This file is indexed.

/usr/include/mozjs-52/js/CharacterEncoding.h is in libmozjs-52-dev 52.3.1-7fakesync1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 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
329
330
331
332
333
334
335
336
337
338
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 4 -*-
 * vim: set ts=8 sts=4 et sw=4 tw=99:
 * This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#ifndef js_CharacterEncoding_h
#define js_CharacterEncoding_h

#include "mozilla/Range.h"

#include "js/TypeDecls.h"
#include "js/Utility.h"

namespace js {
class ExclusiveContext;
} // namespace js

class JSFlatString;

namespace JS {

/*
 * By default, all C/C++ 1-byte-per-character strings passed into the JSAPI
 * are treated as ISO/IEC 8859-1, also known as Latin-1. That is, each
 * byte is treated as a 2-byte character, and there is no way to pass in a
 * string containing characters beyond U+00FF.
 */
class Latin1Chars : public mozilla::Range<Latin1Char>
{
    typedef mozilla::Range<Latin1Char> Base;

  public:
    using CharT = Latin1Char;

    Latin1Chars() : Base() {}
    Latin1Chars(char* aBytes, size_t aLength) : Base(reinterpret_cast<Latin1Char*>(aBytes), aLength) {}
    Latin1Chars(const Latin1Char* aBytes, size_t aLength)
      : Base(const_cast<Latin1Char*>(aBytes), aLength)
    {}
    Latin1Chars(const char* aBytes, size_t aLength)
      : Base(reinterpret_cast<Latin1Char*>(const_cast<char*>(aBytes)), aLength)
    {}
};

/*
 * A Latin1Chars, but with \0 termination for C compatibility.
 */
class Latin1CharsZ : public mozilla::RangedPtr<Latin1Char>
{
    typedef mozilla::RangedPtr<Latin1Char> Base;

  public:
    using CharT = Latin1Char;

    Latin1CharsZ() : Base(nullptr, 0) {}

    Latin1CharsZ(char* aBytes, size_t aLength)
      : Base(reinterpret_cast<Latin1Char*>(aBytes), aLength)
    {
        MOZ_ASSERT(aBytes[aLength] == '\0');
    }

    Latin1CharsZ(Latin1Char* aBytes, size_t aLength)
      : Base(aBytes, aLength)
    {
        MOZ_ASSERT(aBytes[aLength] == '\0');
    }

    using Base::operator=;

    char* c_str() { return reinterpret_cast<char*>(get()); }
};

class UTF8Chars : public mozilla::Range<unsigned char>
{
    typedef mozilla::Range<unsigned char> Base;

  public:
    using CharT = unsigned char;

    UTF8Chars() : Base() {}
    UTF8Chars(char* aBytes, size_t aLength)
      : Base(reinterpret_cast<unsigned char*>(aBytes), aLength)
    {}
    UTF8Chars(const char* aBytes, size_t aLength)
      : Base(reinterpret_cast<unsigned char*>(const_cast<char*>(aBytes)), aLength)
    {}
};

/*
 * SpiderMonkey also deals directly with UTF-8 encoded text in some places.
 */
class UTF8CharsZ : public mozilla::RangedPtr<unsigned char>
{
    typedef mozilla::RangedPtr<unsigned char> Base;

  public:
    using CharT = unsigned char;

    UTF8CharsZ() : Base(nullptr, 0) {}

    UTF8CharsZ(char* aBytes, size_t aLength)
      : Base(reinterpret_cast<unsigned char*>(aBytes), aLength)
    {
        MOZ_ASSERT(aBytes[aLength] == '\0');
    }

    UTF8CharsZ(unsigned char* aBytes, size_t aLength)
      : Base(aBytes, aLength)
    {
        MOZ_ASSERT(aBytes[aLength] == '\0');
    }

    using Base::operator=;

    char* c_str() { return reinterpret_cast<char*>(get()); }
};

/*
 * A wrapper for a "const char*" that is encoded using UTF-8.
 * This class does not manage ownership of the data; that is left
 * to others.  This differs from UTF8CharsZ in that the chars are
 * const and it allows assignment.
 */
class ConstUTF8CharsZ
{
    const char* data_;

  public:
    using CharT = unsigned char;

    ConstUTF8CharsZ() : data_(nullptr)
    {}

    ConstUTF8CharsZ(const char* aBytes, size_t aLength)
      : data_(aBytes)
    {
        MOZ_ASSERT(aBytes[aLength] == '\0');
#ifdef DEBUG
        validate(aLength);
#endif
    }

    const void* get() const { return data_; }

    const char* c_str() const { return data_; }

    explicit operator bool() const { return data_ != nullptr; }

  private:
#ifdef DEBUG
    void validate(size_t aLength);
#endif
};

/*
 * SpiderMonkey uses a 2-byte character representation: it is a
 * 2-byte-at-a-time view of a UTF-16 byte stream. This is similar to UCS-2,
 * but unlike UCS-2, we do not strip UTF-16 extension bytes. This allows a
 * sufficiently dedicated JavaScript program to be fully unicode-aware by
 * manually interpreting UTF-16 extension characters embedded in the JS
 * string.
 */
class TwoByteChars : public mozilla::Range<char16_t>
{
    typedef mozilla::Range<char16_t> Base;

  public:
    using CharT = char16_t;

    TwoByteChars() : Base() {}
    TwoByteChars(char16_t* aChars, size_t aLength) : Base(aChars, aLength) {}
    TwoByteChars(const char16_t* aChars, size_t aLength) : Base(const_cast<char16_t*>(aChars), aLength) {}
};

/*
 * A TwoByteChars, but \0 terminated for compatibility with JSFlatString.
 */
class TwoByteCharsZ : public mozilla::RangedPtr<char16_t>
{
    typedef mozilla::RangedPtr<char16_t> Base;

  public:
    using CharT = char16_t;

    TwoByteCharsZ() : Base(nullptr, 0) {}

    TwoByteCharsZ(char16_t* chars, size_t length)
      : Base(chars, length)
    {
        MOZ_ASSERT(chars[length] == '\0');
    }

    using Base::operator=;
};

typedef mozilla::RangedPtr<const char16_t> ConstCharPtr;

/*
 * Like TwoByteChars, but the chars are const.
 */
class ConstTwoByteChars : public mozilla::Range<const char16_t>
{
    typedef mozilla::Range<const char16_t> Base;

  public:
    using CharT = char16_t;

    ConstTwoByteChars() : Base() {}
    ConstTwoByteChars(const char16_t* aChars, size_t aLength) : Base(aChars, aLength) {}
};

/*
 * Convert a 2-byte character sequence to "ISO-Latin-1". This works by
 * truncating each 2-byte pair in the sequence to a 1-byte pair. If the source
 * contains any UTF-16 extension characters, then this may give invalid Latin1
 * output. The returned string is zero terminated. The returned string or the
 * returned string's |start()| must be freed with JS_free or js_free,
 * respectively. If allocation fails, an OOM error will be set and the method
 * will return a nullptr chars (which can be tested for with the ! operator).
 * This method cannot trigger GC.
 */
extern Latin1CharsZ
LossyTwoByteCharsToNewLatin1CharsZ(js::ExclusiveContext* cx,
                                   const mozilla::Range<const char16_t> tbchars);

inline Latin1CharsZ
LossyTwoByteCharsToNewLatin1CharsZ(js::ExclusiveContext* cx, const char16_t* begin, size_t length)
{
    const mozilla::Range<const char16_t> tbchars(begin, length);
    return JS::LossyTwoByteCharsToNewLatin1CharsZ(cx, tbchars);
}

template <typename CharT>
extern UTF8CharsZ
CharsToNewUTF8CharsZ(js::ExclusiveContext* maybeCx, const mozilla::Range<CharT> chars);

JS_PUBLIC_API(uint32_t)
Utf8ToOneUcs4Char(const uint8_t* utf8Buffer, int utf8Length);

/*
 * Inflate bytes in UTF-8 encoding to char16_t.
 * - On error, returns an empty TwoByteCharsZ.
 * - On success, returns a malloc'd TwoByteCharsZ, and updates |outlen| to hold
 *   its length;  the length value excludes the trailing null.
 */
extern JS_PUBLIC_API(TwoByteCharsZ)
UTF8CharsToNewTwoByteCharsZ(JSContext* cx, const UTF8Chars utf8, size_t* outlen);

/*
 * Like UTF8CharsToNewTwoByteCharsZ, but for ConstUTF8CharsZ.
 */
extern JS_PUBLIC_API(TwoByteCharsZ)
UTF8CharsToNewTwoByteCharsZ(JSContext* cx, const ConstUTF8CharsZ& utf8, size_t* outlen);

/*
 * The same as UTF8CharsToNewTwoByteCharsZ(), except that any malformed UTF-8 characters
 * will be replaced by \uFFFD. No exception will be thrown for malformed UTF-8
 * input.
 */
extern JS_PUBLIC_API(TwoByteCharsZ)
LossyUTF8CharsToNewTwoByteCharsZ(JSContext* cx, const UTF8Chars utf8, size_t* outlen);

extern JS_PUBLIC_API(TwoByteCharsZ)
LossyUTF8CharsToNewTwoByteCharsZ(JSContext* cx, const ConstUTF8CharsZ& utf8, size_t* outlen);

/*
 * Returns the length of the char buffer required to encode |s| as UTF8.
 * Does not include the null-terminator.
 */
JS_PUBLIC_API(size_t)
GetDeflatedUTF8StringLength(JSFlatString* s);

/*
 * Encode |src| as UTF8. The caller must either ensure |dst| has enough space
 * to encode the entire string or pass the length of the buffer as |dstlenp|,
 * in which case the function will encode characters from the string until
 * the buffer is exhausted. Does not write the null terminator.
 *
 * If |dstlenp| is provided, it will be updated to hold the number of bytes
 * written to the buffer. If |numcharsp| is provided, it will be updated to hold
 * the number of Unicode characters written to the buffer (which can be less
 * than the length of the string, if the buffer is exhausted before the string
 * is fully encoded).
 */
JS_PUBLIC_API(void)
DeflateStringToUTF8Buffer(JSFlatString* src, mozilla::RangedPtr<char> dst,
                          size_t* dstlenp = nullptr, size_t* numcharsp = nullptr);

/*
 * The smallest character encoding capable of fully representing a particular
 * string.
 */
enum class SmallestEncoding {
    ASCII,
    Latin1,
    UTF16
};

/*
 * Returns the smallest encoding possible for the given string: if all
 * codepoints are <128 then ASCII, otherwise if all codepoints are <256
 * Latin-1, else UTF16.
 */
JS_PUBLIC_API(SmallestEncoding)
FindSmallestEncoding(UTF8Chars utf8);

/*
  * Return a null-terminated Latin-1 string copied from the input string,
  * storing its length (excluding null terminator) in |*outlen|.  Fail and
  * report an error if the string contains non-Latin-1 codepoints.  Returns
  * Latin1CharsZ() on failure.
 */
extern JS_PUBLIC_API(Latin1CharsZ)
UTF8CharsToNewLatin1CharsZ(JSContext* cx, const UTF8Chars utf8, size_t* outlen);

/*
 * Return a null-terminated Latin-1 string copied from the input string,
 * storing its length (excluding null terminator) in |*outlen|.  Non-Latin-1
 * codepoints are replaced by '?'.  Returns Latin1CharsZ() on failure.
 */
extern JS_PUBLIC_API(Latin1CharsZ)
LossyUTF8CharsToNewLatin1CharsZ(JSContext* cx, const UTF8Chars utf8, size_t* outlen);

/*
 * Returns true if all characters in the given null-terminated string are
 * ASCII, i.e. < 0x80, false otherwise.
 */
extern JS_PUBLIC_API(bool)
StringIsASCII(const char* s);

} // namespace JS

inline void JS_free(JS::Latin1CharsZ& ptr) { js_free((void*)ptr.get()); }
inline void JS_free(JS::UTF8CharsZ& ptr) { js_free((void*)ptr.get()); }

#endif /* js_CharacterEncoding_h */