klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-09 13:25:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Extract empty line escape sequences var into constants file for reuse

Browse Source
This commit is contained in:
Debanjum Singh Solanky
2022-02-27 19:01:49 -05:00
parent 624a3faf92
commit 3d8a07f252
2 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/processor/ledger/beancount_to_jsonl.py
View File

@@ -11,6 +11,7 @@ import re
# Internal Packages # Internal Packages
from src.processor.org_mode import orgnode from src.processor.org_mode import orgnode
from src.utils.helpers import get_absolute_path, is_none_or_empty from src.utils.helpers import get_absolute_path, is_none_or_empty
from src.utils.constants import empty_escape_sequences
# Define Functions # Define Functions
@@ -62,7 +63,6 @@ def load_jsonl(input_path, verbose=0):
# Initialize Variables # Initialize Variables
data = [] data = []
jsonl_file = None jsonl_file = None
escape_sequences = '\n|\r\t '
# Open JSONL file # Open JSONL file
if input_path.suffix == ".gz": if input_path.suffix == ".gz":
@@ -72,7 +72,7 @@ def load_jsonl(input_path, verbose=0):
# Read JSONL file # Read JSONL file
for line in jsonl_file: for line in jsonl_file:
data.append(json.loads(line.strip(escape_sequences))) data.append(json.loads(line.strip(empty_escape_sequences)))
# Close JSONL file # Close JSONL file
jsonl_file.close() jsonl_file.close()
@@ -114,13 +114,13 @@ def extract_beancount_entries(beancount_files):
# Initialize Regex for extracting Beancount Entries # Initialize Regex for extracting Beancount Entries
date_regex = r'^\n?\d{4}-\d{2}-\d{2}' date_regex = r'^\n?\d{4}-\d{2}-\d{2}'
empty_newline = r'^[\n\r\t ]*$' empty_newline = f'^[{empty_escape_sequences}]*$'
entries = [] entries = []
for beancount_file in beancount_files: for beancount_file in beancount_files:
with open(beancount_file) as f: with open(beancount_file) as f:
ledger_content = f.read() ledger_content = f.read()
entries.extend([entry.strip('\n|\r|\t| ') entries.extend([entry.strip(empty_escape_sequences)
for entry for entry
in re.split(empty_newline, ledger_content, flags=re.MULTILINE) in re.split(empty_newline, ledger_content, flags=re.MULTILINE)
if re.match(date_regex, entry)]) if re.match(date_regex, entry)])

1
src/utils/constants.py Normal file
View File

@@ -0,0 +1 @@
empty_escape_sequences = r'\n|\r\t '