def test_akkadian_syllabifier(self):
"""Test Akkadian syllabifier"""
syllabifier = AkkadianSyllabifier()
word = "epištašu"
syllables = syllabifier.syllabify(word)
target = ['e','piš','ta','šu']
self.assertEqual(syllables, target)
def test_akkadian_syllabifier(self):
"""Test Akkadian syllabifier"""
syllabifier = AkkadianSyllabifier()
word = "epištašu"
syllables = syllabifier.syllabify(word)
target = ['e','piš','ta','šu']
self.assertEqual(syllables, target)
class BoundForm(object):
"""
Return the bound form of a noun, suitable for adding suffixed pronouns.
"""
def __init__(self):
self.syllabifier = Syllabifier()
self.stemmer = Stemmer()
self.cv_patterner = CVPattern()
def get_bound_form(self, noun, gender):
"""Return bound form of nound, given its gender."""
syllables = self.syllabifier.syllabify(noun)
stem = self.stemmer.get_stem(noun, gender)
cv_pattern = self.cv_patterner.get_cv_pattern(stem)
# Based on Huehnergard Appendix 6.C.1: base in -VC
if [letter[0] for letter in cv_pattern[-2:]] == ['V', 'C'] or stem in ['nakr']:
# a. 2-syllable
if len(syllables) > 2:
# awīlum > awīl, nakrum > naker
if stem in ['nakr']:
return 'naker'
else:
return stem
# b. 1-syllable
elif len(syllables) > 1:
# bēlum > bēl
return stem
# c. abum, aḫum
if stem in ['ab', 'aḫ']:
return stem + 'i'
# Appendix 6.C.2: base in -C₁C₁
if cv_pattern[-1][:2] == cv_pattern[-2][:2]:
# a. 1-syllable
if 3 > len(syllables) > 1:
return stem + 'i'
# b. 2-syllable, -tt
if len(syllables) > 2 and cv_pattern[-1][2] + cv_pattern[-2][2] == 'tt':
return stem + 'i'
# c. 2-syllable, other
if len(syllables) > 2:
return stem[:-1]
# Appendix 6.C.3: base in -C₁C₂, C₂ ≠ t, i.e. pVrs
if cv_pattern[-1][0] == cv_pattern[-2][0] and cv_pattern[-1][1] != cv_pattern[-2][1]:
return stem[:-1] + stem[1] + stem[-1]
# Appendix 6.C.4: base in -Ct (fem.)
if cv_pattern[-1][2] == 't' and cv_pattern[-2][0] == 'C':
if len(syllables) > 2:
return stem + 'i'
# Need to deal with fem. Ptcpl. māḫirtum -> māḫirat
if len(syllables) > 1:
# These are case by case
if stem in ['qīšt']:
return stem + 'i'
if stem in ['mārt']:
return stem[:-1] + stem[1] + stem[-1]
def find_stress(self, word):
"""
Find the stressed syllable in a word.
The general logic follows Huehnergard 3rd edition (pgs. 3-4):
(a) Light: ending in a short vowel: e.g., -a, -ba
(b) Heavy: ending in a long vowel marked with a macron, or in a
short vowel plus a consonant: e.g., -ā, -bā, -ak, -bak
(c) Ultraheavy: ending in a long vowel marked with a circumflex,
in any long vowel plus a consonant: e.g., -â, -bâ, -āk, -bāk, -âk, -bâk.
(a) If the last syllable is ultraheavy, it bears the stress.
(b) Otherwise, stress falls on the last non-final heavy or ultraheavy syllable.
(c) Words that contain no non-final heavy or ultraheavy syllables have the
stress fall on the first syllable.
:param word: a string (or list) in Akkadian
:return: a list of syllables with stressed syllable surrounded by "[]"
"""
syllabifier = Syllabifier()
if type(word) is str:
word = syllabifier.syllabify(word)
syllables_stress = []
for i, syllable in enumerate(word):
# Enumerate over the syllables and mark them for length
# We check each type of length by looking at the length of the
# syllable and verifying rules based on character length.
# Ultraheavy:
# -â, -bâ, -āk, -bāk, -âk, -bâk.
if len(syllable) == 1:
if self._is_circumflex_vowel(syllable):
syllables_stress.append((syllable, "Ultraheavy"))
continue
elif len(syllable) == 2:
if self._is_consonant(
syllable[0]) and self._is_circumflex_vowel(
syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
if (self._is_macron_vowel(syllable[0]) or self._is_circumflex_vowel(syllable[0])) \
and self._is_consonant(syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
elif len(syllable) == 3:
if self._is_macron_vowel(
syllable[1]) or self._is_circumflex_vowel(syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
# Heavy:
# -ā, -bā, -ak, -bak
if len(syllable) == 1:
if self._is_macron_vowel(syllable):
syllables_stress.append((syllable, "Heavy"))
continue
elif len(syllable) == 2:
if self._is_consonant(syllable[0]) and self._is_macron_vowel(
syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
if self._is_short_vowel(syllable[0]) and self._is_consonant(
syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
elif len(syllable) == 3:
if self._is_short_vowel(syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
# Light:
# -a, -ba
if len(syllable) == 1:
if self._is_short_vowel(syllable):
syllables_stress.append((syllable, "Light"))
continue
elif len(syllable) == 2:
if self._is_consonant(syllable[0]) and self._is_short_vowel(
syllable[1]):
syllables_stress.append((syllable, "Light"))
continue
# It's easier to find stress backwards
syllables_stress = syllables_stress[::-1]
syllables = []
found_stress = 0
for i, syllable in enumerate(syllables_stress):
# If we've found the stressed syllable just append the next syllable
if found_stress:
syllables.append(syllable[0])
continue
# Rule (a)
elif syllable[1] == "Ultraheavy" and i == 0:
syllables.append("[{}]".format(syllable[0]))
found_stress = 1
continue
# Rule (b)
elif syllable[1] in ['Ultraheavy', 'Heavy'] and i > 0:
syllables.append("[{}]".format(syllable[0]))
found_stress = 1
continue
# Final 'Heavy' syllable, gets no stress
elif syllable[1] == 'Heavy' and i == 0:
syllables.append(syllable[0])
continue
# Light syllable gets no stress
elif syllable[1] == "Light":
syllables.append(syllable[0])
continue
# Reverse the list again
syllables = syllables[::-1]
# If we still haven't found stress then rule (c) applies
# Rule (c)
if not found_stress:
syllables[0] = "[{}]".format(syllables[0])
return syllables
def __init__(self):
self.syllabifier = Syllabifier()
self.stemmer = Stemmer()
self.cv_patterner = CVPattern()
def find_stress(self, word):
"""
Find the stressed syllable in a word.
The general logic follows Huehnergard 3rd edition (pgs. 3-4):
(a) Light: ending in a short vowel: e.g., -a, -ba
(b) Heavy: ending in a long vowel marked with a macron, or in a
short vowel plus a consonant: e.g., -ā, -bā, -ak, -bak
(c) Ultraheavy: ending in a long vowel marked with a circumflex,
in any long vowel plus a consonant: e.g., -â, -bâ, -āk, -bāk, -âk, -bâk.
(a) If the last syllable is ultraheavy, it bears the stress.
(b) Otherwise, stress falls on the last non-final heavy or ultraheavy syllable.
(c) Words that contain no non-final heavy or ultraheavy syllables have the
stress fall on the first syllable.
:param word: a string (or list) in Akkadian
:return: a list of syllables with stressed syllable surrounded by "[]"
"""
syllabifier = Syllabifier()
if type(word) is str:
word = syllabifier.syllabify(word)
syllables_stress = []
for i, syllable in enumerate(word):
# Enumerate over the syllables and mark them for length
# We check each type of length by looking at the length of the
# syllable and verifying rules based on character length.
# Ultraheavy:
# -â, -bâ, -āk, -bāk, -âk, -bâk.
if len(syllable) == 1:
if self._is_circumflex_vowel(syllable):
syllables_stress.append((syllable, "Ultraheavy"))
continue
elif len(syllable) == 2:
if self._is_consonant(syllable[0]) and self._is_circumflex_vowel(syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
if (self._is_macron_vowel(syllable[0]) or self._is_circumflex_vowel(syllable[0])) \
and self._is_consonant(syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
elif len(syllable) == 3:
if self._is_macron_vowel(syllable[1]) or self._is_circumflex_vowel(syllable[1]):
syllables_stress.append((syllable, "Ultraheavy"))
continue
# Heavy:
# -ā, -bā, -ak, -bak
if len(syllable) == 1:
if self._is_macron_vowel(syllable):
syllables_stress.append((syllable, "Heavy"))
continue
elif len(syllable) == 2:
if self._is_consonant(syllable[0]) and self._is_macron_vowel(syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
if self._is_short_vowel(syllable[0]) and self._is_consonant(syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
elif len(syllable) == 3:
if self._is_short_vowel(syllable[1]):
syllables_stress.append((syllable, "Heavy"))
continue
# Light:
# -a, -ba
if len(syllable) == 1:
if self._is_short_vowel(syllable):
syllables_stress.append((syllable, "Light"))
continue
elif len(syllable) == 2:
if self._is_consonant(syllable[0]) and self._is_short_vowel(syllable[1]):
syllables_stress.append((syllable, "Light"))
continue
# It's easier to find stress backwards
syllables_stress = syllables_stress[::-1]
syllables = []
found_stress = 0
for i, syllable in enumerate(syllables_stress):
# If we've found the stressed syllable just append the next syllable
if found_stress:
syllables.append(syllable[0])
continue
# Rule (a)
elif syllable[1] == "Ultraheavy" and i == 0:
syllables.append("[{}]".format(syllable[0]))
found_stress = 1
continue
# Rule (b)
elif syllable[1] in ['Ultraheavy', 'Heavy'] and i > 0:
syllables.append("[{}]".format(syllable[0]))
found_stress = 1
continue
# Final 'Heavy' syllable, gets no stress
elif syllable[1] == 'Heavy' and i == 0:
syllables.append(syllable[0])
continue
# Light syllable gets no stress
elif syllable[1] == "Light":
syllables.append(syllable[0])
continue
# Reverse the list again
syllables = syllables[::-1]
# If we still haven't found stress then rule (c) applies
# Rule (c)
if not found_stress:
syllables[0] = "[{}]".format(syllables[0])
return syllables