| 1 | import re |
| 2 | import sys |
| 3 | import time |
| 4 | from helpers import files |
| 5 | |
| 6 | def sanitize_string(s: str, encoding: str = "utf-8") -> str: |
| 7 | # Replace surrogates and invalid unicode with replacement character |
| 8 | if not isinstance(s, str): |
| 9 | s = str(s) |
| 10 | return s.encode(encoding, 'replace').decode(encoding, 'replace') |
| 11 | |
| 12 | def calculate_valid_match_lengths(first: bytes | str, second: bytes | str, |
| 13 | deviation_threshold: int = 5, |
| 14 | deviation_reset: int = 5, |
| 15 | ignore_patterns: list[bytes|str] = [], |
| 16 | debug: bool = False) -> tuple[int, int]: |
| 17 | |
| 18 | first_length = len(first) |
| 19 | second_length = len(second) |
| 20 | |
| 21 | i, j = 0, 0 |
| 22 | deviations = 0 |
| 23 | matched_since_deviation = 0 |
| 24 | last_matched_i, last_matched_j = 0, 0 # Track the last matched index |
| 25 | |
| 26 | def skip_ignored_patterns(s, index): |
| 27 | """Skip characters in `s` that match any pattern in `ignore_patterns` starting from `index`.""" |
| 28 | while index < len(s): |
| 29 | for pattern in ignore_patterns: |
| 30 | match = re.match(pattern, s[index:]) |
| 31 | if match: |
| 32 | index += len(match.group(0)) |
| 33 | break |
| 34 | else: |
| 35 | break |
| 36 | return index |
| 37 | |
| 38 | while i < first_length and j < second_length: |
| 39 | # Skip ignored patterns |
| 40 | i = skip_ignored_patterns(first, i) |
| 41 | j = skip_ignored_patterns(second, j) |
| 42 | |
| 43 | if i < first_length and j < second_length and first[i] == second[j]: |
| 44 | last_matched_i, last_matched_j = i + 1, j + 1 # Update last matched position |
| 45 | i += 1 |
| 46 | j += 1 |
| 47 | matched_since_deviation += 1 |
| 48 | |
| 49 | # Reset the deviation counter if we've matched enough characters since the last deviation |
| 50 | if matched_since_deviation >= deviation_reset: |
| 51 | deviations = 0 |
| 52 | matched_since_deviation = 0 |
| 53 | else: |
| 54 | # Determine the look-ahead based on the remaining deviation threshold |
| 55 | look_ahead = deviation_threshold - deviations |
| 56 | |
| 57 | # Look ahead to find the best match within the remaining deviation allowance |
| 58 | best_match = None |
| 59 | for k in range(1, look_ahead + 1): |
| 60 | if i + k < first_length and j < second_length and first[i + k] == second[j]: |
| 61 | best_match = ('i', k) |
| 62 | break |
| 63 | if j + k < second_length and i < first_length and first[i] == second[j + k]: |
| 64 | best_match = ('j', k) |
| 65 | break |
| 66 | |
| 67 | if best_match: |
| 68 | if best_match[0] == 'i': |
| 69 | i += best_match[1] |
| 70 | elif best_match[0] == 'j': |
| 71 | j += best_match[1] |
| 72 | else: |
| 73 | i += 1 |
| 74 | j += 1 |
| 75 | |
| 76 | deviations += 1 |
| 77 | matched_since_deviation = 0 |
| 78 | |
| 79 | if deviations > deviation_threshold: |
| 80 | break |
| 81 | |
| 82 | if debug: |
| 83 | output = ( |
| 84 | f"First (up to {last_matched_i}): {first[:last_matched_i]!r}\n" |
| 85 | "\n" |
| 86 | f"Second (up to {last_matched_j}): {second[:last_matched_j]!r}\n" |
| 87 | "\n" |
| 88 | f"Current deviation: {deviations}\n" |
| 89 | f"Matched since last deviation: {matched_since_deviation}\n" |
| 90 | + "-" * 40 + "\n" |
| 91 | ) |
| 92 | sys.stdout.write("\r" + output) |
| 93 | sys.stdout.flush() |
| 94 | time.sleep(0.01) # Add a short delay for readability (optional) |
| 95 | |
| 96 | # Return the last matched positions instead of the current indices |
| 97 | return last_matched_i, last_matched_j |
| 98 | |
| 99 | def format_key(key: str) -> str: |
| 100 | """Format a key string to be more readable. |
| 101 | Converts camelCase and snake_case to Title Case with spaces.""" |
| 102 | # First replace non-alphanumeric with spaces |
| 103 | result = ''.join(' ' if not c.isalnum() else c for c in key) |
| 104 | |
| 105 | # Handle camelCase |
| 106 | formatted = '' |
| 107 | for i, c in enumerate(result): |
| 108 | if i > 0 and c.isupper() and result[i-1].islower(): |
| 109 | formatted += ' ' + c |
| 110 | else: |
| 111 | formatted += c |
| 112 | |
| 113 | # Split on spaces and capitalize each word |
| 114 | return ' '.join(word.capitalize() for word in formatted.split()) |
| 115 | |
| 116 | def dict_to_text(d: dict) -> str: |
| 117 | parts = [] |
| 118 | for key, value in d.items(): |
| 119 | parts.append(f"{format_key(str(key))}:") |
| 120 | parts.append(f"{value}") |
| 121 | parts.append("") # Add empty line between entries |
| 122 | |
| 123 | return "\n".join(parts).rstrip() # rstrip to remove trailing newline |
| 124 | |
| 125 | def truncate_text(text: str, length: int, at_end: bool = True, replacement: str = "...") -> str: |
| 126 | orig_length = len(text) |
| 127 | if orig_length <= length: |
| 128 | return text |
| 129 | if at_end: |
| 130 | return text[:length] + replacement |
| 131 | else: |
| 132 | return replacement + text[-length:] |
| 133 | |
| 134 | def truncate_text_by_ratio(text: str, threshold: int, replacement: str = "...", ratio: float = 0.5) -> str: |
| 135 | """Truncate text with replacement at a specified ratio position.""" |
| 136 | threshold = int(threshold) |
| 137 | if not threshold or len(text) <= threshold: |
| 138 | return text |
| 139 | |
| 140 | # Clamp ratio to valid range |
| 141 | ratio = max(0.0, min(1.0, float(ratio))) |
| 142 | |
| 143 | # Calculate available space for original text after accounting for replacement |
| 144 | available_space = threshold - len(replacement) |
| 145 | if available_space <= 0: |
| 146 | return replacement[:threshold] |
| 147 | |
| 148 | # Handle edge cases for efficiency |
| 149 | if ratio == 0.0: |
| 150 | # Replace from start: "...text" |
| 151 | return replacement + text[-available_space:] |
| 152 | elif ratio == 1.0: |
| 153 | # Replace from end: "text..." |
| 154 | return text[:available_space] + replacement |
| 155 | else: |
| 156 | # Replace in middle based on ratio |
| 157 | start_len = int(available_space * ratio) |
| 158 | end_len = available_space - start_len |
| 159 | return text[:start_len] + replacement + text[-end_len:] |
| 160 | |
| 161 | |
| 162 | def replace_file_includes(text: str, placeholder_pattern: str = r"§§include\(([^)]+)\)") -> str: |
| 163 | # Replace include aliases with file content |
| 164 | if not text: |
| 165 | return text |
| 166 | |
| 167 | def _repl(match): |
| 168 | path = match.group(1) |
| 169 | try: |
| 170 | # read file content |
| 171 | path = files.fix_dev_path(path) |
| 172 | return files.read_file(path) |
| 173 | except Exception: |
| 174 | # if file not readable keep original placeholder |
| 175 | return match.group(0) |
| 176 | |
| 177 | return re.sub(placeholder_pattern, _repl, text) |