move data formating scripts into this repo

scripts/extractmeta.py

@@ -0,0 +1,35 @@
+#!/bin/python
+
+import tarfile
+from tqdm import tqdm
+from eisgenerator import EisSpectra
+import csv
+import argparse
+
+if __name__ == "__main__":
+	parser = argparse.ArgumentParser("KissExpiramentExtractMeta")
+	parser.add_argument('--data', '-d', required=True, help="Data input tar file")
+	parser.add_argument('--out', '-o', required=True, help="output file")
+	args = parser.parse_args()
+
+	with open(args.out, 'w', newline='') as outfile:
+		csvwriter = csv.writer(outfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
+		with tarfile.open(args.data, mode="r") as tar:
+			master_labels = None
+			rows = list()
+			for file_info in tqdm(tar, desc="Extracting Metadata", total=len(list(tar))):
+				if file_info.isfile():
+					filestr = tar.extractfile(file_info).read()
+					spectra = EisSpectra.loadFromString(filestr)
+					if master_labels is None:
+						master_labels = spectra.labelNames
+						master_labels_copy = master_labels.copy()
+						for i in range(len(master_labels_copy)):
+							print(master_labels_copy[i])
+							master_labels_copy[i] = master_labels_copy[i].strip(' "')
+						csvwriter.writerow(master_labels_copy)
+					elif master_labels != spectra.labelNames:
+						print(f"Error: not all files in {args.data} have the same labelNames")
+						exit(1)
+					csvwriter.writerow(spectra.labels)
+			tar.close()