chromium/third_party/icu/source/common/bmpset.cpp

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
*   Copyright (C) 2007-2012, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
******************************************************************************
*   file name:  bmpset.cpp
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2007jan29
*   created by: Markus W. Scherer
*/

#include "unicode/utypes.h"
#include "unicode/uniset.h"
#include "unicode/utf8.h"
#include "unicode/utf16.h"
#include "cmemory.h"
#include "bmpset.h"
#include "uassert.h"

U_NAMESPACE_BEGIN

BMPSet::BMPSet(const int32_t *parentList, int32_t parentListLength) : … { … }

BMPSet::BMPSet(const BMPSet &otherBMPSet, const int32_t *newParentList, int32_t newParentListLength) : … { … }

BMPSet::~BMPSet() { … }

/*
 * Set bits in a bit rectangle in "vertical" bit organization.
 * start<limit<=0x800
 */
static void set32x64Bits(uint32_t table[64], int32_t start, int32_t limit) { … }

void BMPSet::initBits() { … }

/*
 * Override some bits and bytes to the result of contains(FFFD)
 * for faster validity checking at runtime.
 * No need to set 0 values where they were reset to 0 in the constructor
 * and not modified by initBits().
 * (table7FF[] 0..7F, bmpBlockBits[] 0..7FF)
 * Need to set 0 values for surrogates D800..DFFF.
 */
void BMPSet::overrideIllegal() { … }

int32_t BMPSet::findCodePoint(UChar32 c, int32_t lo, int32_t hi) const { … }

UBool
BMPSet::contains(UChar32 c) const { … }

/*
 * Check for sufficient length for trail unit for each surrogate pair.
 * Handle single surrogates as surrogate code points as usual in ICU.
 */
const char16_t *
BMPSet::span(const char16_t *s, const char16_t *limit, USetSpanCondition spanCondition) const { … }

/* Symmetrical with span(). */
const char16_t *
BMPSet::spanBack(const char16_t *s, const char16_t *limit, USetSpanCondition spanCondition) const { … }

/*
 * Precheck for sufficient trail bytes at end of string only once per span.
 * Check validity.
 */
const uint8_t *
BMPSet::spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCondition) const { … }

/*
 * While going backwards through UTF-8 optimize only for ASCII.
 * Unlike UTF-16, UTF-8 is not forward-backward symmetrical, that is, it is not
 * possible to tell from the last byte in a multi-byte sequence how many
 * preceding bytes there should be. Therefore, going backwards through UTF-8
 * is much harder than going forward.
 */
int32_t
BMPSet::spanBackUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCondition) const { … }

U_NAMESPACE_END