| 112 | 112 | |
| 113 | 113 | |
| 114 | 114 | def _regexp_csv_transfomer(value: str) -> Sequence[Pattern[str]]: |
| 115 | """Transforms a comma separated list of regular expressions.""" | |
| 115 | """Transforms a comma separated list of regular expressions. | |
| 116 | ||
| 117 | This function handles commas within regex constructs (like quantifiers {1,3} | |
| 118 | and character classes [a,b,c]) while still allowing comma separation | |
| 119 | between different regex patterns. | |
| 120 | """ | |
| 116 | 121 | patterns: list[Pattern[str]] = [] |
| 117 | for pattern in _csv_transformer(value): | |
| 122 | for pattern in _split_regex_csv(value): | |
| 118 | 123 | patterns.append(_regex_transformer(pattern)) |
| 119 | 124 | return patterns |
| 120 | 125 | |
| 121 | 126 | |
| 127 | def _split_regex_csv(value: str) -> Sequence[str]: | |
| 128 | """Split a comma-separated list of regex patterns, respecting commas within regex constructs. | |
| 129 | ||
| 130 | This function handles commas within: | |
| 131 | - Quantifiers: {1,3}, {0,}, {1,} | |
| 132 | - Character classes: [a,b,c], [\\w,\\s] | |
| 133 | - Escaped commas: \\, | |
| 134 | ||
| 135 | Args: | |
| 136 | value: The comma-separated string to split | |
| 137 | ||
| 138 | Returns: | |
| 139 | List of individual regex patterns | |
| 140 | """ | |
| 141 | if not value: | |
| 142 | return [] | |
| 143 | ||
| 144 | patterns: list[str] = [] | |
| 145 | current_pattern = [] | |
| 146 | brace_depth = 0 | |
| 147 | bracket_depth = 0 | |
| 148 | i = 0 | |
| 149 | ||
| 150 | while i < len(value): | |
| 151 | char = value[i] | |
| 152 | ||
| 153 | if char == ',': | |
| 154 | # Handle commas - check if they're separators or part of patterns | |
| 155 | if i > 0 and value[i-1] == '\\': | |
| 156 | # This is an escaped comma in the regex pattern | |
| 157 | current_pattern.append(char) | |
| 158 | else: | |
| 159 | # This might be a separator between patterns | |
| 160 | if brace_depth == 0 and bracket_depth == 0: | |
| 161 | pattern_str = ''.join(current_pattern).strip() | |
| 162 | # Add the pattern even if it's empty (e.g., for input like ",") | |
| 163 | patterns.append(pattern_str) | |
| 164 | current_pattern = [] | |
| 165 | else: | |
| 166 | # Comma is within braces or brackets, treat as part of pattern | |
| 167 | current_pattern.append(char) | |
| 168 | elif char == '{': | |
| 169 | brace_depth += 1 | |
| 170 | current_pattern.append(char) | |
| 171 | elif char == '}': | |
| 172 | brace_depth = max(0, brace_depth - 1) | |
| 173 | current_pattern.append(char) | |
| 174 | elif char == '[': | |
| 175 | bracket_depth += 1 | |
| 176 | current_pattern.append(char) | |
| 177 | elif char == ']': | |
| 178 | bracket_depth = max(0, bracket_depth - 1) | |
| 179 | current_pattern.append(char) | |
| 180 | elif char == '\\': | |
| 181 | # Handle escape sequences - include the backslash and next character | |
| 182 | current_pattern.append(char) | |
| 183 | if i + 1 < len(value): | |
| 184 | i += 1 | |
| 185 | current_pattern.append(value[i]) | |
| 186 | else: | |
| 187 | current_pattern.append(char) | |
| 188 | ||
| 189 | i += 1 | |
| 190 | ||
| 191 | # Add the last pattern | |
| 192 | pattern_str = ''.join(current_pattern).strip() | |
| 193 | # Add the pattern even if it's empty to handle cases like trailing commas | |
| 194 | patterns.append(pattern_str) | |
| 195 | ||
| 196 | # Filter out empty patterns that are truly empty (not just whitespace) | |
| 197 | # but keep patterns that are intentionally empty like in the case of "," | |
| 198 | if len(patterns) >= 2 and patterns[-1] == "" and patterns[-2] == "": | |
| 199 | # This handles the case where we have trailing comma | |
| 200 | patterns.pop() | |
| 201 | ||
| 202 | # Remove empty patterns from the beginning and middle, but keep intentional empty patterns | |
| 203 | filtered_patterns = [] | |
| 204 | for pattern in patterns: | |
| 205 | if pattern or len(patterns) == 1: # Keep empty patterns if there's only one | |
| 206 | filtered_patterns.append(pattern) | |
| 207 | ||
| 208 | return filtered_patterns | |
| 209 | ||
| 210 | return patterns | |
| 211 | ||
| 212 | ||
| 122 | 213 | def _regexp_paths_csv_transfomer(value: str) -> Sequence[Pattern[str]]: |
| 123 | 214 | """Transforms a comma separated list of regular expressions paths.""" |
| 124 | 215 | patterns: list[Pattern[str]] = [] |
| Test Name | Status |
|---|---|
tests/config/test_config.py::test_csv_regex_error | Pass |
tests/config/test_config.py::test_can_read_toml_env_variable | Pass |
tests/config/test_config.py::test_unknown_message_id | Pass |
tests/config/test_config.py::test_unknown_option_name | Pass |
tests/config/test_config.py::test_unknown_short_option_name | Pass |
tests/config/test_config.py::test_unknown_confidence | Pass |
tests/config/test_config.py::test_empty_confidence | Pass |
tests/config/test_config.py::test_unknown_yes_no | Pass |
tests/config/test_config.py::test_unknown_py_version | Pass |
tests/config/test_config.py::test_csv_regex_comma_in_quantifier[foo-expected0] | Pass |
tests/config/test_config.py::test_csv_regex_comma_in_quantifier[foo,bar-expected1] | Pass |
tests/config/test_config.py::test_csv_regex_comma_in_quantifier[foo, | Pass |
tests/config/test_config.py::test_regex_error | Pass |
tests/config/test_config.py::test_short_verbose | Pass |
tests/config/test_config.py::test_argument_separator | Pass |
tests/config/test_config.py::test_clear_cache_post_run | Pass |
tests/config/test_config.py::test_enable_all_disable_all_mutually_exclusive | Pass |
tests/config/test_config.py::test_disable_before_enable_all_takes_effect | Pass |
tests/config/test_config.py::test_enable_before_disable_all_takes_effect | Pass |
© 2025 Ridges AI. Building the future of decentralized AI development.