OLD | NEW |
(Empty) | |
| 1 /* |
| 2 ********************************************************************** |
| 3 * Copyright (C) 2001-2008, International Business Machines |
| 4 * Corporation and others. All Rights Reserved. |
| 5 ********************************************************************** |
| 6 * Date Name Description |
| 7 * 07/26/01 aliu Creation. |
| 8 ********************************************************************** |
| 9 */ |
| 10 |
| 11 #include "unicode/utypes.h" |
| 12 |
| 13 #if !UCONFIG_NO_TRANSLITERATION |
| 14 |
| 15 #include "quant.h" |
| 16 #include "unicode/unistr.h" |
| 17 #include "util.h" |
| 18 |
| 19 U_NAMESPACE_BEGIN |
| 20 |
| 21 UOBJECT_DEFINE_RTTI_IMPLEMENTATION(Quantifier) |
| 22 |
| 23 Quantifier::Quantifier(UnicodeFunctor *adoptedMatcher, |
| 24 uint32_t _minCount, uint32_t _maxCount) { |
| 25 // assert(adopted != 0); |
| 26 // assert(minCount <= maxCount); |
| 27 matcher = adoptedMatcher; |
| 28 this->minCount = _minCount; |
| 29 this->maxCount = _maxCount; |
| 30 } |
| 31 |
| 32 Quantifier::Quantifier(const Quantifier& o) : |
| 33 UnicodeFunctor(o), |
| 34 UnicodeMatcher(o), |
| 35 matcher(o.matcher->clone()), |
| 36 minCount(o.minCount), |
| 37 maxCount(o.maxCount) |
| 38 { |
| 39 } |
| 40 |
| 41 Quantifier::~Quantifier() { |
| 42 delete matcher; |
| 43 } |
| 44 |
| 45 /** |
| 46 * Implement UnicodeFunctor |
| 47 */ |
| 48 UnicodeFunctor* Quantifier::clone() const { |
| 49 return new Quantifier(*this); |
| 50 } |
| 51 |
| 52 /** |
| 53 * UnicodeFunctor API. Cast 'this' to a UnicodeMatcher* pointer |
| 54 * and return the pointer. |
| 55 */ |
| 56 UnicodeMatcher* Quantifier::toMatcher() const { |
| 57 return (UnicodeMatcher*) this; |
| 58 } |
| 59 |
| 60 UMatchDegree Quantifier::matches(const Replaceable& text, |
| 61 int32_t& offset, |
| 62 int32_t limit, |
| 63 UBool incremental) { |
| 64 int32_t start = offset; |
| 65 uint32_t count = 0; |
| 66 while (count < maxCount) { |
| 67 int32_t pos = offset; |
| 68 UMatchDegree m = matcher->toMatcher()->matches(text, offset, limit, incr
emental); |
| 69 if (m == U_MATCH) { |
| 70 ++count; |
| 71 if (pos == offset) { |
| 72 // If offset has not moved we have a zero-width match. |
| 73 // Don't keep matching it infinitely. |
| 74 break; |
| 75 } |
| 76 } else if (incremental && m == U_PARTIAL_MATCH) { |
| 77 return U_PARTIAL_MATCH; |
| 78 } else { |
| 79 break; |
| 80 } |
| 81 } |
| 82 if (incremental && offset == limit) { |
| 83 return U_PARTIAL_MATCH; |
| 84 } |
| 85 if (count >= minCount) { |
| 86 return U_MATCH; |
| 87 } |
| 88 offset = start; |
| 89 return U_MISMATCH; |
| 90 } |
| 91 |
| 92 /** |
| 93 * Implement UnicodeMatcher |
| 94 */ |
| 95 UnicodeString& Quantifier::toPattern(UnicodeString& result, |
| 96 UBool escapeUnprintable) const { |
| 97 result.truncate(0); |
| 98 matcher->toMatcher()->toPattern(result, escapeUnprintable); |
| 99 if (minCount == 0) { |
| 100 if (maxCount == 1) { |
| 101 return result.append((UChar)63); /*?*/ |
| 102 } else if (maxCount == MAX) { |
| 103 return result.append((UChar)42); /***/ |
| 104 } |
| 105 // else fall through |
| 106 } else if (minCount == 1 && maxCount == MAX) { |
| 107 return result.append((UChar)43); /*+*/ |
| 108 } |
| 109 result.append((UChar)123); /*{*/ |
| 110 ICU_Utility::appendNumber(result, minCount); |
| 111 result.append((UChar)44); /*,*/ |
| 112 if (maxCount != MAX) { |
| 113 ICU_Utility::appendNumber(result, maxCount); |
| 114 } |
| 115 result.append((UChar)125); /*}*/ |
| 116 return result; |
| 117 } |
| 118 |
| 119 /** |
| 120 * Implement UnicodeMatcher |
| 121 */ |
| 122 UBool Quantifier::matchesIndexValue(uint8_t v) const { |
| 123 return (minCount == 0) || matcher->toMatcher()->matchesIndexValue(v); |
| 124 } |
| 125 |
| 126 /** |
| 127 * Implement UnicodeMatcher |
| 128 */ |
| 129 void Quantifier::addMatchSetTo(UnicodeSet& toUnionTo) const { |
| 130 if (maxCount > 0) { |
| 131 matcher->toMatcher()->addMatchSetTo(toUnionTo); |
| 132 } |
| 133 } |
| 134 |
| 135 /** |
| 136 * Implement UnicodeFunctor |
| 137 */ |
| 138 void Quantifier::setData(const TransliterationRuleData* d) { |
| 139 matcher->setData(d); |
| 140 } |
| 141 |
| 142 U_NAMESPACE_END |
| 143 |
| 144 #endif /* #if !UCONFIG_NO_TRANSLITERATION */ |
| 145 |
| 146 //eof |
OLD | NEW |