blob: efffb613eed1ad44cad4cdf24b28105b9430b8d9 (
plain)
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
|
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2005-2008, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __INPUTEXT_H
#define __INPUTEXT_H
/**
* \file
* \internal
*
* This is an internal header for the Character Set Detection code. The
* name is probably too generic...
*/
#include "unicode/uobject.h"
#if !UCONFIG_NO_CONVERSION
U_NAMESPACE_BEGIN
class InputText : public UMemory
{
// Prevent copying
InputText(const InputText &);
public:
InputText(UErrorCode &status);
~InputText();
void setText(const char *in, int32_t len);
void setDeclaredEncoding(const char *encoding, int32_t len);
UBool isSet() const;
void MungeInput(UBool fStripTags);
// The text to be checked. Markup will have been
// removed if appropriate.
uint8_t *fInputBytes;
int32_t fInputLen; // Length of the byte data in fInputBytes.
// byte frequency statistics for the input text.
// Value is percent, not absolute.
// Value is rounded up, so zero really means zero occurences.
int16_t *fByteStats;
UBool fC1Bytes; // True if any bytes in the range 0x80 - 0x9F are in the input;false by default
char *fDeclaredEncoding;
const uint8_t *fRawInput; // Original, untouched input bytes.
// If user gave us a byte array, this is it.
// If user gave us a stream, it's read to a
// buffer here.
int32_t fRawLength; // Length of data in fRawInput array.
};
U_NAMESPACE_END
#endif
#endif /* __INPUTEXT_H */
|
