From 01769f10e088b4fd41a750ae4901d83c2b357b37 Mon Sep 17 00:00:00 2001
From: Florez Ospina Juan Felipe <juan.florez-ospina@psi.ch>
Date: Wed, 21 May 2025 09:43:36 +0200
Subject: [PATCH] Implement new step to remove column from already created nas
 file.

---
 pipelines/steps/drop_column_from_nas_file.py | 133 +++++++++++++++++++
 1 file changed, 133 insertions(+)
 create mode 100644 pipelines/steps/drop_column_from_nas_file.py

diff --git a/pipelines/steps/drop_column_from_nas_file.py b/pipelines/steps/drop_column_from_nas_file.py
new file mode 100644
index 0000000..c27d54b
--- /dev/null
+++ b/pipelines/steps/drop_column_from_nas_file.py
@@ -0,0 +1,133 @@
+import sys, os
+import re
+
+try:
+    thisFilePath = os.path.abspath(__file__)
+    print(thisFilePath)
+except NameError:
+    print("[Notice] The __file__ attribute is unavailable in this environment (e.g., Jupyter or IDLE).")
+    print("When using a terminal, make sure the working directory is set to the script's location to prevent path issues (for the DIMA submodule)")
+    #print("Otherwise, path to submodule DIMA may not be resolved properly.")
+    thisFilePath = os.getcwd()  # Use current directory or specify a default
+
+
+projectPath = os.path.normpath(os.path.join(thisFilePath, "..", "..",'..'))  # Move up to project root
+
+if projectPath not in sys.path:
+    sys.path.insert(0,projectPath)
+
+import numpy as np
+import pandas as pd
+from dima.instruments.readers.nasa_ames_reader import read_nasa_ames_as_dict
+
+
+
+
+
+
+
+def main(path_to_data_file, column_to_remove):
+
+    if not path_to_data_file.endswith('.nas'):
+        raise RuntimeError(f'Invalid file extension. The input file{path_to_data_file} must be a .nas file.')
+    
+    #path_to_data_file = os.path.join(projectPath,path_to_data_file)
+    #path_to_data_file = os.path.normpath(path_to_data_file)
+ #import pandas as pd
+
+    idr_dict = read_nasa_ames_as_dict(path_to_data_file)
+    header_metadata_dict = idr_dict['attributes_dict']
+
+    # Locate the dataset
+    dataset = None
+    for d in idr_dict['datasets']:
+        if d['name'] == 'data_table':
+            dataset = d
+            break
+
+    if dataset is None:
+        raise ValueError("Dataset named 'data_table' not found.")
+
+    data_table = dataset['data']  # structured numpy array
+
+    # Convert to DataFrame
+    df = pd.DataFrame(data_table)
+
+    # Drop the column
+    index = data_table.dtype.names.index(column_to_remove)
+    df = df.drop(columns=column_to_remove)
+
+    # Update header part2
+    part2 = header_metadata_dict['raw_header_part2']
+    nvars = df.columns.size
+    part2[1] = f'{nvars}\n'.encode('utf-8')
+
+    part2_2_tmp = part2[2].decode('utf-8').strip().split()
+    del part2_2_tmp[index]
+    part2[2] = (' '.join(part2_2_tmp) + '\n').encode('utf-8')
+    print(part2[2])
+
+    del part2[4+index-1]
+
+    part2_3_tmp = part2[3].decode('utf-8').strip().split()
+    del part2_3_tmp[index]
+    part2[3] = (' '.join(part2_3_tmp) + '\n').encode('utf-8')
+
+    # Update header part1 (adjust header length)
+    part1 = header_metadata_dict['raw_header_part1']
+    part1_0_tmp = part1[0].decode('utf-8').split()
+    header_length = int(part1_0_tmp[0]) - 1
+    part1_0_tmp[0] = str(header_length)
+    part1[0] = (' '.join(part1_0_tmp) + '\n').encode('utf-8')
+
+    output_path = "output_file.na"  # or any .txt, .na, etc.
+
+    
+
+    
+
+    # Read all lines once
+    with open(path_to_data_file, 'rb') as file:
+        raw_lines = file.readlines()
+
+    data_table_lines = []
+    for line_idx in range(len(raw_lines)):
+        if line_idx >= header_metadata_dict['header_length']-1:
+            line = raw_lines[line_idx]
+            # Find all "fields" with positions (this preserves spacing info)
+            fields = list(re.finditer(rb'\S+', line))
+            if index < len(fields):
+                # Remove the field at the given index by slicing the bytes
+                start, end = fields[index].span()
+                line = line[:start] + line[end:]  # Remove the selected field
+            data_table_lines.append(line)
+
+
+
+
+
+
+    # Extract header length from the first line
+    #header_length = int(lines[0].split()[0])
+    #file_header = lines[:header_length]
+
+    # Split header in three parts, header preamble, var descriptions, and metadata pairs 
+    #part1, part2, part3 = split_header(file_header)
+
+    #var_descriptions = extract_var_descriptions(part2)
+
+    #table_header = part3[len(part3)-1]
+
+    processed_lines = header_metadata_dict['raw_header_part1']
+    processed_lines = processed_lines + header_metadata_dict['raw_header_part2'] 
+    processed_lines = processed_lines + header_metadata_dict['raw_header_part3'] 
+    processed_lines = processed_lines + data_table_lines
+
+    with open(path_to_data_file, 'wb') as f:
+        # Write header part 1
+        for line in processed_lines:
+            f.write(line) 
+
+if __name__ == '__main__':
+    path_to_data_file = os.path.normpath(os.path.join(projectPath,'data/CH0001G.20240201010000.20250519140310.aerosol_mass_spectrometer.chemistry_ACSM.pm1_non_refractory.2mo.1h.CH02L_Aerodyne_ToF-ACSM_017.CH02L_Aerodyne_ToF-ACSM_JFJ.lev2.nas'))
+    main(path_to_data_file, column_to_remove='inletP')
\ No newline at end of file