marked 0.8.0 → 1.1.0

package/src/Lexer.js

@@ -1,10 +1,47 @@
+const Tokenizer = require('./Tokenizer.js');
 const { defaults } = require('./defaults.js');
-const { block } = require('./rules.js');
-const {
-  rtrim,
-  splitCells,
-  escape
-} = require('./helpers.js');
+const { block, inline } = require('./rules.js');
+
+/**
+ * smartypants text replacement
+ */
+function smartypants(text) {
+  return text
+    // em-dashes
+    .replace(/---/g, '\u2014')
+    // en-dashes
+    .replace(/--/g, '\u2013')
+    // opening singles
+    .replace(/(^|[-\u2014/(\[{"\s])'/g, '$1\u2018')
+    // closing singles & apostrophes
+    .replace(/'/g, '\u2019')
+    // opening doubles
+    .replace(/(^|[-\u2014/(\[{\u2018\s])"/g, '$1\u201c')
+    // closing doubles
+    .replace(/"/g, '\u201d')
+    // ellipses
+    .replace(/\.{3}/g, '\u2026');
+}
+
+/**
+ * mangle email addresses
+ */
+function mangle(text) {
+  let out = '',
+    i,
+    ch;
+
+  const l = text.length;
+  for (i = 0; i < l; i++) {
+    ch = text.charCodeAt(i);
+    if (Math.random() > 0.5) {
+      ch = 'x' + ch.toString(16);
+    }
+    out += '&#' + ch + ';';
+  }
+
+  return out;
+}
 
 /**
  * Block Lexer
@@ -14,20 +51,37 @@ module.exports = class Lexer {
     this.tokens = [];
     this.tokens.links = Object.create(null);
     this.options = options || defaults;
-    this.rules = block.normal;
+    this.options.tokenizer = this.options.tokenizer || new Tokenizer();
+    this.tokenizer = this.options.tokenizer;
+    this.tokenizer.options = this.options;
+
+    const rules = {
+      block: block.normal,
+      inline: inline.normal
+    };
 
     if (this.options.pedantic) {
-      this.rules = block.pedantic;
+      rules.block = block.pedantic;
+      rules.inline = inline.pedantic;
     } else if (this.options.gfm) {
-      this.rules = block.gfm;
+      rules.block = block.gfm;
+      if (this.options.breaks) {
+        rules.inline = inline.breaks;
+      } else {
+        rules.inline = inline.gfm;
+      }
     }
+    this.tokenizer.rules = rules;
   }
 
   /**
-   * Expose Block Rules
+   * Expose Rules
    */
   static get rules() {
-    return block;
+    return {
+      block,
+      inline
+    };
   }
 
   /**
@@ -36,7 +90,7 @@ module.exports = class Lexer {
   static lex(src, options) {
     const lexer = new Lexer(options);
     return lexer.lex(src);
-  };
+  }
 
   /**
    * Preprocessing
@@ -46,357 +100,335 @@ module.exports = class Lexer {
       .replace(/\r\n|\r/g, '\n')
       .replace(/\t/g, '    ');
 
-    return this.token(src, true);
-  };
+    this.blockTokens(src, this.tokens, true);
+
+    this.inline(this.tokens);
+
+    return this.tokens;
+  }
 
   /**
    * Lexing
    */
-  token(src, top) {
+  blockTokens(src, tokens = [], top = true) {
     src = src.replace(/^ +$/gm, '');
-    let next,
-      loose,
-      cap,
-      bull,
-      b,
-      item,
-      listStart,
-      listItems,
-      t,
-      space,
-      i,
-      tag,
-      l,
-      isordered,
-      istask,
-      ischecked;
+    let token, i, l, lastToken;
 
     while (src) {
       // newline
-      if (cap = this.rules.newline.exec(src)) {
-        src = src.substring(cap[0].length);
-        if (cap[0].length > 1) {
-          this.tokens.push({
-            type: 'space'
-          });
+      if (token = this.tokenizer.space(src)) {
+        src = src.substring(token.raw.length);
+        if (token.type) {
+          tokens.push(token);
         }
+        continue;
       }
 
       // code
-      if (cap = this.rules.code.exec(src)) {
-        const lastToken = this.tokens[this.tokens.length - 1];
-        src = src.substring(cap[0].length);
-        // An indented code block cannot interrupt a paragraph.
-        if (lastToken && lastToken.type === 'paragraph') {
-          lastToken.text += '\n' + cap[0].trimRight();
+      if (token = this.tokenizer.code(src, tokens)) {
+        src = src.substring(token.raw.length);
+        if (token.type) {
+          tokens.push(token);
         } else {
-          cap = cap[0].replace(/^ {4}/gm, '');
-          this.tokens.push({
-            type: 'code',
-            codeBlockStyle: 'indented',
-            text: !this.options.pedantic
-              ? rtrim(cap, '\n')
-              : cap
-          });
+          lastToken = tokens[tokens.length - 1];
+          lastToken.raw += '\n' + token.raw;
+          lastToken.text += '\n' + token.text;
         }
         continue;
       }
 
       // fences
-      if (cap = this.rules.fences.exec(src)) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'code',
-          lang: cap[2] ? cap[2].trim() : cap[2],
-          text: cap[3] || ''
-        });
+      if (token = this.tokenizer.fences(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
       // heading
-      if (cap = this.rules.heading.exec(src)) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'heading',
-          depth: cap[1].length,
-          text: cap[2]
-        });
+      if (token = this.tokenizer.heading(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
       // table no leading pipe (gfm)
-      if (cap = this.rules.nptable.exec(src)) {
-        item = {
-          type: 'table',
-          header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
-          align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
-          cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : []
-        };
-
-        if (item.header.length === item.align.length) {
-          src = src.substring(cap[0].length);
-
-          for (i = 0; i < item.align.length; i++) {
-            if (/^ *-+: *$/.test(item.align[i])) {
-              item.align[i] = 'right';
-            } else if (/^ *:-+: *$/.test(item.align[i])) {
-              item.align[i] = 'center';
-            } else if (/^ *:-+ *$/.test(item.align[i])) {
-              item.align[i] = 'left';
-            } else {
-              item.align[i] = null;
-            }
-          }
-
-          for (i = 0; i < item.cells.length; i++) {
-            item.cells[i] = splitCells(item.cells[i], item.header.length);
-          }
-
-          this.tokens.push(item);
-
-          continue;
-        }
+      if (token = this.tokenizer.nptable(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
       }
 
       // hr
-      if (cap = this.rules.hr.exec(src)) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'hr'
-        });
+      if (token = this.tokenizer.hr(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
       // blockquote
-      if (cap = this.rules.blockquote.exec(src)) {
-        src = src.substring(cap[0].length);
-
-        this.tokens.push({
-          type: 'blockquote_start'
-        });
+      if (token = this.tokenizer.blockquote(src)) {
+        src = src.substring(token.raw.length);
+        token.tokens = this.blockTokens(token.text, [], top);
+        tokens.push(token);
+        continue;
+      }
 
-        cap = cap[0].replace(/^ *> ?/gm, '');
+      // list
+      if (token = this.tokenizer.list(src)) {
+        src = src.substring(token.raw.length);
+        l = token.items.length;
+        for (i = 0; i < l; i++) {
+          token.items[i].tokens = this.blockTokens(token.items[i].text, [], false);
+        }
+        tokens.push(token);
+        continue;
+      }
 
-        // Pass `top` to keep the current
-        // "toplevel" state. This is exactly
-        // how markdown.pl works.
-        this.token(cap, top);
+      // html
+      if (token = this.tokenizer.html(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
+      }
 
-        this.tokens.push({
-          type: 'blockquote_end'
-        });
+      // def
+      if (top && (token = this.tokenizer.def(src))) {
+        src = src.substring(token.raw.length);
+        if (!this.tokens.links[token.tag]) {
+          this.tokens.links[token.tag] = {
+            href: token.href,
+            title: token.title
+          };
+        }
+        continue;
+      }
 
+      // table (gfm)
+      if (token = this.tokenizer.table(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
-      // list
-      if (cap = this.rules.list.exec(src)) {
-        src = src.substring(cap[0].length);
-        bull = cap[2];
-        isordered = bull.length > 1;
-
-        listStart = {
-          type: 'list_start',
-          ordered: isordered,
-          start: isordered ? +bull : '',
-          loose: false
-        };
-
-        this.tokens.push(listStart);
-
-        // Get each top-level item.
-        cap = cap[0].match(this.rules.item);
-
-        listItems = [];
-        next = false;
-        l = cap.length;
-        i = 0;
-
-        for (; i < l; i++) {
-          item = cap[i];
-
-          // Remove the list item's bullet
-          // so it is seen as the next token.
-          space = item.length;
-          item = item.replace(/^ *([*+-]|\d+\.) */, '');
-
-          // Outdent whatever the
-          // list item contains. Hacky.
-          if (~item.indexOf('\n ')) {
-            space -= item.length;
-            item = !this.options.pedantic
-              ? item.replace(new RegExp('^ {1,' + space + '}', 'gm'), '')
-              : item.replace(/^ {1,4}/gm, '');
-          }
+      // lheading
+      if (token = this.tokenizer.lheading(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
+      }
 
-          // Determine whether the next list item belongs here.
-          // Backpedal if it does not belong in this list.
-          if (i !== l - 1) {
-            b = block.bullet.exec(cap[i + 1])[0];
-            if (bull.length > 1 ? b.length === 1
-              : (b.length > 1 || (this.options.smartLists && b !== bull))) {
-              src = cap.slice(i + 1).join('\n') + src;
-              i = l - 1;
-            }
-          }
+      // top-level paragraph
+      if (top && (token = this.tokenizer.paragraph(src))) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
+      }
 
-          // Determine whether item is loose or not.
-          // Use: /(^|\n)(?! )[^\n]+\n\n(?!\s*$)/
-          // for discount behavior.
-          loose = next || /\n\n(?!\s*$)/.test(item);
-          if (i !== l - 1) {
-            next = item.charAt(item.length - 1) === '\n';
-            if (!loose) loose = next;
-          }
+      // text
+      if (token = this.tokenizer.text(src, tokens)) {
+        src = src.substring(token.raw.length);
+        if (token.type) {
+          tokens.push(token);
+        } else {
+          lastToken = tokens[tokens.length - 1];
+          lastToken.raw += '\n' + token.raw;
+          lastToken.text += '\n' + token.text;
+        }
+        continue;
+      }
 
-          if (loose) {
-            listStart.loose = true;
-          }
+      if (src) {
+        const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0);
+        if (this.options.silent) {
+          console.error(errMsg);
+          break;
+        } else {
+          throw new Error(errMsg);
+        }
+      }
+    }
 
-          // Check for task list items
-          istask = /^\[[ xX]\] /.test(item);
-          ischecked = undefined;
-          if (istask) {
-            ischecked = item[1] !== ' ';
-            item = item.replace(/^\[[ xX]\] +/, '');
-          }
+    return tokens;
+  }
 
-          t = {
-            type: 'list_item_start',
-            task: istask,
-            checked: ischecked,
-            loose: loose
+  inline(tokens) {
+    let i,
+      j,
+      k,
+      l2,
+      row,
+      token;
+
+    const l = tokens.length;
+    for (i = 0; i < l; i++) {
+      token = tokens[i];
+      switch (token.type) {
+        case 'paragraph':
+        case 'text':
+        case 'heading': {
+          token.tokens = [];
+          this.inlineTokens(token.text, token.tokens);
+          break;
+        }
+        case 'table': {
+          token.tokens = {
+            header: [],
+            cells: []
           };
 
-          listItems.push(t);
-          this.tokens.push(t);
+          // header
+          l2 = token.header.length;
+          for (j = 0; j < l2; j++) {
+            token.tokens.header[j] = [];
+            this.inlineTokens(token.header[j], token.tokens.header[j]);
+          }
 
-          // Recurse.
-          this.token(item, false);
+          // cells
+          l2 = token.cells.length;
+          for (j = 0; j < l2; j++) {
+            row = token.cells[j];
+            token.tokens.cells[j] = [];
+            for (k = 0; k < row.length; k++) {
+              token.tokens.cells[j][k] = [];
+              this.inlineTokens(row[k], token.tokens.cells[j][k]);
+            }
+          }
 
-          this.tokens.push({
-            type: 'list_item_end'
-          });
+          break;
         }
-
-        if (listStart.loose) {
-          l = listItems.length;
-          i = 0;
-          for (; i < l; i++) {
-            listItems[i].loose = true;
+        case 'blockquote': {
+          this.inline(token.tokens);
+          break;
+        }
+        case 'list': {
+          l2 = token.items.length;
+          for (j = 0; j < l2; j++) {
+            this.inline(token.items[j].tokens);
           }
+          break;
+        }
+        default: {
+          // do nothing
         }
+      }
+    }
 
-        this.tokens.push({
-          type: 'list_end'
-        });
+    return tokens;
+  }
 
+  /**
+   * Lexing/Compiling
+   */
+  inlineTokens(src, tokens = [], inLink = false, inRawBlock = false) {
+    let token;
+
+    while (src) {
+      // escape
+      if (token = this.tokenizer.escape(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
-      // html
-      if (cap = this.rules.html.exec(src)) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: this.options.sanitize
-            ? 'paragraph'
-            : 'html',
-          pre: !this.options.sanitizer
-            && (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'),
-          text: this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]
-        });
+      // tag
+      if (token = this.tokenizer.tag(src, inLink, inRawBlock)) {
+        src = src.substring(token.raw.length);
+        inLink = token.inLink;
+        inRawBlock = token.inRawBlock;
+        tokens.push(token);
         continue;
       }
 
-      // def
-      if (top && (cap = this.rules.def.exec(src))) {
-        src = src.substring(cap[0].length);
-        if (cap[3]) cap[3] = cap[3].substring(1, cap[3].length - 1);
-        tag = cap[1].toLowerCase().replace(/\s+/g, ' ');
-        if (!this.tokens.links[tag]) {
-          this.tokens.links[tag] = {
-            href: cap[2],
-            title: cap[3]
-          };
+      // link
+      if (token = this.tokenizer.link(src)) {
+        src = src.substring(token.raw.length);
+        if (token.type === 'link') {
+          token.tokens = this.inlineTokens(token.text, [], true, inRawBlock);
         }
+        tokens.push(token);
         continue;
       }
 
-      // table (gfm)
-      if (cap = this.rules.table.exec(src)) {
-        item = {
-          type: 'table',
-          header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
-          align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
-          cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : []
-        };
-
-        if (item.header.length === item.align.length) {
-          src = src.substring(cap[0].length);
-
-          for (i = 0; i < item.align.length; i++) {
-            if (/^ *-+: *$/.test(item.align[i])) {
-              item.align[i] = 'right';
-            } else if (/^ *:-+: *$/.test(item.align[i])) {
-              item.align[i] = 'center';
-            } else if (/^ *:-+ *$/.test(item.align[i])) {
-              item.align[i] = 'left';
-            } else {
-              item.align[i] = null;
-            }
-          }
+      // reflink, nolink
+      if (token = this.tokenizer.reflink(src, this.tokens.links)) {
+        src = src.substring(token.raw.length);
+        if (token.type === 'link') {
+          token.tokens = this.inlineTokens(token.text, [], true, inRawBlock);
+        }
+        tokens.push(token);
+        continue;
+      }
 
-          for (i = 0; i < item.cells.length; i++) {
-            item.cells[i] = splitCells(
-              item.cells[i].replace(/^ *\| *| *\| *$/g, ''),
-              item.header.length);
-          }
+      // strong
+      if (token = this.tokenizer.strong(src)) {
+        src = src.substring(token.raw.length);
+        token.tokens = this.inlineTokens(token.text, [], inLink, inRawBlock);
+        tokens.push(token);
+        continue;
+      }
 
-          this.tokens.push(item);
+      // em
+      if (token = this.tokenizer.em(src)) {
+        src = src.substring(token.raw.length);
+        token.tokens = this.inlineTokens(token.text, [], inLink, inRawBlock);
+        tokens.push(token);
+        continue;
+      }
 
-          continue;
-        }
+      // code
+      if (token = this.tokenizer.codespan(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
       }
 
-      // lheading
-      if (cap = this.rules.lheading.exec(src)) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'heading',
-          depth: cap[2].charAt(0) === '=' ? 1 : 2,
-          text: cap[1]
-        });
+      // br
+      if (token = this.tokenizer.br(src)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
-      // top-level paragraph
-      if (top && (cap = this.rules.paragraph.exec(src))) {
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'paragraph',
-          text: cap[1].charAt(cap[1].length - 1) === '\n'
-            ? cap[1].slice(0, -1)
-            : cap[1]
-        });
+      // del (gfm)
+      if (token = this.tokenizer.del(src)) {
+        src = src.substring(token.raw.length);
+        token.tokens = this.inlineTokens(token.text, [], inLink, inRawBlock);
+        tokens.push(token);
+        continue;
+      }
+
+      // autolink
+      if (token = this.tokenizer.autolink(src, mangle)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
+        continue;
+      }
+
+      // url (gfm)
+      if (!inLink && (token = this.tokenizer.url(src, mangle))) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
       // text
-      if (cap = this.rules.text.exec(src)) {
-        // Top-level should never reach here.
-        src = src.substring(cap[0].length);
-        this.tokens.push({
-          type: 'text',
-          text: cap[0]
-        });
+      if (token = this.tokenizer.inlineText(src, inRawBlock, smartypants)) {
+        src = src.substring(token.raw.length);
+        tokens.push(token);
         continue;
       }
 
       if (src) {
-        throw new Error('Infinite loop on byte: ' + src.charCodeAt(0));
+        const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0);
+        if (this.options.silent) {
+          console.error(errMsg);
+          break;
+        } else {
+          throw new Error(errMsg);
+        }
       }
     }
 
-    return this.tokens;
-  };
+    return tokens;
+  }
 };