Replace markdown-renderer with annotater

Handle blocks for now

3 files changed, 98 insertions, 14 deletions

diff --git a/packages/gitbook-markdown/lib/annotate.js b/packages/gitbook-markdown/lib/annotate.js
new file mode 100644
index 0000000..dab3d0e
--- /dev/null
+++ b/packages/gitbook-markdown/lib/annotate.js
@@ -0,0 +1,80 @@
+// Pulled from "kramed.Lexer.rules.tables"
+var rules = { newline: /^\n+/,
+    code: /^( {4}[^\n]+\n*)+/,
+    fences: /^ *(`{3,}|~{3,}) *(\S+)? *\n([\s\S]+?)\s*\1 *(?:\n+|$)/,
+    hr: /^( *[-*_]){3,} *(?:\n+|$)/,
+    heading: /^ *(#{1,6}) *([^\n]+?) *#* *(?:\n+|$)/,
+    nptable: /^ *(\S.*\|.*)\n *([-:]+ *\|[-| :]*)\n((?:.*\|.*(?:\n|$))*)\n*/,
+    lheading: /^([^\n]+)\n *(=|-){2,} *(?:\n+|$)/,
+    blockquote: /^( *>[^\n]+(\n(?! *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$))[^\n]+)*\n*)+/,
+    list: /^( *)((?:[*+-]|\d+\.)) [\s\S]+?(?:\n+(?=\1?(?:[-*_] *){3,}(?:\n+|$))|\n+(?= *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$))|\n{2,}(?! )(?!\1(?:[*+-]|\d+\.) )\n*|\s*$)/,
+    html: /^ *(?:<!--[\s\S]*?--> *(?:\n|\s*$)|<((?!(?:a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)\b)\w+(?!:\/|[^\w\s@]*@)\b)[\s\S]+?<\/\1> *(?:\n{2,}|\s*$)|<(?!(?:a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)\b)\w+(?!:\/|[^\w\s@]*@)\b(?:"[^"]*"|'[^']*'|[^'">])*?> *(?:\n{2,}|\s*$))/,
+    def: /^ *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$)/,
+    footnote: /^\[\^([^\]]+)\]: ([^\n]+)/,
+    table: /^ *\|(.+)\n *\|( *[-:]+[-| :]*)\n((?: *\|.*(?:\n|$))*)\n*/,
+    paragraph: /^((?:[^\n]+\n?(?! *(`{3,}|~{3,}) *(\S+)? *\n([\s\S]+?)\s*\2 *(?:\n+|$)|( *)((?:[*+-]|\d+\.)) [\s\S]+?(?:\n+(?=\3?(?:[-*_] *){3,}(?:\n+|$))|\n+(?= *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$))|\n{2,}(?! )(?!\1(?:[*+-]|\d+\.) )\n*|\s*$)|( *[-*_]){3,} *(?:\n+|$)| *(#{1,6}) *([^\n]+?) *#* *(?:\n+|$)|([^\n]+)\n *(=|-){2,} *(?:\n+|$)|( *>[^\n]+(\n(?! *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$))[^\n]+)*\n*)+|<(?!(?:a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)\b)\w+(?!:\/|[^\w\s@]*@)\b| *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +["(]([^\n]+)[")])? *(?:\n+|$)| *(\${2,}) *([\s\S]+?)\s*\1 *(?:\n+|$)))+)\n*/,
+    text: /^[^\n]+/,
+    math: /^ *(\${2,}) *([\s\S]+?)\s*\1 *(?:\n+|$)/,
+    // These are lower level, ignore them
+    //bullet: /(?:[*+-]|\d+\.)/,
+    //item: /^( *)((?:[*+-]|\d+\.)) [^\n]*(?:\n(?!\1(?:[*+-]|\d+\.) )[^\n]*)*/gm,
+    //_tag: '(?!(?:a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)\\b)\\w+(?!:/|[^\\w\\s@]*@)\\b'
+};
+
+// List of all the regexes we want to run
+var ruleTypes = [
+'newline', 'code', 'fences', 'footnote', 'math', 'heading',
+'nptable', 'lheading', 'hr', 'blockquote', 'list',
+'html', 'def', 'table', 'paragraph', 'text',
+];
+
+// Mapping if rule type is different from token type
+var ruleMap = {
+    'nptable': 'table',
+    'lheading': 'heading',
+    'newline': 'space',
+}
+
+function annotate(src) {
+    var tokens = [];
+
+    while(src) {
+        // Pick rule
+        var rule = ruleTypes.filter(function(ruleName, idx) {
+            var regex = rules[ruleName];
+            return regex.exec(src);
+        })[0];
+
+        // No matching rules
+        if(!rule) {
+            throw new Error('No rule found for: ' + src);
+        }
+
+        // Use rule to extract block
+        var ruleRegex = rules[rule];
+        var block = ruleRegex.exec(src);
+
+        // Get rule type
+        var type = ruleMap[rule] || rule;
+
+        // Get raw text
+        var raw = block[0];
+
+        // Break out here to avoid infinite loops
+        if(raw.length === 0) {
+            break;
+        }
+
+        tokens.push({
+            type: ruleMap[rule] || rule,
+            raw: raw,
+        });
+
+        // Update source
+        src = src.substring(raw.length);
+    }
+
+    return tokens
+}
+
+module.exports = annotate;
diff --git a/packages/gitbook-markdown/lib/page.js b/packages/gitbook-markdown/lib/page.js
index 5876beb..d98bb72 100644
--- a/packages/gitbook-markdown/lib/page.js
+++ b/packages/gitbook-markdown/lib/page.js
@@ -3,27 +3,32 @@ var kramed = require('kramed');
 var hljs = require('highlight.js');
 
 var lnormalize = require('./utils/lang').normalize;
-var mdRenderer = require('kramed-markdown-renderer');
+var annotate = require('./annotate');
 
 var RAW_START = "{% raw %}";
 var RAW_END = "{% endraw %}";
 
-function preparePage(src) {
-    var renderer = mdRenderer();
+function escape(str) {
+    return RAW_START + str + RAW_END;
+}
 
-    var escape = function(func, code, lang, escaped) {
-        return RAW_START+func(code, lang, escaped)+RAW_END;
-    };
+// Combines annotated nodes
+function combine(nodes) {
+    return _.pluck(nodes, 'raw').join('');
+}
 
-    renderer.code = _.wrap(renderer.code, escape);
-    renderer.codespan = _.wrap(renderer.codespan, escape);
+function preparePage(src) {
+    var lexed = annotate(src);
 
-    var options = _.extend({}, kramed.defaults, {
-        renderer: renderer,
-        escape: false
-    });
+    // Escape code blocks
+    var escaped = lexed.map(function(el) {
+        if(el.type == 'code') {
+            el.raw = escape(el.raw);
+        }
+        return el;
+    })
 
-    return kramed(src, options);
+    return combine(escaped);
 }
 
 function parsePage(src) {
diff --git a/packages/gitbook-markdown/package.json b/packages/gitbook-markdown/package.json
index 4e8b919..7ae1989 100644
--- a/packages/gitbook-markdown/package.json
+++ b/packages/gitbook-markdown/package.json
@@ -8,7 +8,6 @@
         "lodash": "^3.2.0",
         "kramed": "0.4.6",
         "kramed-text-renderer": "0.2.1",
-        "kramed-markdown-renderer": "0.1.2",
         "highlight.js": "8.4.0"
     },
     "devDependencies": {