def test_modify_text_by_function():
original = TextChunk(Ref("Job"), vtitle="The Holy Scriptures: A New Translation (JPS 1917)")
total_spaces = JaggedTextArray(original.text).flatten_to_string(joiner="|").count(" ")
v = Version({
"language": "en",
"title": "Job",
"versionSource": "http://foobar.com",
"versionTitle": "TextChangeTest",
"chapter": original.text
}).save()
modify_text_by_function("Job", "TextChangeTest", "en", lambda x, sections: x.replace(" ", "$"), 23432)
modified = TextChunk(Ref("Job"), vtitle="TextChangeTest")
total_dollars = JaggedTextArray(modified.text).flatten_to_string(joiner="|").count("$")
v.delete()
assert total_dollars > 0
assert total_spaces == total_dollars
def test_modify_text_by_function():
original = TextChunk(Ref("Job"), vtitle="The Holy Scriptures: A New Translation (JPS 1917)")
total_spaces = JaggedTextArray(original.text).flatten_to_string(joiner=u"|").count(u" ")
v = Version({
"language": "en",
"title": "Job",
"versionSource": "http://foobar.com",
"versionTitle": "TextChangeTest",
"chapter": original.text
}).save()
modify_text_by_function("Job", "TextChangeTest", "en", lambda x: x.replace(u" ", u"$"), 23432)
modified = TextChunk(Ref("Job"), vtitle="TextChangeTest")
total_dollars = JaggedTextArray(modified.text).flatten_to_string(joiner=u"|").count(u"$")
v.delete()
assert total_dollars > 0
assert total_spaces == total_dollars
import re
from sefaria.model.text import IndexSet
from sefaria.helper.text import modify_text_by_function
def out_brace(raw_string):
temp_string = re.sub(r"\((.*?)\)", r"#\1%", raw_string)
temp_string = re.sub(r" [\u05d0-\u05ea]{1,2}\)", "", temp_string)
temp_string = temp_string.replace("#", "(")
temp_string = temp_string.replace("%", ")")
return temp_string
tyt = IndexSet({'title': {'$regex': '^Tosafot Yom Tov.*'}})
vtitle = 'Mishnah, ed. Romm, Vilna 1913'
for i, dex in enumerate(tyt):
print("{}/{}".format(i + 1, tyt.count()))
modify_text_by_function(dex.title, vtitle, 'he', out_brace, 23432)
dex.versionState().refresh()
import argparse
import re
from sefaria.model import *
from sefaria.helper.text import modify_text_by_function
def replace_double_quotes(text):
"""
:param text: the text to replace
:return:a text with all 2 character length double quotes replaced with a single character double quote.
"""
return text.replace("''", '"')
bible_books = library.get_indexes_in_category('Tanach')
for book in bible_books:
rashi_title = "Rashi on {}".format(book)
print rashi_title.encode('utf-8')
vs = VersionSet({'title': rashi_title, 'language': 'he'})
for v in vs:
modify_text_by_function(rashi_title, v.versionTitle, 'he', replace_double_quotes, 8646, skip_links=True)
talmud_books = library.get_indexes_in_category('Talmud')
for book in talmud_books:
rashi_title = "Rashi on {}".format(book)
print rashi_title.encode('utf-8')
vs = VersionSet({'title': rashi_title, 'language': 'he'})
for v in vs:
modify_text_by_function(rashi_title, v.versionTitle, 'he', replace_double_quotes, 8646, skip_links=True)
"""
:param text: the text to replace
:return:a text with all 2 character length double quotes replaced with a single character double quote.
"""
return text.replace("''", '"')
bible_books = library.get_indexes_in_category('Tanach')
for book in bible_books:
rashi_title = "Rashi on {}".format(book)
print rashi_title.encode('utf-8')
vs = VersionSet({'title': rashi_title, 'language': 'he'})
for v in vs:
modify_text_by_function(rashi_title,
v.versionTitle,
'he',
replace_double_quotes,
8646,
skip_links=True)
talmud_books = library.get_indexes_in_category('Talmud')
for book in talmud_books:
rashi_title = "Rashi on {}".format(book)
print rashi_title.encode('utf-8')
vs = VersionSet({'title': rashi_title, 'language': 'he'})
for v in vs:
modify_text_by_function(rashi_title,
v.versionTitle,
'he',
replace_double_quotes,
8646,
skip_links=True)