summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/Text/Wrap.pm
blob: d364cfc11956628022b65096b8eaddc9f1eb68a3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
package Text::Wrap;

require Exporter;

@ISA = qw(Exporter);
@EXPORT = qw(wrap fill);
@EXPORT_OK = qw($columns $break $huge);

$VERSION = 2005.0824_01;

use vars qw($VERSION $columns $debug $break $huge $unexpand $tabstop
	$separator $separator2);
use strict;

BEGIN	{
	$columns = 76;  # <= screen width
	$debug = 0;
	$break = '\s';
	$huge = 'wrap'; # alternatively: 'die' or 'overflow'
	$unexpand = 1;
	$tabstop = 8;
	$separator = "\n";
	$separator2 = undef;
}

use Text::Tabs qw(expand unexpand);

sub wrap
{
	my ($ip, $xp, @t) = @_;

	local($Text::Tabs::tabstop) = $tabstop;
	my $r = "";
	my $tail = pop(@t);
	my $t = expand(join("", (map { /\s+\z/ ? ( $_ ) : ($_, ' ') } @t), $tail));
	my $lead = $ip;
	my $ll = $columns - length(expand($ip)) - 1;
	$ll = 0 if $ll < 0;
	my $nll = $columns - length(expand($xp)) - 1;
	my $nl = "";
	my $remainder = "";

	use re 'taint';

	pos($t) = 0;
	while ($t !~ /\G\s*\Z/gc) {
		if ($t =~ /\G([^\n]{0,$ll})($break|\n*\z)/xmgc) {
			$r .= $unexpand 
				? unexpand($nl . $lead . $1)
				: $nl . $lead . $1;
			$remainder = $2;
		} elsif ($huge eq 'wrap' && $t =~ /\G([^\n]{$ll})/gc) {
			$r .= $unexpand 
				? unexpand($nl . $lead . $1)
				: $nl . $lead . $1;
			$remainder = defined($separator2) ? $separator2 : $separator;
		} elsif ($huge eq 'overflow' && $t =~ /\G([^\n]*?)($break|\z)/xmgc) {
			$r .= $unexpand 
				? unexpand($nl . $lead . $1)
				: $nl . $lead . $1;
			$remainder = $2;
		} elsif ($huge eq 'die') {
			die "couldn't wrap '$t'";
		} else {
			die "This shouldn't happen";
		}
			
		$lead = $xp;
		$ll = $nll;
		$nl = defined($separator2)
			? ($remainder eq "\n"
				? "\n"
				: $separator2)
			: $separator;
	}
	$r .= $remainder;

	print "-----------$r---------\n" if $debug;

	print "Finish up with '$lead'\n" if $debug;

	$r .= $lead . substr($t, pos($t), length($t)-pos($t))
		if pos($t) ne length($t);

	print "-----------$r---------\n" if $debug;;

	return $r;
}

sub fill 
{
	my ($ip, $xp, @raw) = @_;
	my @para;
	my $pp;

	for $pp (split(/\n\s+/, join("\n",@raw))) {
		$pp =~ s/\s+/ /g;
		my $x = wrap($ip, $xp, $pp);
		push(@para, $x);
	}

	# if paragraph_indent is the same as line_indent, 
	# separate paragraphs with blank lines

	my $ps = ($ip eq $xp) ? "\n\n" : "\n";
	return join ($ps, @para);
}

1;
__END__

=head1 NAME

Text::Wrap - line wrapping to form simple paragraphs

=head1 SYNOPSIS 

B<Example 1>

	use Text::Wrap

	$initial_tab = "\t";	# Tab before first line
	$subsequent_tab = "";	# All other lines flush left

	print wrap($initial_tab, $subsequent_tab, @text);
	print fill($initial_tab, $subsequent_tab, @text);

	$lines = wrap($initial_tab, $subsequent_tab, @text);

	@paragraphs = fill($initial_tab, $subsequent_tab, @text);

B<Example 2>

	use Text::Wrap qw(wrap $columns $huge);

	$columns = 132;		# Wrap at 132 characters
	$huge = 'die';
	$huge = 'wrap';
	$huge = 'overflow';

B<Example 3>

	use Text::Wrap

	$Text::Wrap::columns = 72;
	print wrap('', '', @text);

=head1 DESCRIPTION

C<Text::Wrap::wrap()> is a very simple paragraph formatter.  It formats a
single paragraph at a time by breaking lines at word boundries.
Indentation is controlled for the first line (C<$initial_tab>) and
all subsequent lines (C<$subsequent_tab>) independently.  Please note: 
C<$initial_tab> and C<$subsequent_tab> are the literal strings that will
be used: it is unlikley you would want to pass in a number.

Text::Wrap::fill() is a simple multi-paragraph formatter.  It formats
each paragraph separately and then joins them together when it's done.  It
will destroy any whitespace in the original text.  It breaks text into
paragraphs by looking for whitespace after a newline.  In other respects
it acts like wrap().

=head1 OVERRIDES

C<Text::Wrap::wrap()> has a number of variables that control its behavior.
Because other modules might be using C<Text::Wrap::wrap()> it is suggested
that you leave these variables alone!  If you can't do that, then 
use C<local($Text::Wrap::VARIABLE) = YOURVALUE> when you change the
values so that the original value is restored.  This C<local()> trick
will not work if you import the variable into your own namespace.

Lines are wrapped at C<$Text::Wrap::columns> columns.  C<$Text::Wrap::columns>
should be set to the full width of your output device.  In fact,
every resulting line will have length of no more than C<$columns - 1>.  

It is possible to control which characters terminate words by
modifying C<$Text::Wrap::break>. Set this to a string such as
C<'[\s:]'> (to break before spaces or colons) or a pre-compiled regexp
such as C<qr/[\s']/> (to break before spaces or apostrophes). The
default is simply C<'\s'>; that is, words are terminated by spaces.
(This means, among other things, that trailing punctuation  such as
full stops or commas stay with the word they are "attached" to.)

Beginner note: In example 2, above C<$columns> is imported into
the local namespace, and set locally.  In example 3,
C<$Text::Wrap::columns> is set in its own namespace without importing it.

C<Text::Wrap::wrap()> starts its work by expanding all the tabs in its
input into spaces.  The last thing it does it to turn spaces back
into tabs.  If you do not want tabs in your results, set 
C<$Text::Wrap::unexpand> to a false value.  Likewise if you do not
want to use 8-character tabstops, set C<$Text::Wrap::tabstop> to
the number of characters you do want for your tabstops.

If you want to separate your lines with something other than C<\n>
then set C<$Text::Wrap::separator> to your preference.  This replaces
all newlines with C<$Text::Wrap::separator>.  If you just to preserve
existing newlines but add new breaks with something else, set 
C<$Text::Wrap::separator2> instead.

When words that are longer than C<$columns> are encountered, they
are broken up.  C<wrap()> adds a C<"\n"> at column C<$columns>.
This behavior can be overridden by setting C<$huge> to
'die' or to 'overflow'.  When set to 'die', large words will cause
C<die()> to be called.  When set to 'overflow', large words will be
left intact.  

Historical notes: 'die' used to be the default value of
C<$huge>.  Now, 'wrap' is the default value.

=head1 EXAMPLE

	print wrap("\t","","This is a bit of text that forms 
		a normal book-style paragraph");

=head1 LICENSE

David Muir Sharnoff <muir@idiom.com> with help from Tim Pierce and
many many others.  Copyright (C) 1996-2002 David Muir Sharnoff.  
This module may be modified, used, copied, and redistributed at
your own risk.  Publicly redistributed modified versions must use 
a different name.