Class: Oj::Doc

Inherits:
Object
  • Object
show all
Defined in:
ext/oj/fast.c,
ext/oj/fast.c

Overview

The Doc class is used to parse and navigate a JSON document. The model it employs is that of a document that while open can be navigated and values extracted. Once the document is closed the document can not longer be accessed. This allows the parsing and data extraction to be extremely fast compared to other JSON parses.

An Oj::Doc class is not created directly but the open() class method is used to open a document and the yield parameter to the block of the #open() call is the Doc instance. The Doc instance can be moved across, up, and down the JSON document. At each element the data associated with the element can be extracted. It is also possible to just provide a path to the data to be extracted and retrieve the data in that manner.

For many of the methods a path is used to describe the location of an element. Paths follow a subset of the XPath syntax. The slash ('/') character is the separator. Each step in the path identifies the next branch to take through the document. A JSON object will expect a key string while an array will expect a positive index. A .. step indicates a move up the JSON document.

element of the array. doc.fetch() end #=> 2

# Now try again using a path to Oj::Doc.fetch() directly and not using a

block. doc = Oj::Doc.open(json) doc.fetch('/2/three') #=> 3 doc.close()

Examples:

json = %{[
  {
    "one"   : 1,
    "two"   : 2
  },
  {
    "three" : 3,
    "four"  : 4
  }
]}
# move and get value
Oj::Doc.open(json) do |doc|
  doc.move('/1/two')
  # doc location is now at the 'two' element of the hash that is the first

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.open(json) ⇒ Object

Parses a JSON document String and then yields to the provided block if one is given with an instance of the Oj::Doc as the single yield parameter. If a block is not given then an Oj::Doc instance is returned and must be closed with a call to the #close() method when no longer needed.

@param [String] json JSON document string

method call

Examples:

Oj::Doc.open('[1,2,3]') { |doc| doc.size() }  #=> 4
# or as an alternative
doc = Oj::Doc.open('[1,2,3]')
doc.size()  #=> 4
doc.close()

Yield Parameters:

  • doc (Oj::Doc) —

    parsed JSON document

Yield Returns:

  • (Object) —

    returns the result of the yield as the result of the



1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
 
# File 'ext/oj/fast.c', line 1139

static VALUE doc_open(VALUE clas, VALUE str) {
    char          *json;
    size_t         len;
    volatile VALUE obj;
    int            given = rb_block_given_p();

    Check_Type(str, T_STRING);
    len  = RSTRING_LEN(str) + 1;
    json = OJ_R_ALLOC_N(char, len);

    memcpy(json, StringValuePtr(str), len);
    obj = parse_json(clas, json, given);
    // json is owned by the doc and freed by doc_free(); do not free it here.
    return obj;
}

.open_file(filename) ⇒ Object

Parses a JSON document from a file and then yields to the provided block if one is given with an instance of the Oj::Doc as the single yield parameter. If a block is not given then an Oj::Doc instance is returned and must be closed with a call to the #close() method when no longer needed.

@param [String] filename name of file that contains a JSON document

method call

Examples:

File.open('array.json', 'w') { |f| f.write('[1,2,3]') }
Oj::Doc.open_file(filename) { |doc| doc.size() }  #=> 4
# or as an alternative
doc = Oj::Doc.open_file(filename)
doc.size()  #=> 4
doc.close()

Yield Parameters:

  • doc (Oj::Doc) —

    parsed JSON document

Yield Returns:

  • (Object) —

    returns the result of the yield as the result of the



1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
 
# File 'ext/oj/fast.c', line 1174

static VALUE doc_open_file(VALUE clas, VALUE filename) {
    char          *path;
    char          *json;
    FILE          *f;
    size_t         len;
    volatile VALUE obj;
    int            given = rb_block_given_p();

    path = StringValuePtr(filename);
    // Open in binary mode. On Windows a text mode read translates CRLF into LF
    // so fewer bytes are read than the file size reported by ftell().
    if (0 == (f = fopen(path, "rb"))) {
        rb_raise(rb_eIOError, "%s", strerror(errno));
    }
    fseek(f, 0, SEEK_END);
    len  = ftell(f);
    json = OJ_R_ALLOC_N(char, len + 1);

    fseek(f, 0, SEEK_SET);
    if (len != fread(json, 1, len, f)) {
        fclose(f);
        rb_raise(rb_const_get_at(Oj, rb_intern("LoadError")),
                 "Failed to read %lu bytes from %s.",
                 (unsigned long)len,
                 path);
    }
    fclose(f);
    json[len] = '\0';
    obj       = parse_json(clas, json, given);
    // json is owned by the doc and freed by doc_free(); do not free it here.
    return obj;
}

.open(json) ⇒ Object

Parses a JSON document String and then yields to the provided block if one is given with an instance of the Oj::Doc as the single yield parameter. If a block is not given then an Oj::Doc instance is returned and must be closed with a call to the #close() method when no longer needed.

@param [String] json JSON document string

method call

Examples:

Oj::Doc.open('[1,2,3]') { |doc| doc.size() }  #=> 4
# or as an alternative
doc = Oj::Doc.open('[1,2,3]')
doc.size()  #=> 4
doc.close()

Yield Parameters:

  • doc (Oj::Doc) —

    parsed JSON document

Yield Returns:

  • (Object) —

    returns the result of the yield as the result of the



1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
 
# File 'ext/oj/fast.c', line 1139

static VALUE doc_open(VALUE clas, VALUE str) {
    char          *json;
    size_t         len;
    volatile VALUE obj;
    int            given = rb_block_given_p();

    Check_Type(str, T_STRING);
    len  = RSTRING_LEN(str) + 1;
    json = OJ_R_ALLOC_N(char, len);

    memcpy(json, StringValuePtr(str), len);
    obj = parse_json(clas, json, given);
    // json is owned by the doc and freed by doc_free(); do not free it here.
    return obj;
}

Instance Method Details

#clone ⇒ Object 



1700
1701
1702
1703
 
# File 'ext/oj/fast.c', line 1700

static VALUE doc_not_implemented(VALUE self) {
    rb_raise(rb_eNotImpError, "Not implemented.");
    return Qnil;
}

#close ⇒ Object

Closes an open document. No further calls to the document will be valid after closing.

Examples:

doc = Oj::Doc.open('[1,2,3]')
doc.size()  #=> 4
doc.close()


1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
 
# File 'ext/oj/fast.c', line 1685

static VALUE doc_close(VALUE self) {
    Doc doc = self_doc(self);

    rb_gc_unregister_address(&doc->self);
    DATA_PTR(doc->self) = NULL;
    if (0 != doc) {
        doc_free(doc);
    }
    return Qnil;
}

#dump(path, filename) ⇒ Object

Dumps the document or nodes to a new JSON document. It uses the default options for generating the JSON. @param path [String] if provided it identified the top of the branch to dump to JSON @param filename [String] if provided it is the filename to write the output to

Examples:

Oj::Doc.open('[3,[2,1]]') { |doc|
    doc.dump('/2')
}
#=> "[2,1]"


1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
 
# File 'ext/oj/fast.c', line 1626

static VALUE doc_dump(int argc, VALUE *argv, VALUE self) {
    Doc         doc = self_doc(self);
    Leaf        leaf;
    const char *path     = 0;
    const char *filename = 0;

    if (1 <= argc) {
        if (Qnil != *argv) {
            path = StringValuePtr(*argv);
        }
        if (2 <= argc) {
            filename = StringValuePtr(argv[1]);
        }
    }
    if (0 != (leaf = get_doc_leaf(doc, path))) {
        volatile VALUE rjson;

        if (0 == filename) {
            struct _out out;

            oj_out_init(&out);

            out.omit_nil = oj_default_options.dump_opts.omit_nil;
            oj_dump_leaf_to_json(leaf, &oj_default_options, &out);
            rjson = rb_str_new2(out.buf);

            oj_out_free(&out);
        } else {
            oj_write_leaf_to_file(leaf, filename, &oj_default_options);
            rjson = Qnil;
        }
        return rjson;
    }
    return Qnil;
}

#dup ⇒ Object 



1700
1701
1702
1703
 
# File 'ext/oj/fast.c', line 1700

static VALUE doc_not_implemented(VALUE self) {
    rb_raise(rb_eNotImpError, "Not implemented.");
    return Qnil;
}

#each_child(path = nil) ⇒ Object

Yields to the provided block for each immediate child node with the identified location of the JSON document as the root. The parameter passed to the block on yield is the Doc instance after moving to the child location. @param [String] path if provided it identified the top of the branch to process the children of

Examples:

Oj::Doc.open('[3,[2,1]]') { |doc|
    result = []
    doc.each_value('/2') { |doc| result << doc.where? }
    result
}
#=> ["/2/1", "/2/2"]

Yield Parameters:

  • Doc (Doc) —

    at the child location



1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
 
# File 'ext/oj/fast.c', line 1517

static VALUE doc_each_child(int argc, VALUE *argv, VALUE self) {
    if (rb_block_given_p()) {
        Leaf        save_path[MAX_STACK];
        Doc         doc  = self_doc(self);
        const char *path = 0;
        size_t      wlen;
        Leaf       *where_orig = doc->where;

        wlen = doc->where - doc->where_path;
        if (0 < wlen) {
            memcpy(save_path, doc->where_path, sizeof(Leaf) * (wlen + 1));
        }
        if (1 <= argc) {
            path = StringValuePtr(*argv);
            if ('/' == *path) {
                doc->where = doc->where_path;
                path++;
            }
            if (0 != move_step(doc, path, 1)) {
                if (0 < wlen) {
                    memcpy(doc->where_path, save_path, sizeof(Leaf) * (wlen + 1));
                }
                doc->where = where_orig;
                return Qnil;
            }
        }
        if (NULL == doc->where || NULL == *doc->where) {
            return Qnil;
        }
        if (COL_VAL == (*doc->where)->value_type && 0 != (*doc->where)->elements) {
            Leaf first = (*doc->where)->elements->next;
            Leaf e     = first;

            if (MAX_STACK <= (doc->where + 1) - doc->where_path) {
                rb_raise(rb_const_get_at(Oj, rb_intern("DepthError")), "Path too deep. Limit is %d levels.", MAX_STACK);
            }
            doc->where++;
            do {
                *doc->where = e;
                rb_yield(self);
                if (NULL == DATA_PTR(self)) {
                    rb_raise(rb_eIOError, "Document closed.");
                }
                e = e->next;
            } while (e != first);
            doc->where--;
        }
        if (0 < wlen) {
            memcpy(doc->where_path, save_path, sizeof(Leaf) * (wlen + 1));
        }
        doc->where = where_orig;
    }
    return Qnil;
}

#each_leaf(path = nil) ⇒ Object

Yields to the provided block for each leaf node with the identified location of the JSON document as the root. The parameter passed to the block on yield is the Doc instance after moving to the child location. @param [String] path if provided it identified the top of the branch to process the leaves of

Examples:

Oj::Doc.open('[3,[2,1]]') { |doc|
    result = {}
    doc.each_leaf() { |d| result[d.where?] = d.fetch() }
    result
}
#=> ["/1" => 3, "/2/1" => 2, "/2/2" => 1]

Yield Parameters:

  • Doc (Doc) —

    at the child location



1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
 
# File 'ext/oj/fast.c', line 1440

static VALUE doc_each_leaf(int argc, VALUE *argv, VALUE self) {
    if (rb_block_given_p()) {
        Leaf        save_path[MAX_STACK];
        Doc         doc  = self_doc(self);
        const char *path = 0;
        size_t      wlen;

        wlen = doc->where - doc->where_path;
        if (0 < wlen) {
            memcpy(save_path, doc->where_path, sizeof(Leaf) * (wlen + 1));
        }
        if (1 <= argc) {
            path = StringValuePtr(*argv);
            if ('/' == *path) {
                doc->where = doc->where_path;
                path++;
            }
            if (0 != move_step(doc, path, 1)) {
                if (0 < wlen) {
                    memcpy(doc->where_path, save_path, sizeof(Leaf) * (wlen + 1));
                }
                return Qnil;
            }
        }
        if (NULL == doc->where || NULL == *doc->where) {
            return Qnil;
        }
        each_leaf(doc, self);
        if (0 < wlen) {
            memcpy(doc->where_path, save_path, sizeof(Leaf) * (wlen + 1));
        }
    }
    return Qnil;
}

#each_value(path = nil) ⇒ Object

Yields to the provided block for each leaf value in the identified location of the JSON document. The parameter passed to the block on yield is the value of the leaf. Only those leaves below the element specified by the path parameter are processed. @param [String] path if provided it identified the top of the branch to process the leaf values of

Examples:

Oj::Doc.open('[3,[2,1]]') { |doc|
    result = []
    doc.each_value() { |v| result << v }
    result
}
#=> [3, 2, 1]

Oj::Doc.open('[3,[2,1]]') { |doc|
    result = []
    doc.each_value('/2') { |v| result << v }
    result
}
#=> [2, 1]

Yield Parameters:

  • val (Object) —

    each leaf value



1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
 
# File 'ext/oj/fast.c', line 1596

static VALUE doc_each_value(int argc, VALUE *argv, VALUE self) {
    if (rb_block_given_p()) {
        Doc         doc  = self_doc(self);
        const char *path = 0;
        Leaf        leaf;

        if (1 <= argc) {
            path = StringValuePtr(*argv);
        }
        if (0 != (leaf = get_doc_leaf(doc, path))) {
            each_value(doc, leaf, self);
        }
    }
    return Qnil;
}

#exists?(path) ⇒ Boolean

Returns true if the value at the location identified by the path exists. @param [String] path path to the location

Examples:

Oj::Doc.open('[1,2]') { |doc| doc.exists?('/1') }  #=> true
Oj::Doc.open('[1,2]') { |doc| doc.exists?('/3') }  #=> false

Returns:

  • (Boolean) 


1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
 
# File 'ext/oj/fast.c', line 1411

static VALUE doc_exists(VALUE self, VALUE str) {
    Doc  doc;
    Leaf leaf;

    doc = self_doc(self);
    if (0 != (leaf = get_doc_leaf(doc, StringValuePtr(str)))) {
        if (NULL != leaf) {
            return Qtrue;
        }
    }
    return Qfalse;
}

#fetch(path = nil, default = nil) ⇒ Object

Hash

Returns the value at the location identified by the path or the current location if the path is nil or not provided. This method will create and return an Array or Hash if that is the type of Object at the location specified. This is more expensive than navigating to the leaves of the JSON document. If a default is provided that is used if no value if found. @param [String] path path to the location to get the type of if provided

Examples:

Oj::Doc.open('[1,2]') { |doc| doc.fetch() }      #=> [1, 2]
Oj::Doc.open('[1,2]') { |doc| doc.fetch('/1') }  #=> 1


1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
 
# File 'ext/oj/fast.c', line 1384

static VALUE doc_fetch(int argc, VALUE *argv, VALUE self) {
    Doc            doc;
    Leaf           leaf;
    volatile VALUE val  = Qnil;
    const char    *path = 0;

    doc = self_doc(self);
    if (1 <= argc) {
        path = StringValuePtr(*argv);
        if (2 == argc) {
            val = argv[1];
        }
    }
    if (0 != (leaf = get_doc_leaf(doc, path))) {
        val = leaf_value(doc, leaf);
    }
    return val;
}

#home ⇒ Object

Moves the document marker or location to the hoot or home position. The same operation can be performed with a Oj::Doc.move('/'). #=> '/'

Examples:

Oj::Doc.open('[1,2,3]') { |doc| doc.move('/2'); doc.home(); doc.where? }


1326
1327
1328
1329
1330
1331
1332
1333
 
# File 'ext/oj/fast.c', line 1326

static VALUE doc_home(VALUE self) {
    Doc doc = self_doc(self);

    *doc->where_path = doc->data;
    doc->where       = doc->where_path;

    return oj_slash_string;
}

#local_key ⇒ Object

Returns the final key to the current location. "one" Oj::Doc.open('[1,2,3]') { |doc| doc.local_key() } #=> nil

Examples:

Oj::Doc.open('[1,2,3]') { |doc| doc.move('/2'); doc.local_key() } #=> 2
Oj::Doc.open('{"one":3}') { |doc| doc.move('/one'); doc.local_key() }  #=>


1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
 
# File 'ext/oj/fast.c', line 1301

static VALUE doc_local_key(VALUE self) {
    Doc            doc = self_doc(self);
    Leaf           leaf;
    volatile VALUE key = Qnil;

    if (NULL == doc->where || NULL == *doc->where) {
        return Qnil;
    }
    leaf = *doc->where;
    if (T_HASH == leaf->parent_type) {
        key = rb_utf8_str_new_cstr(leaf->key);
    } else if (T_ARRAY == leaf->parent_type) {
        key = LONG2NUM(leaf->index);
    }
    return key;
}

#move(path) ⇒ Object

Moves the document marker to the path specified. The path can an absolute path or a relative path. @param [String] path path to the location to move to "/one/2"

Examples:

Oj::Doc.open('{"one":[1,2]') { |doc| doc.move('/one/2'); doc.where? }  #=>


1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
 
# File 'ext/oj/fast.c', line 1484

static VALUE doc_move(VALUE self, VALUE str) {
    Doc         doc = self_doc(self);
    const char *path;
    int         loc;

    path = StringValuePtr(str);
    if ('/' == *path) {
        doc->where = doc->where_path;
        path++;
    }
    if (0 != (loc = move_step(doc, path, 1))) {
        rb_raise(rb_eArgError, "Failed to locate element %d of the path %s.", loc, path);
    }
    return Qnil;
}

#path ⇒ Object

Returns a String that describes the absolute path to the current location in the JSON document.



1288
1289
1290
 
# File 'ext/oj/fast.c', line 1288

static VALUE doc_path(VALUE self) {
    return doc_where(self);
}

#size ⇒ Object

Returns the number of nodes in the JSON document where a node is any one of the basic JSON components.

Examples:

Oj::Doc.open('[1,2,3]') { |doc| doc.size() }  #=> 4

Returns:

  • Returns the size of the JSON document.



1670
1671
1672
1673
1674
 
# File 'ext/oj/fast.c', line 1670

static VALUE doc_size(VALUE self) {
    Doc d;
    TypedData_Get_Struct(self, struct _doc, &oj_doc_type, d);
    return ULONG2NUM(d->size);
}

#type(path = nil) ⇒ Object

Returns the Class of the data value at the location identified by the path or the current location if the path is nil or not provided. This method does not create the Ruby Object at the location specified so the overhead is low. @param [String] path path to the location to get the type of if provided

Examples:

Oj::Doc.open('[1,2]') { |doc| doc.type() }	     #=> Array
Oj::Doc.open('[1,2]') { |doc| doc.type('/1') }  #=> Fixnum


1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
 
# File 'ext/oj/fast.c', line 1346

static VALUE doc_type(int argc, VALUE *argv, VALUE self) {
    Doc         doc = self_doc(self);
    Leaf        leaf;
    const char *path = 0;
    VALUE       type = Qnil;

    if (1 <= argc) {
        path = StringValuePtr(*argv);
    }
    if (0 != (leaf = get_doc_leaf(doc, path))) {
        switch (leaf->rtype) {
        case T_NIL: type = rb_cNilClass; break;
        case T_TRUE: type = rb_cTrueClass; break;
        case T_FALSE: type = rb_cFalseClass; break;
        case T_STRING: type = rb_cString; break;
        case T_FIXNUM: type = rb_cInteger; break;
        case T_FLOAT: type = rb_cFloat; break;
        case T_ARRAY: type = rb_cArray; break;
        case T_HASH: type = rb_cHash; break;
        default: break;
        }
    }
    return type;
}

#where ⇒ Object

Returns a String that describes the absolute path to the current location in the JSON document.



1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
 
# File 'ext/oj/fast.c', line 1237

static VALUE doc_where(VALUE self) {
    Doc doc = self_doc(self);

    if (0 == *doc->where_path || doc->where == doc->where_path) {
        return oj_slash_string;
    } else {
        Leaf  *lp;
        Leaf   leaf;
        size_t size = 3;  // leading / and terminating \0
        char  *path;
        char  *p;

        for (lp = doc->where_path; lp <= doc->where; lp++) {
            leaf = *lp;
            if (T_HASH == leaf->parent_type) {
                size += esc_strlen((*lp)->key) + 1;
            } else if (T_ARRAY == leaf->parent_type) {
                size += ((*lp)->index < 100) ? 3 : 11;
            }
        }
        path = ALLOCA_N(char, size);
        p    = path;
        for (lp = doc->where_path; lp <= doc->where; lp++) {
            leaf = *lp;
            if (T_HASH == leaf->parent_type) {
                p = append_key(p, (*lp)->key);
            } else if (T_ARRAY == leaf->parent_type) {
                p = ulong_fill(p, (*lp)->index);
            }
            *p++ = '/';
        }
        *--p = '\0';

        return rb_str_new(path, p - path);
    }
}

#where? ⇒ Boolean

Deprecated.

Returns a String that describes the absolute path to the current location in the JSON document.

Returns:

  • (Boolean) 


1279
1280
1281
 
# File 'ext/oj/fast.c', line 1279

static VALUE doc_where_q(VALUE self) {
    return doc_where(self);
}