Re: [PATCH] docbook: Added support for generating man files

[Sam Ravnborg <sam@ravnborg.org>]

Hi Linus - please apply. Only docbook relevant changes [with patch this time].

Originally by Michael Still <mikal@stillhq.com>
 
This patch adds two new targets to the docbook makefile -- mandocs, and
installmandocs. The targets require two new perl scripts in the scripts/
directory, but in return we get a series of man pages for kernel
functions, which are installed in man section 9. This is a good thing, as
many programmers expect documentation to be available with man, and
hunting through various PS or PDF documents to find the documentation for
the function you want can be quite frustrating.

The man pages are just extracted from the various existing DocBook SGML
documents, which are generated by kernel-doc. You also need to have
docbook2man installed on your machine.

Please note the formatting is not perfect, but I will tweak
other stuff later with further patches -- this is just an initial
implementation.

Sample output (HTMLised) can be found at
http://www.stillhq.com/linux/mandocs/2.5.68/ and
http://www.stillhq.com/linux/mandocs/2.5.70/



 CREDITS                        |    8 ++
 Documentation/DocBook/Makefile |   30 +++++++++-
 Makefile                       |    4 -
 scripts/makeman                |   46 ++++++++++++++++
 scripts/split-man              |  112 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 193 insertions(+), 7 deletions(-)

diff -Nru a/CREDITS b/CREDITS
--- a/CREDITS	Fri Jul 18 23:21:44 2003
+++ b/CREDITS	Fri Jul 18 23:21:44 2003
@@ -2981,6 +2981,14 @@
 S: Sunyvale, CA 94086
 S: USA
 
+N: Michael Still
+E: mikal@stillhq.com
+W: http://www.stillhq.com
+D: Various janitorial patches
+D: mandocs and mandocs_install build targets
+S: (Email me and ask)
+S: Australia
+
 N: Henrik Storner
 E: storner@image.dk
 W: http://www.image.dk/~storner/
diff -Nru a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
--- a/Documentation/DocBook/Makefile	Fri Jul 18 23:21:44 2003
+++ b/Documentation/DocBook/Makefile	Fri Jul 18 23:21:44 2003
@@ -20,10 +20,11 @@
 # file.tmpl --> file.sgml +--> file.ps  (psdocs)
 #                         +--> file.pdf  (pdfdocs)
 #                         +--> DIR=file  (htmldocs)
+#                         +--> man/      (mandocs)
 
 ###
 # The targets that may be used.
-.PHONY:	sgmldocs psdocs pdfdocs htmldocs clean mrproper
+.PHONY:	sgmldocs psdocs pdfdocs htmldocs mandocs installmandocs
 
 BOOKS := $(addprefix $(obj)/,$(DOCBOOKS))
 sgmldocs: $(BOOKS)
@@ -37,10 +38,18 @@
 HTML := $(patsubst %.sgml, %.html, $(BOOKS))
 htmldocs: $(HTML)
 
+MAN := $(patsubst %.sgml, %.9, $(BOOKS))
+mandocs: $(MAN)
+
+installmandocs: mandocs
+	$(MAKEMAN) install Documentation/DocBook/man
+
 ###
 #External programs used
 KERNELDOC = scripts/kernel-doc
 DOCPROC   = scripts/docproc
+SPLITMAN  = $(PERL) $(srctree)/scripts/split-man
+MAKEMAN   = $(PERL) $(srctree)/scripts/makeman
 
 ###
 # DOCPROC is used for two purposes:
@@ -128,6 +137,13 @@
             cp $(PNG-$(basename $(notdir $@))) $(patsubst %.html,%,$@); fi
 
 ###
+# Rule to generate man files - output is placed in the man subdirectory
+
+%.9:	%.sgml
+	$(SPLITMAN) $< $(objtree)/Documentation/DocBook/man "$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)"
+	$(MAKEMAN) convert $(objtree)/Documentation/DocBook/man $<
+
+###
 # Rules to generate postscripts and PNG imgages from .fig format files
 quiet_cmd_fig2eps = FIG2EPS $@
       cmd_fig2eps = fig2dev -Leps $< $@
@@ -157,10 +173,10 @@
 # Help targets as used by the top-level makefile
 dochelp:
 	@echo  '  Linux kernel internal documentation in different formats:'
-	@echo  '  sgmldocs (SGML), psdocs (Postscript), pdfdocs (PDF), htmldocs (HTML)'
+	@echo  '  sgmldocs (SGML), psdocs (Postscript), pdfdocs (PDF)'
+	@echo  '  htmldocs (HTML), mandocs (man pages, use installmandocs to install)'
 
 ###
-# clean and mrproper as used by the top-level makefile 
 # Temporary files left by various tools
 clean-files := $(DOCBOOKS) \
 	$(patsubst %.sgml, %.dvi,  $(DOCBOOKS)) \
@@ -171,10 +187,14 @@
 	$(patsubst %.sgml, %.ps,   $(DOCBOOKS)) \
 	$(patsubst %.sgml, %.pdf,  $(DOCBOOKS)) \
 	$(patsubst %.sgml, %.html, $(DOCBOOKS)) \
-	$(patsubst %.fig,%.eps, $(IMG-parportbook)) \
-	$(patsubst %.fig,%.png, $(IMG-parportbook)) \
+	$(patsubst %.sgml, %.9,    $(DOCBOOKS)) \
+	$(patsubst %.fig,%.eps,    $(IMG-parportbook)) \
+	$(patsubst %.fig,%.png,    $(IMG-parportbook)) \
 	$(C-procfs-example)
 
 ifneq ($(wildcard $(patsubst %.html,%,$(HTML))),)
 clean-rule := rm -rf $(wildcard $(patsubst %.html,%,$(HTML)))
 endif
+
+#man put files in man subdir - traverse down
+subdir- := man/
diff -Nru a/Makefile b/Makefile
--- a/Makefile	Fri Jul 18 23:21:44 2003
+++ b/Makefile	Fri Jul 18 23:21:44 2003
@@ -236,7 +236,7 @@
 noconfig_targets := xconfig gconfig menuconfig config oldconfig randconfig \
 		    defconfig allyesconfig allnoconfig allmodconfig \
 		    clean mrproper distclean rpm \
-		    help tags TAGS cscope sgmldocs psdocs pdfdocs htmldocs \
+		    help tags TAGS cscope %docs \
 		    checkconfig checkhelp checkincludes
 
 RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o -name CVS \) -prune -o
@@ -830,7 +830,7 @@
 
 # Documentation targets
 # ---------------------------------------------------------------------------
-sgmldocs psdocs pdfdocs htmldocs: scripts/docproc FORCE
+%docs: scripts/docproc FORCE
 	$(Q)$(MAKE) $(build)=Documentation/DocBook $@
 
 # Scripts to check various things for consistency
diff -Nru a/scripts/makeman b/scripts/makeman
--- /dev/null	Wed Dec 31 16:00:00 1969
+++ b/scripts/makeman	Fri Jul 18 23:21:44 2003
@@ -0,0 +1,46 @@
+#!/usr/bin/perl
+
+use strict;
+
+## Copyright (C) Michael Still (mikal@stillhq.com)
+## Released under the terms of the GNU GPL
+##
+## A script to make or install the manpages extracted by split-man
+##
+## Arguements: $1 -- the word "convert" or "install"
+##             $2 -- the directory containing the SGML files for the manpages
+##             $3 -- the filename which contained the sgmldoc output
+##                     (I need this so I know which manpages to convert)
+
+my($LISTING);
+
+if($ARGV[0] eq ""){
+  die "Usage: makeman [convert | install] <dir> <file>\n";
+}
+
+if( ! -d "$ARGV[1]" ){
+  die "Output directory \"$ARGV[1]\" does not exist\n";
+}
+
+if($ARGV[0] eq "convert"){
+  open LISTING, "grep \"<refentrytitle>\" $ARGV[2] |";
+  while(<LISTING>){
+    s/<\/.*$//;
+    s/^.*>//;
+    s/\.sgml//;
+    s/struct //;
+    s/typedef //;
+
+    chomp;
+    print "Processing $_\n";
+    system("cd $ARGV[1]; docbook2man $_.sgml; gzip -f $_.9\n");
+  }
+}
+elsif($ARGV[0] eq "install"){
+  system("mkdir -p /usr/local/man/man9/; install $ARGV[1]/*.9.gz /usr/local/man/man9/");
+}
+else{
+  die "Usage: makeman [convert | install] <dir> <file>\n";
+}
+
+print "Done\n";
diff -Nru a/scripts/split-man b/scripts/split-man
--- /dev/null	Wed Dec 31 16:00:00 1969
+++ b/scripts/split-man	Fri Jul 18 23:21:44 2003
@@ -0,0 +1,112 @@
+#!/usr/bin/perl
+
+use strict;
+
+## Copyright (C) Michael Still (mikal@stillhq.com)
+## Released under the terms of the GNU GPL
+##
+## Hoon through the specified DocBook SGML file, and split out the
+## man pages. These can then be processed into groff format, and
+## installed if desired...
+##
+## Arguements: $1 -- the name of the sgml file
+##             $2 -- the directory to put the generated SGML files in
+##             $3 -- kernel version
+
+my($SGML, $REF, $front, $refdata, $mode, $filename);
+
+if(($ARGV[0] eq "") || ($ARGV[1] eq "") || ($ARGV[2] eq "")){
+  die "Usage: split-man <sgml file> <output dir> <kernel version>\n";
+}
+
+open SGML, "< $ARGV[0]" or die "Could not open input file \"$ARGV[0]\"\n";
+if( ! -d "$ARGV[1]" ){
+  die "Output directory \"$ARGV[1]\" does not exist\n";
+}
+
+# Possible modes:
+#   0: Looking for input I care about
+#   1: Inside book front matter
+#   2: Inside a refentry
+#   3: Inside a refentry, and we know the filename
+
+$mode = 0;
+$refdata = "";
+$front = "";
+while(<SGML>){
+  # Starting modes
+  if(/<legalnotice>/){
+    $mode = 1;
+  }
+  elsif(/<refentry>/){
+    $mode = 2;
+  }
+  elsif(/<refentrytitle><phrase[^>]*>([^<]*)<.*$/){
+    $mode = 3;
+    $filename = $1;
+
+    $filename =~ s/struct //;
+    $filename =~ s/typedef //;
+
+    print "Found manpage for $filename\n";
+    open REF, "> $ARGV[1]/$filename.sgml" or
+      die "Couldn't open output file \"$ARGV[1]/$filename.sgml\": $!\n";
+    print REF "<!DOCTYPE refentry PUBLIC \"-//Davenport//DTD DocBook V3.0//EN\">\n\n";
+    print REF "$refdata";
+    $refdata = "";
+  }
+
+  # Extraction
+  if($mode == 1){
+    $front = "$front$_";
+  }
+  elsif($mode == 2){
+    $refdata = "$refdata$_";
+  }
+  elsif($mode == 3){
+    # There are some fixups which need to be applied
+    if(/<\/refmeta>/){
+      print REF "<manvolnum>9</manvolnum>\n";
+    }
+    if(/<\/refentry>/){
+      $front =~ s/<legalnotice>//;
+      $front =~ s/<\/legalnotice>//;
+      print REF <<EOF;
+<refsect1><title>About this document</title>
+$front
+<para>
+If you have comments on the formatting of this manpage, then please contact
+Michael Still (mikal\@stillhq.com).
+</para>
+
+<para>
+This documentation was generated with kernel version $ARGV[2].
+</para>
+</refsect1>
+EOF
+    }
+
+    # For some reason, we title the synopsis twice in the main DocBook
+    if(! /<title>Synopsis<\/title>/){
+      if(/<refentrytitle>/){
+	s/struct //;
+	s/typedef //;
+      }
+
+      print REF "$_";
+    }
+  }
+
+  # Ending modes
+  if(/<\/legalnotice>/){
+    $mode = 0;
+  }
+  elsif(/<\/refentry>/){
+    $mode = 0;
+    close REF;
+  }
+}
+
+# And make sure we don't process this unnessesarily
+$ARGV[0] =~ s/\.sgml/.9/;
+`touch $ARGV[0]`;