data.cc 19.1 KB
Newer Older
1 2
// XXXMLG UTF-8 and binary are all encoded as UTF-8, and decoded as UTF-8.
// XXXMLG This will cause issues down the road, but for today it works.
3 4 5 6 7 8 9 10 11 12 13 14 15 16

#include "data.h"

#include <cstdio>
#include <iostream>
#include <sstream>

#include <boost/algorithm/string.hpp>

using namespace std;
using namespace ISC::Data;

const unsigned char PROTOCOL_VERSION[4] = { 0x53, 0x6b, 0x61, 0x6e };

17
const unsigned char ITEM_BLOB = 0x01;
18 19 20
const unsigned char ITEM_HASH = 0x02;
const unsigned char ITEM_LIST = 0x03;
const unsigned char ITEM_NULL = 0x04;
Jelte Jansen's avatar
Jelte Jansen committed
21
const unsigned char ITEM_BOOL = 0x05;
22
const unsigned char ITEM_INT  = 0x06;
23
const unsigned char ITEM_UTF8 = 0x08;
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328
const unsigned char ITEM_MASK = 0x0f;

const unsigned char ITEM_LENGTH_32   = 0x00;
const unsigned char ITEM_LENGTH_16   = 0x10;
const unsigned char ITEM_LENGTH_8    = 0x20;
const unsigned char ITEM_LENGTH_MASK = 0x30;

std::ostream& operator <<(std::ostream &out, const ISC::Data::ElementPtr& e) {
    return out << e->str();
}

//
// factory functions
//
ElementPtr
Element::create(const int i)
{
    try {
        return ElementPtr(new IntElement(i));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}

ElementPtr
Element::create(const double d)
{
    try {
        return ElementPtr(new DoubleElement(d));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}

ElementPtr
Element::create(const std::string& s)
{
    try {
        return ElementPtr(new StringElement(s));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}

ElementPtr
Element::create(const bool b)
{
    try {
        cout << "creating boolelement" << endl;
        return ElementPtr(new BoolElement(b));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}

ElementPtr
Element::create(const std::vector<ElementPtr>& v)
{
    try {
        return ElementPtr(new ListElement(v));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}

ElementPtr
Element::create(const std::map<std::string, ElementPtr>& m)
{
    try {
        return ElementPtr(new MapElement(m));
    } catch (std::bad_alloc) {
        return ElementPtr();
    }
}


//
// helper functions for create_from_string factory
// these should probably also be moved to member functions
//

static bool
char_in(char c, const char *chars)
{
    for (size_t i = 0; i < strlen(chars); i++) {
        if (chars[i] == c) {
            return true;
        }
    }
    return false;
}

static void
skip_chars(std::stringstream &in, const char *chars)
{
    char c = in.peek();
    while (char_in(c, chars) && c != EOF) {
        in.get();
        c = in.peek();
    }
}

// skip on the input stream to one of the characters in chars
// if another character is found this function returns false
// unles that character is specified in the optional may_skip
//
// the character found is left on the stream
static bool
skip_to(std::stringstream &in, const char *chars, const char *may_skip="")
{
    char c = in.get();
    while (c != EOF) {
        if (char_in(c, may_skip)) {
            c = in.get();
        } else if (char_in(c, chars)) {
            while(char_in(in.peek(), may_skip)) {
                in.get();
            }
            in.putback(c);
            return true;
        } else {
            // TODO: provide feeback mechanism?
            cout << "error, '" << c << "' read; one of \"" << chars << "\" expected" << endl;
            in.putback(c);
            return false;
        }
    }
    // TODO: provide feeback mechanism?
    cout << "error, EOF read; one of \"" << chars << "\" expected" << endl;
            in.putback(c);
    return false;
}

static std::string
str_from_stringstream(std::stringstream &in)
{
    char c = 0;
    std::stringstream ss;
    c = in.get();
    if (c == '"') {
        c = in.get();
    } else {
        return "badstring";
    }
    while (c != EOF && c != '"') {
        ss << c;
        if (c == '\\' && in.peek() == '"') {
            ss << in.get();
        }
        c = in.get();
    }
    return ss.str();
}

static std::string
word_from_stringstream(std::stringstream &in)
{
    std::stringstream ss;
    while (isalpha(in.peek())) {
        ss << (char) in.get();
    }
    return ss.str();
}


static ElementPtr
from_stringstream_int_or_double(std::stringstream &in)
{
    int i;
    in >> i;
    if (in.peek() == '.') {
        double d;
        in >> d;
        d += i;
        return Element::create(d);
    } else {
        return Element::create(i);
    }
}

static ElementPtr
from_stringstream_bool(std::stringstream &in)
{
    std::string word = word_from_stringstream(in);
    if (boost::iequals(word, "True")) {
        return Element::create(true);
    } else if (boost::iequals(word, "False")) {
        return Element::create(false);
    } else {
        return ElementPtr();
    }
}

static ElementPtr
from_stringstream_string(std::stringstream &in)
{
    return Element::create(str_from_stringstream(in));
}

static ElementPtr
from_stringstream_list(std::stringstream &in)
{
    char c = 0;
    std::vector<ElementPtr> v;
    ElementPtr cur_list_element;

    skip_chars(in, " \t\n");
    while (c != EOF && c != ']') {
        cur_list_element = Element::create_from_string(in);
        v.push_back(cur_list_element);
        if (!skip_to(in, ",]", " \t\n")) {
            return ElementPtr();
        }
        c = in.get();
    }
    return Element::create(v);
}

static ElementPtr
from_stringstream_map(std::stringstream &in)
{
    char c = 0;
    std::map<std::string, ElementPtr> m;
    std::pair<std::string, ElementPtr> p;
    std::string cur_map_key;
    ElementPtr cur_map_element;
    skip_chars(in, " \t\n");
    while (c != EOF && c != '}') {
        p.first = str_from_stringstream(in);
        if (!skip_to(in, ":", " \t\n")) {
            return ElementPtr();
        } else {
            // skip the :
            in.get();
        }
        p.second = Element::create_from_string(in);
        if (!p.second) { return ElementPtr(); };
        m.insert(p);
        skip_to(in, ",}", " \t\n");
        c = in.get();
    }
    return Element::create(m);
}

ElementPtr
Element::create_from_string(std::stringstream &in)
{
    char c = 0;
    ElementPtr element;
    bool el_read = false;
    skip_chars(in, " \n\t");
    while (c != EOF && !el_read) {
        c = in.get();
        switch(c) {
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
            case '0':
                in.putback(c);
                element = from_stringstream_int_or_double(in);
                el_read = true;
                break;
            case 't':
            case 'T':
            case 'f':
            case 'F':
                in.putback(c);
                element = from_stringstream_bool(in);
                el_read = true;
                break;
            case '"':
                in.putback('"');
                element = from_stringstream_string(in);
                el_read = true;
                break;
            case '[':
                element = from_stringstream_list(in);
                el_read = true;
                break;
            case '{':
                element = from_stringstream_map(in);
                el_read = true;
                break;
            default:
                // TODO this might not be a fatal error
                // provide feedback mechanism?
                cout << "error: unexpected '" << c << "'" << endl;
                return ElementPtr();
                break;
        }
    }
    if (el_read) {
        return element;
    } else {
        // throw exception?
        return ElementPtr();
    }
}

329 330 331 332 333 334 335
ElementPtr
Element::create_from_string(const std::string &in)
{
    std::stringstream ss;
    ss << in;
    return create_from_string(ss);
}
336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
//
// a general to_str() function
//
std::string
IntElement::str()
{
    std::stringstream ss;
    ss << int_value();
    return ss.str();
}

std::string
DoubleElement::str()
{
    std::stringstream ss;
    ss << double_value();
    return ss.str();
}

std::string
BoolElement::str()
{
    if (b) {
        return "True";
    } else {
        return "False";
    }
}

std::string
StringElement::str()
{
    std::stringstream ss;
    ss << "\"";
    ss << string_value();
    ss << "\"";
    return ss.str();
}

std::string
ListElement::str()
{
    std::stringstream ss;
    std::vector<ElementPtr> v;
    ss << "[ ";
    v = list_value();
    for (std::vector<ElementPtr>::iterator it = v.begin(); it != v.end(); ++it) {
        if (it != v.begin()) {
            ss << ", ";
        }
        ss << (*it)->str();
    }
    ss << " ]";
    return ss.str();
}

std::string
MapElement::str()
{
    std::stringstream ss;
    std::map<std::string, ElementPtr> m;
    ss << "{";
    m = map_value();
    for (std::map<std::string, ElementPtr>::iterator it = m.begin(); it != m.end(); ++it) {
        if (it != m.begin()) {
            ss << ", ";
        }
        ss << "\"" << (*it).first << "\": ";
        ss << (*it).second->str();
    }
    ss << "}";
    return ss.str();
}

//
// helpers for str_xml() functions
//

// prefix with 'prefix' number of spaces
static void
pre(std::ostream &out, size_t prefix)
{
    for (size_t i = 0; i < prefix; i++) {
        out << " ";
    }
}

std::string
IntElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    pre(ss, prefix);
    ss << str();
    return ss.str();
}

std::string
DoubleElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    pre(ss, prefix);
    ss << str();
    return ss.str();
}

std::string
BoolElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    pre(ss, prefix);
    ss << str();
    return ss.str();
}

std::string
StringElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    pre(ss, prefix);
    ss << string_value();
    return ss.str();
}

std::string
ListElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    std::vector<ElementPtr> v;
    pre(ss, prefix);
    ss << "<list>" << endl;;
    v = list_value();
    for (std::vector<ElementPtr>::iterator it = v.begin(); it != v.end(); ++it) {
        pre(ss, prefix + 4);
        ss << "<listitem>" << endl;
        ss << (*it)->str_xml(prefix + 8) << endl;
        pre(ss, prefix + 4);
        ss << "</listitem>" << endl;
    }
    pre(ss, prefix);
    ss << "</list>";
    return ss.str();
}

std::string
MapElement::str_xml(size_t prefix)
{
    std::stringstream ss;
    std::map<std::string, ElementPtr> m;
    m = map_value();
    pre(ss, prefix);
    ss << "<map>" << endl;
    for (std::map<std::string, ElementPtr>::iterator it = m.begin(); it != m.end(); ++it) {
        pre(ss, prefix + 4);
        ss << "<mapitem name=\"" << (*it).first << "\">" << endl;
        pre(ss, prefix);
        ss << (*it).second->str_xml(prefix+8) << endl;
        pre(ss, prefix + 4);
        ss << "</mapitem>" << endl;
    }
    pre(ss, prefix);
    ss << "</map>";
    return ss.str();
}

// currently throws when one of the types in the path (except the one
// we're looking for) is not a MapElement
// returns 0 if it could simply not be found
// should that also be an exception?
ElementPtr
MapElement::find(const std::string& id)
{
    if (get_type() != map) {
        throw TypeError();
    }
    size_t sep = id.find('/');
    if (sep == std::string::npos) {
        return get(id);
    } else {
        ElementPtr ce = get(id.substr(0, sep));
        if (ce) {
            return ce->find(id.substr(sep+1));
        } else {
            return ElementPtr();
        }
    }
}

//
// Decode from wire format.
//

ElementPtr decode_element(std::stringstream& in, int& in_length);

static unsigned char
get_byte(std::stringstream& in)
{
    int c = in.get();
    if (c == EOF) {
        throw DecodeError("End of data while decoding wire format message");
    }

    return c;
}

std::string
decode_tag(std::stringstream& in, int& item_length)
{
    char buf[256];

    int len = get_byte(in);
    item_length--;

    in.read(buf, len);
    if (in.fail()) {
        throw DecodeError();
    }
    buf[len] = 0;
    item_length -= len;

    return std::string(buf, len);
}

Jelte Jansen's avatar
Jelte Jansen committed
558 559 560 561 562 563 564 565 566 567 568 569
ElementPtr
decode_bool(std::stringstream& in, int& item_length)
{
    char c;
    c = in.get();
    if (c == 0x01) {
        return Element::create(true);
    } else {
        return Element::create(false);
    }
}

570 571 572 573 574 575
ElementPtr
decode_int(std::stringstream& in, int& item_length)
{
    return from_stringstream_int_or_double(in);
}

576
ElementPtr
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
decode_blob(std::stringstream& in, int& item_length)
{
    char *buf = new char[item_length + 1];

    in.read(buf, item_length);
    if (in.fail()) {
        throw DecodeError();
    }
    buf[item_length] = 0;

    std::string s = std::string(buf, item_length);
    item_length -= item_length;

    delete [] buf;
    return Element::create(s);
}

// XXXMLG currently identical to decode_blob
ElementPtr
decode_utf8(std::stringstream& in, int& item_length)
597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
{
    char *buf = new char[item_length + 1];

    in.read(buf, item_length);
    if (in.fail()) {
        throw DecodeError();
    }
    buf[item_length] = 0;

    std::string s = std::string(buf, item_length);
    item_length -= item_length;

    delete [] buf;
    return Element::create(s);
}

ElementPtr
decode_hash(std::stringstream& in, int& item_length)
{
    std::map<std::string, ElementPtr> m;
    std::pair<std::string, ElementPtr> p;

    while (item_length > 0) {
        p.first = decode_tag(in, item_length);
        p.second = decode_element(in, item_length);
        m.insert(p);
    }

    return Element::create(m);
}

ElementPtr
decode_list(std::stringstream& in, int& item_length)
{
    std::vector<ElementPtr> v;

    while (item_length > 0) {
        v.push_back(decode_element(in, item_length));
    }
    return Element::create(v);
}

ElementPtr
decode_null(std::stringstream& in, int& item_length)
{
    return Element::create("NULL");
}

ElementPtr
decode_element(std::stringstream& in, int& in_length)
{
    ElementPtr element;

    unsigned char type_and_length = get_byte(in);
    unsigned char type = type_and_length & ITEM_MASK;
    unsigned char lenbytes = type_and_length & ITEM_LENGTH_MASK;
    in_length--;

    int item_length = 0;
    switch (lenbytes) {
    case ITEM_LENGTH_32:
        item_length |= get_byte(in);
        item_length <<= 8;
        item_length |= get_byte(in);
        item_length <<= 8;
        in_length -= 2;  // only 2 here, we will get more later
    case ITEM_LENGTH_16:
        item_length |= get_byte(in);
        item_length <<= 8;
        in_length--;  // only 1 here
    case ITEM_LENGTH_8:
        item_length |= get_byte(in);
        in_length--;
    }

    in_length -= item_length;

    switch (type) {
Jelte Jansen's avatar
Jelte Jansen committed
675 676 677
    case ITEM_BOOL:
        element = decode_bool(in, item_length);
        break;
678 679 680
    case ITEM_INT:
        element = decode_int(in, item_length);
        break;
681 682 683 684 685
    case ITEM_BLOB:
        element = decode_blob(in, item_length);
        break;
    case ITEM_UTF8:
        element = decode_utf8(in, item_length);
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764
        break;
    case ITEM_HASH:
        element = decode_hash(in, item_length);
        break;
    case ITEM_LIST:
        element = decode_list(in, item_length);
        break;
    case ITEM_NULL:
        element = decode_null(in, item_length);
        break;
    }

    return (element);
}

ElementPtr
Element::from_wire(const std::string& s)
{
    std::stringstream ss;
    ss << s;
    return from_wire(ss, s.length());
}

ElementPtr
Element::from_wire(std::stringstream& in, int length)
{
    //
    // Check protocol version
    //
    for (int i = 0 ; i < 4 ; i++) {
        unsigned char version_byte = get_byte(in);
        if (PROTOCOL_VERSION[i] != version_byte) {
            throw DecodeError("Protocol version incorrect");
        }
    }
    length -= 4;

    ElementPtr element;
    element = decode_hash(in, length);
    return (element);
}

//
// Encode into wire format.
//

std::string
encode_length(unsigned int length, unsigned char type)
{
    std::stringstream ss;

    if (length <= 0x000000ff) {
        unsigned char val = (length & 0x000000ff);
        type |= ITEM_LENGTH_8;
        ss << type << val;
    } else if (length <= 0x0000ffff) {
        unsigned char val[2];
        val[0] = (length & 0x0000ff00) >> 8;
        val[1] = (length & 0x000000ff);
        type |= ITEM_LENGTH_16;
        ss << type << val;
    } else {
        unsigned char val[4];
        val[0] = (length & 0xff000000) >> 24;
        val[1] = (length & 0x00ff0000) >> 16;
        val[2] = (length & 0x0000ff00) >> 8;
        val[3] = (length & 0x000000ff);
        type |= ITEM_LENGTH_32;
        ss << type << val;
    }
    return ss.str();
}

std::string
StringElement::to_wire(int omit_length)
{
    std::stringstream ss;

    int length = string_value().length();
765
    ss << encode_length(length, ITEM_UTF8) << string_value();
766 767 768 769 770 771 772 773 774 775 776 777

    return ss.str();
}

std::string
IntElement::to_wire(int omit_length)
{
    std::stringstream ss;
    std::stringstream text;

    text << str();
    int length = text.str().length();
778
    ss << encode_length(length, ITEM_INT) << text.str();
779 780 781 782 783 784 785 786 787 788 789

    return ss.str();
}

std::string
BoolElement::to_wire(int omit_length)
{
    std::stringstream ss;
    std::stringstream text;

    text << str();
Jelte Jansen's avatar
Jelte Jansen committed
790 791 792 793 794 795 796
    int length = 1;
    ss << encode_length(length, ITEM_BOOL);
    if (bool_value()) {
        ss << 0x01;
    } else {
        ss << 0x00;
    }
797 798 799 800 801 802 803 804 805 806 807 808

    return ss.str();
}

std::string
DoubleElement::to_wire(int omit_length)
{
    std::stringstream ss;
    std::stringstream text;

    text << str();
    int length = text.str().length();
809
    ss << encode_length(length, ITEM_UTF8) << text.str();
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894

    return ss.str();
}

std::string
ListElement::to_wire(int omit_length)
{
    std::stringstream ss;
    std::vector<ElementPtr> v;
    v = list_value();
    for (std::vector<ElementPtr>::iterator it = v.begin() ;
         it != v.end() ; ++it) {
        ss << (*it)->to_wire(0);
    }

    if (omit_length) {
        return ss.str();
    } else {
        std::stringstream ss_len;
        ss_len << encode_length(ss.str().length(), ITEM_LIST);
        ss_len << ss.str();
        return ss_len.str();
    }
}

std::string
encode_tag(const std::string &s)
{
    std::stringstream ss;
    int length = s.length();
    unsigned char val = length & 0x000000ff;

    ss << val << s;

    return ss.str();
}

std::string
MapElement::to_wire(int omit_length)
{
    std::stringstream ss;
    std::map<std::string, ElementPtr> m;

    //
    // If we don't want the length, we will want the protocol header
    //
    if (omit_length) {
        ss << PROTOCOL_VERSION[0] << PROTOCOL_VERSION[1];
        ss << PROTOCOL_VERSION[2] << PROTOCOL_VERSION[3];
    }

    m = map_value();
    for (std::map<std::string, ElementPtr>::iterator it = m.begin() ;
         it != m.end() ; ++it) {
        ss << encode_tag((*it).first);
        ss << (*it).second->to_wire(0);
    }

    //
    // add length if needed
    //
    if (omit_length) {
        return ss.str();
    } else {
        std::stringstream ss_len;
        ss_len << encode_length(ss.str().length(), ITEM_HASH);
        ss_len << ss.str();
        return ss_len.str();
    }
}

bool
MapElement::find(const std::string& id, ElementPtr& t) {
    ElementPtr p;
    try {
        p = find(id);
        if (p) {
            t = p;
            return true;
        }
    } catch (TypeError e) {
        // ignore
    }
    return false;
}