From c50197bab81d7105c9c790548821b61bcb97a62a Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 13 Apr 2016 16:50:38 -0700
Subject: Changed `process_emphasis` to get better results in corner cases.

This will need corresponding spec changes.

The change is this:  when considering matches between an interior
delimiter run (one that can open and can close) and another delimiter
run, we require that the sum of the lengths of the two delimiter
runs mod 3 is not 0.

Thus, for example, in

    *a**b*
    1 23 4

delimiter 1 cannot match 2, since the sum of the lengths of
the first delimiter run (1) and the second (1,2) == 3.
Thus we get `<em>a**b</em>` instead of `<em>a</em><em>b</em>`.

This gives better behavior on things like

    *a**b**c*

which previously got parsed as

    <em>a</em><em>b</em><em>c</em>

and now would be parsed as

    <em>a<strong>b</strong>c</em>

With this change we get four spec test failures, but in each
case the output seems more "intuitive":

```
Example 386 (lines 6490-6494) Emphasis and strong emphasis
*foo**bar**baz*

--- expected HTML
+++ actual HTML
@@ -1 +1 @@
-<p><em>foo</em><em>bar</em><em>baz</em></p>
+<p><em>foo<strong>bar</strong>baz</em></p>

Example 389 (lines 6518-6522) Emphasis and strong emphasis
*foo**bar***

--- expected HTML
+++ actual HTML
@@ -1 +1 @@
-<p><em>foo</em><em>bar</em>**</p>
+<p><em>foo<strong>bar</strong></em></p>

Example 401 (lines 6620-6624) Emphasis and strong emphasis
**foo*bar*baz**

--- expected HTML
+++ actual HTML
@@ -1 +1 @@
-<p><em><em>foo</em>bar</em>baz**</p>
+<p><strong>foo<em>bar</em>baz</strong></p>

Example 442 (lines 6944-6948) Emphasis and strong emphasis
**foo*bar**

--- expected HTML
+++ actual HTML
@@ -1 +1 @@
-<p><em><em>foo</em>bar</em>*</p>
+<p><strong>foo*bar</strong></p>
```
---
 src/inlines.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

(limited to 'src')

diff --git a/src/inlines.c b/src/inlines.c
index 41c7140..6ed0661 100644
--- a/src/inlines.c
+++ b/src/inlines.c
@@ -483,6 +483,7 @@ static void process_emphasis(subject *subj, delimiter *stack_bottom) {
   delimiter *opener;
   delimiter *old_closer;
   bool opener_found;
+  bool odd_match;
   delimiter *openers_bottom[128];
 
   // initialize openers_bottom:
@@ -502,9 +503,18 @@ static void process_emphasis(subject *subj, delimiter *stack_bottom) {
       // Now look backwards for first matching opener:
       opener = closer->previous;
       opener_found = false;
+      odd_match = false;
       while (opener != NULL && opener != stack_bottom &&
              opener != openers_bottom[closer->delim_char]) {
-        if (opener->delim_char == closer->delim_char && opener->can_open) {
+	// interior closer of size 2 can't match opener of size 1
+	// or of size 1 can't match 2
+	odd_match = (closer->can_open || opener->can_close) &&
+		opener->inl_text->as.literal.len !=
+		  closer->inl_text->as.literal.len &&
+		((opener->inl_text->as.literal.len +
+		    closer->inl_text->as.literal.len) % 3 == 0);
+        if (opener->delim_char == closer->delim_char && opener->can_open &&
+			!odd_match) {
           opener_found = true;
           break;
         }
@@ -534,8 +544,12 @@ static void process_emphasis(subject *subj, delimiter *stack_bottom) {
         }
         closer = closer->next;
       }
-      if (!opener_found) {
-        // set lower bound for future searches for openers:
+      if (!opener_found && !odd_match) {
+        // set lower bound for future searches for openers
+	// (we don't do this with 'odd_match' set because
+	// a ** that didn't match an earlier * might turn into
+	// an opener, and the * might be matched by something
+	// else.
         openers_bottom[old_closer->delim_char] = old_closer->previous;
         if (!old_closer->can_open) {
           // we can remove a closer that can't be an
-- 
cgit v1.2.3