def toNumber(self, lang, s):
if lang == "en":
try:
if s[-1] in ["a", "b"]:
amud = s[-1]
daf = int(s[:-1])
else:
amud = "a"
daf = int(s)
except ValueError:
raise InputError(u"Couldn't parse Talmud reference: {}".format(s))
if self.length and daf > self.length:
#todo: Catch this above and put the book name on it. Proably change Exception type.
raise InputError(u"{} exceeds max of {} dafs.".format(daf, self.length))
indx = daf * 2
if amud == "a":
indx -= 1
return indx
elif lang == "he":
num = re.split("[.:,\s]", s)[0]
daf = decode_hebrew_numeral(num) * 2
if s[-1] == ":" or (
s[-1] == u"\u05d1" #bet
and
((len(s) > 2 and s[-2] in ", ") # simple bet
or (len(s) > 4 and s[-3] == u'\u05e2') # ayin"bet
or (len(s) > 5 and s[-4] == u"\u05e2") # ayin''bet
)
):
return daf # amud B
return daf - 1
def test_encodes_and_decodes_correctly(self):
for x in range(1, 5000):
if x in (2000, 3000, 4000, 5000):
# known ambiguity with single thousands above 1000
pass
else:
assert x == h.decode_hebrew_numeral(h.encode_hebrew_numeral(x))
def test_encodes_and_decodes_correctly(self):
for x in range(1, 5000):
if x in (2000, 3000, 4000, 5000):
# known ambiguity with single thousands above 1000
pass
else:
assert x == h.decode_hebrew_numeral(h.encode_hebrew_numeral(x))
def toNumber(self, lang, s):
if lang == "en":
try:
if s[-1] in ["a", "b"]:
amud = s[-1]
daf = int(s[:-1])
else:
amud = "a"
daf = int(s)
except ValueError:
raise InputError(
u"Couldn't parse Talmud reference: {}".format(s))
if self.length and daf > self.length:
#todo: Catch this above and put the book name on it. Proably change Exception type.
raise InputError(u"{} exceeds max of {} dafs.".format(
daf, self.length))
indx = daf * 2
if amud == "a":
indx -= 1
return indx
elif lang == "he":
num = re.split("[.:,\s]", s)[0]
daf = decode_hebrew_numeral(num) * 2
if s[-1] == ":" or (
s[-1] == u"\u05d1" #bet
and ((len(s) > 2 and s[-2] in ", ") # simple bet
or (len(s) > 4 and s[-3] == u'\u05e2') # ayin"bet
or (len(s) > 5 and s[-4] == u"\u05e2") # ayin''bet
)):
return daf # amud B
return daf - 1
def parse_text():
"""
Takes the result of strip_tags() and parses into a level four data structure for easy upload
:return: Dictionary of books, depth 4.
"""
# initiate data structure and variables
full_text, chapters, verses, raw_text = {}, {}, {}, u''
current_book, current_chapter, current_verse = u'', u'', u''
to_parse = codecs.open('chizkuni_no-tags.txt', 'r', 'utf-8')
for line in to_parse:
# if new book add book to full_text.
if line.find(u'<book>') != -1:
# if this is the first book, do nothing
if current_book != u'':
# set up book and add it to full_text
verses[current_verse] = process_verse(raw_text)
chapters[current_chapter] = convertDictToArray(verses)
full_text[current_book] = convertDictToArray(chapters)
# reset verses and chapters
chapters, verses, raw_text = {}, {} ,u''
current_chapter, current_verse = u'', u''
# save the next book as current_book
current_book = removeAllStrings([u'\n', u'\r', u' '], to_parse.readline())
# if new chapter, add verses to previous chapter
elif line.find(u'<perek>') != -1:
# if first chapter, set current chapter but do nothing else
if current_chapter != u'':
verses[current_verse] = process_verse(raw_text)
chapters[current_chapter] = convertDictToArray(verses)
verses, raw_text = {}, u''
# get next chapter number
current_chapter = removeAllStrings([u'.', u'\n'], to_parse.readline())
current_chapter = decode_hebrew_numeral(current_chapter)
current_verse = u''
# if new verse, process raw text and add to verses
elif line.find(u'<pasuk>') != -1:
# add previous verse if not first verse
if current_verse != u'':
verses[current_verse] = process_verse(raw_text)
raw_text = u''
# get next verse number
current_verse = removeAllStrings([u'.', u'\n'], to_parse.readline())
current_verse = decode_hebrew_numeral(current_verse)
# don't include parsha tags
elif line.find(u'<parsha>') != -1:
continue
else:
# add to raw text
raw_text += line
# add final book
verses[current_verse] = process_verse(raw_text)
chapters[current_chapter] = convertDictToArray(verses)
full_text[current_book] = convertDictToArray(chapters)
to_parse.close()
return full_text
def toNumber(self, lang, s):
if lang == "en":
return int(s)
elif lang == "he":
return decode_hebrew_numeral(s)
def toNumber(self, lang, s):
if lang == "en":
return int(s)
elif lang == "he":
return decode_hebrew_numeral(s)