2 Commits

Author SHA1 Message Date
Jake 7b929b3b84 fix: 🐛 Fixed time calculations for ETA & Completion 2025-12-12 19:50:04 +00:00
Jake 2c4c4a3f4e feat: added the extraction proces into the main multithreaded loop
Also added a warning when the app finds existing CSV files in the combined folder
2025-12-12 18:35:26 +00:00
4 changed files with 11 additions and 8 deletions
+1 -1
View File
@@ -15,7 +15,7 @@ The project consists of a main pipeline workflow that processes multiple modules
### main.py ### main.py
- **Startup Safety Check**: Scans the `COMBINED_FOLDER` at startup and warns the user if existing files are found, Deleting existing files if continue is accepted. - **Startup Safety Check**: Scans the `COMBINED_FOLDER` at startup and warns the user if existing files are found, offering a chance to abort to prevent accidental data mixing.
- **Batch Processing**: Processes input tar files in configurable batches to manage resource usage. - **Batch Processing**: Processes input tar files in configurable batches to manage resource usage.
- **End-to-End Processing**: Extracts GZ files, processes DAT/ASC, and appends to CSV in a single thread per file. - **End-to-End Processing**: Extracts GZ files, processes DAT/ASC, and appends to CSV in a single thread per file.
- **Concurrency**: Uses multi-threading to process individual GZ files within a batch concurrently. - **Concurrency**: Uses multi-threading to process individual GZ files within a batch concurrently.
+7 -4
View File
@@ -92,16 +92,13 @@ if __name__ == "__main__":
f"Found {len(existing_combined)} files in {Config.COMBINED_FOLDER}" f"Found {len(existing_combined)} files in {Config.COMBINED_FOLDER}"
) )
logging.warning( logging.warning(
"If you continue these WILL BE DELETED, Please make sure you have them saved." "You may want to remove these before continuing to avoid duplicates or messy data."
) )
logging.warning("!" * 80) logging.warning("!" * 80)
response = input("Continue? (Y/N): ").strip().lower() response = input("Continue? (Y/N): ").strip().lower()
if response != "y": if response != "y":
logging.info("Aborting...") logging.info("Aborting...")
exit(0) exit(0)
else:
shutil.rmtree(Path(Config.COMBINED_FOLDER)) # Delete everything including the directory
Path(Config.COMBINED_FOLDER).mkdir()
extraction = Extract(Config) extraction = Extract(Config)
batch = BatchNimrod(Config) batch = BatchNimrod(Config)
@@ -133,6 +130,12 @@ if __name__ == "__main__":
# 1. Extract batch (TAR -> GZ) # 1. Extract batch (TAR -> GZ)
logging.info("Extracting tar files for batch") logging.info("Extracting tar files for batch")
extraction.extract_tar_batch(batch_files) extraction.extract_tar_batch(batch_files)
# Note: We do NOT run extract_gz_batch anymore. We will find GZ files and process them.
# Get list of GZ files (recursively or flat?)
# extract_tar_batch puts them in GZ_TOP_FOLDER/tar_name_without_ext
# So we need to look there.
# Ideally we know where we put them.
gz_files_to_process = [] gz_files_to_process = []
for tar_file in batch_files: for tar_file in batch_files:
+2 -2
View File
@@ -1,7 +1,7 @@
[project] [project]
name = "met-office" name = "met-office"
version = "1.3.2" version = "1.3.1"
description = "Convert nimrod files to .csv timeseries" description = "Convert .dat nimrod files to .asc files"
readme = "README.md" readme = "README.md"
requires-python = ">=3.14" requires-python = ">=3.14"
dependencies = [ dependencies = [
Generated
+1 -1
View File
@@ -4,7 +4,7 @@ requires-python = ">=3.14"
[[package]] [[package]]
name = "met-office" name = "met-office"
version = "1.3.2" version = "1.3.1"
source = { virtual = "." } source = { virtual = "." }
dependencies = [ dependencies = [
{ name = "numpy" }, { name = "numpy" },