+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
-* Copyright (C) 1999-2004, International Business Machines
+* Copyright (C) 1999-2015, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
*/
#include "unicode/utypes.h"
-#include "unicode/uniset.h"
#include "unicode/parsepos.h"
#include "unicode/symtable.h"
+#include "unicode/uniset.h"
+#include "unicode/ustring.h"
+#include "unicode/utf8.h"
+#include "unicode/utf16.h"
#include "ruleiter.h"
#include "cmemory.h"
-#include "uhash.h"
+#include "cstring.h"
+#include "patternprops.h"
+#include "uelement.h"
#include "util.h"
#include "uvector.h"
#include "charstr.h"
#include "ustrfmt.h"
-#include "mutex.h"
#include "uassert.h"
-#include "hash.h"
+#include "bmpset.h"
+#include "unisetspan.h"
// Define UChar constants using hex for EBCDIC compatibility
// Used #define to reduce private static exports and memory access time.
// LOW <= all valid values. ZERO for codepoints
#define UNICODESET_LOW 0x000000
-// initial storage. Must be >= 0
-#define START_EXTRA 16
-
-// extra amount for growth. Must be >= 0
-#define GROW_EXTRA START_EXTRA
+/** Max list [0, 1, 2, ..., max code point, HIGH] */
+constexpr int32_t MAX_LENGTH = UNICODESET_HIGH + 1;
U_NAMESPACE_BEGIN
SymbolTable::~SymbolTable() {}
-/**
- * Minimum value that can be stored in a UnicodeSet.
- */
-const UChar32 UnicodeSet::MIN_VALUE = UNICODESET_LOW;
-
-/**
- * Maximum value that can be stored in a UnicodeSet.
- */
-const UChar32 UnicodeSet::MAX_VALUE = UNICODESET_HIGH - 1;
-
UOBJECT_DEFINE_RTTI_IMPLEMENTATION(UnicodeSet)
/**
// UnicodeString in UVector support
//----------------------------------------------------------------
-static void U_CALLCONV cloneUnicodeString(UHashTok *dst, UHashTok *src) {
+static void U_CALLCONV cloneUnicodeString(UElement *dst, UElement *src) {
dst->pointer = new UnicodeString(*(UnicodeString*)src->pointer);
}
-static int8_t U_CALLCONV compareUnicodeString(UHashTok t1, UHashTok t2) {
+static int8_t U_CALLCONV compareUnicodeString(UElement t1, UElement t2) {
const UnicodeString &a = *(const UnicodeString*)t1.pointer;
const UnicodeString &b = *(const UnicodeString*)t2.pointer;
return a.compare(b);
}
+UBool UnicodeSet::hasStrings() const {
+ return strings != nullptr && !strings->isEmpty();
+}
+
+int32_t UnicodeSet::stringsSize() const {
+ return strings == nullptr ? 0 : strings->size();
+}
+
+UBool UnicodeSet::stringsContains(const UnicodeString &s) const {
+ return strings != nullptr && strings->contains((void*) &s);
+}
+
//----------------------------------------------------------------
// Constructors &c
//----------------------------------------------------------------
/**
* Constructs an empty set.
*/
-UnicodeSet::UnicodeSet() :
- len(1), capacity(1 + START_EXTRA), bufferCapacity(0),
- list(0), buffer(0), strings(0)
-{
- list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
- if(list!=NULL){
- list[0] = UNICODESET_HIGH;
- }
- allocateStrings();
+UnicodeSet::UnicodeSet() {
+ list[0] = UNICODESET_HIGH;
_dbgct(this);
}
* @param start first character, inclusive, of range
* @param end last character, inclusive, of range
*/
-UnicodeSet::UnicodeSet(UChar32 start, UChar32 end) :
- len(1), capacity(1 + START_EXTRA), bufferCapacity(0),
- list(0), buffer(0), strings(0)
-{
- list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
- if(list!=NULL){
- list[0] = UNICODESET_HIGH;
- }
- allocateStrings();
- complement(start, end);
+UnicodeSet::UnicodeSet(UChar32 start, UChar32 end) {
+ list[0] = UNICODESET_HIGH;
+ add(start, end);
_dbgct(this);
}
/**
* Constructs a set that is identical to the given UnicodeSet.
*/
-UnicodeSet::UnicodeSet(const UnicodeSet& o) :
- UnicodeFilter(o),
- len(0), capacity(o.len + GROW_EXTRA), bufferCapacity(0),
- list(0), buffer(0), strings(0)
-{
- list = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
- if(list!=NULL){
- allocateStrings();
- *this = o;
- }
+UnicodeSet::UnicodeSet(const UnicodeSet& o) : UnicodeFilter(o) {
+ *this = o;
_dbgct(this);
}
+// Copy-construct as thawed.
+UnicodeSet::UnicodeSet(const UnicodeSet& o, UBool /* asThawed */) : UnicodeFilter(o) {
+ if (ensureCapacity(o.len)) {
+ // *this = o except for bmpSet and stringSpan
+ len = o.len;
+ uprv_memcpy(list, o.list, (size_t)len*sizeof(UChar32));
+ if (o.hasStrings()) {
+ UErrorCode status = U_ZERO_ERROR;
+ if (!allocateStrings(status) ||
+ (strings->assign(*o.strings, cloneUnicodeString, status), U_FAILURE(status))) {
+ setToBogus();
+ return;
+ }
+ }
+ if (o.pat) {
+ setPattern(o.pat, o.patLen);
+ }
+ _dbgct(this);
+ }
+}
+
/**
* Destructs the set.
*/
UnicodeSet::~UnicodeSet() {
_dbgdt(this); // first!
- uprv_free(list);
- if (buffer) {
+ if (list != stackList) {
+ uprv_free(list);
+ }
+ delete bmpSet;
+ if (buffer != stackList) {
uprv_free(buffer);
}
delete strings;
+ delete stringSpan;
+ releasePattern();
}
/**
* Assigns this object to be a copy of another.
*/
UnicodeSet& UnicodeSet::operator=(const UnicodeSet& o) {
- ensureCapacity(o.len);
+ return copyFrom(o, FALSE);
+}
+
+UnicodeSet& UnicodeSet::copyFrom(const UnicodeSet& o, UBool asThawed) {
+ if (this == &o) {
+ return *this;
+ }
+ if (isFrozen()) {
+ return *this;
+ }
+ if (o.isBogus()) {
+ setToBogus();
+ return *this;
+ }
+ if (!ensureCapacity(o.len)) {
+ // ensureCapacity will mark the UnicodeSet as Bogus if OOM failure happens.
+ return *this;
+ }
len = o.len;
- uprv_memcpy(list, o.list, len*sizeof(UChar32));
- UErrorCode ec = U_ZERO_ERROR;
- strings->assign(*o.strings, cloneUnicodeString, ec);
- pat = o.pat;
+ uprv_memcpy(list, o.list, (size_t)len*sizeof(UChar32));
+ if (o.bmpSet != nullptr && !asThawed) {
+ bmpSet = new BMPSet(*o.bmpSet, list, len);
+ if (bmpSet == NULL) { // Check for memory allocation error.
+ setToBogus();
+ return *this;
+ }
+ }
+ if (o.hasStrings()) {
+ UErrorCode status = U_ZERO_ERROR;
+ if ((strings == nullptr && !allocateStrings(status)) ||
+ (strings->assign(*o.strings, cloneUnicodeString, status), U_FAILURE(status))) {
+ setToBogus();
+ return *this;
+ }
+ } else if (hasStrings()) {
+ strings->removeAllElements();
+ }
+ if (o.stringSpan != nullptr && !asThawed) {
+ stringSpan = new UnicodeSetStringSpan(*o.stringSpan, *strings);
+ if (stringSpan == NULL) { // Check for memory allocation error.
+ setToBogus();
+ return *this;
+ }
+ }
+ releasePattern();
+ if (o.pat) {
+ setPattern(o.pat, o.patLen);
+ }
return *this;
}
+/**
+ * Returns a copy of this object. All UnicodeMatcher objects have
+ * to support cloning in order to allow classes using
+ * UnicodeMatchers, such as Transliterator, to implement cloning.
+ */
+UnicodeFunctor* UnicodeSet::clone() const {
+ return new UnicodeSet(*this);
+}
+
+UnicodeFunctor *UnicodeSet::cloneAsThawed() const {
+ return new UnicodeSet(*this, TRUE);
+}
+
/**
* Compares the specified object with this set for equality. Returns
* <tt>true</tt> if the two sets
for (int32_t i = 0; i < len; ++i) {
if (list[i] != o.list[i]) return FALSE;
}
- if (*strings != *o.strings) return FALSE;
+ if (hasStrings() != o.hasStrings()) { return FALSE; }
+ if (hasStrings() && *strings != *o.strings) return FALSE;
return TRUE;
}
-/**
- * Returns a copy of this object. All UnicodeMatcher objects have
- * to support cloning in order to allow classes using
- * UnicodeMatchers, such as Transliterator, to implement cloning.
- */
-UnicodeFunctor* UnicodeSet::clone() const {
- return new UnicodeSet(*this);
-}
-
/**
* Returns the hash code value for this set.
*
* @see Object#hashCode()
*/
int32_t UnicodeSet::hashCode(void) const {
- int32_t result = len;
+ uint32_t result = static_cast<uint32_t>(len);
for (int32_t i = 0; i < len; ++i) {
- result *= 1000003;
+ result *= 1000003u;
result += list[i];
}
- return result;
+ return static_cast<int32_t>(result);
}
//----------------------------------------------------------------
// Public API
//----------------------------------------------------------------
-/**
- * Make this object represent the range <code>start - end</code>.
- * If <code>end > start</code> then this object is set to an
- * an empty range.
- *
- * @param start first character in the set, inclusive
- * @rparam end last character in the set, inclusive
- */
-UnicodeSet& UnicodeSet::set(UChar32 start, UChar32 end) {
- clear();
- complement(start, end);
- return *this;
-}
-
/**
* Returns the number of elements in this set (its cardinality),
* Note than the elements of a set may include both individual
for (int32_t i = 0; i < count; ++i) {
n += getRangeEnd(i) - getRangeStart(i) + 1;
}
- return n + strings->size();
+ return n + stringsSize();
}
/**
* @return <tt>true</tt> if this set contains no elements.
*/
UBool UnicodeSet::isEmpty(void) const {
- return len == 1 && strings->size() == 0;
+ return len == 1 && !hasStrings();
}
/**
//for (;;) {
// if (c < list[++i]) break;
//}
+ if (bmpSet != NULL) {
+ return bmpSet->contains(c);
+ }
+ if (stringSpan != NULL) {
+ return stringSpan->contains(c);
+ }
if (c >= UNICODESET_HIGH) { // Don't need to check LOW bound
return FALSE;
}
int32_t i = findCodePoint(c);
- return ((i & 1) != 0); // return true if odd
+ return (UBool)(i & 1); // return true if odd
}
/**
// Return the smallest i such that c < list[i]. Assume
// list[len - 1] == HIGH and that c is legal (0..HIGH-1).
- if (c < list[0]) return 0;
+ if (c < list[0])
+ return 0;
// High runner test. c is often after the last range, so an
// initial check for this condition pays off.
- if (len >= 2 && c >= list[len-2]) return len-1;
int32_t lo = 0;
int32_t hi = len - 1;
+ if (lo >= hi || c >= list[hi-1])
+ return hi;
// invariant: c >= list[lo]
// invariant: c < list[hi]
for (;;) {
int32_t i = (lo + hi) >> 1;
- if (i == lo) return hi;
- if (c < list[i]) {
+ if (i == lo) {
+ break; // Found!
+ } else if (c < list[i]) {
hi = i;
} else {
lo = i;
}
}
- return 0; // To make compiler happy; never reached
+ return hi;
}
/**
if (s.length() == 0) return FALSE;
int32_t cp = getSingleCP(s);
if (cp < 0) {
- return strings->contains((void*) &s);
+ return stringsContains(s);
} else {
return contains((UChar32) cp);
}
return FALSE;
}
}
- if (!strings->containsAll(*c.strings)) return FALSE;
- return TRUE;
+ return !c.hasStrings() || (strings != nullptr && strings->containsAll(*c.strings));
}
/**
* @return true if the test condition is met
*/
UBool UnicodeSet::containsAll(const UnicodeString& s) const {
- UChar32 cp;
- for (int32_t i = 0; i < s.length(); i += UTF_CHAR_LENGTH(cp)) {
- cp = s.char32At(i);
- if (!contains(cp)) return FALSE;
- }
- return TRUE;
+ return (UBool)(span(s.getBuffer(), s.length(), USET_SPAN_CONTAINED) ==
+ s.length());
}
/**
return FALSE;
}
}
- if (!strings->containsNone(*c.strings)) return FALSE;
- return TRUE;
+ return strings == nullptr || !c.hasStrings() || strings->containsNone(*c.strings);
}
/**
* @return true if the test condition is met
*/
UBool UnicodeSet::containsNone(const UnicodeString& s) const {
- UChar32 cp;
- for (int32_t i = 0; i < s.length(); i += UTF_CHAR_LENGTH(cp)) {
- cp = s.char32At(i);
- if (contains(cp)) return FALSE;
- }
- return TRUE;
+ return (UBool)(span(s.getBuffer(), s.length(), USET_SPAN_NOT_CONTAINED) ==
+ s.length());
}
/**
* time zone month containment logic.)
*/
int32_t i;
- for (i=0; i<getRangeCount(); ++i) {
+ int32_t rangeCount=getRangeCount();
+ for (i=0; i<rangeCount; ++i) {
UChar32 low = getRangeStart(i);
UChar32 high = getRangeEnd(i);
if ((low & ~0xFF) == (high & ~0xFF)) {
return TRUE;
}
}
- if (strings->size() != 0) {
+ if (hasStrings()) {
for (i=0; i<strings->size(); ++i) {
const UnicodeString& s = *(const UnicodeString*)strings->elementAt(i);
//if (s.length() == 0) {
return U_MISMATCH;
}
} else {
- if (strings->size() != 0) { // try strings first
+ if (hasStrings()) { // try strings first
// might separate forward and backward loops later
// for now they are combined
return (UChar32)-1;
}
+/**
+ * Make this object represent the range <code>start - end</code>.
+ * If <code>end > start</code> then this object is set to an
+ * an empty range.
+ *
+ * @param start first character in the set, inclusive
+ * @rparam end last character in the set, inclusive
+ */
+UnicodeSet& UnicodeSet::set(UChar32 start, UChar32 end) {
+ clear();
+ complement(start, end);
+ return *this;
+}
+
/**
* Adds the specified range to this set if it is not already
* present. If this set already contains the specified range,
*/
UnicodeSet& UnicodeSet::add(UChar32 start, UChar32 end) {
if (pinCodePoint(start) < pinCodePoint(end)) {
- UChar32 range[3] = { start, end+1, UNICODESET_HIGH };
+ UChar32 limit = end + 1;
+ // Fast path for adding a new range after the last one.
+ // Odd list length: [..., lastStart, lastLimit, HIGH]
+ if ((len & 1) != 0) {
+ // If the list is empty, set lastLimit low enough to not be adjacent to 0.
+ UChar32 lastLimit = len == 1 ? -2 : list[len - 2];
+ if (lastLimit <= start && !isFrozen() && !isBogus()) {
+ if (lastLimit == start) {
+ // Extend the last range.
+ list[len - 2] = limit;
+ if (limit == UNICODESET_HIGH) {
+ --len;
+ }
+ } else {
+ list[len - 1] = start;
+ if (limit < UNICODESET_HIGH) {
+ if (ensureCapacity(len + 2)) {
+ list[len++] = limit;
+ list[len++] = UNICODESET_HIGH;
+ }
+ } else { // limit == UNICODESET_HIGH
+ if (ensureCapacity(len + 1)) {
+ list[len++] = UNICODESET_HIGH;
+ }
+ }
+ }
+ releasePattern();
+ return *this;
+ }
+ }
+ // This is slow. Could be much faster using findCodePoint(start)
+ // and modifying the list, dealing with adjacent & overlapping ranges.
+ UChar32 range[3] = { start, limit, UNICODESET_HIGH };
add(range, 2, 0);
} else if (start == end) {
add(start);
int32_t i = findCodePoint(pinCodePoint(c));
// already in set?
- if ((i & 1) != 0) return *this;
+ if ((i & 1) != 0 || isFrozen() || isBogus()) return *this;
// HIGH is 0x110000
// assert(list[len-1] == HIGH);
list[i] = c;
// if we touched the HIGH mark, then add a new one
if (c == (UNICODESET_HIGH - 1)) {
- ensureCapacity(len+1);
+ if (!ensureCapacity(len+1)) {
+ // ensureCapacity will mark the object as Bogus if OOM failure happens.
+ return *this;
+ }
list[len++] = UNICODESET_HIGH;
}
if (i > 0 && c == list[i-1]) {
// ^
// list[i]
- ensureCapacity(len+2);
-
- //for (int32_t k=len-1; k>=i; --k) {
- // list[k+2] = list[k];
- //}
- UChar32* src = list + len;
- UChar32* dst = src + 2;
- UChar32* srclimit = list + i;
- while (src > srclimit) *(--dst) = *(--src);
+ if (!ensureCapacity(len+2)) {
+ // ensureCapacity will mark the object as Bogus if OOM failure happens.
+ return *this;
+ }
+ UChar32 *p = list + i;
+ uprv_memmove(p + 2, p, (len - i) * sizeof(*p));
list[i] = c;
list[i+1] = c+1;
len += 2;
}
#endif
- pat.truncate(0);
+ releasePattern();
return *this;
}
* @return the modified set, for chaining
*/
UnicodeSet& UnicodeSet::add(const UnicodeString& s) {
- if (s.length() == 0) return *this;
+ if (s.length() == 0 || isFrozen() || isBogus()) return *this;
int32_t cp = getSingleCP(s);
if (cp < 0) {
- if (!strings->contains((void*) &s)) {
+ if (!stringsContains(s)) {
_add(s);
- pat.truncate(0);
+ releasePattern();
}
} else {
- add((UChar32)cp, (UChar32)cp);
+ add((UChar32)cp);
}
return *this;
}
* already be in 'strings'.
*/
void UnicodeSet::_add(const UnicodeString& s) {
- UnicodeString* t = new UnicodeString(s);
+ if (isFrozen() || isBogus()) {
+ return;
+ }
UErrorCode ec = U_ZERO_ERROR;
+ if (strings == nullptr && !allocateStrings(ec)) {
+ setToBogus();
+ return;
+ }
+ UnicodeString* t = new UnicodeString(s);
+ if (t == NULL) { // Check for memory allocation error.
+ setToBogus();
+ return;
+ }
strings->sortedInsert(t, compareUnicodeString, ec);
+ if (U_FAILURE(ec)) {
+ setToBogus();
+ delete t;
+ }
}
/**
*/
UnicodeSet& UnicodeSet::addAll(const UnicodeString& s) {
UChar32 cp;
- for (int32_t i = 0; i < s.length(); i += UTF_CHAR_LENGTH(cp)) {
+ for (int32_t i = 0; i < s.length(); i += U16_LENGTH(cp)) {
cp = s.char32At(i);
- add(cp, cp);
+ add(cp);
}
return *this;
}
return *this;
}
+UnicodeSet& UnicodeSet::removeAllStrings() {
+ if (!isFrozen() && hasStrings()) {
+ strings->removeAllElements();
+ releasePattern();
+ }
+ return *this;
+}
+
+
/**
* Makes a set from a multicharacter string. Thus "ch" => {"ch"}
* <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b>
*/
UnicodeSet* U_EXPORT2 UnicodeSet::createFrom(const UnicodeString& s) {
UnicodeSet *set = new UnicodeSet();
- set->add(s);
+ if (set != NULL) { // Check for memory allocation error.
+ set->add(s);
+ }
return set;
}
*/
UnicodeSet* U_EXPORT2 UnicodeSet::createFromAll(const UnicodeString& s) {
UnicodeSet *set = new UnicodeSet();
- set->addAll(s);
+ if (set != NULL) { // Check for memory allocation error.
+ set->addAll(s);
+ }
return set;
}
* @return the modified set, for chaining
*/
UnicodeSet& UnicodeSet::remove(const UnicodeString& s) {
- if (s.length() == 0) return *this;
+ if (s.length() == 0 || isFrozen() || isBogus()) return *this;
int32_t cp = getSingleCP(s);
if (cp < 0) {
- strings->removeElement((void*) &s);
- pat.truncate(0);
+ if (strings != nullptr && strings->removeElement((void*) &s)) {
+ releasePattern();
+ }
} else {
remove((UChar32)cp, (UChar32)cp);
}
* from this set.
*/
UnicodeSet& UnicodeSet::complement(UChar32 start, UChar32 end) {
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
if (pinCodePoint(start) <= pinCodePoint(end)) {
UChar32 range[3] = { start, end+1, UNICODESET_HIGH };
exclusiveOr(range, 2, 0);
}
- pat.truncate(0);
+ releasePattern();
return *this;
}
* <code>complement(MIN_VALUE, MAX_VALUE)</code>.
*/
UnicodeSet& UnicodeSet::complement(void) {
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
if (list[0] == UNICODESET_LOW) {
- ensureBufferCapacity(len-1);
- uprv_memcpy(buffer, list + 1, (len-1)*sizeof(UChar32));
+ uprv_memmove(list, list + 1, (size_t)(len-1)*sizeof(UChar32));
--len;
} else {
- ensureBufferCapacity(len+1);
- uprv_memcpy(buffer + 1, list, len*sizeof(UChar32));
- buffer[0] = UNICODESET_LOW;
+ if (!ensureCapacity(len+1)) {
+ return *this;
+ }
+ uprv_memmove(list + 1, list, (size_t)len*sizeof(UChar32));
+ list[0] = UNICODESET_LOW;
++len;
}
- swapBuffers();
- pat.truncate(0);
+ releasePattern();
return *this;
}
* @return this object, for chaining
*/
UnicodeSet& UnicodeSet::complement(const UnicodeString& s) {
- if (s.length() == 0) return *this;
+ if (s.length() == 0 || isFrozen() || isBogus()) return *this;
int32_t cp = getSingleCP(s);
if (cp < 0) {
- if (strings->contains((void*) &s)) {
+ if (stringsContains(s)) {
strings->removeElement((void*) &s);
} else {
_add(s);
}
- pat.truncate(0);
+ releasePattern();
} else {
complement((UChar32)cp, (UChar32)cp);
}
* @see #add(char, char)
*/
UnicodeSet& UnicodeSet::addAll(const UnicodeSet& c) {
- add(c.list, c.len, 0);
+ if ( c.len>0 && c.list!=NULL ) {
+ add(c.list, c.len, 0);
+ }
// Add strings in order
- for (int32_t i=0; i<c.strings->size(); ++i) {
- const UnicodeString* s = (const UnicodeString*)c.strings->elementAt(i);
- if (!strings->contains((void*) s)) {
- _add(*s);
+ if ( c.strings!=NULL ) {
+ for (int32_t i=0; i<c.strings->size(); ++i) {
+ const UnicodeString* s = (const UnicodeString*)c.strings->elementAt(i);
+ if (!stringsContains(*s)) {
+ _add(*s);
+ }
}
}
return *this;
* @param c set that defines which elements this set will retain.
*/
UnicodeSet& UnicodeSet::retainAll(const UnicodeSet& c) {
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
retain(c.list, c.len, 0);
- strings->retainAll(*c.strings);
+ if (hasStrings()) {
+ if (!c.hasStrings()) {
+ strings->removeAllElements();
+ } else {
+ strings->retainAll(*c.strings);
+ }
+ }
return *this;
}
* this set.
*/
UnicodeSet& UnicodeSet::removeAll(const UnicodeSet& c) {
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
retain(c.list, c.len, 2);
- strings->removeAll(*c.strings);
+ if (hasStrings() && c.hasStrings()) {
+ strings->removeAll(*c.strings);
+ }
return *this;
}
* this set.
*/
UnicodeSet& UnicodeSet::complementAll(const UnicodeSet& c) {
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
exclusiveOr(c.list, c.len, 0);
- for (int32_t i=0; i<c.strings->size(); ++i) {
- void* e = c.strings->elementAt(i);
- if (!strings->removeElement(e)) {
- _add(*(const UnicodeString*)e);
+ if (c.strings != nullptr) {
+ for (int32_t i=0; i<c.strings->size(); ++i) {
+ void* e = c.strings->elementAt(i);
+ if (strings == nullptr || !strings->removeElement(e)) {
+ _add(*(const UnicodeString*)e);
+ }
}
}
return *this;
* empty after this call returns.
*/
UnicodeSet& UnicodeSet::clear(void) {
+ if (isFrozen()) {
+ return *this;
+ }
list[0] = UNICODESET_HIGH;
len = 1;
- pat.truncate(0);
- strings->removeAllElements();
+ releasePattern();
+ if (strings != NULL) {
+ strings->removeAllElements();
+ }
+ // Remove bogus
+ fFlags = 0;
return *this;
}
return list[index*2 + 1] - 1;
}
-int32_t UnicodeSet::getStringCount() const {
- return strings->size();
-}
-
const UnicodeString* UnicodeSet::getString(int32_t index) const {
return (const UnicodeString*) strings->elementAt(index);
}
* possible space, without changing this object's value.
*/
UnicodeSet& UnicodeSet::compact() {
- if (len != capacity) {
- capacity = len;
- UChar32* temp = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
- uprv_memcpy(temp, list, len*sizeof(UChar32));
+ if (isFrozen() || isBogus()) {
+ return *this;
+ }
+ // Delete buffer first to defragment memory less.
+ if (buffer != stackList) {
+ uprv_free(buffer);
+ buffer = NULL;
+ bufferCapacity = 0;
+ }
+ if (list == stackList) {
+ // pass
+ } else if (len <= INITIAL_CAPACITY) {
+ uprv_memcpy(stackList, list, len * sizeof(UChar32));
uprv_free(list);
- list = temp;
+ list = stackList;
+ capacity = INITIAL_CAPACITY;
+ } else if ((len + 7) < capacity) {
+ // If we have more than a little unused capacity, shrink it to len.
+ UChar32* temp = (UChar32*) uprv_realloc(list, sizeof(UChar32) * len);
+ if (temp) {
+ list = temp;
+ capacity = len;
+ }
+ // else what the heck happened?! We allocated less memory!
+ // Oh well. We'll keep our original array.
+ }
+ if (strings != nullptr && strings->isEmpty()) {
+ delete strings;
+ strings = nullptr;
}
- uprv_free(buffer);
- buffer = NULL;
return *this;
}
+#ifdef DEBUG_SERIALIZE
+#include <stdio.h>
+#endif
+
+/**
+ * Deserialize constructor.
+ */
+UnicodeSet::UnicodeSet(const uint16_t data[], int32_t dataLen, ESerialization serialization,
+ UErrorCode &ec) {
+
+ if(U_FAILURE(ec)) {
+ setToBogus();
+ return;
+ }
+
+ if( (serialization != kSerialized)
+ || (data==NULL)
+ || (dataLen < 1)) {
+ ec = U_ILLEGAL_ARGUMENT_ERROR;
+ setToBogus();
+ return;
+ }
+
+ // bmp?
+ int32_t headerSize = ((data[0]&0x8000)) ?2:1;
+ int32_t bmpLength = (headerSize==1)?data[0]:data[1];
+
+ int32_t newLength = (((data[0]&0x7FFF)-bmpLength)/2)+bmpLength;
+#ifdef DEBUG_SERIALIZE
+ printf("dataLen %d headerSize %d bmpLen %d len %d. data[0]=%X/%X/%X/%X\n", dataLen,headerSize,bmpLength,newLength, data[0],data[1],data[2],data[3]);
+#endif
+ if(!ensureCapacity(newLength + 1)) { // +1 for HIGH
+ return;
+ }
+ // copy bmp
+ int32_t i;
+ for(i = 0; i< bmpLength;i++) {
+ list[i] = data[i+headerSize];
+#ifdef DEBUG_SERIALIZE
+ printf("<<16@%d[%d] %X\n", i+headerSize, i, list[i]);
+#endif
+ }
+ // copy smp
+ for(i=bmpLength;i<newLength;i++) {
+ list[i] = ((UChar32)data[headerSize+bmpLength+(i-bmpLength)*2+0] << 16) +
+ ((UChar32)data[headerSize+bmpLength+(i-bmpLength)*2+1]);
+#ifdef DEBUG_SERIALIZE
+ printf("<<32@%d+[%d] %lX\n", headerSize+bmpLength+i, i, list[i]);
+#endif
+ }
+ U_ASSERT(i == newLength);
+ if (i == 0 || list[i - 1] != UNICODESET_HIGH) {
+ list[i++] = UNICODESET_HIGH;
+ }
+ len = i;
+}
+
+
int32_t UnicodeSet::serialize(uint16_t *dest, int32_t destCapacity, UErrorCode& ec) const {
int32_t bmpLength, length, destLength;
for (bmpLength=0; bmpLength<length && this->list[bmpLength]<=0xffff; ++bmpLength) {}
length=bmpLength+2*(length-bmpLength);
}
-
+#ifdef DEBUG_SERIALIZE
+ printf(">> bmpLength%d length%d len%d\n", bmpLength, length, len);
+#endif
/* length: number of 16-bit array units */
if (length>0x7fff) {
/* there are only 15 bits for the length in the first serialized word */
const UChar32 *p;
int32_t i;
+#ifdef DEBUG_SERIALIZE
+ printf("writeHdr\n");
+#endif
*dest=(uint16_t)length;
if (length>bmpLength) {
*dest|=0x8000;
/* write the BMP part of the array */
p=this->list;
for (i=0; i<bmpLength; ++i) {
+#ifdef DEBUG_SERIALIZE
+ printf("writebmp: %x\n", (int)*p);
+#endif
*dest++=(uint16_t)*p++;
}
/* write the supplementary part of the array */
for (; i<length; i+=2) {
+#ifdef DEBUG_SERIALIZE
+ printf("write32: %x\n", (int)*p);
+#endif
*dest++=(uint16_t)(*p>>16);
*dest++=(uint16_t)*p++;
}
/**
* Allocate our strings vector and return TRUE if successful.
*/
-UBool UnicodeSet::allocateStrings() {
- UErrorCode ec = U_ZERO_ERROR;
- strings = new UVector(uhash_deleteUnicodeString,
- uhash_compareUnicodeString, ec);
- if (U_FAILURE(ec)) {
+UBool UnicodeSet::allocateStrings(UErrorCode &status) {
+ if (U_FAILURE(status)) {
+ return FALSE;
+ }
+ strings = new UVector(uprv_deleteUObject,
+ uhash_compareUnicodeString, 1, status);
+ if (strings == NULL) { // Check for memory allocation error.
+ status = U_MEMORY_ALLOCATION_ERROR;
+ return FALSE;
+ }
+ if (U_FAILURE(status)) {
delete strings;
strings = NULL;
return FALSE;
- }
+ }
return TRUE;
}
-void UnicodeSet::ensureCapacity(int32_t newLen) {
- if (newLen <= capacity)
- return;
- capacity = newLen + GROW_EXTRA;
- UChar32* temp = (UChar32*) uprv_malloc(sizeof(UChar32) * capacity);
- uprv_memcpy(temp, list, len*sizeof(UChar32));
- uprv_free(list);
+int32_t UnicodeSet::nextCapacity(int32_t minCapacity) {
+ // Grow exponentially to reduce the frequency of allocations.
+ if (minCapacity < INITIAL_CAPACITY) {
+ return minCapacity + INITIAL_CAPACITY;
+ } else if (minCapacity <= 2500) {
+ return 5 * minCapacity;
+ } else {
+ int32_t newCapacity = 2 * minCapacity;
+ if (newCapacity > MAX_LENGTH) {
+ newCapacity = MAX_LENGTH;
+ }
+ return newCapacity;
+ }
+}
+
+bool UnicodeSet::ensureCapacity(int32_t newLen) {
+ if (newLen > MAX_LENGTH) {
+ newLen = MAX_LENGTH;
+ }
+ if (newLen <= capacity) {
+ return true;
+ }
+ int32_t newCapacity = nextCapacity(newLen);
+ UChar32* temp = (UChar32*) uprv_malloc(newCapacity * sizeof(UChar32));
+ if (temp == NULL) {
+ setToBogus(); // set the object to bogus state if an OOM failure occurred.
+ return false;
+ }
+ // Copy only the actual contents.
+ uprv_memcpy(temp, list, len * sizeof(UChar32));
+ if (list != stackList) {
+ uprv_free(list);
+ }
list = temp;
+ capacity = newCapacity;
+ return true;
}
-void UnicodeSet::ensureBufferCapacity(int32_t newLen) {
- if (buffer != NULL && newLen <= bufferCapacity)
- return;
- if (buffer) {
+bool UnicodeSet::ensureBufferCapacity(int32_t newLen) {
+ if (newLen > MAX_LENGTH) {
+ newLen = MAX_LENGTH;
+ }
+ if (newLen <= bufferCapacity) {
+ return true;
+ }
+ int32_t newCapacity = nextCapacity(newLen);
+ UChar32* temp = (UChar32*) uprv_malloc(newCapacity * sizeof(UChar32));
+ if (temp == NULL) {
+ setToBogus();
+ return false;
+ }
+ // The buffer has no contents to be copied.
+ // It is always filled from scratch after this call.
+ if (buffer != stackList) {
uprv_free(buffer);
}
- bufferCapacity = newLen + GROW_EXTRA;
- buffer = (UChar32*) uprv_malloc(sizeof(UChar32) * bufferCapacity);
+ buffer = temp;
+ bufferCapacity = newCapacity;
+ return true;
}
/**
bufferCapacity = c;
}
+void UnicodeSet::setToBogus() {
+ clear(); // Remove everything in the set.
+ fFlags = kIsBogus;
+}
+
//----------------------------------------------------------------
// Implementation: Fundamental operators
//----------------------------------------------------------------
// polarity = 1, 2: x xor ~y == x === y
void UnicodeSet::exclusiveOr(const UChar32* other, int32_t otherLen, int8_t polarity) {
- ensureBufferCapacity(len + otherLen);
+ if (isFrozen() || isBogus()) {
+ return;
+ }
+ if (!ensureBufferCapacity(len + otherLen)) {
+ return;
+ }
+
int32_t i = 0, j = 0, k = 0;
UChar32 a = list[i++];
UChar32 b;
}
}
swapBuffers();
- pat.truncate(0);
+ releasePattern();
}
// polarity = 0 is normal: x union y
// polarity = 3: ~x union ~y
void UnicodeSet::add(const UChar32* other, int32_t otherLen, int8_t polarity) {
- ensureBufferCapacity(len + otherLen);
+ if (isFrozen() || isBogus() || other==NULL) {
+ return;
+ }
+ if (!ensureBufferCapacity(len + otherLen)) {
+ return;
+ }
+
int32_t i = 0, j = 0, k = 0;
UChar32 a = list[i++];
UChar32 b = other[j++];
buffer[k++] = UNICODESET_HIGH; // terminate
len = k;
swapBuffers();
- pat.truncate(0);
+ releasePattern();
}
// polarity = 0 is normal: x intersect y
// polarity = 3: ~x intersect ~y
void UnicodeSet::retain(const UChar32* other, int32_t otherLen, int8_t polarity) {
- ensureBufferCapacity(len + otherLen);
+ if (isFrozen() || isBogus()) {
+ return;
+ }
+ if (!ensureBufferCapacity(len + otherLen)) {
+ return;
+ }
+
int32_t i = 0, j = 0, k = 0;
UChar32 a = list[i++];
UChar32 b = other[j++];
buffer[k++] = UNICODESET_HIGH; // terminate
len = k;
swapBuffers();
- pat.truncate(0);
+ releasePattern();
}
/**
void UnicodeSet::_appendToPat(UnicodeString& buf, const UnicodeString& s, UBool
escapeUnprintable) {
UChar32 cp;
- for (int32_t i = 0; i < s.length(); i += UTF_CHAR_LENGTH(cp)) {
+ for (int32_t i = 0; i < s.length(); i += U16_LENGTH(cp)) {
_appendToPat(buf, cp = s.char32At(i), escapeUnprintable);
}
}
break;
default:
// Escape whitespace
- if (uprv_isRuleWhiteSpace(c)) {
+ if (PatternProps::isWhiteSpace(c)) {
buf.append(BACKSLASH);
}
break;
* is one. Otherwise it will be generated.
*/
UnicodeString& UnicodeSet::_toPattern(UnicodeString& result,
- UBool escapeUnprintable) const {
- if (pat.length() > 0) {
+ UBool escapeUnprintable) const
+{
+ if (pat != NULL) {
int32_t i;
int32_t backslashCount = 0;
- for (i=0; i<pat.length(); ) {
- UChar32 c = pat.char32At(i);
- i += UTF_CHAR_LENGTH(c);
+ for (i=0; i<patLen; ) {
+ UChar32 c;
+ U16_NEXT(pat, i, patLen, c);
if (escapeUnprintable && ICU_Utility::isUnprintable(c)) {
// If the unprintable character is preceded by an odd
// number of backslashes, then it has been escaped.
* will produce another set that is equal to this one.
*/
UnicodeString& UnicodeSet::toPattern(UnicodeString& result,
- UBool escapeUnprintable) const {
+ UBool escapeUnprintable) const
+{
result.truncate(0);
return _toPattern(result, escapeUnprintable);
}
* passed to applyPattern().
*/
UnicodeString& UnicodeSet::_generatePattern(UnicodeString& result,
- UBool escapeUnprintable) const {
+ UBool escapeUnprintable) const
+{
result.append(SET_OPEN);
// // Check against the predefined categories. We implicitly build
}
}
- for (int32_t i = 0; i<strings->size(); ++i) {
- result.append(OPEN_BRACE);
- _appendToPat(result,
- *(const UnicodeString*) strings->elementAt(i),
- escapeUnprintable);
- result.append(CLOSE_BRACE);
+ if (strings != nullptr) {
+ for (int32_t i = 0; i<strings->size(); ++i) {
+ result.append(OPEN_BRACE);
+ _appendToPat(result,
+ *(const UnicodeString*) strings->elementAt(i),
+ escapeUnprintable);
+ result.append(CLOSE_BRACE);
+ }
}
return result.append(SET_CLOSE);
}
+/**
+* Release existing cached pattern
+*/
+void UnicodeSet::releasePattern() {
+ if (pat) {
+ uprv_free(pat);
+ pat = NULL;
+ patLen = 0;
+ }
+}
+
+/**
+* Set the new pattern to cache.
+*/
+void UnicodeSet::setPattern(const char16_t *newPat, int32_t newPatLen) {
+ releasePattern();
+ pat = (UChar *)uprv_malloc((newPatLen + 1) * sizeof(UChar));
+ if (pat) {
+ patLen = newPatLen;
+ u_memcpy(pat, newPat, patLen);
+ pat[patLen] = 0;
+ }
+ // else we don't care if malloc failed. This was just a nice cache.
+ // We can regenerate an equivalent pattern later when requested.
+}
+
+UnicodeFunctor *UnicodeSet::freeze() {
+ if(!isFrozen() && !isBogus()) {
+ compact();
+
+ // Optimize contains() and span() and similar functions.
+ if (hasStrings()) {
+ stringSpan = new UnicodeSetStringSpan(*this, *strings, UnicodeSetStringSpan::ALL);
+ if (stringSpan == nullptr) {
+ setToBogus();
+ return this;
+ } else if (!stringSpan->needsStringSpanUTF16()) {
+ // All strings are irrelevant for span() etc. because
+ // all of each string's code points are contained in this set.
+ // Do not check needsStringSpanUTF8() because UTF-8 has at most as
+ // many relevant strings as UTF-16.
+ // (Thus needsStringSpanUTF8() implies needsStringSpanUTF16().)
+ delete stringSpan;
+ stringSpan = NULL;
+ }
+ }
+ if (stringSpan == NULL) {
+ // No span-relevant strings: Optimize for code point spans.
+ bmpSet=new BMPSet(list, len);
+ if (bmpSet == NULL) { // Check for memory allocation error.
+ setToBogus();
+ }
+ }
+ }
+ return this;
+}
+
+int32_t UnicodeSet::span(const UChar *s, int32_t length, USetSpanCondition spanCondition) const {
+ if(length>0 && bmpSet!=NULL) {
+ return (int32_t)(bmpSet->span(s, s+length, spanCondition)-s);
+ }
+ if(length<0) {
+ length=u_strlen(s);
+ }
+ if(length==0) {
+ return 0;
+ }
+ if(stringSpan!=NULL) {
+ return stringSpan->span(s, length, spanCondition);
+ } else if(hasStrings()) {
+ uint32_t which= spanCondition==USET_SPAN_NOT_CONTAINED ?
+ UnicodeSetStringSpan::FWD_UTF16_NOT_CONTAINED :
+ UnicodeSetStringSpan::FWD_UTF16_CONTAINED;
+ UnicodeSetStringSpan strSpan(*this, *strings, which);
+ if(strSpan.needsStringSpanUTF16()) {
+ return strSpan.span(s, length, spanCondition);
+ }
+ }
+
+ if(spanCondition!=USET_SPAN_NOT_CONTAINED) {
+ spanCondition=USET_SPAN_CONTAINED; // Pin to 0/1 values.
+ }
+
+ UChar32 c;
+ int32_t start=0, prev=0;
+ do {
+ U16_NEXT(s, start, length, c);
+ if(spanCondition!=contains(c)) {
+ break;
+ }
+ } while((prev=start)<length);
+ return prev;
+}
+
+int32_t UnicodeSet::spanBack(const UChar *s, int32_t length, USetSpanCondition spanCondition) const {
+ if(length>0 && bmpSet!=NULL) {
+ return (int32_t)(bmpSet->spanBack(s, s+length, spanCondition)-s);
+ }
+ if(length<0) {
+ length=u_strlen(s);
+ }
+ if(length==0) {
+ return 0;
+ }
+ if(stringSpan!=NULL) {
+ return stringSpan->spanBack(s, length, spanCondition);
+ } else if(hasStrings()) {
+ uint32_t which= spanCondition==USET_SPAN_NOT_CONTAINED ?
+ UnicodeSetStringSpan::BACK_UTF16_NOT_CONTAINED :
+ UnicodeSetStringSpan::BACK_UTF16_CONTAINED;
+ UnicodeSetStringSpan strSpan(*this, *strings, which);
+ if(strSpan.needsStringSpanUTF16()) {
+ return strSpan.spanBack(s, length, spanCondition);
+ }
+ }
+
+ if(spanCondition!=USET_SPAN_NOT_CONTAINED) {
+ spanCondition=USET_SPAN_CONTAINED; // Pin to 0/1 values.
+ }
+
+ UChar32 c;
+ int32_t prev=length;
+ do {
+ U16_PREV(s, 0, length, c);
+ if(spanCondition!=contains(c)) {
+ break;
+ }
+ } while((prev=length)>0);
+ return prev;
+}
+
+int32_t UnicodeSet::spanUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const {
+ if(length>0 && bmpSet!=NULL) {
+ const uint8_t *s0=(const uint8_t *)s;
+ return (int32_t)(bmpSet->spanUTF8(s0, length, spanCondition)-s0);
+ }
+ if(length<0) {
+ length=(int32_t)uprv_strlen(s);
+ }
+ if(length==0) {
+ return 0;
+ }
+ if(stringSpan!=NULL) {
+ return stringSpan->spanUTF8((const uint8_t *)s, length, spanCondition);
+ } else if(hasStrings()) {
+ uint32_t which= spanCondition==USET_SPAN_NOT_CONTAINED ?
+ UnicodeSetStringSpan::FWD_UTF8_NOT_CONTAINED :
+ UnicodeSetStringSpan::FWD_UTF8_CONTAINED;
+ UnicodeSetStringSpan strSpan(*this, *strings, which);
+ if(strSpan.needsStringSpanUTF8()) {
+ return strSpan.spanUTF8((const uint8_t *)s, length, spanCondition);
+ }
+ }
+
+ if(spanCondition!=USET_SPAN_NOT_CONTAINED) {
+ spanCondition=USET_SPAN_CONTAINED; // Pin to 0/1 values.
+ }
+
+ UChar32 c;
+ int32_t start=0, prev=0;
+ do {
+ U8_NEXT_OR_FFFD(s, start, length, c);
+ if(spanCondition!=contains(c)) {
+ break;
+ }
+ } while((prev=start)<length);
+ return prev;
+}
+
+int32_t UnicodeSet::spanBackUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const {
+ if(length>0 && bmpSet!=NULL) {
+ const uint8_t *s0=(const uint8_t *)s;
+ return bmpSet->spanBackUTF8(s0, length, spanCondition);
+ }
+ if(length<0) {
+ length=(int32_t)uprv_strlen(s);
+ }
+ if(length==0) {
+ return 0;
+ }
+ if(stringSpan!=NULL) {
+ return stringSpan->spanBackUTF8((const uint8_t *)s, length, spanCondition);
+ } else if(hasStrings()) {
+ uint32_t which= spanCondition==USET_SPAN_NOT_CONTAINED ?
+ UnicodeSetStringSpan::BACK_UTF8_NOT_CONTAINED :
+ UnicodeSetStringSpan::BACK_UTF8_CONTAINED;
+ UnicodeSetStringSpan strSpan(*this, *strings, which);
+ if(strSpan.needsStringSpanUTF8()) {
+ return strSpan.spanBackUTF8((const uint8_t *)s, length, spanCondition);
+ }
+ }
+
+ if(spanCondition!=USET_SPAN_NOT_CONTAINED) {
+ spanCondition=USET_SPAN_CONTAINED; // Pin to 0/1 values.
+ }
+
+ UChar32 c;
+ int32_t prev=length;
+ do {
+ U8_PREV_OR_FFFD(s, 0, length, c);
+ if(spanCondition!=contains(c)) {
+ break;
+ }
+ } while((prev=length)>0);
+ return prev;
+}
U_NAMESPACE_END
projects / apple / icu.git / blobdiff