    echo "
    \n";
-                    $mode = "ul";
-                    continue;
+                    preg_match("/^\*\s*(.*)$/", $line, $matches);
+                    $current = array("mode" => "*", "texts" => array(trim($matches[1])));
+                    $mode = "*";
                 } else {
-                    $mode = "raw";
-                    continue;
+                    // text_line
+                    yield array("mode"=>"", "text" => trim($line));
                 }
             } else {
-                if ("raw"==$mode) {
-                    if (empty($line)) {
-                        $line = " ";
-                    } else {
-                        htmlPrepare($line);
-                        if ($mode_textAttributes xor $mode_textAttributes_temp)
-                            addTextAttributes($line);
-                    }
-                    echo "
    $line
    \n";
-                    $mode = null;
-                } elseif ("pre"==$mode) {
+                if ("```"==$mode) {
                     if ("```" == $line3) {
-                        echo "
\n";
+                        yield $current;
+                        $current = array();
                         $mode = null;
                     } else {
-                        htmlPrepare($line);
-                        echo $line."\n";
+                        $current["texts"] []= $line; // No trim() as it’s a preformated text!
                     }
-                } elseif ("quote"==$mode) {
+                } elseif (">"==$mode) {
                     if (">" == $line1) {
-                        preg_match("/^>\s*(.*)$/", $line, $quoteParts);
-                        $quote = $quoteParts[1];
-                        if (empty($quote))
-                            echo "
 
\n";
-                        else {
-                            htmlPrepare($quote);
-                            if ($mode_textAttributes xor $mode_textAttributes_temp)
-                                addTextAttributes($line);
-                            echo "
".$quote."
\n";
-                        }
+                        preg_match("/^>\s*(.*)$/", $line, $matches);
+                        $current["texts"] []= trim($matches[1]);
                     } else {
-                        echo "\n";
+                        yield $current;
+                        $current = array();
                         $mode = null;
                         continue;
                     }
-                } elseif ("ul"==$mode) {
+                } elseif ("*"==$mode) {
                     if ("*" == $line1) {
-                        preg_match("/^\*\s*(.*)$/", $line, $ulParts);
-                        $li = $ulParts[1];
-                        if (empty($li)) {
-                            echo "
  •  \n";
-                        } else {
-                            htmlPrepare($li);
-                            if ($mode_textAttributes xor $mode_textAttributes_temp) addTextAttributes($li);
-                            echo "
  • ".$li."\n";
-                        }
+                        preg_match("/^\*\s*(.*)$/", $line, $matches);
+                        $current["texts"] []= trim($matches[1]);
                     } else {
-                        echo "\n";
+                        yield $current;
+                        $current = array();
                         $mode = null;
                         continue;
                     }
@@ -211,10 +86,266 @@ function translateGemToHtml($fileContents) {
             }
             break; // exits the while(true) as no continue occured
         } // while(true)
+    }// foreach
+    if ($current) yield $current; # File ends before the block.
+} // gemtextParser
+
+
+/**
+ * Translates the internal format into a gemtext.
+ * Uses cases:
+ *
+ * - test suites
+ * - serialisation easier with a text content
+ * - normalization (trimming spaces for instance)
+ */
+class GemtextTranslate_gemtext {
+
+    function __construct($parsedGemtext) {
+        $this->parsedGemtext = $parsedGemtext;
+        $this->translate();
     }
-    $html = ob_get_contents();
-    ob_clean();
-    return $html;
-}
+
+    protected function translate() {
+        ob_start();
+        foreach ($this->parsedGemtext as $node) {
+            $mode = $node["mode"];
+            switch($mode) {
+                case "":
+                    echo $node["text"]."\n";
+                    break;
+                case "*":
+                    foreach ($node["texts"] as $text) {
+                        echo "* $text\n";
+                    }
+                    break;
+                case "```":
+                    print("```\n");
+                    foreach ($node["texts"] as $text) {
+                        echo "$text\n";
+                    }
+                    print("```\n");
+                    break;
+                case ">":
+                    foreach ($node["texts"] as $text) {
+                        echo "> $text\n";
+                    }
+                    break;
+                case "=>":
+                    $linkText = $node["text"];
+                    if (!empty($linkText)) $linkText = " $linkText";
+                    print("=> ".$node["link"].$linkText."\n");
+                    break;
+                case "#":
+                case "##":
+                case "###":
+                    print("$mode ".$node["title"]."\n");
+                    break;
+                case "^^^":
+                    print("^^^\n");
+                    break;
+                default:
+                    die("Unknown mode: '{$node["mode"]}'\n");
+            }
+        }
+
+        $this->translatedGemtext = ob_get_contents();
+        ob_end_clean();
+    }
+
+    public function __toString() {
+        return $this->translatedGemtext;
+    }
+} // GemtextTranslate_gemtext
+
+
+/**
+ * Translates the internal format to HTML
+ */
+class GemtextTranslate_html {
+
+    protected $cssList = array();
+    protected $pageTitle = "";
+    public $translatedGemtext;
+
+    function __construct($parsedGemtext, $textDecorationEnabled=true) {
+        if (empty($parsedGemtext))
+            // So translate() will do no loop.
+            $parsedGemtext = array();
+        elseif (is_string($parsedGemtext))
+            // to delete the last empty line, 
     
     in HTML
+            $parsedGemtext = rtrim($parsedGemtext);
+            // The text must be parsed
+            $parsedGemtext = gemtextParser($parsedGemtext);
+        $this->parsedGemtext = $parsedGemtext;
+        $this->translate($textDecorationEnabled);
+    }
+
+    function addCss($css) {
+        $this->cssList []= $css;
+    }
+
+    const NARROW_NO_BREAK_SPACE = " ";
+    const 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)
+    ;
+
+    /**
+     * Replaces markups things like __underlined__ to underlined.
+     * @param $instruction the characters to replace, ex. _
+     * @param $markup the markup to replace to, ex. "u" to get …
+     * @param &$text where to replace.
+     */
+    protected static 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 $line the line to process
+     */
+    protected static function addTextDecoration(&$line) {
+        self::markupPreg("__",   "u",      $line);
+        self::markupPreg("\*\*", "strong", $line);
+        self::markupPreg("//",   "em",     $line);
+        self::markupPreg("~~",   "del",    $line);
+    }
+
+    /**
+     * 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, $text2 texts to process
+     */
+    protected static function htmlPrepare(&$text) {
+        if (empty($text)) {
+            $text = " ";
+        } else {
+            $text = htmlspecialchars($text, ENT_HTML5|ENT_NOQUOTES, "UTF-8", false);
+            $text = mb_ereg_replace("\ ([?!:;»€$])", self::NARROW_NO_BREAK_SPACE."\\1", $text);
+            $text = mb_ereg_replace("([«])\ ", "\\1".self::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("([".self::DASHES."]) ([^".self::DASHES.".]+) ([".self::DASHES."])", "\\1".self::NARROW_NO_BREAK_SPACE."\\2".self::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".self::NARROW_NO_BREAK_SPACE."\\2.", $text);
+        }
+    }
+
+    public function translate($textDecoration=true) {
+        ob_start();
+        foreach ($this->parsedGemtext as $node) {
+            $mode = $node["mode"];
+            switch($mode) {
+                case "":
+                    $text = $node["text"];
+                    self::htmlPrepare($text);
+                    if ($textDecoration) self::addTextDecoration($text);
+                    echo "
    $text
    \n";
+                    break;
+                case "*":
+                    echo "
      \n";
+                    foreach ($node["texts"] as $text) {
+                        self::htmlPrepare($text);
+                        if ($textDecoration) self::addTextDecoration($text);
+                        print("
    • $text\n");
+                    }
+                    echo "
    \n";
+                    break;
+                case "```":
+                    $text = implode("\n", $node["texts"]);
+                    self::htmlPrepare($text);
+                    echo "
    \n$text\n
    \n";
+                    break;
+                case ">":
+                    $text = implode("\n", $node["texts"]);
+                    self::htmlPrepare($text);
+                    if ($textDecoration) self::addTextDecoration($text);
+                    echo "
    \n$text\n
    \n";
+                    break;
+                case "=>":
+                    $link = $node["link"];
+                    $linkText = $node["text"];
+                    if (empty($linkText)) {
+                        $linkText = $link;
+                        self::htmlPrepare($linkText);
+                    } else {
+                        self::htmlPrepare($linkText);
+                        if ($textDecoration) self::addTextDecoration($linkText);
+                    }
+                    preg_match("/^([^:]+):/", $link, $matches);
+                    $protocol = @$matches[1];
+                    if (empty($protocol)) $protocol = "local";
+                    echo "
    $linkText
    \n";
+                    break;
+                case "#":
+                    $title = $node["title"];
+                    self::htmlPrepare($title);
+                    if (empty($this->pageTitle)) $this->pageTitle = $title;
+                    echo "
    $title
    \n";
+                    break;
+                case "##":
+                    $title = $node["title"];
+                    self::htmlPrepare($title);
+                    echo "
    $title
    \n";
+                    break;
+                case "###":
+                    $title = $node["title"];
+                    self::htmlPrepare($title);
+                    echo "
    $title
    \n";
+                    break;
+                case "^^^":
+                    $this->textDecorationEnabled = !$this->textDecorationEnabled;
+                    break;
+                default:
+                    die("Unknown mode: '{$node["mode"]}'\n");
+            }
+        }
+
+        $this->translatedGemtext = ob_get_contents();
+        ob_end_clean();
+    }
+
+    function getFullHtml() {
+        if (!$this->cssList)
+            $css = array("/htmgem/css/htmgem.css");
+        else
+            $css = $this->cssList;
+        echo <<
+
+
+{$this->pageTitle}
+
+EOL;
+        foreach ($css as $c) {
+            echo "\n";
+        }
+        echo <<
+\n
+EOL;
+        echo $this->translatedGemtext;
+        echo "\n\n";
+    }
+
+    public function __toString() {
+        return $this->translatedGemtext;
+    }
+} // GemTextTranslate_html
 
 ?>
diff --git a/tutogemtext.gmi b/tutogemtext.gmi
index a0d6f1c..32f03c7 100644
--- a/tutogemtext.gmi
+++ b/tutogemtext.gmi
@@ -53,9 +53,11 @@ Il ne peut exister qu’un lien par ligne. Et la ligne est dédiée à ça ! Voi
 
 La décoration du texte ne fait pas partie des spécifications de Gemini.
 
-^ Cette **ligne** utilise la //décoration du texte// qui peut ~~barrer~~ ou __souligner__ des mots.
+Cette *​*ligne*​* utilise la /​/décoration du texte/​/ qui peut ~​~barrer~​~ ou _​_souligner_​_ des mots.
 Cette **ligne** utilise la //décoration du texte// qui peut ~~barrer~~ ou __souligner__ des mots.
 
+On peut désactiver et activer la décoration du texte avec **^^^** sur une ligne.
+
 Et voilà ! Vous savez tout ce qui est à savoir 🥳 Les spécifications complètes sont sur le site de Gemini :
 => https://gemini.circumlunar.space/docs/specification.gmi