def add_ending(self, ending=u""):
""" Add an ending to the word, combining vowel-consonant
pairs if necessary """
# If ending begins with a vowel, the word must end with a consonant
# and this consonant-vowel pair should be combined
# If the word doesn't end with a consonant, raise a value error
if TamilLetter.is_vowel(ending[0]):
if TamilLetter.is_consonant(self.word[-1]):
# replace the last letter of the word with the consonant-vowel
# combination, then copy over the rest of the ending
self.word[-1] = TamilLetter.get_combination(self.word[-1], ending[0])
self.word += ending[1:]
# Unless word ends with a consonant, ending cannot start with a vowel
else:
raise ValueError(
"""Invalid word-ending pair - ending
can only start with a vowel if word ends with consonant"""
)
# In all other cases, simply add the ending to the word
self.word += ending
def validate(word=u""):
""" Asserts that a given word is valid """
# if input was a TamilWord object, extract out the word portion
if isinstance(word, TamilWord):
word = word.word
# simple test: every element of string must be valid Tamil character
for codepoint in word:
TamilLetter.assert_valid_letter(codepoint)
# TODO: implement method this more thoroughly
# TODO: check for pulli or combination_ending at beginning of word
return True
def validate(word=''):
""" Asserts that a given word is valid """
# if input was a TamilWord object, extract out the word portion
if isinstance(word, TamilWord):
word = word.word
# simple test: every element of string must be valid Tamil character
for codepoint in word:
TamilLetter.assert_valid_letter(codepoint)
# TODO: implement method this more thoroughly
# TODO: check for pulli or combination_ending at beginning of word
return True
def split_syllables(letters=[]):
""" Returns the syllables in a given word as a list """
# Generic algorithm:
# Each vowel and combination is its own syllable. Consonants and
# aytham get added to the end of the previous syllable
# ensure that the word is a valid word
TamilWord.validate("".join(letters))
# initialize empty list
syllables = []
# loop through letters in the word
for letter in letters:
# if letter is a vowel or combination, it gets its own syllable
if TamilLetter.is_combination(letter) or TamilLetter.is_vowel(letter):
syllables.append(letter)
# if codepoint is a consonant or aytham, add it to the end
# of the previously-added codepoint
elif TamilLetter.is_consonant(letter) or TamilLetter.is_aytham(letter):
# ensure that at least one character already exists
if len(syllables) > 0:
syllables[-1] = syllables[-1] + letter
# if the first letter is a consonant (probably b/c it' s a
# loanword), add it to the beginning of the string
else:
syllables.append(letter)
# if codepoint was neither a vowel, aytham, a pulli or a
# combination ending, an unexpected error has occurred
else:
raise Exception(
"""Unknown error: \'%s\' in word %s is neither
a vowel, consonant, combination or aytham"""
% (letter, "".join(letters))
)
return syllables
def split_syllables(letters=[]):
""" Returns the syllables in a given word as a list """
# Generic algorithm:
# Each vowel and combination is its own syllable. Consonants and
# aytham get added to the end of the previous syllable
# ensure that the word is a valid word
TamilWord.validate(''.join(letters))
# initialize empty list
syllables = []
# loop through letters in the word
for letter in letters:
# if letter is a vowel or combination, it gets its own syllable
if TamilLetter.is_combination(letter) or \
TamilLetter.is_vowel(letter):
syllables.append(letter)
# if codepoint is a consonant or aytham, add it to the end
# of the previously-added codepoint
elif TamilLetter.is_consonant(letter) or \
TamilLetter.is_aytham(letter):
# ensure that at least one character already exists
if len(syllables) > 0:
syllables[-1] = syllables[-1] + letter
# if the first letter is a consonant (probably b/c it' s a
# loanword), add it to the beginning of the string
else:
syllables.append(letter)
# if codepoint was neither a vowel, aytham, a pulli or a
# combination ending, an unexpected error has occurred
else:
raise Exception("""Unknown error: \'%s\' in word %s is neither
a vowel, consonant, combination or aytham""" %
(letter, ''.join(letters)))
def split_letters(word=u""):
""" Returns the graphemes (i.e. the Tamil characters)
in a given word as a list """
# ensure that the word is a valid word
TamilWord.validate(word)
# list (which will be returned to user)
letters = []
# a tuple of all combination endings and of all அ combinations
combination_endings = TamilLetter.get_combination_endings()
a_combinations = TamilLetter.get_combination_column(u"அ").values()
# loop through
for codepoint in word:
# if codepoint is an அ combination, a vowel, aytham or a space,
# add it to the list
if (
codepoint in a_combinations
or TamilLetter.is_whitespace(codepoint)
or TamilLetter.is_vowel(codepoint)
or TamilLetter.is_aytham(codepoint)
):
letters.append(codepoint)
# if codepoint is a combination ending or a pulli ('்'), add it
# to the end of the previously-added codepoint
elif codepoint in combination_endings or codepoint == TamilLetter.get_pulli():
# ensure that at least one character already exists
if len(letters) > 0:
letters[-1] = letters[-1] + codepoint
# otherwise raise an Error. However, validate_word()
# should catch this
else:
raise ValueError(
"""Unknown error: Combination ending %s
cannot be first character of a word"""
% (codepoint)
)
# if codepoint was neither a vowel, aytham, a pulli or a
# combination ending, an unexpected error has occurred
else:
raise ValueError(
"""Unknown error: Codepoint \'%s\' in word %s
is neither a vowel, consonant, combination or aytham"""
% (codepoint, word)
)
# TODO: Write extensive test cases for this
return letters
def add_ending(self, ending=''):
""" Add an ending to the word, combining vowel-consonant
pairs if necessary """
# If ending begins with a vowel, the word must end with a consonant
# and this consonant-vowel pair should be combined
# If the word doesn't end with a consonant, raise a value error
if TamilLetter.is_vowel(ending[0]):
if TamilLetter.is_consonant(self.word[-1]):
# replace the last letter of the word with the consonant-vowel
# combination, then copy over the rest of the ending
self.word[-1] = TamilLetter.get_combination(self.word[-1], \
ending[0])
self.word += ending[1:]
# Unless word ends with a consonant, ending cannot start with a vowel
else:
raise ValueError("""Invalid word-ending pair - ending
can only start with a vowel if word ends with consonant""")
# In all other cases, simply add the ending to the word
self.word += ending
def split_letters(word=''):
""" Returns the graphemes (i.e. the Tamil characters)
in a given word as a list """
# ensure that the word is a valid word
TamilWord.validate(word)
# list (which will be returned to user)
letters = []
# a tuple of all combination endings and of all அ combinations
combination_endings = TamilLetter.get_combination_endings()
a_combinations = list(TamilLetter.get_combination_column('அ').values())
# loop through
for codepoint in word:
# if codepoint is an அ combination, a vowel, aytham or a space,
# add it to the list
if codepoint in a_combinations or \
TamilLetter.is_whitespace(codepoint) or \
TamilLetter.is_vowel(codepoint) or \
TamilLetter.is_aytham(codepoint):
letters.append(codepoint)
# if codepoint is a combination ending or a pulli ('்'), add it
# to the end of the previously-added codepoint
elif codepoint in combination_endings or \
codepoint == TamilLetter.get_pulli():
# ensure that at least one character already exists
if len(letters) > 0:
letters[-1] = letters[-1] + codepoint
# otherwise raise an Error. However, validate_word()
# should catch this
else:
raise ValueError("""Unknown error: Combination ending %s
cannot be first character of a word""" % (codepoint))
# if codepoint was neither a vowel, aytham, a pulli or a
# combination ending, an unexpected error has occurred
else:
raise ValueError("""Unknown error: Codepoint \'%s\' in word %s
is neither a vowel, consonant, combination or aytham""" %
(codepoint, word))
# TODO: Write extensive test cases for this
return letters