Re: [PATCH] scripts/kernel-doc: Adding cross-reference links to html documentation.

[Danilo Cesar Lemes de Paula <danilo.cesar@collabora.co.uk>]

On 06/24/2015 06:22 PM, Daniel Vetter wrote:
> On Wed, Jun 24, 2015 at 04:10:24PM -0300, Danilo Cesar Lemes de Paula wrote:
>> Functions, Structs and Parameters definitions on kernel documentation
>> are pure cosmetic, it only highlights the element.
>>
>> To ease the navigation in the documentation we should use <links> inside
>> those tags so readers can easily jump between methods directly.
>>
>> This was discussed in 2014[1] and is implemented by getting a list
>> of <refentries> from the DocBook XML to generate a database. Then it looks
>> for <function>,<structnames> and <paramdef> tags that matches the ones in
>> the database. As it only links existent references, no broken links are
>> added.
>>
>> [1] - lists.freedesktop.org/archives/dri-devel/2014-August/065404.html
>>
>> Signed-off-by: Danilo Cesar Lemes de Paula <danilo.cesar@collabora.co.uk>
>> Cc: Randy Dunlap <rdunlap@infradead.org>
>> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
>> Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
>> Cc: linux-doc@vger.kernel.org
>> Cc: intel-gfx <intel-gfx@lists.freedesktop.org>
>> Cc: dri-devel <dri-devel@lists.freedesktop.org>
>> ---
>>  To understand a bit more of what this patch is trying to acomplish you can find
>>  two examples of the old and new htmldocs outputs:
>>  OLD: https://people.collabora.com/~danilo/intel/Documentation.old/DocBook/drm/API-drm-crtc-vblank-on.html
>>  NEW: https://people.collabora.com/~danilo/intel/Documentation.new/DocBook/drm/API-drm-crtc-vblank-on.html
> 
> Already discussed on irc With Danilo but here for the record: I really
> like this since it massively improves the usefulness of the docbooks we
> have. One small thing I noticed though while clicking a bit more through
> the generated html: It also generates selflinks, i.e. drm_crtc_vblank_on
> links to itself. That one is a bit confusing. Could we filter out
> self-links somehow on the reference sections?

Yes we could! I'm sending a reviewed patch in a few minutes.

- Danilo Cesar

> -Daniel
> 
>>
>>  Documentation/DocBook/Makefile |  34 +++++---
>>  scripts/kernel-doc-xml-ref     | 176 +++++++++++++++++++++++++++++++++++++++++
>>  2 files changed, 197 insertions(+), 13 deletions(-)
>>  create mode 100755 scripts/kernel-doc-xml-ref
>>
>> diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
>> index b6a6a2e..8aea45a 100644
>> --- a/Documentation/DocBook/Makefile
>> +++ b/Documentation/DocBook/Makefile
>> @@ -64,8 +64,9 @@ installmandocs: mandocs
>>  
>>  ###
>>  #External programs used
>> -KERNELDOC = $(srctree)/scripts/kernel-doc
>> -DOCPROC   = $(objtree)/scripts/docproc
>> +KERNELDOCXMLREF = $(srctree)/scripts/kernel-doc-xml-ref
>> +KERNELDOC       = $(srctree)/scripts/kernel-doc
>> +DOCPROC         = $(objtree)/scripts/docproc
>>  
>>  XMLTOFLAGS = -m $(srctree)/$(src)/stylesheet.xsl
>>  XMLTOFLAGS += --skip-validation
>> @@ -89,7 +90,7 @@ define rule_docproc
>>          ) > $(dir $@).$(notdir $@).cmd
>>  endef
>>  
>> -%.xml: %.tmpl $(KERNELDOC) $(DOCPROC) FORCE
>> +%.xml: %.tmpl $(KERNELDOC) $(DOCPROC) $(KERNELDOCXMLREF) FORCE
>>  	$(call if_changed_rule,docproc)
>>  
>>  # Tell kbuild to always build the programs
>> @@ -139,8 +140,12 @@ quiet_cmd_db2html = HTML    $@
>>        cmd_db2html = xmlto html $(XMLTOFLAGS) -o $(patsubst %.html,%,$@) $< && \
>>  		echo '<a HREF="$(patsubst %.html,%,$(notdir $@))/index.html"> \
>>  		$(patsubst %.html,%,$(notdir $@))</a><p>' > $@
>> +%.aux.xml: %.xml
>> +	@rm -rf $@
>> +	(cat $< | egrep "^<refentry id" | egrep -o "\".*\"" | cut -f 2 -d \" > $<.db)
>> +	$(KERNELDOCXMLREF) -db $<.db $< > $@
>>  
>> -%.html:	%.xml
>> +%.html:	%.aux.xml
>>  	@(which xmlto > /dev/null 2>&1) || \
>>  	 (echo "*** You need to install xmlto ***"; \
>>  	  exit 1)
>> @@ -209,15 +214,18 @@ dochelp:
>>  ###
>>  # Temporary files left by various tools
>>  clean-files := $(DOCBOOKS) \
>> -	$(patsubst %.xml, %.dvi,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.aux,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.tex,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.log,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.out,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.ps,   $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.pdf,  $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.html, $(DOCBOOKS)) \
>> -	$(patsubst %.xml, %.9,    $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.dvi,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.aux,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.tex,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.log,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.out,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.ps,      $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.pdf,     $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.html,    $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.9,       $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.aux.xml, $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.xml.db,  $(DOCBOOKS)) \
>> +	$(patsubst %.xml, %.xml,     $(DOCBOOKS)) \
>>  	$(index)
>>  
>>  clean-dirs := $(patsubst %.xml,%,$(DOCBOOKS)) man
>> diff --git a/scripts/kernel-doc-xml-ref b/scripts/kernel-doc-xml-ref
>> new file mode 100755
>> index 0000000..756e897
>> --- /dev/null
>> +++ b/scripts/kernel-doc-xml-ref
>> @@ -0,0 +1,176 @@
>> +#!/usr/bin/perl -w
>> +
>> +use strict;
>> +
>> +## Copyright (C) 2015  Intel Corporation                         ##
>> +#                                                                ##
>> +## This software falls under the GNU General Public License.     ##
>> +## Please read the COPYING file for more information             ##
>> +#
>> +#
>> +# This software reads a XML file and a list of valid interal
>> +# references to replace Docbook tags with links.
>> +#
>> +# usage:
>> +# kernel-doc-xml-ref -db filename
>> +#		     xml filename > outputfile
>> +
>> +# read arguments
>> +if ($#ARGV != 2) {
>> +	usage();
>> +}
>> +
>> +#Holds the database filename
>> +my $databasefile;
>> +my @database;
>> +
>> +#holds the inputfile
>> +my $inputfile;
>> +my $errors = 0;
>> +
>> +my %highlights = (
>> +	"<function>(.*?)</function>",
>> +	    "\"<function>\" . convert_function(\$1) . \"</function>\"",
>> +	"<structname>(.*?)</structname>",
>> +	    "\"<structname>\" . convert_struct(\$1) . \"</structname>\"",
>> +	"<paramdef>(.*?)<parameter>(.*?)</parameter></paramdef>",
>> +	    "\"<paramdef>\" . convert_param(\$1) . \"<parameter>\$2</parameter></paramdef>\"");
>> +
>> +while($ARGV[0] =~ m/^-(.*)/) {
>> +	my $cmd = shift @ARGV;
>> +	if ($cmd eq "-db") {
>> +		$databasefile = shift @ARGV
>> +	}
>> +}
>> +$inputfile = shift @ARGV;
>> +
>> +sub open_database {
>> +	open my $handle, '<', $databasefile;
>> +	chomp(my @lines = <$handle>);
>> +	close $handle;
>> +
>> +	@database = @lines;
>> +}
>> +
>> +sub process_file {
>> +	open_database();
>> +
>> +	my $dohighlight;
>> +	foreach my $pattern (keys %highlights) {
>> +		$dohighlight .=  "\$line =~ s:$pattern:$highlights{$pattern}:eg;\n";
>> +	}
>> +
>> +	open(FILE, $inputfile) or die("Could not open $inputfile");
>> +	foreach my $line (<FILE>)  {
>> +		eval $dohighlight;
>> +		print $line;
>> +	}
>> +}
>> +
>> +sub trim($_)
>> +{
>> +	my $str = $_[0];
>> +	$str =~ s/^\s+|\s+$//g;
>> +	return $str
>> +}
>> +
>> +sub has_key_defined($_)
>> +{
>> +	if ( grep( /^$_[0]$/, @database)) {
>> +		return 1;
>> +	}
>> +	return 0;
>> +}
>> +
>> +sub convert_function($_)
>> +{
>> +	my $arg = $_[0];
>> +	my $key = $_[0];
>> +
>> +	$key = trim($key);
>> +
>> +	$key =~ s/[^A-Za-z0-9]/-/g;
>> +	$key = "API-" . $key;
>> +
>> +	if (!has_key_defined($key)) {
>> +		return $arg;
>> +	}
>> +
>> +	my $head = $arg;
>> +	my $tail = "";
>> +	if ($arg =~ /(.*?)( ?)$/) {
>> +		$head = $1;
>> +		$tail = $2;
>> +	}
>> +	return "<link linkend=\"$key\">$head</link>$tail";
>> +}
>> +sub convert_struct($_)
>> +{
>> +	my $arg = $_[0];
>> +	my $key = $_[0];
>> +	$key =~ s/(struct )?(\w)/$2/g;
>> +	$key =~ s/[^A-Za-z0-9]/-/g;
>> +	$key = "API-struct-" . $key;
>> +
>> +	if (!has_key_defined($key)) {
>> +		return $arg;
>> +	}
>> +
>> +	my ($head, $tail) = split_pointer($arg);
>> +	return "<link linkend=\"$key\">$head</link>$tail";
>> +}
>> +
>> +sub split_pointer($_)
>> +{
>> +	my $arg = $_[0];
>> +	if ($arg =~ /(.*?)( ?\* ?)/) {
>> +		return ($1, $2);
>> +	}
>> +	return ($arg, "");
>> +}
>> +
>> +sub convert_param($_)
>> +{
>> +	my $type = $_[0];
>> +	my $keyname = convert_key_name($type);
>> +
>> +	if (!has_key_defined($keyname)) {
>> +		return $type;
>> +	}
>> +
>> +	my ($head, $tail) = split_pointer($type);
>> +	return "<link linkend=\"$keyname\">$head</link>$tail";
>> +
>> +}
>> +
>> +sub convert_key_name($_)
>> +{
>> +	#Pattern $2 is optional and might be uninitialized
>> +	no warnings 'uninitialized';
>> +
>> +	my $str = $_[0];
>> +	$str =~ s/(const|static)? ?(struct)? ?([a-zA-Z0-9_]+) ?(\*|&)?/$2 $3/g ;
>> +
>> +	# trim
>> +	$str =~ s/^\s+|\s+$//g;
>> +
>> +	# spaces and _ to -
>> +	$str =~ s/[^A-Za-z0-9]/-/g;
>> +
>> +	return "API-" . $str;
>> +}
>> +
>> +sub usage {
>> +	print "Usage: $0 -db database filename ]\n";
>> +	print "         xml source file(s) > outputfile\n";
>> +	exit 1;
>> +}
>> +
>> +# starting point
>> +process_file();
>> +
>> +if ($errors) {
>> +	print STDERR "$errors errors\n";
>> +}
>> +
>> +exit($errors);
>> -- 
>> 2.1.4
>>
>