Consistently treat character escape sequences as operators,

not as letters, even if their names contain letters.

This is certainly not perfect, but code to recognize that \(*a is
not an operator but a letter would need a huge table, or Unicode
character property support, which won't happen at this time.

diff --git a/eqn_html.c b/eqn_html.c
index e7393a96aa935c2e17f4318d74dce9ded7c2d0ee..2d9eeb8a3afbc143b0101c5fda61ccfde8992be2 100644 (file)
--- a/eqn_html.c
+++ b/eqn_html.c
@@ -1,4 +1,4 @@
-/*     $Id: eqn_html.c,v 1.13 2017/06/23 02:32:12 schwarze Exp $ */
+/*     $Id: eqn_html.c,v 1.14 2017/06/23 23:00:01 schwarze Exp $ */

 /*
  * Copyright (c) 2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2017 Ingo Schwarze <schwarze@openbsd.org>
 /*
  * Copyright (c) 2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2017 Ingo Schwarze <schwarze@openbsd.org>


@@ -34,7 +34,7 @@ eqn_box(struct html *p, const struct eqn_box *bp)
 {
        struct tag      *post, *row, *cell, *t;
        const struct eqn_box *child, *parent;
 {
        struct tag      *post, *row, *cell, *t;
        const struct eqn_box *child, *parent;

-       const unsigned char *cp;
+       const char      *cp;

        size_t           i, j, rows;
        enum htmltag     tag;
        enum eqn_fontt   font;
        size_t           i, j, rows;
        enum htmltag     tag;
        enum eqn_fontt   font;


@@ -143,22 +143,28 @@ eqn_box(struct html *p, const struct eqn_box *bp)
        if (bp->text != NULL) {
                assert(post == NULL);
                tag = TAG_MI;
        if (bp->text != NULL) {
                assert(post == NULL);
                tag = TAG_MI;

-               cp = (unsigned char *)bp->text;
-               if (isdigit(cp[0]) || (cp[0] == '.' && isdigit(cp[1]))) {
+               cp = bp->text;
+               if (isdigit((unsigned char)cp[0]) ||
+                   (cp[0] == '.' && isdigit((unsigned char)cp[1]))) {

                        tag = TAG_MN;
                        while (*++cp != '\0') {
                        tag = TAG_MN;
                        while (*++cp != '\0') {

-                               if (*cp != '.' && !isdigit(*cp)) {
+                               if (*cp != '.' &&
+                                   isdigit((unsigned char)*cp) == 0) {

                                        tag = TAG_MI;
                                        break;
                                }
                        }
                                        tag = TAG_MI;
                                        break;
                                }
                        }

-               } else if (*cp != '\0' && isalpha(*cp) == 0) {
+               } else if (*cp != '\0' && isalpha((unsigned char)*cp) == 0) {

                        tag = TAG_MO;
                        tag = TAG_MO;

-                       while (*++cp != '\0') {
-                               if (isalnum(*cp)) {
+                       while (*cp != '\0') {
+                               if (cp[0] == '\\' && cp[1] != '\0') {
+                                       cp++;
+                                       mandoc_escape(&cp, NULL, NULL);
+                               } else if (isalnum((unsigned char)*cp)) {

                                        tag = TAG_MI;
                                        break;
                                        tag = TAG_MI;
                                        break;

-                               }
+                               } else
+                                       cp++;

                        }
                }
                font = bp->font;
                        }
                }
                font = bp->font;