#!/usr/bin/env perl # SPDX-License-Identifier: GPL-2.0 use warnings; use strict; ## Copyright (c) 1998 Michael Zucchi, All Rights Reserved ## ## Copyright (C) 2000, 1 Tim Waugh ## ## Copyright (C) 2001 Simon Huggins ## ## Copyright (C) 2005-2012 Randy Dunlap ## ## Copyright (C) 2012 Dan Luedtke ## ## ## ## #define enhancements by Armin Kuster ## ## Copyright (c) 2000 MontaVista Software, Inc. ## ## ## ## This software falls under the GNU General Public License. ## ## Please read the COPYING file for more information ## # 18/01/2001 - Cleanups # Functions prototyped as foo(void) same as foo() # Stop eval'ing where we don't need to. # -- huggie@earth.li # 27/06/2001 - Allowed whitespace after initial "/**" and # allowed comments before function declarations. # -- Christian Kreibich # Still to do: # - add perldoc documentation # - Look more closely at some of the scarier bits :) # 26/05/2001 - Support for separate source and object trees. # Return error code. # Keith Owens # 23/09/2001 - Added support for typedefs, structs, enums and unions # Support for Context section; can be terminated using empty line # Small fixes (like spaces vs. \s in regex) # -- Tim Jansen # 25/07/2012 - Added support for HTML5 # -- Dan Luedtke sub usage { my $message = <<"EOF"; Usage: $0 [OPTION ...] FILE ... Read C language source or header FILEs, extract embedded documentation comments, and print formatted documentation to standard output. The documentation comments are identified by "/**" opening comment mark. See Documentation/doc-guide/kernel-doc.rst for the documentation comment syntax. Output format selection (mutually exclusive): -man Output troff manual page format. This is the default. -rst Output reStructuredText format. -none Do not output documentation, only warnings. Output selection (mutually exclusive): -export Only output documentation for symbols that have been exported using EXPORT_SYMBOL() or EXPORT_SYMBOL_GPL() in any input FILE or -export-file FILE. -internal Only output documentation for symbols that have NOT been exported using EXPORT_SYMBOL() or EXPORT_SYMBOL_GPL() in any input FILE or -export-file FILE. -function NAME Only output documentation for the given function(s) or DOC: section title(s). All other functions and DOC: sections are ignored. May be specified multiple times. -nofunction NAME Do NOT output documentation for the given function(s); only output documentation for the other functions and DOC: sections. May be specified multiple times. Output selection modifiers: -no-doc-sections Do not output DOC: sections. -enable-lineno Enable output of #define LINENO lines. Only works with reStructuredText format. -export-file FILE Specify an additional FILE in which to look for EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL(). To be used with -export or -internal. May be specified multiple times. Other parameters: -v Verbose output, more warnings and other information. -h Print this help. EOF print $message; exit 1; } # # format of comments. # In the following table, (...)? signifies optional structure. # (...)* signifies 0 or more structure elements # /** # * function_name(:)? (- short description)? # (* @parameterx: (description of parameter x)?)* # (* a blank line)? # * (Description:)? (Description of function)? # * (section header: (section description)? )* # (*)?*/ # # So .. the trivial example would be: # # /** # * my_function # */ # # If the Description: header tag is omitted, then there must be a blank line # after the last parameter specification. # e.g. # /** # * my_function - does my stuff # * @my_arg: its mine damnit # * # * Does my stuff explained. # */ # # or, could also use: # /** # * my_function - does my stuff # * @my_arg: its mine damnit # * Description: Does my stuff explained. # */ # etc. # # Besides functions you can also write documentation for structs, unions, # enums and typedefs. Instead of the function name you must write the name # of the declaration; the struct/union/enum/typedef must always precede # the name. Nesting of declarations is not supported. # Use the argument mechanism to document members or constants. # e.g. # /** # * struct my_struct - short description # * @a: first member # * @b: second member # * # * Longer description # */ # struct my_struct { # int a; # int b; # /* private: */ # int c; # }; # # All descriptions can be multiline, except the short function description. # # For really longs structs, you can also describe arguments inside the # body of the struct. # eg. # /** # * struct my_struct - short description # * @a: first member # * @b: second member # * # * Longer description # */ # struct my_struct { # int a; # int b; # /** # * @c: This is longer description of C # * # * You can use paragraphs to describe arguments # * using this method. # */ # int c; # }; # # This should be use only for struct/enum members. # # You can also add additional sections. When documenting kernel functions you # should document the "Context:" of the function, e.g. whether the functions # can be called form interrupts. Unlike other sections you can end it with an # empty line. # A non-void function should have a "Return:" section describing the return # value(s). # Example-sections should contain the string EXAMPLE so that they are marked # appropriately in DocBook. # # Example: # /** # * user_function - function that can only be called in user context # * @a: some argument # * Context: !in_interrupt() # * # * Some description # * Example: # * user_function(22); # */ # ... # # # All descriptive text is further processed, scanning for the following special # patterns, which are highlighted appropriately. # # 'funcname()' - function # '$ENVVAR' - environmental variable # '&struct_name' - name of a structure (up to two words including 'struct') # '&struct_name.member' - name of a structure member # '@parameter' - name of a parameter # '%CONST' - name of a constant. # '``LITERAL``' - literal string without any spaces on it. ## init lots of data my $errors = 0; my $warnings = 0; my $anon_struct_union = 0; # match expressions used to find embedded type information my $type_constant = '\b``([^\`]+)``\b'; my $type_constant2 = '\%([-_\w]+)'; my $type_func = '(\w+)\(\)'; my $type_param = '\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)'; my $type_fp_param = '\@(\w+)\(\)'; # Special RST handling for func ptr params my $type_fp_param2 = '\@(\w+->\S+)\(\)'; # Special RST handling for structs with func ptr params my $type_env = '(\$\w+)'; my $type_enum = '\&(enum\s*([_\w]+))'; my $type_struct = '\&(struct\s*([_\w]+))'; my $type_typedef = '\&(typedef\s*([_\w]+))'; my $type_union = '\&(union\s*([_\w]+))'; my $type_member = '\&([_\w]+)(\.|->)([_\w]+)'; my $type_fallback = '\&([_\w]+)'; my $type_member_func = $type_member . '\(\)'; # Output conversion substitutions. # One for each output format # these are pretty rough my @highlights_man = ( [$type_constant, "\$1"], [$type_constant2, "\$1"], [$type_func, "\\\\fB\$1\\\\fP"], [$type_enum, "\\\\fI\$1\\\\fP"], [$type_struct, "\\\\fI\$1\\\\fP"], [$type_typedef, "\\\\fI\$1\\\\fP"], [$type_union, "\\\\fI\$1\\\\fP"], [$type_param, "\\\\fI\$1\\\\fP"], [$type_member, "\\\\fI\$1\$2\$3\\\\fP"], [$type_fallback, "\\\\fI\$1\\\\fP"] ); my $blankline_man = ""; # rst-mode my @highlights_rst = ( [$type_constant, "``\$1``"], [$type_constant2, "``\$1``"], # Note: need to escape () to avoid func matching later [$type_member_func, "\\:c\\:type\\:`\$1\$2\$3\\\\(\\\\) <\$1>`"], [$type_member, "\\:c\\:type\\:`\$1\$2\$3 <\$1>`"], [$type_fp_param, "**\$1\\\\(\\\\)**"], [$type_fp_param2, "**\$1\\\\(\\\\)**"], [$type_func, "\$1()"], [$type_enum, "\\:c\\:type\\:`\$1 <\$2>`"], [$type_struct, "\\:c\\:type\\:`\$1 <\$2>`"], [$type_typedef, "\\:c\\:type\\:`\$1 <\$2>`"], [$type_union, "\\:c\\:type\\:`\$1 <\$2>`"], # in rst this can refer to any type [$type_fallback, "\\:c\\:type\\:`\$1`"], [$type_param, "**\$1**"] ); my $blankline_rst = "\n"; # read arguments if ($#ARGV == -1) { usage(); } my $kernelversion; my $dohighlight = ""; my $verbose = 0; my $output_mode = "rst"; my $output_preformatted = 0; my $no_doc_sections = 0; my $enable_lineno = 0; my @highlights = @highlights_rst; my $blankline = $blankline_rst; my $modulename = "Kernel API"; use constant { OUTPUT_ALL => 0, # output all symbols and doc sections OUTPUT_INCLUDE => 1, # output only specified symbols OUTPUT_EXCLUDE => 2, # output everything except specified symbols OUTPUT_EXPORTED => 3, # output exported symbols OUTPUT_INTERNAL => 4, # output non-exported symbols }; my $output_selection = OUTPUT_ALL; my $show_not_found = 0; # No longer used my @export_file_list; my @build_time; if (defined($ENV{'KBUILD_BUILD_TIMESTAMP'}) && (my $seconds = `date -d"${ENV{'KBUILD_BUILD_TIMESTAMP'}}" +%s`) ne '') { @build_time = gmtime($seconds); } else { @build_time = localtime; } my $man_date = ('January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December')[$build_time[4]] . " " . ($build_time[5]+1900); # Essentially these are globals. # They probably want to be tidied up, made more localised or something. # CAVEAT EMPTOR! Some of the others I localised may not want to be, which # could cause "use of undefined value" or other bugs. my ($function, %function_table, %parametertypes, $declaration_purpose); my $declaration_start_line; my ($type, $declaration_name, $return_type); my ($newsection, $newcontents, $prototype, $brcount, %source_map); if (defined($ENV{'KBUILD_VERBOSE'})) { $verbose = "$ENV{'KBUILD_VERBOSE'}"; } # Generated docbook code is inserted in a template at a point where # docbook v3.1 requires a non-zero sequence of RefEntry's; see: # http://www.oasis-open.org/docbook/documentation/reference/html/refentry.html # We keep track of number of generated entries and generate a dummy # if needs be to ensure the expanded template can be postprocessed # into html. my $section_counter = 0; my $lineprefix=""; # Parser states use constant { STATE_NORMAL => 0, # normal code STATE_NAME => 1, # looking for function name STATE_BODY_MAYBE => 2, # body - or maybe more description STATE_BODY => 3, # the body of the comment STATE_PROTO => 4, # scanning prototype STATE_DOCBLOCK => 5, # documentation block STATE_INLINE => 6, # gathering documentation outside main block }; my $state; my $in_doc_sect; my $leading_space; # Inline documentation state use constant { STATE_INLINE_NA => 0, # not applicable ($state != STATE_INLINE) STATE_INLINE_NAME => 1, # looking for member name (@foo:) STATE_INLINE_TEXT => 2, # looking for member documentation STATE_INLINE_END => 3, # done STATE_INLINE_ERROR => 4, # error - Comment without header was found. # Spit a warning as it's not # proper kernel-doc and ignore the rest. }; my $inline_doc_state; #declaration types: can be # 'function', 'struct', 'union', 'enum', 'typedef' my $decl_type; my $doc_start = '^/\*\*\s*$'; # Allow whitespace at end of comment start. my $doc_end = '\*/'; my $doc_com = '\s*\*\s*'; my $doc_com_body = '\s*\* ?'; my $doc_decl = $doc_com . '(\w+)'; # @params and a strictly limited set of supported section names my $doc_sect = $doc_com . '\s*(\@[.\w]+|\@\.\.\.|description|context|returns?|notes?|examples?)\s*:(.*)'; my $doc_content = $doc_com_body . '(.*)'; my $doc_block = $doc_com . 'DOC:\s*(.*)?'; my $doc_inline_start = '^\s*/\*\*\s*$'; my $doc_inline_sect = '\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)'; my $doc_inline_end = '^\s*\*/\s*$'; my $doc_inline_oneline = '^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$'; my $export_symbol = '^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*;'; my %parameterdescs; my %parameterdesc_start_lines; my @parameterlist; my %sections; my @sectionlist; my %section_start_lines; my $sectcheck; my $struct_actual; my $contents = ""; my $new_start_line = 0; # the canonical section names. see also $doc_sect above. my $section_default = "Description"; # default section my $section_intro = "Introduction"; my $section = $section_default; my $section_context = "Context"; my $section_return = "Return"; my $undescribed = "-- undescribed --"; reset_state(); while ($ARGV[0] =~ m/^--?(.*)/) { my $cmd = $1; shift @ARGV; if ($cmd eq "man") { $output_mode = "man"; @highlights = @highlights_man; $blankline = $blankline_man; } elsif ($cmd eq "rst") { $output_mode = "rst"; @highlights = @highlights_rst; $blankline = $blankline_rst; } elsif ($cmd eq "none") { $output_mode = "none"; } elsif ($cmd eq "module") { # not needed for XML, inherits from calling document $modulename = shift @ARGV; } elsif ($cmd eq "function") { # to only output specific functions $output_selection = OUTPUT_INCLUDE; $function = shift @ARGV; $function_table{$function} = 1; } elsif ($cmd eq "nofunction") { # output all except specific functions $output_selection = OUTPUT_EXCLUDE; $function = shift @ARGV; $function_table{$function} = 1; } elsif ($cmd eq "export") { # only exported symbols $output_selection = OUTPUT_EXPORTED; %function_table = (); } elsif ($cmd eq "internal") { # only non-exported symbols $output_selection = OUTPUT_INTERNAL; %function_table = (); } elsif ($cmd eq "export-file") { my $file = shift @ARGV; push(@export_file_list, $file); } elsif ($cmd eq "v") { $verbose = 1; } elsif (($cmd eq "h") || ($cmd eq "help")) { usage(); } elsif ($cmd eq 'no-doc-sections') { $no_doc_sections = 1; } elsif ($cmd eq 'enable-lineno') { $enable_lineno = 1; } elsif ($cmd eq 'show-not-found') { $show_not_found = 1; # A no-op but don't fail } else { # Unknown argument usage(); } } # continue execution near EOF; # get kernel version from env sub get_kernel_version() { my $version = 'unknown kernel version'; if (defined($ENV{'KERNELVERSION'})) { $version = $ENV{'KERNELVERSION'}; } return $version; } # sub print_lineno { my $lineno = shift; if ($enable_lineno && defined($lineno)) { print "#define LINENO " . $lineno . "\n"; } } ## # dumps section contents to arrays/hashes intended for that purpose. # sub dump_section { my $file = shift; my $name = shift; my $contents = join "\n", @_; if ($name =~ m/$type_param/) { $name = $1; $parameterdescs{$name} = $contents; $sectcheck = $sectcheck . $name . " "; $parameterdesc_start_lines{$name} = $new_start_line; $new_start_line = 0; } elsif ($name eq "@\.\.\.") { $name = "..."; $parameterdescs{$name} = $contents; $sectcheck = $sectcheck . $name . " "; $parameterdesc_start_lines{$name} = $new_start_line; $new_start_line = 0; } else { if (defined($sections{$name}) && ($sections{$name} ne "")) { # Only warn on user specified duplicate section names. if ($name ne $section_default) { print STDERR "${file}:$.: warning: duplicate section name '$name'\n"; ++$warnings; } $sections{$name} .= $contents; } else { $sections{$name} = $contents; push @sectionlist, $name; $section_start_lines{$name} = $new_start_line; $new_start_line = 0; } } } ## # dump DOC: section after checking that it should go out # sub dump_doc_section { my $file = shift; my $name = shift; my $contents = join "\n", @_; if ($no_doc_sections) { return; } if (($output_selection == OUTPUT_ALL) || ($output_selection == OUTPUT_INCLUDE && defined($function_table{$name})) || ($output_selection == OUTPUT_EXCLUDE && !defined($function_table{$name}))) { dump_section($file, $name, $contents); output_blockhead({'sectionlist' => \@sectionlist, 'sections' => \%sections, 'module' => $modulename, 'content-only' => ($output_selection != OUTPUT_ALL), }); } } ## # output function # # parameterdescs, a hash. # function => "function name" # parameterlist => @list of parameters # parameterdescs => %parameter descriptions # sectionlist => @list of sections # sections => %section descriptions # sub output_highlight { my $contents = join "\n",@_; my $line; # DEBUG # if (!defined $contents) { # use Carp; # confess "output_highlight got called with no args?\n"; # } # print STDERR "contents b4:$contents\n"; eval $dohighlight; die $@ if $@; # print STDERR "contents af:$contents\n"; foreach $line (split "\n", $contents) { if (! $output_preformatted) { $line =~ s/^\s*//; } if ($line eq ""){ if (! $output_preformatted) { print $lineprefix, $blankline; } } else { if ($output_mode eq "man" && substr($line, 0, 1) eq ".") { print "\\&$line"; } else { print $lineprefix, $line; } } print "\n"; } } ## # output function in man sub output_function_man(%) { my %args = %{$_[0]}; my ($parameter, $section); my $count; print ".TH \"$args{'function'}\" 9 \"$args{'function'}\" \"$man_date\" \"Kernel Hacker's Manual\" LINUX\n"; print ".SH NAME\n"; print $args{'function'} . " \\- " . $args{'purpose'} . "\n"; print ".SH SYNOPSIS\n"; if ($args{'functiontype'} ne "") { print ".B \"" . $args{'functiontype'} . "\" " . $args{'function'} . "\n"; } else { print ".B \"" . $args{'function'} . "\n"; } $count = 0; my $parenth = "("; my $post = ","; foreach my $parameter (@{$args{'parameterlist'}}) { if ($count == $#{$args{'parameterlist'}}) { $post = ");"; } $type = $args{'parametertypes'}{$parameter}; if ($type =~ m/([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)/) { # pointer-to-function print ".BI \"" . $parenth . $1 . "\" " . $parameter . " \") (" . $2 . ")" . $post . "\"\n"; } else { $type =~ s/([^\*])$/$1 /; print ".BI \"" . $parenth . $type . "\" " . $parameter . " \"" . $post . "\"\n"; } $count++; $parenth = ""; } print ".SH ARGUMENTS\n"; foreach $parameter (@{$args{'parameterlist'}}) { my $parameter_name = $parameter; $parameter_name =~ s/\[.*//; print ".IP \"" . $parameter . "\" 12\n"; output_highlight($args{'parameterdescs'}{$parameter_name}); } foreach $section (@{$args{'sectionlist'}}) { print ".SH \"", uc $section, "\"\n"; output_highlight($args{'sections'}{$section}); } } ## # output enum in man sub output_enum_man(%) { my %args = %{$_[0]}; my ($parameter, $section); my $count; print ".TH \"$args{'module'}\" 9 \"enum $args{'enum'}\" \"$man_date\" \"API Manual\" LINUX\n"; print ".SH NAME\n"; print "enum " . $args{'enum'} . " \\- " . $args{'purpose'} . "\n"; print ".SH SYNOPSIS\n"; print "enum " . $args{'enum'} . " {\n"; $count = 0; foreach my $parameter (@{$args{'parameterlist'}}) { print ".br\n.BI \" $parameter\"\n"; if ($count == $#{$args{'parameterlist'}}) { print "\n};\n"; last; } else { print ", \n.br\n"; } $count++; } print ".SH Constants\n"; foreach $parameter (@{$args{'parameterlist'}}) { my $parameter_name = $parameter; $parameter_name =~ s/\[.*//; print ".IP \"" . $parameter . "\" 12\n"; output_highlight($args{'parameterdescs'}{$parameter_name}); } foreach $section (@{$args{'sectionlist'}}) { print ".SH \"$section\"\n"; output_highlight($args{'sections'}{$section}); } } ## # output struct in man sub output_struct_man(%) { my %args = %{$_[0]}; my ($parameter, $section); print ".TH \"$args{'module'}\" 9 \"" . $args{'type'} . " " . $args{'struct'} . "\" \"$man_date\" \"API Manual\" LINUX\n"; print ".SH NAME\n"; print $args{'type'} . " " . $args{'struct'} . " \\- " . $args{'purpose'} . "\n"; my $declaration = $args{'definition'}; $declaration =~ s/\t/ /g; $declaration =~ s/\n/"\n.br\n.BI \"/g; print ".SH SYNOPSIS\n"; print $args{'type'} . " " . $args{'struct'} . " {\n.br\n"; print ".BI \"$declaration\n};\n.br\n\n"; print ".SH Members\n"; foreach $parameter (@{$args{'parameterlist'}}) { ($parameter =~ /^#/) && next; my $parameter_name = $parameter; $parameter_name =~ s/\[.*//; ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; print ".IP \"" . $parameter . "\" 12\n"; output_highlight($args{'parameterdescs'}{$parameter_name}); } foreach $section (@{$args{'sectionlist'}}) { print ".SH \"$section\"\n"; output_highlight($args{'sections'}{$section}); } } ## # output typedef in man sub output_typedef_man(%) { my %args = %{$_[0]}; my ($parameter, $section); print ".TH \"$args{'module'}\" 9 \"$args{'typedef'}\" \"$man_date\" \"API Manual\" LINUX\n"; print ".SH NAME\n"; print "typedef " . $args{'typedef'} . " \\- " . $args{'purpose'} . "\n"; foreach $section (@{$args{'sectionlist'}}) { print ".SH \"$section\"\n"; output_highlight($args{'sections'}{$section}); } } sub output_blockhead_man(%) { my %args = %{$_[0]}; my ($parameter, $section); my $count; print ".TH \"$args{'module'}\" 9 \"$args{'module'}\" \"$man_date\" \"API Manual\" LINUX\n"; foreach $section (@{$args{'sectionlist'}}) { print ".SH \"$section\"\n"; output_highlight($args{'sections'}{$section}); } } ## # output in restructured text # # # This could use some work; it's used to output the DOC: sections, and # starts by putting out the name of the doc section itself, but that tends # to duplicate a header already in the template file. # sub output_blockhead_rst(%) { my %args = %{$_[0]}; my ($parameter, $section); foreach $section (@{$args{'sectionlist'}}) { if ($output_selection != OUTPUT_INCLUDE) { print "**$section**\n\n"; } print_lineno($section_start_lines{$section}); output_highlight_rst($args{'sections'}{$section}); print "\n"; } } # # Apply the RST highlights to a sub-block of text. # sub highlight_block($) { # The dohighlight kludge requires the text be called $contents my $contents = shift; eval $dohighlight; die $@ if $@; return $contents; } # # Regexes used only here. # my $sphinx_literal = '^[^.].*::$'; my $sphinx_cblock = '^\.\.\ +code-block::'; sub output_highlight_rst { my $input = join "\n",@_; my $output = ""; my $line; my $in_literal = 0; my $litprefix; my $block = ""; foreach $line (split "\n",$input) { # # If we're in a literal block, see if we should drop out # of it. Otherwise pass the line straight through unmunged. # if ($in_literal) { if (! ($line =~ /^\s*$/)) { # # If this is the first non-blank line in a literal # block we need to figure out what the proper indent is. # if ($litprefix eq "") { $line =~ /^(\s*)/; $litprefix = '^' . $1; $output .= $line . "\n"; } elsif (! ($line =~ /$litprefix/)) { $in_literal = 0; } else { $output .= $line . "\n"; } } else { $output .= $line . "\n"; } } # # Not in a literal block (or just dropped out) # if (! $in_literal) { $block .= $line . "\n"; if (($line =~ /$sphinx_literal/) || ($line =~ /$sphinx_cblock/)) { $in_literal = 1; $litprefix = ""; $output .= highlight_block($block); $block = "" } } } if ($block) { $output .= highlight_block($block); } foreach $line (split "\n", $output) { print $lineprefix . $line . "\n"; } } sub output_function_rst(%) { my %args = %{$_[0]}; my ($parameter, $section); my $oldprefix = $lineprefix; my $start = ""; if ($args{'typedef'}) { print ".. c:type:: ". $args{'function'} . "\n\n"; print_lineno($declaration_start_line); print " **Typedef**: "; $lineprefix = ""; output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; } else { print ".. c:function:: "; } if ($args{'functiontype'} ne "") { $start .= $args{'functiontype'} . " " . $args{'function'} . " ("; } else { $start .= $args{'function'} . " ("; } print $start; my $count = 0; foreach my $parameter (@{$args{'parameterlist'}}) { if ($count ne 0) { print ", "; } $count++; $type = $args{'parametertypes'}{$parameter}; if ($type =~ m/([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)/) { # pointer-to-function print $1 . $parameter . ") (" . $2 . ")"; } else { print $type . " " . $parameter; } } if ($args{'typedef'}) { print ");``\n\n"; } else { print ")\n\n"; print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); print "\n"; } print "**Parameters**\n\n"; $lineprefix = " "; foreach $parameter (@{$args{'parameterlist'}}) { my $parameter_name = $parameter; $parameter_name =~ s/\[.*//; $type = $args{'parametertypes'}{$parameter}; if ($type ne "") { print "``$type $parameter``\n"; } else { print "``$parameter``\n"; } print_lineno($parameterdesc_start_lines{$parameter_name}); if (defined($args{'parameterdescs'}{$parameter_name}) && $args{'parameterdescs'}{$parameter_name} ne $undescribed) { output_highlight_rst($args{'parameterdescs'}{$parameter_name}); } else { print " *undescribed*\n"; } print "\n"; } $lineprefix = $oldprefix; output_section_rst(@_); } sub output_section_rst(%) { my %args = %{$_[0]}; my $section; my $oldprefix = $lineprefix; $lineprefix = ""; foreach $section (@{$args{'sectionlist'}}) { print "**$section**\n\n"; print_lineno($section_start_lines{$section}); output_highlight_rst($args{'sections'}{$section}); print "\n"; } print "\n"; $lineprefix = $oldprefix; } sub output_enum_rst(%) { my %args = %{$_[0]}; my ($parameter); my $oldprefix = $lineprefix; my $count; my $name = "enum " . $args{'enum'}; print "\n\n.. c:type:: " . $name . "\n\n"; print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); print "\n"; print "**Constants**\n\n"; $lineprefix = " "; foreach $parameter (@{$args{'parameterlist'}}) { print "``$parameter``\n"; if ($args{'parameterdescs'}{$parameter} ne $undescribed) { output_highlight_rst($args{'parameterdescs'}{$parameter}); } else { print " *undescribed*\n"; } print "\n"; } $lineprefix = $oldprefix; output_section_rst(@_); } sub output_typedef_rst(%) { my %args = %{$_[0]}; my ($parameter); my $oldprefix = $lineprefix; my $name = "typedef " . $args{'typedef'}; print "\n\n.. c:type:: " . $name . "\n\n"; print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); print "\n"; $lineprefix = $oldprefix; output_section_rst(@_); } sub output_struct_rst(%) { my %args = %{$_[0]}; my ($parameter); my $oldprefix = $lineprefix; my $name = $args{'type'} . " " . $args{'struct'}; print "\n\n.. c:type:: " . $name . "\n\n"; print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); print "\n"; print "**Definition**\n\n"; print "::\n\n"; my $declaration = $args{'definition'}; $declaration =~ s/\t/ /g; print " " . $args{'type'} . " " . $args{'struct'} . " {\n$declaration };\n\n"; print "**Members**\n\n"; $lineprefix = " "; foreach $parameter (@{$args{'parameterlist'}}) { ($parameter =~ /^#/) && next; my $parameter_name = $parameter; $parameter_name =~ s/\[.*//; ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; $type = $args{'parametertypes'}{$parameter}; print_lineno($parameterdesc_start_lines{$parameter_name}); print "``" . $parameter . "``\n"; output_highlight_rst($args{'parameterdescs'}{$parameter_name}); print "\n"; } print "\n"; $lineprefix = $oldprefix; output_section_rst(@_); } ## none mode output functions sub output_function_none(%) { } sub output_enum_none(%) { } sub output_typedef_none(%) { } sub output_struct_none(%) { } sub output_blockhead_none(%) { } ## # generic output function for all types (function, struct/union, typedef, enum); # calls the generated, variable output_ function name based on # functype and output_mode sub output_declaration { no strict 'refs'; my $name = shift; my $functype = shift; my $func = "output_${functype}_$output_mode"; if (($output_selection == OUTPUT_ALL) || (($output_selection == OUTPUT_INCLUDE || $output_selection == OUTPUT_EXPORTED) && defined($function_table{$name})) || (($output_selection == OUTPUT_EXCLUDE || $output_selection == OUTPUT_INTERNAL) && !($functype eq "function" && defined($function_table{$name})))) { &$func(@_); $section_counter++; } } ## # generic output function - calls the right one based on current output mode. sub output_blockhead { no strict 'refs'; my $func = "output_blockhead_" . $output_mode; &$func(@_); $section_counter++; } ## # takes a declaration (struct, union, enum, typedef) and # invokes the right handler. NOT called for functions. sub dump_declaration($$) { no strict 'refs'; my ($prototype, $file) = @_; my $func = "dump_" . $decl_type; &$func(@_); } sub dump_union($$) { dump_struct(@_); } sub dump_struct($$) { my $x = shift; my $file = shift; if ($x =~ /(struct|union)\s+(\w+)\s*\{(.*)\}(\s*(__packed|__aligned|____cacheline_aligned_in_smp|__attribute__\s*\(\([a-z0-9,_\s\(\)]*\)\)))*/) { my $decl_type = $1; $declaration_name = $2; my $members = $3; # ignore members marked private: $members =~ s/\/\*\s*private:.*?\/\*\s*public:.*?\*\///gosi; $members =~ s/\/\*\s*private:.*//gosi; # strip comments: $members =~ s/\/\*.*?\*\///gos; # strip attributes $members =~ s/\s*__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)/ /gi; $members =~ s/\s*__aligned\s*\([^;]*\)/ /gos; $members =~ s/\s*__packed\s*/ /gos; $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; # replace DECLARE_BITMAP $members =~ s/DECLARE_BITMAP\s*\(([^,)]+),\s*([^,)]+)\)/unsigned long $1\[BITS_TO_LONGS($2)\]/gos; # replace DECLARE_HASHTABLE $members =~ s/DECLARE_HASHTABLE\s*\(([^,)]+),\s*([^,)]+)\)/unsigned long $1\[1 << (($2) - 1)\]/gos; # replace DECLARE_KFIFO $members =~ s/DECLARE_KFIFO\s*\(([^,)]+),\s*([^,)]+),\s*([^,)]+)\)/$2 \*$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*\(([^,)]+),\s*([^,)]+)\)/$2 \*$1/gos; my $declaration = $members; # Split nested struct/union elements as newer ones while ($members =~ m/(struct|union)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;/) { my $newmember; my $maintype = $1; my $ids = $4; my $content = $3; foreach my $id(split /,/, $ids) { $newmember .= "$maintype $id; "; $id =~ s/[:\[].*//; $id =~ s/^\s*\**(\S+)\s*/$1/; foreach my $arg (split /;/, $content) { next if ($arg =~ m/^\s*$/); if ($arg =~ m/^([^\(]+\(\*?\s*)([\w\.]*)(\s*\).*)/) { # pointer-to-function my $type = $1; my $name = $2; my $extra = $3; next if (!$name); if ($id =~ m/^\s*$/) { # anonymous struct/union $newmember .= "$type$name$extra; "; } else { $newmember .= "$type$id.$name$extra; "; } } else { my $type; my $names; $arg =~ s/^\s+//; $arg =~ s/\s+$//; # Handle bitmaps $arg =~ s/:\s*\d+\s*//g; # Handle arrays $arg =~ s/\[.*\]//g; # The type may have multiple words, # and multiple IDs can be defined, like: # const struct foo, *bar, foobar # So, we remove spaces when parsing the # names, in order to match just names # and commas for the names $arg =~ s/\s*,\s*/,/g; if ($arg =~ m/(.*)\s+([\S+,]+)/) { $type = $1; $names = $2; } else { $newmember .= "$arg; "; next; } foreach my $name (split /,/, $names) { $name =~ s/^\s*\**(\S+)\s*/$1/; next if (($name =~ m/^\s*$/)); if ($id =~ m/^\s*$/) { # anonymous struct/union $newmember .= "$type $name; "; } else { $newmember .= "$type $id.$name; "; } } } } } $members =~ s/(struct|union)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;/$newmember/; } # Ignore other nested elements, like enums $members =~ s/(\{[^\{\}]*\})//g; create_parameterlist($members, ';', $file, $declaration_name); check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual); # Adjust declaration for better display $declaration =~ s/([\{;])/$1\n/g; $declaration =~ s/\}\s+;/};/g; # Better handle inlined enums do {} while ($declaration =~ s/(enum\s+\{[^\}]+),([^\n])/$1,\n$2/); my @def_args = split /\n/, $declaration; my $level = 1; $declaration = ""; foreach my $clause (@def_args) { $clause =~ s/^\s+//; $clause =~ s/\s+$//; $clause =~ s/\s+/ /; next if (!$clause); $level-- if ($clause =~ m/(\})/ && $level > 1); if (!($clause =~ m/^\s*#/)) { $declaration .= "\t" x $level; } $declaration .= "\t" . $clause . "\n"; $level++ if ($clause =~ m/(\{)/ && !($clause =~m/\}/)); } output_declaration($declaration_name, 'struct', {'struct' => $declaration_name, 'module' => $modulename, 'definition' => $declaration, 'parameterlist' => \@parameterlist, 'parameterdescs' => \%parameterdescs, 'parametertypes' => \%parametertypes, 'sectionlist' => \@sectionlist, 'sections' => \%sections, 'purpose' => $declaration_purpose, 'type' => $decl_type }); } else { print STDERR "${file}:$.: error: Cannot parse struct or union!\n"; ++$errors; } } sub show_warnings($$) { my $functype = shift; my $name = shift; return 1 if ($output_selection == OUTPUT_ALL); if ($output_selection == OUTPUT_EXPORTED) { if (defined($function_table{$name})) { return 1; } else { return 0; } } if ($output_selection == OUTPUT_INTERNAL) { if (!($functype eq "function" && defined($function_table{$name}))) { return 1; } else { return 0; } } if ($output_selection == OUTPUT_INCLUDE) { if (defined($function_table{$name})) { return 1; } else { return 0; } } if ($output_selection == OUTPUT_EXCLUDE) { if (!defined($function_table{$name})) { return 1; } else { return 0; } } die("Please add the new output type at show_warnings()"); } sub dump_enum($$) { my $x = shift; my $file = shift; $x =~ s@/\*.*?\*/@@gos; # strip comments. # strip #define macros inside enums $x =~ s@#\s*((define|ifdef)\s+|endif)[^;]*;@@gos; if ($x =~ /enum\s+(\w*)\s*\{(.*)\}/) { $declaration_name = $1; my $members = $2; my %_members; $members =~ s/\s+$//; foreach my $arg (split ',', $members) { $arg =~ s/^\s*(\w+).*/$1/; push @parameterlist, $arg; if (!$parameterdescs{$arg}) { $parameterdescs{$arg} = $undescribed; if (show_warnings("enum", $declaration_name)) { print STDERR "${file}:$.: warning: Enum value '$arg' not described in enum '$declaration_name'\n"; } } $_members{$arg} = 1; } while (my ($k, $v) = each %parameterdescs) { if (!exists($_members{$k})) { if (show_warnings("enum", $declaration_name)) { print STDERR "${file}:$.: warning: Excess enum value '$k' description in '$declaration_name'\n"; } } } output_declaration($declaration_name, 'enum', {'enum' => $declaration_name, 'module' => $modulename, 'parameterlist' => \@parameterlist, 'parameterdescs' => \%parameterdescs, 'sectionlist' => \@sectionlist, 'sections' => \%sections, 'purpose' => $declaration_purpose }); } else { print STDERR "${file}:$.: error: Cannot parse enum!\n"; ++$errors; } } sub dump_typedef($$) { my $x = shift; my $file = shift; $x =~ s@/\*.*?\*/@@gos; # strip comments. # Parse function prototypes if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ || $x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) { # Function typedefs $return_type = $1; $declaration_name = $2; my $args = $3; create_parameterlist($args, ',', $file, $declaration_name); output_declaration($declaration_name, 'function', {'function' => $declaration_name, 'typedef' => 1, 'module' => $modulename, 'functiontype' => $return_type, 'parameterlist' => \@parameterlist, 'parameterdescs' => \%parameterdescs, 'parametertypes' => \%parametertypes, 'sectionlist' => \@sectionlist, 'sections' => \%sections, 'purpose' => $declaration_purpose }); return; } while (($x =~ /\(*.\)\s*;$/) || ($x =~ /\[*.\]\s*;$/)) { $x =~ s/\(*.\)\s*;$/;/; $x =~ s/\[*.\]\s*;$/;/; } if ($x =~ /typedef.*\s+(\w+)\s*;/) { $declaration_name = $1; output_declaration($declaration_name, 'typedef', {'typedef' => $declaration_name, 'module' => $modulename, 'sectionlist' => \@sectionlist, 'sections' => \%sections, 'purpose' => $declaration_purpose }); } else { print STDERR "${file}:$.: error: Cannot parse typedef!\n"; ++$errors; } } sub save_struct_actual($) { my $actual = shift; # strip all spaces from the actual param so that it looks like one string item $actual =~ s/\s*//g; $struct_actual = $struct_actual . $actual . " "; } sub create_parameterlist($$$$) { my $args = shift; my $splitter = shift; my $file = shift; my $declaration_name = shift; my $type; my $param; # temporarily replace commas inside function pointer definition while ($args =~ /(\([^\),]+),/) { $args =~ s/(\([^\),]+),/$1#/g; } foreach my $arg (split($splitter, $args)) { # strip comments $arg =~ s/\/\*.*\*\///; # strip leading/trailing spaces $arg =~ s/^\s*//; $arg =~ s/\s*$//; $arg =~ s/\s+/ /; if ($arg =~ /^#/) { # Treat preprocessor directive as a typeless variable just to fill # corresponding data structures "correctly". Catch it later in # output_* subs. push_parameter($arg, "", $file); } elsif ($arg =~ m/\(.+\)\s*\(/) { # pointer-to-function $arg =~ tr/#/,/; $arg =~ m/[^\(]+\(\*?\s*([\w\.]*)\s*\)/; $param = $1; $type = $arg; $type =~ s/([^\(]+\(\*?)\s*$param/$1/; save_struct_actual($param); push_parameter($param, $type, $file, $declaration_name); } elsif ($arg) { $arg =~ s/\s*:\s*/:/g; $arg =~ s/\s*\[/\[/g; my @args = split('\s*,\s*', $arg); if ($args[0] =~ m/\*/) { $args[0] =~ s/(\*+)\s*/ $1/; } my @first_arg; if ($args[0] =~ /^(.*\s+)(.*?\[.*\].*)$/) { shift @args; push(@first_arg, split('\s+', $1)); push(@first_arg, $2); } else { @first_arg = split('\s+', shift @args); } unshift(@args, pop @first_arg); $type = join " ", @first_arg; foreach $param (@args) { if ($param =~ m/^(\*+)\s*(.*)/) { save_struct_actual($2); push_parameter($2, "$type $1", $file, $declaration_name); } elsif ($param =~ m/(.*?):(\d+)/) { if ($type ne "") { # skip unnamed bit-fields save_struct_actual($1); push_parameter($1, "$type:$2", $file, $declaration_name) } } else { save_struct_actual($param); push_parameter($param, $type, $file, $declaration_name); } } } } } sub push_parameter($$$$) { my $param = shift; my $type = shift; my $file = shift; my $declaration_name = shift; if (($anon_struct_union == 1) && ($type eq "") && ($param eq "}")) { return; # ignore the ending }; from anon. struct/union } $anon_struct_union = 0; $param =~ s/[\[\)].*//; if ($type eq "" && $param =~ /\.\.\.$/) { if (!$param =~ /\w\.\.\.$/) { # handles unnamed variable parameters $param = "..."; } elsif ($param =~ /\w\.\.\.$/) { # for named variable parameters of the form `x...`, remove the dots $param =~ s/\.\.\.$//; } if (!defined $parameterdescs{$param} || $parameterdescs{$param} eq "") { $parameterdescs{$param} = "variable arguments"; } } elsif ($type eq "" && ($param eq "" or $param eq "void")) { $param="void"; $parameterdescs{void} = "no arguments"; } elsif ($type eq "" && ($param eq "struct" or $param eq "union")) # handle unnamed (anonymous) union or struct: { $type = $param; $param = "{unnamed_" . $param . "}"; $parameterdescs{$param} = "anonymous\n"; $anon_struct_union = 1; } # warn if parameter has no description # (but ignore ones starting with # as these are not parameters # but inline preprocessor statements); # Note: It will also ignore void params and unnamed structs/unions if (!defined $parameterdescs{$param} && $param !~ /^#/) { $parameterdescs{$param} = $undescribed; if (show_warnings($type, $declaration_name) && $param !~ /\./) { print STDERR "${file}:$.: warning: Function parameter or member '$param' not described in '$declaration_name'\n"; ++$warnings; } } # strip spaces from $param so that it is one continuous string # on @parameterlist; # this fixes a problem where check_sections() cannot find # a parameter like "addr[6 + 2]" because it actually appears # as "addr[6", "+", "2]" on the parameter list; # but it's better to maintain the param string unchanged for output, # so just weaken the string compare in check_sections() to ignore # "[blah" in a parameter string; ###$param =~ s/\s*//g; push @parameterlist, $param; $type =~ s/\s\s+/ /g; $parametertypes{$param} = $type; } sub check_sections($$$$$) { my ($file, $decl_name, $decl_type, $sectcheck, $prmscheck) = @_; my @sects = split ' ', $sectcheck; my @prms = split ' ', $prmscheck; my $err; my ($px, $sx); my $prm_clean; # strip trailing "[array size]" and/or beginning "*" foreach $sx (0 .. $#sects) { $err = 1; foreach $px (0 .. $#prms) { $prm_clean = $prms[$px]; $prm_clean =~ s/\[.*\]//; $prm_clean =~ s/__attribute__\s*\(\([a-z,_\*\s\(\)]*\)\)//i; # ignore array size in a parameter string; # however, the original param string may contain # spaces, e.g.: addr[6 + 2] # and this appears in @prms as "addr[6" since the # parameter list is split at spaces; # hence just ignore "[..." for the sections check; $prm_clean =~ s/\[.*//; ##$prm_clean =~ s/^\**//; if ($prm_clean eq $sects[$sx]) { $err = 0; last; } } if ($err) { if ($decl_type eq "function") { print STDERR "${file}:$.: warning: " . "Excess function parameter " . "'$sects[$sx]' " . "description in '$decl_name'\n"; ++$warnings; } } } } ## # Checks the section describing the return value of a function. sub check_return_section { my $file = shift; my $declaration_name = shift; my $return_type = shift; # Ignore an empty return type (It's a macro) # Ignore functions with a "void" return type. (But don't ignore "void *") if (($return_type eq "") || ($return_type =~ /void\s*\w*\s*$/)) { return; } if (!defined($sections{$section_return}) || $sections{$section_return} eq "") { print STDERR "${file}:$.: warning: " . "No description found for return value of " . "'$declaration_name'\n"; ++$warnings; } } ## # takes a function prototype and the name of the current file being # processed and spits out all the details stored in the global # arrays/hashes. sub dump_function($$) { my $prototype = shift; my $file = shift; my $noret = 0; $prototype =~ s/^static +//; $prototype =~ s/^extern +//; $prototype =~ s/^asmlinkage +//; $prototype =~ s/^inline +//; $prototype =~ s/^__inline__ +//; $prototype =~ s/^__inline +//; $prototype =~ s/^__always_inline +//; $prototype =~ s/^noinline +//; $prototype =~ s/__init +//; $prototype =~ s/__init_or_module +//; $prototype =~ s/__meminit +//; $prototype =~ s/__must_check +//; $prototype =~ s/__weak +//; $prototype =~ s/__sched +//; $prototype =~ s/__printf\s*\(\s*\d*\s*,\s*\d*\s*\) +//; my $define = $prototype =~ s/^#\s*define\s+//; #ak added $prototype =~ s/__attribute__\s*\(\( (?: [\w\s]++ # attribute name (?:\([^)]*+\))? # attribute arguments \s*+,? # optional comma at the end )+ \)\)\s+//x; # Yes, this truly is vile. We are looking for: # 1. Return type (may be nothing if we're looking at a macro) # 2. Function name # 3. Function parameters. # # All the while we have to watch out for function pointer parameters # (which IIRC is what the two sections are for), C types (these # regexps don't even start to express all the possibilities), and # so on. # # If you mess with these regexps, it's a good idea to check that # the following functions' documentation still comes out right: # - parport_register_device (function pointer parameters) # - atomic_set (macro) # - pci_match_device, __copy_to_user (long return type) if ($define && $prototype =~ m/^()([a-zA-Z0-9_~:]+)\s+/) { # This is an object-like macro, it has no return type and no parameter # list. # Function-like macros are not allowed to have spaces between # declaration_name and opening parenthesis (notice the \s+). $return_type = $1; $declaration_name = $2; $noret = 1; } elsif ($prototype =~ m/^()([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ || $prototype =~ m/^()([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s+\w+\s+\w+\s*\*+)\s*([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/ || $prototype =~ m/^(\w+\s+\w+\s*\*+\s*\w+\s*\*+\s*)\s*([a-zA-Z0-9_~:]+)\s*\(([^\{]*)\)/) { $return_type = $1; $declaration_name = $2; my $args = $3; create_parameterlist($args, ',', $file, $declaration_name); } else { print STDERR "${file}:$.: warning: cannot understand function prototype: '$prototype'\n"; return; } my $prms = join " ", @parameterlist; check_sections($file, $declaration_name, "function", $sectcheck, $prms); # This check emits a lot of warnings at the moment, because many # functions don't have a 'Return' doc section. So until the number # of warnings goes sufficiently down, the check is only performed in # verbose mode. # TODO: always perform the check. if ($verbose && !$noret) { check_return_section($file, $declaration_name, $return_type); } output_declaration($declaration_name, 'function', {'function' => $declaration_name, 'module' => $modulename, 'functiontype' => $return_type, 'parameterlist' => \@parameterlist, 'parameterdescs' => \%parameterdescs, 'parametertypes' => \%parametertypes, 'sectionlist' => \@sectionlist, 'sections' => \%sections, 'purpose' => $declaration_purpose }); } sub reset_state { $function = ""; %parameterdescs = (); %parametertypes = (); @parameterlist = (); %sections = (); @sectionlist = (); $sectcheck = ""; $struct_actual = ""; $prototype = ""; $state = STATE_NORMAL; $inline_doc_state = STATE_INLINE_NA; } sub tracepoint_munge($) { my $file = shift; my $tracepointname = 0; my $tracepointargs = 0; if ($prototype =~ m/TRACE_EVENT\((.*?),/) { $tracepointname = $1; } if ($prototype =~ m/DEFINE_SINGLE_EVENT\((.*?),/) { $tracepointname = $1; } if ($prototype =~ m/DEFINE_EVENT\((.*?),(.*?),/) { $tracepointname = $2; } $tracepointname =~ s/^\s+//; #strip leading whitespace if ($prototype =~ m/TP_PROTO\((.*?)\)/) { $tracepointargs = $1; } if (($tracepointname eq 0) || ($tracepointargs eq 0)) { print STDERR "${file}:$.: warning: Unrecognized tracepoint format: \n". "$prototype\n"; } else { $prototype = "static inline void trace_$tracepointname($tracepointargs)"; } } sub syscall_munge() { my $void = 0; $prototype =~ s@[\r\n]+@ @gos; # strip newlines/CR's ## if ($prototype =~ m/SYSCALL_DEFINE0\s*\(\s*(a-zA-Z0-9_)*\s*\)/) { if ($prototype =~ m/SYSCALL_DEFINE0/) { $void = 1; ## $prototype = "long sys_$1(void)"; } $prototype =~ s/SYSCALL_DEFINE.*\(/long sys_/; # fix return type & func name if ($prototype =~ m/long (sys_.*?),/) { $prototype =~ s/,/\(/; } elsif ($void) { $prototype =~ s/\)/\(void\)/; } # now delete all of the odd-number commas in $prototype # so that arg types & arg names don't have a comma between them my $count = 0; my $len = length($prototype); if ($void) { $len = 0; # skip the for-loop } for (my $ix = 0; $ix < $len; $ix++) { if (substr($prototype, $ix, 1) eq ',') { $count++; if ($count % 2 == 1) { substr($prototype, $ix, 1) = ' '; } } } } sub process_proto_function($$) { my $x = shift; my $file = shift; $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line if ($x =~ m#\s*/\*\s+MACDOC\s*#io || ($x =~ /^#/ && $x !~ /^#\s*define/)) { # do nothing } elsif ($x =~ /([^\{]*)/) { $prototype .= $1; } if (($x =~ /\{/) || ($x =~ /\#\s*define/) || ($x =~ /;/)) { $prototype =~ s@/\*.*?\*/@@gos; # strip comments. $prototype =~ s@[\r\n]+@ @gos; # strip newlines/cr's. $prototype =~ s@^\s+@@gos; # strip leading spaces if ($prototype =~ /SYSCALL_DEFINE/) { syscall_munge(); } if ($prototype =~ /TRACE_EVENT/ || $prototype =~ /DEFINE_EVENT/ || $prototype =~ /DEFINE_SINGLE_EVENT/) { tracepoint_munge($file); } dump_function($prototype, $file); reset_state(); } } sub process_proto_type($$) { my $x = shift; my $file = shift; $x =~ s@[\r\n]+@ @gos; # strip newlines/cr's. $x =~ s@^\s+@@gos; # strip leading spaces $x =~ s@\s+$@@gos; # strip trailing spaces $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line if ($x =~ /^#/) { # To distinguish preprocessor directive from regular declaration later. $x .= ";"; } while (1) { if ( $x =~ /([^\{\};]*)([\{\};])(.*)/ ) { if( length $prototype ) { $prototype .= " " } $prototype .= $1 . $2; ($2 eq '{') && $brcount++; ($2 eq '}') && $brcount--; if (($2 eq ';') && ($brcount == 0)) { dump_declaration($prototype, $file); reset_state(); last; } $x = $3; } else { $prototype .= $x; last; } } } sub map_filename($) { my $file; my ($orig_file) = @_; if (defined($ENV{'SRCTREE'})) { $file = "$ENV{'SRCTREE'}" . "/" . $orig_file; } else { $file = $orig_file; } if (defined($source_map{$file})) { $file = $source_map{$file}; } return $file; } sub process_export_file($) { my ($orig_file) = @_; my $file = map_filename($orig_file); if (!open(IN,"<$file")) { print STDERR "Error: Cannot open file $file\n"; ++$errors; return; } while () { if (/$export_symbol/) { $function_table{$2} = 1; } } close(IN); } # # Parsers for the various processing states. # # STATE_NORMAL: looking for the /** to begin everything. # sub process_normal() { if (/$doc_start/o) { $state = STATE_NAME; # next line is always the function name $in_doc_sect = 0; $declaration_start_line = $. + 1; } } # # STATE_NAME: Looking for the "name - description" line # sub process_name($$) { my $file = shift; my $identifier; my $descr; if (/$doc_block/o) { $state = STATE_DOCBLOCK; $contents = ""; $new_start_line = $. + 1; if ( $1 eq "" ) { $section = $section_intro; } else { $section = $1; } } elsif (/$doc_decl/o) { $identifier = $1; if (/\s*([\w\s]+?)(\(\))?\s*-/) { $identifier = $1; } $state = STATE_BODY; # if there's no @param blocks need to set up default section # here $contents = ""; $section = $section_default; $new_start_line = $. + 1; if (/-(.*)/) { # strip leading/trailing/multiple spaces $descr= $1; $descr =~ s/^\s*//; $descr =~ s/\s*$//; $descr =~ s/\s+/ /g; $declaration_purpose = $descr; $state = STATE_BODY_MAYBE; } else { $declaration_purpose = ""; } if (($declaration_purpose eq "") && $verbose) { print STDERR "${file}:$.: warning: missing initial short description on line:\n"; print STDERR $_; ++$warnings; } if ($identifier =~ m/^struct\b/) { $decl_type = 'struct'; } elsif ($identifier =~ m/^union\b/) { $decl_type = 'union'; } elsif ($identifier =~ m/^enum\b/) { $decl_type = 'enum'; } elsif ($identifier =~ m/^typedef\b/) { $decl_type = 'typedef'; } else { $decl_type = 'function'; } if ($verbose) { print STDERR "${file}:$.: info: Scanning doc for $identifier\n"; } } else { print STDERR "${file}:$.: warning: Cannot understand $_ on line $.", " - I thought it was a doc line\n"; ++$warnings; $state = STATE_NORMAL; } } # # STATE_BODY and STATE_BODY_MAYBE: the bulk of a kerneldoc comment. # sub process_body($$) { my $file = shift; # Until all named variable macro parameters are # documented using the bare name (`x`) rather than with # dots (`x...`), strip the dots: if ($section =~ /\w\.\.\.$/) { $section =~ s/\.\.\.$//; if ($verbose) { print STDERR "${file}:$.: warning: Variable macro arguments should be documented without dots\n"; ++$warnings; } } if (/$doc_sect/i) { # case insensitive for supported section names $newsection = $1; $newcontents = $2; # map the supported section names to the canonical names if ($newsection =~ m/^description$/i) { $newsection = $section_default; } elsif ($newsection =~ m/^context$/i) { $newsection = $section_context; } elsif ($newsection =~ m/^returns?$/i) { $newsection = $section_return; } elsif ($newsection =~ m/^\@return$/) { # special: @return is a section, not a param description $newsection = $section_return; } if (($contents ne "") && ($contents ne "\n")) { if (!$in_doc_sect && $verbose) { print STDERR "${file}:$.: warning: contents before sections\n"; ++$warnings; } dump_section($file, $section, $contents); $section = $section_default; } $in_doc_sect = 1; $state = STATE_BODY; $contents = $newcontents; $new_start_line = $.; while (substr($contents, 0, 1) eq " ") { $contents = substr($contents, 1); } if ($contents ne "") { $contents .= "\n"; } $section = $newsection; $leading_space = undef; } elsif (/$doc_end/) { if (($contents ne "") && ($contents ne "\n")) { dump_section($file, $section, $contents); $section = $section_default; $contents = ""; } # look for doc_com + + doc_end: if ($_ =~ m'\s*\*\s*[a-zA-Z_0-9:\.]+\*/') { print STDERR "${file}:$.: warning: suspicious ending line: $_"; ++$warnings; } $prototype = ""; $state = STATE_PROTO; $brcount = 0; } elsif (/$doc_content/) { # miguel-style comment kludge, look for blank lines after # @parameter line to signify start of description if ($1 eq "") { if ($section =~ m/^@/ || $section eq $section_context) { dump_section($file, $section, $contents); $section = $section_default; $contents = ""; $new_start_line = $.; } else { $contents .= "\n"; } $state = STATE_BODY; } elsif ($state == STATE_BODY_MAYBE) { # Continued declaration purpose chomp($declaration_purpose); $declaration_purpose .= " " . $1; $declaration_purpose =~ s/\s+/ /g; } else { my $cont = $1; if ($section =~ m/^@/ || $section eq $section_context) { if (!defined $leading_space) { if ($cont =~ m/^(\s+)/) { $leading_space = $1; } else { $leading_space = ""; } } $cont =~ s/^$leading_space//; } $contents .= $cont . "\n"; } } else { # i dont know - bad line? ignore. print STDERR "${file}:$.: warning: bad line: $_"; ++$warnings; } } # # STATE_PROTO: reading a function/whatever prototype. # sub process_proto($$) { my $file = shift; if (/$doc_inline_oneline/) { $section = $1; $contents = $2; if ($contents ne "") { $contents .= "\n"; dump_section($file, $section, $contents); $section = $section_default; $contents = ""; } } elsif (/$doc_inline_start/) { $state = STATE_INLINE; $inline_doc_state = STATE_INLINE_NAME; } elsif ($decl_type eq 'function') { process_proto_function($_, $file); } else { process_proto_type($_, $file); } } # # STATE_DOCBLOCK: within a DOC: block. # sub process_docblock($$) { my $file = shift; if (/$doc_end/) { dump_doc_section($file, $section, $contents); $section = $section_default; $contents = ""; $function = ""; %parameterdescs = (); %parametertypes = (); @parameterlist = (); %sections = (); @sectionlist = (); $prototype = ""; $state = STATE_NORMAL; } elsif (/$doc_content/) { if ( $1 eq "" ) { $contents .= $blankline; } else { $contents .= $1 . "\n"; } } } # # STATE_INLINE: docbook comments within a prototype. # sub process_inline($$) { my $file = shift; # First line (state 1) needs to be a @parameter if ($inline_doc_state == STATE_INLINE_NAME && /$doc_inline_sect/o) { $section = $1; $contents = $2; $new_start_line = $.; if ($contents ne "") { while (substr($contents, 0, 1) eq " ") { $contents = substr($contents, 1); } $contents .= "\n"; } $inline_doc_state = STATE_INLINE_TEXT; # Documentation block end */ } elsif (/$doc_inline_end/) { if (($contents ne "") && ($contents ne "\n")) { dump_section($file, $section, $contents); $section = $section_default; $contents = ""; } $state = STATE_PROTO; $inline_doc_state = STATE_INLINE_NA; # Regular text } elsif (/$doc_content/) { if ($inline_doc_state == STATE_INLINE_TEXT) { $contents .= $1 . "\n"; # nuke leading blank lines if ($contents =~ /^\s*$/) { $contents = ""; } } elsif ($inline_doc_state == STATE_INLINE_NAME) { $inline_doc_state = STATE_INLINE_ERROR; print STDERR "${file}:$.: warning: "; print STDERR "Incorrect use of kernel-doc format: $_"; ++$warnings; } } } sub process_file($) { my $file; my $initial_section_counter = $section_counter; my ($orig_file) = @_; $file = map_filename($orig_file); if (!open(IN,"<$file")) { print STDERR "Error: Cannot open file $file\n"; ++$errors; return; } $. = 1; $section_counter = 0; while () { while (s/\\\s*$//) { $_ .= ; } # Replace tabs by spaces while ($_ =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}; # Hand this line to the appropriate state handler if ($state == STATE_NORMAL) { process_normal(); } elsif ($state == STATE_NAME) { process_name($file, $_); } elsif ($state == STATE_BODY || $state == STATE_BODY_MAYBE) { process_body($file, $_); } elsif ($state == STATE_INLINE) { # scanning for inline parameters process_inline($file, $_); } elsif ($state == STATE_PROTO) { process_proto($file, $_); } elsif ($state == STATE_DOCBLOCK) { process_docblock($file, $_); } } # Make sure we got something interesting. if ($initial_section_counter == $section_counter && $ output_mode ne "none") { if ($output_selection == OUTPUT_INCLUDE) { print STDERR "${file}:1: warning: '$_' not found\n" for keys %function_table; } else { print STDERR "${file}:1: warning: no structured comments found\n"; } } } $kernelversion = get_kernel_version(); # generate a sequence of code that will splice in highlighting information # using the s// operator. for (my $k = 0; $k < @highlights; $k++) { my $pattern = $highlights[$k][0]; my $result = $highlights[$k][1]; # print STDERR "scanning pattern:$pattern, highlight:($result)\n"; $dohighlight .= "\$contents =~ s:$pattern:$result:gs;\n"; } # Read the file that maps relative names to absolute names for # separate source and object directories and for shadow trees. if (open(SOURCE_MAP, "<.tmp_filelist.txt")) { my ($relname, $absname); while() { chop(); ($relname, $absname) = (split())[0..1]; $relname =~ s:^/+::; $source_map{$relname} = $absname; } close(SOURCE_MAP); } if ($output_selection == OUTPUT_EXPORTED || $output_selection == OUTPUT_INTERNAL) { push(@export_file_list, @ARGV); foreach (@export_file_list) { chomp; process_export_file($_); } } foreach (@ARGV) { chomp; process_file($_); } if ($verbose && $errors) { print STDERR "$errors errors\n"; } if ($verbose && $warnings) { print STDERR "$warnings warnings\n"; } exit($output_mode eq "none" ? 0 : $errors);