oj 3.13.17 → 3.16.3

data/ext/oj/parse.h

@@ -16,23 +16,25 @@
 #include "val_stack.h"
 
 struct _rxClass;
+struct _parseInfo;
 
 typedef struct _numInfo {
-    int64_t     i;
-    int64_t     num;
-    int64_t     div;
-    int64_t     di;
-    const char *str;
-    size_t      len;
-    long        exp;
-    int         big;
-    int         infinity;
-    int         nan;
-    int         neg;
-    int         has_exp;
-    int         no_big;
-    int         bigdec_load;
-} * NumInfo;
+    int64_t            i;
+    int64_t            num;
+    int64_t            div;
+    int64_t            di;
+    const char        *str;
+    size_t             len;
+    long               exp;
+    struct _parseInfo *pi;
+    int                big;
+    int                infinity;
+    int                nan;
+    int                neg;
+    int                has_exp;
+    int                no_big;
+    int                bigdec_load;
+} *NumInfo;
 
 typedef struct _parseInfo {
     // used for the string parser
@@ -54,11 +56,7 @@ typedef struct _parseInfo {
     VALUE (*start_hash)(struct _parseInfo *pi);
     void (*end_hash)(struct _parseInfo *pi);
     VALUE (*hash_key)(struct _parseInfo *pi, const char *key, size_t klen);
-    void (*hash_set_cstr)(struct _parseInfo *pi,
-                          Val                kval,
-                          const char *       str,
-                          size_t             len,
-                          const char *       orig);
+    void (*hash_set_cstr)(struct _parseInfo *pi, Val kval, const char *str, size_t len, const char *orig);
     void (*hash_set_num)(struct _parseInfo *pi, Val kval, NumInfo ni);
     void (*hash_set_value)(struct _parseInfo *pi, Val kval, VALUE value);
 
@@ -73,11 +71,10 @@ typedef struct _parseInfo {
     void (*add_value)(struct _parseInfo *pi, VALUE val);
     VALUE err_class;
     bool  has_callbacks;
-} * ParseInfo;
+} *ParseInfo;
 
-extern void oj_parse2(ParseInfo pi);
-extern void
-             oj_set_error_at(ParseInfo pi, VALUE err_clas, const char *file, int line, const char *format, ...);
+extern void  oj_parse2(ParseInfo pi);
+extern void  oj_set_error_at(ParseInfo pi, VALUE err_clas, const char *file, int line, const char *format, ...);
 extern VALUE oj_pi_parse(int argc, VALUE *argv, ParseInfo pi, char *json, size_t len, int yieldOk);
 extern VALUE oj_num_as_value(NumInfo ni);
 
@@ -97,6 +94,8 @@ static inline void parse_info_init(ParseInfo pi) {
     memset(pi, 0, sizeof(struct _parseInfo));
 }
 
+extern void oj_scanner_init(void);
+
 static inline bool empty_ok(Options options) {
     switch (options->mode) {
     case ObjectMode:

data/ext/oj/parser.c

@@ -20,7 +20,7 @@
 #define FRAC_LIMIT 10000000000000000ULL
 
 // Give better performance with indented JSON but worse with unindented.
-//#define SPACE_JUMP
+// #define SPACE_JUMP
 
 enum {
     SKIP_CHAR        = 'a',
@@ -1145,8 +1145,10 @@ static void parser_free(void *ptr) {
     p = (ojParser)ptr;
     buf_cleanup(&p->key);
     buf_cleanup(&p->buf);
-    p->free(p);
-    xfree(ptr);
+    if (NULL != p->free) {
+        p->free(p);
+    }
+    OJ_R_FREE(ptr);
 }
 
 static void parser_mark(void *ptr) {
@@ -1156,10 +1158,23 @@ static void parser_mark(void *ptr) {
         if (0 != p->reader) {
             rb_gc_mark(p->reader);
         }
-        p->mark(p);
+        if (NULL != p->mark) {
+            p->mark(p);
+        }
     }
 }
 
+static const rb_data_type_t oj_parser_type = {
+    "Oj/parser",
+    {
+        parser_mark,
+        parser_free,
+        NULL,
+    },
+    0,
+    0,
+};
+
 extern void oj_set_parser_validator(ojParser p);
 extern void oj_set_parser_saj(ojParser p);
 extern void oj_set_parser_usual(ojParser p);
@@ -1176,7 +1191,7 @@ static int opt_cb(VALUE rkey, VALUE value, VALUE ptr) {
         rkey = rb_sym2str(rkey);
         // fall through
     case RUBY_T_STRING:
-        key  = rb_string_value_ptr(&rkey);
+        key  = StringValuePtr(rkey);
         klen = RSTRING_LEN(rkey);
         break;
     default: rb_raise(rb_eArgError, "option keys must be a symbol or string");
@@ -1201,7 +1216,7 @@ static int opt_cb(VALUE rkey, VALUE value, VALUE ptr) {
  * Oj::Parser.new(:usual, cache_keys: true).
  */
 static VALUE parser_new(int argc, VALUE *argv, VALUE self) {
-    ojParser p = ALLOC(struct _ojParser);
+    ojParser p = OJ_R_ALLOC(struct _ojParser);
 
 #if HAVE_RB_EXT_RACTOR_SAFE
     // This doesn't seem to do anything.
@@ -1251,7 +1266,33 @@ static VALUE parser_new(int argc, VALUE *argv, VALUE self) {
             rb_hash_foreach(ropts, opt_cb, (VALUE)p);
         }
     }
-    return Data_Wrap_Struct(parser_class, parser_mark, parser_free, p);
+    return TypedData_Wrap_Struct(parser_class, &oj_parser_type, p);
+}
+
+// Create a new parser without setting the delegate. The parser is
+// wrapped. The parser is (ojParser)DATA_PTR(value) where value is the return
+// from this function. A delegate must be added before the parser can be
+// used. Optionally oj_parser_set_options can be called if the options are not
+// set directly.
+VALUE oj_parser_new(void) {
+    ojParser p = OJ_R_ALLOC(struct _ojParser);
+
+#if HAVE_RB_EXT_RACTOR_SAFE
+    // This doesn't seem to do anything.
+    rb_ext_ractor_safe(true);
+#endif
+    memset(p, 0, sizeof(struct _ojParser));
+    buf_init(&p->key);
+    buf_init(&p->buf);
+    p->map = value_map;
+
+    return TypedData_Wrap_Struct(parser_class, &oj_parser_type, p);
+}
+
+// Set set the options from a hash (ropts).
+void oj_parser_set_option(ojParser p, VALUE ropts) {
+    Check_Type(ropts, T_HASH);
+    rb_hash_foreach(ropts, opt_cb, (VALUE)p);
 }
 
 /* Document-method: method_missing(value)
@@ -1264,53 +1305,41 @@ static VALUE parser_new(int argc, VALUE *argv, VALUE self) {
  *   - no options
  *
  * - *:saj*
- *   - _cache_keys=_ sets the value of the _cache_keys_ flag.
- *   - _cache_keys_ returns the value of the _cache_keys_ flag.
- *   - _cache_strings=_ sets the value of the _cache_strings_ to an positive integer less than 35. Strings shorter than
- * that length are cached.
- *   - _cache_strings_ returns the value of the _cache_strings_ integer value.
- *   - _handler=_ sets the SAJ handler
- *   - _handler_ returns the SAJ handler
+ *   - _cache_keys_ is a flag indicating hash keys should be cached.
+ *   - _cache_strings_ is a positive integer less than 35. Strings shorter than that length are cached.
+ *   - _handler_ is the SAJ handler
  *
  * - *:usual*
- *   - _cache_keys=_ sets the value of the _cache_keys_ flag.
- *   - _cache_keys_ returns the value of the _cache_keys_ flag.
- *   - _cache_strings=_ sets the value of the _cache_strings_ to a positive integer less than 35. Strings shorter than
- * that length are cached.
- *   - _cache_strings_ returns the value of the _cache_strings_ integer value.
- *   - _cache_expunge=_ sets the value of the _cache_expunge_ where 0 never expunges, 1 expunges slowly, 2 expunges
- * faster, and 3 or higher expunges agressively.
- *   - _cache_expunge_ returns the value of the _cache_expunge_ integer value.
- *   - _capacity=_ sets the capacity of the parser. The parser grows automatically but can be updated directly with this
- * call.
- *   - _capacity_ returns the current capacity of the parser's internal stack.
- *   - _create_id_ returns the value _create_id_ or _nil_ if there is no _create_id_.
- *   - _create_id=_ sets the value _create_id_ or if _nil_ unsets it. Parsed JSON objects that include the specified
- * element use the element value as the name of the class to create an object from instead of a Hash.
- *   - _decimal=_ sets the approach to how decimals are parser. If _:auto_ then the decimals with significant digits are
- * 16 or less are Floats and long ones are BigDecimal. _:ruby_ uses a call to Ruby to convert a string to a Float.
- * _:float_ always generates a Float. _:bigdecimal_ always results in a BigDecimal.
- *   - _decimal_ returns the value of the decimal conversion option which can be :auto (default), :ruby, :float, or
- * :bigdecimal.
- *   - _ignore_json_create_ returns the value of the _ignore_json_create_ flag.
- *   - _ignore_json_create=_ sets the value of the _ignore_json_create_ flag. When set the class json_create method is
- * ignored on parsing in favor of creating an instance and populating directly.
- *   - _missing_class_ return the value of the _missing_class_ indicator.
- *   - _missing_class=_ sets the value of the _missing_class_ flag. Valid values are _:auto_ which creates any missing
- * classes on parse, :ignore which ignores and continues as a Hash (default), and :raise which raises an exception if
- * the class is not found.
- *   - _omit_null=_ sets the _omit_null_ flag. If true then null values in a map or object are omitted from the
- * resulting Hash or Object.
- *   - _omit_null_ returns the value of the _omit_null_ flag.
- *   - _symbol_keys=_ sets the flag that indicates Hash keys should be parsed to Symbols versus Strings.
- *   - _symbol_keys_ returns the value of the _symbol_keys_ flag.
+ *   - _cache_keys_ is a flag indicating hash keys should be cached.
+ *   - _cache_strings_ is a positive integer less than 35. Strings shorter than that length are cached.
+ *   - _cache_expunge_ dictates when the cache will be expunged where 0 never expunges,
+ *     1 expunges slowly, 2 expunges faster, and 3 or higher expunges agressively.
+ *   - _capacity_ is the capacity of the parser's internal stack. The parser grows automatically
+ *     but can be updated directly with this call.
+ *   - _create_id_ if non-nil is the key that is used to specify the type of object to create
+ *     when parsing. Parsed JSON objects that include the specified element use the element
+ *     value as the name of the class to create an object from instead of a Hash.
+ *   - _decimal_ is the approach to how decimals are parsed. If _:auto_ then
+ *     the decimals with significant digits are 16 or less are Floats and long
+ *     ones are BigDecimal. _:ruby_ uses a call to Ruby to convert a string to a Float.
+ *     _:float_ always generates a Float. _:bigdecimal_ always results in a BigDecimal.
+ *   - _ignore_json_create_ is a flag that when set the class json_create method is
+ *     ignored on parsing in favor of creating an instance and populating directly.
+ *   - _missing_class_ is an indicator that determines how unknown class names are handled.
+ *     Valid values are _:auto_ which creates any missing classes on parse, :ignore which ignores
+ *     and continues as a Hash (default), and :raise which raises an exception if the class is not found.
+ *   - _omit_null_ is a flag that if true then null values in a map or object are omitted
+ *     from the resulting Hash or Object.
+ *   - _symbol_keys_ is a flag that indicates Hash keys should be parsed to Symbols versus Strings.
  */
 static VALUE parser_missing(int argc, VALUE *argv, VALUE self) {
-    ojParser       p    = (ojParser)DATA_PTR(self);
+    ojParser       p;
     const char    *key  = NULL;
     volatile VALUE rkey = *argv;
     volatile VALUE rv   = Qnil;
 
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
+
 #if HAVE_RB_EXT_RACTOR_SAFE
     // This doesn't seem to do anything.
     rb_ext_ractor_safe(true);
@@ -1319,7 +1348,7 @@ static VALUE parser_missing(int argc, VALUE *argv, VALUE self) {
     case RUBY_T_SYMBOL:
         rkey = rb_sym2str(rkey);
         // fall through
-    case RUBY_T_STRING: key = rb_string_value_ptr(&rkey); break;
+    case RUBY_T_STRING: key = StringValuePtr(rkey); break;
     default: rb_raise(rb_eArgError, "option method must be a symbol or string");
     }
     if (1 < argc) {
@@ -1336,12 +1365,14 @@ static VALUE parser_missing(int argc, VALUE *argv, VALUE self) {
  * Returns the result according to the delegate of the parser.
  */
 static VALUE parser_parse(VALUE self, VALUE json) {
-    ojParser p = (ojParser)DATA_PTR(self);
+    ojParser    p;
+    const byte *ptr = (const byte *)StringValuePtr(json);
+
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
 
-    Check_Type(json, T_STRING);
     parser_reset(p);
     p->start(p);
-    parse(p, (const byte *)rb_string_value_ptr(&json));
+    parse(p, ptr);
 
     return p->result(p);
 }
@@ -1352,9 +1383,11 @@ static VALUE load_rescue(VALUE self, VALUE x) {
 }
 
 static VALUE load(VALUE self) {
-    ojParser       p    = (ojParser)DATA_PTR(self);
+    ojParser       p;
     volatile VALUE rbuf = rb_str_new2("");
 
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
+
     p->start(p);
     while (true) {
         rb_funcall(p->reader, oj_readpartial_id, 2, INT2NUM(16385), rbuf);
@@ -1373,7 +1406,9 @@ static VALUE load(VALUE self) {
  * Returns the result according to the delegate of the parser.
  */
 static VALUE parser_load(VALUE self, VALUE reader) {
-    ojParser p = (ojParser)DATA_PTR(self);
+    ojParser p;
+
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
 
     parser_reset(p);
     p->reader = reader;
@@ -1390,12 +1425,13 @@ static VALUE parser_load(VALUE self, VALUE reader) {
  * Returns the result according to the delegate of the parser.
  */
 static VALUE parser_file(VALUE self, VALUE filename) {
-    ojParser    p = (ojParser)DATA_PTR(self);
+    ojParser    p;
     const char *path;
     int         fd;
 
-    Check_Type(filename, T_STRING);
-    path = rb_string_value_ptr(&filename);
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
+
+    path = StringValuePtr(filename);
 
     parser_reset(p);
     p->start(p);
@@ -1438,7 +1474,9 @@ static VALUE parser_file(VALUE self, VALUE filename) {
  * Returns the current state of the just_one [_Boolean_] option.
  */
 static VALUE parser_just_one(VALUE self) {
-    ojParser p = (ojParser)DATA_PTR(self);
+    ojParser p;
+
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
 
     return p->just_one ? Qtrue : Qfalse;
 }
@@ -1452,7 +1490,9 @@ static VALUE parser_just_one(VALUE self) {
  * Returns the current state of the just_one [_Boolean_] option.
  */
 static VALUE parser_just_one_set(VALUE self, VALUE v) {
-    ojParser p = (ojParser)DATA_PTR(self);
+    ojParser p;
+
+    TypedData_Get_Struct(self, struct _ojParser, &oj_parser_type, p);
 
     p->just_one = (Qtrue == v);
 
@@ -1469,14 +1509,14 @@ static VALUE usual_parser = Qundef;
  */
 static VALUE parser_usual(VALUE self) {
     if (Qundef == usual_parser) {
-        ojParser p = ALLOC(struct _ojParser);
+        ojParser p = OJ_R_ALLOC(struct _ojParser);
 
         memset(p, 0, sizeof(struct _ojParser));
         buf_init(&p->key);
         buf_init(&p->buf);
         p->map = value_map;
         oj_set_parser_usual(p);
-        usual_parser = Data_Wrap_Struct(parser_class, parser_mark, parser_free, p);
+        usual_parser = TypedData_Wrap_Struct(parser_class, &oj_parser_type, p);
         rb_gc_register_address(&usual_parser);
     }
     return usual_parser;
@@ -1492,14 +1532,14 @@ static VALUE saj_parser = Qundef;
  */
 static VALUE parser_saj(VALUE self) {
     if (Qundef == saj_parser) {
-        ojParser p = ALLOC(struct _ojParser);
+        ojParser p = OJ_R_ALLOC(struct _ojParser);
 
         memset(p, 0, sizeof(struct _ojParser));
         buf_init(&p->key);
         buf_init(&p->buf);
         p->map = value_map;
         oj_set_parser_saj(p);
-        saj_parser = Data_Wrap_Struct(parser_class, parser_mark, parser_free, p);
+        saj_parser = TypedData_Wrap_Struct(parser_class, &oj_parser_type, p);
         rb_gc_register_address(&saj_parser);
     }
     return saj_parser;
@@ -1514,14 +1554,14 @@ static VALUE validate_parser = Qundef;
  */
 static VALUE parser_validate(VALUE self) {
     if (Qundef == validate_parser) {
-        ojParser p = ALLOC(struct _ojParser);
+        ojParser p = OJ_R_ALLOC(struct _ojParser);
 
         memset(p, 0, sizeof(struct _ojParser));
         buf_init(&p->key);
         buf_init(&p->buf);
         p->map = value_map;
         oj_set_parser_validator(p);
-        validate_parser = Data_Wrap_Struct(parser_class, parser_mark, parser_free, p);
+        validate_parser = TypedData_Wrap_Struct(parser_class, &oj_parser_type, p);
         rb_gc_register_address(&validate_parser);
     }
     return validate_parser;

data/ext/oj/parser.h

@@ -4,8 +4,8 @@
 #ifndef OJ_PARSER_H
 #define OJ_PARSER_H
 
-#include <stdbool.h>
 #include <ruby.h>
+#include <stdbool.h>
 
 #include "buf.h"
 
@@ -32,13 +32,13 @@ typedef struct _num {
     long double dub;
     int64_t     fixnum;  // holds all digits
     uint32_t    len;
-    int16_t     div;  // 10^div
+    int16_t     div;     // 10^div
     int16_t     exp;
-    uint8_t     shift;  // shift of fixnum to get decimal
+    uint8_t     shift;   // shift of fixnum to get decimal
     bool        neg;
     bool        exp_neg;
     // for numbers as strings, reuse buf
-} * Num;
+} *Num;
 
 struct _ojParser;
 
@@ -54,11 +54,11 @@ typedef struct _funcs {
     void (*close_array)(struct _ojParser *p);
     void (*open_object)(struct _ojParser *p);
     void (*close_object)(struct _ojParser *p);
-} * Funcs;
+} *Funcs;
 
 typedef struct _ojParser {
-    const char *  map;
-    const char *  next_map;
+    const char   *map;
+    const char   *next_map;
     int           depth;
     unsigned char stack[1024];
 
@@ -67,7 +67,7 @@ typedef struct _ojParser {
     struct _buf key;
     struct _buf buf;
 
-    struct _funcs funcs[3]; // indexed by XXX_FUN defines
+    struct _funcs funcs[3];  // indexed by XXX_FUN defines
 
     void (*start)(struct _ojParser *p);
     VALUE (*option)(struct _ojParser *p, const char *key, VALUE value);
@@ -86,6 +86,16 @@ typedef struct _ojParser {
     uint32_t ucode;
     ojType   type;  // valType
     bool     just_one;
-} * ojParser;
+} *ojParser;
+
+// Create a new parser without setting the delegate. The parser is
+// wrapped. The parser is (ojParser)DATA_PTR(value) where value is the return
+// from this function. A delegate must be added before the parser can be
+// used. Optionally oj_parser_set_options can be called if the options are not
+// set directly.
+extern VALUE oj_parser_new();
+
+// Set set the options from a hash (ropts).
+extern void oj_parser_set_option(ojParser p, VALUE ropts);
 
 #endif /* OJ_PARSER_H */