[ViewVC] Diff of: cvs/JSON-XS/XS.pm

Comparing JSON-XS/XS.pm (file contents):
Revision 1.1 by root, Thu Mar 22 16:40:16 2007 UTC vs.
Revision 1.78 by root, Wed Dec 5 10:59:28 2007 UTC

1	=head1 NAME	1	=head1 NAME
2		2
3	JSON::XS - JSON serialising/deserialising, done correctly and fast	3	JSON::XS - JSON serialising/deserialising, done correctly and fast
4		4
		5	JSON::XS - 正しくて高速な JSON シリアライザ/デシリアライザ
		6	(http://fleur.hio.jp/perldoc/mix/lib/JSON/XS.html)
		7
5	=head1 SYNOPSIS	8	=head1 SYNOPSIS
6		9
7	use JSON::XS;	10	use JSON::XS;
8		11
		12	# exported functions, they croak on error
		13	# and expect/generate UTF-8
		14
		15	$utf8_encoded_json_text = encode_json $perl_hash_or_arrayref;
		16	$perl_hash_or_arrayref = decode_json $utf8_encoded_json_text;
		17
		18	# OO-interface
		19
		20	$coder = JSON::XS->new->ascii->pretty->allow_nonref;
		21	$pretty_printed_unencoded = $coder->encode ($perl_scalar);
		22	$perl_scalar = $coder->decode ($unicode_json_text);
		23
		24	# Note that JSON version 2.0 and above will automatically use JSON::XS
		25	# if available, at virtually no speed overhead either, so you should
		26	# be able to just:
		27
		28	use JSON;
		29
		30	# and do the same things, except that you have a pure-perl fallback now.
		31
9	=head1 DESCRIPTION	32	=head1 DESCRIPTION
10		33
		34	This module converts Perl data structures to JSON and vice versa. Its
		35	primary goal is to be I<correct> and its secondary goal is to be
		36	I<fast>. To reach the latter goal it was written in C.
		37
		38	Beginning with version 2.0 of the JSON module, when both JSON and
		39	JSON::XS are installed, then JSON will fall back on JSON::XS (this can be
		40	overriden) with no overhead due to emulation (by inheritign constructor
		41	and methods). If JSON::XS is not available, it will fall back to the
		42	compatible JSON::PP module as backend, so using JSON instead of JSON::XS
		43	gives you a portable JSON API that can be fast when you need and doesn't
		44	require a C compiler when that is a problem.
		45
		46	As this is the n-th-something JSON module on CPAN, what was the reason
		47	to write yet another JSON module? While it seems there are many JSON
		48	modules, none of them correctly handle all corner cases, and in most cases
		49	their maintainers are unresponsive, gone missing, or not listening to bug
		50	reports for other reasons.
		51
		52	See COMPARISON, below, for a comparison to some other JSON modules.
		53
		54	See MAPPING, below, on how JSON::XS maps perl values to JSON values and
		55	vice versa.
		56
		57	=head2 FEATURES
		58
11	=over 4	59	=over 4
12		60
		61	=item * correct Unicode handling
		62
		63	This module knows how to handle Unicode, and even documents how and when
		64	it does so.
		65
		66	=item * round-trip integrity
		67
		68	When you serialise a perl data structure using only datatypes supported
		69	by JSON, the deserialised data structure is identical on the Perl level.
		70	(e.g. the string "2.0" doesn't suddenly become "2" just because it looks
		71	like a number).
		72
		73	=item * strict checking of JSON correctness
		74
		75	There is no guessing, no generating of illegal JSON texts by default,
		76	and only JSON is accepted as input by default (the latter is a security
		77	feature).
		78
		79	=item * fast
		80
		81	Compared to other JSON modules, this module compares favourably in terms
		82	of speed, too.
		83
		84	=item * simple to use
		85
		86	This module has both a simple functional interface as well as an OO
		87	interface.
		88
		89	=item * reasonably versatile output formats
		90
		91	You can choose between the most compact guaranteed single-line format
		92	possible (nice for simple line-based protocols), a pure-ascii format
		93	(for when your transport is not 8-bit clean, still supports the whole
		94	Unicode range), or a pretty-printed format (for when you want to read that
		95	stuff). Or you can combine those features in whatever way you like.
		96
		97	=back
		98
13	=cut	99	=cut
14		100
15	package JSON::XS;	101	package JSON::XS;
16		102
17	BEGIN {	103	use strict;
		104
18	$VERSION = '0.1';	105	our $VERSION = '2.01';
19	@ISA = qw(Exporter);	106	our @ISA = qw(Exporter);
20		107
21	require Exporter;	108	our @EXPORT = qw(encode_json decode_json to_json from_json);
22		109
		110	sub to_json($) {
23	require XSLoader;	111	require Carp;
24	XSLoader::load JSON::XS::, $VERSION;	112	Carp::croak ("JSON::XS::to_json has been renamed to encode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call");
25	}	113	}
26		114
27	=item	115	sub from_json($) {
		116	require Carp;
		117	Carp::croak ("JSON::XS::from_json has been renamed to decode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call");
		118	}
		119
		120	use Exporter;
		121	use XSLoader;
		122
		123	=head1 FUNCTIONAL INTERFACE
		124
		125	The following convenience methods are provided by this module. They are
		126	exported by default:
		127
		128	=over 4
		129
		130	=item $json_text = encode_json $perl_scalar
		131
		132	Converts the given Perl data structure to a UTF-8 encoded, binary string
		133	(that is, the string contains octets only). Croaks on error.
		134
		135	This function call is functionally identical to:
		136
		137	$json_text = JSON::XS->new->utf8->encode ($perl_scalar)
		138
		139	except being faster.
		140
		141	=item $perl_scalar = decode_json $json_text
		142
		143	The opposite of C<encode_json>: expects an UTF-8 (binary) string and tries
		144	to parse that as an UTF-8 encoded JSON text, returning the resulting
		145	reference. Croaks on error.
		146
		147	This function call is functionally identical to:
		148
		149	$perl_scalar = JSON::XS->new->utf8->decode ($json_text)
		150
		151	except being faster.
		152
		153	=item $is_boolean = JSON::XS::is_bool $scalar
		154
		155	Returns true if the passed scalar represents either JSON::XS::true or
		156	JSON::XS::false, two constants that act like C<1> and C<0>, respectively
		157	and are used to represent JSON C<true> and C<false> values in Perl.
		158
		159	See MAPPING, below, for more information on how JSON values are mapped to
		160	Perl.
		161
		162	=back
		163
		164
		165	=head1 A FEW NOTES ON UNICODE AND PERL
		166
		167	Since this often leads to confusion, here are a few very clear words on
		168	how Unicode works in Perl, modulo bugs.
		169
		170	=over 4
		171
		172	=item 1. Perl strings can store characters with ordinal values > 255.
		173
		174	This enables you to store Unicode characters as single characters in a
		175	Perl string - very natural.
		176
		177	=item 2. Perl does I<not> associate an encoding with your strings.
		178
		179	Unless you force it to, e.g. when matching it against a regex, or printing
		180	the scalar to a file, in which case Perl either interprets your string as
		181	locale-encoded text, octets/binary, or as Unicode, depending on various
		182	settings. In no case is an encoding stored together with your data, it is
		183	I<use> that decides encoding, not any magical metadata.
		184
		185	=item 3. The internal utf-8 flag has no meaning with regards to the
		186	encoding of your string.
		187
		188	Just ignore that flag unless you debug a Perl bug, a module written in
		189	XS or want to dive into the internals of perl. Otherwise it will only
		190	confuse you, as, despite the name, it says nothing about how your string
		191	is encoded. You can have Unicode strings with that flag set, with that
		192	flag clear, and you can have binary data with that flag set and that flag
		193	clear. Other possibilities exist, too.
		194
		195	If you didn't know about that flag, just the better, pretend it doesn't
		196	exist.
		197
		198	=item 4. A "Unicode String" is simply a string where each character can be
		199	validly interpreted as a Unicode codepoint.
		200
		201	If you have UTF-8 encoded data, it is no longer a Unicode string, but a
		202	Unicode string encoded in UTF-8, giving you a binary string.
		203
		204	=item 5. A string containing "high" (> 255) character values is I<not> a UTF-8 string.
		205
		206	It's a fact. Learn to live with it.
		207
		208	=back
		209
		210	I hope this helps :)
		211
		212
		213	=head1 OBJECT-ORIENTED INTERFACE
		214
		215	The object oriented interface lets you configure your own encoding or
		216	decoding style, within the limits of supported formats.
		217
		218	=over 4
		219
		220	=item $json = new JSON::XS
		221
		222	Creates a new JSON::XS object that can be used to de/encode JSON
		223	strings. All boolean flags described below are by default I<disabled>.
		224
		225	The mutators for flags all return the JSON object again and thus calls can
		226	be chained:
		227
		228	my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]})
		229	=> {"a": [1, 2]}
		230
		231	=item $json = $json->ascii ([$enable])
		232
		233	=item $enabled = $json->get_ascii
		234
		235	If C<$enable> is true (or missing), then the C<encode> method will not
		236	generate characters outside the code range C<0..127> (which is ASCII). Any
		237	Unicode characters outside that range will be escaped using either a
		238	single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence,
		239	as per RFC4627. The resulting encoded JSON text can be treated as a native
		240	Unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string,
		241	or any other superset of ASCII.
		242
		243	If C<$enable> is false, then the C<encode> method will not escape Unicode
		244	characters unless required by the JSON syntax or other flags. This results
		245	in a faster and more compact format.
		246
		247	The main use for this flag is to produce JSON texts that can be
		248	transmitted over a 7-bit channel, as the encoded JSON texts will not
		249	contain any 8 bit characters.
		250
		251	JSON::XS->new->ascii (1)->encode ([chr 0x10401])
		252	=> ["\ud801\udc01"]
		253
		254	=item $json = $json->latin1 ([$enable])
		255
		256	=item $enabled = $json->get_latin1
		257
		258	If C<$enable> is true (or missing), then the C<encode> method will encode
		259	the resulting JSON text as latin1 (or iso-8859-1), escaping any characters
		260	outside the code range C<0..255>. The resulting string can be treated as a
		261	latin1-encoded JSON text or a native Unicode string. The C<decode> method
		262	will not be affected in any way by this flag, as C<decode> by default
		263	expects Unicode, which is a strict superset of latin1.
		264
		265	If C<$enable> is false, then the C<encode> method will not escape Unicode
		266	characters unless required by the JSON syntax or other flags.
		267
		268	The main use for this flag is efficiently encoding binary data as JSON
		269	text, as most octets will not be escaped, resulting in a smaller encoded
		270	size. The disadvantage is that the resulting JSON text is encoded
		271	in latin1 (and must correctly be treated as such when storing and
		272	transferring), a rare encoding for JSON. It is therefore most useful when
		273	you want to store data structures known to contain binary data efficiently
		274	in files or databases, not when talking to other JSON encoders/decoders.
		275
		276	JSON::XS->new->latin1->encode (["\x{89}\x{abc}"]
		277	=> ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not)
		278
		279	=item $json = $json->utf8 ([$enable])
		280
		281	=item $enabled = $json->get_utf8
		282
		283	If C<$enable> is true (or missing), then the C<encode> method will encode
		284	the JSON result into UTF-8, as required by many protocols, while the
		285	C<decode> method expects to be handled an UTF-8-encoded string. Please
		286	note that UTF-8-encoded strings do not contain any characters outside the
		287	range C<0..255>, they are thus useful for bytewise/binary I/O. In future
		288	versions, enabling this option might enable autodetection of the UTF-16
		289	and UTF-32 encoding families, as described in RFC4627.
		290
		291	If C<$enable> is false, then the C<encode> method will return the JSON
		292	string as a (non-encoded) Unicode string, while C<decode> expects thus a
		293	Unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs
		294	to be done yourself, e.g. using the Encode module.
		295
		296	Example, output UTF-16BE-encoded JSON:
		297
		298	use Encode;
		299	$jsontext = encode "UTF-16BE", JSON::XS->new->encode ($object);
		300
		301	Example, decode UTF-32LE-encoded JSON:
		302
		303	use Encode;
		304	$object = JSON::XS->new->decode (decode "UTF-32LE", $jsontext);
		305
		306	=item $json = $json->pretty ([$enable])
		307
		308	This enables (or disables) all of the C<indent>, C<space_before> and
		309	C<space_after> (and in the future possibly more) flags in one call to
		310	generate the most readable (or most compact) form possible.
		311
		312	Example, pretty-print some simple structure:
		313
		314	my $json = JSON::XS->new->pretty(1)->encode ({a => [1,2]})
		315	=>
		316	{
		317	"a" : [
		318	1,
		319	2
		320	]
		321	}
		322
		323	=item $json = $json->indent ([$enable])
		324
		325	=item $enabled = $json->get_indent
		326
		327	If C<$enable> is true (or missing), then the C<encode> method will use a multiline
		328	format as output, putting every array member or object/hash key-value pair
		329	into its own line, indenting them properly.
		330
		331	If C<$enable> is false, no newlines or indenting will be produced, and the
		332	resulting JSON text is guaranteed not to contain any C<newlines>.
		333
		334	This setting has no effect when decoding JSON texts.
		335
		336	=item $json = $json->space_before ([$enable])
		337
		338	=item $enabled = $json->get_space_before
		339
		340	If C<$enable> is true (or missing), then the C<encode> method will add an extra
		341	optional space before the C<:> separating keys from values in JSON objects.
		342
		343	If C<$enable> is false, then the C<encode> method will not add any extra
		344	space at those places.
		345
		346	This setting has no effect when decoding JSON texts. You will also
		347	most likely combine this setting with C<space_after>.
		348
		349	Example, space_before enabled, space_after and indent disabled:
		350
		351	{"key" :"value"}
		352
		353	=item $json = $json->space_after ([$enable])
		354
		355	=item $enabled = $json->get_space_after
		356
		357	If C<$enable> is true (or missing), then the C<encode> method will add an extra
		358	optional space after the C<:> separating keys from values in JSON objects
		359	and extra whitespace after the C<,> separating key-value pairs and array
		360	members.
		361
		362	If C<$enable> is false, then the C<encode> method will not add any extra
		363	space at those places.
		364
		365	This setting has no effect when decoding JSON texts.
		366
		367	Example, space_before and indent disabled, space_after enabled:
		368
		369	{"key": "value"}
		370
		371	=item $json = $json->relaxed ([$enable])
		372
		373	=item $enabled = $json->get_relaxed
		374
		375	If C<$enable> is true (or missing), then C<decode> will accept some
		376	extensions to normal JSON syntax (see below). C<encode> will not be
		377	affected in anyway. I<Be aware that this option makes you accept invalid
		378	JSON texts as if they were valid!>. I suggest only to use this option to
		379	parse application-specific files written by humans (configuration files,
		380	resource files etc.)
		381
		382	If C<$enable> is false (the default), then C<decode> will only accept
		383	valid JSON texts.
		384
		385	Currently accepted extensions are:
		386
		387	=over 4
		388
		389	=item * list items can have an end-comma
		390
		391	JSON I<separates> array elements and key-value pairs with commas. This
		392	can be annoying if you write JSON texts manually and want to be able to
		393	quickly append elements, so this extension accepts comma at the end of
		394	such items not just between them:
		395
		396	[
		397	1,
		398	2, <- this comma not normally allowed
		399	]
		400	{
		401	"k1": "v1",
		402	"k2": "v2", <- this comma not normally allowed
		403	}
		404
		405	=item * shell-style '#'-comments
		406
		407	Whenever JSON allows whitespace, shell-style comments are additionally
		408	allowed. They are terminated by the first carriage-return or line-feed
		409	character, after which more white-space and comments are allowed.
		410
		411	[
		412	1, # this comment not allowed in JSON
		413	# neither this one...
		414	]
		415
		416	=back
		417
		418	=item $json = $json->canonical ([$enable])
		419
		420	=item $enabled = $json->get_canonical
		421
		422	If C<$enable> is true (or missing), then the C<encode> method will output JSON objects
		423	by sorting their keys. This is adding a comparatively high overhead.
		424
		425	If C<$enable> is false, then the C<encode> method will output key-value
		426	pairs in the order Perl stores them (which will likely change between runs
		427	of the same script).
		428
		429	This option is useful if you want the same data structure to be encoded as
		430	the same JSON text (given the same overall settings). If it is disabled,
		431	the same hash might be encoded differently even if contains the same data,
		432	as key-value pairs have no inherent ordering in Perl.
		433
		434	This setting has no effect when decoding JSON texts.
		435
		436	=item $json = $json->allow_nonref ([$enable])
		437
		438	=item $enabled = $json->get_allow_nonref
		439
		440	If C<$enable> is true (or missing), then the C<encode> method can convert a
		441	non-reference into its corresponding string, number or null JSON value,
		442	which is an extension to RFC4627. Likewise, C<decode> will accept those JSON
		443	values instead of croaking.
		444
		445	If C<$enable> is false, then the C<encode> method will croak if it isn't
		446	passed an arrayref or hashref, as JSON texts must either be an object
		447	or array. Likewise, C<decode> will croak if given something that is not a
		448	JSON object or array.
		449
		450	Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>,
		451	resulting in an invalid JSON text:
		452
		453	JSON::XS->new->allow_nonref->encode ("Hello, World!")
		454	=> "Hello, World!"
		455
		456	=item $json = $json->allow_blessed ([$enable])
		457
		458	=item $enabled = $json->get_allow_blessed
		459
		460	If C<$enable> is true (or missing), then the C<encode> method will not
		461	barf when it encounters a blessed reference. Instead, the value of the
		462	B<convert_blessed> option will decide whether C<null> (C<convert_blessed>
		463	disabled or no C<TO_JSON> method found) or a representation of the
		464	object (C<convert_blessed> enabled and C<TO_JSON> method found) is being
		465	encoded. Has no effect on C<decode>.
		466
		467	If C<$enable> is false (the default), then C<encode> will throw an
		468	exception when it encounters a blessed object.
		469
		470	=item $json = $json->convert_blessed ([$enable])
		471
		472	=item $enabled = $json->get_convert_blessed
		473
		474	If C<$enable> is true (or missing), then C<encode>, upon encountering a
		475	blessed object, will check for the availability of the C<TO_JSON> method
		476	on the object's class. If found, it will be called in scalar context
		477	and the resulting scalar will be encoded instead of the object. If no
		478	C<TO_JSON> method is found, the value of C<allow_blessed> will decide what
		479	to do.
		480
		481	The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON>
		482	returns other blessed objects, those will be handled in the same
		483	way. C<TO_JSON> must take care of not causing an endless recursion cycle
		484	(== crash) in this case. The name of C<TO_JSON> was chosen because other
		485	methods called by the Perl core (== not by the user of the object) are
		486	usually in upper case letters and to avoid collisions with any C<to_json>
		487	function or method.
		488
		489	This setting does not yet influence C<decode> in any way, but in the
		490	future, global hooks might get installed that influence C<decode> and are
		491	enabled by this setting.
		492
		493	If C<$enable> is false, then the C<allow_blessed> setting will decide what
		494	to do when a blessed object is found.
		495
		496	=item $json = $json->filter_json_object ([$coderef->($hashref)])
		497
		498	When C<$coderef> is specified, it will be called from C<decode> each
		499	time it decodes a JSON object. The only argument is a reference to the
		500	newly-created hash. If the code references returns a single scalar (which
		501	need not be a reference), this value (i.e. a copy of that scalar to avoid
		502	aliasing) is inserted into the deserialised data structure. If it returns
		503	an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the
		504	original deserialised hash will be inserted. This setting can slow down
		505	decoding considerably.
		506
		507	When C<$coderef> is omitted or undefined, any existing callback will
		508	be removed and C<decode> will not change the deserialised hash in any
		509	way.
		510
		511	Example, convert all JSON objects into the integer 5:
		512
		513	my $js = JSON::XS->new->filter_json_object (sub { 5 });
		514	# returns [5]
		515	$js->decode ('[{}]')
		516	# throw an exception because allow_nonref is not enabled
		517	# so a lone 5 is not allowed.
		518	$js->decode ('{"a":1, "b":2}');
		519
		520	=item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)])
		521
		522	Works remotely similar to C<filter_json_object>, but is only called for
		523	JSON objects having a single key named C<$key>.
		524
		525	This C<$coderef> is called before the one specified via
		526	C<filter_json_object>, if any. It gets passed the single value in the JSON
		527	object. If it returns a single value, it will be inserted into the data
		528	structure. If it returns nothing (not even C<undef> but the empty list),
		529	the callback from C<filter_json_object> will be called next, as if no
		530	single-key callback were specified.
		531
		532	If C<$coderef> is omitted or undefined, the corresponding callback will be
		533	disabled. There can only ever be one callback for a given key.
		534
		535	As this callback gets called less often then the C<filter_json_object>
		536	one, decoding speed will not usually suffer as much. Therefore, single-key
		537	objects make excellent targets to serialise Perl objects into, especially
		538	as single-key JSON objects are as close to the type-tagged value concept
		539	as JSON gets (it's basically an ID/VALUE tuple). Of course, JSON does not
		540	support this in any way, so you need to make sure your data never looks
		541	like a serialised Perl hash.
		542
		543	Typical names for the single object key are C<__class_whatever__>, or
		544	C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even
		545	things like C<__class_md5sum(classname)__>, to reduce the risk of clashing
		546	with real hashes.
		547
		548	Example, decode JSON objects of the form C<< { "__widget__" => <id> } >>
		549	into the corresponding C<< $WIDGET{<id>} >> object:
		550
		551	# return whatever is in $WIDGET{5}:
		552	JSON::XS
		553	->new
		554	->filter_json_single_key_object (__widget__ => sub {
		555	$WIDGET{ $_[0] }
		556	})
		557	->decode ('{"__widget__": 5')
		558
		559	# this can be used with a TO_JSON method in some "widget" class
		560	# for serialisation to json:
		561	sub WidgetBase::TO_JSON {
		562	my ($self) = @_;
		563
		564	unless ($self->{id}) {
		565	$self->{id} = ..get..some..id..;
		566	$WIDGET{$self->{id}} = $self;
		567	}
		568
		569	{ __widget__ => $self->{id} }
		570	}
		571
		572	=item $json = $json->shrink ([$enable])
		573
		574	=item $enabled = $json->get_shrink
		575
		576	Perl usually over-allocates memory a bit when allocating space for
		577	strings. This flag optionally resizes strings generated by either
		578	C<encode> or C<decode> to their minimum size possible. This can save
		579	memory when your JSON texts are either very very long or you have many
		580	short strings. It will also try to downgrade any strings to octet-form
		581	if possible: perl stores strings internally either in an encoding called
		582	UTF-X or in octet-form. The latter cannot store everything but uses less
		583	space in general (and some buggy Perl or C code might even rely on that
		584	internal representation being used).
		585
		586	The actual definition of what shrink does might change in future versions,
		587	but it will always try to save space at the expense of time.
		588
		589	If C<$enable> is true (or missing), the string returned by C<encode> will
		590	be shrunk-to-fit, while all strings generated by C<decode> will also be
		591	shrunk-to-fit.
		592
		593	If C<$enable> is false, then the normal perl allocation algorithms are used.
		594	If you work with your data, then this is likely to be faster.
		595
		596	In the future, this setting might control other things, such as converting
		597	strings that look like integers or floats into integers or floats
		598	internally (there is no difference on the Perl level), saving space.
		599
		600	=item $json = $json->max_depth ([$maximum_nesting_depth])
		601
		602	=item $max_depth = $json->get_max_depth
		603
		604	Sets the maximum nesting level (default C<512>) accepted while encoding
		605	or decoding. If the JSON text or Perl data structure has an equal or
		606	higher nesting level then this limit, then the encoder and decoder will
		607	stop and croak at that point.
		608
		609	Nesting level is defined by number of hash- or arrayrefs that the encoder
		610	needs to traverse to reach a given point or the number of C<{> or C<[>
		611	characters without their matching closing parenthesis crossed to reach a
		612	given character in a string.
		613
		614	Setting the maximum depth to one disallows any nesting, so that ensures
		615	that the object is only a single hash/object or array.
		616
		617	The argument to C<max_depth> will be rounded up to the next highest power
		618	of two. If no argument is given, the highest possible setting will be
		619	used, which is rarely useful.
		620
		621	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.
		622
		623	=item $json = $json->max_size ([$maximum_string_size])
		624
		625	=item $max_size = $json->get_max_size
		626
		627	Set the maximum length a JSON text may have (in bytes) where decoding is
		628	being attempted. The default is C<0>, meaning no limit. When C<decode>
		629	is called on a string longer then this number of characters it will not
		630	attempt to decode the string but throw an exception. This setting has no
		631	effect on C<encode> (yet).
		632
		633	The argument to C<max_size> will be rounded up to the next B<highest>
		634	power of two (so may be more than requested). If no argument is given, the
		635	limit check will be deactivated (same as when C<0> is specified).
		636
		637	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.
		638
		639	=item $json_text = $json->encode ($perl_scalar)
		640
		641	Converts the given Perl data structure (a simple scalar or a reference
		642	to a hash or array) to its JSON representation. Simple scalars will be
		643	converted into JSON string or number sequences, while references to arrays
		644	become JSON arrays and references to hashes become JSON objects. Undefined
		645	Perl values (e.g. C<undef>) become JSON C<null> values. Neither C<true>
		646	nor C<false> values will be generated.
		647
		648	=item $perl_scalar = $json->decode ($json_text)
		649
		650	The opposite of C<encode>: expects a JSON text and tries to parse it,
		651	returning the resulting simple scalar or reference. Croaks on error.
		652
		653	JSON numbers and strings become simple Perl scalars. JSON arrays become
		654	Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes
		655	C<1>, C<false> becomes C<0> and C<null> becomes C<undef>.
		656
		657	=item ($perl_scalar, $characters) = $json->decode_prefix ($json_text)
		658
		659	This works like the C<decode> method, but instead of raising an exception
		660	when there is trailing garbage after the first JSON object, it will
		661	silently stop parsing there and return the number of characters consumed
		662	so far.
		663
		664	This is useful if your JSON texts are not delimited by an outer protocol
		665	(which is not the brightest thing to do in the first place) and you need
		666	to know where the JSON text ends.
		667
		668	JSON::XS->new->decode_prefix ("[1] the tail")
		669	=> ([], 3)
		670
		671	=back
		672
		673
		674	=head1 MAPPING
		675
		676	This section describes how JSON::XS maps Perl values to JSON values and
		677	vice versa. These mappings are designed to "do the right thing" in most
		678	circumstances automatically, preserving round-tripping characteristics
		679	(what you put in comes out as something equivalent).
		680
		681	For the more enlightened: note that in the following descriptions,
		682	lowercase I<perl> refers to the Perl interpreter, while uppercase I<Perl>
		683	refers to the abstract Perl language itself.
		684
		685
		686	=head2 JSON -> PERL
		687
		688	=over 4
		689
		690	=item object
		691
		692	A JSON object becomes a reference to a hash in Perl. No ordering of object
		693	keys is preserved (JSON does not preserve object key ordering itself).
		694
		695	=item array
		696
		697	A JSON array becomes a reference to an array in Perl.
		698
		699	=item string
		700
		701	A JSON string becomes a string scalar in Perl - Unicode codepoints in JSON
		702	are represented by the same codepoints in the Perl string, so no manual
		703	decoding is necessary.
		704
		705	=item number
		706
		707	A JSON number becomes either an integer, numeric (floating point) or
		708	string scalar in perl, depending on its range and any fractional parts. On
		709	the Perl level, there is no difference between those as Perl handles all
		710	the conversion details, but an integer may take slightly less memory and
		711	might represent more values exactly than (floating point) numbers.
		712
		713	If the number consists of digits only, JSON::XS will try to represent
		714	it as an integer value. If that fails, it will try to represent it as
		715	a numeric (floating point) value if that is possible without loss of
		716	precision. Otherwise it will preserve the number as a string value.
		717
		718	Numbers containing a fractional or exponential part will always be
		719	represented as numeric (floating point) values, possibly at a loss of
		720	precision.
		721
		722	This might create round-tripping problems as numbers might become strings,
		723	but as Perl is typeless there is no other way to do it.
		724
		725	=item true, false
		726
		727	These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>,
		728	respectively. They are overloaded to act almost exactly like the numbers
		729	C<1> and C<0>. You can check whether a scalar is a JSON boolean by using
		730	the C<JSON::XS::is_bool> function.
		731
		732	=item null
		733
		734	A JSON null atom becomes C<undef> in Perl.
		735
		736	=back
		737
		738
		739	=head2 PERL -> JSON
		740
		741	The mapping from Perl to JSON is slightly more difficult, as Perl is a
		742	truly typeless language, so we can only guess which JSON type is meant by
		743	a Perl value.
		744
		745	=over 4
		746
		747	=item hash references
		748
		749	Perl hash references become JSON objects. As there is no inherent ordering
		750	in hash keys (or JSON objects), they will usually be encoded in a
		751	pseudo-random order that can change between runs of the same program but
		752	stays generally the same within a single run of a program. JSON::XS can
		753	optionally sort the hash keys (determined by the I<canonical> flag), so
		754	the same datastructure will serialise to the same JSON text (given same
		755	settings and version of JSON::XS), but this incurs a runtime overhead
		756	and is only rarely useful, e.g. when you want to compare some JSON text
		757	against another for equality.
		758
		759	=item array references
		760
		761	Perl array references become JSON arrays.
		762
		763	=item other references
		764
		765	Other unblessed references are generally not allowed and will cause an
		766	exception to be thrown, except for references to the integers C<0> and
		767	C<1>, which get turned into C<false> and C<true> atoms in JSON. You can
		768	also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability.
		769
		770	encode_json [\0,JSON::XS::true] # yields [false,true]
		771
		772	=item JSON::XS::true, JSON::XS::false
		773
		774	These special values become JSON true and JSON false values,
		775	respectively. You can also use C<\1> and C<\0> directly if you want.
		776
		777	=item blessed objects
		778
		779	Blessed objects are not allowed. JSON::XS currently tries to encode their
		780	underlying representation (hash- or arrayref), but this behaviour might
		781	change in future versions.
		782
		783	=item simple scalars
		784
		785	Simple Perl scalars (any scalar that is not a reference) are the most
		786	difficult objects to encode: JSON::XS will encode undefined scalars as
		787	JSON null value, scalars that have last been used in a string context
		788	before encoding as JSON strings and anything else as number value:
		789
		790	# dump as number
		791	encode_json [2] # yields [2]
		792	encode_json [-3.0e17] # yields [-3e+17]
		793	my $value = 5; encode_json [$value] # yields [5]
		794
		795	# used as string, so dump as string
		796	print $value;
		797	encode_json [$value] # yields ["5"]
		798
		799	# undef becomes null
		800	encode_json [undef] # yields [null]
		801
		802	You can force the type to be a JSON string by stringifying it:
		803
		804	my $x = 3.1; # some variable containing a number
		805	"$x"; # stringified
		806	$x .= ""; # another, more awkward way to stringify
		807	print $x; # perl does it for you, too, quite often
		808
		809	You can force the type to be a JSON number by numifying it:
		810
		811	my $x = "3"; # some variable containing a string
		812	$x += 0; # numify it, ensuring it will be dumped as a number
		813	$x *= 1; # same thing, the choice is yours.
		814
		815	You can not currently force the type in other, less obscure, ways. Tell me
		816	if you need this capability.
		817
		818	=back
		819
		820
		821	=head1 COMPARISON
		822
		823	As already mentioned, this module was created because none of the existing
		824	JSON modules could be made to work correctly. First I will describe the
		825	problems (or pleasures) I encountered with various existing JSON modules,
		826	followed by some benchmark values. JSON::XS was designed not to suffer
		827	from any of these problems or limitations.
		828
		829	=over 4
		830
		831	=item JSON 1.07
		832
		833	Slow (but very portable, as it is written in pure Perl).
		834
		835	Undocumented/buggy Unicode handling (how JSON handles Unicode values is
		836	undocumented. One can get far by feeding it Unicode strings and doing
		837	en-/decoding oneself, but Unicode escapes are not working properly).
		838
		839	No round-tripping (strings get clobbered if they look like numbers, e.g.
		840	the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will
		841	decode into the number 2.
		842
		843	=item JSON::PC 0.01
		844
		845	Very fast.
		846
		847	Undocumented/buggy Unicode handling.
		848
		849	No round-tripping.
		850
		851	Has problems handling many Perl values (e.g. regex results and other magic
		852	values will make it croak).
		853
		854	Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}>
		855	which is not a valid JSON text.
		856
		857	Unmaintained (maintainer unresponsive for many months, bugs are not
		858	getting fixed).
		859
		860	=item JSON::Syck 0.21
		861
		862	Very buggy (often crashes).
		863
		864	Very inflexible (no human-readable format supported, format pretty much
		865	undocumented. I need at least a format for easy reading by humans and a
		866	single-line compact format for use in a protocol, and preferably a way to
		867	generate ASCII-only JSON texts).
		868
		869	Completely broken (and confusingly documented) Unicode handling (Unicode
		870	escapes are not working properly, you need to set ImplicitUnicode to
		871	I<different> values on en- and decoding to get symmetric behaviour).
		872
		873	No round-tripping (simple cases work, but this depends on whether the scalar
		874	value was used in a numeric context or not).
		875
		876	Dumping hashes may skip hash values depending on iterator state.
		877
		878	Unmaintained (maintainer unresponsive for many months, bugs are not
		879	getting fixed).
		880
		881	Does not check input for validity (i.e. will accept non-JSON input and
		882	return "something" instead of raising an exception. This is a security
		883	issue: imagine two banks transferring money between each other using
		884	JSON. One bank might parse a given non-JSON request and deduct money,
		885	while the other might reject the transaction with a syntax error. While a
		886	good protocol will at least recover, that is extra unnecessary work and
		887	the transaction will still not succeed).
		888
		889	=item JSON::DWIW 0.04
		890
		891	Very fast. Very natural. Very nice.
		892
		893	Undocumented Unicode handling (but the best of the pack. Unicode escapes
		894	still don't get parsed properly).
		895
		896	Very inflexible.
		897
		898	No round-tripping.
		899
		900	Does not generate valid JSON texts (key strings are often unquoted, empty keys
		901	result in nothing being output)
		902
		903	Does not check input for validity.
		904
		905	=back
		906
		907
		908	=head2 JSON and YAML
		909
		910	You often hear that JSON is a subset (or a close subset) of YAML. This is,
		911	however, a mass hysteria and very far from the truth. In general, there is
		912	no way to configure JSON::XS to output a data structure as valid YAML.
		913
		914	If you really must use JSON::XS to generate YAML, you should use this
		915	algorithm (subject to change in future versions):
		916
		917	my $to_yaml = JSON::XS->new->utf8->space_after (1);
		918	my $yaml = $to_yaml->encode ($ref) . "\n";
		919
		920	This will usually generate JSON texts that also parse as valid
		921	YAML. Please note that YAML has hardcoded limits on (simple) object key
		922	lengths that JSON doesn't have, so you should make sure that your hash
		923	keys are noticeably shorter than the 1024 characters YAML allows.
		924
		925	There might be other incompatibilities that I am not aware of. In general
		926	you should not try to generate YAML with a JSON generator or vice versa,
		927	or try to parse JSON with a YAML parser or vice versa: chances are high
		928	that you will run into severe interoperability problems.
		929
		930
		931	=head2 SPEED
		932
		933	It seems that JSON::XS is surprisingly fast, as shown in the following
		934	tables. They have been generated with the help of the C<eg/bench> program
		935	in the JSON::XS distribution, to make it easy to compare on your own
		936	system.
		937
		938	First comes a comparison between various modules using a very short
		939	single-line JSON string:
		940
		941	{"method": "handleMessage", "params": ["user1", "we were just talking"], \
		942	"id": null, "array":[1,11,234,-5,1e5,1e7, true, false]}
		943
		944	It shows the number of encodes/decodes per second (JSON::XS uses
		945	the functional interface, while JSON::XS/2 uses the OO interface
		946	with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables
		947	shrink). Higher is better:
		948
		949	module \| encode \| decode \|
		950	-----------\|------------\|------------\|
		951	JSON 1.x \| 4990.842 \| 4088.813 \|
		952	JSON::DWIW \| 51653.990 \| 71575.154 \|
		953	JSON::PC \| 65948.176 \| 74631.744 \|
		954	JSON::PP \| 8931.652 \| 3817.168 \|
		955	JSON::Syck \| 24877.248 \| 27776.848 \|
		956	JSON::XS \| 388361.481 \| 227951.304 \|
		957	JSON::XS/2 \| 227951.304 \| 218453.333 \|
		958	JSON::XS/3 \| 338250.323 \| 218453.333 \|
		959	Storable \| 16500.016 \| 135300.129 \|
		960	-----------+------------+------------+
		961
		962	That is, JSON::XS is about five times faster than JSON::DWIW on encoding,
		963	about three times faster on decoding, and over forty times faster
		964	than JSON, even with pretty-printing and key sorting. It also compares
		965	favourably to Storable for small amounts of data.
		966
		967	Using a longer test string (roughly 18KB, generated from Yahoo! Locals
		968	search API (http://nanoref.com/yahooapis/mgPdGg):
		969
		970	module \| encode \| decode \|
		971	-----------\|------------\|------------\|
		972	JSON 1.x \| 55.260 \| 34.971 \|
		973	JSON::DWIW \| 825.228 \| 1082.513 \|
		974	JSON::PC \| 3571.444 \| 2394.829 \|
		975	JSON::PP \| 210.987 \| 32.574 \|
		976	JSON::Syck \| 552.551 \| 787.544 \|
		977	JSON::XS \| 5780.463 \| 4854.519 \|
		978	JSON::XS/2 \| 3869.998 \| 4798.975 \|
		979	JSON::XS/3 \| 5862.880 \| 4798.975 \|
		980	Storable \| 4445.002 \| 5235.027 \|
		981	-----------+------------+------------+
		982
		983	Again, JSON::XS leads by far (except for Storable which non-surprisingly
		984	decodes faster).
		985
		986	On large strings containing lots of high Unicode characters, some modules
		987	(such as JSON::PC) seem to decode faster than JSON::XS, but the result
		988	will be broken due to missing (or wrong) Unicode handling. Others refuse
		989	to decode or encode properly, so it was impossible to prepare a fair
		990	comparison table for that case.
		991
		992
		993	=head1 SECURITY CONSIDERATIONS
		994
		995	When you are using JSON in a protocol, talking to untrusted potentially
		996	hostile creatures requires relatively few measures.
		997
		998	First of all, your JSON decoder should be secure, that is, should not have
		999	any buffer overflows. Obviously, this module should ensure that and I am
		1000	trying hard on making that true, but you never know.
		1001
		1002	Second, you need to avoid resource-starving attacks. That means you should
		1003	limit the size of JSON texts you accept, or make sure then when your
		1004	resources run out, that's just fine (e.g. by using a separate process that
		1005	can crash safely). The size of a JSON text in octets or characters is
		1006	usually a good indication of the size of the resources required to decode
		1007	it into a Perl structure. While JSON::XS can check the size of the JSON
		1008	text, it might be too late when you already have it in memory, so you
		1009	might want to check the size before you accept the string.
		1010
		1011	Third, JSON::XS recurses using the C stack when decoding objects and
		1012	arrays. The C stack is a limited resource: for instance, on my amd64
		1013	machine with 8MB of stack size I can decode around 180k nested arrays but
		1014	only 14k nested JSON objects (due to perl itself recursing deeply on croak
		1015	to free the temporary). If that is exceeded, the program crashes. to be
		1016	conservative, the default nesting limit is set to 512. If your process
		1017	has a smaller stack, you should adjust this setting accordingly with the
		1018	C<max_depth> method.
		1019
		1020	And last but least, something else could bomb you that I forgot to think
		1021	of. In that case, you get to keep the pieces. I am always open for hints,
		1022	though...
		1023
		1024	If you are using JSON::XS to return packets to consumption
		1025	by JavaScript scripts in a browser you should have a look at
		1026	L<http://jpsykes.com/47/practical-csrf-and-json-security> to see whether
		1027	you are vulnerable to some common attack vectors (which really are browser
		1028	design bugs, but it is still you who will have to deal with it, as major
		1029	browser developers care only for features, not about doing security
		1030	right).
		1031
		1032
		1033	=head1 THREADS
		1034
		1035	This module is I<not> guaranteed to be thread safe and there are no
		1036	plans to change this until Perl gets thread support (as opposed to the
		1037	horribly slow so-called "threads" which are simply slow and bloated
		1038	process simulations - use fork, its I<much> faster, cheaper, better).
		1039
		1040	(It might actually work, but you have been warned).
		1041
		1042
		1043	=head1 BUGS
		1044
		1045	While the goal of this module is to be correct, that unfortunately does
		1046	not mean its bug-free, only that I think its design is bug-free. It is
		1047	still relatively early in its development. If you keep reporting bugs they
		1048	will be fixed swiftly, though.
		1049
		1050	Please refrain from using rt.cpan.org or any other bug reporting
		1051	service. I put the contact address into my modules for a reason.
28		1052
29	=cut	1053	=cut
30		1054
31	use JSON::DWIW;	1055	our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" };
32	use Benchmark;	1056	our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" };
33		1057
34	use utf8;	1058	sub true() { $true }
35	#my $json = '{"ü":1,"a":[1,{"3":4},2],"b":5,"üü":2}';	1059	sub false() { $false }
36	my $json = '{"test":9555555555555555555,"hu" : -1e+5, "arr" : [ 1,2,3,4,5]}';
37		1060
38	my $js = JSON::XS->new;	1061	sub is_bool($) {
39	warn $js->indent (0);	1062	UNIVERSAL::isa $_[0], "JSON::XS::Boolean"
40	warn $js->canonical (0);	1063	# or UNIVERSAL::isa $_[0], "JSON::Literal"
41	warn $js->ascii (0);	1064	}
42	warn $js->space_after (0);
43	use Data::Dumper;
44	warn Dumper $js->decode ($json);
45	warn Dumper $js->encode ($js->decode ($json));
46	#my $x = {"üü" => 2, "ü" => 1, "a" => [1,{3,4},2], b => 5};
47		1065
48	#my $js2 = JSON::DWIW->new;	1066	XSLoader::load "JSON::XS", $VERSION;
49	#	1067
50	#timethese 200000, {	1068	package JSON::XS::Boolean;
51	# a => sub { $js->encode ($x) },	1069
52	# b => sub { $js2->to_json ($x) },	1070	use overload
53	#};	1071	"0+" => sub { ${$_[0]} },
		1072	"++" => sub { $_[0] = ${$_[0]} + 1 },
		1073	"--" => sub { $_[0] = ${$_[0]} - 1 },
		1074	fallback => 1;
54		1075
55	1;	1076	1;
56
57	=back
58		1077
59	=head1 AUTHOR	1078	=head1 AUTHOR
60		1079
61	Marc Lehmann <schmorp@schmorp.de>	1080	Marc Lehmann <schmorp@schmorp.de>
62	http://home.schmorp.de/	1081	http://home.schmorp.de/

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing JSON-XS/XS.pm (file contents): Revision 1.1 by root, Thu Mar 22 16:40:16 2007 UTC vs. Revision 1.78 by root, Wed Dec 5 10:59:28 2007 UTC

Diff Legend

Comparing JSON-XS/XS.pm (file contents):
Revision 1.1 by root, Thu Mar 22 16:40:16 2007 UTC vs.
Revision 1.78 by root, Wed Dec 5 10:59:28 2007 UTC