man.pm

UNIX下perl实现代码

# Pod::Man -- Convert POD data to formatted *roff input.
# $Id: Man.pm,v 1.15 2001/02/10 06:50:22 eagle Exp $
#
# Copyright 1999, 2000, 2001 by Russ Allbery <[e-mail]>
#
# This program is free software; you can redistribute it and/or modify it
# under the same terms as Perl itself.
#
# This module is intended to be a replacement for the pod2man script
# distributed with versions of Perl prior to 5.6, and attempts to match its
# output except for some specific circumstances where other decisions seemed
# to produce better output.  It uses Pod::Parser and is designed to be easy
# to subclass.
#
# Perl core hackers, please note that this module is also separately
# maintained outside of the Perl core as part of the podlators.  Please send
# me any patches at the address above in addition to sending them to the
# standard Perl mailing lists.

############################################################################
# Modules and declarations
############################################################################

package Pod::Man;

require 5.004;

use Carp qw(carp croak);
use Pod::Parser ();

use strict;
use subs qw(makespace);
use vars qw(@ISA %ESCAPES $PREAMBLE $VERSION);

@ISA = qw(Pod::Parser);

# Don't use the CVS revision as the version, since this module is also in
# Perl core and too many things could munge CVS magic revision strings.
# This number should ideally be the same as the CVS revision in podlators,
# however.
$VERSION = 1.15;


############################################################################
# Preamble and *roff output tables
############################################################################

# The following is the static preamble which starts all *roff output we
# generate.  It's completely static except for the font to use as a
# fixed-width font, which is designed by @CFONT@, and the left and right
# quotes to use for C<> text, designated by @LQOUTE@ and @RQUOTE@.
# $PREAMBLE should therefore be run through s/\@CFONT\@/<font>/g before
# output.
$PREAMBLE = <<'----END OF PREAMBLE----';
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Ip \" List item
.br
.ie \\n(.$>=3 .ne \\$3
.el .ne 3
.IP "\\$1" \\$2
..
.de Vb \" Begin verbatim text
.ft @CFONT@
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R

.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  | will give a
.\" real vertical bar.  \*(C+ will give a nicer C++.  Capital omega is used
.\" to do unbreakable dashes and therefore won't be available.  \*(C` and
.\" \*(C' expand to `' in nroff, nothing in troff, for use with C<>
.tr \(*W-|\(bv\*(Tr
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` @LQUOTE@
.    ds C' @RQUOTE@
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr
.\" for titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and
.\" index entries marked with X<> in POD.  Of course, you'll have to process
.\" the output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it
.\" makes way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.bd B 3
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
----END OF PREAMBLE----
#`# for cperl-mode

# This table is taken nearly verbatim from Tom Christiansen's pod2man.  It
# assumes that the standard preamble has already been printed, since that's
# what defines all of the accent marks.  Note that some of these are quoted
# with double quotes since they contain embedded single quotes, so use \\
# uniformly for backslash for readability.
%ESCAPES = (
    'amp'       =>    '&',      # ampersand
    'lt'        =>    '<',      # left chevron, less-than
    'gt'        =>    '>',      # right chevron, greater-than
    'quot'      =>    '"',      # double quote
    'sol'       =>    '/',      # solidus (forward slash)
    'verbar'    =>    '|',      # vertical bar

    'Aacute'    =>    "A\\*'",  # capital A, acute accent
    'aacute'    =>    "a\\*'",  # small a, acute accent
    'Acirc'     =>    'A\\*^',  # capital A, circumflex accent
    'acirc'     =>    'a\\*^',  # small a, circumflex accent
    'AElig'     =>    '\*(AE',  # capital AE diphthong (ligature)
    'aelig'     =>    '\*(ae',  # small ae diphthong (ligature)
    'Agrave'    =>    "A\\*`",  # capital A, grave accent
    'agrave'    =>    "A\\*`",  # small a, grave accent
    'Aring'     =>    'A\\*o',  # capital A, ring
    'aring'     =>    'a\\*o',  # small a, ring
    'Atilde'    =>    'A\\*~',  # capital A, tilde
    'atilde'    =>    'a\\*~',  # small a, tilde
    'Auml'      =>    'A\\*:',  # capital A, dieresis or umlaut mark
    'auml'      =>    'a\\*:',  # small a, dieresis or umlaut mark
    'Ccedil'    =>    'C\\*,',  # capital C, cedilla
    'ccedil'    =>    'c\\*,',  # small c, cedilla
    'Eacute'    =>    "E\\*'",  # capital E, acute accent
    'eacute'    =>    "e\\*'",  # small e, acute accent
    'Ecirc'     =>    'E\\*^',  # capital E, circumflex accent
    'ecirc'     =>    'e\\*^',  # small e, circumflex accent
    'Egrave'    =>    'E\\*`',  # capital E, grave accent
    'egrave'    =>    'e\\*`',  # small e, grave accent
    'ETH'       =>    '\\*(D-', # capital Eth, Icelandic
    'eth'       =>    '\\*(d-', # small eth, Icelandic
    'Euml'      =>    'E\\*:',  # capital E, dieresis or umlaut mark
    'euml'      =>    'e\\*:',  # small e, dieresis or umlaut mark
    'Iacute'    =>    "I\\*'",  # capital I, acute accent
    'iacute'    =>    "i\\*'",  # small i, acute accent
    'Icirc'     =>    'I\\*^',  # capital I, circumflex accent
    'icirc'     =>    'i\\*^',  # small i, circumflex accent
    'Igrave'    =>    'I\\*`',  # capital I, grave accent
    'igrave'    =>    'i\\*`',  # small i, grave accent
    'Iuml'      =>    'I\\*:',  # capital I, dieresis or umlaut mark
    'iuml'      =>    'i\\*:',  # small i, dieresis or umlaut mark
    'Ntilde'    =>    'N\*~',   # capital N, tilde
    'ntilde'    =>    'n\*~',   # small n, tilde
    'Oacute'    =>    "O\\*'",  # capital O, acute accent
    'oacute'    =>    "o\\*'",  # small o, acute accent
    'Ocirc'     =>    'O\\*^',  # capital O, circumflex accent
    'ocirc'     =>    'o\\*^',  # small o, circumflex accent
    'Ograve'    =>    'O\\*`',  # capital O, grave accent
    'ograve'    =>    'o\\*`',  # small o, grave accent
    'Oslash'    =>    'O\\*/',  # capital O, slash
    'oslash'    =>    'o\\*/',  # small o, slash
    'Otilde'    =>    'O\\*~',  # capital O, tilde
    'otilde'    =>    'o\\*~',  # small o, tilde
    'Ouml'      =>    'O\\*:',  # capital O, dieresis or umlaut mark
    'ouml'      =>    'o\\*:',  # small o, dieresis or umlaut mark
    'szlig'     =>    '\*8',    # small sharp s, German (sz ligature)
    'THORN'     =>    '\\*(Th', # capital THORN, Icelandic
    'thorn'     =>    '\\*(th', # small thorn, Icelandic
    'Uacute'    =>    "U\\*'",  # capital U, acute accent
    'uacute'    =>    "u\\*'",  # small u, acute accent
    'Ucirc'     =>    'U\\*^',  # capital U, circumflex accent
    'ucirc'     =>    'u\\*^',  # small u, circumflex accent
    'Ugrave'    =>    'U\\*`',  # capital U, grave accent
    'ugrave'    =>    'u\\*`',  # small u, grave accent
    'Uuml'      =>    'U\\*:',  # capital U, dieresis or umlaut mark
    'uuml'      =>    'u\\*:',  # small u, dieresis or umlaut mark
    'Yacute'    =>    "Y\\*'",  # capital Y, acute accent
    'yacute'    =>    "y\\*'",  # small y, acute accent
    'yuml'      =>    'y\\*:',  # small y, dieresis or umlaut mark
);


############################################################################
# Static helper functions
############################################################################

# Protect leading quotes and periods against interpretation as commands.
# Also protect anything starting with a backslash, since it could expand
# or hide something that *roff would interpret as a command.  This is
# overkill, but it's much simpler than trying to parse *roff here.
sub protect {
    local $_ = shift;
    s/^([.\'\\])/\\&$1/mg;
    $_;
}

# Translate a font string into an escape.
sub toescape { (length ($_[0]) > 1 ? '\f(' : '\f') . $_[0] }


############################################################################
# Initialization
############################################################################

# Initialize the object.  Here, we also process any additional options
# passed to the constructor or set up defaults if none were given.  center
# is the centered title, release is the version number, and date is the date
# for the documentation.  Note that we can't know what file name we're
# processing due to the architecture of Pod::Parser, so that *has* to either
# be passed to the constructor or set separately with Pod::Man::name().
sub initialize {
    my $self = shift;

    # Figure out the fixed-width font.  If user-supplied, make sure that
    # they are the right length.
    for (qw/fixed fixedbold fixeditalic fixedbolditalic/) {
        if (defined $$self{$_}) {
            if (length ($$self{$_}) < 1 || length ($$self{$_}) > 2) {
                croak qq(roff font should be 1 or 2 chars,)
                    . qq( not "$$self{$_}");
            }
        } else {
            $$self{$_} = '';
        }
    }

    # Set the default fonts.  We can't be sure what fixed bold-italic is
    # going to be called, so default to just bold.
    $$self{fixed}           ||= 'CW';
    $$self{fixedbold}       ||= 'CB';
    $$self{fixeditalic}     ||= 'CI';
    $$self{fixedbolditalic} ||= 'CB';

    # Set up a table of font escapes.  First number is fixed-width, second
    # is bold, third is italic.
    $$self{FONTS} = { '000' => '\fR', '001' => '\fI',
                      '010' => '\fB', '011' => '\f(BI',
                      '100' => toescape ($$self{fixed}),
                      '101' => toescape ($$self{fixeditalic}),
                      '110' => toescape ($$self{fixedbold}),
                      '111' => toescape ($$self{fixedbolditalic})};

    # Extra stuff for page titles.
    $$self{center} = 'User Contributed Perl Documentation'
        unless defined $$self{center};
    $$self{indent}  = 4 unless defined $$self{indent};

    # We used to try first to get the version number from a local binary,
    # but we shouldn't need that any more.  Get the version from the running
    # Perl.  Work a little magic to handle subversions correctly under both
    # the pre-5.6 and the post-5.6 version numbering schemes.
    if (!defined $$self{release}) {
        my @version = ($] =~ /^(\d+)\.(\d{3})(\d{0,3})$/);
        $version[2] ||= 0;
        $version[2] *= 10 ** (3 - length $version[2]);
        for (@version) { $_ += 0 }
        $$self{release} = 'perl v' . join ('.', @version);
    }

    # Double quotes in things that will be quoted.
    for (qw/center date release/) {
        $$self{$_} =~ s/\"/\"\"/g if $$self{$_};