godot/thirdparty/icu4c/common/ucase.cpp

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2004-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  ucase.cpp
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2004aug30
*   created by: Markus W. Scherer
*
*   Low-level Unicode character/string case mapping code.
*   Much code moved here (and modified) from uchar.c.
*/

#include "unicode/utypes.h"
#include "unicode/unistr.h"
#include "unicode/uset.h"
#include "unicode/utf16.h"
#include "cmemory.h"
#include "uassert.h"
#include "ucase.h"
#include "umutex.h"
#include "utrie2.h"

/* ucase_props_data.h is machine-generated by genprops/casepropsbuilder.cpp */
#define INCLUDED_FROM_UCASE_CPP
#include "ucase_props_data.h"

/* set of property starts for UnicodeSet ------------------------------------ */

static UBool U_CALLCONV
_enumPropertyStartsRange(const void *context, UChar32 start, UChar32 /*end*/, uint32_t /*value*/) { … }

U_CFUNC void U_EXPORT2
ucase_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) { … }

/* data access primitives --------------------------------------------------- */

U_CAPI const struct UCaseProps * U_EXPORT2
ucase_getSingleton(int32_t *pExceptionsLength, int32_t *pUnfoldLength) { … }

U_CFUNC const UTrie2 * U_EXPORT2
ucase_getTrie() { … }

#define GET_EXCEPTIONS(csp, props) …

/* number of bits in an 8-bit integer value */
static const uint8_t flagsOffset[256]= …;

#define HAS_SLOT(flags, idx) …
#define SLOT_OFFSET(flags, idx) …

/*
 * Get the value of an optional-value slot where HAS_SLOT(excWord, idx).
 *
 * @param excWord (in) initial exceptions word
 * @param idx (in) desired slot index
 * @param pExc16 (in/out) const uint16_t * after excWord=*pExc16++;
 *               moved to the last uint16_t of the value, use +1 for beginning of next slot
 * @param value (out) int32_t or uint32_t output if hasSlot, otherwise not modified
 */
#define GET_SLOT_VALUE(excWord, idx, pExc16, value) …

/* simple case mappings ----------------------------------------------------- */

U_CAPI UChar32 U_EXPORT2
ucase_tolower(UChar32 c) { … }

U_CAPI UChar32 U_EXPORT2
ucase_toupper(UChar32 c) { … }

U_CAPI UChar32 U_EXPORT2
ucase_totitle(UChar32 c) { … }

static const char16_t iDot[2] = …;
static const char16_t jDot[2] = …;
static const char16_t iOgonekDot[3] = …;
static const char16_t iDotGrave[3] = …;
static const char16_t iDotAcute[3] = …;
static const char16_t iDotTilde[3] = …;


U_CFUNC void U_EXPORT2
ucase_addCaseClosure(UChar32 c, const USetAdder *sa) { … }

U_CFUNC void U_EXPORT2
ucase_addSimpleCaseClosure(UChar32 c, const USetAdder *sa) { … }

/*
 * compare s, which has a length, with t, which has a maximum length or is NUL-terminated
 * must be length>0 and max>0 and length<=max
 */
static inline int32_t
strcmpMax(const char16_t *s, int32_t length, const char16_t *t, int32_t max) { … }

U_CFUNC UBool U_EXPORT2
ucase_addStringCaseClosure(const char16_t *s, int32_t length, const USetAdder *sa) { … }

U_NAMESPACE_BEGIN

FullCaseFoldingIterator::FullCaseFoldingIterator()
        : … { … }

UChar32
FullCaseFoldingIterator::next(UnicodeString &full) { … }

namespace LatinCase {

const int8_t TO_LOWER_NORMAL[LIMIT] = …;

const int8_t TO_LOWER_TR_LT[LIMIT] = …;

const int8_t TO_UPPER_NORMAL[LIMIT] = …;

const int8_t TO_UPPER_TR[LIMIT] = …;

}  // namespace LatinCase

U_NAMESPACE_END

/** @return UCASE_NONE, UCASE_LOWER, UCASE_UPPER, UCASE_TITLE */
U_CAPI int32_t U_EXPORT2
ucase_getType(UChar32 c) { … }

/** @return same as ucase_getType() and set bit 2 if c is case-ignorable */
U_CAPI int32_t U_EXPORT2
ucase_getTypeOrIgnorable(UChar32 c) { … }

/** @return UCASE_NO_DOT, UCASE_SOFT_DOTTED, UCASE_ABOVE, UCASE_OTHER_ACCENT */
static inline int32_t
getDotType(UChar32 c) { … }

U_CAPI UBool U_EXPORT2
ucase_isSoftDotted(UChar32 c) { … }

U_CAPI UBool U_EXPORT2
ucase_isCaseSensitive(UChar32 c) { … }

/* string casing ------------------------------------------------------------ */

/*
 * These internal functions form the core of string case mappings.
 * They map single code points to result code points or strings and take
 * all necessary conditions (context, locale ID, options) into account.
 *
 * They do not iterate over the source or write to the destination
 * so that the same functions are useful for non-standard string storage,
 * such as in a Replaceable (for Transliterator) or UTF-8/32 strings etc.
 * For the same reason, the "surrounding text" context is passed in as a
 * UCaseContextIterator which does not make any assumptions about
 * the underlying storage.
 *
 * This section contains helper functions that check for conditions
 * in the input text surrounding the current code point
 * according to SpecialCasing.txt.
 *
 * Each helper function gets the index
 * - after the current code point if it looks at following text
 * - before the current code point if it looks at preceding text
 *
 * Unicode 3.2 UAX 21 "Case Mappings" defines the conditions as follows:
 *
 * Final_Sigma
 *   C is preceded by a sequence consisting of
 *     a cased letter and a case-ignorable sequence,
 *   and C is not followed by a sequence consisting of
 *     an ignorable sequence and then a cased letter.
 *
 * More_Above
 *   C is followed by one or more characters of combining class 230 (ABOVE)
 *   in the combining character sequence.
 *
 * After_Soft_Dotted
 *   The last preceding character with combining class of zero before C
 *   was Soft_Dotted,
 *   and there is no intervening combining character class 230 (ABOVE).
 *
 * Before_Dot
 *   C is followed by combining dot above (U+0307).
 *   Any sequence of characters with a combining class that is neither 0 nor 230
 *   may intervene between the current character and the combining dot above.
 *
 * The erratum from 2002-10-31 adds the condition
 *
 * After_I
 *   The last preceding base character was an uppercase I, and there is no
 *   intervening combining character class 230 (ABOVE).
 *
 *   (See Jitterbug 2344 and the comments on After_I below.)
 *
 * Helper definitions in Unicode 3.2 UAX 21:
 *
 * D1. A character C is defined to be cased
 *     if it meets any of the following criteria:
 *
 *   - The general category of C is Titlecase Letter (Lt)
 *   - In [CoreProps], C has one of the properties Uppercase, or Lowercase
 *   - Given D = NFD(C), then it is not the case that:
 *     D = UCD_lower(D) = UCD_upper(D) = UCD_title(D)
 *     (This third criterion does not add any characters to the list
 *      for Unicode 3.2. Ignored.)
 *
 * D2. A character C is defined to be case-ignorable
 *     if it meets either of the following criteria:
 *
 *   - The general category of C is
 *     Nonspacing Mark (Mn), or Enclosing Mark (Me), or Format Control (Cf), or
 *     Letter Modifier (Lm), or Symbol Modifier (Sk)
 *   - C is one of the following characters
 *     U+0027 APOSTROPHE
 *     U+00AD SOFT HYPHEN (SHY)
 *     U+2019 RIGHT SINGLE QUOTATION MARK
 *            (the preferred character for apostrophe)
 *
 * D3. A case-ignorable sequence is a sequence of
 *     zero or more case-ignorable characters.
 */

#define is_d(c) …
#define is_e(c) …
#define is_i(c) …
#define is_l(c) …
#define is_r(c) …
#define is_t(c) …
#define is_u(c) …
#define is_y(c) …
#define is_z(c) …

/* separator? */
#define is_sep(c) …

/**
 * Requires non-nullptr locale ID but otherwise does the equivalent of
 * checking for language codes as if uloc_getLanguage() were called:
 * Accepts both 2- and 3-letter codes and accepts case variants.
 */
U_CFUNC int32_t
ucase_getCaseLocale(const char *locale) { … }

/*
 * Is followed by
 *   {case-ignorable}* cased
 * ?
 * (dir determines looking forward/backward)
 * If a character is case-ignorable, it is skipped regardless of whether
 * it is also cased or not.
 */
static UBool
isFollowedByCasedLetter(UCaseContextIterator *iter, void *context, int8_t dir) { … }

/* Is preceded by Soft_Dotted character with no intervening cc=230 ? */
static UBool
isPrecededBySoftDotted(UCaseContextIterator *iter, void *context) { … }

/*
 * See Jitterbug 2344:
 * The condition After_I for Turkic-lowercasing of U+0307 combining dot above
 * is checked in ICU 2.0, 2.1, 2.6 but was not in 2.2 & 2.4 because
 * we made those releases compatible with Unicode 3.2 which had not fixed
 * a related bug in SpecialCasing.txt.
 *
 * From the Jitterbug 2344 text:
 * ... this bug is listed as a Unicode erratum
 * from 2002-10-31 at http://www.unicode.org/uni2errata/UnicodeErrata.html
 * <quote>
 * There are two errors in SpecialCasing.txt.
 * 1. Missing semicolons on two lines. ... [irrelevant for ICU]
 * 2. An incorrect context definition. Correct as follows:
 * < 0307; ; 0307; 0307; tr After_Soft_Dotted; # COMBINING DOT ABOVE
 * < 0307; ; 0307; 0307; az After_Soft_Dotted; # COMBINING DOT ABOVE
 * ---
 * > 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
 * > 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
 * where the context After_I is defined as:
 * The last preceding base character was an uppercase I, and there is no
 * intervening combining character class 230 (ABOVE).
 * </quote>
 *
 * Note that SpecialCasing.txt even in Unicode 3.2 described the condition as:
 *
 * # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
 * # This matches the behavior of the canonically equivalent I-dot_above
 *
 * See also the description in this place in older versions of uchar.c (revision 1.100).
 *
 * Markus W. Scherer 2003-feb-15
 */

/* Is preceded by base character 'I' with no intervening cc=230 ? */
static UBool
isPrecededBy_I(UCaseContextIterator *iter, void *context) { … }

/* Is followed by one or more cc==230 ? */
static UBool
isFollowedByMoreAbove(UCaseContextIterator *iter, void *context) { … }

/* Is followed by a dot above (without cc==230 in between) ? */
static UBool
isFollowedByDotAbove(UCaseContextIterator *iter, void *context) { … }

U_CAPI int32_t U_EXPORT2
ucase_toFullLower(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t loc) { … }

/* internal */
static int32_t
toUpperOrTitle(UChar32 c,
               UCaseContextIterator *iter, void *context,
               const char16_t **pString,
               int32_t loc,
               UBool upperNotTitle) { … }

U_CAPI int32_t U_EXPORT2
ucase_toFullUpper(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t caseLocale) { … }

U_CAPI int32_t U_EXPORT2
ucase_toFullTitle(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t caseLocale) { … }

/* case folding ------------------------------------------------------------- */

/*
 * Case folding is similar to lowercasing.
 * The result may be a simple mapping, i.e., a single code point, or
 * a full mapping, i.e., a string.
 * If the case folding for a code point is the same as its simple (1:1) lowercase mapping,
 * then only the lowercase mapping is stored.
 *
 * Some special cases are hardcoded because their conditions cannot be
 * parsed and processed from CaseFolding.txt.
 *
 * Unicode 3.2 CaseFolding.txt specifies for its status field:

# C: common case folding, common mappings shared by both simple and full mappings.
# F: full case folding, mappings that cause strings to grow in length. Multiple characters are separated by spaces.
# S: simple case folding, mappings to single characters where different from F.
# T: special case for uppercase I and dotted uppercase I
#    - For non-Turkic languages, this mapping is normally not used.
#    - For Turkic languages (tr, az), this mapping can be used instead of the normal mapping for these characters.
#
# Usage:
#  A. To do a simple case folding, use the mappings with status C + S.
#  B. To do a full case folding, use the mappings with status C + F.
#
#    The mappings with status T can be used or omitted depending on the desired case-folding
#    behavior. (The default option is to exclude them.)

 * Unicode 3.2 has 'T' mappings as follows:

0049; T; 0131; # LATIN CAPITAL LETTER I
0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE

 * while the default mappings for these code points are:

0049; C; 0069; # LATIN CAPITAL LETTER I
0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE

 * U+0130 has no simple case folding (simple-case-folds to itself).
 */

/* return the simple case folding mapping for c */
U_CAPI UChar32 U_EXPORT2
ucase_fold(UChar32 c, uint32_t options) { … }

/*
 * Issue for canonical caseless match (UAX #21):
 * Turkic casefolding (using "T" mappings in CaseFolding.txt) does not preserve
 * canonical equivalence, unlike default-option casefolding.
 * For example, I-grave and I + grave fold to strings that are not canonically
 * equivalent.
 * For more details, see the comment in unorm_compare() in unorm.cpp
 * and the intermediate prototype changes for Jitterbug 2021.
 * (For example, revision 1.104 of uchar.c and 1.4 of CaseFolding.txt.)
 *
 * This did not get fixed because it appears that it is not possible to fix
 * it for uppercase and lowercase characters (I-grave vs. i-grave)
 * together in a way that they still fold to common result strings.
 */

U_CAPI int32_t U_EXPORT2
ucase_toFullFolding(UChar32 c,
                    const char16_t **pString,
                    uint32_t options) { … }

/* case mapping properties API ---------------------------------------------- */

/* public API (see uchar.h) */

U_CAPI UBool U_EXPORT2
u_isULowercase(UChar32 c) { … }

U_CAPI UBool U_EXPORT2
u_isUUppercase(UChar32 c) { … }

/* Transforms the Unicode character to its lower case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_tolower(UChar32 c) { … }

/* Transforms the Unicode character to its upper case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_toupper(UChar32 c) { … }

/* Transforms the Unicode character to its title case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_totitle(UChar32 c) { … }

/* return the simple case folding mapping for c */
U_CAPI UChar32 U_EXPORT2
u_foldCase(UChar32 c, uint32_t options) { … }

U_CFUNC int32_t U_EXPORT2
ucase_hasBinaryProperty(UChar32 c, UProperty which) { … }