Skip to content

Format code with black #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Format code with black
This commit fixes the style issues introduced in 8ebb419 according to the output
from black.

Details: https://deepsource.io/gh/deterministic-algorithms-lab/Std-Indic-NLP/transform/3e12f8e4-1099-4b18-a4fc-debf3915afb3/
  • Loading branch information
deepsource-autofix[bot] authored Nov 23, 2020
commit c2d95729cb20027eca92599e14f5d0a660496807
125 changes: 68 additions & 57 deletions std_indic/cleaners.py
Original file line number Diff line number Diff line change
@@ -1,108 +1,119 @@
import re

BYTE_ORDER_MARK='\uFEFF'
BYTE_ORDER_MARK_2='\uFFFE'
WORD_JOINER='\u2060'
SOFT_HYPHEN='\u00AD'
BYTE_ORDER_MARK = "\uFEFF"
BYTE_ORDER_MARK_2 = "\uFFFE"
WORD_JOINER = "\u2060"
SOFT_HYPHEN = "\u00AD"

ZERO_WIDTH_SPACE='\u200B'
NO_BREAK_SPACE='\u00A0'
ZERO_WIDTH_SPACE = "\u200B"
NO_BREAK_SPACE = "\u00A0"

ZERO_WIDTH_NON_JOINER='\u200C'
ZERO_WIDTH_JOINER='\u200D'
ZERO_WIDTH_NON_JOINER = "\u200C"
ZERO_WIDTH_JOINER = "\u200D"


def clean_text(text):
text = text.lower()
text=text.replace(BYTE_ORDER_MARK,'')
text=text.replace(BYTE_ORDER_MARK_2,'')
text=text.replace(WORD_JOINER,'')
text=text.replace(SOFT_HYPHEN,'')

text=text.replace(ZERO_WIDTH_SPACE,' ') # ??
text=text.replace(NO_BREAK_SPACE,' ')

text=text.replace(ZERO_WIDTH_NON_JOINER, '')
text=text.replace(ZERO_WIDTH_JOINER,'')
text = re.sub(r"[-()\"#/@;:<>{}-=~|.?,]","",text)
text = text.replace(BYTE_ORDER_MARK, "")
text = text.replace(BYTE_ORDER_MARK_2, "")
text = text.replace(WORD_JOINER, "")
text = text.replace(SOFT_HYPHEN, "")

text = text.replace(ZERO_WIDTH_SPACE, " ") # ??
text = text.replace(NO_BREAK_SPACE, " ")

text = text.replace(ZERO_WIDTH_NON_JOINER, "")
text = text.replace(ZERO_WIDTH_JOINER, "")

text = re.sub(r"[-()\"#/@;:<>{}-=~|.?,]", "", text)
return text


def str_to_unicode(str):
return chr(int(str[2:],16))
return chr(int(str[2:], 16))


class resolve_cotractions(object):
def __init__(self, lang):
super().__init__()
self.lang = lang
self.contractions = []
with open('./std_indic/contractions/'+lang+'.txt', 'r') as f:
self.contractions = []
with open("./std_indic/contractions/" + lang + ".txt", "r") as f:
for line in f.readlines():
text = line.rstrip()
text = re.sub(r'\s+', r' ', text)
self.contractions.append(text.split(' ', 1))
text = re.sub(r"\s+", r" ", text)
self.contractions.append(text.split(" ", 1))

def resolve_contractions(self, text):
for contraction in self.contractions:
text = text.replace(contraction[0], contraction[1])
return text


class resolve_chars(object):
def __init__(self, lang):
super().__init__()
self.lang = lang
self.normalizations = []
with open('./std_indic/unicode_normalization/'+lang+'.txt', 'r') as f :
with open("./std_indic/unicode_normalization/" + lang + ".txt", "r") as f:
content = f.read()
replacements = re.findall(r'\[.+\]', content)
for elem in replacements :
elem = elem.strip('[]')
elems = elem.split(' , ')
self.normalizations.append( [str_to_unicode(elems[0]), str_to_unicode(elems[1])] )

def normalize(self, text) :
replacements = re.findall(r"\[.+\]", content)
for elem in replacements:
elem = elem.strip("[]")
elems = elem.split(" , ")
self.normalizations.append(
[str_to_unicode(elems[0]), str_to_unicode(elems[1])]
)

def normalize(self, text):
for norm in self.normalizations:
text = text.replace( norm[0], norm[1])
text = text.replace(norm[0], norm[1])
return text



class resolve_group_chars(object):
def __init__(self, lang):
super().__init__()
self.lang = lang
self.replaces = []
with open('./std_indic/unicode_normalization/groups/'+lang+'.txt', 'r') as f :
with open(
"./std_indic/unicode_normalization/groups/" + lang + ".txt", "r"
) as f:
for line in f.readlines():
line = re.sub(r'\s+',r' ',line.rstrip())
line = line.split('#')[0].rstrip()
#print(line)
original, replacement = line.split(' ')
line = re.sub(r"\s+", r" ", line.rstrip())
line = line.split("#")[0].rstrip()
# print(line)
original, replacement = line.split(" ")
match_str = self.make_pattern(original)
repl_str = self.make_pattern(replacement, True)
print(match_str, repl_str)
self.replaces.append((match_str, repl_str))
self.replaces.append((match_str, repl_str))

def make_pattern(self, original, is_replacement=False):
original_parts = original.split(',')
match_str = ''
#print(original_parts)
original_parts = original.split(",")
match_str = ""
# print(original_parts)
for part in original_parts:
if is_replacement:
if not part.startswith('0x'):
match_str += '\\g<'+part+'>'
if not part.startswith("0x"):
match_str += "\\g<" + part + ">"
else:
match_str += str_to_unicode(part)
else :
if '-' not in part:
match_str += '('+str_to_unicode(part)+')'
else:
if "-" not in part:
match_str += "(" + str_to_unicode(part) + ")"
else:
match_str += '([' + str_to_unicode(part.split('-')[0]) + '-' + str_to_unicode(part.split('-')[1]) + '])'
match_str += (
"(["
+ str_to_unicode(part.split("-")[0])
+ "-"
+ str_to_unicode(part.split("-")[1])
+ "])"
)
return match_str

def normalize(self, text) :
def normalize(self, text):
for norm in self.replaces:
print(norm[0], norm[1])
text = re.sub( norm[0], norm[1], text)
text = re.sub(norm[0], norm[1], text)
return text