Python Base.explode方法代码示例

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def syllableMatches(syl, form):
	""" eg. syllableMatches('rte', '[V]VCe')
	capital 'V' or 'C' match vowels and consonants respectively
	letters in []'s shows optional letters. checks from the end of the word"""
	# FIXME this is not necessarily done on a syllable by syllable basis. sometimes it
	# can overlap boundaries
	sylMatches = False

	# better handling of 'ng' and other double letters
	syl = Base.explode(syl)
	form = Base.explode(form)

	syl = syl[::-1]
	form = form[::-1]

	#FIXME need to write test about if form longer than syl has correct behavior
	#FIXME optional '[]' letters should not increment i
	inBrackets = False
	j = 0

	if len(syl) > 0 and len(syl) >= len(form):
		for i in range(len(form)):
			if i <= j:
				if inBrackets:
					# FIXME not sure if there is really anything to do but ignore
					if form[i] == '[':
						inBrackets = False
						j += 1
				else:
					if form[i] == 'V' and Alphabet.isVowel(syl[j]):
						sylMatches = True
						j += 1
					elif form[i] == 'C' and Alphabet.isConsonant(syl[j]):
						sylMatches = True
						j += 1
					elif form[i] == syl[j]:
						#FIXME this may have some false positives
						sylMatches = True
						j += 1
					elif form[i] == ']':
						# we are reversed, so close brackets = open brackets
						inBrackets = True
					else:
						sylMatches = False
						break
			else:
				break
	return sylMatches

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def apostrophePurpose(word):
	"""is the apostrophe being used for gemination, separate 'n' and 'g', etc."""
	exp = Base.explode(word)
	purpose = -1
	for i in range(len(exp)):
		if i > 0 and exp[i] == '\'':
			if i < len(exp) - 1:
				if Alphabet.isVowel(exp[i - 1]):
					if Alphabet.isVowel(exp[i + 1]):
						purpose = APOS_PREVENT_GEMMINATION
						break
					elif exp[i + 1] == 'r':
						purpose = APOS_DISRUPT_STRESS
						break
				else:
					if Alphabet.isVowel(exp[i + 1]):
						purpose = APOS_GEMINATION_MARKER
						break
					elif exp[i - 1] == 'n' and exp[i + 1] == 'g':
						purpose = APOS_NG_SEPARATOR
						break
					else:
						# FIXME need to test if a catch-all is appropriate. technically the only
						# other valid use of a \' is whenever auto-devoicing occurs. (stop + nasal || fric)
						#FIXME need to do research on autodevoicing to make sure this ^^ is acurate
						# FIXME will need to write a test to make sure cases without auto devoicing are not matched
						purpose = APOS_PREVENT_DEVOICING
						break
			else:
				purpose = APOS_SHORT_WORD
	return purpose

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def getVoicingPattern(word):
	vp = []
	exp = Base.explode(word)
	for i in range(len(exp)):
		vp.append(isVoiced(word, i))

	return vp

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def getSyllables(word):
	""" return a list of the syllables that make up word """
	syllables = []
	syl = []
	exp = Base.explode(word)

	for i in range(len(exp)):
		c = exp[i]
		syl.append(c)
		if i < len(exp) - 1:
			if Alphabet.isConsonant(c) and Alphabet.isConsonant(exp[i + 1]):
				syllables.append(syl)
				syl = []
	syllables.append(syl)

	syl = []
	syl2 = []
	for s in syllables:
		for i in range(len(s)):
			if Alphabet.isConsonant(s[i]) and (i > 0 and i < len(s) - 1):
				if Alphabet.isVowel(s[i - 1]) and Alphabet.isVowel(s[i + 1]):
					syl2.append(syl)
					syl = []
			syl.append(s[i])
		syl2.append(syl)
		syl = []
	return syl2

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def hasRhythmicLength(word, index):
	""" does the sylIndex-th syllable have rhythmic vowel length """
	exp = Base.explode(word)
	syl = Syllables.getSyllables(word)
	rl = getRhythmicVowelLengthPattern(word)
	rlexp = []
	for s in range(len(syl)):
		for r in range(len(syl[s])):
			rlexp.append(rl[s])
	return rlexp[index]

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def lSyllableMatches(syl, form):
	""" eg. syllableMatches('rte', '[V]VCe')
	capital 'V' or 'C' match vowels and consonants respectivly
	letters in []'s shows optional letters. checks from the start of the word"""
	# FIXME this is not necessarily done on a syllable by syllable basis. sometimes it
	# can overlap boundaries
	sylMatches = False

	# better handling of 'ng' and other double letters
	syl = Base.explode(syl)
	form = Base.explode(form)

	if len(syl) > 0:
		inBrackets = False
		j = 0
		for i in range(len(form)):
			if inBrackets:
				# FIXME not sure if there is really anything to do but ignore
				if form[i] == '[':
					inBrackets = False
					j += 1
			else:
				if form[i] == 'V' and Alphabet.isVowel(syl[j]):
					sylMatches = True
					j += 1
				elif form[i] == 'C' and Alphabet.isConsonant(syl[j]):
					sylMatches = True
					j += 1
				elif form[i] == syl[j]:
					#FIXME this may have some false positives
					sylMatches = True
					j += 1
				elif form[i] == ']':
					# we are reversed, so close brackets = open brackets
					inBrackets = True
				else:
					sylMatches = False
					break
	return sylMatches

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def getVoicingText(word):
	voi = ''
	exp = Base.explode(word)
	vpat = getVoicingPattern(word)

	for i in range(len(exp)):
		voi = voi + exp[i] + ': '
		if vpat[i]:
			voi += '+ , '
		else:
			voi += '- , '
	# remove trailing ','
	voi = voi[:-2]
	return voi

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def getAutoGemminationPattern(word):
	gempat = []
	exp = Base.explode(word)
	rl = getRhythmicVowelLengthPattern(word)
	for i in range(len(exp)):
		if i > 0 and i < len(exp) - 2:
			if Alphabet.isVowel(exp[i - 1]) and Alphabet.isConsonant(exp[i]) and Alphabet.isVowel(
					exp[i + 1]) and Alphabet.isVowel(exp[i + 2]):
				gempat.append(True)
			else:
				gempat.append(False)
		elif i > 0 and exp[i - 1] == 'e' and hasRhythmicLength(word, i - 1):
			gempat.append(True)
		else:
			gempat.append(False)
	return gempat

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def isVoiced(word, c):
	"""test position c to see if it is voiced"""
	# FIXME does not properly handle if char other than a stop or fricative is found at 'c'
	voiced = True
	exp = Base.explode(word)
	l = exp[c]
	if c == 0 and l == 's':
		voiced = False
	elif c == len(exp) - 1 and l == 'r':
		voiced = False
	elif Alphabet.isVoicelessFricative(l):
		voiced = False
	elif Alphabet.isVoicelessNasal(l):
		voiced = False
	elif Alphabet.isVoicedFricative(l):
		if c > 0 and (Alphabet.isVoicelessFricative(exp[c - 1]) or Alphabet.isStop(exp[c - 1])):
			voiced = False
		elif c < len(exp) - 1 and Alphabet.isStop(exp[c + 1]):
			voiced = False
	elif Alphabet.isVoicedNasal(l) and c > 0 and (
		Alphabet.isVoicelessFricative(exp[c - 1]) or Alphabet.isStop(exp[c - 1])):
		voiced = False

	return voiced

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def applyPostbase(word, postbase):
	""" add a postbase to a word """
	#TODO would be cool if you could pass a list of postbases in here and have it do the "right thing"
	exp = Base.explode(word)
	keepStrongCfinal = False
	# @ symbol?
	dropVCfinal = False
	attachIrregular = False

	#keep the final consonant
	plus = string.find(postbase, '+')
	if plus > -1:
		postbase = postbase[:plus] + postbase[plus + 1:]

	# FIXME need to check against words that contain '-' as a part of the word
	# FIXME this might cause trouble with enclitics
	# remove the last consonant
	minus = string.find(postbase, '-')
	if minus > -1:
		postbase = postbase[:minus] + postbase[minus + 1:]
		if not Word.isVowel(exp[-1]):
			exp.pop(-1)

	# remove final 'e'
	tilde = string.find(postbase, '~')
	if tilde > -1:
		postbase = postbase[:tilde] + postbase[tilde + 1:]
		if exp[-1] == 'e':
			exp.pop(-1)

	# choose between letters in parenthesis
	paren = string.find(postbase, '(')
	if paren > -1:
		pl = parenLetter(word, postbase)
		#FIXME, what if multiple parens
		parenOpen = string.find(postbase, '(')
		parenClose = string.find(postbase, ')') + 1

		postbase = postbase[:parenOpen] + pl + postbase[parenClose:]

	# add gemination if needed
	#FIXME not tested on words that contain 2 \' ...does such a word exist?
	apos = string.find(postbase, '\'')
	if apos > -1:
		postbase = postbase[:apos] + postbase[apos + 1:]

		# FIXME this may indicate that there's something that needs tweaked about the syllablematches
		# function. A short base is defined as [C]VCe, currently this only tests the end of the word.
		# this should match VCe and CVCe only
		shortA = len(exp) == 3 and Syllables.syllableMatches(exp, 'VCe')
		shortB = len(exp) == 4 and Syllables.syllableMatches(exp, 'CVCe')
		if shortA or shortB:
			exp.pop(-1)
			if Syllables.syllableCount(exp) == 1:
				exp.append('\'')
		elif exp[-1] == 'e':
			exp.pop(-1)

	# velar dropping suffixes
	colon = string.find(postbase, ':')
	if colon > -1:
		testsuf = exp[-1] + postbase
		testExp = Base.explode(testsuf)
		colon = testExp.index(':')
		velar = testExp[colon + 1]
		testExp = testExp[:colon] + testExp[colon + 1:]

		if Syllables.syllableMatches(testExp, 'CV' + velar + 'V'): #FIXME might crash if word isn't long enough
			testExp = Base.explode(postbase)
			colon = testExp.index(':')
			testExp.pop(colon)
			testExp.pop(colon)
		else:
			testExp = Base.explode(postbase)
			colon = testExp.index(':')
			testExp.pop(colon)

		postbase = ''.join(testExp)

	if postbase[0] == '÷':
		keepStrongCfinal = True

	if string.find(postbase, ':') > -1:
		dropVelar = True

	if postbase[0] == '- -':
		dropVCfinal = True

	if postbase[0] == '%':
		attachIrregular = True

	word = ''.join(exp)
	word = word + postbase

	#cleanup for words that wind up not needing the \' for gemination because they are followed by 2 vowels
	#FIXME not tested on words that contain 2 \' ...does such a word exist
	exp = Base.explode(word)
	try:
		gemmarker = exp.index('\'')
	except ValueError:
#.........这里部分代码省略.........

# 需要导入模块: import Base [as 别名]
# 或者: from Base import explode [as 别名]
def syllableCount(word):
	"""get the number of syllables in word"""
	return len(getSyllables(Base.explode(word)))