summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Benchmark.pm4
-rw-r--r--lib/Cwd.pm23
-rw-r--r--lib/English.pm16
-rw-r--r--lib/ExtUtils/MM_Unix.pm2
-rw-r--r--lib/ExtUtils/MM_Win32.pm1
-rw-r--r--lib/ExtUtils/Manifest.pm2
-rw-r--r--lib/Fatal.pm2
-rw-r--r--lib/File/Find.pm3
-rw-r--r--lib/File/Spec/Win32.pm13
-rw-r--r--lib/Math/BigFloat.pm2
-rw-r--r--lib/Pod/Checker.pm849
-rw-r--r--lib/Pod/Find.pm259
-rw-r--r--lib/Pod/ParseUtils.pm792
-rw-r--r--lib/Text/ParseWords.pm2
-rw-r--r--lib/Text/Tabs.pm8
-rw-r--r--lib/byte.pm21
-rw-r--r--lib/byte_heavy.pl6
-rw-r--r--lib/caller.pm58
-rw-r--r--lib/charnames.pm16
-rw-r--r--lib/perl5db.pl26
-rw-r--r--lib/utf8.pm175
-rw-r--r--lib/utf8_heavy.pl2
-rw-r--r--lib/warnings.pm15
23 files changed, 1590 insertions, 707 deletions
diff --git a/lib/Benchmark.pm b/lib/Benchmark.pm
index f9ade27bc5..3c10a5bc52 100644
--- a/lib/Benchmark.pm
+++ b/lib/Benchmark.pm
@@ -423,14 +423,14 @@ sub timestr {
my @t = @$tr;
warn "bad time value (@t)" unless @t==6;
my($r, $pu, $ps, $cu, $cs, $n) = @t;
- my($pt, $ct, $t) = ($tr->cpu_p, $tr->cpu_c, $tr->cpu_a);
+ my($pt, $ct, $tt) = ($tr->cpu_p, $tr->cpu_c, $tr->cpu_a);
$f = $defaultfmt unless defined $f;
# format a time in the required style, other formats may be added here
$style ||= $defaultstyle;
$style = ($ct>0) ? 'all' : 'noc' if $style eq 'auto';
my $s = "@t $style"; # default for unknown style
$s=sprintf("%2d wallclock secs (%$f usr %$f sys + %$f cusr %$f csys = %$f CPU)",
- @t,$t) if $style eq 'all';
+ $r,$pu,$ps,$cu,$cs,$tt) if $style eq 'all';
$s=sprintf("%2d wallclock secs (%$f usr + %$f sys = %$f CPU)",
$r,$pu,$ps,$pt) if $style eq 'noc';
$s=sprintf("%2d wallclock secs (%$f cusr + %$f csys = %$f CPU)",
diff --git a/lib/Cwd.pm b/lib/Cwd.pm
index ee1bc28367..e3c45903c3 100644
--- a/lib/Cwd.pm
+++ b/lib/Cwd.pm
@@ -20,7 +20,7 @@ getcwd - get pathname of current working directory
chdir "/tmp";
print $ENV{'PWD'};
- use Cwd 'abs_path';
+ use Cwd 'abs_path'; # aka realpath()
print abs_path($ENV{'PWD'});
use Cwd 'fast_abs_path';
@@ -32,8 +32,11 @@ The getcwd() function re-implements the getcwd(3) (or getwd(3)) functions
in Perl.
The abs_path() function takes a single argument and returns the
-absolute pathname for that argument. It uses the same algorithm as
-getcwd(). (actually getcwd() is abs_path("."))
+absolute pathname for that argument. It uses the same algorithm
+as getcwd(). (Actually, getcwd() is abs_path(".")) Symbolic links
+and relative-path components ("." and "..") are resolved to return
+the canonical pathname, just like realpath(3). Also callable as
+realpath().
The fastcwd() function looks the same as getcwd(), but runs faster.
It's also more dangerous because it might conceivably chdir() you out
@@ -67,12 +70,12 @@ kept up to date if all packages which use chdir import it from Cwd.
use Carp;
-$VERSION = '2.01';
+$VERSION = '2.02';
require Exporter;
@ISA = qw(Exporter);
@EXPORT = qw(cwd getcwd fastcwd fastgetcwd);
-@EXPORT_OK = qw(chdir abs_path fast_abs_path);
+@EXPORT_OK = qw(chdir abs_path fast_abs_path realpath fast_realpath);
# The 'natural and safe form' for UNIX (pwd may be setuid root)
@@ -257,6 +260,10 @@ sub abs_path
$cwd;
}
+# added function alias for those of us more
+# used to the libc function. --tchrist 27-Jan-00
+*realpath = \&abs_path;
+
sub fast_abs_path {
my $cwd = getcwd();
my $path = shift || '.';
@@ -266,6 +273,10 @@ sub fast_abs_path {
$realpath;
}
+# added function alias to follow principle of least surprise
+# based on previous aliasing. --tchrist 27-Jan-00
+*fast_realpath = \&fast_abs_path;
+
# --- PORTING SECTION ---
@@ -331,7 +342,7 @@ sub _qnx_abs_path {
}
{
- local $^W = 0; # assignments trigger 'subroutine redefined' warning
+ no warnings; # assignments trigger 'subroutine redefined' warning
if ($^O eq 'VMS') {
*cwd = \&_vms_cwd;
diff --git a/lib/English.pm b/lib/English.pm
index 9f29a487dc..86d75a4268 100644
--- a/lib/English.pm
+++ b/lib/English.pm
@@ -15,14 +15,6 @@ English - use nice English (or awk) names for ugly punctuation variables
=head1 DESCRIPTION
-You should I<not> use this module in programs intended to be portable
-among Perl versions, programs that must perform regular expression
-matching operations efficiently, or libraries intended for use with
-such programs. In a sense, this module is deprecated. The reasons
-for this have to do with implementation details of the Perl
-interpreter which are too thorny to go into here. Perhaps someday
-they will be fixed to make "C<use English>" more practical.
-
This module provides aliases for the built-in variables whose
names no one seems to like to read. Variables with side-effects
which get triggered just by accessing them (like $0) will still
@@ -35,9 +27,15 @@ $INPUT_RECORD_SEPARATOR if you are using the English module.
See L<perlvar> for a complete list of these.
+=head1 BUGS
+
+This module provokes sizeable inefficiencies for regular expressions,
+due to unfortunate implementation details. If performance matters,
+consider avoiding English.
+
=cut
-local $^W = 0;
+no warnings;
# Grandfather $NAME import
sub import {
diff --git a/lib/ExtUtils/MM_Unix.pm b/lib/ExtUtils/MM_Unix.pm
index f4329e13d7..c5cf7066bf 100644
--- a/lib/ExtUtils/MM_Unix.pm
+++ b/lib/ExtUtils/MM_Unix.pm
@@ -2766,7 +2766,7 @@ sub parse_version {
$_
}; \$$2
};
- local($^W) = 0;
+ no warnings;
$result = eval($eval);
warn "Could not eval '$eval' in $parsefile: $@" if $@;
$result = "undef" unless defined $result;
diff --git a/lib/ExtUtils/MM_Win32.pm b/lib/ExtUtils/MM_Win32.pm
index 534f26d823..e08c6791ee 100644
--- a/lib/ExtUtils/MM_Win32.pm
+++ b/lib/ExtUtils/MM_Win32.pm
@@ -388,7 +388,6 @@ PM_TO_BLIB = }.join(" \\\n\t", %{$self->{PM}}).q{
sub path {
- local $^W = 1;
my($self) = @_;
my $path = $ENV{'PATH'} || $ENV{'Path'} || $ENV{'path'};
my @path = split(';',$path);
diff --git a/lib/ExtUtils/Manifest.pm b/lib/ExtUtils/Manifest.pm
index 58c91bc44b..8bb3fc8ebd 100644
--- a/lib/ExtUtils/Manifest.pm
+++ b/lib/ExtUtils/Manifest.pm
@@ -25,7 +25,7 @@ $MANIFEST = 'MANIFEST';
# Really cool fix from Ilya :)
unless (defined $Config{d_link}) {
- local $^W;
+ no warnings;
*ln = \&cp;
}
diff --git a/lib/Fatal.pm b/lib/Fatal.pm
index 12fef27d61..5b832f6427 100644
--- a/lib/Fatal.pm
+++ b/lib/Fatal.pm
@@ -116,7 +116,7 @@ EOS
no strict 'refs'; # to avoid: Can't use string (...) as a symbol ref ...
$code = eval("package $pkg; use Carp; $code");
die if $@;
- local($^W) = 0; # to avoid: Subroutine foo redefined ...
+ no warnings; # to avoid: Subroutine foo redefined ...
*{$sub} = $code;
}
}
diff --git a/lib/File/Find.pm b/lib/File/Find.pm
index 9963d8198b..42905dec80 100644
--- a/lib/File/Find.pm
+++ b/lib/File/Find.pm
@@ -309,6 +309,8 @@ sub _find_opt {
$top_item =~ s|/$|| unless $top_item eq '/';
$Is_Dir= 0;
+ ($topdev,$topino,$topmode,$topnlink) = stat $top_item;
+
if ($follow) {
if (substr($top_item,0,1) eq '/') {
$abs_dir = $top_item;
@@ -331,7 +333,6 @@ sub _find_opt {
}
else { # no follow
$topdir = $top_item;
- ($topdev,$topino,$topmode,$topnlink) = lstat $top_item;
unless (defined $topnlink) {
warn "Can't stat $top_item: $!\n";
next Proc_Top_Item;
diff --git a/lib/File/Spec/Win32.pm b/lib/File/Spec/Win32.pm
index 0ea4970b41..120b799cd2 100644
--- a/lib/File/Spec/Win32.pm
+++ b/lib/File/Spec/Win32.pm
@@ -81,7 +81,6 @@ sub catfile {
}
sub path {
- local $^W = 1;
my $path = $ENV{'PATH'} || $ENV{'Path'} || $ENV{'path'};
my @path = split(';',$path);
foreach (@path) { $_ = '.' if $_ eq '' }
@@ -309,14 +308,18 @@ sub abs2rel {
$path_directories = CORE::join( '\\', @pathchunks );
$base_directories = CORE::join( '\\', @basechunks );
- # $base now contains the directories the resulting relative path
- # must ascend out of before it can descend to $path_directory. So,
+ # $base_directories now contains the directories the resulting relative
+ # path must ascend out of before it can descend to $path_directory. So,
# replace all names with $parentDir
- $base_directories =~ s|[^/]+|..|g ;
+
+ #FA Need to replace between backslashes...
+ $base_directories =~ s|[^\\]+|..|g ;
# Glue the two together, using a separator if necessary, and preventing an
# empty result.
- if ( $path ne '' && $base ne '' ) {
+
+ #FA Must check that new directories are not empty.
+ if ( $path_directories ne '' && $base_directories ne '' ) {
$path_directories = "$base_directories\\$path_directories" ;
} else {
$path_directories = "$base_directories$path_directories" ;
diff --git a/lib/Math/BigFloat.pm b/lib/Math/BigFloat.pm
index 1a9195e185..d8d643ca3e 100644
--- a/lib/Math/BigFloat.pm
+++ b/lib/Math/BigFloat.pm
@@ -74,7 +74,7 @@ sub fnorm; sub fsqrt;
sub fnorm { #(string) return fnum_str
local($_) = @_;
s/\s+//g; # strip white space
- local $^W = 0; # $4 and $5 below might legitimately be undefined
+ no warnings; # $4 and $5 below might legitimately be undefined
if (/^([+-]?)(\d*)(\.(\d*))?([Ee]([+-]?\d+))?$/ && "$2$4" ne '') {
&norm(($1 ? "$1$2$4" : "+$2$4"),(($4 ne '') ? $6-length($4) : $6));
} else {
diff --git a/lib/Pod/Checker.pm b/lib/Pod/Checker.pm
index aa5c5490ae..c661c7527e 100644
--- a/lib/Pod/Checker.pm
+++ b/lib/Pod/Checker.pm
@@ -10,9 +10,11 @@
package Pod::Checker;
use vars qw($VERSION);
-$VERSION = 1.090; ## Current version of this package
+$VERSION = 1.096; ## Current version of this package
require 5.004; ## requires this Perl version or later
+use Pod::ParseUtils; ## for hyperlinks and lists
+
=head1 NAME
Pod::Checker, podchecker() - check pod documents for syntax errors
@@ -23,15 +25,19 @@ Pod::Checker, podchecker() - check pod documents for syntax errors
$syntax_okay = podchecker($filepath, $outputpath, %options);
+ my $checker = new Pod::Checker %options;
+
=head1 OPTIONS/ARGUMENTS
C<$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
@@ -45,20 +51,25 @@ Turn warnings on/off. See L<"Warnings">.
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.
+I<NOTE THAT THIS MODULE IS CURRENTLY IN THE BETA STAGE!>
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>.
+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 preformed:
=over 4
=item *
-Check for proper balancing of C<=begin> and C<=end>.
+Unknown '=xxxx' commands, unknown 'X<...>' 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 *
@@ -66,55 +77,156 @@ Check for proper nesting and balancing of C<=over>, C<=item> and C<=back>.
=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 nonexisting 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
-=head2 Warnings
+=head2 Additional Features
+
+While checking, this module collects document properties, e.g. the nodes
+for hyperlinks (C<=headX>, C<=item>). 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.
+
+=head1 DIAGNOSTICS
-The following warnings are printed. These may not necessarily cause trouble,
-but indicate mediocre style.
+=head2 Errors
=over 4
-=item *
+=item * =over on line I<N> without closing =back
-Spurious characters after C<=back> and C<=end>.
+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 * =item without previous =over
-Unescaped C<E<lt>> and C<E<gt>> in the text.
+=item * =back without previous =over
-=item *
+An C<=item> or C<=back> command has been found outside a
+C<=over>/C<=back> block.
-Missing arguments for C<=begin> and C<=over>.
+=item * No argument for =begin
-=item *
+A C<=begin> command was found that is not followed by the formatter
+specification.
-Empty C<=over> / C<=back> list.
+=item * =end without =begin
-=item *
+A standalone C<=end> command was found.
+
+=item * Nested =begin's
+
+There were at least two concecutive C<=begin> commands without
+the corresponding C<=end>. Only one C<=begin> may be active at
+a time.
+
+=item * =for without formatter specification
-Hyperlinks: leading/trailing whitespace, brackets C<()> in the page name.
+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 happend 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<=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 an character entity.
+
+=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>.
=back
-=head1 DIAGNOSTICS
+=head2 Warnings
-I<[T.B.D.]>
+These may not necessarily cause trouble, but indicate mediocre style.
+
+=over 4
+
+=item * No numeric argument for =over
+
+The C<=over> command is supposed to have a numeric argument (the
+indentation).
+
+=item * Spurious character(s) after =back
+
+The C<=back> command does not take any arguments.
+
+=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.
+
+=item * Non-standard entity
+
+A character entity was found that does not belong to the standard
+ISO set.
+
+=item * No items in =over
+
+The list 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 * 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 * Hyperlinks
+
+There are some warnings wrt. hyperlinks:
+Leading/trailing whitespace, newlines in hyperlinks,
+brackets C<()>.
+
+=back
=head1 RETURN VALUE
@@ -174,6 +286,117 @@ 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 => '÷',
+);
+
##---------------------------------------------------------------------------
##---------------------------------
@@ -219,16 +442,18 @@ sub initialize {
## 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->errorsub('poderror'); # set the error handling subroutine
$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
+ # print warnings?
$self->{-warnings} = 1 unless(defined $self->{-warnings});
+ $self->{_current_head1} = ''; # the current =head1 block
}
-## Invoked as $self->poderror( @args ), or $self->poderror( {%opts}, @args )
+# Invoked as $self->poderror( @args ), or $self->poderror( {%opts}, @args )
sub poderror {
my $self = shift;
my %opts = (ref $_[0]) ? %{shift()} : ();
@@ -243,13 +468,43 @@ sub poderror {
++($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");
+ print $out_fh ($severity, $msg, $line, $file, "\n")
+ if($self->{-warnings} || !%opts || $opts{-severity} ne 'WARNING');
}
+# set/retrieve the number of errors found
sub num_errors {
return (@_ > 1) ? ($_[0]->{_NUM_ERRORS} = $_[1]) : $_[0]->{_NUM_ERRORS};
}
+# set and/or retrieve canonical name of POD
+sub name {
+ return (@_ > 1 && $_[1]) ?
+ ($_[0]->{-name} = $_[1]) : $_[0]->{-name};
+}
+
+# set/return nodes of the current POD
+sub node {
+ my ($self,$text) = @_;
+ if(defined $text) {
+ $text =~ s/[\s\n]+$//; # strip trailing whitespace
+ # add node
+ push(@{$self->{_nodes}}, $text);
+ return $text;
+ }
+ @{$self->{_nodes}};
+}
+
+# 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 {
@@ -273,7 +528,6 @@ sub end_pod {
# 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.
@@ -282,7 +536,6 @@ sub end_pod {
}
}
foreach($self->hyperlink()) {
- #print "Seek node: +$_+\n";
my $line = '';
s/^(\d+):// && ($line = $1);
if($_ && !$nodes{$_}) {
@@ -307,6 +560,7 @@ sub end_pod {
}
}
+# check a POD command directive
sub command {
my ($self, $cmd, $paragraph, $line_num, $pod_para) = @_;
my ($file, $line) = $pod_para->file_line;
@@ -320,32 +574,47 @@ sub command {
$self->{_commands}++; # found a valid command
## check syntax of particular command
if($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;
+ } else {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "No numeric argument for =over"});
+ }
# start a new list
- unshift(@{$self->{_list_stack}},
- Pod::List->new(
- -indent => $paragraph,
+ unshift(@{$self->{_list_stack}}, Pod::List->new(
+ -indent => $indent,
-start => $line,
-file => $file));
}
elsif($cmd eq 'item') {
+ # are we in a list?
unless(@{$self->{_list_stack}}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => "=item without previous =over" });
+ # auto-open in case we encounter many more
+ unshift(@{$self->{_list_stack}},
+ Pod::List->new(
+ -indent => 'auto',
+ -start => $line,
+ -file => $file));
}
- else {
- # check for argument
- $arg = $self->_interpolate_and_check($paragraph, $line, $file);
- unless($arg && $arg =~ /(\S+)/) {
- $self->poderror({ -line => $line, -file => $file,
- -severity => 'WARNING',
- -msg => "No argument for =item" });
- }
- # add this item
- $self->{_list_stack}[0]->item($arg || '');
- # remember this node
- $self->node($arg) if($arg);
+ # check for argument
+ $arg = $self->interpolate_and_check($paragraph, $line, $file);
+ unless($arg && $arg =~ /(\S+)/) {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "No argument for =item" });
+ $arg = ' '; # empty
}
+ # add this item
+ $self->{_list_stack}[0]->item($arg);
+ # remember this node
+ $self->node($arg);
}
elsif($cmd eq 'back') {
# check if we have an open list
@@ -356,7 +625,7 @@ sub command {
}
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 => $file,
-severity => 'WARNING',
@@ -380,13 +649,19 @@ sub command {
while($list = shift(@{$self->{_list_stack}})) {
$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);
+ $arg = $self->interpolate_and_check($paragraph, $line,$file);
$self->node($arg) if($arg);
+ if($cmd eq 'head1') {
+ $arg =~ s/[\s\n]+$//;
+ $self->{_current_head1} = $arg;
+ } else {
+ $self->{_current_head1} = '';
+ }
}
elsif($cmd eq 'begin') {
if($self->{_have_begin}) {
@@ -398,10 +673,10 @@ sub command {
}
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
@@ -413,27 +688,37 @@ sub command {
# 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
+ }
## Check the interior sequences in the command-text
- $self->_interpolate_and_check($paragraph, $line,$file)
+ $self->interpolate_and_check($paragraph, $line,$file)
unless(defined $arg);
+ }
}
-sub _interpolate_and_check {
+# process a block of some text
+sub interpolate_and_check {
my ($self, $paragraph, $line, $file) = @_;
## Check the interior sequences in the command-text
# and return the text
@@ -452,10 +737,11 @@ sub _check_ptree {
my $count;
# count the unescaped angle brackets
my $i = $_;
- if($count = $i =~ s/[<>]/$self->expand_unescaped_bracket($&)/ge) {
+ if($count = $i =~ tr/<>/<>/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
- -msg => "$count unescaped <>" });
+ -msg => "$count unescaped <> in paragraph" })
+ if($self->{-warnings});
}
$text .= $i;
next;
@@ -488,7 +774,21 @@ sub _check_ptree {
-msg => "garbled entity " . $_->raw_text()});
next;
}
- $text .= $self->expand_entity($$contents[0]);
+ my $ent = $$contents[0];
+ if($ent =~ /^\d+$/) {
+ # numeric entity
+ $text .= chr($ent);
+ }
+ elsif($ENTITIES{$ent}) {
+ # known ISO entity
+ $text .= $ENTITIES{$ent};
+ }
+ else {
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => "Non-standard entity " . $_->raw_text()});
+ $text .= "E<$ent>";
+ }
}
elsif($cmd eq 'L') {
# try to parse the hyperlink
@@ -496,7 +796,7 @@ sub _check_ptree {
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
@@ -511,13 +811,14 @@ sub _check_ptree {
$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
+ # remember 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 && !$link->page());
+ # e.g. in Tk::Pod : L<Tk::Pod/"DESCRIPTION">
+ if($link->node() && !$link->page() && $link->type() ne 'hyperlink') {
+ $node = $self->_check_ptree($self->parse_text($link->node(),
+ $line), $line, $file, "$nestlist$cmd");
+ $self->hyperlink("$line:$node") if($node);
+ }
}
elsif($cmd =~ /[BCFIS]/) {
# add the guts
@@ -531,397 +832,35 @@ sub _check_ptree {
$text;
}
-# default method - just return it
-sub expand_unescaped_bracket {
- my ($self,$bracket) = @_;
- $bracket;
-}
-
-# keep the entities
-sub expand_entity {
- my ($self,$entity) = @_;
- "E<$entity>";
-}
-
-# _TODO_ overloadable methods for BC..Z<...> expansion
+# _TODO_ overloadable methods for BC..Z<...> expansion?
+# process a block of verbatim text
sub verbatim {
## Nothing to check
- ## my ($self, $paragraph, $line_num, $pod_para) = @_;
+ my ($self, $paragraph, $line_num, $pod_para) = @_;
+ if($self->{_current_head1} eq 'NAME') {
+ my ($file, $line) = $pod_para->file_line;
+ $self->poderror({ -line => $line, -file => $file,
+ -severity => 'WARNING',
+ -msg => 'Verbatim paragraph in NAME section' });
+ }
}
+# process a block of regular text
sub textblock {
my ($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}};
-}
-
-# set/return hyperlinks of the current POD
-sub hyperlink {
- my $self = shift;
- if($_[0]) {
- push(@{$self->{_links}}, $_[0]);
- return $_[0];
- }
- @{$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
-
-use Carp;
-
-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]));
- }
- }
- 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 {
- 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 = $2; # strip that extension
+ # skip this paragraph if in a =begin block
+ unless($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});
+ }
}
}
- $self->page($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]) : $_[0]->{-file};
-}
-
-# The line in the file the link appears
-sub line {
- return (@_ > 1) ? ($_[0]->{-line} = $_[1]) : $_[0]->{-line};
-}
-
-# The POD page the link appears on
-sub page {
- return (@_ > 1) ? ($_[0]->{-page} = $_[1]) : $_[0]->{-page};
-}
-
-# The link destination
-sub node {
- return (@_ > 1) ? ($_[0]->{-node} = $_[1]) : $_[0]->{-node};
-}
-
-# Potential alternative text
-sub alttext {
- return (@_ > 1) ? ($_[0]->{-alttext} = $_[1]) : $_[0]->{-alttext};
-}
-
-# The type
-sub type {
- return (@_ > 1) ? ($_[0]->{-type} = $_[1]) : $_[0]->{-type};
-}
-
-sub _invalid_link {
- my ($msg) = @_;
- # this sets @_
- #eval { die "$msg\n" };
- #chomp $@;
- $@ = $msg; # this seems to work, too!
- undef;
}
1;
diff --git a/lib/Pod/Find.pm b/lib/Pod/Find.pm
new file mode 100644
index 0000000000..399bbba252
--- /dev/null
+++ b/lib/Pod/Find.pm
@@ -0,0 +1,259 @@
+#############################################################################
+# Pod/Find.pm -- finds files containing POD documentation
+#
+# Author: Marek Rouchal <marek@saftsack.fs.uni-bayreuth.de>
+#
+# borrowing code from Nick Ing-Simmon's PodToHtml
+# This file is part of "PodParser". Pod::Find is free software;
+# you can redistribute it and/or modify it under the same terms
+# as Perl itself.
+#############################################################################
+
+package Pod::Find;
+
+use vars qw($VERSION);
+$VERSION = 0.10; ## Current version of this package
+require 5.005; ## requires this Perl version or later
+
+#############################################################################
+
+=head1 NAME
+
+Pod::Find - find POD documents in directory trees
+
+=head1 SYNOPSIS
+
+ use Pod::Find qw(pod_find simplify_name);
+ my %pods = pod_find({ -verbose => 1, -inc => 1 });
+ foreach(keys %pods) {
+ print "found library POD `$pods{$_}' in $_\n";
+ }
+
+ print "podname=",simplify_name('a/b/c/mymodule.pod'),"\n";
+
+=head1 DESCRIPTION
+
+B<Pod::Find> provides a function B<pod_find> that searches for POD
+documents in a given set of files and directories. It returns a hash
+with the file names as keys and the POD name as value. The POD name
+is derived from the file name and its position in the directory tree.
+
+E.g. when searching in F<$HOME/perl5lib>, the file
+F<$HOME/perl5lib/MyModule.pm> would get the POD name I<MyModule>,
+whereas F<$HOME/perl5lib/Myclass/Subclass.pm> would be
+I<Myclass::Subclass>. The name information can be used for POD
+translators.
+
+Only text files containing at least one valid POD command are found.
+
+A warning is printed if more than one POD file with the same POD name
+is found, e.g. F<CPAN.pm> in different directories. This usually
+indicates duplicate occurences of modules in the I<@INC> search path.
+
+The function B<simplify_name> is equivalent to B<basename>, but also
+strips Perl-like extensions (.pm, .pl, .pod).
+
+Note that neither B<pod_find> nor B<simplify_name> are exported by
+default so be sure to specify them in the B<use> statement if you need them:
+
+ use Pod::Find qw(pod_find simplify_name);
+
+=head1 OPTIONS
+
+The first argument for B<pod_find> may be a hash reference with options.
+The rest are either directories that are searched recursively or files.
+The POD names of files are the plain basenames with any Perl-like extension
+(.pm, .pl, .pod) stripped.
+
+=over 4
+
+=item B<-verbose>
+
+Print progress information while scanning.
+
+=item B<-perl>
+
+Apply Perl-specific heuristics to find the correct PODs. This includes
+stripping Perl-like extensions, omitting subdirectories that are numeric
+but do I<not> match the current Perl interpreter's version id, suppressing
+F<site_perl> as a module hierarchy name etc.
+
+=item B<-script>
+
+Search for PODs in the current Perl interpreter's installation
+B<scriptdir>. This is taken from the local L<Config|Config> module.
+
+=item B<-inc>
+
+Search for PODs in the current Perl interpreter's I<@INC> paths.
+
+=back
+
+=head1 AUTHOR
+
+Marek Rouchal E<lt>marek@saftsack.fs.uni-bayreuth.deE<gt>,
+heavily borrowing code from Nick Ing-Simmons' PodToHtml.
+
+=head1 SEE ALSO
+
+L<Pod::Parser>, L<Pod::Checker>
+
+=cut
+
+use strict;
+#use diagnostics;
+use Exporter;
+use File::Find;
+use Cwd;
+
+use vars qw(@ISA @EXPORT_OK $VERSION);
+@ISA = qw(Exporter);
+@EXPORT_OK = qw(&pod_find &simplify_name);
+
+# package global variables
+my $SIMPLIFY_RX;
+
+# return a hash of the
+sub pod_find
+{
+ my %opts;
+ if(ref $_[0]) {
+ %opts = %{shift()};
+ }
+
+ $opts{-verbose} ||= 0;
+ $opts{-perl} ||= 0;
+
+ my (@search) = @_;
+
+ if($opts{-script}) {
+ require Config;
+ push(@search, $Config::Config{scriptdir});
+ $opts{-perl} = 1;
+ }
+
+ if($opts{-inc}) {
+ push(@search, grep($_ ne '.',@INC));
+ $opts{-perl} = 1;
+ }
+
+ if($opts{-perl}) {
+ require Config;
+ # this code simplifies the POD name for Perl modules:
+ # * remove "site_perl"
+ # * remove e.g. "i586-linux"
+ # * remove e.g. 5.00503
+ # * remove pod/ if followed by *.pod (e.g. in pod/perlfunc.pod)
+ $SIMPLIFY_RX =
+ qr!^(?i:site_perl/|$Config::Config{archname}/|\d+\.\d+([_.]?\d+)?/|pod/(?=.*?\.pod$))*!o;
+ }
+
+ my %dirs_visited;
+ my %pods;
+ my %names;
+ my $pwd = cwd();
+
+ foreach my $try (@search) {
+ unless($try =~ m:^/:) {
+ # make path absolute
+ $try = join('/',$pwd,$try);
+ }
+ $try =~ s:/\.?(?=/|$)::; # simplify path
+ my $name;
+ if(-f $try) {
+ if($name = _check_and_extract_name($try, $opts{-verbose})) {
+ _check_for_duplicates($try, $name, \%names, \%pods);
+ }
+ next;
+ }
+ my $root_rx = qr!^\Q$try\E/!;
+ File::Find::find( sub {
+ my $item = $File::Find::name;
+ if(-d) {
+ if($dirs_visited{$item}) {
+ warn "Directory '$item' already seen, skipping.\n"
+ if($opts{-verbose});
+ $File::Find::prune = 1;
+ return;
+ }
+ else {
+ $dirs_visited{$item} = 1;
+ }
+ if($opts{-perl} && /^(\d+\.[\d_]+)$/ && eval "$1" != $]) {
+ $File::Find::prune = 1;
+ warn "Perl $] version mismatch on $_, skipping.\n"
+ if($opts{-verbose});
+ }
+ return;
+ }
+ if($name = _check_and_extract_name($item, $opts{-verbose}, $root_rx)) {
+ _check_for_duplicates($item, $name, \%names, \%pods);
+ }
+ }, $try); # end of File::Find::find
+ }
+ chdir $pwd;
+ %pods;
+}
+
+sub _check_for_duplicates {
+ my ($file, $name, $names_ref, $pods_ref) = @_;
+ if($$names_ref{$name}) {
+ warn "Duplicate POD found (shadowing?): $name ($file)\n";
+ warn " Already seen in ",
+ join(' ', grep($$pods_ref{$_} eq $name, keys %$pods_ref)),"\n";
+ }
+ else {
+ $$names_ref{$name} = 1;
+ }
+ $$pods_ref{$file} = $name;
+}
+
+sub _check_and_extract_name {
+ my ($file, $verbose, $root_rx) = @_;
+
+ # check extension or executable
+ unless($file =~ /\.(pod|pm|pl)$/i || (-f $file && -x _ && -T _)) {
+ return undef;
+ }
+
+ # check for one line of POD
+ unless(open(POD,"<$file")) {
+ warn "Error: $file is unreadable: $!\n";
+ return undef;
+ }
+ local $/ = undef;
+ my $pod = <POD>;
+ close(POD);
+ unless($pod =~ /\n=(head\d|pod|over|item)\b/) {
+ warn "No POD in $file, skipping.\n"
+ if($verbose);
+ return;
+ }
+ undef $pod;
+
+ # strip non-significant path components
+ # _TODO_ what happens on e.g. Win32?
+ my $name = $file;
+ if(defined $root_rx) {
+ $name =~ s!$root_rx!!;
+ $name =~ s!$SIMPLIFY_RX!!o if(defined $SIMPLIFY_RX);
+ }
+ else {
+ $name =~ s:^.*/::;
+ }
+ $name =~ s/\.(pod|pm|pl)$//i;
+ $name =~ s!/+!::!g;
+ $name;
+}
+
+# basic simplification of the POD name:
+# basename & strip extension
+sub simplify_name {
+ my ($str) = @_;
+ $str =~ s:^.*/::;
+ $str =~ s:\.p([lm]|od)$::i;
+ $str;
+}
+
+1;
+
diff --git a/lib/Pod/ParseUtils.pm b/lib/Pod/ParseUtils.pm
new file mode 100644
index 0000000000..a66e8f5e8b
--- /dev/null
+++ b/lib/Pod/ParseUtils.pm
@@ -0,0 +1,792 @@
+#############################################################################
+# Pod/ParseUtils.pm -- helpers for POD parsing and conversion
+#
+# Copyright (C) 1999 by Marek Rouchal. All rights reserved.
+# This file is part of "PodParser". PodParser is free software;
+# you can redistribute it and/or modify it under the same terms
+# as Perl itself.
+#############################################################################
+
+package Pod::ParseUtils;
+
+use vars qw($VERSION);
+$VERSION = 0.2; ## Current version of this package
+require 5.004; ## requires this Perl version or later
+
+=head1 NAME
+
+Pod::ParseUtils - helpers for POD parsing and conversion
+
+=head1 SYNOPSIS
+
+ use Pod::ParseUtils;
+
+ my $list = new Pod::List;
+ my $link = Pod::Hyperlink->new('Pod::Parser');
+
+=head1 DESCRIPTION
+
+B<Pod::ParseUtils> contains a few object-oriented helper packages for
+POD parsing and processing (i.e. in POD formatters and translators).
+
+=cut
+
+#-----------------------------------------------------------------------------
+# Pod::List
+#
+# class to hold POD list info (=over, =item, =back)
+#-----------------------------------------------------------------------------
+
+package Pod::List;
+
+use Carp;
+
+=head2 Pod::List
+
+B<Pod::List> can be used to hold information about POD lists
+(written as =over ... =item ... =back) for further processing.
+The following methods are available:
+
+=over 4
+
+=item new()
+
+Create a new list object. Properties may be specified through a hash
+reference like this:
+
+ my $list = Pod::List->new({ -start => $., -indent => 4 });
+
+See the individual methods/properties for details.
+
+=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;
+ $self->{-file} ||= 'unknown';
+ $self->{-start} ||= 'unknown';
+ $self->{-indent} ||= 4; # perlpod: "should be the default"
+ $self->{_items} = [];
+ $self->{-type} ||= '';
+}
+
+=item file()
+
+Without argument, retrieves the file name the list is in. This must
+have been set before by either specifying B<-file> in the B<new()>
+method or by calling the B<file()> method with a scalar argument.
+
+=cut
+
+# The POD file name the list appears in
+sub file {
+ return (@_ > 1) ? ($_[0]->{-file} = $_[1]) : $_[0]->{-file};
+}
+
+=item start()
+
+Without argument, retrieves the line number where the list started.
+This must have been set before by either specifying B<-start> in the
+B<new()> method or by calling the B<start()> method with a scalar
+argument.
+
+=cut
+
+# The line in the file the node appears
+sub start {
+ return (@_ > 1) ? ($_[0]->{-start} = $_[1]) : $_[0]->{-start};
+}
+
+=item indent()
+
+Without argument, retrieves the indent level of the list as specified
+in C<=over n>. This must have been set before by either specifying
+B<-indent> in the B<new()> method or by calling the B<indent()> method
+with a scalar argument.
+
+=cut
+
+# indent level
+sub indent {
+ return (@_ > 1) ? ($_[0]->{-indent} = $_[1]) : $_[0]->{-indent};
+}
+
+=item type()
+
+Without argument, retrieves the list type, which can be an arbitrary value,
+e.g. C<OL>, C<UL>, ... when thinking the HTML way.
+This must have been set before by either specifying
+B<-type> in the B<new()> method or by calling the B<type()> method
+with a scalar argument.
+
+=cut
+
+# The type of the list (UL, OL, ...)
+sub type {
+ return (@_ > 1) ? ($_[0]->{-type} = $_[1]) : $_[0]->{-type};
+}
+
+=item rx()
+
+Without argument, retrieves a regular expression for simplifying the
+individual item strings once the list type has been determined. Usage:
+E.g. when converting to HTML, one might strip the leading number in
+an ordered list as C<E<lt>OLE<gt>> already prints numbers itself.
+This must have been set before by either specifying
+B<-rx> in the B<new()> method or by calling the B<rx()> method
+with a scalar argument.
+
+=cut
+
+# The regular expression to simplify the items
+sub rx {
+ return (@_ > 1) ? ($_[0]->{-rx} = $_[1]) : $_[0]->{-rx};
+}
+
+=item item()
+
+Without argument, retrieves the array of the items in this list.
+The items may be represented by any scalar.
+If an argument has been given, it is pushed on the list of items.
+
+=cut
+
+# The individual =items of this list
+sub item {
+ my ($self,$item) = @_;
+ if(defined $item) {
+ push(@{$self->{_items}}, $item);
+ return $item;
+ }
+ else {
+ return @{$self->{_items}};
+ }
+}
+
+=item parent()
+
+Without argument, retrieves information about the parent holding this
+list, which is represented as an arbitrary scalar.
+This must have been set before by either specifying
+B<-parent> in the B<new()> method or by calling the B<parent()> method
+with a scalar argument.
+
+=cut
+
+# possibility for parsers/translators to store information about the
+# lists's parent object
+sub parent {
+ return (@_ > 1) ? ($_[0]->{-parent} = $_[1]) : $_[0]->{-parent};
+}
+
+=item tag()
+
+Without argument, retrieves information about the list tag, which can be
+any scalar.
+This must have been set before by either specifying
+B<-tag> in the B<new()> method or by calling the B<tag()> method
+with a scalar argument.
+
+=back
+
+=cut
+
+# possibility for parsers/translators to store information about the
+# list's object
+sub tag {
+ return (@_ > 1) ? ($_[0]->{-tag} = $_[1]) : $_[0]->{-tag};
+}
+
+#-----------------------------------------------------------------------------
+# Pod::Hyperlink
+#
+# class to manipulate POD hyperlinks (L<>)
+#-----------------------------------------------------------------------------
+
+package Pod::Hyperlink;
+
+=head2 Pod::Hyperlink
+
+B<Pod::Hyperlink> is a class for manipulation of POD hyperlinks. Usage:
+
+ my $link = Pod::Hyperlink->new('alternative text|page/"section in page"');
+
+The B<Pod::Hyperlink> class is mainly designed to parse the contents of the
+C<LE<lt>...E<gt>> sequence, providing a simple interface for accessing the
+different parts of a POD hyperlink for further processing. It can also be
+used to construct hyperlinks.
+
+=over 4
+
+=item new()
+
+The B<new()> method can either be passed a set of key/value pairs or a single
+scalar value, namely the contents of a C<LE<lt>...E<gt>> sequence. An object
+of the class C<Pod::Hyperlink> is returned. The value C<undef> indicates a
+failure, the error message is stored in C<$@>.
+
+=cut
+
+use Carp;
+
+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]};
+ $self->_construct_text();
+ }
+ else {
+ # called with L<> contents
+ return undef unless($self->parse($_[0]));
+ }
+ }
+ return $self;
+}
+
+sub initialize {
+ my $self = shift;
+ $self->{-line} ||= 'undef';
+ $self->{-file} ||= 'undef';
+ $self->{-page} ||= '';
+ $self->{-node} ||= '';
+ $self->{-alttext} ||= '';
+ $self->{-type} ||= 'undef';
+ $self->{_warnings} = [];
+}
+
+=item parse($string)
+
+This method can be used to (re)parse a (new) hyperlink, i.e. the contents
+of a C<LE<lt>...E<gt>> sequence. The result is stored in the current object.
+
+=cut
+
+sub parse {
+ my $self = shift;
+ local($_) = $_[0];
+ # syntax check the link and extract destination
+ my ($alttext,$page,$node,$type) = ('','','','');
+
+ $self->{_warnings} = [];
+
+ # collapse newlines with whitespace
+ if(s/\s*\n+\s*/ /g) {
+ $self->warning("collapsing newlines to blanks");
+ }
+ # strip leading/trailing whitespace
+ if(s/^[\s\n]+//) {
+ $self->warning("ignoring leading whitespace in link");
+ }
+ if(s/[\s\n]+$//) {
+ $self->warning("ignoring trailing whitespace in link");
+ }
+ unless(length($_)) {
+ _invalid_link("empty link");
+ return undef;
+ }
+
+ ## Check for different possibilities. This is tedious and error-prone
+ # we match all possibilities (alttext, page, section/item)
+ #warn "DEBUG: link=$_\n";
+
+ # only page
+ if(m!^(\w+(?:::\w+)*)\s*(\(\w*\)|)$!) {
+ $page = $1 . $2;
+ $type = 'page';
+ }
+ # alttext, page and section
+ elsif(m!^(.+?)\s*[|]\s*(\w+(?:::\w+)*)\s*(\(\w*\)|)\s*/\s*"(.+)"$!) {
+ ($alttext, $page, $node) = ($1, $2 . $3, $4);
+ $type = 'section';
+ }
+ # page and section
+ elsif(m!^(\w+(?:::\w+)*)\s*(\(\w*\)|)\s*/\s*"(.+)"$!) {
+ ($page, $node) = ($1 . $2, $3);
+ $type = 'section';
+ }
+ # page and item
+ elsif(m!^(\w+(?:::\w+)*)\s*(\(\w*\)|)\s*/\s*(.+)$!) {
+ ($page, $node) = ($1 . $2, $3);
+ $type = 'item';
+ }
+ # only section
+ elsif(m!^(?:/\s*|)"(.+)"$!) {
+ $node = $1;
+ $type = 'section';
+ }
+ # only item
+ elsif(m!^/(.+)$!) {
+ $node = $1;
+ $type = 'item';
+ }
+ # non-standard: Hyperlink
+ elsif(m!^((?:http|ftp|mailto|news):.+)$!i) {
+ $node = $1;
+ $type = 'hyperlink';
+ }
+ # alttext, page and item
+ elsif(m!^(.+?)\s*[|]\s*(\w+(?:::\w+)*)\s*(\(\w*\)|)\s*/\s*(.+)$!) {
+ ($alttext, $page, $node) = ($1, $2 . $3, $4);
+ $type = 'item';
+ }
+ # alttext and page
+ elsif(m!^(.+?)\s*[|]\s*(\w+(?:::\w+)*)\s*(\(\w*\)|)$!) {
+ ($alttext, $page) = ($1, $2 . $3);
+ $type = 'page';
+ }
+ # alttext and section
+ elsif(m!^(.+?)\s*[|]\s*(?:/\s*|)"(.+)"$!) {
+ ($alttext, $node) = ($1,$2);
+ $type = 'section';
+ }
+ # alttext and item
+ elsif(m!^(.+?)\s*[|]\s*/(.+)$!) {
+ ($alttext, $node) = ($1,$2);
+ }
+ # nonstandard: alttext and hyperlink
+ elsif(m!^(.+?)\s*[|]\s*((?:http|ftp|mailto|news):.+)$!) {
+ ($alttext, $node) = ($1,$2);
+ $type = 'hyperlink';
+ }
+ # must be an item or a "malformed" section (without "")
+ else {
+ $node = $_;
+ $type = 'item';
+ }
+
+ if($page =~ /[(]\w*[)]$/) {
+ $self->warning("section in `$page' deprecated");
+ }
+ $self->{-page} = $page;
+ $self->{-node} = $node;
+ $self->{-alttext} = $alttext;
+ #warn "DEBUG: page=$page section=$section item=$item alttext=$alttext\n";
+ $self->{-type} = $type;
+ $self->_construct_text();
+ 1;
+}
+
+sub _construct_text {
+ my $self = shift;
+ my $alttext = $self->alttext();
+ my $type = $self->type();
+ my $section = $self->node();
+ my $page = $self->page();
+ my $page_ext = '';
+ $page =~ s/([(]\w*[)])$// && ($page_ext = $1);
+ if($alttext) {
+ $self->{_text} = $alttext;
+ }
+ elsif($type eq 'hyperlink') {
+ $self->{_text} = $section;
+ }
+ else {
+ $self->{_text} = (!$section ? '' :
+ $type eq 'item' ? "the $section entry" :
+ "the section on $section" ) .
+ ($page ? ($section ? ' in ':'') . "the $page$page_ext manpage" :
+ ' elsewhere in this document');
+ }
+ # for being marked up later
+ # use the non-standard markers P<> and Q<>, so that the resulting
+ # text can be parsed by the translators. It's their job to put
+ # the correct hypertext around the linktext
+ if($alttext) {
+ $self->{_markup} = "Q<$alttext>";
+ }
+ elsif($type eq 'hyperlink') {
+ $self->{_markup} = "Q<$section>";
+ }
+ else {
+ $self->{_markup} = (!$section ? '' :
+ $type eq 'item' ? "the Q<$section> entry" :
+ "the section on Q<$section>" ) .
+ ($page ? ($section ? ' in ':'') . "the P<$page>$page_ext manpage" :
+ ' elsewhere in this document');
+ }
+}
+
+=item markup($string)
+
+Set/retrieve the textual value of the link. This string contains special
+markers C<PE<lt>E<gt>> and C<QE<lt>E<gt>> that should be expanded by the
+translator's interior sequence expansion engine to the
+formatter-specific code to highlight/activate the hyperlink. The details
+have to be implemented in the translator.
+
+=cut
+
+#' retrieve/set markuped text
+sub markup {
+ return (@_ > 1) ? ($_[0]->{_markup} = $_[1]) : $_[0]->{_markup};
+}
+
+=item text()
+
+This method returns the textual representation of the hyperlink as above,
+but without markers (read only). Depending on the link type this is one of
+the following alternatives (the + and * denote the portions of the text
+that are marked up):
+
+ the +perl+ manpage
+ the *$|* entry in the +perlvar+ manpage
+ the section on *OPTIONS* in the +perldoc+ manpage
+ the section on *DESCRIPTION* elsewhere in this document
+
+=cut
+
+# The complete link's text
+sub text {
+ $_[0]->{_text};
+}
+
+=item warning()
+
+After parsing, this method returns any warnings encountered during the
+parsing process.
+
+=cut
+
+# Set/retrieve warnings
+sub warning {
+ my $self = shift;
+ if(@_) {
+ push(@{$self->{_warnings}}, @_);
+ return @_;
+ }
+ return @{$self->{_warnings}};
+}
+
+=item line(), file()
+
+Just simple slots for storing information about the line and the file
+the link was encountered in. Has to be filled in manually.
+
+=cut
+
+# The line in the file the link appears
+sub line {
+ return (@_ > 1) ? ($_[0]->{-line} = $_[1]) : $_[0]->{-line};
+}
+
+# The POD file name the link appears in
+sub file {
+ return (@_ > 1) ? ($_[0]->{-file} = $_[1]) : $_[0]->{-file};
+}
+
+=item page()
+
+This method sets or returns the POD page this link points to.
+
+=cut
+
+# The POD page the link appears on
+sub page {
+ if (@_ > 1) {
+ $_[0]->{-page} = $_[1];
+ $_[0]->_construct_text();
+ }
+ $_[0]->{-page};
+}
+
+=item node()
+
+As above, but the destination node text of the link.
+
+=cut
+
+# The link destination
+sub node {
+ if (@_ > 1) {
+ $_[0]->{-node} = $_[1];
+ $_[0]->_construct_text();
+ }
+ $_[0]->{-node};
+}
+
+=item alttext()
+
+Sets or returns an alternative text specified in the link.
+
+=cut
+
+# Potential alternative text
+sub alttext {
+ if (@_ > 1) {
+ $_[0]->{-alttext} = $_[1];
+ $_[0]->_construct_text();
+ }
+ $_[0]->{-alttext};
+}
+
+=item type()
+
+The node type, either C<section> or C<item>. As an unofficial type,
+there is also C<hyperlink>, derived from e.g. C<LE<lt>http://perl.comE<gt>>
+
+=cut
+
+# The type: item or headn
+sub type {
+ return (@_ > 1) ? ($_[0]->{-type} = $_[1]) : $_[0]->{-type};
+}
+
+=item link()
+
+Returns the link as contents of C<LE<lt>E<gt>>. Reciprocal to B<parse()>.
+
+=back
+
+=cut
+
+# The link itself
+sub link {
+ my $self = shift;
+ my $link = $self->page() || '';
+ if($self->node()) {
+ if($self->type() eq 'section') {
+ $link .= ($link ? '/' : '') . '"' . $self->node() . '"';
+ }
+ elsif($self->type() eq 'hyperlink') {
+ $link = $self->node();
+ }
+ else { # item
+ $link .= '/' . $self->node();
+ }
+ }
+ if($self->alttext()) {
+ $link = $self->alttext() . '|' . $link;
+ }
+ $link;
+}
+
+sub _invalid_link {
+ my ($msg) = @_;
+ # this sets @_
+ #eval { die "$msg\n" };
+ #chomp $@;
+ $@ = $msg; # this seems to work, too!
+ undef;
+}
+
+#-----------------------------------------------------------------------------
+# Pod::Cache
+#
+# class to hold POD page details
+#-----------------------------------------------------------------------------
+
+package Pod::Cache;
+
+=head2 Pod::Cache
+
+B<Pod::Cache> holds information about a set of POD documents,
+especially the nodes for hyperlinks.
+The following methods are available:
+
+=over 4
+
+=item new()
+
+Create a new cache object. This object can hold an arbitrary number of
+POD documents of class Pod::Cache::Item.
+
+=cut
+
+sub new {
+ my $this = shift;
+ my $class = ref($this) || $this;
+ my $self = [];
+ bless $self, $class;
+ return $self;
+}
+
+=item item()
+
+Add a new item to the cache. Without arguments, this method returns a
+list of all cache elements.
+
+=cut
+
+sub item {
+ my ($self,%param) = @_;
+ if(%param) {
+ my $item = Pod::Cache::Item->new(%param);
+ push(@$self, $item);
+ return $item;
+ }
+ else {
+ return @{$self};
+ }
+}
+
+=item find_page($name)
+
+Look for a POD document named C<$name> in the cache. Returns the
+reference to the corresponding Pod::Cache::Item object or undef if
+not found.
+
+=back
+
+=cut
+
+sub find_page {
+ my ($self,$page) = @_;
+ foreach(@$self) {
+ if($_->page() eq $page) {
+ return $_;
+ }
+ }
+ undef;
+}
+
+package Pod::Cache::Item;
+
+=head2 Pod::Cache::Item
+
+B<Pod::Cache::Item> holds information about individual POD documents,
+that can be grouped in a Pod::Cache object.
+It is intended to hold information about the hyperlink nodes of POD
+documents.
+The following methods are available:
+
+=over 4
+
+=item new()
+
+Create a new object.
+
+=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;
+ $self->{-nodes} = [] unless(defined $self->{-nodes});
+}
+
+=item page()
+
+Set/retrieve the POD document name (e.g. "Pod::Parser").
+
+=cut
+
+# The POD page
+sub page {
+ return (@_ > 1) ? ($_[0]->{-page} = $_[1]) : $_[0]->{-page};
+}
+
+=item description()
+
+Set/retrieve the POD short description as found in the C<=head1 NAME>
+section.
+
+=cut
+
+# The POD description, taken out of NAME if present
+sub description {
+ return (@_ > 1) ? ($_[0]->{-description} = $_[1]) : $_[0]->{-description};
+}
+
+=item path()
+
+Set/retrieve the POD file storage path.
+
+=cut
+
+# The file path
+sub path {
+ return (@_ > 1) ? ($_[0]->{-path} = $_[1]) : $_[0]->{-path};
+}
+
+=item file()
+
+Set/retrieve the POD file name.
+
+=cut
+
+# The POD file name
+sub file {
+ return (@_ > 1) ? ($_[0]->{-file} = $_[1]) : $_[0]->{-file};
+}
+
+=item nodes()
+
+Add a node (or a list of nodes) to the document's node list. Note that
+the order is kept, i.e. start with the first node and end with the last.
+If no argument is given, the current list of nodes is returned in the
+same order the nodes have been added.
+A node can be any scalar, but usually is a pair of node string and
+unique id for the C<find_node> method to work correctly.
+
+=cut
+
+# The POD nodes
+sub nodes {
+ my ($self,@nodes) = @_;
+ if(@nodes) {
+ push(@{$self->{-nodes}}, @nodes);
+ return @nodes;
+ }
+ else {
+ return @{$self->{-nodes}};
+ }
+}
+
+=item find_node($name)
+
+Look for a node named C<$name> in the object's node list. Returns the
+unique id of the node (i.e. the second element of the array stored in
+the node arry) or undef if not found.
+
+=back
+
+=cut
+
+sub find_node {
+ my ($self,$node) = @_;
+ foreach(@{$self->{-nodes}}) {
+ if($_->[0] eq $node) {
+ return $_->[1]; # id
+ }
+ }
+ undef;
+}
+
+
+=head1 AUTHOR
+
+Marek Rouchal E<lt>marek@saftsack.fs.uni-bayreuth.deE<gt>, borrowing
+a lot of things from L<pod2man> and L<pod2roff> as well as other POD
+processing tools by Tom Christiansen, Brad Appleton and Russ Allbery.
+
+=head1 SEE ALSO
+
+L<pod2man>, L<pod2roff>, L<Pod::Parser>, L<Pod::Checker>,
+L<pod2html>
+
+=cut
+
+1;
diff --git a/lib/Text/ParseWords.pm b/lib/Text/ParseWords.pm
index ada9d70d74..2a6afc3be9 100644
--- a/lib/Text/ParseWords.pm
+++ b/lib/Text/ParseWords.pm
@@ -49,7 +49,7 @@ sub nested_quotewords {
sub parse_line {
# We will be testing undef strings
- local($^W) = 0;
+ no warnings;
my($delimiter, $keep, $line) = @_;
my($quote, $quoted, $unquoted, $delim, $word, @pieces);
diff --git a/lib/Text/Tabs.pm b/lib/Text/Tabs.pm
index c431019908..933f917acd 100644
--- a/lib/Text/Tabs.pm
+++ b/lib/Text/Tabs.pm
@@ -73,11 +73,11 @@ Text::Tabs -- expand and unexpand tabs per the unix expand(1) and unexpand(1)
=head1 SYNOPSIS
-use Text::Tabs;
+ use Text::Tabs;
-$tabstop = 4;
-@lines_without_tabs = expand(@lines_with_tabs);
-@lines_with_tabs = unexpand(@lines_without_tabs);
+ $tabstop = 4;
+ @lines_without_tabs = expand(@lines_with_tabs);
+ @lines_with_tabs = unexpand(@lines_without_tabs);
=head1 DESCRIPTION
diff --git a/lib/byte.pm b/lib/byte.pm
index cc23b40f4f..33ffb769e8 100644
--- a/lib/byte.pm
+++ b/lib/byte.pm
@@ -20,7 +20,7 @@ __END__
=head1 NAME
-byte - Perl pragma to turn force treating strings as bytes not UNICODE
+byte - Perl pragma to force byte semantics rather than character semantics
=head1 SYNOPSIS
@@ -29,5 +29,24 @@ byte - Perl pragma to turn force treating strings as bytes not UNICODE
=head1 DESCRIPTION
+WARNING: The implementation of Unicode support in Perl is incomplete.
+Expect sudden and unannounced changes!
+
+The C<use byte> pragma disables character semantics for the rest of the
+lexical scope in which it appears. C<no byte> can be used to reverse
+the effect of C<use byte> within the current lexical scope.
+
+Perl normally assumes character semantics in the presence of
+character data (i.e. data that has come from a source that has
+been marked as being of a particular character encoding) or when
+the global $^U flag is enabled. [XXX: implement -C command line
+switch and mention that instead of $^U?]
+
+To understand the implications and differences between character
+semantics and byte semantics, see L<perlunicode>.
+
+=head1 SEE ALSO
+
+L<perlunicode>, L<utf8>
=cut
diff --git a/lib/byte_heavy.pl b/lib/byte_heavy.pl
index 07c908a689..ec0558561d 100644
--- a/lib/byte_heavy.pl
+++ b/lib/byte_heavy.pl
@@ -1,8 +1,8 @@
package byte;
-sub length ($)
-{
- return CORE::length($_[0]);
+sub length ($) {
+ BEGIN { byte::import() }
+ return CORE::length($_[0]);
}
1;
diff --git a/lib/caller.pm b/lib/caller.pm
deleted file mode 100644
index 98d4f3f28a..0000000000
--- a/lib/caller.pm
+++ /dev/null
@@ -1,58 +0,0 @@
-package caller;
-our $VERSION = "1.0";
-
-=head1 NAME
-
-caller - inherit pragmatic attributes from the context of the caller
-
-=head1 SYNOPSIS
-
- use caller qw(encoding);
-
-=head1 DESCRIPTION
-
-This pragma allows a module to inherit some attributes from the
-context which loaded it.
-
-Inheriting attributes takes place at compile time; this means
-only attributes that are visible in the calling context at compile
-time will be propagated.
-
-Currently, the only supported attribute is C<encoding>.
-
-=over
-
-=item encoding
-
-Indicates that the character set encoding of the caller's context
-must be inherited. This can be used to inherit the C<use utf8>
-setting in the calling context.
-
-=back
-
-=cut
-
-my %bitmask = (
- # only HINT_UTF8 supported for now
- encoding => 0x8
-);
-
-sub bits {
- my $bits = 0;
- for my $s (@_) { $bits |= $bitmask{$s} || 0; };
- $bits;
-}
-
-sub import {
- shift;
- my @cxt = caller(3);
- if (@cxt and $cxt[7]) { # was our parent require-d?
- $^H |= bits(@_) & $cxt[8];
- }
-}
-
-sub unimport {
- # noop currently
-}
-
-1;
diff --git a/lib/charnames.pm b/lib/charnames.pm
index bd97983abc..59350b2df9 100644
--- a/lib/charnames.pm
+++ b/lib/charnames.pm
@@ -29,17 +29,15 @@ sub charnames {
}
die "Unknown charname '$name'" unless @off;
- # use caller 'encoding'; # Does not work at compile time?
-
my $ord = hex substr $txt, $off[0] - 4, 4;
- if ($^H & 0x8) {
- use utf8;
- return chr $ord;
+ if ($^H & 0x10) { # "use byte" in effect?
+ use byte;
+ return chr $ord if $ord <= 255;
+ my $hex = sprintf '%X=0%o', $ord, $ord;
+ my $fname = substr $txt, $off[0] + 2, $off[1] - $off[0] - 2;
+ die "Character 0x$hex with name '$fname' is above 0xFF";
}
- return chr $ord if $ord <= 255;
- my $hex = sprintf '%X=0%o', $ord, $ord;
- my $fname = substr $txt, $off[0] + 2, $off[1] - $off[0] - 2;
- die "Character 0x$hex with name '$fname' is above 0xFF";
+ return chr $ord;
}
sub import {
diff --git a/lib/perl5db.pl b/lib/perl5db.pl
index d2bd98e654..aff5c687e7 100644
--- a/lib/perl5db.pl
+++ b/lib/perl5db.pl
@@ -607,6 +607,8 @@ EOP
$subrange = pop @pieces;
$file = join(':', @pieces);
if ($file ne $filename) {
+ print $OUT "Switching to file '$file'.\n"
+ unless $emacs;
*dbline = $main::{'_<' . $file};
$max = $#dbline;
$filename = $file;
@@ -793,8 +795,8 @@ EOP
($file,$i) = (find_sub($subname) =~ /^(.*):(.*)$/);
$i += 0;
if ($i) {
- $filename = $file;
- *dbline = $main::{'_<' . $filename};
+ local $filename = $file;
+ local *dbline = $main::{'_<' . $filename};
$had_breakpoints{$filename} = 1;
$max = $#dbline;
++$i while $dbline[$i] == 0 && $i < $max;
@@ -884,6 +886,10 @@ EOP
$cmd =~ /^c\b\s*([\w:]*)\s*$/ && do {
end_report(), next CMD if $finished and $level <= 1;
$subname = $i = $1;
+ # Probably not needed, since we finish an interactive
+ # sub-session anyway...
+ # local $filename = $filename;
+ # local *dbline = *dbline; # XXX Would this work?!
if ($i =~ /\D/) { # subroutine name
$subname = $package."::".$subname
unless $subname =~ /::/;
@@ -1254,11 +1260,11 @@ sub save {
# The following takes its argument via $evalarg to preserve current @_
sub eval {
- my @res;
+ local @res; # 'my' would make it visible from user code
{
- my $otrace = $trace;
- my $osingle = $single;
- my $od = $^D;
+ local $otrace = $trace;
+ local $osingle = $single;
+ local $od = $^D;
@res = eval "$usercontext $evalarg;\n"; # '\n' for nice recursive debug
$trace = $otrace;
$single = $osingle;
@@ -1811,7 +1817,13 @@ B<l> List next window of lines.
B<-> List previous window of lines.
B<w> [I<line>] List window around I<line>.
B<.> Return to the executed line.
-B<f> I<filename> Switch to viewing I<filename>. Must be loaded.
+B<f> I<filename> Switch to viewing I<filename>. File must be already loaded.
+ I<filename> may be either the full name of the file, or a regular
+ expression matching the full file name:
+ B<f> I</home/me/foo.pl> and B<f> I<oo\\.> may access the same file.
+ Evals (with saved bodies) are considered to be filenames:
+ B<f> I<(eval 7)> and B<f> I<eval 7\\b> access the body of the 7th eval
+ (in the order of execution).
B</>I<pattern>B</> Search forwards for I<pattern>; final B</> is optional.
B<?>I<pattern>B<?> Search backwards for I<pattern>; final B<?> is optional.
B<L> List all breakpoints and actions.
diff --git a/lib/utf8.pm b/lib/utf8.pm
index 5ddd4ba21a..be7cc0bf0c 100644
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -1,12 +1,15 @@
package utf8;
+$^U = 1 if caller and caller eq 'main'; # they are unicode aware
+ # XXX split this out?
+
sub import {
- $^H |= 0x00000008;
+ $^H |= 0x00800000;
$enc{caller()} = $_[1] if $_[1];
}
sub unimport {
- $^H &= ~0x00000008;
+ $^H &= ~0x00800000;
}
sub AUTOLOAD {
@@ -19,7 +22,7 @@ __END__
=head1 NAME
-utf8 - Perl pragma to turn on UTF-8 and Unicode support
+utf8 - Perl pragma to enable/disable UTF-8 in source code
=head1 SYNOPSIS
@@ -28,154 +31,60 @@ utf8 - Perl pragma to turn on UTF-8 and Unicode support
=head1 DESCRIPTION
-The utf8 pragma tells Perl to use UTF-8 as its internal string
-representation for the rest of the enclosing block. (The "no utf8"
-pragma tells Perl to switch back to ordinary byte-oriented processing
-for the rest of the enclosing block.) Under utf8, many operations that
-formerly operated on bytes change to operating on characters. For
-ASCII data this makes no difference, because UTF-8 stores ASCII in
-single bytes, but for any character greater than C<chr(127)>, the
-character is stored in a sequence of two or more bytes, all of which
-have the high bit set. But by and large, the user need not worry about
-this, because the utf8 pragma hides it from the user. A character
-under utf8 is logically just a number ranging from 0 to 2**32 or so.
-Larger characters encode to longer sequences of bytes, but again, this
-is hidden.
-
-Use of the utf8 pragma has the following effects:
-
-=over 4
-
-=item *
-
-Strings and patterns may contain characters that have an ordinal value
-larger than 255. Presuming you use a Unicode editor to edit your
-program, these will typically occur directly within the literal strings
-as UTF-8 characters, but you can also specify a particular character
-with an extension of the C<\x> notation. UTF-8 characters are
-specified by putting the hexadecimal code within curlies after the
-C<\x>. For instance, a Unicode smiley face is C<\x{263A}>. A
-character in the Latin-1 range (128..255) should be written C<\x{ab}>
-rather than C<\xab>, since the former will turn into a two-byte UTF-8
-code, while the latter will continue to be interpreted as generating a
-8-bit byte rather than a character. In fact, if C<-w> is turned on, it will
-produce a warning that you might be generating invalid UTF-8.
+WARNING: The implementation of Unicode support in Perl is incomplete.
+Expect sudden and unannounced changes!
-=item *
+The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
+program text in the current lexical scope. The C<no utf8> pragma
+tells Perl to switch back to treating the source text as literal
+bytes in the current lexical scope.
-Identifiers within the Perl script may contain Unicode alphanumeric
-characters, including ideographs. (You are currently on your own when
-it comes to using the canonical forms of characters--Perl doesn't (yet)
-attempt to canonicalize variable names for you.)
+This pragma is primarily a compatibility device. Perl versions
+earlier than 5.6 allowed arbitrary bytes in source code, whereas
+in future we would like to standardize on the UTF-8 encoding for
+source text. Until UTF-8 becomes the default format for source
+text, this pragma should be used to recognize UTF-8 in the source.
+When UTF-8 becomes the standard source format, this pragma will
+effectively become a no-op.
-=item *
+Enabling the C<utf8> pragma has the following effects:
-Regular expressions match characters instead of bytes. For instance,
-"." matches a character instead of a byte. (However, the C<\C> pattern
-is provided to force a match a single byte ("C<char>" in C, hence
-C<\C>).)
+=over
=item *
-Character classes in regular expressions match characters instead of
-bytes, and match against the character properties specified in the
-Unicode properties database. So C<\w> can be used to match an ideograph,
-for instance.
+Bytes in the source text that have their high-bit set will be treated
+as being part of a literal UTF-8 character. This includes most literals
+such as identifiers, string constants, constant regular expression patterns
+and package names.
=item *
-Named Unicode properties and block ranges make be used as character
-classes via the new C<\p{}> (matches property) and C<\P{}> (doesn't
-match property) constructs. For instance, C<\p{Lu}> matches any
-character with the Unicode uppercase property, while C<\p{M}> matches
-any mark character. Single letter properties may omit the brackets, so
-that can be written C<\pM> also. Many predefined character classes are
-available, such as C<\p{IsMirrored}> and C<\p{InTibetan}>.
+As a side effect, when this pragma is used within the main package,
+it also enables Unicode character semantics for the entire program.
+See L<perlunicode> for more on that.
-=item *
-
-The special pattern C<\X> match matches any extended Unicode sequence
-(a "combining character sequence" in Standardese), where the first
-character is a base character and subsequent characters are mark
-characters that apply to the base character. It is equivalent to
-C<(?:\PM\pM*)>.
+[XXX: split this out into separate "pragma" and/or -C command-line
+switch?]
=item *
-The C<tr///> operator translates characters instead of bytes. It can also
-be forced to translate between 8-bit codes and UTF-8 regardless of the
-surrounding utf8 state. For instance, if you know your input in Latin-1,
-you can say:
+In the absence of inputs marked as UTF-8, regular expressions within the
+scope of this pragma will default to using character semantics instead
+of byte semantics.
- use utf8;
- while (<>) {
- tr/\0-\xff//CU; # latin1 char to utf8
- ...
+ @bytes_or_chars = split //, $data; # may split to bytes if data
+ # $data isn't UTF-8
+ {
+ use utf8; # force char semantics
+ @chars = split //, $data; # splits characters
}
-Similarly you could translate your output with
-
- tr/\0-\x{ff}//UC; # utf8 to latin1 char
-
-No, C<s///> doesn't take /U or /C (yet?).
-
-=item *
-
-Case translation operators use the Unicode case translation tables.
-Note that C<uc()> translates to uppercase, while C<ucfirst> translates
-to titlecase (for languages that make the distinction). Naturally
-the corresponding backslash sequences have the same semantics.
-
-=item *
-
-Most operators that deal with positions or lengths in the string will
-automatically switch to using character positions, including C<chop()>,
-C<substr()>, C<pos()>, C<index()>, C<rindex()>, C<sprintf()>,
-C<write()>, and C<length()>. Operators that specifically don't switch
-include C<vec()>, C<pack()>, and C<unpack()>. Operators that really
-don't care include C<chomp()>, as well as any other operator that
-treats a string as a bucket of bits, such as C<sort()>, and the
-operators dealing with filenames.
-
-=item *
-
-The C<pack()>/C<unpack()> letters "C<c>" and "C<C>" do I<not> change,
-since they're often used for byte-oriented formats. (Again, think
-"C<char>" in the C language.) However, there is a new "C<U>" specifier
-that will convert between UTF-8 characters and integers. (It works
-outside of the utf8 pragma too.)
-
-=item *
-
-The C<chr()> and C<ord()> functions work on characters. This is like
-C<pack("U")> and C<unpack("U")>, not like C<pack("C")> and
-C<unpack("C")>. In fact, the latter are how you now emulate
-byte-oriented C<chr()> and C<ord()> under utf8.
-
-=item *
-
-And finally, C<scalar reverse()> reverses by character rather than by byte.
-
-=back
-
-=head1 CAVEATS
-
-As of yet, there is no method for automatically coercing input and
-output to some encoding other than UTF-8. This is planned in the near
-future, however.
+[XXX: Should this should be enabled like chr()/sprintf("%c") by looking
+at $^U instead?]
-In any event, you'll need to keep track of whether interfaces to other
-modules expect UTF-8 data or something else. The utf8 pragma does not
-magically mark strings for you in order to remember their encoding, nor
-will any automatic coercion happen (other than that eventually planned
-for I/O). If you want such automatic coercion, you can build yourself
-a set of pretty object-oriented modules. Expect it to run considerably
-slower than than this low-level support.
+=head1 SEE ALSO
-Use of locales with utf8 may lead to odd results. Currently there is
-some attempt to apply 8-bit locale info to characters in the range
-0..255, but this is demonstrably incorrect for locales that use
-characters above that range (when mapped into Unicode). It will also
-tend to run slower. Avoidance of locales is strongly encouraged.
+L<perlunicode>, L<byte>
=cut
diff --git a/lib/utf8_heavy.pl b/lib/utf8_heavy.pl
index 0f588237eb..8649e9e07e 100644
--- a/lib/utf8_heavy.pl
+++ b/lib/utf8_heavy.pl
@@ -38,7 +38,7 @@ sub SWASHNEW {
if ($list) {
my @tmp = split(/^/m, $list);
my %seen;
- local $^W = 0;
+ no warnings;
$extras = join '', grep /^[^0-9a-fA-F]/, @tmp;
$list = join '',
sort { hex $a <=> hex $b }
diff --git a/lib/warnings.pm b/lib/warnings.pm
index e15d364193..977395b74e 100644
--- a/lib/warnings.pm
+++ b/lib/warnings.pm
@@ -115,14 +115,15 @@ sub bits {
my $catmask ;
my $fatal = 0 ;
foreach my $word (@_) {
- if ($word eq 'FATAL')
- { $fatal = 1 }
- elsif ($catmask = $Bits{$word}) {
- $mask |= $catmask ;
- $mask |= $DeadBits{$word} if $fatal ;
+ if ($word eq 'FATAL') {
+ $fatal = 1;
+ }
+ else {
+ if ($catmask = $Bits{$word}) {
+ $mask |= $catmask ;
+ $mask |= $DeadBits{$word} if $fatal ;
+ }
}
- else
- { croak "unknown warning category '$word'" }
}
return $mask ;
View Lorry Controller Status