remove support for smart whitespace trimming from all_text and text m…

…ethods in Mojo::DOM
mojolicious · Jun 21, 2016 · 3e1051a · 3e1051a
1 parent 425cb74
commit 3e1051a
Show file tree

Hide file tree

Showing 10 changed files with 150 additions and 219 deletions.
diff --git a/Changes b/Changes
@@ -1,5 +1,10 @@
 
-6.67  2016-06-21
+7.0  2016-06-21
+  - Code name "Nerd Face", this is a major release.
+  - Removed squish method from Mojo::ByteStream.
+  - Removed squish function from Mojo::Util.
+  - Removed support for smart whitespace trimming from all_text and text methods
+    in Mojo::DOM.
   - Fix a few whitespace bugs in Mojo::DOM.
 
 6.66  2016-06-16

diff --git a/lib/Mojo/ByteStream.pm b/lib/Mojo/ByteStream.pm
@@ -12,8 +12,8 @@ our @EXPORT_OK = ('b');
 my @UTILS = (
   qw(b64_decode b64_encode camelize decamelize hmac_sha1_sum html_unescape),
   qw(md5_bytes md5_sum punycode_decode punycode_encode quote sha1_bytes),
-  qw(sha1_sum slurp spurt squish term_escape trim unindent unquote),
-  qw(url_escape url_unescape xml_escape xor_encode)
+  qw(sha1_sum slurp spurt term_escape trim unindent unquote url_escape),
+  qw(url_unescape xml_escape xor_encode)
 );
 for my $name (@UTILS) {
   my $sub = Mojo::Util->can($name);
@@ -266,7 +266,7 @@ Read all data at once from file into bytestream with L<Mojo::Util/"slurp">.
 Write all data from bytestream at once to file with L<Mojo::Util/"spurt">.
 
   # Remove unnecessary whitespace from file
-  b('/home/sri/foo.txt')->slurp->squish->spurt('/home/sri/bar.txt');
+  b('/home/sri/foo.txt')->slurp->trim->spurt('/home/sri/bar.txt');
 
 =head2 split
 
@@ -278,14 +278,6 @@ objects.
   # "One,Two,Three"
   b("one,two,three")->split(',')->map('camelize')->join(',');
 
-=head2 squish
-
-  $stream = $stream->squish;
-
-Trim whitespace characters from both ends of bytestream and then change all
-consecutive groups of whitespace into one space each with
-L<Mojo::Util/"squish">.
-
 =head2 tap
 
   $stream = $stream->tap(sub {...});

diff --git a/lib/Mojo/DOM.pm b/lib/Mojo/DOM.pm
@@ -13,10 +13,9 @@ use Carp 'croak';
 use Mojo::Collection;
 use Mojo::DOM::CSS;
 use Mojo::DOM::HTML;
-use Mojo::Util 'squish';
 use Scalar::Util qw(blessed weaken);
 
-sub all_text { shift->_all_text(1, @_) }
+sub all_text { _text([_nodes(shift->tree)], 1) }
 
 sub ancestors { _select($_[0]->_collect($_[0]->_ancestors), $_[1]) }
 
@@ -151,7 +150,7 @@ sub tag {
 
 sub tap { shift->Mojo::Base::tap(@_) }
 
-sub text { shift->_all_text(0, @_) }
+sub text { _text([_nodes(shift->tree)], 0) }
 
 sub to_string { shift->_delegate('render') }
 
@@ -199,17 +198,6 @@ sub _all {
   map { $_->[0] eq 'tag' ? ($_, _all(_nodes($_))) : ($_) } @_;
 }
 
-sub _all_text {
-  my ($self, $recurse, $trim) = (shift, shift, shift // 1);
-
-  # Detect "pre" tag
-  my $tree = $self->tree;
-  map { $_->[1] eq 'pre' and $trim = 0 } $self->_ancestors, $tree
-    if $trim && $tree->[0] ne 'root';
-
-  return _text([_nodes($tree)], $recurse, $trim);
-}
-
 sub _ancestors {
   my ($self, $root) = @_;
 
@@ -316,26 +304,22 @@ sub _siblings {
 sub _start { $_[0][0] eq 'root' ? 1 : 4 }
 
 sub _text {
-  my ($nodes, $recurse, $trim) = @_;
+  my ($nodes, $recurse) = @_;
 
   my $text = '';
   for my $node (@$nodes) {
     my $type = $node->[0];
 
     # Text
-    my $chunk = '';
-    if ($type eq 'text') { $chunk = $trim ? squish $node->[1] : $node->[1] }
-
-    # CDATA or raw text
-    elsif ($type eq 'cdata' || $type eq 'raw') { $chunk = $node->[1] }
+    if ($type eq 'text' || $type eq 'cdata' || $type eq 'raw') {
+      $text .= $node->[1];
+    }
 
     # Nested tag
     elsif ($type eq 'tag' && $recurse) {
       no warnings 'recursion';
-      $chunk = _text([_nodes($node)], 1, $node->[1] eq 'pre' ? 0 : $trim);
+      $text .= _text([_nodes($node)], 1);
     }
-
-    $text .= $chunk;
   }
 
   return $text;
@@ -465,17 +449,12 @@ L<Mojo::DOM> implements the following methods.
 
 =head2 all_text
 
-  my $trimmed   = $dom->all_text;
-  my $untrimmed = $dom->all_text(0);
-
-Extract text content from all descendant nodes of this element, smart
-whitespace trimming is enabled by default.
+  my $text = $dom->all_text;
 
-  # "foo bar baz"
-  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text;
+Extract text content from all descendant nodes of this element.
 
   # "foo\nbarbaz\n"
-  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text(0);
+  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text;
 
 =head2 ancestors
 
@@ -882,17 +861,12 @@ Alias for L<Mojo::Base/"tap">.
 
 =head2 text
 
-  my $trimmed   = $dom->text;
-  my $untrimmed = $dom->text(0);
+  my $text = $dom->text;
 
-Extract text content from this element only (not including child elements),
-smart whitespace trimming is enabled by default.
-
-  # "foo baz"
-  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text;
+Extract text content from this element only (not including child elements).
 
   # "foo\nbaz\n"
-  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text(0);
+  $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text;
 
 =head2 to_string
 

diff --git a/lib/Mojo/Util.pm b/lib/Mojo/Util.pm
@@ -57,8 +57,8 @@ our @EXPORT_OK = (
   qw(decode deprecated dumper encode files hmac_sha1_sum html_unescape),
   qw(md5_bytes md5_sum monkey_patch punycode_decode punycode_encode quote),
   qw(secure_compare sha1_bytes sha1_sum slurp split_cookie_header),
-  qw(split_header spurt squish steady_time tablify term_escape trim unindent),
-  qw(unquote url_escape url_unescape xml_escape xor_encode)
+  qw(split_header spurt steady_time tablify term_escape trim unindent unquote),
+  qw(url_escape url_unescape xml_escape xor_encode)
 );
 
 # Aliases
@@ -264,12 +264,6 @@ sub spurt {
   return $content;
 }
 
-sub squish {
-  my $str = trim(@_);
-  $str =~ s/\s+/ /g;
-  return $str;
-}
-
 sub tablify {
   my $rows = shift;
 
@@ -730,16 +724,6 @@ its own array reference, and keys without a value get C<undef> assigned.
 
 Write all data at once to file.
 
-=head2 squish
-
-  my $squished = squish $str;
-
-Trim whitespace characters from both ends of string and then change all
-consecutive groups of whitespace into one space each.
-
-  # "foo bar"
-  squish '  foo  bar  ';
-
 =head2 steady_time
 
   my $time = steady_time;

diff --git a/lib/Mojolicious.pm b/lib/Mojolicious.pm
@@ -42,8 +42,8 @@ has static    => sub { Mojolicious::Static->new };
 has types     => sub { Mojolicious::Types->new };
 has validator => sub { Mojolicious::Validator->new };
 
-our $CODENAME = 'Clinking Beer Mugs';
-our $VERSION  = '6.67';
+our $CODENAME = 'Nerd Face';
+our $VERSION  = '7.0';
 
 sub AUTOLOAD {
   my $self = shift;
@@ -718,6 +718,8 @@ L<http://www.apache.org/licenses/LICENSE-2.0>.
 Every major release of L<Mojolicious> has a code name, these are the ones that
 have been used in the past.
 
+7.0, C<Nerd Face> (U+1F913)
+
 6.0, C<Clinking Beer Mugs> (U+1F37B)
 
 5.0, C<Tiger Face> (U+1F42F)

diff --git a/t/mojo/bytestream.t b/t/mojo/bytestream.t
@@ -61,9 +61,6 @@ is b('"foo 23 \"bar"')->unquote, 'foo 23 "bar', 'right unquoted result';
 # trim
 is b(' la la la ')->trim, 'la la la', 'right trimmed result';
 
-# squish
-is b("\n la\nla la \n")->squish, 'la la la', 'right squished result';
-
 # md5_bytes
 is unpack('H*', b('foo bar baz ♥')->encode->md5_bytes),
   'a740aeb6e066f158cbf19fd92e890d2d', 'right binary md5 checksum';