Re-write of eqn(7) parser and MathML output.

This adds parser-level support for the grammar described by the eqn
second-edition technical paper, "Typesetting Mathematics — User's Guide"
(Kernighan, Cherry).
The reason for this re-write is the grouping rules, which were not
possible given the existing implementation.
The re-write has also considerably simplified the HTML (and, if it ever
is completed, terminal) front-end.

1 files changed, 112 insertions, 145 deletions

diff --git a/eqn_html.c b/eqn_html.c
index f2e7f79d..73828684 100644
--- a/eqn_html.c
+++ b/eqn_html.c
@@ -1,4 +1,4 @@
-/*	$Id: eqn_html.c,v 1.7 2014/09/28 20:14:20 kristaps Exp $ */
+/*	$Id: eqn_html.c,v 1.8 2014/10/10 08:44:24 kristaps Exp $ */
 /*
  * Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  *
@@ -27,90 +27,64 @@
 #include "out.h"
 #include "html.h"
 
-static	const enum htmltag fontmap[EQNFONT__MAX] = {
-	TAG_SPAN, /* EQNFONT_NONE */
-	TAG_SPAN, /* EQNFONT_ROMAN */
-	TAG_B, /* EQNFONT_BOLD */
-	TAG_B, /* EQNFONT_FAT */
-	TAG_I /* EQNFONT_ITALIC */
-};
-
-static const struct eqn_box *
-	eqn_box(struct html *, const struct eqn_box *, int);
-
-
-void
-print_eqn(struct html *p, const struct eqn *ep)
+static void
+eqn_box(struct html *p, const struct eqn_box *bp)
 {
-	struct htmlpair	 tag;
-	struct tag	*t;
-
-	PAIR_CLASS_INIT(&tag, "eqn");
-	t = print_otag(p, TAG_MATH, 1, &tag);
-
-	p->flags |= HTML_NONOSPACE;
-	eqn_box(p, ep->root, 1);
-	p->flags &= ~HTML_NONOSPACE;
-
-	print_tagq(p, t);
-}
-
-/*
- * This function is fairly brittle.
- * This is because the eqn syntax doesn't play so nicely with recusive
- * formats, e.g.,
- *     foo sub bar sub baz
- * ...needs to resolve into
- *     <msub> foo <msub> bar, baz </msub> </msub>
- * In other words, we need to embed some recursive work.
- * FIXME: this does NOT handle right-left associativity or precedence!
- */
-static const struct eqn_box *
-eqn_box(struct html *p, const struct eqn_box *bp, int next)
-{
-	struct tag	*post, *pilet, *tmp;
+	struct tag	*post, *row, *cell, *t;
 	struct htmlpair	 tag[2];
-	int		 skiptwo;
+	const struct eqn_box *child, *parent;
+	size_t		 i, j, rows;
 
 	if (NULL == bp)
-		return(NULL);
-
-	post = pilet = NULL;
-	skiptwo = 0;
+		return;
 
-	/*
-	 * If we're a "row" under a pile, then open up the piling
-	 * context here.
-	 * We do this first because the pile surrounds the content of
-	 * the contained expression.
-	 */
-	if (NULL != bp->parent && bp->parent->pile != EQNPILE_NONE) {
-		pilet = print_otag(p, TAG_MTR, 0, NULL);
-		print_otag(p, TAG_MTD, 0, NULL);
-	}
-	if (NULL != bp->parent && bp->parent->type == EQN_MATRIX) {
-		pilet = print_otag(p, TAG_MTABLE, 0, NULL);
-		print_otag(p, TAG_MTR, 0, NULL);
-		print_otag(p, TAG_MTD, 0, NULL);
-	}
+	post = NULL;
 
 	/*
-	 * If we're establishing a pile, start the table mode now.
-	 * If we've already in a pile row, then don't override "pilet",
-	 * because we'll be closed out anyway.
+	 * Special handling for a matrix, which is presented to us in
+	 * column order, but must be printed in row-order.
 	 */
-	if (bp->pile != EQNPILE_NONE) {
-		tmp = print_otag(p, TAG_MTABLE, 0, NULL);
-		pilet = (NULL == pilet) ? tmp : pilet;
+	if (EQN_MATRIX == bp->type) {
+		if (NULL == bp->first)
+			goto out;
+		assert(EQN_LIST == bp->first->type);
+		if (NULL == (parent = bp->first->first))
+			goto out;
+		assert(EQN_PILE == parent->type);
+		/* Estimate the number of rows, first. */
+		if (NULL == (child = parent->first))
+			goto out;
+		for (rows = 0; NULL != child; rows++) 
+			child = child->next;
+		/* Print row-by-row. */
+		post = print_otag(p, TAG_MTABLE, 0, NULL);
+		for (i = 0; i < rows; i++) {
+			parent = bp->first->first;
+			row = print_otag(p, TAG_MTR, 0, NULL);
+			while (NULL != parent) {
+				child = parent->first;
+				for (j = 0; j < i; j++) {
+					if (NULL == child)
+						break;
+					child = child->next;
+				}
+				cell = print_otag
+					(p, TAG_MTD, 0, NULL);
+				/* 
+				 * If we have no data for this
+				 * particular cell, then print a
+				 * placeholder and continue--don't puke.
+				 */
+				if (NULL != child) 
+					eqn_box(p, child->first);
+				print_tagq(p, cell);
+				parent = parent->next;
+			}
+			print_tagq(p, row);
+		}
+		goto out;
 	}
 
-	/*
-	 * Positioning.
-	 * This is the most complicated part, and actually doesn't quite
-	 * work (FIXME) because it doesn't account for associativity.
-	 * Setting "post" will mean that we're only going to process a
-	 * single or double following expression.
-	 */
 	switch (bp->pos) {
 	case (EQNPOS_TO):
 		post = print_otag(p, TAG_MOVER, 0, NULL);
@@ -129,93 +103,86 @@ eqn_box(struct html *p, const struct eqn_box *bp, int next)
 		break;
 	case (EQNPOS_FROMTO):
 		post = print_otag(p, TAG_MUNDEROVER, 0, NULL);
-		skiptwo = 1;
 		break;
 	case (EQNPOS_SUBSUP):
 		post = print_otag(p, TAG_MSUBSUP, 0, NULL);
-		skiptwo = 1;
+		break;
+	case (EQNPOS_SQRT):
+		post = print_otag(p, TAG_MSQRT, 0, NULL);
 		break;
 	default:
 		break;
 	}
 
-	/*t = EQNFONT_NONE == bp->font ? NULL :
-	    print_otag(p, fontmap[(int)bp->font], 0, NULL);*/
+	if (bp->top || bp->bottom) {
+		assert(NULL == post);
+		if (bp->top && NULL == bp->bottom)
+			post = print_otag(p, TAG_MOVER, 0, NULL);
+		else if (bp->top && bp->bottom)
+			post = print_otag(p, TAG_MUNDEROVER, 0, NULL);
+		else if (bp->bottom)
+			post = print_otag(p, TAG_MUNDER, 0, NULL);
+	}
+
+	if (EQN_PILE == bp->type) {
+		assert(NULL == post);
+		post = print_otag(p, TAG_MTABLE, 0, NULL);
+	} else if (bp->parent && EQN_PILE == bp->parent->type) {
+		assert(NULL == post);
+		post = print_otag(p, TAG_MTR, 0, NULL);
+		print_otag(p, TAG_MTD, 0, NULL);
+	}
 
 	if (NULL != bp->text) {
-		assert(NULL == bp->first);
-		/*
-		 * We have text.
-		 * This can be a number, a function, a variable, or
-		 * pretty much anything else.
-		 * First, check for some known functions.
-		 * If we're going to create a structural node (e.g.,
-		 * sqrt), then set the "post" variable only if it's not
-		 * already set.
-		 */
-		if (0 == strcmp(bp->text, "sqrt")) {
-			tmp = print_otag(p, TAG_MSQRT, 0, NULL);
-			post = (NULL == post) ? tmp : post;
-		} else if (0 == strcmp(bp->text, "+") ||
-			   0 == strcmp(bp->text, "-") ||
-			   0 == strcmp(bp->text, "=") ||
-			   0 == strcmp(bp->text, "(") ||
-			   0 == strcmp(bp->text, ")") ||
-			   0 == strcmp(bp->text, "/")) {
-			tmp = print_otag(p, TAG_MO, 0, NULL);
-			print_text(p, bp->text);
-			print_tagq(p, tmp);
-		} else {
-			tmp = print_otag(p, TAG_MI, 0, NULL);
-			print_text(p, bp->text);
-			print_tagq(p, tmp);
-		}
-	} else if (NULL != bp->first) {
-		assert(NULL == bp->text);
-		/* 
-		 * If we're a "fenced" component (i.e., having
-		 * brackets), then process those brackets now.
-		 * Otherwise, introduce a dummy row (if we're not
-		 * already in a table context).
-		 */
-		tmp = NULL;
+		assert(NULL == post);
+		post = print_otag(p, TAG_MI, 0, NULL);
+		print_text(p, bp->text);
+	} else if (NULL == post) { 
 		if (NULL != bp->left || NULL != bp->right) {
 			PAIR_INIT(&tag[0], ATTR_OPEN,
-				NULL != bp->left ? bp->left : "");
+				NULL == bp->left ? "" : bp->left);
 			PAIR_INIT(&tag[1], ATTR_CLOSE,
-				NULL != bp->right ? bp->right : "");
-			tmp = print_otag(p, TAG_MFENCED, 2, tag);
+				NULL == bp->right ? "" : bp->right);
+			post = print_otag(p, TAG_MFENCED, 2, tag);
+		} 
+		if (NULL == post)
+			post = print_otag(p, TAG_MROW, 0, NULL);
+		else
 			print_otag(p, TAG_MROW, 0, NULL);
-		} else if (NULL == pilet)
-			tmp = print_otag(p, TAG_MROW, 0, NULL);
-		eqn_box(p, bp->first, 1);
-		if (NULL != tmp)
-			print_tagq(p, tmp);
 	}
 
-	/*
-	 * If a positional context, invoke the "next" context.
-	 * This is recursive and will return the end of the recursive
-	 * chain of "next" contexts.
-	 */
-	if (NULL != post) {
-		bp = eqn_box(p, bp->next, 0);
-		if (skiptwo)
-			bp = eqn_box(p, bp->next, 0);
-		print_tagq(p, post);
+	eqn_box(p, bp->first);
+
+out:
+	if (NULL != bp->bottom) {
+		t = print_otag(p, TAG_MO, 0, NULL);
+		print_text(p, bp->bottom);
+		print_tagq(p, t);
+	} 
+	if (NULL != bp->top) {
+		t = print_otag(p, TAG_MO, 0, NULL);
+		print_text(p, bp->top);
+		print_tagq(p, t);
 	}
 
-	/* 
-	 * If we're being piled (either directly, in the table, or
-	 * indirectly in a table row), then close that out.
-	 */
-	if (NULL != pilet)
-		print_tagq(p, pilet);
+	if (NULL != post)
+		print_tagq(p, post);
 
-	/*
-	 * If we're normally processing, then grab the next node.
-	 * If we're in a recursive context, then don't seek to the next
-	 * node; further recursion has already been handled.
-	 */
-	return(next ? eqn_box(p, bp->next, 1) : bp);
+	eqn_box(p, bp->next);
+}
+
+void
+print_eqn(struct html *p, const struct eqn *ep)
+{
+	struct htmlpair	 tag;
+	struct tag	*t;
+
+	PAIR_CLASS_INIT(&tag, "eqn");
+	t = print_otag(p, TAG_MATH, 1, &tag);
+
+	p->flags |= HTML_NONOSPACE;
+	eqn_box(p, ep->root);
+	p->flags &= ~HTML_NONOSPACE;
+
+	print_tagq(p, t);
 }