Commit | Line | Data |
d80786d0 |
1 | package HTML::Zoom; |
2 | |
1cf03540 |
3 | use strictures 1; |
d80786d0 |
4 | |
5 | use HTML::Zoom::ZConfig; |
bf5a23d0 |
6 | use HTML::Zoom::ReadFH; |
655965b3 |
7 | use HTML::Zoom::Transform; |
eeeb0921 |
8 | use HTML::Zoom::TransformBuilder; |
94a3ddd9 |
9 | use Scalar::Util (); |
d80786d0 |
10 | |
57076fa1 |
11 | our $VERSION = '0.009008_01'; |
7af7362d |
12 | |
13 | $VERSION = eval $VERSION; |
14 | |
d80786d0 |
15 | sub new { |
16 | my ($class, $args) = @_; |
17 | my $new = {}; |
18 | $new->{zconfig} = HTML::Zoom::ZConfig->new($args->{zconfig}||{}); |
19 | bless($new, $class); |
20 | } |
21 | |
22 | sub zconfig { shift->_self_or_new->{zconfig} } |
23 | |
24 | sub _self_or_new { |
25 | ref($_[0]) ? $_[0] : $_[0]->new |
26 | } |
27 | |
28 | sub _with { |
29 | bless({ %{$_[0]}, %{$_[1]} }, ref($_[0])); |
30 | } |
31 | |
7567494d |
32 | sub from_events { |
d80786d0 |
33 | my $self = shift->_self_or_new; |
34 | $self->_with({ |
7567494d |
35 | initial_events => shift, |
d80786d0 |
36 | }); |
37 | } |
38 | |
7567494d |
39 | sub from_html { |
40 | my $self = shift->_self_or_new; |
41 | $self->from_events($self->zconfig->parser->html_to_events($_[0])) |
42 | } |
43 | |
bf5a23d0 |
44 | sub from_file { |
45 | my $self = shift->_self_or_new; |
46 | my $filename = shift; |
47 | $self->from_html(do { local (@ARGV, $/) = ($filename); <> }); |
48 | } |
49 | |
d80786d0 |
50 | sub to_stream { |
51 | my $self = shift; |
52 | die "No events to build from - forgot to call from_html?" |
53 | unless $self->{initial_events}; |
54 | my $sutils = $self->zconfig->stream_utils; |
55 | my $stream = $sutils->stream_from_array(@{$self->{initial_events}}); |
2f0c6a86 |
56 | $stream = $_->apply_to_stream($stream) for @{$self->{transforms}||[]}; |
d80786d0 |
57 | $stream |
58 | } |
59 | |
bf5a23d0 |
60 | sub to_fh { |
61 | HTML::Zoom::ReadFH->from_zoom(shift); |
62 | } |
63 | |
7567494d |
64 | sub to_events { |
65 | my $self = shift; |
66 | [ $self->zconfig->stream_utils->stream_to_array($self->to_stream) ]; |
67 | } |
68 | |
bf5a23d0 |
69 | sub run { |
70 | my $self = shift; |
7567494d |
71 | $self->to_events; |
bf5a23d0 |
72 | return |
73 | } |
74 | |
75 | sub apply { |
76 | my ($self, $code) = @_; |
77 | local $_ = $self; |
78 | $self->$code; |
79 | } |
80 | |
fdb039c6 |
81 | sub apply_if { |
82 | my ($self, $predicate, $code) = @_; |
83 | if($predicate) { |
84 | local $_ = $self; |
85 | $self->$code; |
86 | } |
87 | else { |
88 | $self; |
89 | } |
90 | } |
91 | |
d80786d0 |
92 | sub to_html { |
93 | my $self = shift; |
94 | $self->zconfig->producer->html_from_stream($self->to_stream); |
95 | } |
96 | |
97 | sub memoize { |
98 | my $self = shift; |
99 | ref($self)->new($self)->from_html($self->to_html); |
100 | } |
101 | |
eeeb0921 |
102 | sub with_transform { |
1c4455ae |
103 | my $self = shift->_self_or_new; |
eeeb0921 |
104 | my ($transform) = @_; |
d80786d0 |
105 | $self->_with({ |
2f0c6a86 |
106 | transforms => [ |
107 | @{$self->{transforms}||[]}, |
eeeb0921 |
108 | $transform |
2f0c6a86 |
109 | ] |
d80786d0 |
110 | }); |
111 | } |
eeeb0921 |
112 | |
113 | sub with_filter { |
114 | my $self = shift->_self_or_new; |
115 | my ($selector, $filter) = @_; |
116 | $self->with_transform( |
117 | HTML::Zoom::Transform->new({ |
118 | zconfig => $self->zconfig, |
119 | selector => $selector, |
120 | filters => [ $filter ] |
121 | }) |
122 | ); |
123 | } |
d80786d0 |
124 | |
125 | sub select { |
1c4455ae |
126 | my $self = shift->_self_or_new; |
127 | my ($selector) = @_; |
eeeb0921 |
128 | return HTML::Zoom::TransformBuilder->new({ |
129 | zconfig => $self->zconfig, |
130 | selector => $selector, |
131 | proto => $self |
132 | }); |
d80786d0 |
133 | } |
134 | |
135 | # There's a bug waiting to happen here: if you do something like |
136 | # |
137 | # $zoom->select('.foo') |
1c4455ae |
138 | # ->remove_attribute(class => 'foo') |
d80786d0 |
139 | # ->then |
140 | # ->well_anything_really |
141 | # |
142 | # the second action won't execute because it doesn't match anymore. |
143 | # Ideally instead we'd merge the match subs but that's more complex to |
144 | # implement so I'm deferring it for the moment. |
145 | |
146 | sub then { |
147 | my $self = shift; |
2f0c6a86 |
148 | die "Can't call ->then without a previous transform" |
149 | unless $self->{transforms}; |
150 | $self->select($self->{transforms}->[-1]->selector); |
d80786d0 |
151 | } |
152 | |
94a3ddd9 |
153 | sub AUTOLOAD { |
154 | my ($self, $selector, @args) = @_; |
155 | my $sel = $self->select($selector); |
156 | my $meth = our $AUTOLOAD; |
157 | $meth =~ s/.*:://; |
6af04df5 |
158 | if (ref($selector) eq 'HASH') { |
159 | my $ret = $self; |
160 | $ret = $ret->_do($_, $meth, @{$selector->{$_}}) for keys %$selector; |
161 | $ret; |
162 | } else { |
163 | $self->_do($selector, $meth, @args); |
164 | } |
165 | } |
166 | |
167 | sub _do { |
168 | my ($self, $selector, $meth, @args) = @_; |
169 | my $sel = $self->select($selector); |
170 | if( my $cr = $sel->_zconfig->filter_builder->can($meth)) { |
94a3ddd9 |
171 | return $sel->$meth(@args); |
172 | } else { |
173 | die "We can't do $meth on ->select('$selector')"; |
174 | } |
175 | } |
176 | |
93f73028 |
177 | sub DESTROY {} |
178 | |
d80786d0 |
179 | 1; |
180 | |
181 | =head1 NAME |
182 | |
183 | HTML::Zoom - selector based streaming template engine |
184 | |
185 | =head1 SYNOPSIS |
186 | |
187 | use HTML::Zoom; |
188 | |
189 | my $template = <<HTML; |
190 | <html> |
191 | <head> |
192 | <title>Hello people</title> |
193 | </head> |
194 | <body> |
195 | <h1 id="greeting">Placeholder</h1> |
196 | <div id="list"> |
197 | <span> |
198 | <p>Name: <span class="name">Bob</span></p> |
199 | <p>Age: <span class="age">23</span></p> |
200 | </span> |
201 | <hr class="between" /> |
202 | </div> |
203 | </body> |
204 | </html> |
205 | HTML |
206 | |
207 | my $output = HTML::Zoom |
208 | ->from_html($template) |
209 | ->select('title, #greeting')->replace_content('Hello world & dog!') |
210 | ->select('#list')->repeat_content( |
211 | [ |
212 | sub { |
213 | $_->select('.name')->replace_content('Matt') |
214 | ->select('.age')->replace_content('26') |
215 | }, |
ac4c037e |
216 | # alternate form |
d80786d0 |
217 | sub { |
ac4c037e |
218 | $_->replace_content({'.name' => ['Mark'],'.age' => ['0x29'] }) |
d80786d0 |
219 | }, |
ac4c037e |
220 | #alternate alternate form |
d80786d0 |
221 | sub { |
ac4c037e |
222 | $_->replace_content('.name' => 'Epitaph') |
223 | ->replace_content('.age' => '<redacted>') |
d80786d0 |
224 | }, |
225 | ], |
226 | { repeat_between => '.between' } |
227 | ) |
228 | ->to_html; |
229 | |
230 | will produce: |
231 | |
232 | =begin testinfo |
233 | |
234 | my $expect = <<HTML; |
235 | |
236 | =end testinfo |
237 | |
238 | <html> |
239 | <head> |
240 | <title>Hello world & dog!</title> |
241 | </head> |
242 | <body> |
243 | <h1 id="greeting">Hello world & dog!</h1> |
244 | <div id="list"> |
245 | <span> |
246 | <p>Name: <span class="name">Matt</span></p> |
247 | <p>Age: <span class="age">26</span></p> |
248 | </span> |
249 | <hr class="between" /> |
250 | <span> |
251 | <p>Name: <span class="name">Mark</span></p> |
252 | <p>Age: <span class="age">0x29</span></p> |
253 | </span> |
254 | <hr class="between" /> |
255 | <span> |
256 | <p>Name: <span class="name">Epitaph</span></p> |
257 | <p>Age: <span class="age"><redacted></span></p> |
258 | </span> |
259 | |
260 | </div> |
261 | </body> |
262 | </html> |
263 | |
264 | =begin testinfo |
265 | |
266 | HTML |
267 | is($output, $expect, 'Synopsis code works ok'); |
268 | |
269 | =end testinfo |
270 | |
1c4455ae |
271 | =head1 DANGER WILL ROBINSON |
272 | |
273 | This is a 0.9 release. That means that I'm fairly happy the API isn't going |
274 | to change in surprising and upsetting ways before 1.0 and a real compatibility |
275 | freeze. But it also means that if it turns out there's a mistake the size of |
276 | a politician's ego in the API design that I haven't spotted yet there may be |
277 | a bit of breakage between here and 1.0. Hopefully not though. Appendages |
278 | crossed and all that. |
279 | |
280 | Worse still, the rest of the distribution isn't documented yet. I'm sorry. |
281 | I suck. But lots of people have been asking me to ship this, docs or no, so |
282 | having got this class itself at least somewhat documented I figured now was |
283 | a good time to cut a first real release. |
284 | |
285 | =head1 DESCRIPTION |
286 | |
287 | HTML::Zoom is a lazy, stream oriented, streaming capable, mostly functional, |
288 | CSS selector based semantic templating engine for HTML and HTML-like |
289 | document formats. |
290 | |
291 | Which is, on the whole, a bit of a mouthful. So let me step back a moment |
292 | and explain why you care enough to understand what I mean: |
293 | |
294 | =head2 JQUERY ENVY |
295 | |
296 | HTML::Zoom is the cure for JQuery envy. When your javascript guy pushes a |
297 | piece of data into a document by doing: |
298 | |
299 | $('.username').replaceAll(username); |
300 | |
301 | In HTML::Zoom one can write |
302 | |
303 | $zoom->select('.username')->replace_content($username); |
304 | |
305 | which is, I hope, almost as clear, hampered only by the fact that Zoom can't |
306 | assume a global document and therefore has nothing quite so simple as the |
307 | $() function to get the initial selection. |
308 | |
309 | L<HTML::Zoom::SelectorParser> implements a subset of the JQuery selector |
310 | specification, and will continue to track that rather than the W3C standards |
311 | for the forseeable future on grounds of pragmatism. Also on grounds of their |
312 | spec is written in EN_US rather than EN_W3C, and I read the former much better. |
313 | |
314 | I am happy to admit that it's very, very much a subset at the moment - see the |
315 | L<HTML::Zoom::SelectorParser> POD for what's currently there, and expect more |
316 | and more to be supported over time as we need it and patch it in. |
317 | |
318 | =head2 CLEAN TEMPLATES |
319 | |
320 | HTML::Zoom is the cure for messy templates. How many times have you looked at |
321 | templates like this: |
322 | |
323 | <form action="/somewhere"> |
324 | [% FOREACH field IN fields %] |
325 | <label for="[% field.id %]">[% field.label %]</label> |
326 | <input name="[% field.name %]" type="[% field.type %]" value="[% field.value %]" /> |
327 | [% END %] |
328 | </form> |
329 | |
330 | and despaired of the fact that neither the HTML structure nor the logic are |
331 | remotely easy to read? Fortunately, with HTML::Zoom we can separate the two |
332 | cleanly: |
333 | |
334 | <form class="myform" action="/somewhere"> |
335 | <label /> |
336 | <input /> |
337 | </form> |
338 | |
339 | $zoom->select('.myform')->repeat_content([ |
340 | map { my $field = $_; sub { |
341 | |
342 | $_->select('label') |
2daa653a |
343 | ->add_to_attribute( for => $field->{id} ) |
1c4455ae |
344 | ->then |
345 | ->replace_content( $field->{label} ) |
ac4c037e |
346 | ->add_to_attribute( |
347 | input => { |
348 | name => $field->{name}, |
349 | type => $field->{type}, |
350 | value => $field->{value} |
351 | }) |
1c4455ae |
352 | } } @fields |
353 | ]); |
354 | |
355 | This is, admittedly, very much not shorter. However, it makes it extremely |
356 | clear what's happening and therefore less hassle to maintain. Especially |
357 | because it allows the designer to fiddle with the HTML without cutting |
358 | himself on sharp ELSE clauses, and the developer to add available data to |
359 | the template without getting angle bracket cuts on sensitive parts. |
360 | |
361 | Better still, HTML::Zoom knows that it's inserting content into HTML and |
362 | can escape it for you - the example template should really have been: |
363 | |
364 | <form action="/somewhere"> |
365 | [% FOREACH field IN fields %] |
366 | <label for="[% field.id | html %]">[% field.label | html %]</label> |
367 | <input name="[% field.name | html %]" type="[% field.type | html %]" value="[% field.value | html %]" /> |
368 | [% END %] |
369 | </form> |
370 | |
371 | and frankly I'll take slightly more code any day over *that* crawling horror. |
372 | |
373 | (addendum: I pick on L<Template Toolkit|Template> here specifically because |
374 | it's the template system I hate the least - for text templating, I don't |
375 | honestly think I'll ever like anything except the next version of Template |
376 | Toolkit better - but HTML isn't text. Zoom knows that. Do you?) |
377 | |
378 | =head2 PUTTING THE FUN INTO FUNCTIONAL |
379 | |
380 | The principle of HTML::Zoom is to provide a reusable, functional container |
381 | object that lets you build up a set of transforms to be applied; every method |
382 | call you make on a zoom object returns a new object, so it's safe to do so |
383 | on one somebody else gave you without worrying about altering state (with |
384 | the notable exception of ->next for stream objects, which I'll come to later). |
385 | |
386 | So: |
387 | |
388 | my $z2 = $z1->select('.name')->replace_content($name); |
389 | |
390 | my $z3 = $z2->select('.title')->replace_content('Ms.'); |
391 | |
392 | each time produces a new Zoom object. If you want to package up a set of |
393 | transforms to re-use, HTML::Zoom provides an 'apply' method: |
394 | |
395 | my $add_name = sub { $_->select('.name')->replace_content($name) }; |
396 | |
397 | my $same_as_z2 = $z1->apply($add_name); |
398 | |
399 | =head2 LAZINESS IS A VIRTUE |
400 | |
401 | HTML::Zoom does its best to defer doing anything until it's absolutely |
402 | required. The only point at which it descends into state is when you force |
403 | it to create a stream, directly by: |
404 | |
c9e76777 |
405 | my $stream = $zoom->to_stream; |
1c4455ae |
406 | |
407 | while (my $evt = $stream->next) { |
408 | # handle zoom event here |
409 | } |
410 | |
411 | or indirectly via: |
412 | |
413 | my $final_html = $zoom->to_html; |
414 | |
415 | my $fh = $zoom->to_fh; |
416 | |
417 | while (my $chunk = $fh->getline) { |
418 | ... |
419 | } |
420 | |
421 | Better still, the $fh returned doesn't create its stream until the first |
422 | call to getline, which means that until you call that and force it to be |
423 | stateful you can get back to the original stateless Zoom object via: |
424 | |
425 | my $zoom = $fh->to_zoom; |
426 | |
427 | which is exceedingly handy for filtering L<Plack> PSGI responses, among other |
428 | things. |
429 | |
430 | Because HTML::Zoom doesn't try and evaluate everything up front, you can |
431 | generally put things together in whatever order is most appropriate. This |
432 | means that: |
433 | |
434 | my $start = HTML::Zoom->from_html($html); |
435 | |
436 | my $zoom = $start->select('div')->replace_content('THIS IS A DIV!'); |
437 | |
438 | and: |
439 | |
440 | my $start = HTML::Zoom->select('div')->replace_content('THIS IS A DIV!'); |
441 | |
442 | my $zoom = $start->from_html($html); |
443 | |
444 | will produce equivalent final $zoom objects, thus proving that there can be |
445 | more than one way to do it without one of them being a |
446 | L<bait and switch|Switch>. |
447 | |
448 | =head2 STOCKTON TO DARLINGTON UNDER STREAM POWER |
449 | |
450 | HTML::Zoom's execution always happens in terms of streams under the hood |
451 | - that is, the basic pattern for doing anything is - |
452 | |
453 | my $stream = get_stream_from_somewhere |
454 | |
455 | while (my ($evt) = $stream->next) { |
456 | # do something with the event |
457 | } |
458 | |
459 | More importantly, all selectors and filters are also built as stream |
460 | operations, so a selector and filter pair is effectively: |
461 | |
462 | sub next { |
463 | my ($self) = @_; |
464 | my $next_evt = $self->parent_stream->next; |
465 | if ($self->selector_matches($next_evt)) { |
466 | return $self->apply_filter_to($next_evt); |
467 | } else { |
468 | return $next_evt; |
469 | } |
470 | } |
471 | |
472 | Internally, things are marginally more complicated than that, but not enough |
473 | that you as a user should normally need to care. |
474 | |
475 | In fact, an HTML::Zoom object is mostly just a container for the relevant |
476 | information from which to build the final stream that does the real work. A |
477 | stream built from a Zoom object is a stream of events from parsing the |
478 | initial HTML, wrapped in a filter stream per selector/filter pair provided |
479 | as described above. |
480 | |
481 | The upshot of this is that the application of filters works just as well on |
482 | streams as on the original Zoom object - in fact, when you run a |
483 | L</repeat_content> operation your subroutines are applied to the stream for |
484 | that element of the repeat, rather than constructing a new zoom per repeat |
485 | element as well. |
486 | |
487 | More concretely: |
488 | |
489 | $_->select('div')->replace_content('I AM A DIV!'); |
490 | |
491 | works on both HTML::Zoom objects themselves and HTML::Zoom stream objects and |
492 | shares sufficient of the implementation that you can generally forget the |
493 | difference - barring the fact that a stream already has state attached so |
494 | things like to_fh are no longer available. |
495 | |
496 | =head2 POP! GOES THE WEASEL |
497 | |
498 | ... and by Weasel, I mean layout. |
499 | |
500 | HTML::Zoom's filehandle object supports an additional event key, 'flush', |
501 | that is transparent to the rest of the system but indicates to the filehandle |
502 | object to end a getline operation at that point and return the HTML so far. |
503 | |
504 | This means that in an environment where streaming output is available, such |
505 | as a number of the L<Plack> PSGI handlers, you can add the flush key to an |
506 | event in order to ensure that the HTML generated so far is flushed through |
507 | to the browser right now. This can be especially useful if you know you're |
508 | about to call a web service or a potentially slow database query or similar |
509 | to ensure that at least the header/layout of your page renders now, improving |
510 | perceived user responsiveness while your application waits around for the |
511 | data it needs. |
512 | |
513 | This is currently exposed by the 'flush_before' option to the collect filter, |
514 | which incidentally also underlies the replace and repeat filters, so to |
515 | indicate we want this behaviour to happen before a query is executed we can |
516 | write something like: |
517 | |
518 | $zoom->select('.item')->repeat(sub { |
519 | if (my $row = $db_thing->next) { |
520 | return sub { $_->select('.item-name')->replace_content($row->name) } |
521 | } else { |
522 | return |
523 | } |
524 | }, { flush_before => 1 }); |
525 | |
526 | which should have the desired effect given a sufficiently lazy $db_thing (for |
527 | example a L<DBIx::Class::ResultSet> object). |
528 | |
529 | =head2 A FISTFUL OF OBJECTS |
530 | |
531 | At the core of an HTML::Zoom system lurks an L<HTML::Zoom::ZConfig> object, |
532 | whose purpose is to hang on to the various bits and pieces that things need |
533 | so that there's a common way of accessing shared functionality. |
534 | |
535 | Were I a computer scientist I would probably call this an "Inversion of |
536 | Control" object - which you'd be welcome to google to learn more about, or |
537 | you can just imagine a computer scientist being suspended upside down over |
538 | a pit. Either way works for me, I'm a pure maths grad. |
539 | |
540 | The ZConfig object hangs on to one each of the following for you: |
541 | |
542 | =over 4 |
543 | |
544 | =item * An HTML parser, normally L<HTML::Zoom::Parser::BuiltIn> |
545 | |
546 | =item * An HTML producer (emitter), normally L<HTML::Zoom::Producer::BuiltIn> |
547 | |
548 | =item * An object to build event filters, normally L<HTML::Zoom::FilterBuilder> |
549 | |
550 | =item * An object to parse CSS selectors, normally L<HTML::Zoom::SelectorParser> |
551 | |
552 | =item * An object to build streams, normally L<HTML::Zoom::StreamUtils> |
553 | |
554 | =back |
555 | |
556 | In theory you could replace any of these with anything you like, but in |
557 | practice you're probably best restricting yourself to subclasses, or at |
558 | least things that manage to look like the original if you squint a bit. |
559 | |
560 | If you do something more clever than that, or find yourself overriding things |
561 | in your ZConfig a lot, please please tell us about it via one of the means |
562 | mentioned under L</SUPPORT>. |
563 | |
564 | =head2 SEMANTIC DIDACTIC |
565 | |
566 | Some will argue that overloading CSS selectors to do data stuff is a terrible |
567 | idea, and possibly even a step towards the "Concrete Javascript" pattern |
568 | (which I abhor) or Smalltalk's Morphic (which I ignore, except for the part |
569 | where it keeps reminding me of the late, great Tony Hart's plasticine friend). |
570 | |
571 | To which I say, "eh", "meh", and possibly also "feh". If it really upsets |
572 | you, either use extra classes for this (and remove them afterwards) or |
573 | use special fake elements or, well, honestly, just use something different. |
574 | L<Template::Semantic> provides a similar idea to zoom except using XPath |
575 | and XML::LibXML transforms rather than a lightweight streaming approach - |
576 | maybe you'd like that better. Or maybe you really did want |
577 | L<Template Toolkit|Template> after all. It is still damn good at what it does, |
578 | after all. |
579 | |
580 | So far, however, I've found that for new sites the designers I'm working with |
581 | generally want to produce nice semantic HTML with classes that represent the |
582 | nature of the data rather than the structure of the layout, so sharing them |
583 | as a common interface works really well for us. |
584 | |
585 | In the absence of any evidence that overloading CSS selectors has killed |
586 | children or unexpectedly set fire to grandmothers - and given microformats |
587 | have been around for a while there's been plenty of opportunity for |
588 | octagenarian combustion - I'd suggest you give it a try and see if you like it. |
589 | |
590 | =head2 GET THEE TO A SUMMARY! |
591 | |
592 | Erm. Well. |
593 | |
594 | HTML::Zoom is a lazy, stream oriented, streaming capable, mostly functional, |
595 | CSS selector based semantic templating engine for HTML and HTML-like |
596 | document formats. |
597 | |
598 | But I said that already. Although hopefully by now you have some idea what I |
599 | meant when I said it. If you didn't have any idea the first time. I mean, I'm |
600 | not trying to call you stupid or anything. Just saying that maybe it wasn't |
601 | totally obvious without the explanation. Or something. |
602 | |
603 | Er. |
604 | |
605 | Maybe we should just move on to the method docs. |
606 | |
607 | =head1 METHODS |
608 | |
609 | =head2 new |
610 | |
611 | my $zoom = HTML::Zoom->new; |
612 | |
613 | my $zoom = HTML::Zoom->new({ zconfig => $zconfig }); |
614 | |
615 | Create a new empty Zoom object. You can optionally pass an |
616 | L<HTML::Zoom::ZConfig> instance if you're trying to override one or more of |
617 | the default components. |
618 | |
619 | This method isn't often used directly since several other methods can also |
620 | act as constructors, notable L</select> and L</from_html> |
621 | |
622 | =head2 zconfig |
623 | |
624 | my $zconfig = $zoom->zconfig; |
625 | |
626 | Retrieve the L<HTML::Zoom::ZConfig> instance used by this Zoom object. You |
627 | shouldn't usually need to call this yourself. |
628 | |
629 | =head2 from_html |
630 | |
631 | my $zoom = HTML::Zoom->from_html($html); |
632 | |
633 | my $z2 = $z1->from_html($html); |
634 | |
635 | Parses the HTML using the current zconfig's parser object and returns a new |
636 | zoom instance with that as the source HTML to be transformed. |
637 | |
638 | =head2 from_file |
639 | |
640 | my $zoom = HTML::Zoom->from_file($file); |
641 | |
642 | my $z2 = $z1->from_file($file); |
643 | |
644 | Convenience method - slurps the contents of $file and calls from_html with it. |
645 | |
f3a758ad |
646 | =head2 from_events |
647 | |
648 | my $zoom = HTML::Zoom->from_events($evt); |
649 | |
650 | Create a new Zoom object from collected events |
651 | |
1c4455ae |
652 | =head2 to_stream |
653 | |
654 | my $stream = $zoom->to_stream; |
655 | |
656 | while (my ($evt) = $stream->next) { |
657 | ... |
658 | |
659 | Creates a stream, starting with a stream of the events from the HTML supplied |
660 | via L</from_html> and then wrapping it in turn with each selector+filter pair |
661 | that have been applied to the zoom object. |
662 | |
663 | =head2 to_fh |
664 | |
665 | my $fh = $zoom->to_fh; |
666 | |
667 | call_something_expecting_a_filehandle($fh); |
668 | |
669 | Returns an L<HTML::Zoom::ReadFH> instance that will create a stream the first |
670 | time its getline method is called and then return all HTML up to the next |
671 | event with 'flush' set. |
672 | |
673 | You can pass this filehandle to compliant PSGI handlers (and probably most |
674 | web frameworks). |
675 | |
676 | =head2 run |
677 | |
678 | $zoom->run; |
679 | |
680 | Runs the zoom object's transforms without doing anything with the results. |
681 | |
682 | Normally used to get side effects of a zoom run - for example when using |
683 | L<HTML::Zoom::FilterBuilder/collect> to slurp events for scraping or layout. |
684 | |
685 | =head2 apply |
686 | |
687 | my $z2 = $z1->apply(sub { |
688 | $_->select('div')->replace_content('I AM A DIV!') }) |
689 | }); |
690 | |
691 | Sets $_ to the zoom object and then runs the provided code. Basically syntax |
692 | sugar, the following is entirely equivalent: |
693 | |
694 | my $sub = sub { |
695 | shift->select('div')->replace_content('I AM A DIV!') }) |
696 | }; |
697 | |
698 | my $z2 = $sub->($z1); |
699 | |
3959a04d |
700 | =head2 apply_if |
701 | |
702 | my $z2 = $z1->apply_if($cond, sub { |
703 | $_->select('div')->replace_content('I AM A DIV!') }) |
704 | }); |
705 | |
706 | ->apply but will only run the tranform if $cond is true |
707 | |
1c4455ae |
708 | =head2 to_html |
709 | |
710 | my $html = $zoom->to_html; |
711 | |
712 | Runs the zoom processing and returns the resulting HTML. |
713 | |
714 | =head2 memoize |
715 | |
716 | my $z2 = $z1->memoize; |
717 | |
718 | Creates a new zoom whose source HTML is the results of the original zoom's |
719 | processing. Effectively syntax sugar for: |
720 | |
721 | my $z2 = HTML::Zoom->from_html($z1->to_html); |
722 | |
723 | but preserves your L<HTML::Zoom::ZConfig> object. |
724 | |
725 | =head2 with_filter |
726 | |
727 | my $zoom = HTML::Zoom->with_filter( |
728 | 'div', $filter_builder->replace_content('I AM A DIV!') |
729 | ); |
730 | |
731 | my $z2 = $z1->with_filter( |
732 | 'div', $filter_builder->replace_content('I AM A DIV!') |
733 | ); |
734 | |
735 | Lower level interface than L</select> to adding filters to your zoom object. |
736 | |
737 | In normal usage, you probably don't need to call this yourself. |
738 | |
739 | =head2 select |
740 | |
741 | my $zoom = HTML::Zoom->select('div')->replace_content('I AM A DIV!'); |
742 | |
743 | my $z2 = $z1->select('div')->replace_content('I AM A DIV!'); |
744 | |
97192b02 |
745 | Returns an intermediary object of the class L<HTML::Zoom::TransformBuilder> |
1c4455ae |
746 | on which methods of your L<HTML::Zoom::FilterBuilder> object can be called. |
747 | |
748 | In normal usage you should generally always put the pair of method calls |
749 | together; the intermediary object isn't designed or expected to stick around. |
750 | |
751 | =head2 then |
752 | |
2daa653a |
753 | my $z2 = $z1->select('div')->add_to_attribute(class => 'spoon') |
1c4455ae |
754 | ->then |
755 | ->replace_content('I AM A DIV!'); |
756 | |
757 | Re-runs the previous select to allow you to chain actions together on the |
758 | same selector. |
759 | |
94a3ddd9 |
760 | =head1 AUTOLOAD METHODS |
761 | |
762 | L<HTML::Zoom> AUTOLOADS methods against L</select> so that you can reduce a |
763 | certain amount of boilerplate typing. This allows you to replace: |
764 | |
765 | $z->select('div')->replace_content("Hello World"); |
766 | |
767 | With: |
768 | |
769 | $z->replace_content(div => "Hello World"); |
770 | |
771 | Besides saving a few keys per invocations, you may feel this looks neater |
772 | in your code and increases understanding. |
773 | |
f107bef7 |
774 | =head1 AUTHOR |
45b4cea1 |
775 | |
f107bef7 |
776 | mst - Matt S. Trout (cpan:MSTROUT) <mst@shadowcat.co.uk> |
45b4cea1 |
777 | |
f107bef7 |
778 | =head1 CONTRIBUTORS |
45b4cea1 |
779 | |
f107bef7 |
780 | Oliver Charles |
781 | |
782 | Jakub Nareski |
783 | |
6af04df5 |
784 | Simon Elliott |
f107bef7 |
785 | |
786 | Joe Highton |
787 | |
788 | John Napiorkowski |
789 | |
5cac799e |
790 | Robert Buels |
791 | |
b0ed2859 |
792 | David Dorward |
793 | |
f107bef7 |
794 | =head1 COPYRIGHT |
795 | |
796 | Copyright (c) 2010-2011 the HTML::Zoom L</AUTHOR> and L</CONTRIBUTORS> |
797 | as listed above. |
45b4cea1 |
798 | |
799 | =head1 LICENSE |
800 | |
801 | This library is free software, you can redistribute it and/or modify |
802 | it under the same terms as Perl itself. |
803 | |
d80786d0 |
804 | =cut |
45b4cea1 |
805 | |