klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: syntax cleanup (#172)

Browse Source
This commit is contained in:
gasolin
2023-07-07 18:40:10 +08:00
committed by GitHub
parent 5e6aef1e37
commit f08ee6420a
2 changed files with 6 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
embedchain/config/InitConfig.py
View File

@@ -33,4 +33,4 @@ class InitConfig(BaseConfig):
def _set_embedding_function(self, ef): def _set_embedding_function(self, ef):
self.ef = ef self.ef = ef
return return

11
embedchain/utils.py
View File

@@ -13,21 +13,20 @@ def clean_string(text):
""" """
# Replacement of newline characters: # Replacement of newline characters:
text = text.replace('\n', ' ') text = text.replace('\n', ' ')
# Stripping and reducing multiple spaces to single: # Stripping and reducing multiple spaces to single:
cleaned_text = re.sub(r'\s+', ' ', text.strip()) cleaned_text = re.sub(r'\s+', ' ', text.strip())
# Removing backslashes: # Removing backslashes:
cleaned_text = cleaned_text.replace('\\', '') cleaned_text = cleaned_text.replace('\\', '')
# Replacing hash characters: # Replacing hash characters:
cleaned_text = cleaned_text.replace('#', ' ') cleaned_text = cleaned_text.replace('#', ' ')
# Eliminating consecutive non-alphanumeric characters: # Eliminating consecutive non-alphanumeric characters:
# This regex identifies consecutive non-alphanumeric characters (i.e., not a word character [a-zA-Z0-9_] and not a whitespace) in the string # This regex identifies consecutive non-alphanumeric characters (i.e., not a word character [a-zA-Z0-9_] and not a whitespace) in the string
# and replaces each group of such characters with a single occurrence of that character. # and replaces each group of such characters with a single occurrence of that character.
# For example, "!!! hello !!!" would become "! hello !". # For example, "!!! hello !!!" would become "! hello !".
cleaned_text = re.sub(r'([^\w\s])\1*', r'\1', cleaned_text) cleaned_text = re.sub(r'([^\w\s])\1*', r'\1', cleaned_text)
return cleaned_text
return cleaned_text