Populate DateOfSecondaryCapture TimeOfSecondaryCapture from TIFF files.

[zgypa]

DateOfSecondaryCapture TimeOfSecondaryCapture are a place to store when the images where first scanned.

[zgypa]

This data is no longer on box, since the upload it was lost. I created a script to extract the creationdate, modification date, and all dates from the files on the drives:

@echo off
setlocal enabledelayedexpansion

REM Parameters for directory and output CSV file
set "directory=%~1"
set "outputFile=%~2"

REM Create the CSV file with headers
> "%outputFile%" echo "DirectoryName","FileName","FilePath","FileSize","HostName","FileCreation","FileModification","LastAccessTime"

REM Loop through all .TIF* and .PDF files in the directory (case-insensitive)
for /r "%directory%" %%f in (*.tif* *.pdf) do (
    set "filePath=%%f"
    set "fileName=%%~nxf"
    set "directoryName=%%~dpf"
    set "fileSize=%%~zf"

    REM Properly escape the file path for the WMIC command
    set "escapedFilePath=!filePath:\=\\!"

    REM Append the file metadata using WMIC directly into the CSV, skipping the header
    for /f "skip=2 tokens=*" %%a in ('wmic datafile where "name='!escapedFilePath!'" get CreationDate^,LastAccessed^,LastModified /format:csv') do (
        <nul set /p ="!directoryName!,!fileName!,!filePath!,!fileSize!,%%a" >> "%outputFile%"
    )
)

echo Done!
endlocal

I had to do a BAT file, becuse no premission to execute .PS1 files on the Labs computers. I will then upload the CSV files to box.

[zgypa]

The .BAT file was so slow, i mean like it was taking hours, and gobbling up RAM like there's no tomorrow: After passing the 1GB or RAM per process, i decided to abort and write a Python script instead, which worked a LOT better. I put everything in box, but here is the script:

import hashlib
import os
import sys
import argparse
from pathlib import Path
import time
from tqdm import tqdm
import fnmatch

args = None

def get_file_timestamps(file_path):
    """Retrieve file timestamps and format them."""
    p = Path(file_path)
    stat = p.stat()
    creation_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(stat.st_birthtime))
    modification_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(stat.st_mtime))
    access_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(stat.st_atime))
    return creation_time, modification_time, access_time

def file_generator(directory):
    """Yield each file path one at a time."""
    for root, dirs, files in os.walk(directory):
        for name in files:
            if args.all:
                yield os.path.join(root, name)
            elif fnmatch.fnmatch(name.lower(), '*.tif*') or fnmatch.fnmatch(name.lower(), '*.pdf*'):
                yield os.path.join(root, name)

def process_directory(directory, output_file=None, add_hash=False):
    """Process files using a generator to handle large datasets efficiently."""
    output_stream = open(output_file, 'w') if output_file else sys.stdout
    progress = tqdm(file_generator(directory), desc="Processing Files")
    try:
        output_stream.write("dirname,basename,size,hash,creation,modification,access\n")
        hash = ""
        for file_path in progress:
            try:
                creation, modification, access = get_file_timestamps(file_path)
                if add_hash:
                    hash = calculate_file_hash(file_path)
                output = f'"{os.path.dirname(file_path)}","{os.path.basename(file_path)}","{os.path.getsize(file_path)}","{hash}","{creation}","{modification}","{access}"\n'
                output_stream.write(output)
            except Exception as e:
                print(f"Error processing {file_path}: {str(e)}")
    finally:
        if output_file:
            output_stream.close()

def calculate_file_hash(file_path):
    hash_md5 = hashlib.md5()
    with open(file_path, "rb") as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash_md5.update(chunk)
    return hash_md5.hexdigest()

def main():
    parser = argparse.ArgumentParser(description="Process a directory and list file timestamps.")
    parser.add_argument("directory", type=str, help="The directory to process")
    parser.add_argument("-o", "--output", type=str, help="Output file to write the results")
    parser.add_argument("-5", "--md5", action="store_true", help="Add md5 hash as well")
    parser.add_argument("-a", "--all", action="store_true", help="Include all files, not only TIFFs and PDFs")

    global args
    args = parser.parse_args()
    if not os.path.exists(args.directory):
        print(f"Error: The directory {args.directory} does not exist.")
        return
    process_directory(args.directory, args.output, args.md5)

if __name__ == "__main__":
    main()