def post_yitzira():
node = JaggedArrayNode()
node.add_title('Sefer Yetzirah', 'en', primary=True)
node.add_title(u'ספר יצירה', 'he', primary=True)
node.key = 'Sefer Yetzirah'
node.depth = 2
node.addressTypes = ['Integer', 'Integer']
node.sectionNames = ['Chapter', 'Mishnah']
node.validate()
y_index = {
'title': 'Sefer Yetzirah',
'categories': ['Kabbalah'],
'language': 'he',
'schema': node.serialize()
}
y_version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': parse_yitzira()
}
post_index(y_index)
post_text("Sefer Yetzirah", y_version, index_count='on')
def post_this():
text_version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': gra
}
schema = JaggedArrayNode()
schema.add_title('HaGra on Sefer Yetzirah Gra Version', 'en', True)
schema.add_title(u'פירוש הגר"א על ספר יצירה', 'he', True)
schema.key = 'HaGra on Sefer Yetzirah Gra Version'
schema.depth = 3
schema.addressTypes = ['Integer', 'Integer','Integer']
schema.sectionNames = ['Chapter', 'Mishnah','Comment']
schema.validate()
index_dict = {
'title': 'HaGra on Sefer Yetzirah Gra Version',
'categories': ['Commentary2','Kabbalah','Gra'],
'schema': schema.serialize() # This line converts the schema into json
}
post_index(index_dict)
post_text('HaGra on Sefer Yetzirah Gra Version', text_version, index_count='on')
def post_raph(ja_raph):
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_raph
}
schema = JaggedArrayNode()
schema.add_title('Hagahot Rabbenu Peretz', 'en', True)
schema.add_title(u'הגהות רבנו פרץ', 'he', True)
schema.key = 'Hagahot Rabbenu Peretz'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
index_dict = {
'title': 'Hagahot Rabbenu Peretz',
'dependence': "Commentary",
'base_text_titles': ["Sefer Mitzvot Katan"],
"categories": ["Halakhah", "Commentary"],
'schema': schema.serialize() # This line converts the schema into json
}
post_index(index_dict)
post_text('Hagahot Rabbenu Peretz', text_version)
def upload():
links = []
for tractate in cards:
he_name = Ref(' '.join(tractate.split()[1:])).he_normal()
he_name = u'רמב"ם {}'.format(he_name)
node = JaggedArrayNode()
node.add_title(tractate, 'en', primary=True)
node.add_title(he_name, 'he', primary=True)
node.key = tractate
node.depth = 3
node.addressTypes = ['Integer', 'Integer', 'Integer']
node.sectionNames = ['Chapter', 'Mishnah', 'Comment']
node.validate()
index = {
'title': tractate,
'categories': ['Commentary2', 'Mishnah', 'Rambam'],
'schema': node.serialize(),
'toc_zoom': 2
}
parsed = parse_file('{}.txt'.format(tractate))
links.extend(parsed['links'])
version = {
'versionTitle': u'Vilna Edition',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957',
'language': 'he',
'text': parsed['parsed text']
}
print 'posting {}'.format(tractate)
post_index(index)
post_text(tractate, version, index_count='on')
post_link(links)
def upload(data, post_index=True):
# create index
schema = JaggedArrayNode()
schema.add_title(data['en'], 'en', True)
schema.add_title(data['he'], 'he', True)
schema.key = data['en']
schema.depth = 3
schema.addressTypes = ['Integer', 'Integer', 'Integer']
schema.sectionNames = ['Chapter', 'Seif', 'Comment']
schema.validate()
index = {
'title': data['en'],
'categories': ['Commentary2', 'Mishnah', 'Yachin'],
'schema': schema.serialize()
}
if post_index:
functions.post_index(index)
# clean and upload text
upload_text = util.clean_jagged_array(data['data'].array(), tags_to_strip())
text_version = {
'versionTitle': u'Mishnah, ed. Romm, Vilna 1913',
'versionSource': 'http://http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001741739',
'language': 'he',
'text': upload_text
}
functions.post_text(data['en'], text_version)
def upload(data, post_index=True):
# create index
schema = JaggedArrayNode()
schema.add_title(data['en'], 'en', True)
schema.add_title(data['he'], 'he', True)
schema.key = data['en']
schema.depth = 3
schema.addressTypes = ['Integer', 'Integer', 'Integer']
schema.sectionNames = ['Chapter', 'Seif', 'Comment']
schema.validate()
index = {
'title': data['en'],
'categories': ['Commentary2', 'Mishnah', 'Yachin'],
'schema': schema.serialize()
}
if post_index:
functions.post_index(index)
# clean and upload text
upload_text = util.clean_jagged_array(data['data'].array(),
tags_to_strip())
text_version = {
'versionTitle': u'Mishnah, ed. Romm, Vilna 1913',
'versionSource':
'http://http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001741739',
'language': 'he',
'text': upload_text
}
functions.post_text(data['en'], text_version)
def post_yitzira():
node = JaggedArrayNode()
node.add_title('Sefer Yetzirah', 'en', primary=True)
node.add_title(u'ספר יצירה', 'he', primary=True)
node.key = 'Sefer Yetzirah'
node.depth = 2
node.addressTypes = ['Integer', 'Integer']
node.sectionNames = ['Chapter', 'Mishnah']
node.validate()
y_index = {
'title': 'Sefer Yetzirah',
'categories': ['Kabbalah'],
'language': 'he',
'schema': node.serialize()
}
y_version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': parse_yitzira()
}
post_index(y_index)
post_text("Sefer Yetzirah", y_version, index_count='on')
def upload():
functions.post_index(construct_index())
parsed = parse()
names = node_names()
en_parasha_names = get_parsha_dict()
for book in names.keys():
for parasha in names[book].keys():
for year in names[book][parasha]:
current_text = {
'versionTitle': 'Sefat emet, Piotrków, 1905-1908',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001186213',
'language': 'he',
'text': parsed[book][parasha][year]
}
en_parasha = en_parasha_names[parasha]
civil_year = get_civil_year(year, book)
url = 'Sefat Emet, {}, {}, {}'.format(book, en_parasha, civil_year)
print url
for i in range(10):
try:
functions.post_text(url, current_text)
except (URLError, HTTPError):
print 'handling weak network'
continue
else:
break
def post_smk(ja_smk):
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_smk
}
schema = JaggedArrayNode()
schema.add_title('Sefer Mitzvot Katan', 'en', True)
schema.add_title(u'ספר מצות קטן', 'he', True)
schema.key = 'Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
index_dict = {
'title': 'Sefer Mitzvot Katan',
'categories': ['Halakhah'],
'schema': schema.serialize() # This line converts the schema into json
}
post_index(index_dict)
post_text('Sefer Mitzvot Katan', text_version)
def post_smk(ja_smk):
# before posting earase all '@'s
ja_smk = clean(ja_smk)
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_smk
}
schema = JaggedArrayNode()
schema.add_title('Sefer Mitzvot Katan', 'en', True)
schema.add_title(u'ספר מצות קטן', 'he', True)
schema.key = 'Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
index_dict = {
'title': 'Sefer Mitzvot Katan',
'categories': ['Halakhah'],
'schema': schema.serialize() # This line converts the schema into json
}
post_index(index_dict)
post_text('Sefer Mitzvot Katan', text_version)
def post_the_text(ja):
testing_file = codecs.open("testing_file.txt", 'w', 'utf-8')
util.jagged_array_to_file(testing_file, ja, ['Perek', 'Mishna', 'Comment'])
testing_file.close()
ref = create_ref()
text = create_text(ja)
functions.post_text(ref, text)
def post_hagahot(ja_hg):
replace_dict = {u"@11\([\u05d0-\u05ea]{1,3}\)\s?@33": u"",
u"@77": u"", u"@44": u"<br>", u"@55": u"<b>", u"@66": u"</b>", u"@00(.+?)\s(.+)": u"",
u"@(?:99|01)(.*?)@": ur"<br><small>\1</small><br>"}
ja_hg = before_post_cleaner(ja_hg, replace_dict)
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_hg
}
schema = JaggedArrayNode()
schema.add_title('Haggahot Chadashot on Sefer Mitzvot Katan', 'en', True)
schema.add_title(u'הגהות חדשות על ספר מצוות קטן', 'he', True)
schema.key = 'Haggahot Chadashot on Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
add_term('Haggahot Chadashot on Sefer Mitzvot Katan',u'הגהות חדשות על ספר מצוות קטן')
index_dict = {
'title': 'Haggahot Chadashot on Sefer Mitzvot Katan',
'dependence': "Commentary",
'base_text_titles': ["Sefer Mitzvot Katan", 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan'],
"categories": ["Halakhah", "Commentary"],
'schema': schema.serialize(), # This line converts the schema into json
'collective_title': 'Haggahot Chadashot on Sefer Mitzvot Katan',
}
post_index(index_dict)
post_text('Haggahot Chadashot on Sefer Mitzvot Katan', text_version)
def post_raph(ja_raph):
replace_dict = {u"@22": u"<br>"}
ja_raph = inlinereferencehtml(ja_raph)
ja_raph = before_post_cleaner(ja_raph, replace_dict)
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_raph
}
schema = JaggedArrayNode()
schema.add_title('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan', 'en', True)
schema.add_title(u'הגהות רבנו פרץ על ספר מצוות קטן', 'he', True)
schema.key = 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
add_term('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan', u'הגהות רבנו פרץ על ספר מצוות קטן')
index_dict = {
'title': 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan',
'dependence': "Commentary",
'base_text_titles': ["Sefer Mitzvot Katan"],
"categories": ["Halakhah", "Commentary"],
'schema': schema.serialize(),# This line converts the schema into json
'collective_title': 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan',
}
post_index(index_dict)
post_text('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan', text_version)
def post():
minchat = {'name': 'Minchat Chinuch', 'text': produce_parsed_data(filename)}
sefer = {'name': 'Sefer HaChinukh', 'text': Ref('Sefer HaChinukh').text('he').text}
chinukh_links = find_links(minchat, sefer, grab_dh, u'<b>', u'</b>')
with codecs.open('links.txt', 'w', 'utf-8') as outfile:
for each_link in chinukh_links:
outfile.write(u'{}\n'.format(each_link['refs']))
alt = construct_alt_struct('Chinukh_by_Parsha.csv', 'Chinukh Mitzva names.csv')
cleaned = util.clean_jagged_array(minchat['text'], [m_pattern, comment_pattern, u'@[0-9]{2}',
u'\n', u'\r'])
with codecs.open('parsed.txt', 'w', 'utf-8') as outfile:
util.jagged_array_to_file(outfile, cleaned, [u'Mitzva', u'Seif', u'Paragraph'])
full_text = {
'versionTitle': 'Minchat Chinuch, Piotrków, 1902',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001175092',
'language': 'he',
'text': cleaned
}
index = construct_index(alt)
functions.post_index(index)
functions.post_text('Minchat Chinuch', full_text)
functions.post_link(chinukh_links)
def upload_version(storage_object, title, destination='http://localhost:8000'):
version = storage_object.get_version_for_title(title)
post_text(title,
version,
index_count="on",
server=destination,
weak_network=True)
def post_this():
text_version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': ari_parse()
}
# we decide to put it as another version of the SeferYetzira Gra version that is up already.
# schema = JaggedArrayNode()
# schema.add_title('Sefer Yetzirah Gra Version', 'en', True)
# schema.add_title(u'ספר יצירה גרסאת הארי', 'he', True)
# schema.key = 'Sefer Yetzirah Gra Version'
# schema.depth = 2
# schema.addressTypes = ['Integer', 'Integer']
# schema.sectionNames = ['Chapter', 'Mishnah']
# schema.validate()
#
# index_dict = {
# 'title': 'Sefer Yetzirah Gra Version',
# 'categories': ['Kabbalah'],
# 'schema': schema.serialize() # This line converts the schema into json
# }
# post_index(index_dict)
post_text('Sefer Yetzirah Gra Version', text_version, index_count='on')
def parse_and_upload():
cards = get_cards()
links = []
for card in cards:
node = JaggedArrayNode()
node.add_title(card, 'en', primary=True)
node.add_title(u'רמב"ם ' + Ref(card.replace('Rambam ', '')).he_normal(), 'he', primary=True)
node.key = card
node.depth = 3
node.addressTypes = ['Integer', 'Integer', 'Integer']
node.sectionNames = ['Chapter', 'Mishnah', 'Comment']
node.validate()
node.toc_zoom = 2
index = {
'title': card,
'categories': ['Commentary2', 'Mishnah', 'Rambam'],
'schema': node.serialize(),
}
parsed = parser(card)
links.extend(parsed['links'])
version = {
'versionTitle': u'Vilna Edition',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957',
'language': 'he',
'text': parsed['parsed']
}
print 'posting {}'.format(card)
post_index(index)
post_text(card, version, index_count='on')
post_link(links)
def post_the_text(ja):
testing_file = codecs.open("testing_file.txt", 'w', 'utf-8')
util.jagged_array_to_file(testing_file, ja, ['Perek', 'Mishna','Comment'])
testing_file.close()
ref = create_ref()
text = create_text(ja)
functions.post_text(ref, text)
def post_raph(ja_raph):
replace_dict = {u"@22": u"<br>"}
ja_raph = inlinereferencehtml(ja_raph)
ja_raph = before_post_cleaner(ja_raph, replace_dict)
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_raph
}
schema = JaggedArrayNode()
schema.add_title('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan', 'en',
True)
schema.add_title(u'הגהות רבנו פרץ על ספר מצוות קטן', 'he', True)
schema.key = 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
add_term('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan',
u'הגהות רבנו פרץ על ספר מצוות קטן')
index_dict = {
'title': 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan',
'dependence': "Commentary",
'base_text_titles': ["Sefer Mitzvot Katan"],
"categories": ["Halakhah", "Commentary"],
'schema':
schema.serialize(), # This line converts the schema into json
'collective_title': 'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan',
}
post_index(index_dict)
post_text('Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan', text_version)
def post_this():
text_version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': gra
}
schema = JaggedArrayNode()
schema.add_title('HaGra on Sefer Yetzirah Gra Version', 'en', True)
schema.add_title(u'פירוש הגר"א על ספר יצירה', 'he', True)
schema.key = 'HaGra on Sefer Yetzirah Gra Version'
schema.depth = 3
schema.addressTypes = ['Integer', 'Integer', 'Integer']
schema.sectionNames = ['Chapter', 'Mishnah', 'Comment']
schema.validate()
index_dict = {
'title': 'HaGra on Sefer Yetzirah Gra Version',
'categories': ['Commentary2', 'Kabbalah', 'Gra'],
'schema': schema.serialize() # This line converts the schema into json
}
post_index(index_dict)
post_text('HaGra on Sefer Yetzirah Gra Version',
text_version,
index_count='on')
def post_this():
text_version = {
"versionTitle": "Sefer Yetzirah, Warsaw 1884",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968",
"language": "he",
"text": ari_parse(),
}
# we decide to put it as another version of the SeferYetzira Gra version that is up already.
# schema = JaggedArrayNode()
# schema.add_title('Sefer Yetzirah Gra Version', 'en', True)
# schema.add_title(u'ספר יצירה גרסאת הארי', 'he', True)
# schema.key = 'Sefer Yetzirah Gra Version'
# schema.depth = 2
# schema.addressTypes = ['Integer', 'Integer']
# schema.sectionNames = ['Chapter', 'Mishnah']
# schema.validate()
#
# index_dict = {
# 'title': 'Sefer Yetzirah Gra Version',
# 'categories': ['Kabbalah'],
# 'schema': schema.serialize() # This line converts the schema into json
# }
# post_index(index_dict)
post_text("Sefer Yetzirah Gra Version", text_version, index_count="on")
def post_avot_comm(title, book_text):
send_text = {
"text": book_text,
"versionTitle": "ToratEmet",
"versionSource": "http://www.toratemetfreeware.com/online/f_01313.html",
"language": "he"
}
post_text(title, send_text, server="http://draft.sefaria.org")
def post_the_text(jagged_array, book_number, parsha_number, intro=False):
ref = create_ref(book_number, parsha_number, intro)
text = create_text(jagged_array)
#print ref
# print text
functions.post_text(ref, text)
def post_the_text(jagged_array, book_number, parsha_number, intro=False):
ref = create_ref(book_number, parsha_number, intro)
text = create_text(jagged_array)
#print ref
# print text
functions.post_text(ref, text)
def post(self):
for index in self.base_indices:
post_index(index, weak_network=True)
for index in self.commentaryIndices:
post_index(index)
for version in self.versionList:
print version['ref']
post_text(version['ref'], version['version'], index_count='on', weak_network=True)
post_link(self.linkSet)
def post_simple_commentaries():
ramban_node, rasag_node = JaggedArrayNode(), JaggedArrayNode()
ramban_text = parse_general('yitzira_ramban.txt')
rasag_text = parse_general('yitzira_rasag.txt')
ramban_node.add_title("Ramban on Sefer Yetzirah", 'en', primary=True)
ramban_node.add_title(u'רמב"ן על ספר יצירה', 'he', primary=True)
ramban_node.key = "Ramban on Sefer Yetzirah"
ramban_node.addressTypes = ['Integer', 'Integer', 'Integer']
ramban_node.sectionNames = ["Chapter", "Mishnah", "Comment"]
ramban_node.toc_zoom = 2
ramban_node.depth = 3
ramban_node.validate()
rasag_node.add_title("Rasag on Sefer Yetzirah", 'en', primary=True)
rasag_node.add_title(u'רס"ג על ספר יצירה', 'he', primary=True)
rasag_node.key = "Rasag on Sefer Yetzirah"
rasag_node.addressTypes = ['Integer', 'Integer', 'Integer']
rasag_node.sectionNames = ["Chapter", "Mishnah", "Comment"]
rasag_node.toc_zoom = 2
rasag_node.depth = 3
rasag_node.validate()
ramban_index = {
"title": "Ramban on Sefer Yetzirah",
"categories": ["Commentary2", "Kabbalah", "Ramban"],
"language": "he",
"schema": ramban_node.serialize()
}
post_index(ramban_index)
post_text(
"Ramban on Sefer Yetzirah", {
'versionTitle': 'Ramban on Sefer Yetzirah, Warsaw 1884',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': ramban_text
})
rasag_index = {
"title": "Rasag on Sefer Yetzirah",
"categories": ["Commentary2", "Kabbalah", "Rasag"],
"language": "he",
"schema": rasag_node.serialize()
}
post_index(rasag_index)
post_text(
"Rasag on Sefer Yetzirah", {
'versionTitle': 'Rasage on Sefer Yetzirah, Warsaw 1884',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': rasag_text
})
links = linker(ramban_text, "Ramban on Sefer Yetzirah")
links.extend(linker(rasag_text, "Rasag on Sefer Yetzirah"))
post_link(links)
def post_text(text):
text = {
"title": "The Midrash of Philo",
"versionTitle": "The Midrash of Philo, by Samuel Belkin, 1989",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001117662",
"language": "he",
"text": text,
}
functions.post_text("The Midrash of Philo", text, index_count="on")
def post_avot_comm(title, book_text):
send_text = {
"text": book_text,
"versionTitle": "ToratEmet",
"versionSource":
"http://www.toratemetfreeware.com/online/f_01313.html",
"language": "he"
}
post_text(title, send_text, server="http://draft.sefaria.org")
def tt_text_post(text_dict):
for key in text_dict.keys():
version_dict = {
'versionTitle': 'Perush al ha-Torah, Hanover, 1838',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001935796',
'language': 'he',
'text': text_dict[key]
}
post_text('Tur HaAroch, {}'.format(key), version_dict)
def intro_text_post():
version_dict = {
'versionTitle': 'Perush al ha-Torah, Hanover, 1838',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001935796',
'language': 'he',
'text':
[u'צריך להקליד את ההקדמה'] # note: if ever coming back to this script
}
post_text('Tur HaAroch, Introduction', version_dict)
def post_the_text(jagged_array, title_counter):
ref = create_ref(title_counter)
text = create_text(jagged_array)
if title_counter > 0:
list_of_links = create_links(jagged_array, title_counter)
#The post_text must be after the creation of the links because create_links() changes the actual text
functions.post_text(ref, text)
if title_counter > 0:
print 1
functions.post_link(list_of_links)
def en_tt_text_post(en_text):
for key in en_text.keys():
version_dict = {
'versionTitle': 'Tur on the Torah, trans. Eliyahu Munk',
'versionSource':
'http://www.urimpublications.com/Merchant2/merchant.mv?Screen=PROD&Store_Code=UP&Product_Code=TUR&Category_Code=bde',
'language': 'en',
'text': en_text[key].array()
}
post_text('Tur HaAroch, {}'.format(key), version_dict)
def post():
parsed = parse()
post_index(build_index(parsed['titles']))
version = {
'versionTitle': 'Sefer HaKana',
'versionSource': 'http://www.hebrew.grimoar.cz/anonym/sefer_ha-kana.htm',
'language': 'he',
'text': parsed['text']
}
post_text('Sefer HaKana', version, index_count='on')
def post_text(parsed_data):
for book in library.get_indexes_in_category('Torah'):
version = {
'versionTitle': 'Siftei Hakhamim',
'versionSource': 'http://www.toratemetfreeware.com/',
'language': 'he',
'text': parsed_data[book]
}
functions.post_text('Siftei Hakhamim, {}'.format(book), version)
def post(book):
title = 'Ibn Ezra on {}'.format(book)
version = {
'title': title,
'versionTitle': 'Ibn Ezra on the Pentateuch; trans. by Jay F. Shachter',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001028367',
'language': 'en',
'text': parse(file_data[book])
}
post_text(title, version)
def post_text(parsed_data):
for book in library.get_indexes_in_category('Torah'):
version = {
'versionTitle': 'Siftei Hakhamim',
'versionSource': 'http://www.toratemetfreeware.com/',
'language': 'he',
'text': parsed_data[book]
}
functions.post_text('Siftei Hakhamim, {}'.format(book), version)
def upload_text(parser):
assert isinstance(parser, Malbim)
book = parser.parsed_text
version = {
"versionTitle": "Malbim, Vilna Romm, 1892.",
"versionSource": 'http://dlib.rsl.ru/viewer/01006563898#?page=1',
"language": 'he',
"text": book
}
functions.post_text("Malbim on Genesis", version, index_count='on')
def post_raavad_text(text_dict):
# version for all the ja
for ja in text_dict.keys():
version = {
'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': text_dict[ja]
}
if ja != 'old_parsing_of_perush':
post_text(ja, version)
def post_raavad_text(text_dict):
# version for all the ja
for ja in text_dict.keys():
version = {
# 'versionTitle': 'Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': text_dict[ja]
}
if ja != 'old_parsing_of_perush':
post_text(ja, version)
def upload_text(parser):
assert isinstance(parser, Malbim)
book = parser.parsed_text
version = {
"versionTitle": "Malbim, Vilna Romm, 1892.",
"versionSource": 'http://dlib.rsl.ru/viewer/01006563898#?page=1',
"language": 'he',
"text": book
}
functions.post_text("Malbim on Genesis", version, index_count='on')
def post():
parsed = parse()
post_index(build_index(parsed['titles']))
version = {
'versionTitle': 'Sefer HaKana',
'versionSource':
'http://www.hebrew.grimoar.cz/anonym/sefer_ha-kana.htm',
'language': 'he',
'text': parsed['text']
}
post_text('Sefer HaKana', version, index_count='on')
def post():
parsed = parse('targum.txt')
for i in range(1, 3):
functions.post_index(build_index(i))
version = {
'versionTitle': 'Wikisource Aramaic Targum to Chronicles',
'versionSource': url,
'language': 'he',
'text': parsed[i-1]
}
functions.post_text('Aramaic Targum to {} Chronicles'.format('I' * i), version)
functions.post_link(build_links(parsed))
def upload_text(parser):
assert isinstance(parser, Malbim)
book = parser.parsed_text
version = {
"versionTitle": "Malbim on Genesis -- Wikisource",
"versionSource":
'https://he.wikisource.org/wiki/%D7%9E%D7%9C%D7%91%D7%99%22%D7%9D_%D7%A2%D7%9C_%D7%91%D7%A8%D7%90%D7%A9%D7%99%D7%AA',
"language": 'he',
"text": book
}
functions.post_text("Malbim on Genesis", version, index_count='on')
def post_simple_commentaries():
ramban_node, rasag_node = JaggedArrayNode(), JaggedArrayNode()
ramban_text = parse_general('yitzira_ramban.txt')
rasag_text = parse_general('yitzira_rasag.txt')
ramban_node.add_title("Ramban on Sefer Yetzirah", 'en', primary=True)
ramban_node.add_title(u'רמב"ן על ספר יצירה', 'he', primary=True)
ramban_node.key = "Ramban on Sefer Yetzirah"
ramban_node.addressTypes = ['Integer', 'Integer', 'Integer']
ramban_node.sectionNames = ["Chapter", "Mishnah", "Comment"]
ramban_node.toc_zoom = 2
ramban_node.depth = 3
ramban_node.validate()
rasag_node.add_title("Rasag on Sefer Yetzirah", 'en', primary=True)
rasag_node.add_title(u'רס"ג על ספר יצירה', 'he', primary=True)
rasag_node.key = "Rasag on Sefer Yetzirah"
rasag_node.addressTypes = ['Integer', 'Integer', 'Integer']
rasag_node.sectionNames = ["Chapter", "Mishnah", "Comment"]
rasag_node.toc_zoom = 2
rasag_node.depth = 3
rasag_node.validate()
ramban_index = {
"title": "Ramban on Sefer Yetzirah",
"categories": ["Commentary2", "Kabbalah", "Ramban"],
"language": "he",
"schema": ramban_node.serialize()
}
post_index(ramban_index)
post_text("Ramban on Sefer Yetzirah", {
'versionTitle': 'Ramban on Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': ramban_text
})
rasag_index = {
"title": "Rasag on Sefer Yetzirah",
"categories": ["Commentary2", "Kabbalah", "Rasag"],
"language": "he",
"schema": rasag_node.serialize()
}
post_index(rasag_index)
post_text("Rasag on Sefer Yetzirah", {
'versionTitle': 'Rasage on Sefer Yetzirah, Warsaw 1884',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001310968',
'language': 'he',
'text': rasag_text
})
links = linker(ramban_text, "Ramban on Sefer Yetzirah")
links.extend(linker(rasag_text, "Rasag on Sefer Yetzirah"))
post_link(links)
def run(self):
for chapter, length in enumerate(self.chapter_lengths):
self.get_text(chapter, length)
print self.extra
send_text = {
"text": self.text,
"language": "he",
"versionTitle": "Kuzari in Judeo-Arabic",
"versionSource": "http://www.cs.toronto.edu/~yuvalf/kuzari.html"
}
post_text("Kuzari", send_text, server="http://proto.sefaria.org")
def run(self):
for chapter, length in enumerate(self.chapter_lengths):
self.get_text(chapter, length)
print self.extra
send_text = {
"text": self.text,
"language": "he",
"versionTitle": "Kuzari in Judeo-Arabic",
"versionSource": "http://www.cs.toronto.edu/~yuvalf/kuzari.html"
}
post_text("Kuzari", send_text, server="http://proto.sefaria.org")
def post(self):
for index in self.base_indices:
post_index(index, weak_network=True)
for he_author in self.commentarySchemas.keys():
en_author = DCXMLsubs.commentatorNames[he_author]
index = {
'title': en_author,
'categories': ['Commentary2', 'Masechtot Ketanot', en_author],
'schema': self.commentarySchemas[he_author].serialize()
}
post_index(index)
for version in self.versionList:
post_text(version['ref'], version['version'], index_count='on', weak_network=True)
post_link(self.linkSet)
def post():
post_index(construct_index())
base_text = restructure_text()
links = build_links(base_text)
version = {
'versionTitle': u'Derech Chaim, Maharal',
'versionSource': u'http://mobile.tora.ws/',
'language': 'he',
'text': base_text
}
post_text("Derech Chaim", version)
version['text'] = get_intro()
post_text("Derech Chaim, Author's Introduction", version, index_count='on')
post_link(links)
def post_text_and_index(text_struct, section_names):
index = build_index(section_names)
functions.post_index(index)
for section_num, section in enumerate(section_names):
new_text = {
"versionTitle": 'Noda BeYehuda Warsaw 1880',
"versionSource": 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001983501',
"language": 'he',
"text": text_struct[section_num]
}
functions.post_text('Noda BeYehuda, {}'.format(section), new_text)
def upload_text(parser):
assert isinstance(parser, PeneiDavid)
for book in parser.book_names:
for parsha in parser.parsha_by_book[book]:
print 'uploading {}'.format(parsha)
version = {
"versionTitle": "Torat Emet Penei David",
"versionSource": url,
"language": 'he',
"text": parser.parsed_as_dict[book][parsha]
}
functions.post_text("Penei David, {}, {}".format(book, parsha),
version)
def post():
post_index(construct_index())
base_text = restructure_text()
links = build_links(base_text)
version = {
'versionTitle': u'Derech Chaim, Maharal',
'versionSource': u'http://mobile.tora.ws/',
'language': 'he',
'text': base_text
}
post_text("Derech Chaim", version)
version['text'] = get_intro()
post_text("Derech Chaim, Author's Introduction", version, index_count='on')
post_link(links)
def post_text_and_index(text_struct, section_names):
index = build_index(section_names)
functions.post_index(index)
for section_num, section in enumerate(section_names):
new_text = {
"versionTitle": 'Noda BeYehuda Warsaw 1880',
"versionSource":
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001983501',
"language": 'he',
"text": text_struct[section_num]
}
functions.post_text('Noda BeYehuda, {}'.format(section), new_text)
def upload(text, text_name):
"""
Upload Mishnah tractate.
:param text: Jagged array like object of the tractate.
:param text_name: name of the text - to be used for url derivation for upload
"""
tractate = {
"versionTitle": "Vilna Mishna",
"versionSource": "http://www.daat.ac.il/encyclopedia/value.asp?id1=836",
"language": "he",
"text": text,
}
print 'uploading {}'.format(text_name)
functions.post_text(text_name, tractate)
def post_hagahot(ja_hg):
replace_dict = {
u"@11\([\u05d0-\u05ea]{1,3}\)\s?@33": u"",
u"@77": u"",
u"@44": u"<br>",
u"@55": u"<b>",
u"@66": u"</b>",
u"@00(.+?)\s(.+)": u"",
u"@(?:99|01)(.*?)@": ur"<br><small>\1</small><br>"
}
ja_hg = before_post_cleaner(ja_hg, replace_dict)
text_version = {
'versionTitle': 'Sefer Mitzvot Katan, Kopys, 1820',
'versionSource':
'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001771677',
'language': 'he',
'text': ja_hg
}
schema = JaggedArrayNode()
schema.add_title('Haggahot Chadashot on Sefer Mitzvot Katan', 'en', True)
schema.add_title(u'הגהות חדשות על ספר מצוות קטן', 'he', True)
schema.key = 'Haggahot Chadashot on Sefer Mitzvot Katan'
schema.depth = 2
schema.addressTypes = ['Integer', 'Integer']
schema.sectionNames = ['Siman', 'Segment']
schema.validate()
add_term('Haggahot Chadashot on Sefer Mitzvot Katan',
u'הגהות חדשות על ספר מצוות קטן')
index_dict = {
'title':
'Haggahot Chadashot on Sefer Mitzvot Katan',
'dependence':
"Commentary",
'base_text_titles': [
"Sefer Mitzvot Katan",
'Haggahot Rabbeinu Peretz on Sefer Mitzvot Katan'
],
"categories": ["Halakhah", "Commentary"],
'schema':
schema.serialize(), # This line converts the schema into json
'collective_title':
'Haggahot Chadashot on Sefer Mitzvot Katan',
}
post_index(index_dict)
post_text('Haggahot Chadashot on Sefer Mitzvot Katan', text_version)
def post_rashi(en_text, he_text, title, server):
if "II" in title:
title = "Rashi on II Kings"
else:
title = "Rashi on I Kings"
for lang, text in [("en", en_text), ("he", he_text)]:
for ch_num in text.keys():
text[ch_num] = convertDictToArray(text[ch_num])
text = convertDictToArray(text)
send_text = {
"text": text,
"language": lang,
"versionTitle": "Metsudah {} -- {}".format(title, lang),
"versionSource": "http://www.sefaria.org"
}
post_text(title, send_text, server=server)
def post():
books = file_to_books()
for book in library.get_indexes_in_category('Torah'):
books[book] = align_text(books[book], u'@\u05e4\u05e8\u05e7 [\u05d0-\u05ea]{1,2}', u'[0-9]{1,2}\.')
functions.post_index(build_index())
node_names = ['Introduction'] + library.get_indexes_in_category('Torah')
for name in node_names:
version = {
'versionTitle': 'Tafsir al-Torah bi-al-Arabiya, Paris, 1893',
'versionSource': 'http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001863864',
'language': 'he',
'text': books[name]
}
functions.post_text('Tafsir Rasag, {}'.format(name), version)
functions.post_link(build_links(books))
def upload_text(full_text, upload=False):
"""
:param full_text: Data structure from parse_text()
:param upload: set to True, otherwise function will do nothing
"""
if not upload:
return
# make JSON object of book
for ref in full_text.keys():
book = {
"versionTitle": "Chizkuni",
"versionSource": "Chizkuni",
"language": "he",
"text": full_text[ref]
}
print ref
post_text('Chizkuni,_{}'.format(ref), book)
def upload():
post_index(construct_index())
version = {
'versionTitle': 'Placeholder',
'versionSource': 'http://www.hebrew.grimoar.cz/azulaj/chesed_le-avraham.htm',
'language': 'he',
'text': parse_intro()
}
post_text('Chesed LeAvraham, Introduction', version)
body = parse_body()
for i, part in enumerate(body):
version['text'] = part
post_text('Chesed LeAvraham, Even Shetiya, Maayan {}'.format(i+1), version)
version['text'] = parse_shokets()
post_text('Chesed LeAvraham, Breichat Avraham', version, index_count='on')