X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/d65113e3415a7bf08be94ad231bf0828177c8925..8c869419331313c43ddda5b1eecd01939b013125:/autodoc.pl diff --git a/autodoc.pl b/autodoc.pl index 8c47ecf..6fea970 100644 --- a/autodoc.pl +++ b/autodoc.pl @@ -15,6 +15,13 @@ # # This script is normally invoked as part of 'make all', but is also # called from from regen.pl. +# +# '=head1' are the only headings looked for. If the next line after the +# heading begins with a word character, it is considered to be the first line +# of documentation that applies to the heading itself. That is, it is output +# immediately after the heading, before the first function, and not indented. +# The next input line that is a pod directive terminates this heading-level +# documentation. use strict; @@ -25,20 +32,59 @@ use strict; # implicit interpreter context argument. # -my %apidocs; -my %gutsdocs; -my %docfuncs; -my %seenfuncs; +my %docs; +my %funcflags; +my %macro = ( + ax => 1, + items => 1, + ix => 1, + svtype => 1, + ); +my %missing; my $curheader = "Unknown section"; sub autodoc ($$) { # parse a file and extract documentation info my($fh,$file) = @_; - my($in, $doc, $line); + my($in, $doc, $line, $header_doc); FUNC: while (defined($in = <$fh>)) { + if ($in =~ /^#\s*define\s+([A-Za-z_][A-Za-z_0-9]+)\(/ && + ($file ne 'embed.h' || $file ne 'proto.h')) { + $macro{$1} = $file; + next FUNC; + } if ($in=~ /^=head1 (.*)/) { $curheader = $1; + + # If the next line begins with a word char, then is the start of + # heading-level documentation. + if (defined($doc = <$fh>)) { + if ($doc !~ /^\w/) { + $in = $doc; + redo FUNC; + } + $header_doc = $doc; + $line++; + + # Continue getting the heading-level documentation until read + # in any pod directive (or as a fail-safe, find a closing + # comment to this pod in a C language file +HDR_DOC: + while (defined($doc = <$fh>)) { + if ($doc =~ /^=\w/) { + $in = $doc; + redo FUNC; + } + $line++; + + if ($doc =~ m:^\s*\*/$:) { + warn "=cut missing? $file:$line:$doc";; + last HDR_DOC; + } + $header_doc .= $doc; + } + } next FUNC; } $line++; @@ -58,18 +104,57 @@ DOC: $docs .= $doc; } $docs = "\n$docs" if $docs and $docs !~ /^\n/; + + # Check the consistency of the flags + my ($embed_where, $inline_where); + my ($embed_may_change, $inline_may_change); + + my $docref = delete $funcflags{$name}; + if ($docref and %$docref) { + $embed_where = $docref->{flags} =~ /A/ ? 'api' : 'guts'; + $embed_may_change = $docref->{flags} =~ /M/; + $flags .= 'D' if $docref->{flags} =~ /D/; + } else { + $missing{$name} = $file; + } if ($flags =~ /m/) { - if ($flags =~ /A/) { - $apidocs{$curheader}{$name} = [$flags, $docs, $ret, $file, @args]; + $inline_where = $flags =~ /A/ ? 'api' : 'guts'; + $inline_may_change = $flags =~ /x/; + + if (defined $embed_where && $inline_where ne $embed_where) { + warn "Function '$name' inconsistency: embed.fnc says $embed_where, Pod says $inline_where"; } - else { - $gutsdocs{$curheader}{$name} = [$flags, $docs, $ret, $file, @args]; + + if (defined $embed_may_change + && $inline_may_change ne $embed_may_change) { + my $message = "Function '$name' inconsistency: "; + if ($embed_may_change) { + $message .= "embed.fnc says 'may change', Pod does not"; + } else { + $message .= "Pod says 'may change', embed.fnc does not"; + } + warn $message; } + } elsif (!defined $embed_where) { + warn "Unable to place $name!\n"; + next; + } else { + $inline_where = $embed_where; + $flags .= 'x' if $embed_may_change; + @args = @{$docref->{args}}; + $ret = $docref->{retval}; } - else { - $docfuncs{$name} = [$flags, $docs, $ret, $file, $curheader, @args]; - } - $seenfuncs{$name} = 1; + + $docs{$inline_where}{$curheader}{$name} + = [$flags, $docs, $ret, $file, @args]; + + # Create a special entry with an empty-string name for the + # heading-level documentation. + if (defined $header_doc) { + $docs{$inline_where}{$curheader}{""} = $header_doc; + undef $header_doc; + } + if (defined $doc) { if ($doc =~ /^=(?:for|head)/) { $in = $doc; @@ -87,10 +172,19 @@ sub docout ($$$) { # output the docs for one function my($flags, $docs, $ret, $file, @args) = @$docref; $name =~ s/\s*$//; - $docs .= "NOTE: this function is experimental and may change or be + if ($flags =~ /D/) { + $docs = "\n\nDEPRECATED! It is planned to remove this function from a +future release of Perl. Do not use it for new code; remove it from +existing code.\n\n$docs"; + } + else { + $docs .= "NOTE: this function is experimental and may change or be removed without notice.\n\n" if $flags =~ /x/; + } $docs .= "NOTE: the perl_ form of this function is deprecated.\n\n" if $flags =~ /p/; + $docs .= "NOTE: this function must be explicitly called as Perl_$name with an aTHX_ parameter.\n\n" + if $flags =~ /o/; print $fh "=item $name\nX<$name>\n$docs"; @@ -101,15 +195,55 @@ removed without notice.\n\n" if $flags =~ /x/; } elsif ($flags =~ /n/) { # no args print $fh "\t$ret\t$name\n\n"; } else { # full usage - print $fh "\t$ret\t$name"; - print $fh "(" . join(", ", @args) . ")"; - print $fh "\n\n"; + my $p = $flags =~ /o/; # no #define foo Perl_foo + my $n = "Perl_"x$p . $name; + my $large_ret = length $ret > 7; + my $indent_size = 7+8 # nroff: 7 under =head + 8 under =item + +8+($large_ret ? 1 + length $ret : 8) + +length($n) + 1; + my $indent; + print $fh "\t$ret" . ($large_ret ? ' ' : "\t") . "$n("; + my $long_args; + for (@args) { + if ($indent_size + 2 + length > 79) { + $long_args=1; + $indent_size -= length($n) - 3; + last; + } + } + my $args = ''; + if ($p) { + $args = @args ? "pTHX_ " : "pTHX"; + if ($long_args) { print $fh $args; $args = '' } + } + $long_args and print $fh "\n"; + my $first = !$long_args; + while () { + if (!@args or + length $args + && $indent_size + 3 + length($args[0]) + length $args > 79 + ) { + print $fh + $first ? '' : ( + $indent //= + "\t".($large_ret ? " " x (1+length $ret) : "\t") + ." "x($long_args ? 4 : 1 + length $n) + ), + $args, (","x($args ne 'pTHX_ ') . "\n")x!!@args; + $args = $first = ''; + } + @args or last; + $args .= ", "x!!(length $args && $args ne 'pTHX_ ') + . shift @args; + } + if ($long_args) { print $fh "\n", substr $indent, 0, -4 } + print $fh ")\n\n"; } print $fh "=for hackers\nFound in file $file\n\n"; } sub output { - my ($podname, $header, $dochash, $footer) = @_; + my ($podname, $header, $dochash, $missing, $footer) = @_; my $filename = "pod/$podname.pod"; open my $fh, '>', $filename or die "Can't open $filename: $!"; @@ -126,7 +260,16 @@ _EOH_ # case insensitive sort, with fallback for determinacy for $key (sort { uc($a) cmp uc($b) || $a cmp $b } keys %$dochash) { my $section = $dochash->{$key}; - print $fh "\n=head1 $key\n\n=over 8\n\n"; + print $fh "\n=head1 $key\n\n"; + + # Output any heading-level documentation and delete so won't get in + # the way later + if (exists $section->{""}) { + print $fh $section->{""} . "\n"; + delete $section->{""}; + } + print $fh "=over 8\n\n"; + # Again, fallback for determinacy for my $key (sort { uc($a) cmp uc($b) || $a cmp $b } keys %$section) { docout($fh, $key, $section->{$key}); @@ -134,7 +277,37 @@ _EOH_ print $fh "\n=back\n"; } - print $fh $footer, <<'_EOF_'; + if (@$missing) { + print $fh "\n=head1 Undocumented functions\n\n"; + print $fh $podname eq 'perlapi' ? <<'_EOB_' : <<'_EOB_'; +The following functions have been flagged as part of the public API, +but are currently undocumented. Use them at your own risk, as the +interfaces are subject to change. Functions that are not listed in this +document are not intended for public use, and should NOT be used under any +circumstances. + +If you use one of the undocumented functions below, you may wish to consider +creating and submitting documentation for it. If your patch is accepted, this +will indicate that the interface is stable (unless it is explicitly marked +otherwise). + +=over + +_EOB_ +The following functions are currently undocumented. If you use one of +them, you may wish to consider creating and submitting documentation for +it. + +=over + +_EOB_ + for my $missing (sort @$missing) { + print $fh "=item $missing\nX<$missing>\n\n"; + } + print $fh "=back\n\n"; +} + +print $fh $footer, <<'_EOF_'; =cut ex: set ro: @@ -149,27 +322,8 @@ if (@ARGV) { or die "Couldn't chdir to '$workdir': $!"; } -my $file; -# glob() picks up docs from extra .c or .h files that may be in unclean -# development trees. -my $MANIFEST = do { - local ($/, *FH); - open FH, "MANIFEST" or die "Can't open MANIFEST: $!"; - ; -}; - -for $file (($MANIFEST =~ /^(\S+\.c)\t/gm), ($MANIFEST =~ /^(\S+\.h)\t/gm)) { - open F, "< $file" or die "Cannot open $file for docs: $!\n"; - $curheader = "Functions in file $file\n"; - autodoc(\*F,$file); - close F or die "Error closing $file: $!\n"; -} - open IN, "embed.fnc" or die $!; -# walk table providing an array of components in each line to -# subroutine, printing the result - while () { chomp; next if /^:/; @@ -182,37 +336,56 @@ while () { my ($flags, $retval, $func, @args) = split /\s*\|\s*/, $_; - next unless $flags =~ /d/; next unless $func; s/\b(NN|NULLOK)\b\s+//g for @args; $func =~ s/\t//g; # clean up fields from embed.pl $retval =~ s/\t//; - my $docref = delete $docfuncs{$func}; - if ($docref and @$docref) { - if ($flags =~ /A/) { - $docref->[0].="x" if $flags =~ /M/; - $apidocs{$docref->[4]}{$func} = - [$docref->[0] . 'A', $docref->[1], $retval, $docref->[3], - @args]; - } else { - $gutsdocs{$docref->[4]}{$func} = - [$docref->[0], $docref->[1], $retval, $docref->[3], @args]; - } - } - else { - warn "no docs for $func\n" unless $seenfuncs{$func}; - } + $funcflags{$func} = { + flags => $flags, + retval => $retval, + args => \@args, + }; } -for (sort keys %docfuncs) { - # Have you used a full for apidoc or just a func name? - # Have you used Ap instead of Am in the for apidoc? - warn "Unable to place $_!\n"; +my $file; +# glob() picks up docs from extra .c or .h files that may be in unclean +# development trees. +my $MANIFEST = do { + local ($/, *FH); + open FH, "MANIFEST" or die "Can't open MANIFEST: $!"; + ; +}; + +for $file (($MANIFEST =~ /^(\S+\.c)\t/gm), ($MANIFEST =~ /^(\S+\.h)\t/gm)) { + open F, "< $file" or die "Cannot open $file for docs: $!\n"; + $curheader = "Functions in file $file\n"; + autodoc(\*F,$file); + close F or die "Error closing $file: $!\n"; } -output('perlapi', <<'_EOB_', \%apidocs, <<'_EOE_'); +for (sort keys %funcflags) { + next unless $funcflags{$_}{flags} =~ /d/; + warn "no docs for $_\n" +} + +foreach (sort keys %missing) { + next if $macro{$_}; + # Heuristics for known not-a-function macros: + next if /^[A-Z]/; + next if /^dj?[A-Z]/; + + warn "Function '$_', documented in $missing{$_}, not listed in embed.fnc"; +} + +# walk table providing an array of components in each line to +# subroutine, printing the result + +# List of funcs in the public API that aren't also marked as experimental nor +# deprecated. +my @missing_api = grep $funcflags{$_}{flags} =~ /A/ && $funcflags{$_}{flags} !~ /[MD]/ && !$docs{api}{$_}, keys %funcflags; +output('perlapi', <<'_EOB_', $docs{api}, \@missing_api, <<'_EOE_'); =head1 NAME perlapi - autogenerated documentation for the perl public API @@ -221,11 +394,13 @@ perlapi - autogenerated documentation for the perl public API X X X This file contains the documentation of the perl public API generated by -embed.pl, specifically a listing of functions, macros, flags, and variables -that may be used by extension writers. The interfaces of any functions that -are not listed here are subject to change without notice. For this reason, -blindly using functions listed in proto.h is to be avoided when writing -extensions. +F, specifically a listing of functions, macros, flags, and variables +that may be used by extension writers. L +is a list of functions which have yet to be documented. The interfaces of +those are subject to change without notice. Any functions not listed here are +not part of the public API, and should not be used by extension writers at +all. For these reasons, blindly using functions listed in proto.h is to be +avoided when writing extensions. Note that all Perl API global variables must be referenced with the C prefix. Some macros are provided for compatibility with the older, @@ -249,11 +424,6 @@ But the ordinals of characters differ between ASCII, EBCDIC, and the UTF- encodings, and a string encoded in UTF-EBCDIC may occupy more bytes than in UTF-8. -Also, on some EBCDIC machines, functions that are documented as operating on -US-ASCII (or Basic Latin in Unicode terminology) may in fact operate on all -256 characters in the EBCDIC range, not just the subset corresponding to -US-ASCII. - The listing below is alphabetical, case insensitive. _EOB_ @@ -274,11 +444,15 @@ Updated to be autogenerated from comments in the source by Benjamin Stuhl. =head1 SEE ALSO -perlguts(1), perlxs(1), perlxstut(1), perlintern(1) +L, L, L, L _EOE_ -output('perlintern', <<'END', \%gutsdocs, <<'END'); +# List of non-static internal functions +my @missing_guts = + grep $funcflags{$_}{flags} !~ /[As]/ && !$docs{guts}{$_}, keys %funcflags; + +output('perlintern', <<'END', $docs{guts}, \@missing_guts, <<'END'); =head1 NAME perlintern - autogenerated documentation of purely B @@ -302,6 +476,6 @@ document their functions. =head1 SEE ALSO -perlguts(1), perlapi(1) +L, L END