#############################################################################
# Pod/Checker.pm -- check pod documents for syntax errors
#
-# Copyright (C) 1994-1999 by Bradford Appleton. All rights reserved.
+# Copyright (C) 1994-2000 by Bradford Appleton. All rights reserved.
# This file is part of "PodParser". PodParser is free software;
# you can redistribute it and/or modify it under the same terms
# as Perl itself.
package Pod::Checker;
use vars qw($VERSION);
-$VERSION = 1.090; ## Current version of this package
-require 5.004; ## requires this Perl version or later
+$VERSION = "1.43_01"; ## Current version of this package
+require 5.005; ## requires this Perl version or later
+
+use Pod::ParseUtils; ## for hyperlinks and lists
=head1 NAME
$syntax_okay = podchecker($filepath, $outputpath, %options);
+ my $checker = new Pod::Checker %options;
+ $checker->parse_from_file($filepath, \*STDERR);
+
=head1 OPTIONS/ARGUMENTS
C<$filepath> is the input POD to read and C<$outputpath> is
where to write POD syntax error messages. Either argument may be a scalar
-indcating a file-path, or else a reference to an open filehandle.
+indicating a file-path, or else a reference to an open filehandle.
If unspecified, the input-file it defaults to C<\*STDIN>, and
the output-file defaults to C<\*STDERR>.
-=head2 Options
+=head2 podchecker()
+
+This function can take a hash of options:
=over 4
=item B<-warnings> =E<gt> I<val>
-Turn warnings on/off. See L<"Warnings">.
+Turn warnings on/off. I<val> is usually 1 for on, but higher values
+trigger additional warnings. See L<"Warnings">.
=back
B<podchecker> will perform syntax checking of Perl5 POD format documentation.
-I<NOTE THAT THIS MODULE IS CURRENTLY IN THE INITIAL DEVELOPMENT STAGE!>
-As of this writing, all it does is check for unknown '=xxxx' commands,
-unknown 'X<...>' interior-sequences, and unterminated interior sequences.
-
-It is hoped that curious/ambitious user will help flesh out and add the
-additional features they wish to see in B<Pod::Checker> and B<podchecker>.
+Curious/ambitious users are welcome to propose additional features they wish
+to see in B<Pod::Checker> and B<podchecker> and verify that the checks are
+consistent with L<perlpod>.
-The following additional checks are preformed:
+The following checks are currently performed:
=over 4
=item *
-Check for proper balancing of C<=begin> and C<=end>.
+Unknown '=xxxx' commands, unknown 'XE<lt>...E<gt>' interior-sequences,
+and unterminated interior sequences.
+
+=item *
+
+Check for proper balancing of C<=begin> and C<=end>. The contents of such
+a block are generally ignored, i.e. no syntax checks are performed.
=item *
=item *
-Check for same nested interior-sequences (e.g. C<LE<lt>...LE<lt>...E<gt>...E<gt>>).
+Check for same nested interior-sequences (e.g.
+C<LE<lt>...LE<lt>...E<gt>...E<gt>>).
=item *
-Check for malformed entities.
+Check for malformed or non-existing entities C<EE<lt>...E<gt>>.
=item *
-Check for correct syntax of hyperlinks C<LE<lt>E<gt>>. See L<perlpod> for
-details.
+Check for correct syntax of hyperlinks C<LE<lt>...E<gt>>. See L<perlpod>
+for details.
=item *
-Check for unresolved document-internal links.
+Check for unresolved document-internal links. This check may also reveal
+misspelled links that seem to be internal links but should be links
+to something else.
+
+=back
+
+=head1 DIAGNOSTICS
+
+=head2 Errors
+
+=over 4
+
+=item * empty =headn
+
+A heading (C<=head1> or C<=head2>) without any text? That ain't no
+heading!
+
+=item * =over on line I<N> without closing =back
+
+The C<=over> command does not have a corresponding C<=back> before the
+next heading (C<=head1> or C<=head2>) or the end of the file.
+
+=item * =item without previous =over
+
+=item * =back without previous =over
+
+An C<=item> or C<=back> command has been found outside a
+C<=over>/C<=back> block.
+
+=item * No argument for =begin
+
+A C<=begin> command was found that is not followed by the formatter
+specification.
+
+=item * =end without =begin
+
+A standalone C<=end> command was found.
+
+=item * Nested =begin's
+
+There were at least two consecutive C<=begin> commands without
+the corresponding C<=end>. Only one C<=begin> may be active at
+a time.
+
+=item * =for without formatter specification
+
+There is no specification of the formatter after the C<=for> command.
+
+=item * unresolved internal link I<NAME>
+
+The given link to I<NAME> does not have a matching node in the current
+POD. This also happened when a single word node name is not enclosed in
+C<"">.
+
+=item * Unknown command "I<CMD>"
+
+An invalid POD command has been found. Valid are C<=head1>, C<=head2>,
+C<=head3>, C<=head4>, C<=over>, C<=item>, C<=back>, C<=begin>, C<=end>,
+C<=for>, C<=pod>, C<=cut>
+
+=item * Unknown interior-sequence "I<SEQ>"
+
+An invalid markup command has been encountered. Valid are:
+C<BE<lt>E<gt>>, C<CE<lt>E<gt>>, C<EE<lt>E<gt>>, C<FE<lt>E<gt>>,
+C<IE<lt>E<gt>>, C<LE<lt>E<gt>>, C<SE<lt>E<gt>>, C<XE<lt>E<gt>>,
+C<ZE<lt>E<gt>>
+
+=item * nested commands I<CMD>E<lt>...I<CMD>E<lt>...E<gt>...E<gt>
+
+Two nested identical markup commands have been found. Generally this
+does not make sense.
+
+=item * garbled entity I<STRING>
+
+The I<STRING> found cannot be interpreted as a character entity.
+
+=item * Entity number out of range
+
+An entity specified by number (dec, hex, oct) is out of range (1-255).
+
+=item * malformed link LE<lt>E<gt>
+
+The link found cannot be parsed because it does not conform to the
+syntax described in L<perlpod>.
+
+=item * nonempty ZE<lt>E<gt>
+
+The C<ZE<lt>E<gt>> sequence is supposed to be empty.
+
+=item * empty XE<lt>E<gt>
+
+The index entry specified contains nothing but whitespace.
+
+=item * Spurious text after =pod / =cut
+
+The commands C<=pod> and C<=cut> do not take any arguments.
+
+=item * Spurious character(s) after =back
+
+The C<=back> command does not take any arguments.
=back
=head2 Warnings
-The following warnings are printed. These may not necessarily cause trouble,
-but indicate mediocre style.
+These may not necessarily cause trouble, but indicate mediocre style.
=over 4
-=item *
+=item * multiple occurrence of link target I<name>
-Spurious characters after C<=back> and C<=end>.
+The POD file has some C<=item> and/or C<=head> commands that have
+the same text. Potential hyperlinks to such a text cannot be unique then.
+This warning is printed only with warning level greater than one.
-=item *
+=item * line containing nothing but whitespace in paragraph
-Unescaped C<E<lt>> and C<E<gt>> in the text.
+There is some whitespace on a seemingly empty line. POD is very sensitive
+to such things, so this is flagged. B<vi> users switch on the B<list>
+option to avoid this problem.
-=item *
+=begin _disabled_
-Missing arguments for C<=begin> and C<=over>.
+=item * file does not start with =head
-=item *
+The file starts with a different POD directive than head.
+This is most probably something you do not want.
-Empty C<=over> / C<=back> list.
+=end _disabled_
-=item *
+=item * previous =item has no contents
+
+There is a list C<=item> right above the flagged line that has no
+text contents. You probably want to delete empty items.
+
+=item * preceding non-item paragraph(s)
+
+A list introduced by C<=over> starts with a text or verbatim paragraph,
+but continues with C<=item>s. Move the non-item paragraph out of the
+C<=over>/C<=back> block.
+
+=item * =item type mismatch (I<one> vs. I<two>)
+
+A list started with e.g. a bullet-like C<=item> and continued with a
+numbered one. This is obviously inconsistent. For most translators the
+type of the I<first> C<=item> determines the type of the list.
+
+=item * I<N> unescaped C<E<lt>E<gt>> in paragraph
+
+Angle brackets not written as C<E<lt>ltE<gt>> and C<E<lt>gtE<gt>>
+can potentially cause errors as they could be misinterpreted as
+markup commands. This is only printed when the -warnings level is
+greater than 1.
+
+=item * Unknown entity
+
+A character entity was found that does not belong to the standard
+ISO set or the POD specials C<verbar> and C<sol>.
-Hyperlinks: leading/trailing whitespace, brackets C<()> in the page name.
+=item * No items in =over
+
+The list opened with C<=over> does not contain any items.
+
+=item * No argument for =item
+
+C<=item> without any parameters is deprecated. It should either be followed
+by C<*> to indicate an unordered list, by a number (optionally followed
+by a dot) to indicate an ordered (numbered) list or simple text for a
+definition list.
+
+=item * empty section in previous paragraph
+
+The previous section (introduced by a C<=head> command) does not contain
+any text. This usually indicates that something is missing. Note: A
+C<=head1> followed immediately by C<=head2> does not trigger this warning.
+
+=item * Verbatim paragraph in NAME section
+
+The NAME section (C<=head1 NAME>) should consist of a single paragraph
+with the script/module name, followed by a dash `-' and a very short
+description of what the thing is good for.
+
+=item * =headI<n> without preceding higher level
+
+For example if there is a C<=head2> in the POD file prior to a
+C<=head1>.
=back
-=head1 DIAGNOSTICS
+=head2 Hyperlinks
+
+There are some warnings with respect to malformed hyperlinks:
+
+=over 4
-I<[T.B.D.]>
+=item * ignoring leading/trailing whitespace in link
+
+There is whitespace at the beginning or the end of the contents of
+LE<lt>...E<gt>.
+
+=item * (section) in '$page' deprecated
+
+There is a section detected in the page name of LE<lt>...E<gt>, e.g.
+C<LE<lt>passwd(2)E<gt>>. POD hyperlinks may point to POD documents only.
+Please write C<CE<lt>passwd(2)E<gt>> instead. Some formatters are able
+to expand this to appropriate code. For links to (builtin) functions,
+please say C<LE<lt>perlfunc/mkdirE<gt>>, without ().
+
+=item * alternative text/node '%s' contains non-escaped | or /
+
+The characters C<|> and C</> are special in the LE<lt>...E<gt> context.
+Although the hyperlink parser does its best to determine which "/" is
+text and which is a delimiter in case of doubt, one ought to escape
+these literal characters like this:
+
+ / E<sol>
+ | E<verbar>
+
+=back
=head1 RETURN VALUE
=head1 EXAMPLES
-I<[T.B.D.]>
+See L</SYNOPSIS>
-=head1 AUTHOR
+=head1 INTERFACE
-Brad Appleton E<lt>bradapp@enteract.comE<gt> (initial version),
-Marek Rouchal E<lt>marek@saftsack.fs.uni-bayreuth.deE<gt>
+While checking, this module collects document properties, e.g. the nodes
+for hyperlinks (C<=headX>, C<=item>) and index entries (C<XE<lt>E<gt>>).
+POD translators can use this feature to syntax-check and get the nodes in
+a first pass before actually starting to convert. This is expensive in terms
+of execution time, but allows for very robust conversions.
-Based on code for B<Pod::Text::pod2text()> written by
-Tom Christiansen E<lt>tchrist@mox.perl.comE<gt>
+Since PodParser-1.24 the B<Pod::Checker> module uses only the B<poderror>
+method to print errors and warnings. The summary output (e.g.
+"Pod syntax OK") has been dropped from the module and has been included in
+B<podchecker> (the script). This allows users of B<Pod::Checker> to
+control completely the output behavior. Users of B<podchecker> (the script)
+get the well-known behavior.
=cut
'cut' => 1,
'head1' => 1,
'head2' => 1,
+ 'head3' => 1,
+ 'head4' => 1,
'over' => 1,
'back' => 1,
'item' => 1,
'for' => 1,
'begin' => 1,
'end' => 1,
+ 'encoding' => '1',
);
my %VALID_SEQUENCES = (
'E' => 1,
);
+# stolen from HTML::Entities
+my %ENTITIES = (
+ # Some normal chars that have special meaning in SGML context
+ amp => '&', # ampersand
+'gt' => '>', # greater than
+'lt' => '<', # less than
+ quot => '"', # double quote
+
+ # PUBLIC ISO 8879-1986//ENTITIES Added Latin 1//EN//HTML
+ AElig => 'Æ', # capital AE diphthong (ligature)
+ Aacute => 'Á', # capital A, acute accent
+ Acirc => 'Â', # capital A, circumflex accent
+ Agrave => 'À', # capital A, grave accent
+ Aring => 'Å', # capital A, ring
+ Atilde => 'Ã', # capital A, tilde
+ Auml => 'Ä', # capital A, dieresis or umlaut mark
+ Ccedil => 'Ç', # capital C, cedilla
+ ETH => 'Ð', # capital Eth, Icelandic
+ Eacute => 'É', # capital E, acute accent
+ Ecirc => 'Ê', # capital E, circumflex accent
+ Egrave => 'È', # capital E, grave accent
+ Euml => 'Ë', # capital E, dieresis or umlaut mark
+ Iacute => 'Í', # capital I, acute accent
+ Icirc => 'Î', # capital I, circumflex accent
+ Igrave => 'Ì', # capital I, grave accent
+ Iuml => 'Ï', # capital I, dieresis or umlaut mark
+ Ntilde => 'Ñ', # capital N, tilde
+ Oacute => 'Ó', # capital O, acute accent
+ Ocirc => 'Ô', # capital O, circumflex accent
+ Ograve => 'Ò', # capital O, grave accent
+ Oslash => 'Ø', # capital O, slash
+ Otilde => 'Õ', # capital O, tilde
+ Ouml => 'Ö', # capital O, dieresis or umlaut mark
+ THORN => 'Þ', # capital THORN, Icelandic
+ Uacute => 'Ú', # capital U, acute accent
+ Ucirc => 'Û', # capital U, circumflex accent
+ Ugrave => 'Ù', # capital U, grave accent
+ Uuml => 'Ü', # capital U, dieresis or umlaut mark
+ Yacute => 'Ý', # capital Y, acute accent
+ aacute => 'á', # small a, acute accent
+ acirc => 'â', # small a, circumflex accent
+ aelig => 'æ', # small ae diphthong (ligature)
+ agrave => 'à', # small a, grave accent
+ aring => 'å', # small a, ring
+ atilde => 'ã', # small a, tilde
+ auml => 'ä', # small a, dieresis or umlaut mark
+ ccedil => 'ç', # small c, cedilla
+ eacute => 'é', # small e, acute accent
+ ecirc => 'ê', # small e, circumflex accent
+ egrave => 'è', # small e, grave accent
+ eth => 'ð', # small eth, Icelandic
+ euml => 'ë', # small e, dieresis or umlaut mark
+ iacute => 'í', # small i, acute accent
+ icirc => 'î', # small i, circumflex accent
+ igrave => 'ì', # small i, grave accent
+ iuml => 'ï', # small i, dieresis or umlaut mark
+ ntilde => 'ñ', # small n, tilde
+ oacute => 'ó', # small o, acute accent
+ ocirc => 'ô', # small o, circumflex accent
+ ograve => 'ò', # small o, grave accent
+ oslash => 'ø', # small o, slash
+ otilde => 'õ', # small o, tilde
+ ouml => 'ö', # small o, dieresis or umlaut mark
+ szlig => 'ß', # small sharp s, German (sz ligature)
+ thorn => 'þ', # small thorn, Icelandic
+ uacute => 'ú', # small u, acute accent
+ ucirc => 'û', # small u, circumflex accent
+ ugrave => 'ù', # small u, grave accent
+ uuml => 'ü', # small u, dieresis or umlaut mark
+ yacute => 'ý', # small y, acute accent
+ yuml => 'ÿ', # small y, dieresis or umlaut mark
+
+ # Some extra Latin 1 chars that are listed in the HTML3.2 draft (21-May-96)
+ copy => '©', # copyright sign
+ reg => '®', # registered sign
+ nbsp => "\240", # non breaking space
+
+ # Additional ISO-8859/1 entities listed in rfc1866 (section 14)
+ iexcl => '¡',
+ cent => '¢',
+ pound => '£',
+ curren => '¤',
+ yen => '¥',
+ brvbar => '¦',
+ sect => '§',
+ uml => '¨',
+ ordf => 'ª',
+ laquo => '«',
+'not' => '¬', # not is a keyword in perl
+ shy => '',
+ macr => '¯',
+ deg => '°',
+ plusmn => '±',
+ sup1 => '¹',
+ sup2 => '²',
+ sup3 => '³',
+ acute => '´',
+ micro => 'µ',
+ para => '¶',
+ middot => '·',
+ cedil => '¸',
+ ordm => 'º',
+ raquo => '»',
+ frac14 => '¼',
+ frac12 => '½',
+ frac34 => '¾',
+ iquest => '¿',
+'times' => '×', # times is a keyword in perl
+ divide => '÷',
+
+# some POD special entities
+ verbar => '|',
+ sol => '/'
+);
+
##---------------------------------------------------------------------------
##---------------------------------
## Now check the pod document for errors
$checker->parse_from_file($infile, $outfile);
-
+
## Return the number of errors found
return $checker->num_errors();
}
## Method definitions begin here
##-------------------------------
-sub new {
- my $this = shift;
- my $class = ref($this) || $this;
- my %params = @_;
- my $self = {%params};
- bless $self, $class;
- $self->initialize();
- return $self;
-}
+##################################
+
+=over 4
+
+=item C<Pod::Checker-E<gt>new( %options )>
+
+Return a reference to a new Pod::Checker object that inherits from
+Pod::Parser and is used for calling the required methods later. The
+following options are recognized:
+
+C<-warnings =E<gt> num>
+ Print warnings if C<num> is true. The higher the value of C<num>,
+the more warnings are printed. Currently there are only levels 1 and 2.
+
+C<-quiet =E<gt> num>
+ If C<num> is true, do not print any errors/warnings. This is useful
+when Pod::Checker is used to munge POD code into plain text from within
+POD formatters.
+
+=cut
+
+## sub new {
+## my $this = shift;
+## my $class = ref($this) || $this;
+## my %params = @_;
+## my $self = {%params};
+## bless $self, $class;
+## $self->initialize();
+## return $self;
+## }
sub initialize {
my $self = shift;
## Initialize number of errors, and setup an error function to
## increment this number and then print to the designated output.
$self->{_NUM_ERRORS} = 0;
- $self->errorsub('poderror');
+ $self->{_NUM_WARNINGS} = 0;
+ $self->{-quiet} ||= 0;
+ # set the error handling subroutine
+ $self->errorsub($self->{-quiet} ? sub { 1; } : 'poderror');
$self->{_commands} = 0; # total number of POD commands encountered
$self->{_list_stack} = []; # stack for nested lists
$self->{_have_begin} = ''; # stores =begin
$self->{_links} = []; # stack for internal hyperlinks
$self->{_nodes} = []; # stack for =head/=item nodes
+ $self->{_index} = []; # text in X<>
+ # print warnings?
$self->{-warnings} = 1 unless(defined $self->{-warnings});
+ $self->{_current_head1} = ''; # the current =head1 block
+ $self->parseopts(-process_cut_cmd => 1, -warnings => $self->{-warnings});
}
-## Invoked as $self->poderror( @args ), or $self->poderror( {%opts}, @args )
+##################################
+
+=item C<$checker-E<gt>poderror( @args )>
+
+=item C<$checker-E<gt>poderror( {%opts}, @args )>
+
+Internal method for printing errors and warnings. If no options are
+given, simply prints "@_". The following options are recognized and used
+to form the output:
+
+ -msg
+
+A message to print prior to C<@args>.
+
+ -line
+
+The line number the error occurred in.
+
+ -file
+
+The file (name) the error occurred in.
+
+ -severity
+
+The error level, should be 'WARNING' or 'ERROR'.
+
+=cut
+
+# Invoked as $self->poderror( @args ), or $self->poderror( {%opts}, @args )
sub poderror {
my $self = shift;
my %opts = (ref $_[0]) ? %{shift()} : ();
chomp( my $msg = ($opts{-msg} || "")."@_" );
my $line = (exists $opts{-line}) ? " at line $opts{-line}" : "";
my $file = (exists $opts{-file}) ? " in file $opts{-file}" : "";
+ unless (exists $opts{-severity}) {
+ ## See if can find severity in message prefix
+ $opts{-severity} = $1 if ( $msg =~ s/^\**\s*([A-Z]{3,}):\s+// );
+ }
my $severity = (exists $opts{-severity}) ? "*** $opts{-severity}: " : "";
## Increment error count and print message "
++($self->{_NUM_ERRORS})
if(!%opts || ($opts{-severity} && $opts{-severity} eq 'ERROR'));
- my $out_fh = $self->output_handle();
- print $out_fh ($severity, $msg, $line, $file, "\n");
+ ++($self->{_NUM_WARNINGS})
+ if(!%opts || ($opts{-severity} && $opts{-severity} eq 'WARNING'));
+ unless($self->{-quiet}) {
+ my $out_fh = $self->output_handle() || \*STDERR;
+ print $out_fh ($severity, $msg, $line, $file, "\n")
+ if($self->{-warnings} || !%opts || $opts{-severity} ne 'WARNING');
+ }
}
+##################################
+
+=item C<$checker-E<gt>num_errors()>
+
+Set (if argument specified) and retrieve the number of errors found.
+
+=cut
+
sub num_errors {
return (@_ > 1) ? ($_[0]->{_NUM_ERRORS} = $_[1]) : $_[0]->{_NUM_ERRORS};
}
+##################################
+
+=item C<$checker-E<gt>num_warnings()>
+
+Set (if argument specified) and retrieve the number of warnings found.
+
+=cut
+
+sub num_warnings {
+ return (@_ > 1) ? ($_[0]->{_NUM_WARNINGS} = $_[1]) : $_[0]->{_NUM_WARNINGS};
+}
+
+##################################
+
+=item C<$checker-E<gt>name()>
+
+Set (if argument specified) and retrieve the canonical name of POD as
+found in the C<=head1 NAME> section.
+
+=cut
+
+sub name {
+ return (@_ > 1 && $_[1]) ?
+ ($_[0]->{-name} = $_[1]) : $_[0]->{-name};
+}
+
+##################################
+
+=item C<$checker-E<gt>node()>
+
+Add (if argument specified) and retrieve the nodes (as defined by C<=headX>
+and C<=item>) of the current POD. The nodes are returned in the order of
+their occurrence. They consist of plain text, each piece of whitespace is
+collapsed to a single blank.
+
+=cut
+
+sub node {
+ my ($self,$text) = @_;
+ if(defined $text) {
+ $text =~ s/\s+$//s; # strip trailing whitespace
+ $text =~ s/\s+/ /gs; # collapse whitespace
+ # add node, order important!
+ push(@{$self->{_nodes}}, $text);
+ # keep also a uniqueness counter
+ $self->{_unique_nodes}->{$text}++ if($text !~ /^\s*$/s);
+ return $text;
+ }
+ @{$self->{_nodes}};
+}
+
+##################################
+
+=item C<$checker-E<gt>idx()>
+
+Add (if argument specified) and retrieve the index entries (as defined by
+C<XE<lt>E<gt>>) of the current POD. They consist of plain text, each piece
+of whitespace is collapsed to a single blank.
+
+=cut
+
+# set/return index entries of current POD
+sub idx {
+ my ($self,$text) = @_;
+ if(defined $text) {
+ $text =~ s/\s+$//s; # strip trailing whitespace
+ $text =~ s/\s+/ /gs; # collapse whitespace
+ # add node, order important!
+ push(@{$self->{_index}}, $text);
+ # keep also a uniqueness counter
+ $self->{_unique_nodes}->{$text}++ if($text !~ /^\s*$/s);
+ return $text;
+ }
+ @{$self->{_index}};
+}
+
+##################################
+
+=item C<$checker-E<gt>hyperlink()>
+
+Add (if argument specified) and retrieve the hyperlinks (as defined by
+C<LE<lt>E<gt>>) of the current POD. They consist of a 2-item array: line
+number and C<Pod::Hyperlink> object.
+
+=back
+
+=cut
+
+# set/return hyperlinks of the current POD
+sub hyperlink {
+ my $self = shift;
+ if($_[0]) {
+ push(@{$self->{_links}}, $_[0]);
+ return $_[0];
+ }
+ @{$self->{_links}};
+}
+
## overrides for Pod::Parser
sub end_pod {
- ## Do some final checks and
- ## print the number of errors found
- my $self = shift;
- my $infile = $self->input_file();
- my $out_fh = $self->output_handle();
-
- if(@{$self->{_list_stack}}) {
- # _TODO_ display, but don't count them for now
- my $list;
- while($list = shift(@{$self->{_list_stack}})) {
- $self->poderror({ -line => 'EOF', -file => $infile,
- -severity => 'ERROR', -msg => "=over on line " .
- $list->start() . " without closing =back" }); #"
- }
- }
-
- # check validity of document internal hyperlinks
- # first build the node names from the paragraph text
- my %nodes;
- foreach($self->node()) {
- #print "Have node: +$_+\n";
- $nodes{$_} = 1;
- if(/^(\S+)\s+/) {
- # we have more than one word. Use the first as a node, too.
- # This is used heavily in perlfunc.pod
- $nodes{$1} ||= 2; # derived node
- }
- }
- foreach($self->hyperlink()) {
- #print "Seek node: +$_+\n";
- my $line = '';
- s/^(\d+):// && ($line = $1);
- if($_ && !$nodes{$_}) {
- $self->poderror({ -line => $line, -file => $infile,
- -severity => 'ERROR',
- -msg => "unresolved internal link `$_'"});
- }
- }
-
- ## Print the number of errors found
- my $num_errors = $self->num_errors();
- if ($num_errors > 0) {
- printf $out_fh ("$infile has $num_errors pod syntax %s.\n",
- ($num_errors == 1) ? "error" : "errors");
- }
- elsif($self->{_commands} == 0) {
- print $out_fh "$infile does not contain any pod commands.\n";
- $self->num_errors(-1);
- }
- else {
- print $out_fh "$infile pod syntax OK.\n";
- }
+ ## Do some final checks and
+ ## print the number of errors found
+ my $self = shift;
+ my $infile = $self->input_file();
+
+ if(@{$self->{_list_stack}}) {
+ my $list;
+ while(($list = $self->_close_list('EOF',$infile)) &&
+ $list->indent() ne 'auto') {
+ $self->poderror({ -line => 'EOF', -file => $infile,
+ -severity => 'ERROR', -msg => "=over on line " .
+ $list->start() . " without closing =back" }); #"
+ }
+ }
+
+ # check validity of document internal hyperlinks
+ # first build the node names from the paragraph text
+ my %nodes;
+ foreach($self->node()) {
+ $nodes{$_} = 1;
+ if(/^(\S+)\s+\S/) {
+ # we have more than one word. Use the first as a node, too.
+ # This is used heavily in perlfunc.pod
+ $nodes{$1} ||= 2; # derived node
+ }
+ }
+ foreach($self->idx()) {
+ $nodes{$_} = 3; # index node
+ }
+ foreach($self->hyperlink()) {
+ my ($line,$link) = @$_;
+ # _TODO_ what if there is a link to the page itself by the name,
+ # e.g. in Tk::Pod : L<Tk::Pod/"DESCRIPTION">
+ if($link->node() && !$link->page() && $link->type() ne 'hyperlink') {
+ my $node = $self->_check_ptree($self->parse_text($link->node(),
+ $line), $line, $infile, 'L');
+ if($node && !$nodes{$node}) {
+ $self->poderror({ -line => $line || '', -file => $infile,
+ -severity => 'ERROR',
+ -msg => "unresolved internal link '$node'"});
+ }
+ }
+ }
+
+ # check the internal nodes for uniqueness. This pertains to
+ # =headX, =item and X<...>
+ if($self->{-warnings} && $self->{-warnings}>1) {
+ foreach(grep($self->{_unique_nodes}->{$_} > 1,
+ keys %{$self->{_unique_nodes}})) {
+ $self->poderror({ -line => '-', -file => $infile,
+ -severity => 'WARNING',
+ -msg => "multiple occurrence of link target '$_'"});
+ }
+ }
+
+ # no POD found here
+ $self->num_errors(-1) if($self->{_commands} == 0);
}
+# check a POD command directive
sub command {
my ($self, $cmd, $paragraph, $line_num, $pod_para) = @_;
my ($file, $line) = $pod_para->file_line;
my $arg; # this will hold the command argument
if (! $VALID_COMMANDS{$cmd}) {
$self->poderror({ -line => $line, -file => $file, -severity => 'ERROR',
- -msg => "Unknown command \"$cmd\"" });
+ -msg => "Unknown command '$cmd'" });
}
- else {
- $self->{_commands}++; # found a valid command
- ## check syntax of particular command
+ else { # found a valid command
+ $self->{_commands}++; # delete this line if below is enabled again
+
+ ##### following check disabled due to strong request
+ #if(!$self->{_commands}++ && $cmd !~ /^head/) {
+ # $self->poderror({ -line => $line, -file => $file,
+ # -severity => 'WARNING',
+ # -msg => "file does not start with =head" });
+ #}
+
+ # check syntax of particular command
if($cmd eq 'over') {
+ # check for argument
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
+ my $indent = 4; # default
+ if($arg && $arg =~ /^\s*(\d+)\s*$/) {
+ $indent = $1;
+ }
# start a new list
- unshift(@{$self->{_list_stack}},
- Pod::List->new(
- -indent => $paragraph,
- -start => $line,
- -file => $file));
+ $self->_open_list($indent,$line,$file);
}
elsif($cmd eq 'item') {
+ # are we in a list?
unless(@{$self->{_list_stack}}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => "=item without previous =over" });
+ # auto-open in case we encounter many more
+ $self->_open_list('auto',$line,$file);
}
- else {
- # check for argument
- $arg = $self->_interpolate_and_check($paragraph, $line, $file);
- unless($arg && $arg =~ /(\S+)/) {
+ my $list = $self->{_list_stack}->[0];
+ # check whether the previous item had some contents
+ if(defined $self->{_list_item_contents} &&
+ $self->{_list_item_contents} == 0) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "previous =item has no contents" });
+ }
+ if($list->{_has_par}) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "preceding non-item paragraph(s)" });
+ delete $list->{_has_par};
+ }
+ # check for argument
+ $arg = $self->interpolate_and_check($paragraph, $line, $file);
+ if($arg && $arg =~ /(\S+)/) {
+ $arg =~ s/[\s\n]+$//;
+ my $type;
+ if($arg =~ /^[*]\s*(\S*.*)/) {
+ $type = 'bullet';
+ $self->{_list_item_contents} = $1 ? 1 : 0;
+ $arg = $1;
+ }
+ elsif($arg =~ /^\d+\.?\s*(\S*)/) {
+ $type = 'number';
+ $self->{_list_item_contents} = $1 ? 1 : 0;
+ $arg = $1;
+ }
+ else {
+ $type = 'definition';
+ $self->{_list_item_contents} = 1;
+ }
+ my $first = $list->type();
+ if($first && $first ne $type) {
$self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
- -msg => "No argument for =item" });
+ -severity => 'WARNING',
+ -msg => "=item type mismatch ('$first' vs. '$type')"});
+ }
+ else { # first item
+ $list->type($type);
}
- # add this item
- $self->{_list_stack}[0]->item($arg || '');
- # remember this node
- $self->node($arg) if($arg);
}
+ else {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "No argument for =item" });
+ $arg = ' '; # empty
+ $self->{_list_item_contents} = 0;
+ }
+ # add this item
+ $list->item($arg);
+ # remember this node
+ $self->node($arg);
}
elsif($cmd eq 'back') {
# check if we have an open list
}
else {
# check for spurious characters
- $arg = $self->_interpolate_and_check($paragraph, $line,$file);
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
if($arg && $arg =~ /\S/) {
$self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
+ -severity => 'ERROR',
-msg => "Spurious character(s) after =back" });
}
# close list
- my $list = shift @{$self->{_list_stack}};
+ my $list = $self->_close_list($line,$file);
# check for empty lists
if(!$list->item() && $self->{-warnings}) {
$self->poderror({ -line => $line, -file => $file,
}
}
}
- elsif($cmd =~ /^head/) {
+ elsif($cmd =~ /^head(\d+)/) {
+ my $hnum = $1;
+ $self->{"_have_head_$hnum"}++; # count head types
+ if($hnum > 1 && !$self->{"_have_head_".($hnum -1)}) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "=head$hnum without preceding higher level"});
+ }
+ # check whether the previous =head section had some contents
+ if(defined $self->{_commands_in_head} &&
+ $self->{_commands_in_head} == 0 &&
+ defined $self->{_last_head} &&
+ $self->{_last_head} >= $hnum) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "empty section in previous paragraph"});
+ }
+ $self->{_commands_in_head} = -1;
+ $self->{_last_head} = $hnum;
# check if there is an open list
if(@{$self->{_list_stack}}) {
my $list;
- while($list = shift(@{$self->{_list_stack}})) {
+ while(($list = $self->_close_list($line,$file)) &&
+ $list->indent() ne 'auto') {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
- -msg => "unclosed =over (line ". $list->start() .
- ") at $cmd" });
+ -msg => "=over on line ". $list->start() .
+ " without closing =back (at $cmd)" });
}
}
# remember this node
- $arg = $self->_interpolate_and_check($paragraph, $line,$file);
- $self->node($arg) if($arg);
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
+ $arg =~ s/[\s\n]+$//s;
+ $self->node($arg);
+ unless(length($arg)) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "empty =$cmd"});
+ }
+ if($cmd eq 'head1') {
+ $self->{_current_head1} = $arg;
+ } else {
+ $self->{_current_head1} = '';
+ }
}
elsif($cmd eq 'begin') {
if($self->{_have_begin}) {
}
else {
# check for argument
- $arg = $self->_interpolate_and_check($paragraph, $line,$file);
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
unless($arg && $arg =~ /(\S+)/) {
$self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
+ -severity => 'ERROR',
-msg => "No argument for =begin"});
}
# remember the =begin
# close the existing =begin
$self->{_have_begin} = '';
# check for spurious characters
- $arg = $self->_interpolate_and_check($paragraph, $line,$file);
- if($arg && $arg =~ /\S/) {
- $self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
- -msg => "Spurious character(s) after =end" });
- }
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
+ # the closing argument is optional
+ #if($arg && $arg =~ /\S/) {
+ # $self->poderror({ -line => $line, -file => $file,
+ # -severity => 'WARNING',
+ # -msg => "Spurious character(s) after =end" });
+ #}
}
else {
# don't have a matching =begin
$self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
+ -severity => 'ERROR',
-msg => "=end without =begin" });
}
}
- }
+ elsif($cmd eq 'for') {
+ unless($paragraph =~ /\s*(\S+)\s*/) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "=for without formatter specification" });
+ }
+ $arg = ''; # do not expand paragraph below
+ }
+ elsif($cmd =~ /^(pod|cut)$/) {
+ # check for argument
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
+ if($arg && $arg =~ /(\S+)/) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "Spurious text after =$cmd"});
+ }
+ }
+ $self->{_commands_in_head}++;
## Check the interior sequences in the command-text
- $self->_interpolate_and_check($paragraph, $line,$file)
+ $self->interpolate_and_check($paragraph, $line,$file)
unless(defined $arg);
+ }
+}
+
+sub _open_list
+{
+ my ($self,$indent,$line,$file) = @_;
+ my $list = Pod::List->new(
+ -indent => $indent,
+ -start => $line,
+ -file => $file);
+ unshift(@{$self->{_list_stack}}, $list);
+ undef $self->{_list_item_contents};
+ $list;
}
-sub _interpolate_and_check {
+sub _close_list
+{
+ my ($self,$line,$file) = @_;
+ my $list = shift(@{$self->{_list_stack}});
+ if(defined $self->{_list_item_contents} &&
+ $self->{_list_item_contents} == 0) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "previous =item has no contents" });
+ }
+ undef $self->{_list_item_contents};
+ $list;
+}
+
+# process a block of some text
+sub interpolate_and_check {
my ($self, $paragraph, $line, $file) = @_;
## Check the interior sequences in the command-text
# and return the text
foreach(@$ptree) {
# regular text chunk
unless(ref) {
- my $count;
# count the unescaped angle brackets
- my $i = $_;
- if($count = $i =~ s/[<>]/$self->expand_unescaped_bracket($&)/ge) {
+ # complain only when warning level is greater than 1
+ if($self->{-warnings} && $self->{-warnings}>1) {
+ my $count;
+ if($count = tr/<>/<>/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
- -msg => "$count unescaped <>" });
+ -msg => "$count unescaped <> in paragraph" });
+ }
}
- $text .= $i;
+ $text .= $_;
next;
}
# have an interior sequence
if (! $VALID_SEQUENCES{$cmd}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
- -msg => qq(Unknown interior-sequence "$cmd")});
+ -msg => qq(Unknown interior-sequence '$cmd')});
# expand it anyway
$text .= $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
next;
}
if($nestlist =~ /$cmd/) {
$self->poderror({ -line => $line, -file => $file,
- -severity => 'ERROR',
+ -severity => 'WARNING',
-msg => "nested commands $cmd<...$cmd<...>...>"});
# _TODO_ should we add the contents anyway?
# expand it anyway, see below
-msg => "garbled entity " . $_->raw_text()});
next;
}
- $text .= $self->expand_entity($$contents[0]);
+ my $ent = $$contents[0];
+ my $val;
+ if($ent =~ /^0x[0-9a-f]+$/i) {
+ # hexadec entity
+ $val = hex($ent);
+ }
+ elsif($ent =~ /^0\d+$/) {
+ # octal
+ $val = oct($ent);
+ }
+ elsif($ent =~ /^\d+$/) {
+ # numeric entity
+ $val = $ent;
+ }
+ if(defined $val) {
+ if($val>0 && $val<256) {
+ $text .= chr($val);
+ }
+ else {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "Entity number out of range " . $_->raw_text()});
+ }
+ }
+ elsif($ENTITIES{$ent}) {
+ # known ISO entity
+ $text .= $ENTITIES{$ent};
+ }
+ else {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "Unknown entity " . $_->raw_text()});
+ $text .= "E<$ent>";
+ }
}
elsif($cmd eq 'L') {
# try to parse the hyperlink
unless(defined $link) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
- -msg => "malformed link L<>: $@"});
+ -msg => "malformed link " . $_->raw_text() ." : $@"});
next;
}
$link->line($line); # remember line
# check the link text
$text .= $self->_check_ptree($self->parse_text($link->text(),
$line), $line, $file, "$nestlist$cmd");
- my $node = '';
- $node = $self->_check_ptree($self->parse_text($link->node(),
- $line), $line, $file, "$nestlist$cmd")
- if($link->node());
- # store internal link
- # _TODO_ what if there is a link to the page itself by the name,
- # e.g. Tk::Pod : L<Tk::Pod/"DESCRIPTION">
- $self->hyperlink("$line:$node") if($node && !$link->page());
+ # remember link
+ $self->hyperlink([$line,$link]);
}
elsif($cmd =~ /[BCFIS]/) {
# add the guts
$text .= $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
}
+ elsif($cmd eq 'Z') {
+ if(length($contents->raw_text())) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "Nonempty Z<>"});
+ }
+ }
+ elsif($cmd eq 'X') {
+ my $idx = $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
+ if($idx =~ /^\s*$/s) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'ERROR',
+ -msg => "Empty X<>"});
+ }
+ else {
+ # remember this node
+ $self->idx($idx);
+ }
+ }
else {
- # check, but add nothing to $text (X<>, Z<>)
- $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
+ # not reached
+ die "internal error";
}
}
$text;
}
-# default method - just return it
-sub expand_unescaped_bracket {
- my ($self,$bracket) = @_;
- $bracket;
-}
-
-# keep the entities
-sub expand_entity {
- my ($self,$entity) = @_;
- "E<$entity>";
-}
-
-# _TODO_ overloadable methods for BC..Z<...> expansion
-
+# process a block of verbatim text
sub verbatim {
- ## Nothing to check
- ## my ($self, $paragraph, $line_num, $pod_para) = @_;
-}
-
-sub textblock {
+ ## Nothing particular to check
my ($self, $paragraph, $line_num, $pod_para) = @_;
- my ($file, $line) = $pod_para->file_line;
- $self->_interpolate_and_check($paragraph, $line,$file);
-}
-# set/return nodes of the current POD
-sub node {
- my ($self,$text) = @_;
- if(defined $text) {
- $text =~ s/[\s\n]+$//; # strip trailing whitespace
- # add node
- push(@{$self->{_nodes}}, $text);
- return $text;
- }
- @{$self->{_nodes}};
-}
+ $self->_preproc_par($paragraph);
-# set/return hyperlinks of the current POD
-sub hyperlink {
- my $self = shift;
- if($_[0]) {
- push(@{$self->{_links}}, $_[0]);
- return $_[0];
+ if($self->{_current_head1} eq 'NAME') {
+ my ($file, $line) = $pod_para->file_line;
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => 'Verbatim paragraph in NAME section' });
}
- @{$self->{_links}};
}
-#-----------------------------------------------------------------------------
-# Pod::List
-#
-# class to hold POD list info (=over, =item, =back)
-#-----------------------------------------------------------------------------
-
-package Pod::List;
-
-use Carp;
-
-sub new {
- my $this = shift;
- my $class = ref($this) || $this;
- my %params = @_;
- my $self = {%params};
- bless $self, $class;
- $self->initialize();
- return $self;
-}
-
-sub initialize {
- my $self = shift;
- $self->{-file} ||= 'unknown';
- $self->{-start} ||= 'unknown';
- $self->{-indent} ||= 4; # perlpod: "should be the default"
- $self->{_items} = [];
-}
-
-# The POD file name the list appears in
-sub file {
- return (@_ > 1) ? ($_[0]->{-file} = $_[1]) : $_[0]->{-file};
-}
-
-# The line in the file the node appears
-sub start {
- return (@_ > 1) ? ($_[0]->{-start} = $_[1]) : $_[0]->{-start};
-}
-
-# indent level
-sub indent {
- return (@_ > 1) ? ($_[0]->{-indent} = $_[1]) : $_[0]->{-indent};
-}
-
-# The individual =items of this list
-sub item {
- my ($self,$item) = @_;
- if(defined $item) {
- push(@{$self->{_items}}, $item);
- return $item;
- }
- else {
- return @{$self->{_items}};
- }
-}
-
-#-----------------------------------------------------------------------------
-# Pod::Hyperlink
-#
-# class to hold hyperlinks (L<>)
-#-----------------------------------------------------------------------------
-
-package Pod::Hyperlink;
-
-=head1 NAME
-
-Pod::Hyperlink - class for manipulation of POD hyperlinks
-
-=head1 SYNOPSIS
-
- my $link = Pod::Hyperlink->new('alternative text|page/"section in page"');
-
-=head1 DESCRIPTION
-
-The B<Pod::Hyperlink> class is mainly designed to parse the contents of the
-C<LE<lt>...E<gt>> sequence, providing a simple interface for accessing the
-different parts of a POD hyperlink.
-
-=head1 METHODS
-
-=over 4
-
-=item new()
-
-The B<new()> method can either be passed a set of key/value pairs or a single
-scalar value, namely the contents of a C<LE<lt>...E<gt>> sequence. An object
-of the class C<Pod::Hyperlink> is returned. The value C<undef> indicates a
-failure, the error message is stored in C<$@>.
-
-=item parse()
-
-This method can be used to (re)parse a (new) hyperlink. The result is stored
-in the current object.
-
-=item markup($on,$off,$pageon,$pageoff)
-
-The result of this method is a string the represents the textual value of the
-link, but with included arbitrary markers that highlight the active portion
-of the link. This will mainly be used by POD translators and saves the
-effort of determining which words have to be highlighted. Examples: Depending
-on the type of link, the following text will be returned, the C<*> represent
-the places where the section/item specific on/off markers will be placed
-(link to a specific node) and C<+> for the pageon/pageoff markers (link to the
-top of the page).
-
- the +perl+ manpage
- the *$|* entry in the +perlvar+ manpage
- the section on *OPTIONS* in the +perldoc+ manpage
- the section on *DESCRIPTION* elsewhere in this document
-
-This method is read-only.
-
-=item text()
-
-This method returns the textual representation of the hyperlink as above,
-but without markers (read only).
-
-=item warning()
-
-After parsing, this method returns any warnings ecountered during the
-parsing process.
-
-=item page()
-
-This method sets or returns the POD page this link points to.
-
-=item node()
-
-As above, but the destination node text of the link.
-
-=item type()
-
-The node type, either C<section> or C<item>.
-
-=item alttext()
-
-Sets or returns an alternative text specified in the link.
-
-=item line(), file()
-
-Just simple slots for storing information about the line and the file
-the link was incountered in. Has to be filled in manually.
-
-=back
-
-=head1 AUTHOR
-
-Marek Rouchal E<lt>marek@saftsack.fs.uni-bayreuth.deE<gt>, borrowing
-a lot of things from L<pod2man> and L<pod2roff>.
-
-=cut
+# process a block of regular text
+sub textblock {
+ my ($self, $paragraph, $line_num, $pod_para) = @_;
+ my ($file, $line) = $pod_para->file_line;
-use Carp;
+ $self->_preproc_par($paragraph);
-sub new {
- my $this = shift;
- my $class = ref($this) || $this;
- my $self = +{};
- bless $self, $class;
- $self->initialize();
- if(defined $_[0]) {
- if(ref($_[0])) {
- # called with a list of parameters
- %$self = %{$_[0]};
- }
- else {
- # called with L<> contents
- return undef unless($self->parse($_[0]));
+ # skip this paragraph if in a =begin block
+ unless($self->{_have_begin}) {
+ my $block = $self->interpolate_and_check($paragraph, $line,$file);
+ if($self->{_current_head1} eq 'NAME') {
+ if($block =~ /^\s*(\S+?)\s*[,-]/) {
+ # this is the canonical name
+ $self->{-name} = $1 unless(defined $self->{-name});
+ }
}
}
- return $self;
-}
-
-sub initialize {
- my $self = shift;
- $self->{-line} ||= 'undef';
- $self->{-file} ||= 'undef';
- $self->{-page} ||= '';
- $self->{-node} ||= '';
- $self->{-alttext} ||= '';
- $self->{-type} ||= 'undef';
- $self->{_warnings} = [];
- $self->_construct_text();
}
-sub parse {
+sub _preproc_par
+{
my $self = shift;
- local($_) = $_[0];
- # syntax check the link and extract destination
- my ($alttext,$page,$section,$item) = ('','','','');
-
- # strip leading/trailing whitespace
- if(s/^[\s\n]+//) {
- $self->warning("ignoring leading whitespace in link");
- }
- if(s/[\s\n]+$//) {
- $self->warning("ignoring trailing whitespace in link");
- }
-
- # collapse newlines with whitespace
- s/\s*\n\s*/ /g;
-
- # extract alternative text
- if(s!^([^|/"\n]*)[|]!!) {
- $alttext = $1;
- }
- # extract page
- if(s!^([^|/"\s]*)(?=/|$)!!) {
- $page = $1;
- }
- # extract section
- if(s!^/?"([^"\n]+)"$!!) { # e.g. L</"blah blah">
- $section = $1;
- }
- # extact item
- if(s!^/(.*)$!!) {
- $item = $1;
- }
- # last chance here
- if(s!^([^|"\s\n/][^"\n/]*)$!!) { # e.g. L<lah di dah>
- $section = $1;
- }
- # now there should be nothing left
- if(length) {
- _invalid_link("garbled entry (spurious characters `$_')");
- return undef;
- }
- elsif(!(length($page) || length($section) || length($item))) {
- _invalid_link("empty link");
- return undef;
- }
- elsif($alttext =~ /[<>]/) {
- _invalid_link("alternative text contains < or >");
- return undef;
- }
- else { # no errors so far
- if($page =~ /[(]\d\w*[)]$/) {
- $self->warning("brackets in `$page'");
- $page = $`; # strip that extension
- }
- if($page =~ /^(\s*)(\S+)(\s*)/ && (length($1) || length($3))) {
- $self->warning("whitespace in `$page'");
- $page = $2; # strip that extension
+ $_[0] =~ s/[\s\n]+$//;
+ if($_[0]) {
+ $self->{_commands_in_head}++;
+ $self->{_list_item_contents}++ if(defined $self->{_list_item_contents});
+ if(@{$self->{_list_stack}} && !$self->{_list_stack}->[0]->item()) {
+ $self->{_list_stack}->[0]->{_has_par} = 1;
}
}
- $self->page($page);
- $self->node($section || $item); # _TODO_ do not distinguish for now
- $self->alttext($alttext);
- $self->type($item ? 'item' : 'section');
- 1;
-}
-
-sub _construct_text {
- my $self = shift;
- my $alttext = $self->alttext();
- my $type = $self->type();
- my $section = $self->node();
- my $page = $self->page();
- $self->{_text} =
- $alttext ? $alttext : (
- !$section ? '' :
- $type eq 'item' ? 'the ' . $section . ' entry' :
- 'the section on ' . $section ) .
- ($page ? ($section ? ' in ':''). 'the ' . $page . ' manpage' :
- 'elsewhere in this document');
- # for being marked up later
- $self->{_markup} =
- $alttext ? '<SECTON>' . $alttext . '<SECTOFF>' : (
- !$section ? '' :
- $type eq 'item' ? 'the <SECTON>' . $section . '<SECTOFF> entry' :
- 'the section on <SECTON>' . $section . '<SECTOFF>' ) .
- ($page ? ($section ? ' in ':'') . 'the <PAGEON>' .
- $page . '<PAGEOFF> manpage' :
- ' elsewhere in this document');
}
-# include markup
-sub markup {
- my ($self,$on,$off,$pageon,$pageoff) = @_;
- $on ||= '';
- $off ||= '';
- $pageon ||= '';
- $pageoff ||= '';
- $_[0]->_construct_text;
- my $str = $self->{_markup};
- $str =~ s/<SECTON>/$on/;
- $str =~ s/<SECTOFF>/$off/;
- $str =~ s/<PAGEON>/$pageon/;
- $str =~ s/<PAGEOFF>/$pageoff/;
- return $str;
-}
-
-# The complete link's text
-sub text {
- $_[0]->_construct_text();
- $_[0]->{_text};
-}
-
-# The POD page the link appears on
-sub warning {
- my $self = shift;
- if(@_) {
- push(@{$self->{_warnings}}, @_);
- return @_;
- }
- return @{$self->{_warnings}};
-}
-
-# The POD file name the link appears in
-sub file {
- return (@_ > 1) ? ($_[0]->{-file} = $_[1]) : $_[0]->{-file};
-}
+1;
-# The line in the file the link appears
-sub line {
- return (@_ > 1) ? ($_[0]->{-line} = $_[1]) : $_[0]->{-line};
-}
+__END__
-# The POD page the link appears on
-sub page {
- return (@_ > 1) ? ($_[0]->{-page} = $_[1]) : $_[0]->{-page};
-}
+=head1 AUTHOR
-# The link destination
-sub node {
- return (@_ > 1) ? ($_[0]->{-node} = $_[1]) : $_[0]->{-node};
-}
+Please report bugs using L<http://rt.cpan.org>.
-# Potential alternative text
-sub alttext {
- return (@_ > 1) ? ($_[0]->{-alttext} = $_[1]) : $_[0]->{-alttext};
-}
+Brad Appleton E<lt>bradapp@enteract.comE<gt> (initial version),
+Marek Rouchal E<lt>marekr@cpan.orgE<gt>
-# The type
-sub type {
- return (@_ > 1) ? ($_[0]->{-type} = $_[1]) : $_[0]->{-type};
-}
+Based on code for B<Pod::Text::pod2text()> written by
+Tom Christiansen E<lt>tchrist@mox.perl.comE<gt>
-sub _invalid_link {
- my ($msg) = @_;
- # this sets @_
- #eval { die "$msg\n" };
- #chomp $@;
- $@ = $msg; # this seems to work, too!
- undef;
-}
+=cut
-1;