DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (31ec81b5d7bb)

VCS Links

Line Code
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
/*
 **********************************************************************
 *   Copyright (C) 2005-2012, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 */

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "csrucode.h"
#include "csmatch.h"

U_NAMESPACE_BEGIN

CharsetRecog_Unicode::~CharsetRecog_Unicode()
{
    // nothing to do
}

CharsetRecog_UTF_16_BE::~CharsetRecog_UTF_16_BE()
{
    // nothing to do
}

const char *CharsetRecog_UTF_16_BE::getName() const
{
    return "UTF-16BE";
}

UBool CharsetRecog_UTF_16_BE::match(InputText* textIn, CharsetMatch *results) const
{
    const uint8_t *input = textIn->fRawInput;
    int32_t confidence = 0;

    if (input[0] == 0xFE && input[1] == 0xFF) {
        confidence = 100;
    }

    // TODO: Do some statastics to check for unsigned UTF-16BE
    results->set(textIn, this, confidence);
    return (confidence > 0);
}

CharsetRecog_UTF_16_LE::~CharsetRecog_UTF_16_LE()
{
    // nothing to do
}

const char *CharsetRecog_UTF_16_LE::getName() const
{
    return "UTF-16LE";
}

UBool CharsetRecog_UTF_16_LE::match(InputText* textIn, CharsetMatch *results) const
{
    const uint8_t *input = textIn->fRawInput;
    int32_t confidence = 0;

    if (input[0] == 0xFF && input[1] == 0xFE && (input[2] != 0x00 || input[3] != 0x00)) {
        confidence = 100;
    }

    // TODO: Do some statastics to check for unsigned UTF-16LE
    results->set(textIn, this, confidence);
    return (confidence > 0);
}

CharsetRecog_UTF_32::~CharsetRecog_UTF_32()
{
    // nothing to do
}

UBool CharsetRecog_UTF_32::match(InputText* textIn, CharsetMatch *results) const
{
    const uint8_t *input = textIn->fRawInput;
    int32_t limit = (textIn->fRawLength / 4) * 4;
    int32_t numValid = 0;
    int32_t numInvalid = 0;
    bool hasBOM = FALSE;
    int32_t confidence = 0;

    if (getChar(input, 0) == 0x0000FEFFUL) {
        hasBOM = TRUE;
    }

    for(int32_t i = 0; i < limit; i += 4) {
        int32_t ch = getChar(input, i);

        if (ch < 0 || ch >= 0x10FFFF || (ch >= 0xD800 && ch <= 0xDFFF)) {
            numInvalid += 1;
        } else {
            numValid += 1;
        }
    }


    // Cook up some sort of confidence score, based on presense of a BOM
    //    and the existence of valid and/or invalid multi-byte sequences.
    if (hasBOM && numInvalid==0) {
        confidence = 100;
    } else if (hasBOM && numValid > numInvalid*10) {
        confidence = 80;
    } else if (numValid > 3 && numInvalid == 0) {
        confidence = 100;            
    } else if (numValid > 0 && numInvalid == 0) {
        confidence = 80;
    } else if (numValid > numInvalid*10) {
        // Probably corruput UTF-32BE data.  Valid sequences aren't likely by chance.
        confidence = 25;
    }

    results->set(textIn, this, confidence);
    return (confidence > 0);
}

CharsetRecog_UTF_32_BE::~CharsetRecog_UTF_32_BE()
{
    // nothing to do
}

const char *CharsetRecog_UTF_32_BE::getName() const
{
    return "UTF-32BE";
}

int32_t CharsetRecog_UTF_32_BE::getChar(const uint8_t *input, int32_t index) const
{
    return input[index + 0] << 24 | input[index + 1] << 16 |
           input[index + 2] <<  8 | input[index + 3];
} 

CharsetRecog_UTF_32_LE::~CharsetRecog_UTF_32_LE()
{
    // nothing to do
}

const char *CharsetRecog_UTF_32_LE::getName() const
{
    return "UTF-32LE";
}

int32_t CharsetRecog_UTF_32_LE::getChar(const uint8_t *input, int32_t index) const
{
    return input[index + 3] << 24 | input[index + 2] << 16 |
           input[index + 1] <<  8 | input[index + 0];
}

U_NAMESPACE_END
#endif