[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 1.51 by root, Mon Jul 2 01:12:27 2007 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use JSON::XS;	7	use JSON::XS;
8		8
		9	# exported functions, they croak on error
		10	# and expect/generate UTF-8
		11
		12	$utf8_encoded_json_text = to_json $perl_hash_or_arrayref;
		13	$perl_hash_or_arrayref = from_json $utf8_encoded_json_text;
		14
		15	# OO-interface
		16
		17	$coder = JSON::XS->new->ascii->pretty->allow_nonref;
		18	$pretty_printed_unencoded = $coder->encode ($perl_scalar);
		19	$perl_scalar = $coder->decode ($unicode_json_text);
		20
9	=head1 DESCRIPTION	21	=head1 DESCRIPTION
10		22
		23	This module converts Perl data structures to JSON and vice versa. Its
		24	primary goal is to be I<correct> and its secondary goal is to be
		25	I<fast>. To reach the latter goal it was written in C.
		26
		27	As this is the n-th-something JSON module on CPAN, what was the reason
		28	to write yet another JSON module? While it seems there are many JSON
		29	modules, none of them correctly handle all corner cases, and in most cases
		30	their maintainers are unresponsive, gone missing, or not listening to bug
		31	reports for other reasons.
		32
		33	See COMPARISON, below, for a comparison to some other JSON modules.
		34
		35	See MAPPING, below, on how JSON::XS maps perl values to JSON values and
		36	vice versa.
		37
		38	=head2 FEATURES
		39
11	=over 4	40	=over 4
12		41
		42	=item * correct unicode handling
		43
		44	This module knows how to handle Unicode, and even documents how and when
		45	it does so.
		46
		47	=item * round-trip integrity
		48
		49	When you serialise a perl data structure using only datatypes supported
		50	by JSON, the deserialised data structure is identical on the Perl level.
		51	(e.g. the string "2.0" doesn't suddenly become "2" just because it looks
		52	like a number).
		53
		54	=item * strict checking of JSON correctness
		55
		56	There is no guessing, no generating of illegal JSON texts by default,
		57	and only JSON is accepted as input by default (the latter is a security
		58	feature).
		59
		60	=item * fast
		61
		62	Compared to other JSON modules, this module compares favourably in terms
		63	of speed, too.
		64
		65	=item * simple to use
		66
		67	This module has both a simple functional interface as well as an OO
		68	interface.
		69
		70	=item * reasonably versatile output formats
		71
		72	You can choose between the most compact guarenteed single-line format
		73	possible (nice for simple line-based protocols), a pure-ascii format
		74	(for when your transport is not 8-bit clean, still supports the whole
		75	unicode range), or a pretty-printed format (for when you want to read that
		76	stuff). Or you can combine those features in whatever way you like.
		77
		78	=back
		79
13	=cut	80	=cut
14		81
15	package JSON::XS;	82	package JSON::XS;
16		83
17	BEGIN {	84	use strict;
		85
18	$VERSION = '0.1';	86	our $VERSION = '1.4';
19	@ISA = qw(Exporter);	87	our @ISA = qw(Exporter);
20		88
21	require Exporter;	89	our @EXPORT = qw(to_json from_json);
22		90
23	require XSLoader;	91	use Exporter;
24	XSLoader::load JSON::XS::, $VERSION;	92	use XSLoader;
		93
		94	=head1 FUNCTIONAL INTERFACE
		95
		96	The following convinience methods are provided by this module. They are
		97	exported by default:
		98
		99	=over 4
		100
		101	=item $json_text = to_json $perl_scalar
		102
		103	Converts the given Perl data structure (a simple scalar or a reference to
		104	a hash or array) to a UTF-8 encoded, binary string (that is, the string contains
		105	octets only). Croaks on error.
		106
		107	This function call is functionally identical to:
		108
		109	$json_text = JSON::XS->new->utf8->encode ($perl_scalar)
		110
		111	except being faster.
		112
		113	=item $perl_scalar = from_json $json_text
		114
		115	The opposite of C<to_json>: expects an UTF-8 (binary) string and tries to
		116	parse that as an UTF-8 encoded JSON text, returning the resulting simple
		117	scalar or reference. Croaks on error.
		118
		119	This function call is functionally identical to:
		120
		121	$perl_scalar = JSON::XS->new->utf8->decode ($json_text)
		122
		123	except being faster.
		124
		125	=item $is_boolean = JSON::XS::is_bool $scalar
		126
		127	Returns true if the passed scalar represents either JSON::XS::true or
		128	JSON::XS::false, two constants that act like C<1> and C<0>, respectively
		129	and are used to represent JSON C<true> and C<false> values in Perl.
		130
		131	See MAPPING, below, for more information on how JSON values are mapped to
		132	Perl.
		133
		134	=back
		135
		136
		137	=head1 OBJECT-ORIENTED INTERFACE
		138
		139	The object oriented interface lets you configure your own encoding or
		140	decoding style, within the limits of supported formats.
		141
		142	=over 4
		143
		144	=item $json = new JSON::XS
		145
		146	Creates a new JSON::XS object that can be used to de/encode JSON
		147	strings. All boolean flags described below are by default I<disabled>.
		148
		149	The mutators for flags all return the JSON object again and thus calls can
		150	be chained:
		151
		152	my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]})
		153	=> {"a": [1, 2]}
		154
		155	=item $json = $json->ascii ([$enable])
		156
		157	If C<$enable> is true (or missing), then the C<encode> method will not
		158	generate characters outside the code range C<0..127> (which is ASCII). Any
		159	unicode characters outside that range will be escaped using either a
		160	single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence,
		161	as per RFC4627. The resulting encoded JSON text can be treated as a native
		162	unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string,
		163	or any other superset of ASCII.
		164
		165	If C<$enable> is false, then the C<encode> method will not escape Unicode
		166	characters unless required by the JSON syntax or other flags. This results
		167	in a faster and more compact format.
		168
		169	The main use for this flag is to produce JSON texts that can be
		170	transmitted over a 7-bit channel, as the encoded JSON texts will not
		171	contain any 8 bit characters.
		172
		173	JSON::XS->new->ascii (1)->encode ([chr 0x10401])
		174	=> ["\ud801\udc01"]
		175
		176	=item $json = $json->latin1 ([$enable])
		177
		178	If C<$enable> is true (or missing), then the C<encode> method will encode
		179	the resulting JSON text as latin1 (or iso-8859-1), escaping any characters
		180	outside the code range C<0..255>. The resulting string can be treated as a
		181	latin1-encoded JSON text or a native unicode string. The C<decode> method
		182	will not be affected in any way by this flag, as C<decode> by default
		183	expects unicode, which is a strict superset of latin1.
		184
		185	If C<$enable> is false, then the C<encode> method will not escape Unicode
		186	characters unless required by the JSON syntax or other flags.
		187
		188	The main use for this flag is efficiently encoding binary data as JSON
		189	text, as most octets will not be escaped, resulting in a smaller encoded
		190	size. The disadvantage is that the resulting JSON text is encoded
		191	in latin1 (and must correctly be treated as such when storing and
		192	transfering), a rare encoding for JSON. It is therefore most useful when
		193	you want to store data structures known to contain binary data efficiently
		194	in files or databases, not when talking to other JSON encoders/decoders.
		195
		196	JSON::XS->new->latin1->encode (["\x{89}\x{abc}"]
		197	=> ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not)
		198
		199	=item $json = $json->utf8 ([$enable])
		200
		201	If C<$enable> is true (or missing), then the C<encode> method will encode
		202	the JSON result into UTF-8, as required by many protocols, while the
		203	C<decode> method expects to be handled an UTF-8-encoded string. Please
		204	note that UTF-8-encoded strings do not contain any characters outside the
		205	range C<0..255>, they are thus useful for bytewise/binary I/O. In future
		206	versions, enabling this option might enable autodetection of the UTF-16
		207	and UTF-32 encoding families, as described in RFC4627.
		208
		209	If C<$enable> is false, then the C<encode> method will return the JSON
		210	string as a (non-encoded) unicode string, while C<decode> expects thus a
		211	unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs
		212	to be done yourself, e.g. using the Encode module.
		213
		214	Example, output UTF-16BE-encoded JSON:
		215
		216	use Encode;
		217	$jsontext = encode "UTF-16BE", JSON::XS->new->encode ($object);
		218
		219	Example, decode UTF-32LE-encoded JSON:
		220
		221	use Encode;
		222	$object = JSON::XS->new->decode (decode "UTF-32LE", $jsontext);
		223
		224	=item $json = $json->pretty ([$enable])
		225
		226	This enables (or disables) all of the C<indent>, C<space_before> and
		227	C<space_after> (and in the future possibly more) flags in one call to
		228	generate the most readable (or most compact) form possible.
		229
		230	Example, pretty-print some simple structure:
		231
		232	my $json = JSON::XS->new->pretty(1)->encode ({a => [1,2]})
		233	=>
		234	{
		235	"a" : [
		236	1,
		237	2
		238	]
		239	}
		240
		241	=item $json = $json->indent ([$enable])
		242
		243	If C<$enable> is true (or missing), then the C<encode> method will use a multiline
		244	format as output, putting every array member or object/hash key-value pair
		245	into its own line, identing them properly.
		246
		247	If C<$enable> is false, no newlines or indenting will be produced, and the
		248	resulting JSON text is guarenteed not to contain any C<newlines>.
		249
		250	This setting has no effect when decoding JSON texts.
		251
		252	=item $json = $json->space_before ([$enable])
		253
		254	If C<$enable> is true (or missing), then the C<encode> method will add an extra
		255	optional space before the C<:> separating keys from values in JSON objects.
		256
		257	If C<$enable> is false, then the C<encode> method will not add any extra
		258	space at those places.
		259
		260	This setting has no effect when decoding JSON texts. You will also
		261	most likely combine this setting with C<space_after>.
		262
		263	Example, space_before enabled, space_after and indent disabled:
		264
		265	{"key" :"value"}
		266
		267	=item $json = $json->space_after ([$enable])
		268
		269	If C<$enable> is true (or missing), then the C<encode> method will add an extra
		270	optional space after the C<:> separating keys from values in JSON objects
		271	and extra whitespace after the C<,> separating key-value pairs and array
		272	members.
		273
		274	If C<$enable> is false, then the C<encode> method will not add any extra
		275	space at those places.
		276
		277	This setting has no effect when decoding JSON texts.
		278
		279	Example, space_before and indent disabled, space_after enabled:
		280
		281	{"key": "value"}
		282
		283	=item $json = $json->canonical ([$enable])
		284
		285	If C<$enable> is true (or missing), then the C<encode> method will output JSON objects
		286	by sorting their keys. This is adding a comparatively high overhead.
		287
		288	If C<$enable> is false, then the C<encode> method will output key-value
		289	pairs in the order Perl stores them (which will likely change between runs
		290	of the same script).
		291
		292	This option is useful if you want the same data structure to be encoded as
		293	the same JSON text (given the same overall settings). If it is disabled,
		294	the same hash migh be encoded differently even if contains the same data,
		295	as key-value pairs have no inherent ordering in Perl.
		296
		297	This setting has no effect when decoding JSON texts.
		298
		299	=item $json = $json->allow_nonref ([$enable])
		300
		301	If C<$enable> is true (or missing), then the C<encode> method can convert a
		302	non-reference into its corresponding string, number or null JSON value,
		303	which is an extension to RFC4627. Likewise, C<decode> will accept those JSON
		304	values instead of croaking.
		305
		306	If C<$enable> is false, then the C<encode> method will croak if it isn't
		307	passed an arrayref or hashref, as JSON texts must either be an object
		308	or array. Likewise, C<decode> will croak if given something that is not a
		309	JSON object or array.
		310
		311	Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>,
		312	resulting in an invalid JSON text:
		313
		314	JSON::XS->new->allow_nonref->encode ("Hello, World!")
		315	=> "Hello, World!"
		316
		317	=item $json = $json->allow_blessed ([$enable])
		318
		319	If C<$enable> is true (or missing), then the C<encode> method will not
		320	barf when it encounters a blessed reference. Instead, the value of the
		321	B<convert_blessed> option will decide wether C<null> (C<convert_blessed>
		322	disabled or no C<to_json> method found) or a representation of the
		323	object (C<convert_blessed> enabled and C<to_json> method found) is being
		324	encoded. Has no effect on C<decode>.
		325
		326	If C<$enable> is false (the default), then C<encode> will throw an
		327	exception when it encounters a blessed object.
		328
		329	=item $json = $json->convert_blessed ([$enable])
		330
		331	If C<$enable> is true (or missing), then C<encode>, upon encountering a
		332	blessed object, will check for the availability of the C<TO_JSON> method
		333	on the object's class. If found, it will be called in scalar context
		334	and the resulting scalar will be encoded instead of the object. If no
		335	C<TO_JSON> method is found, the value of C<allow_blessed> will decide what
		336	to do.
		337
		338	The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON>
		339	returns other blessed objects, those will be handled in the same
		340	way. C<TO_JSON> must take care of not causing an endless recursion cycle
		341	(== crash) in this case. The name of C<TO_JSON> was chosen because other
		342	methods called by the Perl core (== not by the user of the object) are
		343	usually in upper case letters and to avoid collisions with the C<to_json>
		344	function.
		345
		346	This setting does not yet influence C<decode> in any way, but in the
		347	future, global hooks might get installed that influence C<decode> and are
		348	enabled by this setting.
		349
		350	If C<$enable> is false, then the C<allow_blessed> setting will decide what
		351	to do when a blessed object is found.
		352
		353	=item $json = $json->filter_json_object ([$coderef])
		354
		355	When C<$coderef> is specified, it will be called from C<decode> each
		356	time it decodes a JSON object. The only argument is a reference to the
		357	newly-created hash. If the code references returns a single scalar (which
		358	need not be a reference), this value (i.e. a copy of that scalar to avoid
		359	aliasing) is inserted into the deserialised data structure. If it returns
		360	an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the
		361	original deserialised hash will be inserted. This setting can slow down
		362	decoding considerably.
		363
		364	When C<$coderef> is omitted or undefined, C<decode> will not change the
		365	deserialised hash in any way. This is maximally fast.
		366
		367	Example, convert all JSON objects into the integer 5:
		368
		369	my $js = JSON::XS->new->filter_json_object (sub { 5 });
		370	# returns [5]
		371	$js->decode ('[{}]')
		372	# throw an exception because allow_nonref is not enabled:
		373	$js->decode ('{"a":1, "b":2}');
		374
		375	=item $json = $json->filter_json_single_key_object ([$coderef])
		376
		377	Works like C<filter_json_object>, but is only called for JSON objects
		378	having only a single key.
		379
		380	This C<$coderef> is called before the one specified via
		381	C<filter_json_object>, if any. If it returns something, that will be
		382	inserted into the data structure. If it returns nothing, the callback
		383	from C<filter_json_object> will be called next. If you want to force
		384	insertion of single-key objects even in the presence of a mutating
		385	C<filter_json_object> callback, simply return the passed hash.
		386
		387	As this callback gets called less often then the C<filter_json_object>
		388	one, decoding speed will not usually suffer as much. Therefore, single-key
		389	objects make excellent targets to serialise Perl objects into, especially
		390	as single-key JSON objects are as close to the type-tagged value concept
		391	as JSON gets (its basically an ID/VALUE tuple). Of course, JSON does not
		392	support this in any way, so you need to make sure your data never looks
		393	like a serialised Perl hash.
		394
		395	Typical names for the single object key are C<__class_whatever__>, or
		396	C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even
		397	things like C<__class_md5sum(classname)__>, to reduce the risk of clashing
		398	with real hashes.
		399
		400	Example, decode JSON objects of the form C<< { "__widget__" => <id> } >>
		401	into the corresponding C<< $WIDGET{<id>} >> object:
		402
		403	# return whatever is in $WIDGET{5}:
		404	JSON::XS
		405	->new
		406	->filter_json_single_key_object (sub {
		407	exists $_[0]{__widget__}
		408	? $WIDGET{ $_[0]{__widget__} }
		409	: ()
		410	})
		411	->decode ('{"__widget__": 5')
		412
		413	# this can be used with a TO_JSON method in some "widget" class
		414	# for serialisation to json:
		415	sub WidgetBase::TO_JSON {
		416	my ($self) = @_;
		417
		418	unless ($self->{id}) {
		419	$self->{id} = ..get..some..id..;
		420	$WIDGET{$self->{id}} = $self;
		421	}
		422
		423	{ __widget__ => $self->{id} }
		424	}
		425
		426	=item $json = $json->shrink ([$enable])
		427
		428	Perl usually over-allocates memory a bit when allocating space for
		429	strings. This flag optionally resizes strings generated by either
		430	C<encode> or C<decode> to their minimum size possible. This can save
		431	memory when your JSON texts are either very very long or you have many
		432	short strings. It will also try to downgrade any strings to octet-form
		433	if possible: perl stores strings internally either in an encoding called
		434	UTF-X or in octet-form. The latter cannot store everything but uses less
		435	space in general (and some buggy Perl or C code might even rely on that
		436	internal representation being used).
		437
		438	The actual definition of what shrink does might change in future versions,
		439	but it will always try to save space at the expense of time.
		440
		441	If C<$enable> is true (or missing), the string returned by C<encode> will
		442	be shrunk-to-fit, while all strings generated by C<decode> will also be
		443	shrunk-to-fit.
		444
		445	If C<$enable> is false, then the normal perl allocation algorithms are used.
		446	If you work with your data, then this is likely to be faster.
		447
		448	In the future, this setting might control other things, such as converting
		449	strings that look like integers or floats into integers or floats
		450	internally (there is no difference on the Perl level), saving space.
		451
		452	=item $json = $json->max_depth ([$maximum_nesting_depth])
		453
		454	Sets the maximum nesting level (default C<512>) accepted while encoding
		455	or decoding. If the JSON text or Perl data structure has an equal or
		456	higher nesting level then this limit, then the encoder and decoder will
		457	stop and croak at that point.
		458
		459	Nesting level is defined by number of hash- or arrayrefs that the encoder
		460	needs to traverse to reach a given point or the number of C<{> or C<[>
		461	characters without their matching closing parenthesis crossed to reach a
		462	given character in a string.
		463
		464	Setting the maximum depth to one disallows any nesting, so that ensures
		465	that the object is only a single hash/object or array.
		466
		467	The argument to C<max_depth> will be rounded up to the next highest power
		468	of two. If no argument is given, the highest possible setting will be
		469	used, which is rarely useful.
		470
		471	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.
		472
		473	=item $json = $json->max_size ([$maximum_string_size])
		474
		475	Set the maximum length a JSON text may have (in bytes) where decoding is
		476	being attempted. The default is C<0>, meaning no limit. When C<decode>
		477	is called on a string longer then this number of characters it will not
		478	attempt to decode the string but throw an exception. This setting has no
		479	effect on C<encode> (yet).
		480
		481	The argument to C<max_size> will be rounded up to the next B<highest>
		482	power of two (so may be more than requested). If no argument is given, the
		483	limit check will be deactivated (same as when C<0> is specified).
		484
		485	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.
		486
		487	=item $json_text = $json->encode ($perl_scalar)
		488
		489	Converts the given Perl data structure (a simple scalar or a reference
		490	to a hash or array) to its JSON representation. Simple scalars will be
		491	converted into JSON string or number sequences, while references to arrays
		492	become JSON arrays and references to hashes become JSON objects. Undefined
		493	Perl values (e.g. C<undef>) become JSON C<null> values. Neither C<true>
		494	nor C<false> values will be generated.
		495
		496	=item $perl_scalar = $json->decode ($json_text)
		497
		498	The opposite of C<encode>: expects a JSON text and tries to parse it,
		499	returning the resulting simple scalar or reference. Croaks on error.
		500
		501	JSON numbers and strings become simple Perl scalars. JSON arrays become
		502	Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes
		503	C<1>, C<false> becomes C<0> and C<null> becomes C<undef>.
		504
		505	=item ($perl_scalar, $characters) = $json->decode_prefix ($json_text)
		506
		507	This works like the C<decode> method, but instead of raising an exception
		508	when there is trailing garbage after the first JSON object, it will
		509	silently stop parsing there and return the number of characters consumed
		510	so far.
		511
		512	This is useful if your JSON texts are not delimited by an outer protocol
		513	(which is not the brightest thing to do in the first place) and you need
		514	to know where the JSON text ends.
		515
		516	JSON::XS->new->decode_prefix ("[1] the tail")
		517	=> ([], 3)
		518
		519	=back
		520
		521
		522	=head1 MAPPING
		523
		524	This section describes how JSON::XS maps Perl values to JSON values and
		525	vice versa. These mappings are designed to "do the right thing" in most
		526	circumstances automatically, preserving round-tripping characteristics
		527	(what you put in comes out as something equivalent).
		528
		529	For the more enlightened: note that in the following descriptions,
		530	lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl>
		531	refers to the abstract Perl language itself.
		532
		533
		534	=head2 JSON -> PERL
		535
		536	=over 4
		537
		538	=item object
		539
		540	A JSON object becomes a reference to a hash in Perl. No ordering of object
		541	keys is preserved (JSON does not preserver object key ordering itself).
		542
		543	=item array
		544
		545	A JSON array becomes a reference to an array in Perl.
		546
		547	=item string
		548
		549	A JSON string becomes a string scalar in Perl - Unicode codepoints in JSON
		550	are represented by the same codepoints in the Perl string, so no manual
		551	decoding is necessary.
		552
		553	=item number
		554
		555	A JSON number becomes either an integer or numeric (floating point)
		556	scalar in perl, depending on its range and any fractional parts. On the
		557	Perl level, there is no difference between those as Perl handles all the
		558	conversion details, but an integer may take slightly less memory and might
		559	represent more values exactly than (floating point) numbers.
		560
		561	=item true, false
		562
		563	These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>,
		564	respectively. They are overloaded to act almost exactly like the numbers
		565	C<1> and C<0>. You can check wether a scalar is a JSON boolean by using
		566	the C<JSON::XS::is_bool> function.
		567
		568	=item null
		569
		570	A JSON null atom becomes C<undef> in Perl.
		571
		572	=back
		573
		574
		575	=head2 PERL -> JSON
		576
		577	The mapping from Perl to JSON is slightly more difficult, as Perl is a
		578	truly typeless language, so we can only guess which JSON type is meant by
		579	a Perl value.
		580
		581	=over 4
		582
		583	=item hash references
		584
		585	Perl hash references become JSON objects. As there is no inherent ordering
		586	in hash keys (or JSON objects), they will usually be encoded in a
		587	pseudo-random order that can change between runs of the same program but
		588	stays generally the same within a single run of a program. JSON::XS can
		589	optionally sort the hash keys (determined by the I<canonical> flag), so
		590	the same datastructure will serialise to the same JSON text (given same
		591	settings and version of JSON::XS), but this incurs a runtime overhead
		592	and is only rarely useful, e.g. when you want to compare some JSON text
		593	against another for equality.
		594
		595	=item array references
		596
		597	Perl array references become JSON arrays.
		598
		599	=item other references
		600
		601	Other unblessed references are generally not allowed and will cause an
		602	exception to be thrown, except for references to the integers C<0> and
		603	C<1>, which get turned into C<false> and C<true> atoms in JSON. You can
		604	also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability.
		605
		606	to_json [\0,JSON::XS::true] # yields [false,true]
		607
		608	=item JSON::XS::true, JSON::XS::false
		609
		610	These special values become JSON true and JSON false values,
		611	respectively. You cna alos use C<\1> and C<\0> directly if you want.
		612
		613	=item blessed objects
		614
		615	Blessed objects are not allowed. JSON::XS currently tries to encode their
		616	underlying representation (hash- or arrayref), but this behaviour might
		617	change in future versions.
		618
		619	=item simple scalars
		620
		621	Simple Perl scalars (any scalar that is not a reference) are the most
		622	difficult objects to encode: JSON::XS will encode undefined scalars as
		623	JSON null value, scalars that have last been used in a string context
		624	before encoding as JSON strings and anything else as number value:
		625
		626	# dump as number
		627	to_json [2] # yields [2]
		628	to_json [-3.0e17] # yields [-3e+17]
		629	my $value = 5; to_json [$value] # yields [5]
		630
		631	# used as string, so dump as string
		632	print $value;
		633	to_json [$value] # yields ["5"]
		634
		635	# undef becomes null
		636	to_json [undef] # yields [null]
		637
		638	You can force the type to be a string by stringifying it:
		639
		640	my $x = 3.1; # some variable containing a number
		641	"$x"; # stringified
		642	$x .= ""; # another, more awkward way to stringify
		643	print $x; # perl does it for you, too, quite often
		644
		645	You can force the type to be a number by numifying it:
		646
		647	my $x = "3"; # some variable containing a string
		648	$x += 0; # numify it, ensuring it will be dumped as a number
		649	$x *= 1; # same thing, the choise is yours.
		650
		651	You can not currently output JSON booleans or force the type in other,
		652	less obscure, ways. Tell me if you need this capability.
		653
		654	=back
		655
		656
		657	=head1 COMPARISON
		658
		659	As already mentioned, this module was created because none of the existing
		660	JSON modules could be made to work correctly. First I will describe the
		661	problems (or pleasures) I encountered with various existing JSON modules,
		662	followed by some benchmark values. JSON::XS was designed not to suffer
		663	from any of these problems or limitations.
		664
		665	=over 4
		666
		667	=item JSON 1.07
		668
		669	Slow (but very portable, as it is written in pure Perl).
		670
		671	Undocumented/buggy Unicode handling (how JSON handles unicode values is
		672	undocumented. One can get far by feeding it unicode strings and doing
		673	en-/decoding oneself, but unicode escapes are not working properly).
		674
		675	No roundtripping (strings get clobbered if they look like numbers, e.g.
		676	the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will
		677	decode into the number 2.
		678
		679	=item JSON::PC 0.01
		680
		681	Very fast.
		682
		683	Undocumented/buggy Unicode handling.
		684
		685	No roundtripping.
		686
		687	Has problems handling many Perl values (e.g. regex results and other magic
		688	values will make it croak).
		689
		690	Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}>
		691	which is not a valid JSON text.
		692
		693	Unmaintained (maintainer unresponsive for many months, bugs are not
		694	getting fixed).
		695
		696	=item JSON::Syck 0.21
		697
		698	Very buggy (often crashes).
		699
		700	Very inflexible (no human-readable format supported, format pretty much
		701	undocumented. I need at least a format for easy reading by humans and a
		702	single-line compact format for use in a protocol, and preferably a way to
		703	generate ASCII-only JSON texts).
		704
		705	Completely broken (and confusingly documented) Unicode handling (unicode
		706	escapes are not working properly, you need to set ImplicitUnicode to
		707	I<different> values on en- and decoding to get symmetric behaviour).
		708
		709	No roundtripping (simple cases work, but this depends on wether the scalar
		710	value was used in a numeric context or not).
		711
		712	Dumping hashes may skip hash values depending on iterator state.
		713
		714	Unmaintained (maintainer unresponsive for many months, bugs are not
		715	getting fixed).
		716
		717	Does not check input for validity (i.e. will accept non-JSON input and
		718	return "something" instead of raising an exception. This is a security
		719	issue: imagine two banks transfering money between each other using
		720	JSON. One bank might parse a given non-JSON request and deduct money,
		721	while the other might reject the transaction with a syntax error. While a
		722	good protocol will at least recover, that is extra unnecessary work and
		723	the transaction will still not succeed).
		724
		725	=item JSON::DWIW 0.04
		726
		727	Very fast. Very natural. Very nice.
		728
		729	Undocumented unicode handling (but the best of the pack. Unicode escapes
		730	still don't get parsed properly).
		731
		732	Very inflexible.
		733
		734	No roundtripping.
		735
		736	Does not generate valid JSON texts (key strings are often unquoted, empty keys
		737	result in nothing being output)
		738
		739	Does not check input for validity.
		740
		741	=back
		742
		743
		744	=head2 JSON and YAML
		745
		746	You often hear that JSON is a subset (or a close subset) of YAML. This is,
		747	however, a mass hysteria and very far from the truth. In general, there is
		748	no way to configure JSON::XS to output a data structure as valid YAML.
		749
		750	If you really must use JSON::XS to generate YAML, you should use this
		751	algorithm (subject to change in future versions):
		752
		753	my $to_yaml = JSON::XS->new->utf8->space_after (1);
		754	my $yaml = $to_yaml->encode ($ref) . "\n";
		755
		756	This will usually generate JSON texts that also parse as valid
		757	YAML. Please note that YAML has hardcoded limits on (simple) object key
		758	lengths that JSON doesn't have, so you should make sure that your hash
		759	keys are noticably shorter than the 1024 characters YAML allows.
		760
		761	There might be other incompatibilities that I am not aware of. In general
		762	you should not try to generate YAML with a JSON generator or vice versa,
		763	or try to parse JSON with a YAML parser or vice versa: chances are high
		764	that you will run into severe interoperability problems.
		765
		766
		767	=head2 SPEED
		768
		769	It seems that JSON::XS is surprisingly fast, as shown in the following
		770	tables. They have been generated with the help of the C<eg/bench> program
		771	in the JSON::XS distribution, to make it easy to compare on your own
		772	system.
		773
		774	First comes a comparison between various modules using a very short
		775	single-line JSON string:
		776
		777	{"method": "handleMessage", "params": ["user1", "we were just talking"], \
		778	"id": null, "array":[1,11,234,-5,1e5,1e7, true, false]}
		779
		780	It shows the number of encodes/decodes per second (JSON::XS uses
		781	the functional interface, while JSON::XS/2 uses the OO interface
		782	with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables
		783	shrink). Higher is better:
		784
		785	Storable \| 15779.925 \| 14169.946 \|
		786	-----------+------------+------------+
		787	module \| encode \| decode \|
		788	-----------\|------------\|------------\|
		789	JSON \| 4990.842 \| 4088.813 \|
		790	JSON::DWIW \| 51653.990 \| 71575.154 \|
		791	JSON::PC \| 65948.176 \| 74631.744 \|
		792	JSON::PP \| 8931.652 \| 3817.168 \|
		793	JSON::Syck \| 24877.248 \| 27776.848 \|
		794	JSON::XS \| 388361.481 \| 227951.304 \|
		795	JSON::XS/2 \| 227951.304 \| 218453.333 \|
		796	JSON::XS/3 \| 338250.323 \| 218453.333 \|
		797	Storable \| 16500.016 \| 135300.129 \|
		798	-----------+------------+------------+
		799
		800	That is, JSON::XS is about five times faster than JSON::DWIW on encoding,
		801	about three times faster on decoding, and over fourty times faster
		802	than JSON, even with pretty-printing and key sorting. It also compares
		803	favourably to Storable for small amounts of data.
		804
		805	Using a longer test string (roughly 18KB, generated from Yahoo! Locals
		806	search API (http://nanoref.com/yahooapis/mgPdGg):
		807
		808	module \| encode \| decode \|
		809	-----------\|------------\|------------\|
		810	JSON \| 55.260 \| 34.971 \|
		811	JSON::DWIW \| 825.228 \| 1082.513 \|
		812	JSON::PC \| 3571.444 \| 2394.829 \|
		813	JSON::PP \| 210.987 \| 32.574 \|
		814	JSON::Syck \| 552.551 \| 787.544 \|
		815	JSON::XS \| 5780.463 \| 4854.519 \|
		816	JSON::XS/2 \| 3869.998 \| 4798.975 \|
		817	JSON::XS/3 \| 5862.880 \| 4798.975 \|
		818	Storable \| 4445.002 \| 5235.027 \|
		819	-----------+------------+------------+
		820
		821	Again, JSON::XS leads by far (except for Storable which non-surprisingly
		822	decodes faster).
		823
		824	On large strings containing lots of high unicode characters, some modules
		825	(such as JSON::PC) seem to decode faster than JSON::XS, but the result
		826	will be broken due to missing (or wrong) unicode handling. Others refuse
		827	to decode or encode properly, so it was impossible to prepare a fair
		828	comparison table for that case.
		829
		830
		831	=head1 SECURITY CONSIDERATIONS
		832
		833	When you are using JSON in a protocol, talking to untrusted potentially
		834	hostile creatures requires relatively few measures.
		835
		836	First of all, your JSON decoder should be secure, that is, should not have
		837	any buffer overflows. Obviously, this module should ensure that and I am
		838	trying hard on making that true, but you never know.
		839
		840	Second, you need to avoid resource-starving attacks. That means you should
		841	limit the size of JSON texts you accept, or make sure then when your
		842	resources run out, thats just fine (e.g. by using a separate process that
		843	can crash safely). The size of a JSON text in octets or characters is
		844	usually a good indication of the size of the resources required to decode
		845	it into a Perl structure. While JSON::XS can check the size of the JSON
		846	text, it might be too late when you already have it in memory, so you
		847	might want to check the size before you accept the string.
		848
		849	Third, JSON::XS recurses using the C stack when decoding objects and
		850	arrays. The C stack is a limited resource: for instance, on my amd64
		851	machine with 8MB of stack size I can decode around 180k nested arrays but
		852	only 14k nested JSON objects (due to perl itself recursing deeply on croak
		853	to free the temporary). If that is exceeded, the program crashes. to be
		854	conservative, the default nesting limit is set to 512. If your process
		855	has a smaller stack, you should adjust this setting accordingly with the
		856	C<max_depth> method.
		857
		858	And last but least, something else could bomb you that I forgot to think
		859	of. In that case, you get to keep the pieces. I am always open for hints,
		860	though...
		861
		862	If you are using JSON::XS to return packets to consumption
		863	by javascript scripts in a browser you should have a look at
		864	L<http://jpsykes.com/47/practical-csrf-and-json-security> to see wether
		865	you are vulnerable to some common attack vectors (which really are browser
		866	design bugs, but it is still you who will have to deal with it, as major
		867	browser developers care only for features, not about doing security
		868	right).
		869
		870
		871	=head1 BUGS
		872
		873	While the goal of this module is to be correct, that unfortunately does
		874	not mean its bug-free, only that I think its design is bug-free. It is
		875	still relatively early in its development. If you keep reporting bugs they
		876	will be fixed swiftly, though.
		877
		878	=cut
		879
		880	our $true = do { bless \(my $dummy = "1"), "JSON::XS::Boolean" };
		881	our $false = do { bless \(my $dummy = "0"), "JSON::XS::Boolean" };
		882
		883	sub true() { $true }
		884	sub false() { $false }
		885
		886	sub is_bool($) {
		887	UNIVERSAL::isa $_[0], "JSON::XS::Boolean"
		888	# or UNIVERSAL::isa $_[0], "JSON::Literal"
25	}	889	}
26		890
27	=item	891	XSLoader::load "JSON::XS", $VERSION;
28		892
29	=cut	893	package JSON::XS::Boolean;
30		894
31	use JSON::DWIW;	895	use overload
32	use Benchmark;	896	"0+" => sub { ${$_[0]} },
33		897	"++" => sub { $_[0] = ${$_[0]} + 1 },
34	use utf8;	898	"--" => sub { $_[0] = ${$_[0]} - 1 },
35	#my $json = '{"ü":1,"a":[1,{"3":4},2],"b":5,"üü":2}';	899	fallback => 1;
36	my $json = '{"test":9555555555555555555,"hu" : -1e+5, "arr" : [ 1,2,3,4,5]}';
37
38	my $js = JSON::XS->new;
39	warn $js->indent (0);
40	warn $js->canonical (0);
41	warn $js->ascii (0);
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
48	#my $js2 = JSON::DWIW->new;
49	#
50	#timethese 200000, {
51	# a => sub { $js->encode ($x) },
52	# b => sub { $js2->to_json ($x) },
53	#};
54		900
55	1;	901	1;
56
57	=back
58		902
59	=head1 AUTHOR	903	=head1 AUTHOR
60		904
61	Marc Lehmann <schmorp@schmorp.de>	905	Marc Lehmann <schmorp@schmorp.de>
62	http://home.schmorp.de/	906	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 1.51 by root, Mon Jul 2 01:12:27 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 1.51 by root, Mon Jul 2 01:12:27 2007 UTC