Commit | Line | Data |
4633a7c4 |
1 | package Text::Wrap; |
2 | |
9a09eeb5 |
3 | require Exporter; |
4633a7c4 |
4 | |
0c5a43b5 |
5 | @ISA = qw(Exporter); |
6 | @EXPORT = qw(wrap fill); |
7 | @EXPORT_OK = qw($columns $break $huge); |
4633a7c4 |
8 | |
95925ace |
9 | $VERSION = 2006.0711; |
b1a524cb |
10 | |
37a581db |
11 | use vars qw($VERSION $columns $debug $break $huge $unexpand $tabstop |
8dfcc161 |
12 | $separator $separator2); |
9a09eeb5 |
13 | use strict; |
b1a524cb |
14 | |
4633a7c4 |
15 | BEGIN { |
9a09eeb5 |
16 | $columns = 76; # <= screen width |
17 | $debug = 0; |
18 | $break = '\s'; |
3e2ea5df |
19 | $huge = 'wrap'; # alternatively: 'die' or 'overflow' |
37a581db |
20 | $unexpand = 1; |
21 | $tabstop = 8; |
22 | $separator = "\n"; |
8dfcc161 |
23 | $separator2 = undef; |
4633a7c4 |
24 | } |
25 | |
9a09eeb5 |
26 | use Text::Tabs qw(expand unexpand); |
27 | |
4633a7c4 |
28 | sub wrap |
29 | { |
9a09eeb5 |
30 | my ($ip, $xp, @t) = @_; |
31 | |
37a581db |
32 | local($Text::Tabs::tabstop) = $tabstop; |
9a09eeb5 |
33 | my $r = ""; |
3e2ea5df |
34 | my $tail = pop(@t); |
37a581db |
35 | my $t = expand(join("", (map { /\s+\z/ ? ( $_ ) : ($_, ' ') } @t), $tail)); |
9a09eeb5 |
36 | my $lead = $ip; |
37 | my $ll = $columns - length(expand($ip)) - 1; |
718842b0 |
38 | $ll = 0 if $ll < 0; |
9a09eeb5 |
39 | my $nll = $columns - length(expand($xp)) - 1; |
40 | my $nl = ""; |
41 | my $remainder = ""; |
42 | |
37a581db |
43 | use re 'taint'; |
44 | |
3e2ea5df |
45 | pos($t) = 0; |
95925ace |
46 | while ($t !~ /\G(?:$break)*\Z/gc) { |
47 | if ($t =~ /\G([^\n]{0,$ll})($break|\n+|\z)/xmgc) { |
37a581db |
48 | $r .= $unexpand |
49 | ? unexpand($nl . $lead . $1) |
50 | : $nl . $lead . $1; |
9a09eeb5 |
51 | $remainder = $2; |
3e2ea5df |
52 | } elsif ($huge eq 'wrap' && $t =~ /\G([^\n]{$ll})/gc) { |
37a581db |
53 | $r .= $unexpand |
54 | ? unexpand($nl . $lead . $1) |
55 | : $nl . $lead . $1; |
8dfcc161 |
56 | $remainder = defined($separator2) ? $separator2 : $separator; |
95925ace |
57 | } elsif ($huge eq 'overflow' && $t =~ /\G([^\n]*?)($break|\n+|\z)/xmgc) { |
37a581db |
58 | $r .= $unexpand |
59 | ? unexpand($nl . $lead . $1) |
60 | : $nl . $lead . $1; |
3e2ea5df |
61 | $remainder = $2; |
9a09eeb5 |
62 | } elsif ($huge eq 'die') { |
63 | die "couldn't wrap '$t'"; |
95925ace |
64 | } elsif ($columns < 2) { |
65 | warn "Increasing \$Text::Wrap::columns from $columns to 2"; |
66 | $columns = 2; |
67 | return ($ip, $xp, @t); |
9a09eeb5 |
68 | } else { |
69 | die "This shouldn't happen"; |
70 | } |
71 | |
72 | $lead = $xp; |
73 | $ll = $nll; |
8dfcc161 |
74 | $nl = defined($separator2) |
75 | ? ($remainder eq "\n" |
76 | ? "\n" |
77 | : $separator2) |
78 | : $separator; |
9b599b2a |
79 | } |
9a09eeb5 |
80 | $r .= $remainder; |
b1a524cb |
81 | |
9a09eeb5 |
82 | print "-----------$r---------\n" if $debug; |
b1a524cb |
83 | |
3e2ea5df |
84 | print "Finish up with '$lead'\n" if $debug; |
b1a524cb |
85 | |
3e2ea5df |
86 | $r .= $lead . substr($t, pos($t), length($t)-pos($t)) |
87 | if pos($t) ne length($t); |
b1a524cb |
88 | |
9a09eeb5 |
89 | print "-----------$r---------\n" if $debug;; |
3e2ea5df |
90 | |
9a09eeb5 |
91 | return $r; |
4633a7c4 |
92 | } |
93 | |
0c5a43b5 |
94 | sub fill |
95 | { |
96 | my ($ip, $xp, @raw) = @_; |
97 | my @para; |
98 | my $pp; |
99 | |
100 | for $pp (split(/\n\s+/, join("\n",@raw))) { |
101 | $pp =~ s/\s+/ /g; |
102 | my $x = wrap($ip, $xp, $pp); |
103 | push(@para, $x); |
104 | } |
105 | |
106 | # if paragraph_indent is the same as line_indent, |
107 | # separate paragraphs with blank lines |
108 | |
3e2ea5df |
109 | my $ps = ($ip eq $xp) ? "\n\n" : "\n"; |
110 | return join ($ps, @para); |
0c5a43b5 |
111 | } |
112 | |
4633a7c4 |
113 | 1; |
68e56a55 |
114 | __END__ |
b1a524cb |
115 | |
116 | =head1 NAME |
117 | |
118 | Text::Wrap - line wrapping to form simple paragraphs |
119 | |
120 | =head1 SYNOPSIS |
121 | |
3e2ea5df |
122 | B<Example 1> |
123 | |
b1a524cb |
124 | use Text::Wrap |
125 | |
3e2ea5df |
126 | $initial_tab = "\t"; # Tab before first line |
127 | $subsequent_tab = ""; # All other lines flush left |
128 | |
b1a524cb |
129 | print wrap($initial_tab, $subsequent_tab, @text); |
0c5a43b5 |
130 | print fill($initial_tab, $subsequent_tab, @text); |
b1a524cb |
131 | |
7b614c55 |
132 | $lines = wrap($initial_tab, $subsequent_tab, @text); |
3e2ea5df |
133 | |
134 | @paragraphs = fill($initial_tab, $subsequent_tab, @text); |
135 | |
136 | B<Example 2> |
137 | |
9a09eeb5 |
138 | use Text::Wrap qw(wrap $columns $huge); |
b1a524cb |
139 | |
3e2ea5df |
140 | $columns = 132; # Wrap at 132 characters |
9a09eeb5 |
141 | $huge = 'die'; |
142 | $huge = 'wrap'; |
3e2ea5df |
143 | $huge = 'overflow'; |
b1a524cb |
144 | |
3e2ea5df |
145 | B<Example 3> |
95925ace |
146 | |
3e2ea5df |
147 | use Text::Wrap |
b1a524cb |
148 | |
3e2ea5df |
149 | $Text::Wrap::columns = 72; |
150 | print wrap('', '', @text); |
9a09eeb5 |
151 | |
3e2ea5df |
152 | =head1 DESCRIPTION |
9a09eeb5 |
153 | |
37a581db |
154 | C<Text::Wrap::wrap()> is a very simple paragraph formatter. It formats a |
3c4b39be |
155 | single paragraph at a time by breaking lines at word boundaries. |
3e2ea5df |
156 | Indentation is controlled for the first line (C<$initial_tab>) and |
718842b0 |
157 | all subsequent lines (C<$subsequent_tab>) independently. Please note: |
3e2ea5df |
158 | C<$initial_tab> and C<$subsequent_tab> are the literal strings that will |
3c4b39be |
159 | be used: it is unlikely you would want to pass in a number. |
3e2ea5df |
160 | |
37a581db |
161 | Text::Wrap::fill() is a simple multi-paragraph formatter. It formats |
162 | each paragraph separately and then joins them together when it's done. It |
818675a5 |
163 | will destroy any whitespace in the original text. It breaks text into |
37a581db |
164 | paragraphs by looking for whitespace after a newline. In other respects |
165 | it acts like wrap(). |
166 | |
95925ace |
167 | Both C<wrap()> and C<fill()> return a single string. |
168 | |
37a581db |
169 | =head1 OVERRIDES |
170 | |
171 | C<Text::Wrap::wrap()> has a number of variables that control its behavior. |
172 | Because other modules might be using C<Text::Wrap::wrap()> it is suggested |
173 | that you leave these variables alone! If you can't do that, then |
174 | use C<local($Text::Wrap::VARIABLE) = YOURVALUE> when you change the |
175 | values so that the original value is restored. This C<local()> trick |
176 | will not work if you import the variable into your own namespace. |
177 | |
3e2ea5df |
178 | Lines are wrapped at C<$Text::Wrap::columns> columns. C<$Text::Wrap::columns> |
179 | should be set to the full width of your output device. In fact, |
180 | every resulting line will have length of no more than C<$columns - 1>. |
181 | |
37a581db |
182 | It is possible to control which characters terminate words by |
183 | modifying C<$Text::Wrap::break>. Set this to a string such as |
184 | C<'[\s:]'> (to break before spaces or colons) or a pre-compiled regexp |
185 | such as C<qr/[\s']/> (to break before spaces or apostrophes). The |
186 | default is simply C<'\s'>; that is, words are terminated by spaces. |
187 | (This means, among other things, that trailing punctuation such as |
188 | full stops or commas stay with the word they are "attached" to.) |
189 | |
3e2ea5df |
190 | Beginner note: In example 2, above C<$columns> is imported into |
191 | the local namespace, and set locally. In example 3, |
192 | C<$Text::Wrap::columns> is set in its own namespace without importing it. |
193 | |
37a581db |
194 | C<Text::Wrap::wrap()> starts its work by expanding all the tabs in its |
195 | input into spaces. The last thing it does it to turn spaces back |
196 | into tabs. If you do not want tabs in your results, set |
818675a5 |
197 | C<$Text::Wrap::unexpand> to a false value. Likewise if you do not |
37a581db |
198 | want to use 8-character tabstops, set C<$Text::Wrap::tabstop> to |
199 | the number of characters you do want for your tabstops. |
200 | |
201 | If you want to separate your lines with something other than C<\n> |
8dfcc161 |
202 | then set C<$Text::Wrap::separator> to your preference. This replaces |
203 | all newlines with C<$Text::Wrap::separator>. If you just to preserve |
204 | existing newlines but add new breaks with something else, set |
205 | C<$Text::Wrap::separator2> instead. |
37a581db |
206 | |
3e2ea5df |
207 | When words that are longer than C<$columns> are encountered, they |
208 | are broken up. C<wrap()> adds a C<"\n"> at column C<$columns>. |
209 | This behavior can be overridden by setting C<$huge> to |
210 | 'die' or to 'overflow'. When set to 'die', large words will cause |
211 | C<die()> to be called. When set to 'overflow', large words will be |
212 | left intact. |
9b599b2a |
213 | |
37a581db |
214 | Historical notes: 'die' used to be the default value of |
3e2ea5df |
215 | C<$huge>. Now, 'wrap' is the default value. |
216 | |
95925ace |
217 | =head1 EXAMPLES |
218 | |
219 | Code: |
220 | |
221 | print wrap("\t","",<<END); |
222 | This is a bit of text that forms |
223 | a normal book-style indented paragraph |
224 | END |
225 | |
226 | Result: |
227 | |
228 | " This is a bit of text that forms |
229 | a normal book-style indented paragraph |
230 | " |
231 | |
232 | Code: |
233 | |
234 | $Text::Wrap::columns=20; |
235 | $Text::Wrap::separator="|"; |
236 | print wrap("","","This is a bit of text that forms a normal book-style paragraph"); |
237 | |
238 | Result: |
b1a524cb |
239 | |
95925ace |
240 | "This is a bit of|text that forms a|normal book-style|paragraph" |
b1a524cb |
241 | |
8dfcc161 |
242 | =head1 LICENSE |
b1a524cb |
243 | |
4fc6b8d8 |
244 | David Muir Sharnoff <muir@idiom.com> with help from Tim Pierce and |
95925ace |
245 | many many others. Copyright (C) 1996-2006 David Muir Sharnoff. |
8dfcc161 |
246 | This module may be modified, used, copied, and redistributed at |
247 | your own risk. Publicly redistributed modified versions must use |
248 | a different name. |
b1a524cb |
249 | |