1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4 **********************************************************************
5 * Copyright (C) 2005-2008, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 **********************************************************************
8 */
9
10#ifndef __INPUTEXT_H
11#define __INPUTEXT_H
12
13/**
14 * \file
15 * \internal
16 *
17 * This is an internal header for the Character Set Detection code. The
18 * name is probably too generic...
19 */
20
21
22#include "unicode/uobject.h"
23
24#if !UCONFIG_NO_CONVERSION
25
26U_NAMESPACE_BEGIN
27
28class InputText : public UMemory
29{
30 // Prevent copying
31 InputText(const InputText &);
32public:
33 InputText(UErrorCode &status);
34 ~InputText();
35
36 void setText(const char *in, int32_t len);
37 void setDeclaredEncoding(const char *encoding, int32_t len);
38 UBool isSet() const;
39 void MungeInput(UBool fStripTags);
40
41 // The text to be checked. Markup will have been
42 // removed if appropriate.
43 uint8_t *fInputBytes;
44 int32_t fInputLen; // Length of the byte data in fInputBytes.
45 // byte frequency statistics for the input text.
46 // Value is percent, not absolute.
47 // Value is rounded up, so zero really means zero occurences.
48 int16_t *fByteStats;
49 UBool fC1Bytes; // True if any bytes in the range 0x80 - 0x9F are in the input;false by default
50 char *fDeclaredEncoding;
51
52 const uint8_t *fRawInput; // Original, untouched input bytes.
53 // If user gave us a byte array, this is it.
54 // If user gave us a stream, it's read to a
55 // buffer here.
56 int32_t fRawLength; // Length of data in fRawInput array.
57
58};
59
60U_NAMESPACE_END
61
62#endif
63#endif /* __INPUTEXT_H */
64