aiolabs/castle
1
0
Fork 0
Code Issues 5 Pull requests 2 Projects Releases 5 Packages Wiki Activity Actions

Optimize get_journal_entries with server-side date filtering

Browse source 
Use Fava's 'time' query parameter to filter entries on the server
instead of fetching all entries and filtering in Python.

This reduces:
- Data transfer (only relevant entries are sent)
- Memory usage (no need to hold all entries)
- Processing time (no Python-side date parsing/filtering)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
padreug 2025-12-15 01:12:33 +01:00
parent 49d18c3e73
commit addf4cd05f
1 changed files with 26 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

67
fava_client.py
View file

@ -866,6 +866,9 @@ class FavaClient:
""" """
Get journal entries from Fava (with entry hashes), optionally filtered by date. Get journal entries from Fava (with entry hashes), optionally filtered by date.
Uses Fava's server-side 'time' parameter for efficient date filtering,
avoiding the need to fetch all entries and filter in Python.
Args: Args:
days: If provided, only return entries from the last N days. days: If provided, only return entries from the last N days.
If None, returns all entries (default behavior). If None, returns all entries (default behavior).
@ -890,59 +893,35 @@ class FavaClient:
# Get entries in custom date range # Get entries in custom date range
custom = await fava.get_journal_entries(start_date="2024-01-01", end_date="2024-01-31") custom = await fava.get_journal_entries(start_date="2024-01-01", end_date="2024-01-31")
""" """
try:
async with httpx.AsyncClient(timeout=self.timeout) as client:
response = await client.get(f"{self.base_url}/journal")
response.raise_for_status()
result = response.json()
entries = result.get("data", [])
logger.info(f"Fava /journal returned {len(entries)} entries")
# Filter by date range or days
from datetime import datetime, timedelta from datetime import datetime, timedelta
try:
# Build query parameters for server-side filtering
params = {}
# Use date range if both start_date and end_date are provided # Use date range if both start_date and end_date are provided
if start_date and end_date: if start_date and end_date:
try: # Fava uses "YYYY-MM-DD - YYYY-MM-DD" format for time ranges
filter_start = datetime.strptime(start_date, "%Y-%m-%d").date() params["time"] = f"{start_date} - {end_date}"
filter_end = datetime.strptime(end_date, "%Y-%m-%d").date() logger.info(f"Querying journal with date range: {start_date} to {end_date}")
filtered_entries = []
for e in entries:
entry_date_str = e.get("date")
if entry_date_str:
try:
entry_date = datetime.strptime(entry_date_str, "%Y-%m-%d").date()
if filter_start <= entry_date <= filter_end:
filtered_entries.append(e)
except (ValueError, TypeError):
# Include entries with invalid dates (shouldn't happen)
filtered_entries.append(e)
logger.info(f"Filtered to {len(filtered_entries)} entries between {start_date} and {end_date}")
entries = filtered_entries
except ValueError as e:
logger.error(f"Invalid date format: {e}")
# Return all entries if date parsing fails
# Fall back to days filter if no date range provided # Fall back to days filter if no date range provided
elif days is not None: elif days is not None:
cutoff_date = (datetime.now() - timedelta(days=days)).date() cutoff_date = (datetime.now() - timedelta(days=days)).date()
filtered_entries = [] today = datetime.now().date()
for e in entries: params["time"] = f"{cutoff_date.isoformat()} - {today.isoformat()}"
entry_date_str = e.get("date") logger.info(f"Querying journal for last {days} days (from {cutoff_date})")
if entry_date_str:
try:
entry_date = datetime.strptime(entry_date_str, "%Y-%m-%d").date()
if entry_date >= cutoff_date:
filtered_entries.append(e)
except (ValueError, TypeError):
# Include entries with invalid dates (shouldn't happen)
filtered_entries.append(e)
logger.info(f"Filtered to {len(filtered_entries)} entries from last {days} days (cutoff: {cutoff_date})")
entries = filtered_entries
# Log transactions with "Lightning payment" in narration async with httpx.AsyncClient(timeout=self.timeout) as client:
lightning_entries = [e for e in entries if "Lightning payment" in e.get("narration", "")] response = await client.get(f"{self.base_url}/journal", params=params)
logger.info(f"Found {len(lightning_entries)} Lightning payment entries in journal") response.raise_for_status()
result = response.json()
entries = result.get("data", [])
if params:
logger.info(f"Fava /journal returned {len(entries)} entries (filtered)")
else:
logger.info(f"Fava /journal returned {len(entries)} entries (all)")
return entries return entries