Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | .\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 |
2 | .\" | |
3 | .\" Standard preamble: | |
4 | .\" ======================================================================== | |
5 | .de Sh \" Subsection heading | |
6 | .br | |
7 | .if t .Sp | |
8 | .ne 5 | |
9 | .PP | |
10 | \fB\\$1\fR | |
11 | .PP | |
12 | .. | |
13 | .de Sp \" Vertical space (when we can't use .PP) | |
14 | .if t .sp .5v | |
15 | .if n .sp | |
16 | .. | |
17 | .de Vb \" Begin verbatim text | |
18 | .ft CW | |
19 | .nf | |
20 | .ne \\$1 | |
21 | .. | |
22 | .de Ve \" End verbatim text | |
23 | .ft R | |
24 | .fi | |
25 | .. | |
26 | .\" Set up some character translations and predefined strings. \*(-- will | |
27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left | |
28 | .\" double quote, and \*(R" will give a right double quote. | will give a | |
29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to | |
30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' | |
31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. | |
32 | .tr \(*W-|\(bv\*(Tr | |
33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' | |
34 | .ie n \{\ | |
35 | . ds -- \(*W- | |
36 | . ds PI pi | |
37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch | |
38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch | |
39 | . ds L" "" | |
40 | . ds R" "" | |
41 | . ds C` "" | |
42 | . ds C' "" | |
43 | 'br\} | |
44 | .el\{\ | |
45 | . ds -- \|\(em\| | |
46 | . ds PI \(*p | |
47 | . ds L" `` | |
48 | . ds R" '' | |
49 | 'br\} | |
50 | .\" | |
51 | .\" If the F register is turned on, we'll generate index entries on stderr for | |
52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index | |
53 | .\" entries marked with X<> in POD. Of course, you'll have to process the | |
54 | .\" output yourself in some meaningful fashion. | |
55 | .if \nF \{\ | |
56 | . de IX | |
57 | . tm Index:\\$1\t\\n%\t"\\$2" | |
58 | .. | |
59 | . nr % 0 | |
60 | . rr F | |
61 | .\} | |
62 | .\" | |
63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes | |
64 | .\" way too many mistakes in technical documents. | |
65 | .hy 0 | |
66 | .if n .na | |
67 | .\" | |
68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). | |
69 | .\" Fear. Run. Save yourself. No user-serviceable parts. | |
70 | . \" fudge factors for nroff and troff | |
71 | .if n \{\ | |
72 | . ds #H 0 | |
73 | . ds #V .8m | |
74 | . ds #F .3m | |
75 | . ds #[ \f1 | |
76 | . ds #] \fP | |
77 | .\} | |
78 | .if t \{\ | |
79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) | |
80 | . ds #V .6m | |
81 | . ds #F 0 | |
82 | . ds #[ \& | |
83 | . ds #] \& | |
84 | .\} | |
85 | . \" simple accents for nroff and troff | |
86 | .if n \{\ | |
87 | . ds ' \& | |
88 | . ds ` \& | |
89 | . ds ^ \& | |
90 | . ds , \& | |
91 | . ds ~ ~ | |
92 | . ds / | |
93 | .\} | |
94 | .if t \{\ | |
95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" | |
96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' | |
97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' | |
98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' | |
99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' | |
100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' | |
101 | .\} | |
102 | . \" troff and (daisy-wheel) nroff accents | |
103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' | |
104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' | |
105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] | |
106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' | |
107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' | |
108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] | |
109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] | |
110 | .ds ae a\h'-(\w'a'u*4/10)'e | |
111 | .ds Ae A\h'-(\w'A'u*4/10)'E | |
112 | . \" corrections for vroff | |
113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' | |
114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' | |
115 | . \" for low resolution devices (crt and lpr) | |
116 | .if \n(.H>23 .if \n(.V>19 \ | |
117 | \{\ | |
118 | . ds : e | |
119 | . ds 8 ss | |
120 | . ds o a | |
121 | . ds d- d\h'-1'\(ga | |
122 | . ds D- D\h'-1'\(hy | |
123 | . ds th \o'bp' | |
124 | . ds Th \o'LP' | |
125 | . ds ae ae | |
126 | . ds Ae AE | |
127 | .\} | |
128 | .rm #[ #] #H #V #F C | |
129 | .\" ======================================================================== | |
130 | .\" | |
131 | .IX Title "PERLLOL 1" | |
132 | .TH PERLLOL 1 "2002-06-08" "perl v5.8.0" "Perl Programmers Reference Guide" | |
133 | .SH "NAME" | |
134 | perllol \- Manipulating Arrays of Arrays in Perl | |
135 | .SH "DESCRIPTION" | |
136 | .IX Header "DESCRIPTION" | |
137 | .Sh "Declaration and Access of Arrays of Arrays" | |
138 | .IX Subsection "Declaration and Access of Arrays of Arrays" | |
139 | The simplest thing to build is an array of arrays (sometimes imprecisely | |
140 | called a list of lists). It's reasonably easy to understand, and | |
141 | almost everything that applies here will also be applicable later | |
142 | on with the fancier data structures. | |
143 | .PP | |
144 | An array of an array is just a regular old array \f(CW@AoA\fR that you can | |
145 | get at with two subscripts, like \f(CW$AoA[3][2]\fR. Here's a declaration | |
146 | of the array: | |
147 | .PP | |
148 | .Vb 6 | |
149 | \& # assign to our array, an array of array references | |
150 | \& @AoA = ( | |
151 | \& [ "fred", "barney" ], | |
152 | \& [ "george", "jane", "elroy" ], | |
153 | \& [ "homer", "marge", "bart" ], | |
154 | \& ); | |
155 | .Ve | |
156 | .PP | |
157 | .Vb 2 | |
158 | \& print $AoA[2][2]; | |
159 | \& bart | |
160 | .Ve | |
161 | .PP | |
162 | Now you should be very careful that the outer bracket type | |
163 | is a round one, that is, a parenthesis. That's because you're assigning to | |
164 | an \f(CW@array\fR, so you need parentheses. If you wanted there \fInot\fR to be an \f(CW@AoA\fR, | |
165 | but rather just a reference to it, you could do something more like this: | |
166 | .PP | |
167 | .Vb 6 | |
168 | \& # assign a reference to array of array references | |
169 | \& $ref_to_AoA = [ | |
170 | \& [ "fred", "barney", "pebbles", "bambam", "dino", ], | |
171 | \& [ "homer", "bart", "marge", "maggie", ], | |
172 | \& [ "george", "jane", "elroy", "judy", ], | |
173 | \& ]; | |
174 | .Ve | |
175 | .PP | |
176 | .Vb 1 | |
177 | \& print $ref_to_AoA->[2][2]; | |
178 | .Ve | |
179 | .PP | |
180 | Notice that the outer bracket type has changed, and so our access syntax | |
181 | has also changed. That's because unlike C, in perl you can't freely | |
182 | interchange arrays and references thereto. \f(CW$ref_to_AoA\fR is a reference to an | |
183 | array, whereas \f(CW@AoA\fR is an array proper. Likewise, \f(CW$AoA[2]\fR is not an | |
184 | array, but an array ref. So how come you can write these: | |
185 | .PP | |
186 | .Vb 2 | |
187 | \& $AoA[2][2] | |
188 | \& $ref_to_AoA->[2][2] | |
189 | .Ve | |
190 | .PP | |
191 | instead of having to write these: | |
192 | .PP | |
193 | .Vb 2 | |
194 | \& $AoA[2]->[2] | |
195 | \& $ref_to_AoA->[2]->[2] | |
196 | .Ve | |
197 | .PP | |
198 | Well, that's because the rule is that on adjacent brackets only (whether | |
199 | square or curly), you are free to omit the pointer dereferencing arrow. | |
200 | But you cannot do so for the very first one if it's a scalar containing | |
201 | a reference, which means that \f(CW$ref_to_AoA\fR always needs it. | |
202 | .Sh "Growing Your Own" | |
203 | .IX Subsection "Growing Your Own" | |
204 | That's all well and good for declaration of a fixed data structure, | |
205 | but what if you wanted to add new elements on the fly, or build | |
206 | it up entirely from scratch? | |
207 | .PP | |
208 | First, let's look at reading it in from a file. This is something like | |
209 | adding a row at a time. We'll assume that there's a flat file in which | |
210 | each line is a row and each word an element. If you're trying to develop an | |
211 | \&\f(CW@AoA\fR array containing all these, here's the right way to do that: | |
212 | .PP | |
213 | .Vb 4 | |
214 | \& while (<>) { | |
215 | \& @tmp = split; | |
216 | \& push @AoA, [ @tmp ]; | |
217 | \& } | |
218 | .Ve | |
219 | .PP | |
220 | You might also have loaded that from a function: | |
221 | .PP | |
222 | .Vb 3 | |
223 | \& for $i ( 1 .. 10 ) { | |
224 | \& $AoA[$i] = [ somefunc($i) ]; | |
225 | \& } | |
226 | .Ve | |
227 | .PP | |
228 | Or you might have had a temporary variable sitting around with the | |
229 | array in it. | |
230 | .PP | |
231 | .Vb 4 | |
232 | \& for $i ( 1 .. 10 ) { | |
233 | \& @tmp = somefunc($i); | |
234 | \& $AoA[$i] = [ @tmp ]; | |
235 | \& } | |
236 | .Ve | |
237 | .PP | |
238 | It's very important that you make sure to use the \f(CW\*(C`[]\*(C'\fR array reference | |
239 | constructor. That's because this will be very wrong: | |
240 | .PP | |
241 | .Vb 1 | |
242 | \& $AoA[$i] = @tmp; | |
243 | .Ve | |
244 | .PP | |
245 | You see, assigning a named array like that to a scalar just counts the | |
246 | number of elements in \f(CW@tmp\fR, which probably isn't what you want. | |
247 | .PP | |
248 | If you are running under \f(CW\*(C`use strict\*(C'\fR, you'll have to add some | |
249 | declarations to make it happy: | |
250 | .PP | |
251 | .Vb 6 | |
252 | \& use strict; | |
253 | \& my(@AoA, @tmp); | |
254 | \& while (<>) { | |
255 | \& @tmp = split; | |
256 | \& push @AoA, [ @tmp ]; | |
257 | \& } | |
258 | .Ve | |
259 | .PP | |
260 | Of course, you don't need the temporary array to have a name at all: | |
261 | .PP | |
262 | .Vb 3 | |
263 | \& while (<>) { | |
264 | \& push @AoA, [ split ]; | |
265 | \& } | |
266 | .Ve | |
267 | .PP | |
268 | You also don't have to use \fIpush()\fR. You could just make a direct assignment | |
269 | if you knew where you wanted to put it: | |
270 | .PP | |
271 | .Vb 5 | |
272 | \& my (@AoA, $i, $line); | |
273 | \& for $i ( 0 .. 10 ) { | |
274 | \& $line = <>; | |
275 | \& $AoA[$i] = [ split ' ', $line ]; | |
276 | \& } | |
277 | .Ve | |
278 | .PP | |
279 | or even just | |
280 | .PP | |
281 | .Vb 4 | |
282 | \& my (@AoA, $i); | |
283 | \& for $i ( 0 .. 10 ) { | |
284 | \& $AoA[$i] = [ split ' ', <> ]; | |
285 | \& } | |
286 | .Ve | |
287 | .PP | |
288 | You should in general be leery of using functions that could | |
289 | potentially return lists in scalar context without explicitly stating | |
290 | such. This would be clearer to the casual reader: | |
291 | .PP | |
292 | .Vb 4 | |
293 | \& my (@AoA, $i); | |
294 | \& for $i ( 0 .. 10 ) { | |
295 | \& $AoA[$i] = [ split ' ', scalar(<>) ]; | |
296 | \& } | |
297 | .Ve | |
298 | .PP | |
299 | If you wanted to have a \f(CW$ref_to_AoA\fR variable as a reference to an array, | |
300 | you'd have to do something like this: | |
301 | .PP | |
302 | .Vb 3 | |
303 | \& while (<>) { | |
304 | \& push @$ref_to_AoA, [ split ]; | |
305 | \& } | |
306 | .Ve | |
307 | .PP | |
308 | Now you can add new rows. What about adding new columns? If you're | |
309 | dealing with just matrices, it's often easiest to use simple assignment: | |
310 | .PP | |
311 | .Vb 5 | |
312 | \& for $x (1 .. 10) { | |
313 | \& for $y (1 .. 10) { | |
314 | \& $AoA[$x][$y] = func($x, $y); | |
315 | \& } | |
316 | \& } | |
317 | .Ve | |
318 | .PP | |
319 | .Vb 3 | |
320 | \& for $x ( 3, 7, 9 ) { | |
321 | \& $AoA[$x][20] += func2($x); | |
322 | \& } | |
323 | .Ve | |
324 | .PP | |
325 | It doesn't matter whether those elements are already | |
326 | there or not: it'll gladly create them for you, setting | |
327 | intervening elements to \f(CW\*(C`undef\*(C'\fR as need be. | |
328 | .PP | |
329 | If you wanted just to append to a row, you'd have | |
330 | to do something a bit funnier looking: | |
331 | .PP | |
332 | .Vb 2 | |
333 | \& # add new columns to an existing row | |
334 | \& push @{ $AoA[0] }, "wilma", "betty"; | |
335 | .Ve | |
336 | .PP | |
337 | Notice that I \fIcouldn't\fR say just: | |
338 | .PP | |
339 | .Vb 1 | |
340 | \& push $AoA[0], "wilma", "betty"; # WRONG! | |
341 | .Ve | |
342 | .PP | |
343 | In fact, that wouldn't even compile. How come? Because the argument | |
344 | to \fIpush()\fR must be a real array, not just a reference to such. | |
345 | .Sh "Access and Printing" | |
346 | .IX Subsection "Access and Printing" | |
347 | Now it's time to print your data structure out. How | |
348 | are you going to do that? Well, if you want only one | |
349 | of the elements, it's trivial: | |
350 | .PP | |
351 | .Vb 1 | |
352 | \& print $AoA[0][0]; | |
353 | .Ve | |
354 | .PP | |
355 | If you want to print the whole thing, though, you can't | |
356 | say | |
357 | .PP | |
358 | .Vb 1 | |
359 | \& print @AoA; # WRONG | |
360 | .Ve | |
361 | .PP | |
362 | because you'll get just references listed, and perl will never | |
363 | automatically dereference things for you. Instead, you have to | |
364 | roll yourself a loop or two. This prints the whole structure, | |
365 | using the shell-style \fIfor()\fR construct to loop across the outer | |
366 | set of subscripts. | |
367 | .PP | |
368 | .Vb 3 | |
369 | \& for $aref ( @AoA ) { | |
370 | \& print "\et [ @$aref ],\en"; | |
371 | \& } | |
372 | .Ve | |
373 | .PP | |
374 | If you wanted to keep track of subscripts, you might do this: | |
375 | .PP | |
376 | .Vb 3 | |
377 | \& for $i ( 0 .. $#AoA ) { | |
378 | \& print "\et elt $i is [ @{$AoA[$i]} ],\en"; | |
379 | \& } | |
380 | .Ve | |
381 | .PP | |
382 | or maybe even this. Notice the inner loop. | |
383 | .PP | |
384 | .Vb 5 | |
385 | \& for $i ( 0 .. $#AoA ) { | |
386 | \& for $j ( 0 .. $#{$AoA[$i]} ) { | |
387 | \& print "elt $i $j is $AoA[$i][$j]\en"; | |
388 | \& } | |
389 | \& } | |
390 | .Ve | |
391 | .PP | |
392 | As you can see, it's getting a bit complicated. That's why | |
393 | sometimes is easier to take a temporary on your way through: | |
394 | .PP | |
395 | .Vb 6 | |
396 | \& for $i ( 0 .. $#AoA ) { | |
397 | \& $aref = $AoA[$i]; | |
398 | \& for $j ( 0 .. $#{$aref} ) { | |
399 | \& print "elt $i $j is $AoA[$i][$j]\en"; | |
400 | \& } | |
401 | \& } | |
402 | .Ve | |
403 | .PP | |
404 | Hmm... that's still a bit ugly. How about this: | |
405 | .PP | |
406 | .Vb 7 | |
407 | \& for $i ( 0 .. $#AoA ) { | |
408 | \& $aref = $AoA[$i]; | |
409 | \& $n = @$aref - 1; | |
410 | \& for $j ( 0 .. $n ) { | |
411 | \& print "elt $i $j is $AoA[$i][$j]\en"; | |
412 | \& } | |
413 | \& } | |
414 | .Ve | |
415 | .Sh "Slices" | |
416 | .IX Subsection "Slices" | |
417 | If you want to get at a slice (part of a row) in a multidimensional | |
418 | array, you're going to have to do some fancy subscripting. That's | |
419 | because while we have a nice synonym for single elements via the | |
420 | pointer arrow for dereferencing, no such convenience exists for slices. | |
421 | (Remember, of course, that you can always write a loop to do a slice | |
422 | operation.) | |
423 | .PP | |
424 | Here's how to do one operation using a loop. We'll assume an \f(CW@AoA\fR | |
425 | variable as before. | |
426 | .PP | |
427 | .Vb 5 | |
428 | \& @part = (); | |
429 | \& $x = 4; | |
430 | \& for ($y = 7; $y < 13; $y++) { | |
431 | \& push @part, $AoA[$x][$y]; | |
432 | \& } | |
433 | .Ve | |
434 | .PP | |
435 | That same loop could be replaced with a slice operation: | |
436 | .PP | |
437 | .Vb 1 | |
438 | \& @part = @{ $AoA[4] } [ 7..12 ]; | |
439 | .Ve | |
440 | .PP | |
441 | but as you might well imagine, this is pretty rough on the reader. | |
442 | .PP | |
443 | Ah, but what if you wanted a \fItwo-dimensional slice\fR, such as having | |
444 | \&\f(CW$x\fR run from 4..8 and \f(CW$y\fR run from 7 to 12? Hmm... here's the simple way: | |
445 | .PP | |
446 | .Vb 6 | |
447 | \& @newAoA = (); | |
448 | \& for ($startx = $x = 4; $x <= 8; $x++) { | |
449 | \& for ($starty = $y = 7; $y <= 12; $y++) { | |
450 | \& $newAoA[$x - $startx][$y - $starty] = $AoA[$x][$y]; | |
451 | \& } | |
452 | \& } | |
453 | .Ve | |
454 | .PP | |
455 | We can reduce some of the looping through slices | |
456 | .PP | |
457 | .Vb 3 | |
458 | \& for ($x = 4; $x <= 8; $x++) { | |
459 | \& push @newAoA, [ @{ $AoA[$x] } [ 7..12 ] ]; | |
460 | \& } | |
461 | .Ve | |
462 | .PP | |
463 | If you were into Schwartzian Transforms, you would probably | |
464 | have selected map for that | |
465 | .PP | |
466 | .Vb 1 | |
467 | \& @newAoA = map { [ @{ $AoA[$_] } [ 7..12 ] ] } 4 .. 8; | |
468 | .Ve | |
469 | .PP | |
470 | Although if your manager accused of seeking job security (or rapid | |
471 | insecurity) through inscrutable code, it would be hard to argue. :\-) | |
472 | If I were you, I'd put that in a function: | |
473 | .PP | |
474 | .Vb 5 | |
475 | \& @newAoA = splice_2D( \e@AoA, 4 => 8, 7 => 12 ); | |
476 | \& sub splice_2D { | |
477 | \& my $lrr = shift; # ref to array of array refs! | |
478 | \& my ($x_lo, $x_hi, | |
479 | \& $y_lo, $y_hi) = @_; | |
480 | .Ve | |
481 | .PP | |
482 | .Vb 4 | |
483 | \& return map { | |
484 | \& [ @{ $lrr->[$_] } [ $y_lo .. $y_hi ] ] | |
485 | \& } $x_lo .. $x_hi; | |
486 | \& } | |
487 | .Ve | |
488 | .SH "SEE ALSO" | |
489 | .IX Header "SEE ALSO" | |
490 | \&\fIperldata\fR\|(1), \fIperlref\fR\|(1), \fIperldsc\fR\|(1) | |
491 | .SH "AUTHOR" | |
492 | .IX Header "AUTHOR" | |
493 | Tom Christiansen <\fItchrist@perl.com\fR> | |
494 | .PP | |
495 | Last update: Thu Jun 4 16:16:23 \s-1MDT\s0 1998 |