1// Copyright (C) 2016 The Qt Company Ltd.
2// SPDX-License-Identifier: LicenseRef-Qt-Commercial OR LGPL-3.0-only OR GPL-2.0-only OR GPL-3.0-only
3// Qt-Security score:critical reason:data-parser
4
5#include <qstring.h>
6
7#include "qxmlutils_p.h"
8
9#include <private/qtools_p.h>
10
11QT_BEGIN_NAMESPACE
12
13using namespace QtMiscUtils;
14
15/* TODO:
16 * - isNameChar() doesn't have to be public, it's only needed in
17 * qdom.cpp -- refactor fixedXmlName() to use isNCName()
18 * - A lot of functions can be inlined.
19 */
20
21class QXmlCharRange
22{
23public:
24 ushort min;
25 ushort max;
26};
27typedef const QXmlCharRange *RangeIter;
28
29/*!
30 Performs a binary search between \a begin and \a end inclusive, to check whether \a
31 c is contained. Remember that the QXmlCharRange instances must be in numeric order.
32 */
33bool QXmlUtils::rangeContains(RangeIter begin, RangeIter end, const QChar c)
34{
35 const ushort cp(c.unicode());
36
37 // check the first two ranges "manually" as characters in that
38 // range are checked very often and we avoid the binary search below.
39
40 if (cp <= begin->max)
41 return cp >= begin->min;
42
43 ++begin;
44
45 if (begin == end)
46 return false;
47
48 if (cp <= begin->max)
49 return cp >= begin->min;
50
51 while (begin != end) {
52 qptrdiff delta = (end - begin) / 2;
53 RangeIter mid = begin + delta;
54
55 if (mid->min > cp)
56 end = mid;
57 else if (mid->max < cp)
58 begin = mid;
59 else
60 return true;
61
62 if (delta == 0)
63 break;
64 }
65
66 return false;
67}
68
69// [85] BaseChar ::= ...
70
71static const QXmlCharRange g_base_begin[] =
72{
73 {.min: 0x0041, .max: 0x005A}, {.min: 0x0061, .max: 0x007A}, {.min: 0x00C0, .max: 0x00D6}, {.min: 0x00D8, .max: 0x00F6}, {.min: 0x00F8, .max: 0x00FF},
74 {.min: 0x0100, .max: 0x0131}, {.min: 0x0134, .max: 0x013E}, {.min: 0x0141, .max: 0x0148}, {.min: 0x014A, .max: 0x017E}, {.min: 0x0180, .max: 0x01C3},
75 {.min: 0x01CD, .max: 0x01F0}, {.min: 0x01F4, .max: 0x01F5}, {.min: 0x01FA, .max: 0x0217}, {.min: 0x0250, .max: 0x02A8}, {.min: 0x02BB, .max: 0x02C1},
76 {.min: 0x0386, .max: 0x0386}, {.min: 0x0388, .max: 0x038A}, {.min: 0x038C, .max: 0x038C}, {.min: 0x038E, .max: 0x03A1}, {.min: 0x03A3, .max: 0x03CE},
77 {.min: 0x03D0, .max: 0x03D6}, {.min: 0x03DA, .max: 0x03DA}, {.min: 0x03DC, .max: 0x03DC}, {.min: 0x03DE, .max: 0x03DE}, {.min: 0x03E0, .max: 0x03E0},
78 {.min: 0x03E2, .max: 0x03F3}, {.min: 0x0401, .max: 0x040C}, {.min: 0x040E, .max: 0x044F}, {.min: 0x0451, .max: 0x045C}, {.min: 0x045E, .max: 0x0481},
79 {.min: 0x0490, .max: 0x04C4}, {.min: 0x04C7, .max: 0x04C8}, {.min: 0x04CB, .max: 0x04CC}, {.min: 0x04D0, .max: 0x04EB}, {.min: 0x04EE, .max: 0x04F5},
80 {.min: 0x04F8, .max: 0x04F9}, {.min: 0x0531, .max: 0x0556}, {.min: 0x0559, .max: 0x0559}, {.min: 0x0561, .max: 0x0586}, {.min: 0x05D0, .max: 0x05EA},
81 {.min: 0x05F0, .max: 0x05F2}, {.min: 0x0621, .max: 0x063A}, {.min: 0x0641, .max: 0x064A}, {.min: 0x0671, .max: 0x06B7}, {.min: 0x06BA, .max: 0x06BE},
82 {.min: 0x06C0, .max: 0x06CE}, {.min: 0x06D0, .max: 0x06D3}, {.min: 0x06D5, .max: 0x06D5}, {.min: 0x06E5, .max: 0x06E6}, {.min: 0x0905, .max: 0x0939},
83 {.min: 0x093D, .max: 0x093D}, {.min: 0x0958, .max: 0x0961}, {.min: 0x0985, .max: 0x098C}, {.min: 0x098F, .max: 0x0990}, {.min: 0x0993, .max: 0x09A8},
84 {.min: 0x09AA, .max: 0x09B0}, {.min: 0x09B2, .max: 0x09B2}, {.min: 0x09B6, .max: 0x09B9}, {.min: 0x09DC, .max: 0x09DD}, {.min: 0x09DF, .max: 0x09E1},
85 {.min: 0x09F0, .max: 0x09F1}, {.min: 0x0A05, .max: 0x0A0A}, {.min: 0x0A0F, .max: 0x0A10}, {.min: 0x0A13, .max: 0x0A28}, {.min: 0x0A2A, .max: 0x0A30},
86 {.min: 0x0A32, .max: 0x0A33}, {.min: 0x0A35, .max: 0x0A36}, {.min: 0x0A38, .max: 0x0A39}, {.min: 0x0A59, .max: 0x0A5C}, {.min: 0x0A5E, .max: 0x0A5E},
87 {.min: 0x0A72, .max: 0x0A74}, {.min: 0x0A85, .max: 0x0A8B}, {.min: 0x0A8D, .max: 0x0A8D}, {.min: 0x0A8F, .max: 0x0A91}, {.min: 0x0A93, .max: 0x0AA8},
88 {.min: 0x0AAA, .max: 0x0AB0}, {.min: 0x0AB2, .max: 0x0AB3}, {.min: 0x0AB5, .max: 0x0AB9}, {.min: 0x0ABD, .max: 0x0ABD}, {.min: 0x0AE0, .max: 0x0AE0},
89 {.min: 0x0B05, .max: 0x0B0C}, {.min: 0x0B0F, .max: 0x0B10}, {.min: 0x0B13, .max: 0x0B28}, {.min: 0x0B2A, .max: 0x0B30}, {.min: 0x0B32, .max: 0x0B33},
90 {.min: 0x0B36, .max: 0x0B39}, {.min: 0x0B3D, .max: 0x0B3D}, {.min: 0x0B5C, .max: 0x0B5D}, {.min: 0x0B5F, .max: 0x0B61}, {.min: 0x0B85, .max: 0x0B8A},
91 {.min: 0x0B8E, .max: 0x0B90}, {.min: 0x0B92, .max: 0x0B95}, {.min: 0x0B99, .max: 0x0B9A}, {.min: 0x0B9C, .max: 0x0B9C}, {.min: 0x0B9E, .max: 0x0B9F},
92 {.min: 0x0BA3, .max: 0x0BA4}, {.min: 0x0BA8, .max: 0x0BAA}, {.min: 0x0BAE, .max: 0x0BB5}, {.min: 0x0BB7, .max: 0x0BB9}, {.min: 0x0C05, .max: 0x0C0C},
93 {.min: 0x0C0E, .max: 0x0C10}, {.min: 0x0C12, .max: 0x0C28}, {.min: 0x0C2A, .max: 0x0C33}, {.min: 0x0C35, .max: 0x0C39}, {.min: 0x0C60, .max: 0x0C61},
94 {.min: 0x0C85, .max: 0x0C8C}, {.min: 0x0C8E, .max: 0x0C90}, {.min: 0x0C92, .max: 0x0CA8}, {.min: 0x0CAA, .max: 0x0CB3}, {.min: 0x0CB5, .max: 0x0CB9},
95 {.min: 0x0CDE, .max: 0x0CDE}, {.min: 0x0CE0, .max: 0x0CE1}, {.min: 0x0D05, .max: 0x0D0C}, {.min: 0x0D0E, .max: 0x0D10}, {.min: 0x0D12, .max: 0x0D28},
96 {.min: 0x0D2A, .max: 0x0D39}, {.min: 0x0D60, .max: 0x0D61}, {.min: 0x0E01, .max: 0x0E2E}, {.min: 0x0E30, .max: 0x0E30}, {.min: 0x0E32, .max: 0x0E33},
97 {.min: 0x0E40, .max: 0x0E45}, {.min: 0x0E81, .max: 0x0E82}, {.min: 0x0E84, .max: 0x0E84}, {.min: 0x0E87, .max: 0x0E88}, {.min: 0x0E8A, .max: 0x0E8A},
98 {.min: 0x0E8D, .max: 0x0E8D}, {.min: 0x0E94, .max: 0x0E97}, {.min: 0x0E99, .max: 0x0E9F}, {.min: 0x0EA1, .max: 0x0EA3}, {.min: 0x0EA5, .max: 0x0EA5},
99 {.min: 0x0EA7, .max: 0x0EA7}, {.min: 0x0EAA, .max: 0x0EAB}, {.min: 0x0EAD, .max: 0x0EAE}, {.min: 0x0EB0, .max: 0x0EB0}, {.min: 0x0EB2, .max: 0x0EB3},
100 {.min: 0x0EBD, .max: 0x0EBD}, {.min: 0x0EC0, .max: 0x0EC4}, {.min: 0x0F40, .max: 0x0F47}, {.min: 0x0F49, .max: 0x0F69}, {.min: 0x10A0, .max: 0x10C5},
101 {.min: 0x10D0, .max: 0x10F6}, {.min: 0x1100, .max: 0x1100}, {.min: 0x1102, .max: 0x1103}, {.min: 0x1105, .max: 0x1107}, {.min: 0x1109, .max: 0x1109},
102 {.min: 0x110B, .max: 0x110C}, {.min: 0x110E, .max: 0x1112}, {.min: 0x113C, .max: 0x113C}, {.min: 0x113E, .max: 0x113E}, {.min: 0x1140, .max: 0x1140},
103 {.min: 0x114C, .max: 0x114C}, {.min: 0x114E, .max: 0x114E}, {.min: 0x1150, .max: 0x1150}, {.min: 0x1154, .max: 0x1155}, {.min: 0x1159, .max: 0x1159},
104 {.min: 0x115F, .max: 0x1161}, {.min: 0x1163, .max: 0x1163}, {.min: 0x1165, .max: 0x1165}, {.min: 0x1167, .max: 0x1167}, {.min: 0x1169, .max: 0x1169},
105 {.min: 0x116D, .max: 0x116E}, {.min: 0x1172, .max: 0x1173}, {.min: 0x1175, .max: 0x1175}, {.min: 0x119E, .max: 0x119E}, {.min: 0x11A8, .max: 0x11A8},
106 {.min: 0x11AB, .max: 0x11AB}, {.min: 0x11AE, .max: 0x11AF}, {.min: 0x11B7, .max: 0x11B8}, {.min: 0x11BA, .max: 0x11BA}, {.min: 0x11BC, .max: 0x11C2},
107 {.min: 0x11EB, .max: 0x11EB}, {.min: 0x11F0, .max: 0x11F0}, {.min: 0x11F9, .max: 0x11F9}, {.min: 0x1E00, .max: 0x1E9B}, {.min: 0x1EA0, .max: 0x1EF9},
108 {.min: 0x1F00, .max: 0x1F15}, {.min: 0x1F18, .max: 0x1F1D}, {.min: 0x1F20, .max: 0x1F45}, {.min: 0x1F48, .max: 0x1F4D}, {.min: 0x1F50, .max: 0x1F57},
109 {.min: 0x1F59, .max: 0x1F59}, {.min: 0x1F5B, .max: 0x1F5B}, {.min: 0x1F5D, .max: 0x1F5D}, {.min: 0x1F5F, .max: 0x1F7D}, {.min: 0x1F80, .max: 0x1FB4},
110 {.min: 0x1FB6, .max: 0x1FBC}, {.min: 0x1FBE, .max: 0x1FBE}, {.min: 0x1FC2, .max: 0x1FC4}, {.min: 0x1FC6, .max: 0x1FCC}, {.min: 0x1FD0, .max: 0x1FD3},
111 {.min: 0x1FD6, .max: 0x1FDB}, {.min: 0x1FE0, .max: 0x1FEC}, {.min: 0x1FF2, .max: 0x1FF4}, {.min: 0x1FF6, .max: 0x1FFC}, {.min: 0x2126, .max: 0x2126},
112 {.min: 0x212A, .max: 0x212B}, {.min: 0x212E, .max: 0x212E}, {.min: 0x2180, .max: 0x2182}, {.min: 0x3041, .max: 0x3094}, {.min: 0x30A1, .max: 0x30FA},
113 {.min: 0x3105, .max: 0x312C}, {.min: 0xAC00, .max: 0xD7A3}
114};
115static const RangeIter g_base_end = g_base_begin + sizeof(g_base_begin) / sizeof(QXmlCharRange);
116
117static const QXmlCharRange g_ideographic_begin[] =
118{
119 {.min: 0x3007, .max: 0x3007}, {.min: 0x3021, .max: 0x3029}, {.min: 0x4E00, .max: 0x9FA5}
120};
121static const RangeIter g_ideographic_end = g_ideographic_begin + sizeof(g_ideographic_begin) / sizeof(QXmlCharRange);
122
123bool QXmlUtils::isIdeographic(const QChar c)
124{
125 return rangeContains(begin: g_ideographic_begin, end: g_ideographic_end, c);
126}
127
128static const QXmlCharRange g_combining_begin[] =
129{
130 {.min: 0x0300, .max: 0x0345}, {.min: 0x0360, .max: 0x0361}, {.min: 0x0483, .max: 0x0486}, {.min: 0x0591, .max: 0x05A1}, {.min: 0x05A3, .max: 0x05B9},
131 {.min: 0x05BB, .max: 0x05BD}, {.min: 0x05BF, .max: 0x05BF}, {.min: 0x05C1, .max: 0x05C2}, {.min: 0x05C4, .max: 0x05C4}, {.min: 0x064B, .max: 0x0652},
132 {.min: 0x0670, .max: 0x0670}, {.min: 0x06D6, .max: 0x06DC}, {.min: 0x06DD, .max: 0x06DF}, {.min: 0x06E0, .max: 0x06E4}, {.min: 0x06E7, .max: 0x06E8},
133 {.min: 0x06EA, .max: 0x06ED}, {.min: 0x0901, .max: 0x0903}, {.min: 0x093C, .max: 0x093C}, {.min: 0x093E, .max: 0x094C}, {.min: 0x094D, .max: 0x094D},
134 {.min: 0x0951, .max: 0x0954}, {.min: 0x0962, .max: 0x0963}, {.min: 0x0981, .max: 0x0983}, {.min: 0x09BC, .max: 0x09BC}, {.min: 0x09BE, .max: 0x09BE},
135 {.min: 0x09BF, .max: 0x09BF}, {.min: 0x09C0, .max: 0x09C4}, {.min: 0x09C7, .max: 0x09C8}, {.min: 0x09CB, .max: 0x09CD}, {.min: 0x09D7, .max: 0x09D7},
136 {.min: 0x09E2, .max: 0x09E3}, {.min: 0x0A02, .max: 0x0A02}, {.min: 0x0A3C, .max: 0x0A3C}, {.min: 0x0A3E, .max: 0x0A3E}, {.min: 0x0A3F, .max: 0x0A3F},
137 {.min: 0x0A40, .max: 0x0A42}, {.min: 0x0A47, .max: 0x0A48}, {.min: 0x0A4B, .max: 0x0A4D}, {.min: 0x0A70, .max: 0x0A71}, {.min: 0x0A81, .max: 0x0A83},
138 {.min: 0x0ABC, .max: 0x0ABC}, {.min: 0x0ABE, .max: 0x0AC5}, {.min: 0x0AC7, .max: 0x0AC9}, {.min: 0x0ACB, .max: 0x0ACD}, {.min: 0x0B01, .max: 0x0B03},
139 {.min: 0x0B3C, .max: 0x0B3C}, {.min: 0x0B3E, .max: 0x0B43}, {.min: 0x0B47, .max: 0x0B48}, {.min: 0x0B4B, .max: 0x0B4D}, {.min: 0x0B56, .max: 0x0B57},
140 {.min: 0x0B82, .max: 0x0B83}, {.min: 0x0BBE, .max: 0x0BC2}, {.min: 0x0BC6, .max: 0x0BC8}, {.min: 0x0BCA, .max: 0x0BCD}, {.min: 0x0BD7, .max: 0x0BD7},
141 {.min: 0x0C01, .max: 0x0C03}, {.min: 0x0C3E, .max: 0x0C44}, {.min: 0x0C46, .max: 0x0C48}, {.min: 0x0C4A, .max: 0x0C4D}, {.min: 0x0C55, .max: 0x0C56},
142 {.min: 0x0C82, .max: 0x0C83}, {.min: 0x0CBE, .max: 0x0CC4}, {.min: 0x0CC6, .max: 0x0CC8}, {.min: 0x0CCA, .max: 0x0CCD}, {.min: 0x0CD5, .max: 0x0CD6},
143 {.min: 0x0D02, .max: 0x0D03}, {.min: 0x0D3E, .max: 0x0D43}, {.min: 0x0D46, .max: 0x0D48}, {.min: 0x0D4A, .max: 0x0D4D}, {.min: 0x0D57, .max: 0x0D57},
144 {.min: 0x0E31, .max: 0x0E31}, {.min: 0x0E34, .max: 0x0E3A}, {.min: 0x0E47, .max: 0x0E4E}, {.min: 0x0EB1, .max: 0x0EB1}, {.min: 0x0EB4, .max: 0x0EB9},
145 {.min: 0x0EBB, .max: 0x0EBC}, {.min: 0x0EC8, .max: 0x0ECD}, {.min: 0x0F18, .max: 0x0F19}, {.min: 0x0F35, .max: 0x0F35}, {.min: 0x0F37, .max: 0x0F37},
146 {.min: 0x0F39, .max: 0x0F39}, {.min: 0x0F3E, .max: 0x0F3E}, {.min: 0x0F3F, .max: 0x0F3F}, {.min: 0x0F71, .max: 0x0F84}, {.min: 0x0F86, .max: 0x0F8B},
147 {.min: 0x0F90, .max: 0x0F95}, {.min: 0x0F97, .max: 0x0F97}, {.min: 0x0F99, .max: 0x0FAD}, {.min: 0x0FB1, .max: 0x0FB7}, {.min: 0x0FB9, .max: 0x0FB9},
148 {.min: 0x20D0, .max: 0x20DC}, {.min: 0x20E1, .max: 0x20E1}, {.min: 0x302A, .max: 0x302F}, {.min: 0x3099, .max: 0x3099}, {.min: 0x309A, .max: 0x309A}
149};
150static const RangeIter g_combining_end = g_combining_begin + sizeof(g_combining_begin) / sizeof(QXmlCharRange);
151
152bool QXmlUtils::isCombiningChar(const QChar c)
153{
154 return rangeContains(begin: g_combining_begin, end: g_combining_end, c);
155}
156
157// [88] Digit ::= ...
158static const QXmlCharRange g_digit_begin[] =
159{
160 {.min: 0x0030, .max: 0x0039}, {.min: 0x0660, .max: 0x0669}, {.min: 0x06F0, .max: 0x06F9}, {.min: 0x0966, .max: 0x096F}, {.min: 0x09E6, .max: 0x09EF},
161 {.min: 0x0A66, .max: 0x0A6F}, {.min: 0x0AE6, .max: 0x0AEF}, {.min: 0x0B66, .max: 0x0B6F}, {.min: 0x0BE7, .max: 0x0BEF}, {.min: 0x0C66, .max: 0x0C6F},
162 {.min: 0x0CE6, .max: 0x0CEF}, {.min: 0x0D66, .max: 0x0D6F}, {.min: 0x0E50, .max: 0x0E59}, {.min: 0x0ED0, .max: 0x0ED9}, {.min: 0x0F20, .max: 0x0F29}
163};
164static const RangeIter g_digit_end = g_digit_begin + sizeof(g_digit_begin) / sizeof(QXmlCharRange);
165
166bool QXmlUtils::isDigit(const QChar c)
167{
168 return rangeContains(begin: g_digit_begin, end: g_digit_end, c);
169}
170
171// [89] Extender ::= ...
172static const QXmlCharRange g_extender_begin[] =
173{
174 {.min: 0x00B7, .max: 0x00B7}, {.min: 0x02D0, .max: 0x02D0}, {.min: 0x02D1, .max: 0x02D1}, {.min: 0x0387, .max: 0x0387}, {.min: 0x0640, .max: 0x0640},
175 {.min: 0x0E46, .max: 0x0E46}, {.min: 0x0EC6, .max: 0x0EC6}, {.min: 0x3005, .max: 0x3005}, {.min: 0x3031, .max: 0x3035}, {.min: 0x309D, .max: 0x309E},
176 {.min: 0x30FC, .max: 0x30FE}
177};
178static const RangeIter g_extender_end = g_extender_begin + sizeof(g_extender_begin) / sizeof(QXmlCharRange);
179
180bool QXmlUtils::isExtender(const QChar c)
181{
182 return rangeContains(begin: g_extender_begin, end: g_extender_end, c);
183}
184
185bool QXmlUtils::isBaseChar(const QChar c)
186{
187 return rangeContains(begin: g_base_begin, end: g_base_end, c);
188}
189
190/*!
191 \internal
192
193 Determines whether \a encName is a valid instance of production [81]EncName in the XML 1.0
194 specification. If it is, true is returned, otherwise false.
195
196 \sa {http://www.w3.org/TR/REC-xml/#NT-EncName},
197 {Extensible Markup Language (XML) 1.0 (Fourth Edition), [81] EncName}
198 */
199bool QXmlUtils::isEncName(QStringView encName)
200{
201 // Valid encoding names are given by "[A-Za-z][A-Za-z0-9._\\-]*"
202 if (encName.isEmpty())
203 return false;
204 const auto first = encName.front().unicode();
205 if (!(isAsciiLower(c: first) || isAsciiUpper(c: first)))
206 return false;
207 for (QChar ch : encName.mid(pos: 1)) {
208 const auto cp = ch.unicode();
209 if (isAsciiLetterOrNumber(c: cp) || cp == '.' || cp == '_' || cp == '-')
210 continue;
211 return false;
212 }
213 return true;
214}
215
216/*!
217 \internal
218
219 Determines whether \a c is a valid instance of production [84]Letter in the XML 1.0
220 specification. If it is, true is returned, otherwise false.
221
222 \sa {http://www.w3.org/TR/REC-xml/#NT-Letter},
223 {Extensible Markup Language (XML) 1.0 (Fourth Edition), [84] Letter}
224 */
225bool QXmlUtils::isLetter(const QChar c)
226{
227 return isBaseChar(c) || isIdeographic(c);
228}
229
230/*!
231 \internal
232
233 Determines whether \a c is a valid instance of production [2]Char in the XML 1.0
234 specification. If it is, true is returned, otherwise false.
235
236 \sa {http://www.w3.org/TR/REC-xml/#NT-Char},
237 {Extensible Markup Language (XML) 1.0 (Fourth Edition), [2] Char}
238 */
239bool QXmlUtils::isChar(const char32_t c)
240{
241 // The valid range is defined by https://www.w3.org/TR/REC-xml/#NT-Char as following:
242 // Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
243 return (c >= 0x0020 && c <= 0xD7FF)
244 || c == 0x0009
245 || c == 0x000A
246 || c == 0x000D
247 || (c >= 0xE000 && c <= 0xFFFD)
248 || (c >= 0x10000 && c <= 0x10FFFF);
249}
250
251/*!
252 \internal
253
254 Determines whether \a c is a valid instance of
255 production [4]NameChar in the XML 1.0 specification. If it
256 is, true is returned, otherwise false.
257
258 \sa {http://www.w3.org/TR/REC-xml/#NT-NameChar},
259 {Extensible Markup Language (XML) 1.0 (Fourth Edition), [4] NameChar}
260 */
261bool QXmlUtils::isNameChar(const QChar c)
262{
263 return isBaseChar(c)
264 || isDigit(c)
265 || c.unicode() == '.'
266 || c.unicode() == '-'
267 || c.unicode() == '_'
268 || c.unicode() == ':'
269 || isCombiningChar(c)
270 || isIdeographic(c)
271 || isExtender(c);
272}
273
274/*!
275 \internal
276
277 Determines whether \a c is a valid instance of
278 production [12] PubidLiteral in the XML 1.0 specification. If it
279 is, true is returned, otherwise false.
280
281 \sa {http://www.w3.org/TR/REC-xml/#NT-PubidLiteral},
282 {Extensible Markup Language (XML) 1.0 (Fourth Edition), [12] PubidLiteral}
283 */
284bool QXmlUtils::isPublicID(QStringView candidate)
285{
286 for (QChar ch : candidate) {
287 const ushort cp = ch.unicode();
288
289 if (isAsciiLetterOrNumber(c: cp))
290 continue;
291
292 switch (cp)
293 {
294 /* Fallthrough all these. */
295 case 0x20:
296 case 0x0D:
297 case 0x0A:
298 case '-':
299 case '\'':
300 case '(':
301 case ')':
302 case '+':
303 case ',':
304 case '.':
305 case '/':
306 case ':':
307 case '=':
308 case '?':
309 case ';':
310 case '!':
311 case '*':
312 case '#':
313 case '@':
314 case '$':
315 case '_':
316 case '%':
317 continue;
318 default:
319 return false;
320 }
321 }
322
323 return true;
324}
325
326/*!
327 \internal
328
329 Determines whether \a c is a valid instance of
330 production [4]NCName in the XML 1.0 Namespaces specification. If it
331 is, true is returned, otherwise false.
332
333 \sa {http://www.w3.org/TR/REC-xml-names/#NT-NCName},
334 {W3CNamespaces in XML 1.0 (Second Edition), [4] NCName}
335 */
336bool QXmlUtils::isNCName(QStringView ncName)
337{
338 if (ncName.isEmpty())
339 return false;
340
341 const QChar first(ncName.at(n: 0));
342
343 if (!QXmlUtils::isLetter(c: first) && first.unicode() != '_' && first.unicode() != ':')
344 return false;
345
346 for (QChar at : ncName) {
347 if (!QXmlUtils::isNameChar(c: at) || at == u':')
348 return false;
349 }
350
351 return true;
352}
353
354QT_END_NAMESPACE
355

source code of qtbase/src/corelib/serialization/qxmlutils.cpp