Skip to content

File Utils module

A collection of utility functions for file management and data integrity.

Functions: - calculate_md5(file_path): Calculate the MD5 hash of a file specified by its path. - check_indir_status(indir=None): Check the status of a directory, providing information on its existence and contents. - check_infile_status(infile, extension=None): Check the status of a file, including its existence and optionally validate its extension. - get_file_creation_date(file_path): Retrieve the creation date of a file specified by its path.

Use these functions to enhance file handling and data validation in your Python projects.

calculate_md5(file_path)

Calculate the md5 checksum for the specified file.

Parameters:

Name Type Description Default
file_path str

the file for which the md5 checksum will be calculated

 required

Returns:

Name Type Description
str str

the calculated md5 checksum
Source code in jira_python_utils/file_utils.py 
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
def calculate_md5(file_path: str) -> str:
    """Calculate the md5 checksum for the specified file.

    Args:
        file_path (str): the file for which the md5 checksum will be calculated

    Returns:
        str: the calculated md5 checksum
    """
    md5_hash = hashlib.md5()
    logging.info(f"Will attempt to calculate the MD5 checksum for file '{file_path}'")

    with open(file_path, "rb") as file:
        # Read the file in chunks to efficiently handle large files
        for chunk in iter(lambda: file.read(4096), b""):
            md5_hash.update(chunk)

    return md5_hash.hexdigest()

check_indir_status(indir=None)

Check if the directory exists and is a regular directory.

Parameters:

Name Type Description Default
indir str

the directory to be checked

 None
Source code in jira_python_utils/file_utils.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
def check_indir_status(indir: str = None) -> None:
    """Check if the directory exists and is a regular directory.

    Args:
        indir (str): the directory to be checked
    """
    error_ctr = 0

    if indir is None or indir == '':
        error_console.print(f"'{indir}' is not defined")
        error_ctr += 1
    else:
        if not os.path.exists(indir):
            error_ctr += 1
            error_console.print(f"directory '{indir}' does not exist")
        else:
            if not os.path.isdir(indir):
                error_ctr += 1
                error_console.print(f"'{indir}' is not a regular directory")

    if error_ctr > 0:
        error_console.print(f"Detected problems with input directory '{indir}'")
        sys.exit(1)

check_infile_status(infile, extension=None)

Check if the file exists, if it is a regular file and whether it has content.

Parameters:

Name Type Description Default
infile str

the file to be checked

 required
Source code in jira_python_utils/file_utils.py 
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
def check_infile_status(infile: str, extension: Optional[str] = None) -> None:
    """Check if the file exists, if it is a regular file and whether it has
    content.

    Args:
        infile (str): the file to be checked

    Raises:
        None
    """

    error_ctr = 0

    if infile is None or infile == "":
        error_console.print(f"'{infile}' is not defined")
        error_ctr += 1
    else:
        if not os.path.exists(infile):
            error_ctr += 1
            error_console.print(f"'{infile}' does not exist")
        else:
            if not os.path.isfile(infile):
                error_ctr += 1
                error_console.print(f"'{infile}' is not a regular file")
            if os.stat(infile).st_size == 0:
                error_console.print(f"'{infile}' has no content")
                error_ctr += 1
            if extension is not None and not infile.endswith(extension):
                error_console.print(
                    f"'{infile}' does not have filename extension '{extension}'"
                )
                error_ctr += 1

    if error_ctr > 0:
        error_console.print(f"Detected problems with input file '{infile}'")
        sys.exit(1)

get_file_creation_date(file_path)

Determine the creation date for the specified file.

Parameters:

Name Type Description Default
file_path str

the absolute path of the file

 required

Returns:

Name Type Description
datetime datetime

the date the file was created according to the operating system
Source code in jira_python_utils/file_utils.py 
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def get_file_creation_date(file_path: str) -> datetime:
    """Determine the creation date for the specified file.

    Args:
        file_path (str): the absolute path of the file

    Returns:
        datetime: the date the file was created according to the operating system
    """
    if platform.system() == "Windows":
        # On Windows, use creation time
        creation_time = os.path.getctime(file_path)
    else:
        # On Unix-based systems, use birth time (creation time)
        # Note: Not all file systems support birth time, and it might not be available on some systems.
        stat_info = os.stat(file_path)
        creation_time = stat_info.st_mtime

    # Convert the timestamp to a readable date
    creation_date = datetime.fromtimestamp(creation_time)

    return creation_date