1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
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
|
"""Utilities for processing CSV files."""
from pathlib import Path
from typing import Union, Callable, Iterator
def is_blank_line(line: str) -> bool:
"""Is the given line a blank line?
:param line: The line to check for blankness.
:type line: str
:rtype bool
"""
return line.strip() == ""
def make_comment_line_checker(comment_char: str) -> Callable[[str], bool]:
"""Make function that checks whether a line is a comment line.
:param comment_char: The character indicating the line is a comment.
:type comment_char: str
:rtype Callable[[str], bool]
"""
def _is_comment_line_(line: str) -> bool:
"""Check whether the line is a comment.
:param line: The line to check.
:type line: str
:rtype bool
"""
return line.startswith(comment_char)
return _is_comment_line_
def read_text_file(filepath: Union[str, Path]) -> Iterator[str]:
"""Read the raw text from a text file.
:param filepath: Path to the plain text file to read.
:type filepath: str | pathlib.Path
:rtype Iterator[str]
"""
with Path(filepath).open("r", encoding="utf8") as _file:
yield from _file
def read_csv_file(
filepath: Path,
separator: str,
is_skippable_line: Callable[[str], bool]
) -> Iterator[tuple[str, ...]]:
"""Read a file as a csv file. This does not process the N/A values.
:param filepath: Path to the file to read as a CSV file.
:type filepath: pathlib.Path
:param separator: The fields' separator in the CSV file.
:type separator: str
:param is_skippable_line: Function to determine whether or not to skip a
particular line when parsing, e.g. comment lines.
:type is_skippable_line: typing.Callable[[str], bool]
:rtype typing.Iterator[tuple[str, ...]]
"""
for line in read_text_file(filepath):
if is_skippable_line(line):
continue
yield tuple(field.strip() for field in line.split(separator))
def read_csv_file_headers(
filepath: Path,
transposed: bool,
separator: str,
is_skippable_line: Callable[[str], bool]
) -> tuple[str, ...]:
"""Read the 'true' headers of a CSV file.
:param filepath: Path to the CSV file to read.
:type filepath: pathlib.Path
:parama transposed: Is the file transposed or not?
:type transposed: bool
:param separator: The fields' separator in the CSV file.
:type separator: str
:param comment_char: The character which, when it begins a line, indicates
that that line is a comment.
:type comment_char: str
:param is_skippable_line: Function to determine whether or not to skip a
particular line when parsing, e.g. comment lines.
:type is_skippable_line: typing.Callable[[str], bool]
:rtype tuple[str, ...]
"""
headers: tuple[str, ...] = tuple()
for line in read_text_file(filepath):
if is_skippable_line(line):
continue
row = tuple(field.strip() for field in line.split(separator))
if not transposed:
return row
headers = headers + (row[0],)
continue
return headers
|