Skip to content

Fix app not working for Python 3.10 #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yashovardhan99 merged 3 commits into from
Aug 23, 2025
Merged

Fix app not working for Python 3.10 #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dd10a81
Add client summary PDF to multiprocessing
yashovardhan99 Aug 22, 2025
cd1ee03
Refactor read excel
yashovardhan99 Aug 22, 2025
957c050
Add tomli for python 3.10 support
yashovardhan99 Aug 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

### Fixed

- Added 3rd party toml library to support Python version 3.10

## [0.1.1] - 2025-08-22

### Changed
Expand Down
2 changes: 1 addition & 1 deletion bulkinvoicer/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ def main() -> None:
logger.critical(e, exc_info=True)
else:
logger.critical("Bulkinvoicer encountered an error.")
logger.critical("Run with --debug for more details.")
logger.critical(e)
sys.exit(1)

logger.info("Bulkinvoicer finished successfully.")
Expand Down
298 changes: 182 additions & 116 deletions bulkinvoicer/driver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

import datetime
from pathlib import Path
import tomllib
import sys
import logging
from typing import Any
import polars as pl
Expand All @@ -12,14 +12,23 @@
from bulkinvoicer.pdf import PDF
from tqdm import tqdm
from tqdm.contrib.logging import logging_redirect_tqdm
from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
from concurrent.futures import (
Future,
ProcessPoolExecutor,
ThreadPoolExecutor,
as_completed,
)

# Configure logging
logger = logging.getLogger(__name__)


def load_config(config_file: str) -> Config:
"""Load configuration from a TOML file."""
if sys.version_info >= (3, 11):
import tomllib
else:
import tomli as tomllib
try:
with open(config_file, "rb") as f:
config = tomllib.load(f)
Expand Down Expand Up @@ -51,37 +60,14 @@ def generate(config: Config) -> None:
if logger.isEnabledFor(logging.DEBUG):
logger.debug("Configuration: %s", config)

logger.info("Reading data from Excel files.")

date_format_invoice = config.invoice.date_format
decimals_invoice = config.invoice.decimals

date_format_receipt = config.receipt.date_format
decimals_receipt = config.receipt.decimals

df_invoice_data = pl.read_excel(
config.excel.filepath,
sheet_name="invoices",
)

df_receipt_data = pl.read_excel(
config.excel.filepath,
sheet_name="receipts",
)

df_clients = pl.read_excel(
config.excel.filepath,
sheet_name="clients",
schema_overrides={
"name": pl.String,
"display name": pl.String,
"address": pl.String,
"phone": pl.String,
"email": pl.String,
},
)
df_invoice_data, df_receipt_data, df_clients = read_excel(config)

logger.info("Data loaded from Excel files. Starting data processing.")
if logger.isEnabledFor(logging.DEBUG):
logger.debug("Invoice DataFrame: %s", df_invoice_data)
logger.debug("Clients DataFrame: %s", df_clients)
Expand Down Expand Up @@ -697,101 +683,98 @@ def generate(config: Config) -> None:
)

elif output_type == "clients":
if include_summary:
logger.info("Generating summary PDF")

pdf = PDF(
config=config,
cover_page=True,
)
pdf.set_title(f"{key} Overall Summary")

pdf.add_combined_summary(summary_details, toc_level=0)

pdf.output(path.format(CLIENT="summary"))

df_transactions = (
pl.concat(
[
df_invoices_close.select(
"sort_date",
pl.col("date"),
pl.col("client"),
pl.lit("Invoice").alias("type"),
pl.col("number").alias("reference"),
pl.col("total").alias("amount"),
),
df_receipts_close.select(
"sort_date",
pl.col("date"),
pl.col("client"),
pl.lit("Receipt").alias("type"),
pl.col("number").alias("reference"),
pl.col("amount").neg(),
),
]
)
.sort("sort_date")
.with_columns(
pl.col("amount")
.cum_sum()
.over("client")
.alias("balance")
)
.filter(
pl.col("sort_date").is_between(start_date, end_date)
)
)
else:
df_transactions = None

logger.info("Generating PDFs for each client.")

with ProcessPoolExecutor() as executor:
futures = [
executor.submit(
generate_client_pdf,
config,
client_id,
df_invoices_report.filter(
pl.col("client") == client_id
).to_dicts(),
df_receipts_report.filter(
pl.col("client") == client_id
).to_dicts(),
df_transactions.filter(pl.col("client") == client_id)
.drop("client")
.to_dicts()
if df_transactions is not None
else None,
reporting_period_text,
include_summary,
df_client_summaries.filter(
pl.col("client") == client_id
).row(0, named=True)
if df_client_summaries is not None
else {},
df_balance.filter(
(pl.col("client") == client_id)
& (
(pl.col("invoiced") != 0)
| (pl.col("received") != 0)
)
if include_summary:
futures = [
executor.submit(
generate_client_summary_pdf, config, summary_details
)
.select(
"sort_date",
"open",
"invoiced",
"received",
"balance",
]
df_transactions = (
pl.concat(
[
df_invoices_close.select(
"sort_date",
pl.col("date"),
pl.col("client"),
pl.lit("Invoice").alias("type"),
pl.col("number").alias("reference"),
pl.col("total").alias("amount"),
),
df_receipts_close.select(
"sort_date",
pl.col("date"),
pl.col("client"),
pl.lit("Receipt").alias("type"),
pl.col("number").alias("reference"),
pl.col("amount").neg(),
),
]
)
.sort("sort_date")
.to_dicts()
if df_balance is not None
else None,
.with_columns(
pl.col("amount")
.cum_sum()
.over("client")
.alias("balance")
)
.filter(
pl.col("sort_date").is_between(start_date, end_date)
)
)
for client_id in clients.to_series()
]
else:
df_transactions = None

logger.info("Generating PDFs for each client.")

futures.extend(
[
executor.submit(
generate_client_pdf,
config,
client_id,
df_invoices_report.filter(
pl.col("client") == client_id
).to_dicts(),
df_receipts_report.filter(
pl.col("client") == client_id
).to_dicts(),
df_transactions.filter(
pl.col("client") == client_id
)
.drop("client")
.to_dicts()
if df_transactions is not None
else None,
reporting_period_text,
include_summary,
df_client_summaries.filter(
pl.col("client") == client_id
).row(0, named=True)
if df_client_summaries is not None
else {},
df_balance.filter(
(pl.col("client") == client_id)
& (
(pl.col("invoiced") != 0)
| (pl.col("received") != 0)
)
)
.select(
"sort_date",
"open",
"invoiced",
"received",
"balance",
)
.sort("sort_date")
.to_dicts()
if df_balance is not None
else None,
)
for client_id in clients.to_series()
]
)

with ThreadPoolExecutor() as thread_executor:
futures_pdfs = []
Expand Down Expand Up @@ -828,6 +811,89 @@ def generate(config: Config) -> None:
)


def read_excel(config: Config) -> tuple[pl.DataFrame, pl.DataFrame, pl.DataFrame]:
"""Read Excel file and return dataframes for invoices, receipts, and clients."""
logger.info("Reading data from Excel files.")

with ThreadPoolExecutor(max_workers=3) as executor:
future_invoice_data = executor.submit(
pl.read_excel,
config.excel.filepath,
sheet_name="invoices",
)
future_receipt_data = executor.submit(
pl.read_excel,
config.excel.filepath,
sheet_name="receipts",
)
future_clients = executor.submit(
pl.read_excel,
config.excel.filepath,
sheet_name="clients",
schema_overrides={
"name": pl.String,
"display name": pl.String,
"address": pl.String,
"phone": pl.String,
"email": pl.String,
},
)

exceptions: list[Exception] = []

def get_results(future: Future[pl.DataFrame]) -> pl.DataFrame:
try:
return future.result()
except TimeoutError as e:
logger.critical("Reading Excel file timed out.")
exceptions.append(e)
except (FileNotFoundError, ValueError) as e:
logger.critical(f"Error reading Excel file: {e}")
exceptions.append(e)
except pl.exceptions.PolarsError as e:
logger.critical(f"Polars error reading Excel file: {e}")
exceptions.append(e)
except Exception as e:
logger.critical(f"Unexpected error reading Excel file: {e}")
exceptions.append(e)

return pl.DataFrame()

df_invoice_data = get_results(future_invoice_data)
df_receipt_data = get_results(future_receipt_data)
df_clients = get_results(future_clients)

if exceptions:
if sys.version_info < (3, 11):
raise ValueError(
f"Errors occurred while reading Excel files: {exceptions}"
)
else:
from builtins import ExceptionGroup

raise ExceptionGroup(
"Errors occurred while reading Excel files.",
exceptions,
)
logger.info("Data loaded from Excel files.")
return (df_invoice_data, df_receipt_data, df_clients)


def generate_client_summary_pdf(config, summary_details) -> tuple[str, bytearray]:
"""Generate summary PDF for all clients."""
logger.info("Generating summary PDF")

pdf = PDF(
config=config,
cover_page=True,
)
pdf.set_title("Overall Summary")

pdf.add_combined_summary(summary_details, toc_level=0)

return "summary", pdf.output()


def generate_client_pdf(
config: Config,
client_id: str,
Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ dependencies = [
"uharfbuzz",
"tqdm >= 4.67.1, < 5.0.0",
"pydantic >= 2.11.7, < 3.0.0",
'tomli ; python_version < "3.11"',
]
requires-python = ">=3.10"
authors = [
Expand Down