From f10f0fe3970de778125a29d73e65e63f32c138e1 Mon Sep 17 00:00:00 2001 From: Ingo Schwarze Date: Fri, 13 Mar 2020 15:32:28 +0000 Subject: 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 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. --- read.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'read.c') diff --git a/read.c b/read.c index b3858061..dc6c2409 100644 --- a/read.c +++ b/read.c @@ -1,7 +1,7 @@ -/* $Id: read.c,v 1.214 2019/07/10 19:39:01 schwarze Exp $ */ +/* $Id: read.c,v 1.215 2020/03/13 15:32:28 schwarze Exp $ */ /* - * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons * Copyright (c) 2010-2019 Ingo Schwarze + * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons * Copyright (c) 2010, 2012 Joerg Sonnenberger * * Permission to use, copy, modify, and distribute this software for any @@ -15,6 +15,12 @@ * 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. + * + * Top-level functions of the mandoc(3) parser: + * Parser and input encoding selection, decompression, + * handling of input bytes, characters, lines, and files, + * handling of roff(7) loops and file inclusion, + * and steering of the various parsers. */ #include "config.h" @@ -36,6 +42,7 @@ #include "mandoc_aux.h" #include "mandoc.h" #include "roff.h" +#include "tag.h" #include "mdoc.h" #include "man.h" #include "mandoc_parse.h" @@ -664,6 +671,7 @@ mparse_alloc(int options, enum mandoc_os os_e, const char *os_s) } curp->man->meta.first->tok = TOKEN_NONE; curp->man->meta.os_e = os_e; + tag_alloc(); return curp; } @@ -680,6 +688,7 @@ mparse_reset(struct mparse *curp) void mparse_free(struct mparse *curp) { + tag_free(); roffhash_free(curp->man->mdocmac); roffhash_free(curp->man->manmac); roff_man_free(curp->man); -- cgit v1.2.3