Golang SnowballWord.FitsInRV方法代码示例

// Step 2b is the removal of Verb suffixes in RV
// that do not begin with "i".
//
func step2b(word *snowballword.SnowballWord) bool {

	// Search for the longest among the following suffixes in RV.
	//
	suffix, suffixRunes := word.FirstSuffixIn(word.RVstart, len(word.RS),
		"eraIent", "assions", "erions", "assiez", "assent",
		"èrent", "eront", "erons", "eriez", "erait", "erais",
		"asses", "antes", "aIent", "âtes", "âmes", "ions",
		"erez", "eras", "erai", "asse", "ants", "ante", "ées",
		"iez", "era", "ant", "ait", "ais", "és", "ée", "ât",
		"ez", "er", "as", "ai", "é", "a",
	)

	switch suffix {
	case "ions":

		// Delete if in R2
		suffixLen := len(suffixRunes)
		if word.FitsInR2(suffixLen) {
			word.RemoveLastNRunes(suffixLen)
			return true
		}
		return false

	case "é", "ée", "ées", "és", "èrent", "er", "era",
		"erai", "eraIent", "erais", "erait", "eras", "erez",
		"eriez", "erions", "erons", "eront", "ez", "iez":

		// Delete
		word.RemoveLastNRunes(len(suffixRunes))
		return true

	case "âmes", "ât", "âtes", "a", "ai", "aIent",
		"ais", "ait", "ant", "ante", "antes", "ants", "as",
		"asse", "assent", "asses", "assiez", "assions":

		// Delete
		word.RemoveLastNRunes(len(suffixRunes))

		// If preceded by e (unicode code point 101), delete
		//
		idx := len(word.RS) - 1
		if idx >= 0 && word.RS[idx] == 101 && word.FitsInRV(1) {
			word.RemoveLastNRunes(1)
		}
		return true

	}
	return false
}

// Step 2a is the removal of Verb suffixes beginning
// with "i" in the RV region.
//
func step2a(word *snowballword.SnowballWord) bool {

	// Search for the longest among the following suffixes
	// in RV and if found, delete if preceded by a non-vowel.

	suffix, suffixRunes := word.FirstSuffixIn(word.RVstart, len(word.RS),
		"issantes", "issaIent", "issions", "issants", "issante",
		"iraIent", "issons", "issiez", "issent", "issant", "issait",
		"issais", "irions", "issez", "isses", "iront", "irons", "iriez",
		"irent", "irait", "irais", "îtes", "îmes", "isse", "irez",
		"iras", "irai", "ira", "ies", "ît", "it", "is", "ir", "ie", "i",
	)
	if suffix != "" {
		sLen := len(suffixRunes)
		idx := len(word.RS) - sLen - 1
		if idx >= 0 && word.FitsInRV(sLen+1) && isLowerVowel(word.RS[idx]) == false {
			word.RemoveLastNRunes(len(suffixRunes))
			return true
		}
	}
	return false
}

// Step 4 is the cleaning up of residual suffixes.
//
func step4(word *snowballword.SnowballWord) bool {

	hadChange := false

	if word.String() == "voudrion" {
		log.Println("...", word)
	}

	// If the word ends s (unicode code point 115),
	// not preceded by a, i, o, u, è or s, delete it.
	//
	if idx := len(word.RS) - 1; idx >= 1 && word.RS[idx] == 115 {
		switch word.RS[idx-1] {

		case 97, 105, 111, 117, 232, 115:

			// Do nothing, preceded by a, i, o, u, è or s
			return false

		default:
			word.RemoveLastNRunes(1)
			hadChange = true

		}
	}

	// Note: all the following are restricted to the RV region.

	// Search for the longest among the following suffixes in RV.
	//
	suffix, suffixRunes := word.FirstSuffixIn(word.RVstart, len(word.RS),
		"Ière", "ière", "Ier", "ier", "ion", "e", "ë",
	)

	switch suffix {
	case "":
		return hadChange
	case "ion":

		// Delete if in R2 and preceded by s or t in RV

		const sLen int = 3 // equivalently, len(suffixRunes)
		idx := len(word.RS) - sLen - 1
		if word.FitsInR2(sLen) && idx >= 0 && word.FitsInRV(sLen+1) {
			if word.RS[idx] == 115 || word.RS[idx] == 116 {
				word.RemoveLastNRunes(sLen)
				return true
			}
		}
		return hadChange

	case "ier", "ière", "Ier", "Ière":
		// Replace with i
		word.ReplaceSuffixRunes(suffixRunes, []rune("i"), true)
		return true

	case "e":
		word.RemoveLastNRunes(1)
		return true

	case "ë":

		// If preceded by gu (unicode code point 103 & 117), delete
		idx := len(word.RS) - 1
		if idx >= 2 && word.RS[idx-2] == 103 && word.RS[idx-1] == 117 {
			word.RemoveLastNRunes(1)
			return true
		}
		return hadChange
	}

	return true
}

//.........这里部分代码省略.........
			// If preceded by "iv", delete if in R2
			// (and if further preceded by "at", delete if in R2)
			newSuffix, newSuffixRunes := word.RemoveFirstSuffixIfIn(word.R2start, "iv")
			if newSuffix != "" {
				word.RemoveFirstSuffixIfIn(word.R2start, "at")
				return true
			}

			// If preceded by "eus", delete if in R2, else replace by "eux" if in R1
			newSuffix, newSuffixRunes = word.FirstSuffix("eus")
			if newSuffix != "" {
				newSuffixLen := len(newSuffixRunes)
				if word.FitsInR2(newSuffixLen) {
					word.RemoveLastNRunes(newSuffixLen)
				} else if word.FitsInR1(newSuffixLen) {
					word.ReplaceSuffixRunes(newSuffixRunes, []rune("eux"), true)
				}
				return true
			}

			// If preceded by abl or iqU, delete if in R2, otherwise,
			newSuffix, newSuffixRunes = word.FirstSuffix("abl", "iqU")
			if newSuffix != "" {
				newSuffixLen := len(newSuffixRunes)
				if word.FitsInR2(newSuffixLen) {
					word.RemoveLastNRunes(newSuffixLen)
				}
				return true
			}

			// If preceded by ièr or Ièr, replace by i if in RV
			newSuffix, newSuffixRunes = word.FirstSuffix("ièr", "Ièr")
			if newSuffix != "" {
				if word.FitsInRV(len(newSuffixRunes)) {
					word.ReplaceSuffixRunes(newSuffixRunes, []rune("i"), true)
				}
				return true
			}

			return true
		}

	case "ité", "ités":

		if isInR2 {

			// Delete if in R2
			word.RemoveLastNRunes(len(suffixRunes))

			// If preceded by "abil", delete if in R2, else replace by "abl"
			newSuffix, newSuffixRunes := word.FirstSuffix("abil")
			if newSuffix != "" {
				newSuffixLen := len(newSuffixRunes)
				if word.FitsInR2(newSuffixLen) {
					word.RemoveLastNRunes(newSuffixLen)
				} else {
					word.ReplaceSuffixRunes(newSuffixRunes, []rune("abl"), true)
				}
				return true
			}

			// If preceded by "ic", delete if in R2, else replace by "iqU"
			newSuffix, newSuffixRunes = word.FirstSuffix("ic")
			if newSuffix != "" {
				newSuffixLen := len(newSuffixRunes)
				if word.FitsInR2(newSuffixLen) {