Skip to content

Reference

dsg_lib.common_functions.file_functions

file_functions.py

This module provides a function to delete a file with a specified name from a specified directory.

Functions:

Name Description
delete_file

str) -> str: Deletes a file with the specified file name from the directory specified by the directory_to_files variable. The file type is determined by the file extension, and the file is deleted from the subdirectory corresponding to the file type.

Args: file_name (str): The name of the file to be deleted.

Returns: str: A string indicating that the file has been deleted.

Raises: TypeError: If the file name is not a string. ValueError: If the file name contains a forward slash or backslash, or if the file type is not supported. FileNotFoundError: If the file does not exist.

Example:

from dsg_lib.common_functions import file_functions

file_functions.delete_file("test.csv")

# Outputs: 'complete'

Author: Mike Ryan Date: 2024/05/16 License: MIT

append_csv(file_name, data, root_folder=None, delimiter=',', quotechar='"')

Appends a list of rows to an existing CSV file with the specified file name in the specified directory. Each element of the data list should be a row (list of values), and the header in data[0] must match the existing CSV's header.

Parameters:

Name Type Description Default
file_name str

The name of the CSV file to append data to. Can be

required
provided without the '.csv' extension. data (list

Rows to append

required
optional)

The root directory where the file is located. If None, the

required
default directory is used. Defaults to None. delimiter (str
required
quotechar str

The character used to quote fields in the CSV

'"'

Returns:

Name Type Description
str str

Returns "appended" if the rows were successfully appended.

Raises:

Type Description
FileNotFoundError

If the CSV file does not exist.

ValueError

If the header row in data does not match the existing

header in the file. TypeError

If data is not a list or file_name is

Example:

from dsg_lib.common_functions import file_functions

csv_rows = [
    ["column1", "column2"],
    ["appended_value1", "appended_value2"]
]
result = file_functions.append_csv(
    file_name="test.csv",
    data=csv_rows,
    root_folder="/path/to/directory"
)
# result would be "appended" on success

Additional usage info
  • Ideal for appending more rows to an existing CSV with matching header.
  • Defaults to "data/csv" if no root_folder is provided.
  • You can supply any valid file path in root_folder to override.
Source code in dsg_lib/common_functions/file_functions.py
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
def append_csv(
    file_name: str,
    data: list,
    root_folder: str = None,
    delimiter: str = ",",
    quotechar: str = '"',
) -> str:
    """
    Appends a list of rows to an existing CSV file with the specified file name
    in the specified directory. Each element of the `data` list should be a row
    (list of values), and the header in `data[0]` must match the existing CSV's
    header.

    Args:
        file_name (str): The name of the CSV file to append data to. Can be
        provided without the '.csv' extension. data (list): Rows to append
        (list of lists), where the first row is the header. root_folder (str,
        optional): The root directory where the file is located. If None, the
        default directory is used. Defaults to None. delimiter (str, optional):
        The character used to separate fields in the CSV file. Defaults to ','.
        quotechar (str, optional): The character used to quote fields in the CSV
        file. Defaults to '"'.

    Returns:
        str: Returns "appended" if the rows were successfully appended.

    Raises:
        FileNotFoundError: If the CSV file does not exist.
        ValueError: If the header row in `data` does not match the existing
        header in the file. TypeError: If `data` is not a list or `file_name` is
        not valid.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    csv_rows = [
        ["column1", "column2"],
        ["appended_value1", "appended_value2"]
    ]
    result = file_functions.append_csv(
        file_name="test.csv",
        data=csv_rows,
        root_folder="/path/to/directory"
    )
    # result would be "appended" on success
    ```

    Additional usage info:
        - Ideal for appending more rows to an existing CSV with matching header.
        - Defaults to "data/csv" if no root_folder is provided.
        - You can supply any valid file path in root_folder to override.
    """
    target_folder = Path(root_folder) if root_folder else Path("data/csv")
    file_path = target_folder / (
        file_name if file_name.endswith(".csv") else f"{file_name}.csv"
    )

    if not file_path.is_file():
        raise FileNotFoundError(f"CSV not found: {file_path}")

    if not isinstance(data, list):
        raise TypeError("data must be a list of rows")

    # Read existing CSV header
    with file_path.open("r", encoding="utf-8") as csv_file:
        reader = csv.reader(csv_file, delimiter=delimiter, quotechar=quotechar)
        existing_header = next(reader)

    # Check new data's header
    new_header = data[0]
    if existing_header != new_header:
        raise ValueError("Headers do not match. Cannot append.")

    # Append the new rows
    with file_path.open("a", encoding="utf-8", newline="") as csv_file:
        writer = csv.writer(csv_file, delimiter=delimiter, quotechar=quotechar)
        # Skip first row (header) to avoid duplication
        writer.writerows(data[1:])

    return "appended"

create_sample_files(file_name, sample_size)

Create sample CSV and JSON files with random data.

Parameters:

Name Type Description Default
file_name str

The base name for the sample files (without extension).

required
sample_size int

The number of rows to generate for the sample files.

required

Returns:

Type Description
None

None

Raises:

Type Description
Exception

If an error occurs while creating the sample files.

Example:

from dsg_lib.common_functions import file_functions

file_functions.create_sample_files(file_name="test.csv", sample_size=100)
# Creates 'test.csv' and 'test.json' each with 100 rows of random data
Additional usage info: - Creates CSV and JSON sample files with random data. - Useful for testing or seeding databases.

Source code in dsg_lib/common_functions/file_functions.py
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
def create_sample_files(file_name: str, sample_size: int) -> None:
    """
    Create sample CSV and JSON files with random data.

    Args:
        file_name (str): The base name for the sample files (without extension).
        sample_size (int): The number of rows to generate for the sample files.

    Returns:
        None

    Raises:
        Exception: If an error occurs while creating the sample files.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    file_functions.create_sample_files(file_name="test.csv", sample_size=100)
    # Creates 'test.csv' and 'test.json' each with 100 rows of random data
    ```
    Additional usage info:
        - Creates CSV and JSON sample files with random data.
        - Useful for testing or seeding databases.
    """
    logger.debug(f"Creating sample files for {file_name} with {sample_size} rows.")

    try:
        # Generate the CSV data
        csv_header = ["name", "birth_date", "number"]
        csv_data: List[List[str]] = [csv_header]

        # Generate rows for CSV data
        for i in range(1, sample_size + 1):
            r_int: int = random.randint(0, len(first_name) - 1)
            name = first_name[r_int]
            row: List[str] = [name, generate_random_date(), str(i)]
            csv_data.append(row)

        # Save the CSV file
        csv_file = f"{file_name}.csv"
        save_csv(csv_file, csv_data)

        # Generate the JSON data
        json_data: List[dict] = []

        # Generate rows for JSON data
        for _ in range(1, sample_size + 1):
            r_int: int = random.randint(0, len(first_name) - 1)
            name = first_name[r_int]
            sample_dict: dict = {
                "name": name,
                "birthday_date": generate_random_date(),
            }
            json_data.append(sample_dict)

        # Save the JSON file
        json_file: str = f"{file_name}.json"
        save_json(json_file, json_data)

        # Log the data
        logger.debug(f"CSV Data: {csv_data}")
        logger.debug(f"JSON Data: {json_data}")

    except Exception as e:  # pragma: no cover
        logger.exception(
            f"Error occurred while creating sample files: {e}"
        )  # pragma: no cover
        raise  # pragma: no cover

delete_file(file_name)

Deletes a file with the specified file name from the specified directory. The file type is determined by the file extension.

Parameters:

Name Type Description Default
directory_to_files str

The directory where the file is located.

required
file_name str

The name of the file to be deleted.

required

Returns:

Name Type Description
str str

A message indicating whether the file has been deleted successfully

str

or an error occurred.

Raises:

Type Description
TypeError

If the directory or file name is not a string. ValueError: If

is not supported. FileNotFoundError

If the file does not exist.

Example:

from dsg_lib.common_functions import file_functions

file_functions.delete_file(file_name="test.csv")

# Outputs: 'complete'
Additional usage info: - Returns "complete" if file is successfully deleted. - Ensure correct file permissions and directory structure.

Source code in dsg_lib/common_functions/file_functions.py
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
def delete_file(file_name: str) -> str:
    """
    Deletes a file with the specified file name from the specified directory.
    The file type is determined by the file extension.

    Args:
        directory_to_files (str): The directory where the file is located.
        file_name (str): The name of the file to be deleted.

    Returns:
        str: A message indicating whether the file has been deleted successfully
        or an error occurred.

    Raises:
        TypeError: If the directory or file name is not a string. ValueError: If
        the file name contains a forward slash or backslash, or if the file type
        is not supported. FileNotFoundError: If the file does not exist.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    file_functions.delete_file(file_name="test.csv")

    # Outputs: 'complete'
    ```
    Additional usage info:
        - Returns "complete" if file is successfully deleted.
        - Ensure correct file permissions and directory structure.
    """
    logger.info(f"Deleting file: {file_name}")

    # Check that the file name is a string
    if not isinstance(file_name, str):
        raise TypeError(f"{file_name} is not a valid string")

    # Split the file name into its name and extension components
    file_name, file_ext = os.path.splitext(file_name)

    # Check that the file name does not contain a forward slash or backslash
    if os.path.sep in file_name:
        raise ValueError(f"{file_name} cannot contain {os.path.sep}")

    # Check that the file type is supported
    if file_ext not in directory_map:
        raise ValueError(
            f"unsupported file type: {file_ext}. Supported file types are: {', '.join(directory_map.keys())}"
        )

    # Construct the full file path
    file_directory = Path.cwd() / directory_to_files / directory_map[file_ext]
    file_path = file_directory / f"{file_name}{file_ext}"

    # Check that the file exists
    if not file_path.is_file():
        raise FileNotFoundError(f"file not found: {file_name}{file_ext}")

    # Delete the file
    os.remove(file_path)
    logger.info(f"File {file_name}{file_ext} deleted from file path: {file_path}")

    # Return a string indicating that the file has been deleted
    return "complete"

generate_random_date()

Generate a random datetime string in the format yyyy-mm-dd hh:mm:ss.ffffff.

Returns:

Name Type Description
str str

A randomly generated datetime string.

Example:

from dsg_lib.common_functions import file_functions

random_timestamp = file_functions.generate_random_date()
# random_timestamp might look like '1992-03-15 10:30:45.123456'
Additional usage info: - Can help produce test data with random timestamps.

Source code in dsg_lib/common_functions/file_functions.py
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
def generate_random_date() -> str:
    """
    Generate a random datetime string in the format yyyy-mm-dd hh:mm:ss.ffffff.

    Returns:
        str: A randomly generated datetime string.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    random_timestamp = file_functions.generate_random_date()
    # random_timestamp might look like '1992-03-15 10:30:45.123456'
    ```
    Additional usage info:
        - Can help produce test data with random timestamps.
    """
    # Define the minimum and maximum years for the date range
    min_year: int = 1905
    max_year: int = datetime.now().year

    # Generate random values for the year, month, day, hour, minute, and second
    year: int = random.randrange(min_year, max_year + 1)
    month: int = random.randint(1, 12)
    day: int = random.randint(1, 28)
    hour: int = random.randint(0, 12)
    minute: int = random.randint(0, 59)
    second: int = random.randint(0, 59)

    # Create a datetime object with the random values
    date_value: datetime = datetime(year, month, day, hour, minute, second)

    # Format the datetime string and return it
    return f"{date_value:%Y-%m-%d %H:%M:%S.%f}"

open_csv(file_name, delimiter=',', quote_level='minimal', skip_initial_space=True, **kwargs)

Opens a CSV file with the specified file name and returns its contents as a list of dictionaries.

Source code in dsg_lib/common_functions/file_functions.py
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
def open_csv(
    file_name: str,
    delimiter: str = ",",
    quote_level: str = "minimal",
    skip_initial_space: bool = True,
    **kwargs,
) -> list:
    """
    Opens a CSV file with the specified file name and returns its contents
    as a list of dictionaries.
    """
    # A dictionary that maps quote levels to csv quoting constants
    quote_levels = {
        "none": csv.QUOTE_NONE,
        "minimal": csv.QUOTE_MINIMAL,
        "all": csv.QUOTE_ALL,
    }
    # Check that file name is a string
    if not isinstance(file_name, str):
        error = f"{file_name} is not a valid string"
        logger.error(error)
        raise TypeError(error)

    # Check delimiter is single character
    if len(delimiter) != 1:
        raise TypeError(f"{delimiter} can only be a single character")

    # Reject any 'quotechar' usage for now
    if "quotechar" in kwargs:
        raise TypeError("quotechar is not supported in open_csv")

    # Validate quote_level
    quote_level = quote_level.lower()
    if quote_level not in quote_levels:
        error = f"Invalid quote level: {quote_level}. Valid levels are: {', '.join(quote_levels)}"
        logger.error(error)
        raise ValueError(error)
    quoting = quote_levels[quote_level]

    file_directory = Path.cwd().joinpath(directory_to_files).joinpath("csv")
    file_path = file_directory.joinpath(file_name)

    if not file_path.is_file():
        error = f"File not found: {file_path}"
        logger.error(error)
        raise FileNotFoundError(error)

    data = []
    with file_path.open(encoding="utf-8") as f:
        reader = csv.DictReader(
            f,
            delimiter=delimiter,
            quoting=quoting,
            skipinitialspace=skip_initial_space,
        )
        for row in reader:
            data.append(dict(row))

    logger.info(f"File opened: {file_name}")
    return data

open_json(file_name)

Open a JSON file and load its contents into a dictionary.

Parameters:

Name Type Description Default
file_name str

The name of the JSON file to open.

required

Returns:

Name Type Description
dict dict

The contents of the JSON file as a dictionary.

Raises:

Type Description
TypeError

If the file name is not a string. FileNotFoundError: If the

Example:

from dsg_lib.common_functions import file_functions

result_dict = file_functions.open_json(file_name="test.json")
# result_dict is a dictionary loaded from 'test.json'
Additional usage info: - Returns a dictionary loaded from the JSON file. - Commonly used for reading app settings or user data.

Source code in dsg_lib/common_functions/file_functions.py
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
def open_json(file_name: str) -> dict:
    """
    Open a JSON file and load its contents into a dictionary.

    Args:
        file_name (str): The name of the JSON file to open.

    Returns:
        dict: The contents of the JSON file as a dictionary.

    Raises:
        TypeError: If the file name is not a string. FileNotFoundError: If the
        file does not exist.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    result_dict = file_functions.open_json(file_name="test.json")
    # result_dict is a dictionary loaded from 'test.json'
    ```
    Additional usage info:
        - Returns a dictionary loaded from the JSON file.
        - Commonly used for reading app settings or user data.
    """
    # Check if file name is a string
    if not isinstance(file_name, str):
        error = f"{file_name} is not a valid string"
        logger.error(error)
        raise TypeError(error)

    file_directory = Path(directory_to_files) / directory_map[".json"]
    file_save = file_directory / file_name

    # Check if path correct
    if not file_save.is_file():
        error = f"file not found error: {file_save}"
        logger.exception(error)
        raise FileNotFoundError(error)

    # open file
    with open(file_save) as read_file:
        # load file into data variable
        result = json.load(read_file)

    logger.info(f"File Opened: {file_name}")
    return result

open_text(file_name)

Opens a text file with the specified file name and returns its contents as a string.

Parameters:

Name Type Description Default
file_name str

The name of the file to open. Should include the '.txt'

required

Returns:

Name Type Description
str str

The contents of the text file as a string.

Raises:

Type Description
TypeError

If the file_name parameter is not a string or contains a

forward slash. FileNotFoundError

If the file does not exist.

Example:

from dsg_lib.common_functions import file_functions

text_content = file_functions.open_text(file_name="test.txt")
# text_content is the file's contents as a single string
Additional usage info: - Retrieves contents as a single string. - Handy for reading simple text resources or logs.

Source code in dsg_lib/common_functions/file_functions.py
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
def open_text(file_name: str) -> str:
    """
    Opens a text file with the specified file name and returns its contents as a
    string.

    Args:
        file_name (str): The name of the file to open. Should include the '.txt'
        extension.

    Returns:
        str: The contents of the text file as a string.

    Raises:
        TypeError: If the `file_name` parameter is not a string or contains a
        forward slash. FileNotFoundError: If the file does not exist.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    text_content = file_functions.open_text(file_name="test.txt")
    # text_content is the file's contents as a single string
    ```
    Additional usage info:
        - Retrieves contents as a single string.
        - Handy for reading simple text resources or logs.
    """
    # Replace backslashes with forward slashes in the file name
    if "\\" in file_name:  # pragma: no cover
        file_name = file_name.replace("\\", "/")  # pragma: no cover

    # Check that file_name does not contain invalid characters
    if "/" in file_name:
        logger.error(f"{file_name} cannot contain /")
        raise TypeError(f"{file_name} cannot contain /")

    # Get the path to the text directory and the file path
    file_directory = os.path.join(directory_to_files, "text")
    file_path = Path.cwd().joinpath(file_directory, file_name)

    # Check if the file exists
    if not file_path.is_file():
        raise FileNotFoundError(f"file not found error: {file_path}")

    # Open the file and read the data
    with open(file_path, "r", encoding="utf-8") as file:
        data = file.read()

    logger.info(f"File opened: {file_path}")
    return data

save_csv(file_name, data, root_folder=None, delimiter=',', quotechar='"')

Saves a list of dictionaries as a CSV file with the specified file name in the specified directory. Each dictionary in the list should represent a row in the CSV file.

Parameters:

Name Type Description Default
file_name str

The name of the file to save the data in. Should

required
include the '.csv' extension. data (list

The data to be saved. Each

required
optional)

The root directory where the file will be saved. If None, the

required
(str, optional

The character used to separate fields in the CSV file.

required
Defaults to ','. quotechar (str

The character used to quote

required

Returns:

Name Type Description
str str

A message indicating whether the file has been saved successfully

str

or an error occurred.

Raises:

Type Description
TypeError

If the data is not a list, or the file name, delimiter, or

quotechar is not a string. ValueError

If the file name does not end

Example:

from dsg_lib.common_functions import file_functions

csv_data = [
    ["column1", "column2"],
    ["value1", "value2"]
]
file_functions.save_csv(file_name="test.csv", data=csv_data,root_folder="/path/to/directory", delimiter=";", quotechar="'")

# Saves data to '/path/to/directory/test.csv'
Additional usage info: - Ideal for exporting data for spreadsheet analysis. - Returns "complete" if file is saved successfully. Additional clarification: - Defaults to "data/csv" if no root_folder is provided. - You can supply any valid file path in root_folder to override.

Source code in dsg_lib/common_functions/file_functions.py
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
def save_csv(
    file_name: str,
    data: list,
    root_folder: str = None,
    delimiter: str = ",",
    quotechar: str = '"',
) -> str:
    """
    Saves a list of dictionaries as a CSV file with the specified file name in
    the specified directory. Each dictionary in the list should represent a row
    in the CSV file.

    Args:
        file_name (str): The name of the file to save the data in. Should
        include the '.csv' extension. data (list): The data to be saved. Each
        element of the list should be a dictionary where the keys are column
        names and the values are the data for those columns. root_folder (str,
        optional): The root directory where the file will be saved. If None, the
        file will be saved in the current directory. Defaults to None. delimiter
        (str, optional): The character used to separate fields in the CSV file.
        Defaults to ','. quotechar (str, optional): The character used to quote
        fields in the CSV file. Defaults to '"'.

    Returns:
        str: A message indicating whether the file has been saved successfully
        or an error occurred.

    Raises:
        TypeError: If the data is not a list, or the file name, delimiter, or
        quotechar is not a string. ValueError: If the file name does not end
        with '.csv'.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    csv_data = [
        ["column1", "column2"],
        ["value1", "value2"]
    ]
    file_functions.save_csv(file_name="test.csv", data=csv_data,root_folder="/path/to/directory", delimiter=";", quotechar="'")

    # Saves data to '/path/to/directory/test.csv'
    ```
    Additional usage info:
        - Ideal for exporting data for spreadsheet analysis.
        - Returns "complete" if file is saved successfully.
    Additional clarification:
        - Defaults to "data/csv" if no root_folder is provided.
        - You can supply any valid file path in root_folder to override.
    """
    target_folder = Path(root_folder) if root_folder else Path("data/csv")
    target_folder.mkdir(parents=True, exist_ok=True)

    # Check that delimiter and quotechar are single characters
    if len(delimiter) != 1:
        raise TypeError(f"{delimiter} can only be a single character")
    if len(quotechar) != 1:
        raise TypeError(f"{quotechar} can only be a single character")

    # Check that data is a list
    if not isinstance(data, list):
        raise TypeError(f"{data} is not a valid list")

    # Check that file_name is a string and does not contain invalid characters
    if not isinstance(file_name, str) or "/" in file_name or "\\" in file_name:
        raise TypeError(f"{file_name} is not a valid file name")

    # Add extension to file_name if needed
    if not file_name.endswith(".csv"):
        file_name += ".csv"

    # Create the file path
    file_path = target_folder / file_name

    # Write data to file
    with open(file_path, "w", encoding="utf-8", newline="") as csv_file:
        csv_writer = csv.writer(csv_file, delimiter=delimiter, quotechar=quotechar)
        csv_writer.writerows(data)

    logger.info(f"File Create: {file_name}")
    return "complete"

save_json(file_name, data, root_folder=None)

Saves a dictionary or a list as a JSON file with the specified file name in the specified directory.

Parameters:

Name Type Description Default
file_name str

The name of the file to save the data in. Should

required
include the '.json' extension. data (list or dict

The data to be

required
saved. root_folder (str

The root directory where the file

required

Returns:

Name Type Description
str str

A message indicating whether the file has been saved successfully

str

or an error occurred.

Raises:

Type Description
TypeError

If the data is not a list or a dictionary, or the file name

or directory is not a string. ValueError

If the file name contains a

Example:

from dsg_lib.common_functions import file_functions

json_data = {"key": "value"}
file_functions.save_json(file_name="test.json", data=json_data, root_folder="/path/to/directory")

# Saves data to '/path/to/directory/test.json'
Additional usage info: - Suitable for config files, logs, or structured application data. - Returns "File saved successfully" on success. Additional clarification: - Defaults to "data/json" if no root_folder is provided. - You can supply any valid file path in root_folder to override.

Source code in dsg_lib/common_functions/file_functions.py
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
def save_json(file_name: str, data, root_folder: str = None) -> str:
    """
    Saves a dictionary or a list as a JSON file with the specified file name in
    the specified directory.

    Args:
        file_name (str): The name of the file to save the data in. Should
        include the '.json' extension. data (list or dict): The data to be
        saved. root_folder (str, optional): The root directory where the file
        will be saved. Defaults to None, which means the file will be saved in
        the 'data' directory.

    Returns:
        str: A message indicating whether the file has been saved successfully
        or an error occurred.

    Raises:
        TypeError: If the data is not a list or a dictionary, or the file name
        or directory is not a string. ValueError: If the file name contains a
        forward slash or backslash, or if the file name does not end with
        '.json'.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    json_data = {"key": "value"}
    file_functions.save_json(file_name="test.json", data=json_data, root_folder="/path/to/directory")

    # Saves data to '/path/to/directory/test.json'
    ```
    Additional usage info:
        - Suitable for config files, logs, or structured application data.
        - Returns "File saved successfully" on success.
    Additional clarification:
        - Defaults to "data/json" if no root_folder is provided.
        - You can supply any valid file path in root_folder to override.
    """
    try:
        if not isinstance(data, (list, dict)):
            raise TypeError(
                f"data must be a list or a dictionary instead of type {type(data)}"
            )
        if "/" in file_name or "\\" in file_name:
            raise ValueError(f"{file_name} cannot contain / or \\")

        if not file_name.endswith(".json"):
            file_name += ".json"

        target_folder = Path(root_folder) if root_folder else Path("data/json")
        # Create the target folder if it doesn't exist
        target_folder.mkdir(parents=True, exist_ok=True)

        file_path = target_folder / file_name

        with open(file_path, "w") as write_file:
            json.dump(data, write_file)

        logger.info(f"File created: {file_path}")
        return "File saved successfully"

    except (TypeError, ValueError) as e:
        logger.error(f"Error creating file {file_name}: {e}")
        raise

save_text(file_name, data, root_folder=None)

Saves a string of text to a file with the specified file name in the specified directory.

Parameters:

Name Type Description Default
file_name str

The name of the file to save the data in. Should not

required
include the '.txt' extension. data (str

The text data to be saved.

required
root_folder str

The root directory where the file will be

None

Returns:

Name Type Description
str str

A message indicating whether the file has been saved successfully

str

or an error occurred.

Raises:

Type Description
TypeError

If the data parameter is not a string, or the file_name

contains a forward slash or backslash. FileNotFoundError

If the

Example:

from dsg_lib.common_functions import file_functions

text_data = "This is a test text file."
file_functions.save_text(file_name="test.txt", data=text_data, root_folder="/path/to/directory")

# Saves data to '/path/to/directory/test.txt'
Additional usage info: - Writes plain text data to a .txt file. - Returns "complete" on success. Additional clarification: - Defaults to "data/text" if no root_folder is provided. - You can supply any valid file path in root_folder to override.

Source code in dsg_lib/common_functions/file_functions.py
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
def save_text(file_name: str, data: str, root_folder: str = None) -> str:
    """
    Saves a string of text to a file with the specified file name in the
    specified directory.

    Args:
        file_name (str): The name of the file to save the data in. Should not
        include the '.txt' extension. data (str): The text data to be saved.
        root_folder (str, optional): The root directory where the file will be
        saved. If None, the file will be saved in the current directory.
        Defaults to None.

    Returns:
        str: A message indicating whether the file has been saved successfully
        or an error occurred.

    Raises:
        TypeError: If the `data` parameter is not a string, or the `file_name`
        contains a forward slash or backslash. FileNotFoundError: If the
        directory does not exist.

    Example:
    ```python
    from dsg_lib.common_functions import file_functions

    text_data = "This is a test text file."
    file_functions.save_text(file_name="test.txt", data=text_data, root_folder="/path/to/directory")

    # Saves data to '/path/to/directory/test.txt'
    ```
    Additional usage info:
        - Writes plain text data to a .txt file.
        - Returns "complete" on success.
    Additional clarification:
        - Defaults to "data/text" if no root_folder is provided.
        - You can supply any valid file path in root_folder to override.
    """
    # If no root folder is provided, use the default directory
    if root_folder is None:  # pragma: no cover
        root_folder = directory_to_files  # pragma: no cover

    # Determine the directory for text files
    text_directory = Path(root_folder) / "text"

    # Construct the file path for text files
    file_path = text_directory / file_name

    # Create the text directory if it does not exist
    text_directory.mkdir(parents=True, exist_ok=True)

    # Check that data is a string and that file_name does not contain invalid
    # characters
    if not isinstance(data, str):
        logger.error(f"{file_name} is not a valid string")
        raise TypeError(f"{file_name} is not a valid string")
    elif "/" in file_name or "\\" in file_name:
        logger.error(f"{file_name} cannot contain \\ or /")
        raise ValueError(f"{file_name} cannot contain \\ or /")

    # Add extension to file_name if needed
    if not file_name.endswith(".txt"):
        file_name += ".txt"
    # Open or create the file and write the data
    with open(file_path, "w+", encoding="utf-8") as file:
        file.write(data)

    logger.info(f"File created: {file_path}")
    return "complete"