|
5 | 5 | # See LICENSE.TXT |
6 | 6 | # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception |
7 | 7 |
|
8 | | -# check if all lines match in a file |
9 | | -# lines in a match file can contain regex inside of double curly braces {{}} |
| 8 | +# Check if all input file content matches match file content. |
| 9 | +# Lines in a match file can contain regex inside of double curly braces {{}}. |
| 10 | +# Regex patterns are limited to single line. |
| 11 | +# |
| 12 | +# List of available special tags: |
| 13 | +# {{OPT}} - makes content in the same line as the tag optional |
| 14 | +# {{IGNORE}} - ignores all content until the next successfully matched line or the end of the input |
| 15 | +# Special tags are mutually exclusive and are expected to be located at the start of a line. |
| 16 | +# |
10 | 17 |
|
| 18 | +import os |
11 | 19 | import sys |
12 | 20 | import re |
| 21 | +from enum import Enum |
13 | 22 |
|
14 | 23 |
|
15 | 24 | ## @brief print the whole content of input and match files |
16 | | -def print_content(input_lines, match_lines): |
| 25 | +def print_content(input_lines, match_lines, ignored_lines): |
17 | 26 | print("--- Input Lines " + "-" * 64) |
18 | 27 | print("".join(input_lines).strip()) |
19 | 28 | print("--- Match Lines " + "-" * 64) |
20 | 29 | print("".join(match_lines).strip()) |
| 30 | + print("--- Ignored Lines " + "-" * 62) |
| 31 | + print("".join(ignored_lines).strip()) |
21 | 32 | print("-" * 80) |
22 | 33 |
|
23 | 34 |
|
24 | | -if len(sys.argv) != 3: |
25 | | - print("Usage: python match.py <input_file> <match_file>") |
26 | | - sys.exit(1) |
27 | | - |
28 | | -input_file = sys.argv[1] |
29 | | -match_file = sys.argv[2] |
30 | | - |
31 | | -with open(input_file, 'r') as input, open(match_file, 'r') as match: |
32 | | - input_lines = input.readlines() |
33 | | - match_lines = match.readlines() |
34 | | - |
35 | | -if len(match_lines) < len(input_lines): |
36 | | - print(f"Match length < input length (input: {len(input_lines)}, match: {len(match_lines)})") |
37 | | - print_content(input_lines, match_lines) |
38 | | - sys.exit(1) |
39 | | - |
40 | | -input_idx = 0 |
41 | | -opt = "{{OPT}}" |
42 | | -for i, match_line in enumerate(match_lines): |
43 | | - if match_line.startswith(opt): |
44 | | - optional_line = True |
45 | | - match_line = match_line[len(opt):] |
46 | | - else: |
47 | | - optional_line = False |
48 | | - |
49 | | - # split into parts at {{ }} |
50 | | - match_parts = re.split(r'\{{(.*?)\}}', match_line.strip()) |
51 | | - pattern = "" |
52 | | - for j, part in enumerate(match_parts): |
53 | | - if j % 2 == 0: |
54 | | - pattern += re.escape(part) |
55 | | - else: |
56 | | - pattern += part |
| 35 | +## @brief print the incorrect match line |
| 36 | +def print_incorrect_match(match_line, present, expected): |
| 37 | + print("Line " + str(match_line) + " does not match") |
| 38 | + print("is: " + present) |
| 39 | + print("expected: " + expected) |
57 | 40 |
|
58 | | - # empty input file or end of input file, from now on match file must be optional |
59 | | - if not input_lines: |
60 | | - if optional_line is True: |
61 | | - continue |
62 | | - else: |
63 | | - print("End of input file or empty file.") |
64 | | - print("expected: " + match_line.strip()) |
| 41 | + |
| 42 | +## @brief pattern matching script status values |
| 43 | +class Status(Enum): |
| 44 | + INPUT_END = 1 |
| 45 | + MATCH_END = 2 |
| 46 | + INPUT_AND_MATCH_END = 3 |
| 47 | + PROCESSING = 4 |
| 48 | + |
| 49 | + |
| 50 | +## @brief check matching script status |
| 51 | +def check_status(input_lines, match_lines): |
| 52 | + if not input_lines and not match_lines: |
| 53 | + return Status.INPUT_AND_MATCH_END |
| 54 | + elif not input_lines: |
| 55 | + return Status.INPUT_END |
| 56 | + elif not match_lines: |
| 57 | + return Status.MATCH_END |
| 58 | + return Status.PROCESSING |
| 59 | + |
| 60 | + |
| 61 | +## @brief pattern matching tags. |
| 62 | +## Tags are expected to be at the start of the line. |
| 63 | +class Tag(Enum): |
| 64 | + OPT = "{{OPT}}" # makes the line optional |
| 65 | + IGNORE = "{{IGNORE}}" # ignores all input until next match or end of input file |
| 66 | + |
| 67 | + |
| 68 | +## @brief main function for the match file processing script |
| 69 | +def main(): |
| 70 | + if len(sys.argv) != 3: |
| 71 | + print("Usage: python match.py <input_file> <match_file>") |
| 72 | + sys.exit(1) |
| 73 | + |
| 74 | + input_file = sys.argv[1] |
| 75 | + match_file = sys.argv[2] |
| 76 | + |
| 77 | + with open(input_file, 'r') as input, open(match_file, 'r') as match: |
| 78 | + input_lines = input.readlines() |
| 79 | + match_lines = match.readlines() |
| 80 | + |
| 81 | + ignored_lines = [] |
| 82 | + |
| 83 | + input_idx = 0 |
| 84 | + match_idx = 0 |
| 85 | + tags_in_effect = [] |
| 86 | + while True: |
| 87 | + # check file status |
| 88 | + status = check_status(input_lines[input_idx:], match_lines[match_idx:]) |
| 89 | + if (status == Status.INPUT_AND_MATCH_END) or (status == Status.MATCH_END and Tag.IGNORE in tags_in_effect): |
| 90 | + # all lines matched or the last line in match file is an ignore tag |
| 91 | + sys.exit(0) |
| 92 | + elif status == Status.MATCH_END: |
| 93 | + print_incorrect_match(match_idx + 1, input_lines[input_idx].strip(), ""); |
| 94 | + print_content(input_lines, match_lines, ignored_lines) |
65 | 95 | sys.exit(1) |
66 | 96 |
|
67 | | - input_line = input_lines[input_idx].strip() |
68 | | - if not re.fullmatch(pattern, input_line): |
69 | | - if optional_line is True: |
70 | | - continue |
| 97 | + input_line = input_lines[input_idx].strip() if input_idx < len(input_lines) else "" |
| 98 | + match_line = match_lines[match_idx] |
| 99 | + |
| 100 | + # check for tags |
| 101 | + if match_line.startswith(Tag.OPT.value): |
| 102 | + tags_in_effect.append(Tag.OPT) |
| 103 | + match_line = match_line[len(Tag.OPT.value):] |
| 104 | + elif match_line.startswith(Tag.IGNORE.value): |
| 105 | + tags_in_effect.append(Tag.IGNORE) |
| 106 | + match_idx += 1 |
| 107 | + continue # line with ignore tag should be skipped |
| 108 | + |
| 109 | + # split into parts at {{ }} |
| 110 | + match_parts = re.split(r'\{{(.*?)\}}', match_line.strip()) |
| 111 | + pattern = "" |
| 112 | + for j, part in enumerate(match_parts): |
| 113 | + if j % 2 == 0: |
| 114 | + pattern += re.escape(part) |
| 115 | + else: |
| 116 | + pattern += part |
| 117 | + |
| 118 | + # match or process tags |
| 119 | + if re.fullmatch(pattern, input_line): |
| 120 | + input_idx += 1 |
| 121 | + match_idx += 1 |
| 122 | + tags_in_effect = [] |
| 123 | + elif Tag.OPT in tags_in_effect: |
| 124 | + match_idx += 1 |
| 125 | + tags_in_effect.remove(Tag.OPT) |
| 126 | + elif Tag.IGNORE in tags_in_effect: |
| 127 | + ignored_lines.append(input_line + os.linesep) |
| 128 | + input_idx += 1 |
71 | 129 | else: |
72 | | - print("Line " + str(i+1) + " does not match") |
73 | | - print("is: " + input_line) |
74 | | - print("expected: " + match_line.strip()) |
75 | | - print_content(input_lines, match_lines) |
| 130 | + print_incorrect_match(match_idx + 1, input_line, match_line.strip()) |
| 131 | + print_content(input_lines, match_lines, ignored_lines) |
76 | 132 | sys.exit(1) |
77 | | - else: |
78 | | - if (input_idx == len(input_lines) - 1): |
79 | | - input_lines = [] |
80 | | - else: |
81 | | - input_idx += 1 |
| 133 | + |
| 134 | + |
| 135 | +if __name__ == "__main__": |
| 136 | + main() |
0 commit comments