From e66cd5bf59e8bf1b0180cb6ee6b5266a088e453f Mon Sep 17 00:00:00 2001
From: Debanjum Singh Solanky <debanjum@gmail.com>
Date: Tue, 19 Jul 2022 19:50:58 +0400
Subject: [PATCH] Only extract transactions from Beancount

- Earlier was extracting all entries starting with dates but the other
  type of entries like account open/close, asserts etc aren't useful for
  querying
---
 src/processor/ledger/beancount_to_jsonl.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/processor/ledger/beancount_to_jsonl.py b/src/processor/ledger/beancount_to_jsonl.py
index 185be16e..ed6f9b4f 100644
--- a/src/processor/ledger/beancount_to_jsonl.py
+++ b/src/processor/ledger/beancount_to_jsonl.py
@@ -113,7 +113,7 @@ def extract_beancount_entries(beancount_files):
     "Extract entries from specified Beancount files"
 
     # Initialize Regex for extracting Beancount Entries
-    date_regex = r'^\n?\d{4}-\d{2}-\d{2}'
+    transaction_regex = r'^\n?\d{4}-\d{2}-\d{2} [\*|\!] '
     empty_newline = f'^[{empty_escape_sequences}]*$'
 
     entries = []
@@ -123,7 +123,7 @@ def extract_beancount_entries(beancount_files):
             entries.extend([entry.strip(empty_escape_sequences)
                for entry
                in re.split(empty_newline, ledger_content, flags=re.MULTILINE)
-               if re.match(date_regex, entry)])
+               if re.match(transaction_regex, entry)])
 
     return entries