Move abbreviations from core to a block chain

lib/parser_block.js

@@ -15,6 +15,7 @@ var _rules = [
   [ 'blockquote', require('./rules_block/blockquote'), [ 'paragraph', 'blockquote', 'list' ] ],
   [ 'hr',         require('./rules_block/hr'),         [ 'paragraph', 'blockquote', 'list' ] ],
   [ 'list',       require('./rules_block/list'),       [ 'paragraph', 'blockquote' ] ],
+  [ 'abbr',       require('./rules_block/abbr'),       [ 'paragraph' ] ],
   [ 'footnote',   require('./rules_block/footnote'),   [ 'paragraph' ] ],
   [ 'heading',    require('./rules_block/heading'),    [ 'paragraph', 'blockquote' ] ],
   [ 'lheading',   require('./rules_block/lheading') ],

lib/parser_core.js

@@ -12,7 +12,6 @@ var Ruler  = require('./ruler');
 
 var _rules = [
   [ 'block',          require('./rules_core/block')          ],
-  [ 'abbr',           require('./rules_core/abbr')           ],
   [ 'references',     require('./rules_core/references')     ],
   [ 'inline',         require('./rules_core/inline')         ],
   [ 'footnote_tail',  require('./rules_core/footnote_tail')  ],

lib/rules_block/abbr.js

@@ -0,0 +1,48 @@
+// Parse abbreviation definitions, i.e. `*[abbr]: description`
+//
+
+'use strict';
+
+
+module.exports = function parseAbbr(state, startLine, endLine, silent) {
+  var label, title, ch, labelStart, labelEnd,
+      pos = state.bMarks[startLine] + state.tShift[startLine],
+      max = state.eMarks[startLine];
+
+  if (pos + 2 >= max) { return false; }
+
+  if (state.src.charCodeAt(pos++) !== 0x2A/* * */) { return false; }
+  if (state.src.charCodeAt(pos++) !== 0x5B/* [ */) { return false; }
+
+  labelStart = pos;
+
+  for (; pos < max; pos++) {
+    ch = state.src.charCodeAt(pos);
+    if (ch === 0x5B /* [ */) {
+      return false;
+    } else if (ch === 0x5D /* ] */) {
+      labelEnd = pos;
+      break;
+    } else if (ch === 0x5C /* \ */) {
+      pos++;
+    }
+  }
+
+  if (labelEnd < 0 || state.src.charCodeAt(labelEnd + 1) !== 0x3A/* : */) {
+    return false;
+  }
+
+  if (silent) { return true; }
+
+  label = state.src.slice(labelStart, labelEnd).replace(/\\(.)/g, '$1');
+  title = state.src.slice(labelEnd + 2, max).trim();
+  if (title.length === 0) { return false; }
+  if (!state.env.abbreviations) { state.env.abbreviations = {}; }
+  // prepend ':' to avoid conflict with Object.prototype members
+  if (typeof state.env.abbreviations[':' + label] === 'undefined') {
+    state.env.abbreviations[':' + label] = title;
+  }
+
+  state.line = startLine + 1;
+  return true;
+};

lib/rules_core/abbr.js

@@ -1,75 +0,0 @@
-// Parse abbreviation definitions, i.e. `*[abbr]: description`
-//
-
-'use strict';
-
-
-function parseAbbr(str, parserInline, options, env) {
-  var pos, label, title, ch,
-      max = str.length,
-      labelEnd = -1;
-
-  if (str.charCodeAt(0) !== 0x2A/* * */) { return -1; }
-  if (str.charCodeAt(1) !== 0x5B/* [ */) { return -1; }
-
-  if (str.indexOf(']:') === -1) { return -1; }
-
-  for (pos = 2; pos < max; pos++) {
-    ch = str.charCodeAt(pos);
-    if (ch === 0x5B /* [ */) {
-      return -1;
-    } else if (ch === 0x5D /* ] */) {
-      labelEnd = pos;
-      break;
-    } else if (ch === 0x5C /* \ */) {
-      pos++;
-    }
-  }
-
-  if (labelEnd < 0 || str.charCodeAt(labelEnd + 1) !== 0x3A/* : */) { return -1; }
-
-  // abbr title is always one line, so looking for ending "\n" here
-  for (pos = labelEnd + 2; pos < max; pos++) {
-    if (str.charCodeAt(pos) === 0x0A) { break; }
-  }
-
-  label = str.slice(2, labelEnd).replace(/\\(.)/g, '$1');
-  title = str.slice(labelEnd + 2, pos).trim();
-  if (title.length === 0) { return -1; }
-  if (!env.abbreviations) { env.abbreviations = {}; }
-  // prepend ':' to avoid conflict with Object.prototype members
-  if (typeof env.abbreviations[':' + label] === 'undefined') {
-    env.abbreviations[':' + label] = title;
-  }
-
-  return pos;
-}
-
-module.exports = function abbr(state) {
-  var tokens = state.tokens, i, l, content, pos;
-
-  if (state.inlineMode) {
-    return;
-  }
-
-  // Parse inlines
-  for (i = 1, l = tokens.length - 1; i < l; i++) {
-    if (tokens[i - 1].type === 'paragraph_open' &&
-        tokens[i].type === 'inline' &&
-        tokens[i + 1].type === 'paragraph_close') {
-
-      content = tokens[i].content;
-      while (content.length) {
-        pos = parseAbbr(content, state.inline, state.options, state.env);
-        if (pos < 0) { break; }
-        content = content.slice(pos).trim();
-      }
-
-      tokens[i].content = content;
-      if (!content.length) {
-        tokens[i - 1].tight = true;
-        tokens[i + 1].tight = true;
-      }
-    }
-  }
-};

test/fixtures/markdown-it/abbr.txt

@@ -11,18 +11,6 @@ is maintained by the W3C.
 is maintained by the <abbr title="World Wide Web Consortium">W3C</abbr>.</p>
 .
 
-They can be multiline (see pandoc implementation). Not sure about newlines, but we should at least skip those definitions:
-
-.
-*[
-foo
-bar
-]: desc
-foo
-.
-<p>foo</p>
-.
-
 They can contain arbitrary markup (see pandoc implementation):
 
 .