def run_parser(text):
parsed_text=[]
cur_chapter = 1
cur_verse = 1
text=re.sub(ur'@20.{6}','',text)
chapters = re.split(ur'@10([^@]*)', text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
if chapter_num.strip() != '':
chapter_num = re.sub("[\(,\)]", "", chapter_num)
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
parsed_chapter = []
expand_list_assign(parsed_text, cur_chapter - 1, parsed_chapter)
psukim = re.split(ur'@11([^@]*)', chapter)
for pasuk_num, pasuk in zip(psukim[1::2], psukim[2::2]):
if pasuk.strip() != '':
parsed_verse = []
pasuk_num = re.sub("[\(,\)]", "", pasuk_num)
cur_verse = hebrew.heb_string_to_int(pasuk_num.strip())
expand_list_assign(parsed_chapter, cur_verse - 1, parsed_verse)
DH = pasuk.split(ur'@12')[1:]
for dibur_hamatchil in DH:
comments = dibur_hamatchil.split('@33')[1:]
comment1=""
for comment in comments:
if comment.strip() != '':
key = re.split(ur'@00', comment)
if len(key) > 1:
comment = '<b>' + key[0] + '</b>' + key[1]
comment1 = comment1 + comment
parsed_verse.append(comment1)
return parsed_text
def run_parser(text):
parasha_num = 0
cur_chapter = 1
cur_verse = 1
chapters = re.split(ur'@09([^@]*)', text)
parashot = [[], [], [], [], []]
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
if chapter_num.strip() != '':
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
names = ['Genesis', 'Exodus', 'Leviticus', 'Numbers', 'Deuteronomy']
parsed_chapter = []
if cur_chapter == 1:
parasha_num += 1
parasha_name = names[parasha_num - 1]
expand_list_assign(parashot[parasha_num - 1], cur_chapter - 1, parsed_chapter)
psukim = re.split(ur'@97([^@]*)', chapter)
for pasuk_num, pasuk in zip(psukim[1::2], psukim[2::2]):
if pasuk.strip() != '':
parsed_verse = []
pasuk_num = re.sub("[\(,\)]", "", pasuk_num)
cur_verse = hebrew.heb_string_to_int(pasuk_num.strip())
expand_list_assign(parsed_chapter, cur_verse - 1, parsed_verse)
comments = pasuk.split('@98')[1:]
for comment in comments:
if comment.strip() != '':
key = re.split(ur'@87', comment)
if len(key) > 1:
comment = '<b>' + key[0] + '</b>' + key[1]
parsed_verse.append(comment)
return parashot
def run_parser(text):
parsed_text = []
cur_chapter = 1
cur_verse = 1
text = re.sub(ur"@20.{6}", "", text)
chapters = re.split(ur"@10([^@]*)", text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
if chapter_num.strip() != "":
chapter_num = re.sub("[\(,\)]", "", chapter_num)
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
parsed_chapter = []
expand_list_assign(parsed_text, cur_chapter - 1, parsed_chapter)
psukim = re.split(ur"@11([^@]*)", chapter)
for pasuk_num, pasuk in zip(psukim[1::2], psukim[2::2]):
if pasuk.strip() != "":
parsed_verse = []
pasuk_num = re.sub("[\(,\)]", "", pasuk_num)
cur_verse = hebrew.heb_string_to_int(pasuk_num.strip())
expand_list_assign(parsed_chapter, cur_verse - 1, parsed_verse)
comments = pasuk.split("@33")[1:]
for comment in comments:
if comment.strip() != "":
key = re.split(ur"@00", comment)
if len(key) > 1:
comment = "<b>" + key[0] + "</b>" + key[1]
parsed_verse.append(comment)
return parsed_text
def run_parser():
print "running parser"
parsed_text = []
cur_chapter = 1
cur_verse = 1
#regex = re.compile(ur'@11(.*)@22',re.UNICODE)
with open("source/Radak_on_Genesis.txt", 'r') as filep:
file_text = filep.read()
ucd_text = unicode(file_text, 'utf-8').strip()
#get rid of some unhelpful markup
ucd_text = re.sub(ur'@11(.*?)@33', ur'@55\1', ucd_text)
ucd_text = re.sub(ur'@00([^@]*)\n', '', ucd_text)
ucd_text = ucd_text.replace(u'@44(שם)@55', u'(שם)')
#split according to chapter. Will also include the chapter letters in the results.
chapters = re.split(ur'@22([^@]*)', ucd_text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
if chapter_num.strip() != '':
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
parsed_chapter = []
expand_list_assign(parsed_text, cur_chapter - 1, parsed_chapter)
#now split on verse numbers, capturing the verse numbers as well
verses = re.split(ur'@44\(([\u0590-\u05ea]{1,2})\)', chapter)
for verse_num, verse in zip(verses[1::2], verses[2::2]):
if verse_num.strip() != '':
parsed_verse = []
cur_verse = hebrew.heb_string_to_int(verse_num.strip())
expand_list_assign(parsed_chapter, cur_verse - 1, parsed_verse)
comments = verse.split('@55')[1:]
for comment in comments:
if comment.strip() != '':
parsed_verse.append(comment)
pretty_print(parsed_text)
save_parsed_text(parsed_text)
def run_parser(text):
parasha_num = 0
cur_chapter = 1
cur_verse = 1
chapters = re.split(ur'@09([^@]*)', text)
parashot = [[], [], [], [], []]
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
if chapter_num.strip() != '':
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
names = [
'Genesis', 'Exodus', 'Leviticus', 'Numbers', 'Deuteronomy'
]
parsed_chapter = []
if cur_chapter == 1:
parasha_num += 1
parasha_name = names[parasha_num - 1]
expand_list_assign(parashot[parasha_num - 1], cur_chapter - 1,
parsed_chapter)
psukim = re.split(ur'@97([^@]*)', chapter)
for pasuk_num, pasuk in zip(psukim[1::2], psukim[2::2]):
if pasuk.strip() != '':
parsed_verse = []
pasuk_num = re.sub("[\(,\)]", "", pasuk_num)
cur_verse = hebrew.heb_string_to_int(pasuk_num.strip())
expand_list_assign(parsed_chapter, cur_verse - 1,
parsed_verse)
comments = pasuk.split('@98')[1:]
for comment in comments:
if comment.strip() != '':
key = re.split(ur'@87', comment)
if len(key) > 1:
comment = '<b>' + key[0] + '</b>' + key[1]
parsed_verse.append(comment)
return parashot
def search2(parsed, part):
for k, seif in enumerate(parsed):
for i, pasuk in enumerate(seif):
found = re.finditer(ur'@44[\[\(](.*?)[\]\)]@55(.*?)\.', pasuk)
for find in found:
daf = find.group(1)
if daf.strip().split(' ')[0] == u"מנחות" and len(
daf.strip().split(' ')) < 6:
if len(daf.strip().split(' ')) == 3:
daf = daf.strip().split(' ')[2]
elif len(daf.strip().split(' ')) == 2:
daf = daf.strip().split(' ')[1]
if daf[-1] == ".":
amud = "a"
elif daf[-1] == ":":
amud = "b"
daf_num = hebrew.heb_string_to_int(daf[0:-1])
#print daf_num, amud
elif daf.strip().split(' ')[0] == u"דף":
daf = daf.strip().split(' ')[1]
if daf[-1] == ".":
amud = "a"
elif daf[-1] == ":":
amud = "b"
daf_num = hebrew.heb_string_to_int(daf[0:-1])
#print daf_num, amud
elif ur"שם" not in daf and ur"דף" in daf:
#print daf
pass
else:
pass
#print daf
text = find.group(2)
try:
print str(k + 1), str(i + 1), daf_num, amud
found = matchobj(daf_num, amud, text)
line = found[1][0]
if line > 0:
#print "Rosh on {}".format(masechet), daf_num, amud, found[1][0], str(i+1), ",", str(j+1) + ",", str(k+1)
talmud = "{}".format(masechet) + "." + str(
daf_num) + amud + "." + str(line)
roash = "Rosh on {}".format(
masechet) + ", " + part + "." + str(
k + 1) + "." + str(1)
links.append(makeLink(talmud, roash))
except Exception as e:
print e
def parse(text):
old_num =0
dibbur =""
#simanim = re.finditer(ur'(@[0-9][0-9])\n?(@[0-9][0-9])(.*\n*)', text)
simanim = re.split("@77",text)
bayit_chadash = []
perek =[]
i=1
for siman in simanim:
simans = re.finditer("@11(.*)@33(.*)",siman)
for s in simans:
dibbur ="(" + str(i) + ")" + "<b>" + s.group(1) + '</b>'+ s.group(2)
print i
i = i +1
if "@22" not in siman:
perek.append(dibbur)
elif "@22" in siman:
#i = 1
num = re.findall("@22(.*)",siman) [0]
new_num = hebrew.heb_string_to_int(num.strip())
#print new_num
if new_num - old_num != 1:
for k in range(1,new_num - old_num):
bayit_chadash.append([])
old_num= new_num
bayit_chadash.append(perek)
perek =[]
perek.append(dibbur)
i=1
bayit_chadash.append(perek)
#print len(bayit_chadash)
return bayit_chadash[1:len(bayit_chadash)]
def search(text, shas):
for i, seif in enumerate(text):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))', siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)',"",siman)
start_of_siman = re.split(" ", start)
matching(start_of_siman, shas, i, j, index, daf, amud)
for match in linked:
lookfor = match.group(2)
tagged = re.split(" ", lookfor.strip())
daf_amud = re.split(ur' ', match.group(1).strip())
daf = hebrew.heb_string_to_int(daf_amud[1])
amud = daf_amud[2]
index = ((daf-2)*2)+1
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
if len(lookfor) < 5:
print "short", daf, amud
break
else:
matching(tagged, shas, i, j, index, daf, amud)
def search2(parsed):
for i,perek in enumerate(parsed):
for j, pasuk in enumerate(perek):
for k, seif in enumerate(pasuk):
found = re.finditer(ur'@44\[דף(.*?)\](.*?)\.', seif)
for find in found:
daf = find.group(1)
text = find.group(2)
if daf.strip().split(" ")[1] == u'ע"א':
amud = 'a'
elif daf.strip().split(" ")[1] == u'ע"ב':
amud = 'b'
new_daf = daf.strip().split(" ")[0]
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud
found = matchobj(daf_num, amud, text)
line = found[1][0]
if line >0:
#print "Rosh on {}".format(masechet), daf_num, amud, found[1][0], str(i+1), ",", str(j+1) + ",", str(k+1)
talmud = "{}".format(masechet) + "." + str(daf_num) + amud + "." + str(line)
roash = "Rosh on {}".format(masechet) +"." + str(i+1) + "." + str(j+1) + "." + str(k+1)
links.append(link(talmud,roash))
except KeyError:
pass
def parse(text):
old_num = 0
simanim = re.finditer(ur'@22\n*(.*)\n*@11(\n?.*)', text)
for siman in simanim:
#print siman.group(1)
new_num = hebrew.heb_string_to_int(siman.group(1).strip())
if new_num - old_num != 1:
print siman.group(1)
print new_num
old_num = new_num
print new_num
bet_yosef = []
simanim = re.split("@22", text)
for siman in simanim:
seif = []
dh = re.split("@66", siman)
i = 1
for text in dh:
bolded_dh = re.finditer(ur'@11(.*)@33(.*)', text)
for bold in bolded_dh:
new_dh = "[" + str(i) + "]" + "<b>" + bold.group(
1) + '</b>' + bold.group(2)
seif.append(new_dh)
i += 1
bet_yosef.append(seif)
print "length bet yosef", len(bet_yosef)
#print bet_yosef[len(bet_yosef)-1][0]
if len(bet_yosef[0]) < 2:
return bet_yosef[1:len(bet_yosef) - 1]
else:
return bet_yosef
def parse(text):
old_num =0
simanim = re.finditer(ur'@22\n*(.*)\n*@11(\n?.*)', text)
for siman in simanim:
si = siman.group(1)
num = re.split(" ", si.strip())[1]
num=re.sub("'","",num)
new_num = hebrew.heb_string_to_int(num.strip())
if new_num - old_num !=1:
print new_num
old_num = new_num
prisha=[]
simanim = re.split("@22", text)
for siman in simanim:
seif =[]
dh = re.split(ur"\(\S\S?\)]", siman)
print dh[0]
i = 1
for text in dh:
bolded_dh = re.finditer(ur'@11(.*)@33(.*)',text)
for bold in bolded_dh:
#new_dh = "{" + str(i) +"}" + "<b>" + bold.group(1) + '</b>' + bold.group(2)
new_dh = "<b>" + bold.group(1) + '</b>' + bold.group(2)
seif.append(new_dh)
i += 1
prisha.append(seif)
print "length prisha", len(prisha)
#print bet_yosef[len(bet_yosef)-1][0]
if len(prisha[0])<2:
return prisha[1:len(prisha)-1]
else:
return prisha
def search(text, shas):
for i, seif in enumerate(text):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))', siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)', "", siman)
start_of_siman = re.split(" ", start)
matching(start_of_siman, shas, i, j, index, daf, amud)
for match in linked:
lookfor = match.group(2)
tagged = re.split(" ", lookfor.strip())
daf_amud = re.split(ur' ', match.group(1).strip())
daf = hebrew.heb_string_to_int(daf_amud[1])
amud = daf_amud[2]
index = ((daf - 2) * 2) + 1
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
if len(lookfor) < 5:
print "short", daf, amud
break
else:
matching(tagged, shas, i, j, index, daf, amud)
def search1(text, shas):
for k, perek in enumerate(text):
for i, seif in enumerate(perek):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))',
siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)', "", siman)
start_of_siman = re.split(" ", start)
if 'index' in locals():
if index >= len(shas):
break
# print "line number: 203", daf, amud
matching1(start_of_siman, shas, i, j, k, index, daf,
amud)
for match in linked:
lookfor = match.group(2)
# print "lookfor is", lookfor
tagged = re.split(" ", lookfor.strip())
if len(tagged) <= 1:
break
daf_amud = re.split(ur' ', match.group(1).strip())
#print daf_amud[0]
if len(daf_amud) >= 2:
daf = re.sub(ur'[^א-ת]', "", daf_amud[1])
else:
# print "no daf "
break
# print daf
daf = hebrew.heb_string_to_int(daf)
if daf > len(shas) or len(daf_amud) < 3:
break
else:
# print len(daf_amud)
# print daf_amud
amud = daf_amud[2]
index = ((daf - 2) * 2) + 1
#if index > len(shas):
# break
if len(amud) < 3:
#print "short amud"
break
else:
#print amud
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
#print daf, amud
if index >= len(shas):
#print "short", daf, amud, lookfor
#return
pass
else:
#print "else"
# print "tagged is", tagged
matching1(tagged, shas, i, j, k, index, daf, amud)
def read_rashi():
for f in os.listdir(u'%s' % commentator):
if masechet_he in f:
pf = os.path.join(u'%s' % commentator, f)
print pf
split = re.split("_",f.strip())
if "_" in masechet_he:
daf_he = split[2]
amud_he = split[3][0]
else:
daf_he = split[1]
amud_he = split[2][0]
daf =hebrew.heb_string_to_int(daf_he)
if amud_he ==u'א':
amud= "a"
elif amud_he ==u'ב':
amud="b"
else:
print "we have a problam"
index = convert_daf_to_index(daf,amud)
print index
print daf
print amud
with open(pf, 'r') as filep:
file_text = filep.read()
list = re.split("\n",file_text)
for liner in list:
if "-" in liner or "–" in liner:
#print line
dh = re.split("(?:-|–)",liner)[0]
match(dh.decode('utf-8'),shas[index],index,liner.decode('utf-8'))
def parse(text):
old_num =0
simanim = re.finditer(ur'@22\n*(.*)\n*@11(\n?.*)', text)
for siman in simanim:
#print siman.group(1)
new_num = hebrew.heb_string_to_int(siman.group(1).strip())
if new_num - old_num !=1:
print siman.group(1)
print new_num
old_num = new_num
print new_num
bet_yosef=[]
simanim = re.split("@22", text)
for siman in simanim:
seif =[]
dh = re.split("@66", siman)
i = 1
for text in dh:
bolded_dh = re.finditer(ur'@11(.*)@33(.*)',text)
for bold in bolded_dh:
new_dh = "[" + str(i) +"]" + "<b>" + bold.group(1) + '</b>' + bold.group(2)
seif.append(new_dh)
i += 1
bet_yosef.append(seif)
print "length bet yosef", len(bet_yosef)
#print bet_yosef[len(bet_yosef)-1][0]
if len(bet_yosef[0])<2:
return bet_yosef[1:len(bet_yosef)-1]
else:
return bet_yosef
def search1(parsed, part):
for i, perek in enumerate(parsed):
for k, seif in enumerate(perek):
found = re.finditer(ur'@44\[דף(.*?)\](.*?)\.', seif)
for find in found:
daf = find.group(1)
text = find.group(2)
if daf.strip().split(" ")[1] == u'ע"א':
amud = 'a'
elif daf.strip().split(" ")[1] == u'ע"ב':
amud = 'b'
new_daf = daf.strip().split(" ")[0]
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud
found = matchobj(daf_num, amud, text)
line = found[1][0]
if line > 0:
#print "Rosh on {}".format(masechet), daf_num, amud, found[1][0], str(i+1), ",", str(j+1) + ",", str(k+1)
talmud = "{}".format(masechet) + "." + str(
daf_num) + amud + "." + str(line)
roash = "Rosh on {}".format(
masechet) + ", " + part + "." + str(
i + 1) + "." + str(k + 1)
links.append(link(talmud, roash))
except KeyError:
pass
def search(parsed):
for i, perek in enumerate(parsed):
for j, pasuk in enumerate(perek):
found = re.finditer(ur'\(דף(.*?)\)', pasuk)
for find in found:
daf = find.group(1)
#text = find.group(2)
if daf[len(daf) - 1] == '.':
#print daf
amud = 'a'
elif daf[len(daf) - 1] == ':':
amud = 'b'
new_daf = daf[0:len(daf.strip())].strip()
#print new_daf
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud + " " + str(i) + " " + str(j+1)
links.append(
link(
"{}".format(masechet) + "." + str(daf_num) + amud,
"Rosh on {}, Hilchot Seder Avodat Yom HaKippurim".
format(masechet) + "." + str(i) + "." +
str(j + 1)))
#links.append(link(
#match(daf_num, amud, text)
except KeyError:
pass
def read_rashi():
for f in os.listdir(u'%s' % commentator):
if masechet_he in f:
pf = os.path.join(u'%s' % commentator, f)
print pf
split = re.split("_", f.strip())
if "_" in masechet_he:
daf_he = split[2]
amud_he = split[3][0]
else:
daf_he = split[1]
amud_he = split[2][0]
daf = hebrew.heb_string_to_int(daf_he)
if amud_he == u'א':
amud = "a"
elif amud_he == u'ב':
amud = "b"
else:
print "we have a problam"
index = convert_daf_to_index(daf, amud)
print index
print daf
print amud
with open(pf, 'r') as filep:
file_text = filep.read()
list = re.split("\n", file_text)
for liner in list:
if "-" in liner or "–" in liner:
if commentator in "Rashi":
dh = re.split("(?:-|–)", liner)[0]
elif "Tosafot" in commentator:
dh = re.split(ur"\.", liner)[0]
match(dh.decode('utf-8'), shas[index], index,
liner.decode('utf-8'))
def search1(text, shas):
for k, perek in enumerate(text):
for i, seif in enumerate(perek):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))', siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)',"",siman)
start_of_siman = re.split(" ", start)
if 'index' in locals():
if index >= len(shas):
break
# print "line number: 203", daf, amud
matching1(start_of_siman, shas, i, j, k, index, daf, amud)
for match in linked:
lookfor = match.group(2)
# print "lookfor is", lookfor
tagged = re.split(" ", lookfor.strip())
if len(tagged)<=1:
break
daf_amud = re.split(ur' ', match.group(1).strip())
#print daf_amud[0]
if len(daf_amud) >=2:
daf = re.sub(ur'[^א-ת]',"",daf_amud[1])
else:
# print "no daf "
break
# print daf
daf = hebrew.heb_string_to_int(daf)
if daf > len(shas) or len(daf_amud) < 3:
break
else:
# print len(daf_amud)
# print daf_amud
amud = daf_amud[2]
index = ((daf-2)*2)+1
#if index > len(shas):
# break
if len(amud) < 3:
#print "short amud"
break
else:
#print amud
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
#print daf, amud
if index >= len(shas):
#print "short", daf, amud, lookfor
#return
pass
else:
#print "else"
# print "tagged is", tagged
matching1(tagged, shas, i, j, k, index, daf, amud)
def parse(text):
older_siman = 0
arbaturim=[]
tur = []
hilchos = re.split(ur'@00', text) #split to names of parts
for halacha in hilchos:
if len(halacha) >0:
halacha_name = halacha.splitlines()[0]
#print halacha_name #get the name of the part
simanim = re.finditer(ur'(@?[0-9]?[0-9]?@?[0-9]?[0-9]?)@22(.*)@11(.*)',halacha) #cut the text to simanim, get kletter of siman and tags to commentary
i = 1
for simans in simanim:
localbet_yosef = 0
siman = simans.group(2)
siman = re.sub(ur'[\(\[].*?[\)\]]',"", siman)
siman = re.sub(ur'[^\u05d0-\u05ea]',"", siman)
if len(siman)> 4:
# print simans.group(2)
#print simans.group(3)
pass
roman_siman = hebrew.heb_string_to_int(siman.strip())
bold = re.split(ur'@33',simans.group(3))
if len(bold) ==2:
text = simans.group(1) +"<b>" + bold[0] + "</b>" + bold[1]
else:
text =simans.group(1) + simans.group(3)
#text1 = re.split(u"(.*?[.:])", text)
#text1 = filter(None, text1)
#taking care of links
try:
for k in range(0,len(karo[len(tur)])):
#print len(tur)+1,k
#for k in range(1,len(re.findall("@66",simans.group(0)))):
#print simans.group(0)
if "@66" in simans.group(1):
links.append(addlink(len(tur)+1,1, k+1 ))
localbet_yosef += len(re.findall("@66",simans.group(2)))
if "@66" in simans.group(2):
links.append(addlink(len(tur)+1,1, k+1 ))
for sif_num,sifs in enumerate(text, start =1):
for a in range(1,len(re.findall("@66", sifs))):
links.append(addlink(len(tur)+1,sif_num , a+k+1 ))
#if localbet_yosef - len(karo[len(tur)+1]) != -1:
#print simans.group(2),roman_siman, localbet_yosef, len(karo[len(tur)+1])
# pass
if roman_siman - older_siman != 1:
print siman
print roman_siman
older_siman = roman_siman
text = re.sub(ur'@66', lambda m, c=count(1): '[{}]'.format(next(c)), text)
tur.append([text])
except IndexError:
print "out of index"
arbaturim.append(tur)
depth = lambda L: isinstance(L, list) and max(map(depth, L))+1
print depth(tur)
return tur
def parse(text):
if os.path.isfile("../source/Korban_Netanel_on_{}.txt".format(masechet)) or os.path.isfile(
"../source/Pilpula_Charifta_on_{}.txt".format(masechet)
):
# print "has korban netanel 2"
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
a = re.split(ur"@22([^@]*)", text)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban = []
if ur"[*]" in seif and (
os.path.isfile(
"../source/Korban_Netanel_on_{}.txt".format(masechet)
or os.path.isfile("../source/PilPula_Charifta_on_{}.txt".format(masechet))
)
and netanel <= len(fixed)
):
if os.path.isfile("../source/Korban_Netanel_on_{}.txt".format(masechet)):
commentator = "Korban Netanel on "
if os.path.isfile("../source/PilPula_Charifta_on_{}.txt".format(masechet)):
commentator = "Pilpula Charifta on "
korban.append(fixed[netanel])
# print len(links_netanel)
roash = "Rosh on %s." % masechet + str(len(links_netanel) + 1) + ".1"
netanelink = commentator + masechet + "." + str(len(links_netanel) + 1) + ".1"
links.append(link(netanelink, roash))
netanel += 1
# print "netanel one seif", seif, netanel
# print fixed[netanel]
content = re.split("@66", cont)
seif = re.sub(ur"[^א-ת]", "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
if ur"[*]" in co:
# print co
a = re.findall("\[\*\](.{6})", co)
for b in a:
if (
os.path.isfile("../source/Korban_netanel_on_{}.txt".format(masechet))
or os.path.isfile("../source/Pilpula_Charifta_on_{}.txt".format(masechet))
) and netanel < len(fixed):
if os.path.isfile("../source/Korban_netanel_on_{}.txt".format(masechet)):
commentator = "Korban Netanel "
if os.path.isfile("../source/Pilpula_Charifta_on_{}.txt".format(masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(len(links_netanel) + 1) + "." + str(num + 1)
netanelink = (
commentator + "on " + masechet + "." + str(len(links_netanel) + 1) + "." + str(len(korban))
)
links.append(link(netanelink, roash))
netanel += 1
si.append(co)
def parse1(text):
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
chapters = re.split(ur'@00', text)
for chapter_num, chapter in enumerate(chapters):
print chapter_num, chapter[0:10]
if len(chapter)<=1:
pass
else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban =[]
print seif
if ur'[*]' in seif:
print "hello1"
if ur'[*]' in seif and (os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel <= len(fixed):
print "hello", seif, netanel, len(fixed)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel"
if os.path.isfile('source/PilPula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta"
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet +str(len(rosh)+2) + "." + str(len(perek)+1) + ".1"
netanelink = commentator + " on " + masechet +"."+ str(len(links_netanel)+1) + ".1"
print roash, netanelink
links.append(link(netanelink, roash))
netanel += 1
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
for b in a:
print b, seif
if (os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel < len(fixed):
if os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel "
if os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(len(rosh)+2) + "." + str(len(perek)+1) + "." + str(num+1)
netanelink = commentator + "on " + masechet + "." + str(len(links_netanel)+1)+ "."+ str(len(korban))
print roash, netanelink
links.append(link(netanelink, roash))
netanel +=1
si.append(co)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
links_netanel.append(korban)
perek.append(si)
rosh.append(perek)
def parse1(text):
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
chapters = re.split(ur'@00', text)
for chapter_num, chapter in enumerate(chapters):
print chapter_num, chapter[0:10]
if len(chapter)<=1:
pass
else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban =[]
print seif
if ur'[*]' in seif:
print "hello1"
if ur'[*]' in seif and (os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel <= len(fixed):
print "hello", seif, netanel, len(fixed)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel"
if os.path.isfile('source/PilPula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta"
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet +str(len(rosh)+2) + "." + str(len(perek)+1) + ".1"
netanelink = commentator + " on " + masechet +"."+ str(len(links_netanel)+1) + ".1"
print roash, netanelink
links.append(link(netanelink, roash))
netanel += 1
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
for b in a:
print b, seif
if (os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel < len(fixed):
if os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel "
if os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(len(rosh)+2) + "." + str(len(perek)+1) + "." + str(num+1)
netanelink = commentator + "on " + masechet + "." + str(len(links_netanel)+1)+ "."+ str(len(korban))
print roash, netanelink
links.append(link(netanelink, roash))
netanel +=1
si.append(co)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
links_netanel.append(korban)
perek.append(si)
rosh.append(perek)
def parse_dapim(text):
old_num = 1
shas = 0
count = 1
ncount = 1
tosafos = 0
rashi = 0
no_b = False
amud_num = 'b'
daf = re.split(ur'@[0-9][0-9](דף[^@]*)', text)
print "length daf", len(daf)
#print len(daf)
chidushei_halachot = [[], []]
for daf_num, content in zip(daf[1::2], daf[2::2]):
#print daf_num
count += 1
cut_books = re.split(ur'@66([^@]*)', content)
if len(re.findall(ur'[0-9][0-9]ע"ב', cut_books[0])) == 0:
#print "is zero", daf_num
no_b = True
amudim = re.split(ur'(?:@44|@11)ע"ב', cut_books[0])
for amud in amudim:
if len(amudim) < 2:
print len(amudim), daf_num
DH = []
if amud_num == 'b':
amud_num = 'a'
elif no_b == True:
amud_num = 'a'
else:
amud_num = 'b'
halachot = re.split(ur'@44', amud)
for i, verse in enumerate(halachot):
pverse = re.sub(ur'@..', "", verse)
if len(pverse) < 3:
pverse = " "
DH.append(pverse)
if len(daf_num[3:]) > 3:
print "longer than 3", daf_num[3:], number
number = hebrew.heb_string_to_int(
re.sub("'", "", daf_num[3:].strip()))
if (number - old_num) < 0 or (number - old_num) > 1:
print "diff", number - old_num, daf_num
old_num = number
#print number
if ur'רש"י' in verse[0:10]:
search_rashi(verse, number, amud_num, i + 1)
rashi += 1
pass
elif ur'תוס' in verse[0:10]:
# search_tosafot(verse, number , amud_num, i+1)
tosafos += 1
pass
else:
search_gemara(verse, number, amud_num, i + 1)
shas += 1
pass
def search2(parsed, part):
for k, seif in enumerate(parsed):
for i,pasuk in enumerate(seif):
found = re.finditer(ur'@44[\[\(](.*?)[\]\)]@55(.*?)\.', pasuk)
for find in found:
daf = find.group(1)
if daf.strip().split(' ')[0] == u"מנחות"and len(daf.strip().split(' '))<6:
if len(daf.strip().split(' ')) ==3:
daf = daf.strip().split(' ')[2]
elif len(daf.strip().split(' ')) ==2:
daf = daf.strip().split(' ')[1]
if daf[-1] ==".":
amud ="a"
elif daf[-1] == ":":
amud = "b"
daf_num = hebrew.heb_string_to_int(daf[0:-1])
#print daf_num, amud
elif daf.strip().split(' ')[0] == u"דף":
daf = daf.strip().split(' ')[1]
if daf[-1] ==".":
amud ="a"
elif daf[-1] == ":":
amud = "b"
daf_num = hebrew.heb_string_to_int(daf[0:-1])
#print daf_num, amud
elif ur"שם" not in daf and ur"דף" in daf:
#print daf
pass
else:
pass
#print daf
text = find.group(2)
try:
print str(k+1), str(i+1),daf_num, amud
found = matchobj(daf_num, amud, text)
line = found[1][0]
if line >0:
#print "Rosh on {}".format(masechet), daf_num, amud, found[1][0], str(i+1), ",", str(j+1) + ",", str(k+1)
talmud = "{}".format(masechet) + "." + str(daf_num) + amud + "." + str(line)
roash = "Rosh on {}".format(masechet) + ", " + part + "." + str(k+1) + "." + str(1)
links.append(makeLink(talmud,roash))
except Exception as e:
print e
def parse_dapim(text):
old_num = 1
shas = 0
count = 1
ncount = 1
tosafos = 0
rashi = 0
no_b=False
amud_num = 'b'
daf = re.split(ur'@[0-9][0-9](דף[^@]*)', text)
print "length daf", len(daf)
#print len(daf)
chidushei_halachot = [[],[]]
for daf_num, content in zip(daf[1::2], daf[2::2]):
#print daf_num
count+=1
cut_books = re.split(ur'@66([^@]*)', content)
if len(re.findall(ur'[0-9][0-9]ע"ב',cut_books[0] ))==0:
#print "is zero", daf_num
no_b= True
amudim = re.split(ur'(?:@44|@11)ע"ב', cut_books[0])
for amud in amudim:
if len(amudim)<2:
print len(amudim), daf_num
DH = []
if amud_num == 'b':
amud_num = 'a'
elif no_b == True:
amud_num = 'a'
else:
amud_num='b'
halachot = re.split(ur'@44',amud)
for i, verse in enumerate(halachot):
pverse = re.sub(ur'@..', "", verse)
if len(pverse)<3:
pverse= " "
DH.append(pverse)
if len(daf_num[3:])>3:
print "longer than 3", daf_num[3:], number
number = hebrew.heb_string_to_int(re.sub("'","",daf_num[3:].strip()))
if (number - old_num) <0 or (number - old_num) >1:
print "diff", number - old_num, daf_num
old_num = number
#print number
if ur'רש"י' in verse[0:10]:
search_rashi(verse, number , amud_num, i+1)
rashi += 1
pass
elif ur'תוס' in verse[0:10]:
# search_tosafot(verse, number , amud_num, i+1)
tosafos += 1
pass
else:
search_gemara(verse, number , amud_num, i+1)
shas += 1
pass
def divrey_chamuot2(text):
chamudotlinks = []
count = 0
file = tiferet_shmuel.open_file(record="chamudot")
parsed = tiferet_shmuel.parse(file)
Helper.createBookRecord(tiferet_shmuel.book_record(record="chamudot"))
tiferet_shmuel.save_parsed_text(parsed, record="chamudot")
tiferet_shmuel.run_post_to_api(record="chamudot")
commentator = "Divrey Chamudot"
rosh = []
chapters = re.split(ur"(?:@00|@99)", text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
print chapter_num
if len(chapter) <= 1:
pass
else:
perek = []
a = re.split(ur"@22([^@]*)", chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
print seif
if ur"(*)" in seif:
print "hello1"
if ur"(*)" in seif:
count += 1
roash = "Rosh on %s." % masechet + str(len(rosh) + 1) + "." + str(len(perek) + 1) + ".1"
shmuel = commentator + " on " + masechet + "." + str(count)
chamudotlinks.append(link(roash, shmuel))
print roash, shmuel
content = re.split("@66", cont)
seif = re.sub(ur"[^א-ת]", "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall("\(\*\)", co)
for b in a:
count += 1
roash = (
"Rosh on %s." % masechet
+ str(len(rosh) + 1)
+ "."
+ str(len(perek) + 1)
+ "."
+ str(num + 1)
)
shmuel = commentator + " on " + masechet + "." + str(count)
print roash, shmuel
chamudotlinks.append(link(shmuel, roash))
# print parsed[count]
si.append(co)
perek.append(si)
rosh.append(perek)
def divrey_chamuot2(text):
chamudotlinks = []
count = 0
file = tiferet_shmuel.open_file(record="chamudot")
parsed = tiferet_shmuel.parse(file)
Helper.createBookRecord(tiferet_shmuel.book_record(record="chamudot"))
tiferet_shmuel.save_parsed_text(parsed, record="chamudot")
tiferet_shmuel.run_post_to_api(record="chamudot")
commentator = "Divrey Chamudot"
rosh = []
chapters = re.split(ur'(?:@00|@99)', text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
print chapter_num
if len(chapter) <= 1:
pass
else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
print seif
if ur'(*)' in seif:
print "hello1"
if ur'(*)' in seif:
count += 1
roash = "Rosh on %s." % masechet + str(
len(rosh) + 1) + "." + str(len(perek) + 1) + ".1"
shmuel = commentator + " on " + masechet + "." + str(count)
chamudotlinks.append(link(roash, shmuel))
print roash, shmuel
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]', "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\(\*\)', co)
for b in a:
count += 1
roash = "Rosh on %s." % masechet + str(
len(rosh) + 1) + "." + str(len(perek) +
1) + "." + str(num + 1)
shmuel = commentator + " on " + masechet + "." + str(
count)
print roash, shmuel
chamudotlinks.append(link(shmuel, roash))
#print parsed[count]
si.append(co)
perek.append(si)
rosh.append(perek)
def links(clean_text, shas):
for i, page in enumerate (clean_text):
for j,chapter in enumerate(page):
a = re.finditer(ur"@88(.+?)@77(.+)", chapter)
for link in a:
heb_links= re.split(" ",link.group(1))
daf =heb_links[1]
amud = heb_links[2]
if amud[2]==ur'א':
eng_amud = 'a'
elif amud[2]==ur'ב':
eng_amud=ur'b'
daf = hebrew.heb_string_to_int(daf)
quote = re.split(" ",link.group(2).strip())
matching(quote, daf, eng_amud,i,j, shas,words =len(quote), ratio = 70)
def run_parser():
print "running parser"
parsed_text = []
cur_chapter = 1
cur_verse = 1
#regex = re.compile(ur'@11(.*)@22',re.UNICODE)
with open("source/Radak_on_Genesis.txt", 'r') as filep:
file_text = filep.read()
ucd_text = unicode(file_text, 'utf-8').strip()
#get rid of some unhelpful markup
ucd_text = re.sub(ur'@11(.*?)@33', ur'@55\1', ucd_text)
ucd_text = re.sub(ur'@00([^@]*)\n', '', ucd_text)
ucd_text = ucd_text.replace(u'@44(שם)@55', u'(שם)')
#split according to chapter. Will also include the chapter letters in the results.
chapters = re.split(ur'@22([^@]*)', ucd_text)
for chapter_num, chapter in zip(chapters[1::2],chapters[2::2]):
if chapter_num.strip() != '':
cur_chapter = hebrew.heb_string_to_int(chapter_num.strip())
parsed_chapter = []
expand_list_assign(parsed_text, cur_chapter-1, parsed_chapter)
#now split on verse numbers, capturing the verse numbers as well
verses = re.split(ur'@44\(([\u0590-\u05ea]{1,2})\)',chapter)
for verse_num, verse in zip(verses[1::2], verses[2::2]):
if verse_num.strip() != '':
parsed_verse = []
cur_verse = hebrew.heb_string_to_int(verse_num.strip())
expand_list_assign(parsed_chapter, cur_verse-1, parsed_verse)
comments = verse.split('@55')[1:]
for comment in comments:
if comment.strip() != '':
parsed_verse.append(comment)
pretty_print(parsed_text)
save_parsed_text(parsed_text)
def link_to_link(link):
if len(link.strip().split(" ")) ==2 and link[0]==ur'ד':
dafamud = link.strip().split(" ")[1]
amods = dafamud[len(dafamud)-1]
if amods == ":":
amod = "b"
elif amods ==".":
amod ="a"
dap = dafamud[0:len(dafamud)-1]
roman_daf = hebrew.heb_string_to_int(dap.strip())
return masechet + "." + str(roman_daf) + amod
elif link[0]==ur'ד':
pass
#print link
elif '.' in link or ":" in link:
pass
def link_to_link(link):
if len(link.strip().split(" ")) == 2 and link[0] == ur'ד':
dafamud = link.strip().split(" ")[1]
amods = dafamud[len(dafamud) - 1]
if amods == ":":
amod = "b"
elif amods == ".":
amod = "a"
dap = dafamud[0:len(dafamud) - 1]
roman_daf = hebrew.heb_string_to_int(dap.strip())
return masechet + "." + str(roman_daf) + amod
elif link[0] == ur'ד':
pass
#print link
elif '.' in link or ":" in link:
pass
def search(text, shas):
for i, seif in enumerate(text):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))', siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)',"",siman)
start_of_siman = re.split(" ", start)
# print "start of siman", start_of_siman[0]
if 'index' in locals():
# print "matching", index
if index > len(shas):
break
matching(start_of_siman, shas, i, j, index, daf, amud)
for match in linked:
lookfor = match.group(2)
tagged = re.split(" ", lookfor.strip())
daf_amud = re.split(ur' ', match.group(1).strip())
daf = re.sub(ur'[^א-ת]',"",daf_amud[1])
daf = hebrew.heb_string_to_int(daf)
if daf > len(shas) or len(daf_amud) <= 2:
# print "daf", daf, "is longer than needs to"
break
else:
print daf_amud[0]
amud = daf_amud[2]
# print "amud", amud
index = ((daf-2)*2)+1
#if index > len(shas):
# break
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
#print "daf", daf, amud
if index >= len(shas):
# print "short", daf, amud, lookfor
return
#break
else:
# print "else"
matching(tagged, shas, i, j, index, daf, amud)
def search(text, shas):
for i, seif in enumerate(text):
for j, siman in enumerate(seif):
if siman.endswith(ur'5 '):
print "yes"
linked = re.finditer(ur'@44(.*?)@(?:55|11)(.*?)(?=(@44|$))', siman)
if '@44' not in siman[0:10] and len(siman) > 8:
start = re.sub('([\[\*\]]|@..|#)', "", siman)
start_of_siman = re.split(" ", start)
# print "start of siman", start_of_siman[0]
if 'index' in locals():
# print "matching", index
if index > len(shas):
break
matching(start_of_siman, shas, i, j, index, daf, amud)
for match in linked:
lookfor = match.group(2)
tagged = re.split(" ", lookfor.strip())
daf_amud = re.split(ur' ', match.group(1).strip())
daf = re.sub(ur'[^א-ת]', "", daf_amud[1])
daf = hebrew.heb_string_to_int(daf)
if daf > len(shas) or len(daf_amud) <= 2:
# print "daf", daf, "is longer than needs to"
break
else:
print daf_amud[0]
amud = daf_amud[2]
# print "amud", amud
index = ((daf - 2) * 2) + 1
#if index > len(shas):
# break
if amud[2].strip() == ur'א':
amud = 'a'
index = index - 1
else:
amud = 'b'
#print "daf", daf, amud
if index >= len(shas):
# print "short", daf, amud, lookfor
pass
#break
else:
# print "else"
matching(tagged, shas, i, j, index, daf, amud)
def yomtov2(text):
chamudotlinks = []
count = 0
file = tiferet_shmuel.open_file(record = "yomtov")
parsed = tiferet_shmuel.parse(file)
Helper.createBookRecord(tiferet_shmuel.book_record(record = "yomtov"))
tiferet_shmuel.save_parsed_text(parsed, record = "yomtov")
tiferet_shmuel.run_post_to_api(record = "yomtov")
commentator = "Maadaney Yom Tov"
rosh = []
chapters = re.split(ur'(?:@00|@99)', text)
for chapter_num, chapter in enumerate(chapters):
if len(chapter)<=1:
pass
else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
print seif
if ur'[*]' in seif:
print "hello1"
if ur'[*]' in seif:
count+=1
roash = "Rosh on %s." % masechet +str(len(rosh)+1) + "." + str(len(perek)+1) + ".1"
shmuel = commentator + " on " + masechet +"."+ str(count)
chamudotlinks.append(link(roash, shmuel))
print roash, shmuel
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
for b in a:
count+=1
roash = "Rosh on %s." % masechet + str(len(rosh)+1) + "." + str(len(perek)+1) + "." + str(num+1)
shmuel = commentator + " on " + masechet + "." + str(count)
print roash, shmuel
chamudotlinks.append(link(shmuel, roash))
#print parsed[count]
si.append(co)
perek.append(si)
rosh.append(perek)
def parse(text):
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
# print "has korban netanel 2"
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
a = re.split(ur'@22([^@]*)', text)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban =[]
if ur'[*]' in seif and (os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet) or os.path.isfile('source/PilPula_Charifta_on_{}.txt'.format(masechet))) and netanel <= len(fixed)):
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel on "
if os.path.isfile('source/PilPula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta on "
korban.append(fixed[netanel])
#print len(links_netanel)
roash = "Rosh on %s." % masechet + str(len(links_netanel)+1) + ".1"
netanelink = commentator + masechet +"."+ str(len(links_netanel)+1) + ".1"
links.append(link(netanelink, roash))
netanel += 1
#print "netanel one seif", seif, netanel
#print fixed[netanel]
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
if ur'[*]' in co:
print co
a = re.findall('\[\*\](.{6})', co)
for b in a:
if (os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel < len(fixed):
if os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel "
if os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(len(links_netanel)+1) + "." + str(num+1)
netanelink = commentator + "on " +masechet + "." + str(len(links_netanel)+1)+ "."+ str(len(korban))
links.append(link(netanelink, roash))
netanel +=1
si.append(co)
def search(parsed):
for i in parsed:
for j in i:
found = re.finditer(ur'\(דף(.*?)\)(.*?)\(', j)
for find in found:
daf = find.group(1)
text = find.group(2)
if daf[len(daf)-1] == '.':
#print daf
amud = 'a'
elif daf[len(daf)-1] == ':':
amud = 'b'
new_daf = daf[0:len(daf.strip())].strip()
#print new_daf
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud
match(daf_num, amud, text)
except KeyError:
pass
def search1(parsed):
for i in parsed:
for k in i:
for j in k:
found = re.finditer(ur'@44\[דף(.*?)\](.*?)\(', j)
for find in found:
daf = find.group(1)
text = find.group(2)
if daf.strip().split(" ")[1] == u'ע"א':
amud = 'a'
elif daf.strip().split(" ")[1] == u'ע"ב':
amud = 'b'
new_daf = daf.strip().split(" ")[0]
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud
match(daf_num, amud, text)
except KeyError:
pass
def links(clean_text, shas):
for i, page in enumerate(clean_text):
for j, chapter in enumerate(page):
a = re.finditer(ur"@88(.+?)@77(.+)", chapter)
for link in a:
heb_links = re.split(" ", link.group(1))
daf = heb_links[1]
amud = heb_links[2]
if amud[2] == ur'א':
eng_amud = 'a'
elif amud[2] == ur'ב':
eng_amud = ur'b'
daf = hebrew.heb_string_to_int(daf)
quote = re.split(" ", link.group(2).strip())
matching(quote,
daf,
eng_amud,
i,
j,
shas,
words=len(quote),
ratio=70)
def search(parsed):
for i,perek in enumerate(parsed):
for j,pasuk in enumerate(perek):
found = re.finditer(ur'\(דף(.*?)\)', pasuk)
for find in found:
daf = find.group(1)
#text = find.group(2)
if daf[len(daf)-1] == '.':
#print daf
amud = 'a'
elif daf[len(daf)-1] == ':':
amud = 'b'
new_daf = daf[0:len(daf.strip())].strip()
#print new_daf
try:
daf_num = hebrew.heb_string_to_int(new_daf)
#print str(daf_num) + amud + " " + str(i) + " " + str(j+1)
links.append(link("{}".format(masechet) + "." + str(daf_num) + amud, "Rosh on {}, Hilchot Seder Avodat Yom HaKippurim".format(masechet) + "." + str(i) + "." + str(j+1)))
#links.append(link(
#match(daf_num, amud, text)
except KeyError:
pass
def parse(text):
links_netanel = []
netanel = 0
rosh = []
a = re.split(ur'@22([^@]*)', text)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
if ur'[*]' in seif:
print seif
netanel += 1
#si.append(seif)
content = re.split('@66', cont)
seif = re.sub(ur'[\s\[\*\]]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\](.{6})', co)
#for b in a:
#print b
netanel +=len(a)
#print seif, num, netanel - len(a), netanel
#print len(a)
si.append(co)
rosh.append(si)
def parse(text):
links_netanel = []
netanel = 0
rosh = []
a = re.split(ur'@22([^@]*)', text)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
if ur'[*]' in seif:
print seif
netanel += 1
#si.append(seif)
content = re.split('@66', cont)
seif = re.sub(ur'[\s\[\*\]]', "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\](.{6})', co)
#for b in a:
#print b
netanel += len(a)
#print seif, num, netanel - len(a), netanel
#print len(a)
si.append(co)
rosh.append(si)
def parse(text):
old_num = 0
dibbur = ""
#simanim = re.finditer(ur'(@[0-9][0-9])\n?(@[0-9][0-9])(.*\n*)', text)
simanim = re.split("@77", text)
bayit_chadash = []
perek = []
i = 1
for siman in simanim:
simans = re.finditer("@11(.*)@33(.*)", siman)
for s in simans:
dibbur = "(" + str(i) + ")" + "<b>" + s.group(
1) + '</b>' + s.group(2)
print i
i = i + 1
if "@22" not in siman:
perek.append(dibbur)
elif "@22" in siman:
#i = 1
num = re.findall("@22(.*)", siman)[0]
new_num = hebrew.heb_string_to_int(num.strip())
#print new_num
if new_num - old_num != 1:
for k in range(1, new_num - old_num):
bayit_chadash.append([])
old_num = new_num
bayit_chadash.append(perek)
perek = []
perek.append(dibbur)
i = 1
bayit_chadash.append(perek)
#print len(bayit_chadash)
return bayit_chadash[1:len(bayit_chadash)]
def parse(text):
agadot=[[],[]]
old_number = 1
dappim = re.split(ur'@[0-9][0-9]ח"א([^@]*)', text)
for daf, content in zip(dappim[1::2],dappim[2::2]):
same = False
ab = False
seifim =[]
if len(daf.split(" ")) > 4:
if len(daf.split(" "))>=5:
string= daf.split(" ")[4]
#print string
daf_n = daf.split(" ")[2]
print daf_n
amud = daf.split(" ")[3].strip()
if amud[2].strip()== ur"א":
amuds = 'a'
elif amud[2].strip() == ur"ב":
amuds ='b'
else:
print "did it get here", amud
else:
continue
number = hebrew.heb_string_to_int(daf_n)
if number - old_number==0:
same =True
if number - old_number>1:
for i in range(1,number-old_number):
agadot.append([])
agadot.append([])
old_number = number
simanim = re.finditer(ur'(?:@[0-9][0-9]|[0-9])(.*)',content)
for match in simanim:
if re.search(ur'[0-9]דף', match.group(0)) is not None:
print match.group(0)
break
siman = match.group(0)
siman = re.split("@77([^(?:@|[0-9]]*)",siman)
for simans in siman:
if simans != "":
simanim = re.split('(?:@[0-9][0-9]|[0-9])',simans)
if len(simanim[0])>1:
simanim_string = "<b>" +string + " " + '</b>'+ simanim[0]
seifim.append(simanim_string)
if ur'<b>ע"ב' in simanim_string:
amuds="b"
print simanim_string
agadot.append(seifim)
seifim=[]
seifim.append(simanim_string)
ab = True
if len(simanim) > 1:
for i in range(1,len(simanim)-1,2):
simanim_string = ur'<b>' + simanim[i] + " " + ur'</b>' + simanim[i+1]
if u'<b>ע"ב' in simanim_string:
print daf_n
amuds="b"
print simanim_string
agadot.append(seifim)
seifim=[]
ab = True
if len(simanim_string) > 1:
seifim.append(simanim_string)
def parse(text):
i = 0
kb = re.split(ur"@00הלכות כלאי בגדים(.*?)@00פרק תשיעי", text)
begadim = kb[1]
ending = re.split(ur"@00הלכות מקוואות", kb[2])
bdy = kb[0] + ending[0]
mikva = ending[1]
old_numeri = 0
rosh = []
kileiggadim = []
hilchotmikvaot = []
chapters = re.split(ur'(?:@00|@99)([^@]*)', bdy)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
mispar = chapter_num.strip().split(" ")[1]
if mispar.encode('utf-8') in misparim.keys():
mispar_numeri = misparim[mispar.encode('utf-8')]
print mispar_numeri
if mispar_numeri - old_numeri > 1:
for i in range(1, mispar_numeri - old_numeri):
rosh.append([])
old_numeri = mispar_numeri
print mispar
#if len(chapter)<=1:
# pass
#else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]', "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
#for b in a:
#print b, seif
si.append(co)
perek.append(si)
if len(perek) is not 0:
rosh.append(perek)
# print len(rosh)
search2(rosh)
#take care of begadim
b = re.split(ur'@22([^@]*)', begadim)
for sei, con in zip(b[1::2], b[2::2]):
si = []
conten = re.split('@66', con)
sei = re.sub(ur'[^א-ת]', "", sei)
sei = hebrew.heb_string_to_int(sei.strip())
for num, co in enumerate(conten):
b = re.findall('\[\*\]', co)
#for c in b:
#print c, sei
si.append(co)
kileiggadim.append(si)
b = re.split(ur'@22([^@]*)', mikva)
for sei, con in zip(b[1::2], b[2::2]):
si = []
conten = re.split('@66', con)
sei = re.sub(ur'[^א-ת]', "", sei)
sei = hebrew.heb_string_to_int(sei.strip())
for num, co in enumerate(conten):
b = re.findall('\[\*\]', co)
for c in b:
print c, sei
si.append(co)
hilchotmikvaot.append(si)
#take care of mikva
return rosh, kileiggadim, hilchotmikvaot
def parse(text):
i=0
kb = re.split(ur"@00הלכות כלאי בגדים(.*?)@00פרק תשיעי", text)
begadim = kb[1]
ending = re.split(ur"@00הלכות מקוואות",kb[2])
bdy = kb[0] + ending[0]
mikva = ending[1]
old_numeri = 0
rosh = []
kileiggadim =[]
hilchotmikvaot =[]
chapters = re.split(ur'(?:@00|@99)([^@]*)', bdy)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
mispar = chapter_num.strip().split(" ")[1]
if mispar.encode('utf-8') in misparim.keys():
mispar_numeri = misparim[mispar.encode('utf-8')]
print mispar_numeri
if mispar_numeri - old_numeri > 1:
for i in range(1,mispar_numeri-old_numeri):
rosh.append([])
old_numeri = mispar_numeri
print mispar
#if len(chapter)<=1:
# pass
#else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
#for b in a:
#print b, seif
si.append(co)
perek.append(si)
if len(perek) is not 0:
rosh.append(perek)
# print len(rosh)
search2(rosh)
#take care of begadim
b = re.split(ur'@22([^@]*)',begadim )
for sei, con in zip(b[1::2], b[2::2]):
si = []
conten = re.split('@66', con)
sei = re.sub(ur'[^א-ת]',"", sei)
sei = hebrew.heb_string_to_int(sei.strip())
for num, co in enumerate(conten):
b = re.findall('\[\*\]', co)
#for c in b:
#print c, sei
si.append(co)
kileiggadim.append(si)
b = re.split(ur'@22([^@]*)', mikva)
for sei, con in zip(b[1::2], b[2::2]):
si = []
conten = re.split('@66', con)
sei = re.sub(ur'[^א-ת]',"", sei)
sei = hebrew.heb_string_to_int(sei.strip())
for num, co in enumerate(conten):
b = re.findall('\[\*\]', co)
for c in b:
print c, sei
si.append(co)
hilchotmikvaot.append(si)
#take care of mikva
return rosh , kileiggadim,hilchotmikvaot
def parse1(text):
old_numeri = 0
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
chapters = re.split(ur'(?:@00|@99)([^@]*)', text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
mispar = chapter_num.strip().split(" ")[1]
if mispar.encode('utf-8') in misparim.keys():
mispar_numeri = misparim[mispar.encode('utf-8')]
print mispar_numeri
if mispar_numeri - old_numeri > 1:
for i in range(1,mispar_numeri-old_numeri):
rosh.append([])
#print "length of rosh", len(rosh)
old_numeri = mispar_numeri
print mispar
#if len(chapter)<=1:
# pass
#else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban =[]
#print seif
if ur'[*]' in seif and (os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel < len(fixed):
# print "hello", seif, netanel, len(fixed)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel"
if os.path.isfile('source/PilPula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta"
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet +str(len(rosh)+1) + "." + str(len(perek)+1) + ".1"
netanelink = commentator + " on " + masechet +"."+ str(len(links_netanel)+1) + ".1"
#print roash, netanelink
links.append(link(netanelink, roash))
netanel += 1
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]',"", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
for b in a:
# print b, seif
if (os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet))) and netanel < len(fixed):
if os.path.isfile('source/Korban_netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel "
if os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(len(rosh)+1) + "." + str(len(perek)+1) + "." + str(num+1)
netanelink = commentator + "on " + masechet + "." + str(len(links_netanel)+1)+ "."+ str(len(korban))
#print roash, netanelink
links.append(link(netanelink, roash))
netanel +=1
si.append(co)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(masechet)) or os.path.isfile('source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
links_netanel.append(korban)
perek.append(si)
if len(perek) is not 0:
rosh.append(perek)
def parse(text):
agadot=[[],[]]
old_number = 1
dappim = re.split(ur'@[0-9][0-9]ח"א([^@]*)', text)
for daf, content in zip(dappim[1::2],dappim[2::2]):
same = False
ab = False
seifim =[]
if len(daf.split(" ")) > 4:
if len(daf.split(" "))>=5:
string= daf.split(" ")[4]
#print string
daf_n = daf.split(" ")[2]
print daf_n
amud = daf.split(" ")[3].strip()
if amud[2].strip()== ur"א":
amuds = 'a'
elif amud[2].strip() == ur"ב":
amuds ='b'
else:
print "did it get here", amud
else:
continue
number = hebrew.heb_string_to_int(daf_n)
if number - old_number==0:
same =True
if number - old_number>1:
for i in range(1,number-old_number):
agadot.append([])
agadot.append([])
old_number = number
simanim = re.finditer(ur'(?:@[0-9][0-9]|[0-9])(.*)',content)
for match in simanim:
if re.search(ur'[0-9]דף', match.group(0)) is not None:
print match.group(0)
break
siman = match.group(0)
siman = re.split("@77([^(?:@|[0-9]]*)",siman)
for simans in siman:
if simans != "":
simanim = re.split('(?:@[0-9][0-9]|[0-9])',simans)
if len(simanim[0])>1:
simanim_string = "<b>" +string + " " + '</b>'+ simanim[0]
seifim.append(simanim_string)
if ur'<b>ע"ב' in simanim_string:
amuds="b"
print simanim_string
agadot.append(seifim)
seifim=[]
seifim.append(simanim_string)
ab = True
if len(simanim) > 1:
for i in range(1,len(simanim)-1,2):
simanim_string = ur'<b>' + simanim[i] + " " + ur'</b>' + simanim[i+1]
if u'<b>ע"ב' in simanim_string:
print daf_n
amuds="b"
print simanim_string
agadot.append(seifim)
seifim=[]
ab = True
if len(simanim_string) > 1:
seifim.append(simanim_string)
def parse(text):
older_siman = 0
arbaturim = []
tur = []
hilchos = re.split(ur'@00', text) #split to names of parts
for halacha in hilchos:
if len(halacha) > 0:
halacha_name = halacha.splitlines()[0]
#print halacha_name #get the name of the part
simanim = re.finditer(
ur'(@?[0-9]?[0-9]?@?[0-9]?[0-9]?)@22(.*)@11(.*)', halacha
) #cut the text to simanim, get kletter of siman and tags to commentary
i = 1
for simans in simanim:
localbet_yosef = 0
siman = simans.group(2)
siman = re.sub(ur'[\(\[].*?[\)\]]', "", siman)
siman = re.sub(ur'[^\u05d0-\u05ea]', "", siman)
if len(siman) > 4:
# print simans.group(2)
#print simans.group(3)
pass
roman_siman = hebrew.heb_string_to_int(siman.strip())
bold = re.split(ur'@33', simans.group(3))
if len(bold) == 2:
text = simans.group(1) + "<b>" + bold[0] + "</b>" + bold[1]
else:
text = simans.group(1) + simans.group(3)
#text1 = re.split(u"(.*?[.:])", text)
#text1 = filter(None, text1)
#taking care of links
try:
for k in range(0, len(karo[len(tur)])):
#print len(tur)+1,k
#for k in range(1,len(re.findall("@66",simans.group(0)))):
#print simans.group(0)
if "@66" in simans.group(1):
links.append(addlink(len(tur) + 1, 1, k + 1))
localbet_yosef += len(re.findall("@66", simans.group(2)))
if "@66" in simans.group(2):
links.append(addlink(len(tur) + 1, 1, k + 1))
for sif_num, sifs in enumerate(text, start=1):
for a in range(1, len(re.findall("@66", sifs))):
links.append(
addlink(len(tur) + 1, sif_num, a + k + 1))
#if localbet_yosef - len(karo[len(tur)+1]) != -1:
#print simans.group(2),roman_siman, localbet_yosef, len(karo[len(tur)+1])
# pass
if roman_siman - older_siman != 1:
print siman
print roman_siman
older_siman = roman_siman
text = re.sub(ur'@66',
lambda m, c=count(1): '[{}]'.format(next(c)),
text)
tur.append([text])
except IndexError:
print "out of index"
arbaturim.append(tur)
depth = lambda L: isinstance(L, list) and max(map(depth, L)) + 1
print depth(tur)
return tur
def parse1(text):
old_numeri = 0
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(
masechet)) or os.path.isfile(
'source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
nose_kelim = nosekelim.open_file()
fixed = nosekelim.parse(nose_kelim)
links_netanel = []
netanel = 0
rosh = []
chapters = re.split(ur'(?:@00|@99)([^@]*)', text)
for chapter_num, chapter in zip(chapters[1::2], chapters[2::2]):
mispar = chapter_num.strip().split(" ")[1]
if mispar.encode('utf-8') in misparim.keys():
mispar_numeri = misparim[mispar.encode('utf-8')]
print mispar_numeri
if mispar_numeri - old_numeri > 1:
for i in range(1, mispar_numeri - old_numeri):
rosh.append([])
#print "length of rosh", len(rosh)
old_numeri = mispar_numeri
print mispar
#if len(chapter)<=1:
# pass
#else:
perek = []
a = re.split(ur'@22([^@]*)', chapter)
for seif, cont in zip(a[1::2], a[2::2]):
si = []
korban = []
#print seif
if ur'[*]' in seif and (
os.path.isfile(
'source/Korban_Netanel_on_{}.txt'.format(masechet))
or os.path.isfile(
'source/Pilpula_Charifta_on_{}.txt'.format(masechet))
) and netanel < len(fixed):
# print "hello", seif, netanel, len(fixed)
if os.path.isfile(
'source/Korban_Netanel_on_{}.txt'.format(masechet)):
commentator = "Korban Netanel"
if os.path.isfile(
'source/PilPula_Charifta_on_{}.txt'.format(masechet)):
commentator = "Pilpula Charifta"
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(
len(rosh) + 1) + "." + str(len(perek) + 1) + ".1"
netanelink = commentator + " on " + masechet + "." + str(
len(links_netanel) + 1) + ".1"
#print roash, netanelink
links.append(link(netanelink, roash))
netanel += 1
content = re.split('@66', cont)
seif = re.sub(ur'[^א-ת]', "", seif)
seif = hebrew.heb_string_to_int(seif.strip())
for num, co in enumerate(content):
a = re.findall('\[\*\]', co)
for b in a:
# print b, seif
if (os.path.isfile(
'source/Korban_netanel_on_{}.txt'.format(masechet))
or os.path.isfile(
'source/Pilpula_Charifta_on_{}.txt'.format(
masechet))) and netanel < len(fixed):
if os.path.isfile(
'source/Korban_netanel_on_{}.txt'.format(
masechet)):
commentator = "Korban Netanel "
if os.path.isfile(
'source/Pilpula_Charifta_on_{}.txt'.format(
masechet)):
commentator = "Pilpula Charifta "
korban.append(fixed[netanel])
roash = "Rosh on %s." % masechet + str(
len(rosh) + 1) + "." + str(len(perek) +
1) + "." + str(num + 1)
netanelink = commentator + "on " + masechet + "." + str(
len(links_netanel) + 1) + "." + str(len(korban))
#print roash, netanelink
links.append(link(netanelink, roash))
netanel += 1
si.append(co)
if os.path.isfile('source/Korban_Netanel_on_{}.txt'.format(
masechet)) or os.path.isfile(
'source/Pilpula_Charifta_on_{}.txt'.format(masechet)):
links_netanel.append(korban)
perek.append(si)
if len(perek) is not 0:
rosh.append(perek)