From 52ef10c67597a98d252e0b678cac8bf603dcb70e Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Sat, 3 Jan 2026 20:38:42 +0000
Subject: [PATCH] feat: add tqdm progress bar to CLI cleaning operations

- Replaced periodic logging with `tqdm` progress bar in `yogimass/processing.py`
- Added `tqdm` to `pyproject.toml` dependencies
- Removed unused `LOG_INTERVAL` constant

This improves the CLI UX by providing real-time progress feedback and ETA for long-running cleaning operations.
---
 pyproject.toml         |  1 +
 yogimass/processing.py | 22 +++++++---------------
 2 files changed, 8 insertions(+), 15 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index af8d045..9cabb73 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -21,6 +21,7 @@ dependencies = [
     "matchms>=0.23",
     "numpy>=1.24",
     "PyYAML>=6.0",
+    "tqdm>=4.66",
 ]
 
 [project.optional-dependencies]
diff --git a/yogimass/processing.py b/yogimass/processing.py
index 1b923c2..7a5b2fd 100644
--- a/yogimass/processing.py
+++ b/yogimass/processing.py
@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import logging
+from tqdm import tqdm
 from matchms.importing import load_from_mgf, load_from_msp
 from matchms.filtering import (
     default_filters,
@@ -25,9 +26,6 @@
 
 logger = logging.getLogger(__name__)
 
-# Interval for progress logging
-LOG_INTERVAL = 1000
-
 
 def metadata_processing(spectrum):
     """
@@ -78,19 +76,16 @@ def clean_mgf_library(mgf_path: str) -> list:
     """
     logger.info(f"Cleaning {mgf_path} library spectra...")
     library_list = list(load_from_mgf(mgf_path))
-    
+
     # Apply filters sequentially
     processed_spectra = []
-    for i, s in enumerate(library_list):
-        if (i + 1) % LOG_INTERVAL == 0:
-            logger.info(f"Processed {i + 1} / {len(library_list)} spectra...")
-
+    for s in tqdm(library_list, desc="Cleaning spectra", unit="spectrum"):
         meta_processed = metadata_processing(s)
         if meta_processed:
             peak_processed = peak_processing(meta_processed)
             if peak_processed:
                 processed_spectra.append(peak_processed)
-    
+
     logger.info(f"Retained {len(processed_spectra)} spectra after cleaning.")
     return processed_spectra
 
@@ -101,17 +96,14 @@ def clean_msp_library(msp_path: str) -> list:
     """
     logger.info(f"Cleaning {msp_path} library spectra...")
     library_list = list(load_from_msp(msp_path))
-    
-    processed_spectra = []
-    for i, s in enumerate(library_list):
-        if (i + 1) % LOG_INTERVAL == 0:
-            logger.info(f"Processed {i + 1} / {len(library_list)} spectra...")
 
+    processed_spectra = []
+    for s in tqdm(library_list, desc="Cleaning spectra", unit="spectrum"):
         meta_processed = metadata_processing(s)
         if meta_processed:
             peak_processed = peak_processing(meta_processed)
             if peak_processed:
                 processed_spectra.append(peak_processed)
-                
+
     logger.info(f"Retained {len(processed_spectra)} spectra after cleaning.")
     return processed_spectra