coolneng
/
adapter-parser
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Refactor regex parenthesis removal into a function

This commit is contained in:
coolneng 2021-12-22 18:36:32 +01:00
parent fa23b1a950
commit 7ed975c7ce
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
parser.py
View File

@ -6,6 +6,9 @@ from re import sub
from pandas import DataFrame, read_html, Series from pandas import DataFrame, read_html, Series
def remove_parenthesis(identifier):
sequence_str = "".join(map(str, identifier))
return sub(r"[()]", "", sequence_str)
def extract_adapters(files) -> Tuple[Series, List]: def extract_adapters(files) -> Tuple[Series, List]:
@ -33,8 +36,7 @@ def preprocess_dataframe(adapters) -> Series:
def save_to_file(filename, adapters) -> None: def save_to_file(filename, adapters) -> None:
with open(filename, "w") as f: with open(filename, "w") as f:
for index, value in adapters.iteritems(): for index, value in adapters.iteritems():
sequence_str = "".join(map(str, index)) sequence_id = remove_parenthesis(index)
sequence_id = sub(r"[()]", "", sequence_str)
fasta_entry = f">{sequence_id}\n{value}\n" fasta_entry = f">{sequence_id}\n{value}\n"
f.write(fasta_entry) f.write(fasta_entry)