summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat (limited to '3rdParty/Expat/src/xmltok_impl.c')
-rw-r--r--3rdParty/Expat/src/xmltok_impl.c132
1 files changed, 58 insertions, 74 deletions
diff --git a/3rdParty/Expat/src/xmltok_impl.c b/3rdParty/Expat/src/xmltok_impl.c
index 5f779c0..4d9ae7d 100644
--- a/3rdParty/Expat/src/xmltok_impl.c
+++ b/3rdParty/Expat/src/xmltok_impl.c
@@ -1,8 +1,35 @@
1/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd 1/* This file is included!
2 See the file COPYING for copying permission. 2 __ __ _
3 ___\ \/ /_ __ __ _| |_
4 / _ \\ /| '_ \ / _` | __|
5 | __// \| |_) | (_| | |_
6 \___/_/\_\ .__/ \__,_|\__|
7 |_| XML parser
8
9 Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
10 Copyright (c) 2000-2017 Expat development team
11 Licensed under the MIT license:
12
13 Permission is hereby granted, free of charge, to any person obtaining
14 a copy of this software and associated documentation files (the
15 "Software"), to deal in the Software without restriction, including
16 without limitation the rights to use, copy, modify, merge, publish,
17 distribute, sublicense, and/or sell copies of the Software, and to permit
18 persons to whom the Software is furnished to do so, subject to the
19 following conditions:
20
21 The above copyright notice and this permission notice shall be included
22 in all copies or substantial portions of the Software.
23
24 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
25 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
27 NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
28 DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
29 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
30 USE OR OTHER DEALINGS IN THE SOFTWARE.
3*/ 31*/
4 32
5/* This file is included! */
6#ifdef XML_TOK_IMPL_C 33#ifdef XML_TOK_IMPL_C
7 34
8#ifndef IS_INVALID_CHAR 35#ifndef IS_INVALID_CHAR
@@ -47,6 +74,7 @@
47 *nextTokPtr = ptr; \ 74 *nextTokPtr = ptr; \
48 return XML_TOK_INVALID; \ 75 return XML_TOK_INVALID; \
49 } \ 76 } \
77 /* fall through */ \
50 case BT_NMSTRT: \ 78 case BT_NMSTRT: \
51 case BT_HEX: \ 79 case BT_HEX: \
52 case BT_DIGIT: \ 80 case BT_DIGIT: \
@@ -75,6 +103,7 @@
75 *nextTokPtr = ptr; \ 103 *nextTokPtr = ptr; \
76 return XML_TOK_INVALID; \ 104 return XML_TOK_INVALID; \
77 } \ 105 } \
106 /* fall through */ \
78 case BT_NMSTRT: \ 107 case BT_NMSTRT: \
79 case BT_HEX: \ 108 case BT_HEX: \
80 ptr += MINBPC(enc); \ 109 ptr += MINBPC(enc); \
@@ -575,7 +604,7 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end,
575 return XML_TOK_INVALID; 604 return XML_TOK_INVALID;
576 } 605 }
577 } 606 }
578 /* fall through */ 607 /* fall through */
579 case BT_EQUALS: 608 case BT_EQUALS:
580 { 609 {
581 int open; 610 int open;
@@ -1198,8 +1227,14 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr,
1198 const char *start; 1227 const char *start;
1199 if (ptr >= end) 1228 if (ptr >= end)
1200 return XML_TOK_NONE; 1229 return XML_TOK_NONE;
1201 else if (! HAS_CHAR(enc, ptr, end)) 1230 else if (! HAS_CHAR(enc, ptr, end)) {
1202 return XML_TOK_PARTIAL; 1231 /* This line cannot be executed. The incoming data has already
1232 * been tokenized once, so incomplete characters like this have
1233 * already been eliminated from the input. Retaining the paranoia
1234 * check is still valuable, however.
1235 */
1236 return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */
1237 }
1203 start = ptr; 1238 start = ptr;
1204 while (HAS_CHAR(enc, ptr, end)) { 1239 while (HAS_CHAR(enc, ptr, end)) {
1205 switch (BYTE_TYPE(enc, ptr)) { 1240 switch (BYTE_TYPE(enc, ptr)) {
@@ -1258,8 +1293,14 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr,
1258 const char *start; 1293 const char *start;
1259 if (ptr >= end) 1294 if (ptr >= end)
1260 return XML_TOK_NONE; 1295 return XML_TOK_NONE;
1261 else if (! HAS_CHAR(enc, ptr, end)) 1296 else if (! HAS_CHAR(enc, ptr, end)) {
1262 return XML_TOK_PARTIAL; 1297 /* This line cannot be executed. The incoming data has already
1298 * been tokenized once, so incomplete characters like this have
1299 * already been eliminated from the input. Retaining the paranoia
1300 * check is still valuable, however.
1301 */
1302 return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */
1303 }
1263 start = ptr; 1304 start = ptr;
1264 while (HAS_CHAR(enc, ptr, end)) { 1305 while (HAS_CHAR(enc, ptr, end)) {
1265 switch (BYTE_TYPE(enc, ptr)) { 1306 switch (BYTE_TYPE(enc, ptr)) {
@@ -1403,6 +1444,7 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end,
1403 case BT_NMSTRT: 1444 case BT_NMSTRT:
1404 if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f)) 1445 if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f))
1405 break; 1446 break;
1447 /* fall through */
1406 default: 1448 default:
1407 switch (BYTE_TO_ASCII(enc, ptr)) { 1449 switch (BYTE_TO_ASCII(enc, ptr)) {
1408 case 0x24: /* $ */ 1450 case 0x24: /* $ */
@@ -1615,76 +1657,18 @@ PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr,
1615} 1657}
1616 1658
1617static int PTRCALL 1659static int PTRCALL
1618PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2)
1619{
1620 for (;;) {
1621 switch (BYTE_TYPE(enc, ptr1)) {
1622#define LEAD_CASE(n) \
1623 case BT_LEAD ## n: \
1624 if (*ptr1++ != *ptr2++) \
1625 return 0;
1626 LEAD_CASE(4) LEAD_CASE(3) LEAD_CASE(2)
1627#undef LEAD_CASE
1628 /* fall through */
1629 if (*ptr1++ != *ptr2++)
1630 return 0;
1631 break;
1632 case BT_NONASCII:
1633 case BT_NMSTRT:
1634#ifdef XML_NS
1635 case BT_COLON:
1636#endif
1637 case BT_HEX:
1638 case BT_DIGIT:
1639 case BT_NAME:
1640 case BT_MINUS:
1641 if (*ptr2++ != *ptr1++)
1642 return 0;
1643 if (MINBPC(enc) > 1) {
1644 if (*ptr2++ != *ptr1++)
1645 return 0;
1646 if (MINBPC(enc) > 2) {
1647 if (*ptr2++ != *ptr1++)
1648 return 0;
1649 if (MINBPC(enc) > 3) {
1650 if (*ptr2++ != *ptr1++)
1651 return 0;
1652 }
1653 }
1654 }
1655 break;
1656 default:
1657 if (MINBPC(enc) == 1 && *ptr1 == *ptr2)
1658 return 1;
1659 switch (BYTE_TYPE(enc, ptr2)) {
1660 case BT_LEAD2:
1661 case BT_LEAD3:
1662 case BT_LEAD4:
1663 case BT_NONASCII:
1664 case BT_NMSTRT:
1665#ifdef XML_NS
1666 case BT_COLON:
1667#endif
1668 case BT_HEX:
1669 case BT_DIGIT:
1670 case BT_NAME:
1671 case BT_MINUS:
1672 return 0;
1673 default:
1674 return 1;
1675 }
1676 }
1677 }
1678 /* not reached */
1679}
1680
1681static int PTRCALL
1682PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1, 1660PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1,
1683 const char *end1, const char *ptr2) 1661 const char *end1, const char *ptr2)
1684{ 1662{
1685 for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { 1663 for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) {
1686 if (end1 - ptr1 < MINBPC(enc)) 1664 if (end1 - ptr1 < MINBPC(enc)) {
1687 return 0; 1665 /* This line cannot be executed. The incoming data has already
1666 * been tokenized once, so incomplete characters like this have
1667 * already been eliminated from the input. Retaining the
1668 * paranoia check is still valuable, however.
1669 */
1670 return 0; /* LCOV_EXCL_LINE */
1671 }
1688 if (!CHAR_MATCHES(enc, ptr1, *ptr2)) 1672 if (!CHAR_MATCHES(enc, ptr1, *ptr2))
1689 return 0; 1673 return 0;
1690 } 1674 }