From 391edb01f8122b4e229a2d7c78529a4e080abc1a Mon Sep 17 00:00:00 2001
From: Aaron Patterson <aaron.patterson@gmail.com>
Date: Mon, 19 Oct 2015 10:53:16 -0700
Subject: resize strings after parsing

The parser uses `rb_str_buf_new` to allocate new strings.
`rb_str_buf_new` [has a minimum size of 128 and is not an embedded
string](https://github.com/ruby/ruby/blob/9949407fd90c1c5bfe332141c75db995a9b867aa/string.c#L1119-L1135).  This causes applications that parse JS to allocate extra memory when parsing short strings.

For a real-world example, we can use the mime-types gem.  The mime-types
gem stores all mime types inside a JSON file and parses them when you
require the gem.

Here is a sample program:

```ruby
require 'objspace'
require 'mime-types'

GC.start
GC.start

p ObjectSpace.memsize_of_all String
```

The example program loads the mime-types gem and outputs the total space
used by all strings.  Here are the results of the program before and
after this patch:

** Before **

```
[aaron@TC json (memuse)]$ ruby test.rb
5497494
[aaron@TC json (memuse)]$
```

** After **

```
[aaron@TC json (memuse)]$ ruby -I lib:ext test.rb
3335862
[aaron@TC json (memuse)]$
```

This change results in a ~40% reduction of memory use for strings in the
mime-types gem.

Thanks @matthewd for finding the problem, and @nobu for the patch!
---
 ext/json/ext/parser/parser.rl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ext/json/ext/parser/parser.rl b/ext/json/ext/parser/parser.rl
index f3933cb..157b001 100644
--- a/ext/json/ext/parser/parser.rl
+++ b/ext/json/ext/parser/parser.rl
@@ -527,6 +527,8 @@ static char *JSON_parse_string(JSON_Parser *json, char *p, char *pe, VALUE *resu
 
     if (json->symbolize_names && json->parsing_name) {
       *result = rb_str_intern(*result);
+    } else {
+      rb_str_resize(*result, RSTRING_LEN(*result));
     }
     if (cs >= JSON_string_first_final) {
         return p + 1;
-- 
cgit v1.2.1


From 4aae95f41b6b972245d15e52c46dbd5f278ff2c2 Mon Sep 17 00:00:00 2001
From: Aaron Patterson <aaron.patterson@gmail.com>
Date: Thu, 3 Mar 2016 14:49:15 -0800
Subject: regenerate parser

---
 ext/json/ext/parser/parser.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ext/json/ext/parser/parser.c b/ext/json/ext/parser/parser.c
index 5b2e61c..ea95e71 100644
--- a/ext/json/ext/parser/parser.c
+++ b/ext/json/ext/parser/parser.c
@@ -1632,6 +1632,8 @@ case 7:
 
     if (json->symbolize_names && json->parsing_name) {
       *result = rb_str_intern(*result);
+    } else {
+      rb_str_resize(*result, RSTRING_LEN(*result));
     }
     if (cs >= JSON_string_first_final) {
         return p + 1;
-- 
cgit v1.2.1