json 2.7.5 → 2.9.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8138305febf8acb1cc4533b5e5b071928167b88f17567cf18d99fc1dcbeef234
-  data.tar.gz: 9648ecf580a9f686cd1fb879efbeb85509c800f13c1372e282298eb713dce740
+  metadata.gz: 8404bbc1f96ebfb471ebafc0fadef1f11125cd62c6cf1157091793183a8bdc32
+  data.tar.gz: 4c93c85a2575eda3308cf404f116d8e638605d884fb14cd3ab3ee511b649c211
 SHA512:
-  metadata.gz: 6a34f95616a3ac364d06004e8b2049c36b760206553e2596993af96cf295755019c083f2e1a51b931829dc199c2ebc919dfbac2079be9c7198b8ed03ae999df6
-  data.tar.gz: fbd73f6e5fa24dd5406556a0dba0ad8cb7d3c704700d29322eded2a2bc6405a16dd12d7cadd6792153970b7dfbbf013dddf70d626ae05609c57a76c4401de950
+  metadata.gz: 2043b99c8ca617249d1b3c81d899ebaf86dc2436196f08b0f9a32ee3ba7fa174c20124ca0f75157828049dc71f46fcd8937978cf463f952b2f2e6af113dfab42
+  data.tar.gz: bccae4170d82569a9018ef7497bfb5b228a9371e7c79d84cb4fcc7659be144e3a3ba455db40ecf509a31b576f311d1ad4f85989aea549f59c003210adf87fc77

data/CHANGES.md

@@ -1,5 +1,41 @@
 # Changes
 
+### 2024-12-18 (2.9.1)
+
+* Fix support for Solaris 10.
+
+### 2024-12-03 (2.9.0)
+
+* Fix C implementation of `script_safe` escaping to not confuse some other 3 wide characters with `\u2028` and `\u2029`.
+  e.g. `JSON.generate(["倩", "瀨"], script_safe: true)` would generate the wrong JSON.
+* `JSON.dump(object, some_io)` now write into the IO in chunks while previously it would buffer the entire JSON before writing.
+* `JSON::GeneratorError` now has a `#invalid_object` attribute, making it easier to understand why an object tree cannot be serialized.
+* Numerous improvements to the JRuby extension.
+
+### 2024-11-14 (2.8.2)
+
+* `JSON.load_file` explictly read the file as UTF-8.
+
+### 2024-11-06 (2.8.1)
+
+* Fix the java packages to include the extension.
+
+### 2024-11-06 (2.8.0)
+
+* Emit a deprecation warning when `JSON.load` create custom types without the `create_additions` option being explictly enabled.
+  * Prefer to use `JSON.unsafe_load(string)` or `JSON.load(string, create_additions: true)`.
+* Emit a deprecation warning when serializing valid UTF-8 strings encoded in `ASCII_8BIT` aka `BINARY`.
+* Bump required Ruby version to 2.7.
+* Add support for optionally parsing trailing commas, via `allow_trailing_comma: true`, which in cunjunction with the
+  pre-existing support for comments, make it suitable to parse `jsonc` documents.
+* Many performance improvements to `JSON.parse` and `JSON.load`, up to `1.7x` faster on real world documents.
+* Some minor performance improvements to `JSON.dump` and `JSON.generate`.
+* `JSON.pretty_generate` no longer include newline inside empty object and arrays. 
+
+### 2024-11-04 (2.7.6)
+
+* Fix a regression in JSON.generate when dealing with Hash keys that are string subclasses, call `to_json` on them.
+
 ### 2024-10-25 (2.7.5)
 
 * Fix a memory leak when `#to_json` methods raise an exception.

data/README.md

@@ -5,16 +5,10 @@
 ## Description
 
 This is an implementation of the JSON specification according to RFC 7159
-http://www.ietf.org/rfc/rfc7159.txt . There is two variants available:
+http://www.ietf.org/rfc/rfc7159.txt .
 
-* A pure ruby variant, that relies on the `strscan` extensions, which is
-  part of the ruby standard library.
-* The quite a bit faster native extension variant, which is in parts
-  implemented in C or Java and comes with a parser generated by the [Ragel]
-  state machine compiler.
-
-Both variants of the JSON generator generate UTF-8 character sequences by
-default. If an :ascii\_only option with a true value is given, they escape all
+The JSON generator generate UTF-8 character sequences by default.
+If an :ascii\_only option with a true value is given, they escape all
 non-ASCII and control characters with \uXXXX escape sequences, and support
 UTF-16 surrogate pairs in order to be able to generate the whole range of
 unicode code points.
@@ -27,10 +21,6 @@ endpoint.
 
 ## Installation
 
-It's recommended to use the extension variant of JSON, because it's faster than
-the pure ruby variant. If you cannot build it on your system, you can settle
-for the latter.
-
 Install the gem and add to the application's Gemfile by executing:
 
     $ bundle add json
@@ -39,12 +29,6 @@ If bundler is not being used to manage dependencies, install the gem by executin
 
     $ gem install json
 
-
-There is also a pure ruby json only variant of the gem, that can be installed
-with:
-
-    $ gem install json_pure
-
 ## Usage
 
 To use JSON you can
@@ -53,20 +37,6 @@ To use JSON you can
 require 'json'
 ```
 
-to load the installed variant (either the extension `'json'` or the pure
-variant `'json_pure'`). If you have installed the extension variant, you can
-pick either the extension variant or the pure variant by typing
-
-```ruby
-require 'json/ext'
-```
-
-or
-
-```ruby
-require 'json/pure'
-```
-
 Now you can parse a JSON document into a ruby data structure by calling
 
 ```ruby
@@ -82,50 +52,11 @@ You can also use the `pretty_generate` method (which formats the output more
 verbosely and nicely) or `fast_generate` (which doesn't do any of the security
 checks generate performs, e. g. nesting deepness checks).
 
-There are also the JSON and JSON[] methods which use parse on a String or
-generate a JSON document from an array or hash:
-
-```ruby
-document = JSON 'test'  => 23 # => "{\"test\":23}"
-document = JSON['test' => 23] # => "{\"test\":23}"
-```
-
-and
-
-```ruby
-data = JSON '{"test":23}'  # => {"test"=>23}
-data = JSON['{"test":23}'] # => {"test"=>23}
-```
-
-You can choose to load a set of common additions to ruby core's objects if
-you
-
-```ruby
-require 'json/add/core'
-```
-
-After requiring this you can, e. g., serialise/deserialise Ruby ranges:
-
-```ruby
-JSON JSON(1..10) # => 1..10
-```
-
-To find out how to add JSON support to other or your own classes, read the
-section "More Examples" below.
-
-## Serializing exceptions
-
-The JSON module doesn't extend `Exception` by default. If you convert an `Exception`
-object to JSON, it will by default only include the exception message.
-
-To include the full details, you must either load the `json/add/core` mentioned
-above, or specifically load the exception addition:
-
-```ruby
-require 'json/add/exception'
-```
+## Handling arbitrary types
 
-## More Examples
+> [!CAUTION]
+> You should never use `JSON.unsafe_load` nor `JSON.parse(str, create_additions: true)` to parse untrusted user input,
+> as it can lead to remote code execution vulnerabilities.
 
 To create a JSON document from a ruby data structure, you can call
 `JSON.generate` like that:
@@ -191,7 +122,7 @@ JSON.parse json
 # => [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
 json = JSON.generate [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
 # => "[1,2,{\"a\":3.141},false,true,null,{\"json_class\":\"Range\",\"data\":[4,10,false]}]"
-JSON.parse json, :create_additions => true
+JSON.unsafe_load json
 # => [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
 ```
 

data/ext/json/ext/fbuffer/fbuffer.h

@@ -4,21 +4,60 @@
 #include "ruby.h"
 #include "ruby/encoding.h"
 
+/* shims */
+/* This is the fallback definition from Ruby 3.4 */
+
+#ifndef RBIMPL_STDBOOL_H
+#if defined(__cplusplus)
+# if defined(HAVE_STDBOOL_H) && (__cplusplus >= 201103L)
+#  include <cstdbool>
+# endif
+#elif defined(HAVE_STDBOOL_H)
+# include <stdbool.h>
+#elif !defined(HAVE__BOOL)
+typedef unsigned char _Bool;
+# define bool  _Bool
+# define true  ((_Bool)+1)
+# define false ((_Bool)+0)
+# define __bool_true_false_are_defined
+#endif
+#endif
+
+#ifndef RB_UNLIKELY
+#define RB_UNLIKELY(expr) expr
+#endif
+
+#ifndef RB_LIKELY
+#define RB_LIKELY(expr) expr
+#endif
+
+#ifndef MAYBE_UNUSED
+# define MAYBE_UNUSED(x) x
+#endif
+
+enum fbuffer_type {
+    FBUFFER_HEAP_ALLOCATED = 0,
+    FBUFFER_STACK_ALLOCATED = 1,
+};
+
 typedef struct FBufferStruct {
+    enum fbuffer_type type;
     unsigned long initial_length;
-    char *ptr;
     unsigned long len;
     unsigned long capa;
+    char *ptr;
+    VALUE io;
 } FBuffer;
 
+#define FBUFFER_STACK_SIZE 512
+#define FBUFFER_IO_BUFFER_SIZE (16384 - 1)
 #define FBUFFER_INITIAL_LENGTH_DEFAULT 1024
 
-#define FBUFFER_PTR(fb) (fb->ptr)
-#define FBUFFER_LEN(fb) (fb->len)
-#define FBUFFER_CAPA(fb) (fb->capa)
+#define FBUFFER_PTR(fb) ((fb)->ptr)
+#define FBUFFER_LEN(fb) ((fb)->len)
+#define FBUFFER_CAPA(fb) ((fb)->capa)
 #define FBUFFER_PAIR(fb) FBUFFER_PTR(fb), FBUFFER_LEN(fb)
 
-static FBuffer *fbuffer_alloc(unsigned long initial_length);
 static void fbuffer_free(FBuffer *fb);
 #ifndef JSON_GENERATOR
 static void fbuffer_clear(FBuffer *fb);
@@ -27,55 +66,85 @@ static void fbuffer_append(FBuffer *fb, const char *newstr, unsigned long len);
 #ifdef JSON_GENERATOR
 static void fbuffer_append_long(FBuffer *fb, long number);
 #endif
-static void fbuffer_append_char(FBuffer *fb, char newchr);
+static inline void fbuffer_append_char(FBuffer *fb, char newchr);
 #ifdef JSON_GENERATOR
-static VALUE fbuffer_to_s(FBuffer *fb);
-#endif
-
-#ifndef RB_UNLIKELY
-#define RB_UNLIKELY(expr) expr
+static VALUE fbuffer_finalize(FBuffer *fb);
 #endif
 
-static FBuffer *fbuffer_alloc(unsigned long initial_length)
+static void fbuffer_stack_init(FBuffer *fb, unsigned long initial_length, char *stack_buffer, long stack_buffer_size)
 {
-    FBuffer *fb;
-    if (initial_length <= 0) initial_length = FBUFFER_INITIAL_LENGTH_DEFAULT;
-    fb = ALLOC(FBuffer);
-    memset((void *) fb, 0, sizeof(FBuffer));
-    fb->initial_length = initial_length;
-    return fb;
+    fb->initial_length = (initial_length > 0) ? initial_length : FBUFFER_INITIAL_LENGTH_DEFAULT;
+    if (stack_buffer) {
+        fb->type = FBUFFER_STACK_ALLOCATED;
+        fb->ptr = stack_buffer;
+        fb->capa = stack_buffer_size;
+    }
 }
 
 static void fbuffer_free(FBuffer *fb)
 {
-    if (fb->ptr) ruby_xfree(fb->ptr);
-    ruby_xfree(fb);
+    if (fb->ptr && fb->type == FBUFFER_HEAP_ALLOCATED) {
+        ruby_xfree(fb->ptr);
+    }
 }
 
-#ifndef JSON_GENERATOR
 static void fbuffer_clear(FBuffer *fb)
 {
     fb->len = 0;
 }
-#endif
 
-static inline void fbuffer_inc_capa(FBuffer *fb, unsigned long requested)
+static void fbuffer_flush(FBuffer *fb)
 {
-    if (RB_UNLIKELY(requested > fb->capa - fb->len)) {
-        unsigned long required;
+    rb_io_write(fb->io, rb_utf8_str_new(fb->ptr, fb->len));
+    fbuffer_clear(fb);
+}
 
-        if (RB_UNLIKELY(!fb->ptr)) {
-            fb->ptr = ALLOC_N(char, fb->initial_length);
-            fb->capa = fb->initial_length;
+static void fbuffer_realloc(FBuffer *fb, unsigned long required)
+{
+    if (required > fb->capa) {
+        if (fb->type == FBUFFER_STACK_ALLOCATED) {
+            const char *old_buffer = fb->ptr;
+            fb->ptr = ALLOC_N(char, required);
+            fb->type = FBUFFER_HEAP_ALLOCATED;
+            MEMCPY(fb->ptr, old_buffer, char, fb->len);
+        } else {
+            REALLOC_N(fb->ptr, char, required);
         }
+        fb->capa = required;
+    }
+}
 
-        for (required = fb->capa; requested > required - fb->len; required <<= 1);
+static void fbuffer_do_inc_capa(FBuffer *fb, unsigned long requested)
+{
+    if (RB_UNLIKELY(fb->io)) {
+        if (fb->capa < FBUFFER_IO_BUFFER_SIZE) {
+            fbuffer_realloc(fb, FBUFFER_IO_BUFFER_SIZE);
+        } else {
+            fbuffer_flush(fb);
+        }
 
-        if (required > fb->capa) {
-            REALLOC_N(fb->ptr, char, required);
-            fb->capa = required;
+        if (RB_LIKELY(requested < fb->capa)) {
+            return;
         }
     }
+
+    unsigned long required;
+
+    if (RB_UNLIKELY(!fb->ptr)) {
+        fb->ptr = ALLOC_N(char, fb->initial_length);
+        fb->capa = fb->initial_length;
+    }
+
+    for (required = fb->capa; requested > required - fb->len; required <<= 1);
+
+    fbuffer_realloc(fb, required);
+}
+
+static inline void fbuffer_inc_capa(FBuffer *fb, unsigned long requested)
+{
+    if (RB_UNLIKELY(requested > fb->capa - fb->len)) {
+        fbuffer_do_inc_capa(fb, requested);
+    }
 }
 
 static void fbuffer_append(FBuffer *fb, const char *newstr, unsigned long len)
@@ -99,7 +168,7 @@ static void fbuffer_append_str(FBuffer *fb, VALUE str)
 }
 #endif
 
-static void fbuffer_append_char(FBuffer *fb, char newchr)
+static inline void fbuffer_append_char(FBuffer *fb, char newchr)
 {
     fbuffer_inc_capa(fb, 1);
     *(fb->ptr + fb->len) = newchr;
@@ -107,40 +176,39 @@ static void fbuffer_append_char(FBuffer *fb, char newchr)
 }
 
 #ifdef JSON_GENERATOR
-static void freverse(char *start, char *end)
-{
-    char c;
-
-    while (end > start) {
-        c = *end, *end-- = *start, *start++ = c;
-    }
-}
-
 static long fltoa(long number, char *buf)
 {
-    static char digits[] = "0123456789";
+    static const char digits[] = "0123456789";
     long sign = number;
     char* tmp = buf;
 
     if (sign < 0) number = -number;
-    do *tmp++ = digits[number % 10]; while (number /= 10);
-    if (sign < 0) *tmp++ = '-';
-    freverse(buf, tmp - 1);
-    return tmp - buf;
+    do *tmp-- = digits[number % 10]; while (number /= 10);
+    if (sign < 0) *tmp-- = '-';
+    return buf - tmp;
 }
 
+#define LONG_BUFFER_SIZE 20
 static void fbuffer_append_long(FBuffer *fb, long number)
 {
-    char buf[20];
-    unsigned long len = fltoa(number, buf);
-    fbuffer_append(fb, buf, len);
+    char buf[LONG_BUFFER_SIZE];
+    char *buffer_end = buf + LONG_BUFFER_SIZE;
+    long len = fltoa(number, buffer_end - 1);
+    fbuffer_append(fb, buffer_end - len, len);
 }
 
-static VALUE fbuffer_to_s(FBuffer *fb)
+static VALUE fbuffer_finalize(FBuffer *fb)
 {
-    VALUE result = rb_utf8_str_new(FBUFFER_PTR(fb), FBUFFER_LEN(fb));
-    fbuffer_free(fb);
-    return result;
+    if (fb->io) {
+        fbuffer_flush(fb);
+        fbuffer_free(fb);
+        rb_io_flush(fb->io);
+        return fb->io;
+    } else {
+        VALUE result = rb_utf8_str_new(FBUFFER_PTR(fb), FBUFFER_LEN(fb));
+        fbuffer_free(fb);
+        return result;
+    }
 }
 #endif
 #endif