Split tagging into a validation part including prioritization

in tag.{h,c} and {mdoc,man}_validate.c
and into a formatting part including command line argument checking
in term_tag.{h,c}, html.c, and {mdoc|man}_{term|html}.c.

Immediate functional benefits include:
* Improved prioritization of automatic tags for .Em and .Sy.
* Avoiding bogus automatic tags when .Em, .Fn, or .Sy are explicitly tagged.
* Explicit tagging of .Er and .Fl now works in HTML output.
* Automatic tagging of .IP and .TP now works in HTML output.
But mainly, this patch provides clean earth to build further improvements on.

Technical changes:
* Main program: Write a tag file for ASCII and UTF-8 output only.
* All formatters: There is no more need to delay writing the tags.
* mdoc(7)+man(7) formatters: No more need for elaborate syntax tree inspection.
* HTML formatter: If available, use the "string" attribute as the tag.
* HTML formatter: New function to write permalinks, to reduce code duplication.

Style cleanup in the vicinity while here:
* mdoc(7) terminal formatter: To set up bold font for children,
defer to termp_bold_pre() rather than calling term_fontpush() manually.
* mdoc(7) terminal formatter: Garbage collect some duplicate functions.
* mdoc(7) HTML formatter: Unify <code> handling, delete redundant functions.
* Where possible, use switch statements rather than if cascades.
* Get rid of some more Yoda notation.

The necessity for such changes was first discussed with kn@, but i didn't
bother him with a request to review the resulting -673/+782 line patch.

1 files changed, 19 insertions, 19 deletions

diff --git a/usr.bin/mandoc/main.c b/usr.bin/mandoc/main.c
index 5c72f60ce7b..8931df51ea1 100644
--- a/usr.bin/mandoc/main.c
+++ b/usr.bin/mandoc/main.c
@@ -1,7 +1,7 @@
-/*	$OpenBSD: main.c,v 1.247 2020/02/24 21:15:05 schwarze Exp $ */
+/* $OpenBSD: main.c,v 1.248 2020/03/13 00:31:04 schwarze Exp $ */
 /*
- * Copyright (c) 2008-2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2012, 2014-2020 Ingo Schwarze <schwarze@openbsd.org>
+ * Copyright (c) 2008-2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010 Joerg Sonnenberger <joerg@netbsd.org>
  *
  * Permission to use, copy, modify, and distribute this software for any
@@ -15,8 +15,9 @@
  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ *
+ * Main program for mandoc(1), man(1), apropos(1), whatis(1), and help(1).
  */
-
 #include <sys/types.h>
 #include <sys/ioctl.h>
 #include <sys/param.h>	/* MACHINE */
@@ -46,7 +47,7 @@
 #include "mdoc.h"
 #include "man.h"
 #include "mandoc_parse.h"
-#include "tag.h"
+#include "term_tag.h"
 #include "main.h"
 #include "manconf.h"
 #include "mansearch.h"
@@ -577,7 +578,6 @@ main(int argc, char *argv[])
 	 * readable: Maybe it won't be needed after all.
 	 */
 	startdir = open(".", O_RDONLY | O_DIRECTORY);
-
 	for (i = 0; i < ressz; i++) {
 		process_onefile(mp, res + i, startdir, &outst, &conf);
 		if (outst.wstop && mandoc_msg_getrc() != MANDOCLEVEL_OK)
@@ -587,7 +587,6 @@ main(int argc, char *argv[])
 		(void)fchdir(startdir);
 		close(startdir);
 	}
-
 	if (outst.outdata != NULL) {
 		switch (outst.outtype) {
 		case OUTT_HTML:
@@ -596,6 +595,7 @@ main(int argc, char *argv[])
 		case OUTT_UTF8:
 		case OUTT_LOCALE:
 		case OUTT_ASCII:
+			term_tag_finish();
 			ascii_free(outst.outdata);
 			break;
 		case OUTT_PDF:
@@ -617,9 +617,8 @@ out:
 
 	if (outst.tag_files != NULL) {
 		fclose(stdout);
-		tag_write();
 		run_pager(outst.tag_files);
-		tag_unlink();
+		term_tag_unlink();
 	} else if (outst.had_output && outst.outtype != OUTT_LINT)
 		mandoc_msg_summary();
 
@@ -810,15 +809,16 @@ process_onefile(struct mparse *mp, struct manpage *resp, int startdir,
 	} else
 		fd = STDIN_FILENO;
 
-	if (outst->use_pager) {
-		outst->use_pager = 0;
-		outst->tag_files = tag_init(conf->output.tag);
-	}
-
-	if (outst->had_output && outst->outtype <= OUTT_UTF8) {
-		if (outst->outdata == NULL)
-			outdata_alloc(outst, &conf->output);
-		terminal_sepline(outst->outdata);
+	if (outst->outtype <= OUTT_UTF8) {
+		if (outst->use_pager) {
+			outst->use_pager = 0;
+			outst->tag_files = term_tag_init(conf->output.tag);
+		}
+		if (outst->had_output) {
+			if (outst->outdata == NULL)
+				outdata_alloc(outst, &conf->output);
+			terminal_sepline(outst->outdata);
+		}
 	}
 
 	if (resp->form == FORM_SRC)
@@ -832,7 +832,7 @@ process_onefile(struct mparse *mp, struct manpage *resp, int startdir,
 		if (outst->tag_files != NULL) {
 			mandoc_msg(MANDOCERR_WRITE, 0, 0, "%s: %s",
 			    outst->tag_files->ofn, strerror(errno));
-			tag_unlink();
+			term_tag_unlink();
 			outst->tag_files = NULL;
 		} else
 			mandoc_msg(MANDOCERR_WRITE, 0, 0, "%s",
@@ -1251,7 +1251,7 @@ spawn_pager(struct tag_files *tag_files)
 		_exit(mandoc_msg_getrc());
 	}
 	close(tag_files->ofd);
-	assert(tag_files->tfd == -1);
+	assert(tag_files->tfs == NULL);
 
 	/* Do not start the pager before controlling the terminal. */