marked - npm Package Compare versions

Comparing version 0.1.1 to 0.1.2

lib/marked.js

@@ -14,3 +14,3 @@ /**
   newline: /^\n+/,
-  block: /^ {4,}[^\n]*(?:\n {4,}[^\n]*|\n)*(?=\n| *$)/,
+  code: /^ {4,}[^\n]*(?:\n {4,}[^\n]*|\n)*(?=\n| *$)/,
   hr: /^( *[\-*_]){3,} *\n/,
@@ -25,16 +25,4 @@ heading: /^ *(#{1,6}) *([^\0]+?) *#* *\n+/,
 
-block.keys = [
-  'newline',
-  'block',
-  'heading',
-  'lheading',
-  'hr',
-  'blockquote',
-  'list',
-  'html',
-  'text'
-];
-
 /**
- * Lexer
+ * Block Lexer
  */
@@ -66,110 +54,145 @@
 block.token = function(str, tokens) {
-  str = str.replace(/^ +$/gm, '');
-
-  var rules = block
-    , keys = block.keys
-    , len = keys.length
-    , key
+  var str = str.replace(/^ +$/gm, '')
+    , loose
     , cap
-    , loose;
+    , item
+    , space
+    , i
+    , l;
 
-  var scan = function() {
-    if (!str) return;
-    for (var i = 0; i < len; i++) {
-      key = keys[i];
-      if (cap = rules[key].exec(str)) {
-        str = str.substring(cap[0].length);
-        return true;
+  while (str) {
+    // newline
+    if (cap = block.newline.exec(str)) {
+      str = str.substring(cap[0].length);
+      if (cap[0].length > 1) {
+        tokens.push({
+          type: 'space'
+        });
       }
+      continue;
     }
-  };
 
-  while (scan()) {
-    switch (key) {
-      case 'newline':
-        if (cap[0].length > 1) {
-          tokens.push({
-            type: 'space'
-          });
+    // code
+    if (cap = block.code.exec(str)) {
+      str = str.substring(cap[0].length);
+      cap = cap[0].replace(/^ {4}/gm, '');
+      tokens.push({
+        type: 'code',
+        text: cap
+      });
+      continue;
+    }
+
+    // heading
+    if (cap = block.heading.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'heading',
+        depth: cap[1].length,
+        text: cap[2]
+      });
+      continue;
+    }
+
+    // lheading
+    if (cap = block.lheading.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'heading',
+        depth: cap[2] === '=' ? 1 : 2,
+        text: cap[1]
+      });
+      continue;
+    }
+
+    // hr
+    if (cap = block.hr.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'hr'
+      });
+      continue;
+    }
+
+    // blockquote
+    if (cap = block.blockquote.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'blockquote_start'
+      });
+      cap = cap[0].replace(/^ *>/gm, '');
+      block.token(cap, tokens);
+      tokens.push({
+        type: 'blockquote_end'
+      });
+      continue;
+    }
+
+    // list
+    if (cap = block.list.exec(str)) {
+      str = str.substring(cap[0].length);
+
+      tokens.push({
+        type: 'list_start',
+        ordered: isFinite(cap[2])
+      });
+
+      loose = /\n *\n *(?:[*+-]|\d+\.)/.test(cap[0]);
+
+      // get each top-level item
+      cap = cap[0].match(
+        /^( *)([*+-]|\d+\.)[^\n]*(?:\n(?!\1(?:\2|\d+\.))[^\n]*)*/gm
+      );
+
+      i = 0;
+      l = cap.length;
+
+      for (; i < l; i++) {
+        // remove the list items sigil
+        // so its seen as the next token
+        item = cap[i].replace(/^ *([*+-]|\d+\.) */, '');
+        // outdent whatever the
+        // list item contains, hacky
+        space = /\n( +)/.exec(item);
+        if (space) {
+          space = new RegExp('^' + space[1], 'gm');
+          item = item.replace(space, '');
         }
-        break;
-      case 'hr':
         tokens.push({
-          type: 'hr'
+          type: loose
+            ? 'loose_item_start'
+            : 'list_item_start'
         });
-        break;
-      case 'lheading':
+        block.token(item, tokens);
         tokens.push({
-          type: 'heading',
-          depth: cap[2] === '=' ? 1 : 2,
-          text: cap[1]
+          type: 'list_item_end'
         });
-        break;
-      case 'heading':
-        tokens.push({
-          type: 'heading',
-          depth: cap[1].length,
-          text: cap[2]
-        });
-        break;
-      case 'block':
-        cap = cap[0].replace(/^ {4}/gm, '');
-        tokens.push({
-          type: 'block',
-          text: cap
-        });
-        break;
-      case 'list':
-        tokens.push({
-          type: 'list_start',
-          ordered: isFinite(cap[2])
-        });
-        loose = /\n *\n *(?:[*+-]|\d+\.)/.test(cap[0]);
-        // get each top-level item
-        cap = cap[0].match(
-          /^( *)([*+-]|\d+\.)[^\n]*(?:\n(?!\1(?:\2|\d+\.))[^\n]*)*/gm
-        );
-        each(cap, function(item) {
-          // remove the list items sigil
-          // so its seen as the next token
-          item = item.replace(/^ *([*+-]|\d+\.) */, '');
-          // outdent whatever the
-          // list item contains, hacky
-          var space = /\n( +)/.exec(item);
-          if (space) {
-            space = new RegExp('^' + space[1], 'gm');
-            item = item.replace(space, '');
-          }
-          tokens.push({
-            type: loose
-              ? 'loose_item_start'
-              : 'list_item_start'
-          });
-          block.token(item, tokens);
-          tokens.push({
-            type: 'list_item_end'
-          });
-        });
-        tokens.push({
-          type: 'list_end'
-        });
-        break;
-      case 'html':
-      case 'text':
-        tokens.push({
-          type: key,
-          text: cap[0]
-        });
-        break;
-      case 'blockquote':
-        tokens.push({
-          type: 'blockquote_start'
-        });
-        cap = cap[0].replace(/^ *>/gm, '');
-        block.token(cap, tokens);
-        tokens.push({
-          type: 'blockquote_end'
-        });
-        break;
+      }
+
+      tokens.push({
+        type: 'list_end'
+      });
+
+      continue;
     }
+
+    // html
+    if (cap = block.html.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'html',
+        text: cap[0]
+      });
+      continue;
+    }
+
+    // text
+    if (cap = block.text.exec(str)) {
+      str = str.substring(cap[0].length);
+      tokens.push({
+        type: 'text',
+        text: cap[0]
+      });
+      continue;
+    }
   }
@@ -198,16 +221,2 @@
 
-inline.keys = [
-  'escape',
-  'autolink',
-  'tag',
-  'link',
-  'reflink',
-  'nolink',
-  'strong',
-  'em',
-  'code',
-  'br',
-  'text'
-];
-
 // hacky, but performant
@@ -243,109 +252,107 @@ inline.text = (function() {
     , text
-    , href;
-
-  var rules = inline
-    , keys = inline.keys
-    , len = keys.length
-    , key
+    , href
     , cap;
 
-  var scan = function() {
-    if (!str) return;
-    for (var i = 0; i < len; i++) {
-      key = keys[i];
-      if (cap = rules[key].exec(str)) {
-        str = str.substring(cap[0].length);
-        return true;
+  while (str) {
+    // escape
+    if (cap = inline.escape.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += cap[1];
+      continue;
+    }
+
+    // autolink
+    if (cap = inline.autolink.exec(str)) {
+      str = str.substring(cap[0].length);
+      if (cap[2] === '@') {
+        text = cap[1][6] === ':'
+          ? mangle(cap[1].substring(7))
+          : mangle(cap[1]);
+        href = mangle('mailto:') + text;
+      } else {
+        text = escape(cap[1]);
+        href = text;
       }
+      out += '<a href="'
+        + href
+        + '">'
+        + text
+        + '</a>';
+      continue;
     }
-  };
 
-  while (scan()) {
-    switch (key) {
-      case 'escape':
-        out += cap[1];
-        break;
-      case 'tag':
-        out += cap[0];
-        break;
-      case 'link':
-      case 'reflink':
-      case 'nolink':
-        if (key !== 'link') {
-          link = (cap[2] || cap[1]).replace(/\s+/g, ' ');
-          link = links[link];
-          if (!link) {
-            out += cap[0][0];
-            str = cap[0].substring(1) + str;
-            break;
-          }
-        } else {
-          text = /^\s*<?([^\s]*?)>?(?:\s+"([^\n]+)")?\s*$/.exec(cap[2]);
-          link = {
-            href: text[1],
-            title: text[2]
-          };
-        }
-        if (cap[0][0] !== '!') {
-          out += '<a href="'
-            + escape(link.href)
-            + '"'
-            + (link.title
-            ? ' title="'
-            + escape(link.title)
-            + '"'
-            : '')
-            + '>'
-            + inline.lexer(cap[1])
-            + '</a>';
-        } else {
-          out += '<img src="'
-            + escape(link.href)
-            + '" alt="'
-            + escape(cap[1])
-            + '"'
-            + (link.title
-            ? ' title="'
-            + escape(link.title)
-            + '"'
-            : '')
-            + '>';
-        }
-        break;
-      case 'autolink':
-        if (cap[2] === '@') {
-          text = cap[1][6] === ':'
-            ? mangle(cap[1].substring(7))
-            : mangle(cap[1]);
-          href = mangle('mailto:') + text;
-        } else {
-          text = escape(cap[1]);
-          href = text;
-        }
-        out += '<a href="' + href + '">'
-          + text
-          + '</a>';
-        break;
-      case 'strong':
-        out += '<strong>'
-          + inline.lexer(cap[2] || cap[1])
-          + '</strong>';
-        break;
-      case 'em':
-        out += '<em>'
-          + inline.lexer(cap[2] || cap[1])
-          + '</em>';
-        break;
-      case 'code':
-        out += '<code>'
-          + escape(cap[2] || cap[1])
-          + '</code>';
-        break;
-      case 'br':
-        out += '<br>';
-        break;
-      case 'text':
-        out += escape(cap[0]);
-        break;
+    // tag
+    if (cap = inline.tag.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += cap[0];
+      continue;
     }
+
+    // link
+    if (cap = inline.link.exec(str)) {
+      str = str.substring(cap[0].length);
+      text = /^\s*<?([^\s]*?)>?(?:\s+"([^\n]+)")?\s*$/.exec(cap[2]);
+      link = {
+        href: text[1],
+        title: text[2]
+      };
+      out += mlink(cap, link);
+      continue;
+    }
+
+    // reflink, nolink
+    if ((cap = inline.reflink.exec(str))
+        || (cap = inline.nolink.exec(str))) {
+      str = str.substring(cap[0].length);
+      link = (cap[2] || cap[1]).replace(/\s+/g, ' ');
+      link = links[link];
+      if (!link) {
+        out += cap[0][0];
+        str = cap[0].substring(1) + str;
+        continue;
+      }
+      out += mlink(cap, link);
+      continue;
+    }
+
+    // strong
+    if (cap = inline.strong.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += '<strong>'
+        + inline.lexer(cap[2] || cap[1])
+        + '</strong>';
+      continue;
+    }
+
+    // em
+    if (cap = inline.em.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += '<em>'
+        + inline.lexer(cap[2] || cap[1])
+        + '</em>';
+      continue;
+    }
+
+    // code
+    if (cap = inline.code.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += '<code>'
+        + escape(cap[2] || cap[1])
+        + '</code>';
+      continue;
+    }
+
+    // br
+    if (cap = inline.br.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += '<br>';
+      continue;
+    }
+
+    // text
+    if (cap = inline.text.exec(str)) {
+      str = str.substring(cap[0].length);
+      out += escape(cap[0]);
+      continue;
+    }
   }
@@ -356,2 +363,30 @@
 
+var mlink = function(cap, link) {
+  if (cap[0][0] !== '!') {
+    return '<a href="'
+      + escape(link.href)
+      + '"'
+      + (link.title
+      ? ' title="'
+      + escape(link.title)
+      + '"'
+      : '')
+      + '>'
+      + inline.lexer(cap[1])
+      + '</a>';
+  } else {
+    return '<img src="'
+      + escape(link.href)
+      + '" alt="'
+      + escape(cap[1])
+      + '"'
+      + (link.title
+      ? ' title="'
+      + escape(link.title)
+      + '"'
+      : '')
+      + '>';
+  }
+};
+
 /**
@@ -370,33 +405,52 @@ * Parsing
   switch (token.type) {
-    case 'space':
+    case 'space': {
       return '';
-    case 'hr':
+    }
+    case 'hr': {
       return '<hr>';
-    case 'heading':
-      return '<h' + token.depth + '>'
+    }
+    case 'heading': {
+      return '<h'
+        + token.depth
+        + '>'
         + inline.lexer(token.text)
-        + '</h' + token.depth + '>';
-    case 'block':
+        + '</h'
+        + token.depth
+        + '>';
+    }
+    case 'code': {
       return '<pre><code>'
         + escape(token.text)
         + '</code></pre>';
-    case 'blockquote_start':
+    }
+    case 'blockquote_start': {
       var body = [];
+
       while (next().type !== 'blockquote_end') {
         body.push(tok());
       }
+
       return '<blockquote>'
         + body.join('')
         + '</blockquote>';
-    case 'list_start':
+    }
+    case 'list_start': {
       var type = token.ordered ? 'ol' : 'ul'
         , body = [];
+
       while (next().type !== 'list_end') {
         body.push(tok());
       }
-      return '<' + type + '>'
+
+      return '<'
+        + type
+        + '>'
         + body.join('')
-        + '</' + type + '>';
-    case 'list_item_start':
+        + '</'
+        + type
+        + '>';
+    }
+    case 'list_item_start': {
       var body = [];
+
       while (next().type !== 'list_item_end') {
@@ -407,18 +461,27 @@ body.push(token.type === 'text'
       }
+
       return '<li>'
         + body.join(' ')
         + '</li>';
-    case 'loose_item_start':
+    }
+    case 'loose_item_start': {
       var body = [];
+
       while (next().type !== 'list_item_end') {
         body.push(tok());
       }
+
       return '<li>'
         + body.join(' ')
         + '</li>';
-    case 'html':
+    }
+    case 'html': {
       return inline.lexer(token.text);
-    case 'text':
-      return '<p>' + text() + '</p>';
- }
+    }
+    case 'text': {
+      return '<p>'
+        + text()
+        + '</p>';
+    }
+  }
 };
@@ -482,7 +545,2 @@
 
-var each = function(obj, func) {
-  var i = 0, l = obj.length;
-  for (; i < l; i++) func(obj[i]);
-};
-
 /**
@@ -489,0 +547,0 @@ * Expose

package.json

@@ -5,3 +5,3 @@ {
   "author": "Christopher Jeffrey",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "main": "./lib/marked.js",
@@ -8,0 +8,0 @@ "bin": { "marked": "./bin/marked" },

README.md

 # marked
 
-A full-featured markdown parser and compiler implemented in ~430 lines of JS.  
+A full-featured markdown parser and compiler implemented in ~430 lines of JS.
 Built for speed.
@@ -10,5 +10,6 @@
 $ node test --bench
-marked completed in 15051ms.
-showdown completed in 28267ms. 
-markdown-js completed in 70732ms.
+marked completed in 12071ms.
+showdown (reuse converter) completed in 27387ms.
+showdown (new converter) completed in 75617ms.
+markdown-js completed in 70069ms.
 ```
@@ -24,15 +25,15 @@
 
-The point of marked was to create a markdown compiler where it was possible to 
-frequently parse huge chunks of markdown without having to worry about 
+The point of marked was to create a markdown compiler where it was possible to
+frequently parse huge chunks of markdown without having to worry about
 caching the compiled output somehow...or blocking for an unnecesarily long time.
 
-marked lingers around 430 (may vary) lines long and still implements all 
+marked lingers around 430 (may vary) lines long and still implements all
 markdown features. It is also now fully compatible with the client-side.
 
-marked more or less passes the official markdown test suite in its 
-entirety. This is important because a surprising number of markdown compilers 
-cannot pass more than a few tests. It was very difficult to get marked as 
-compliant as it is. It could have cut corners in several areas for the sake 
-of performance, but did not in order to be exactly what you expect in terms 
-of a markdown rendering. In fact, this is why marked could be considered at a 
+marked more or less passes the official markdown test suite in its
+entirety. This is important because a surprising number of markdown compilers
+cannot pass more than a few tests. It was very difficult to get marked as
+compliant as it is. It could have cut corners in several areas for the sake
+of performance, but did not in order to be exactly what you expect in terms
+of a markdown rendering. In fact, this is why marked could be considered at a
 disadvantage in the benchmarks above.
@@ -66,6 +67,6 @@
 - Implement GFM features.
-- Possibly add some 
-  [ReMarkable](http://camendesign.com/code/remarkable/documentation.html) 
+- Possibly add some
+  [ReMarkable](http://camendesign.com/code/remarkable/documentation.html)
   features while remaining backwardly compatible with all markdown syntax.
 - Optimize the lexer to return an iterator instead of a collection of tokens.
 - Add an explicit pretty printing and minification feature.

test/index.js

@@ -51,3 +51,3 @@ #!/usr/bin/env node
 
-main: 
+main:
   for (; i_ < l_; i_++) {
@@ -57,10 +57,10 @@ filename = keys[i_];
 
-    // this was messing with 
+    // this was messing with
     // `node test | less` on sakura
-    try { 
+    try {
       text = marked(file.text).replace(/\s/g, '');
       html = file.html.replace(/\s/g, '');
-    } catch(e) { 
-      console.log('%s failed.', filename); 
-      throw e; 
+    } catch(e) {
+      console.log('%s failed.', filename);
+      throw e;
     }
@@ -74,13 +74,13 @@
         text = text.substring(
-          Math.max(i - 30, 0), 
+          Math.max(i - 30, 0),
           Math.min(i + 30, text.length));
         html = html.substring(
-          Math.max(i - 30, 0), 
+          Math.max(i - 30, 0),
           Math.min(i + 30, html.length));
         console.log(
-          '\n#%d. %s failed at offset %d. Near: "%s".\n', 
+          '\n#%d. %s failed at offset %d. Near: "%s".\n',
           i_ + 1, filename, i, text);
-        console.log('\nGot:\n%s\n', 
+        console.log('\nGot:\n%s\n',
           pretty(text).trim() || text);
-        console.log('\nExpected:\n%s\n', 
+        console.log('\nExpected:\n%s\n',
           pretty(html).trim() || html);
@@ -130,12 +130,2 @@ if (breakOnError) {
 
-  /**
-   * There's two ways to benchmark showdown here.
-   * The first way is to create a new converter
-   * every time, this will renew any closured
-   * variables. It is the "proper" way of using
-   * showdown. However, for this benchmark, 
-   * I will use the completely improper method
-   * which is must faster, just to be fair.
-   */
-
   var showdown = (function() {
@@ -148,4 +138,13 @@ var Showdown = require('showdown').Showdown;
   })();
-  main.bench('showdown', showdown);
+  main.bench('showdown (reuse converter)', showdown);
 
+  var showdown_slow = (function() {
+    var Showdown = require('showdown').Showdown;
+    return function(text) {
+      var convert = new Showdown.converter();
+      return convert.makeHtml(text);
+    };
+  })();
+  main.bench('showdown (new converter)', showdown_slow);
+
   var markdownjs = require('markdown-js');
@@ -157,2 +156,7 @@ main.bench('markdown-js', function(text) {
 
+var time = function() {
+  var marked = require('../');
+  main.bench('marked', marked);
+};
+
 var old_bench = function() {
@@ -252,3 +256,3 @@ var text = fs.readFileSync(__dirname + '/main.md', 'utf8');
 
-    // temporarily remove elements before 
+    // temporarily remove elements before
     // processing, also remove whitespace
@@ -259,3 +263,3 @@ str = str.replace(remove, function(element, name) {
           .replace(/[\r\n]/g, '');
-      return '<!' + (hash.push(element) - 1) 
+      return '<!' + (hash.push(element) - 1)
                   + (Array(element.length - 3).join('%')) + '/>';
@@ -282,5 +286,5 @@ });
         out.push(indent(depth) + full);
-        if (!closing[name] 
-            && name[0] !== '!' 
-            && name[0] !== '?' 
+        if (!closing[name]
+            && name[0] !== '!'
+            && name[0] !== '?'
             && tag[tag.length-1] !== '/') {
@@ -296,3 +300,3 @@ depth++;
 
-    // restore the elements to 
+    // restore the elements to
     // their original locations
@@ -324,2 +328,4 @@ str = str.replace(replace, function($0, $1) {
     bench();
+  } else if (~process.argv.indexOf('--time')) {
+    time();
   } else if (~process.argv.indexOf('--old_bench')) {
@@ -326,0 +332,0 @@ old_bench();

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

216350

increased by0.4%

Lines of code

849

increased by4.56%

Number of lines in readme file

70

increased by1.45%

No dependency changes