|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
declare(strict_types=1); |
|
4
|
|
|
|
|
5
|
|
|
namespace MartinGeorgiev\Utils; |
|
6
|
|
|
|
|
7
|
|
|
use MartinGeorgiev\Utils\Exception\InvalidArrayFormatException; |
|
8
|
|
|
|
|
9
|
|
|
/** |
|
10
|
|
|
* Handles transformation from PostgreSQL text arrays to PHP values. |
|
11
|
|
|
* |
|
12
|
|
|
* @since 3.0 |
|
13
|
|
|
* |
|
14
|
|
|
* @author Martin Georgiev <[email protected]> |
|
15
|
|
|
*/ |
|
16
|
|
|
class PostgresArrayToPHPArrayTransformer |
|
17
|
|
|
{ |
|
18
|
|
|
private const POSTGRESQL_EMPTY_ARRAY = '{}'; |
|
19
|
|
|
|
|
20
|
|
|
private const POSTGRESQL_NULL_VALUE = 'null'; |
|
21
|
|
|
|
|
22
|
|
|
/** |
|
23
|
|
|
* Transforms a PostgreSQL text array to a PHP array. |
|
24
|
|
|
* This method supports only single-dimensional text arrays and |
|
25
|
|
|
* relies on the default escaping strategy in PostgreSQL (double quotes). |
|
26
|
|
|
* |
|
27
|
|
|
* @throws InvalidArrayFormatException when the input is a multi-dimensional array or has an invalid format |
|
28
|
|
|
*/ |
|
29
|
43 |
|
public static function transformPostgresArrayToPHPArray(string $postgresArray): array |
|
30
|
|
|
{ |
|
31
|
43 |
|
$trimmed = \trim($postgresArray); |
|
32
|
|
|
|
|
33
|
43 |
|
if ($trimmed === '' || \strtolower($trimmed) === self::POSTGRESQL_NULL_VALUE) { |
|
34
|
3 |
|
return []; |
|
35
|
|
|
} |
|
36
|
|
|
|
|
37
|
40 |
|
if (\str_contains($trimmed, '},{') || \str_starts_with($trimmed, '{{')) { |
|
38
|
1 |
|
throw InvalidArrayFormatException::multiDimensionalArrayNotSupported(); |
|
39
|
|
|
} |
|
40
|
|
|
|
|
41
|
39 |
|
if ($trimmed === self::POSTGRESQL_EMPTY_ARRAY) { |
|
42
|
1 |
|
return []; |
|
43
|
|
|
} |
|
44
|
|
|
|
|
45
|
|
|
// Check for malformed nesting - this is a more specific check than the one above |
|
46
|
|
|
// But we need to exclude cases where curly braces are part of quoted strings |
|
47
|
38 |
|
$content = \trim($trimmed, self::POSTGRESQL_EMPTY_ARRAY); |
|
48
|
38 |
|
$inQuotes = false; |
|
49
|
38 |
|
$escaping = false; |
|
50
|
|
|
|
|
51
|
38 |
|
for ($i = 0, $len = \strlen($content); $i < $len; $i++) { |
|
52
|
38 |
|
$char = $content[$i]; |
|
53
|
|
|
|
|
54
|
38 |
|
if ($escaping) { |
|
55
|
16 |
|
$escaping = false; |
|
56
|
|
|
|
|
57
|
16 |
|
continue; |
|
58
|
|
|
} |
|
59
|
|
|
|
|
60
|
38 |
|
if ($char === '\\' && $inQuotes) { |
|
61
|
16 |
|
$escaping = true; |
|
62
|
|
|
|
|
63
|
16 |
|
continue; |
|
64
|
|
|
} |
|
65
|
|
|
|
|
66
|
38 |
|
if ($char === '"') { |
|
67
|
28 |
|
$inQuotes = !$inQuotes; |
|
|
|
|
|
|
68
|
36 |
|
} elseif (($char === '{' || $char === '}') && !$inQuotes) { |
|
69
|
1 |
|
throw InvalidArrayFormatException::invalidFormat('Malformed array nesting detected'); |
|
70
|
|
|
} |
|
71
|
|
|
} |
|
72
|
|
|
|
|
73
|
|
|
// Check for unclosed quotes |
|
74
|
37 |
|
if ($inQuotes) { |
|
|
|
|
|
|
75
|
2 |
|
throw InvalidArrayFormatException::invalidFormat('Unclosed quotes in array'); |
|
76
|
|
|
} |
|
77
|
|
|
|
|
78
|
|
|
// First try with json_decode for properly quoted values |
|
79
|
35 |
|
$jsonArray = '['.\trim($trimmed, self::POSTGRESQL_EMPTY_ARRAY).']'; |
|
80
|
|
|
|
|
81
|
|
|
/** @var array<int, mixed>|null $decoded */ |
|
82
|
35 |
|
$decoded = \json_decode($jsonArray, true, 512, JSON_BIGINT_AS_STRING); |
|
83
|
|
|
|
|
84
|
|
|
// If json_decode fails, try manual parsing for unquoted strings |
|
85
|
35 |
|
if ($decoded === null && \json_last_error() !== JSON_ERROR_NONE) { |
|
86
|
13 |
|
return self::parsePostgresArrayManually($content); |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
22 |
|
return (array) $decoded; |
|
90
|
|
|
} |
|
91
|
|
|
|
|
92
|
13 |
|
private static function parsePostgresArrayManually(string $content): array |
|
93
|
|
|
{ |
|
94
|
13 |
|
if ($content === '') { |
|
95
|
|
|
return []; |
|
96
|
|
|
} |
|
97
|
|
|
|
|
98
|
|
|
// Parse the array manually, handling quoted and unquoted values |
|
99
|
13 |
|
$result = []; |
|
100
|
13 |
|
$inQuotes = false; |
|
101
|
13 |
|
$currentValue = ''; |
|
102
|
13 |
|
$escaping = false; |
|
103
|
|
|
|
|
104
|
13 |
|
for ($i = 0, $len = \strlen($content); $i < $len; $i++) { |
|
105
|
13 |
|
$char = $content[$i]; |
|
106
|
|
|
|
|
107
|
|
|
// Handle escaping within quotes |
|
108
|
13 |
|
if ($escaping) { |
|
109
|
5 |
|
$currentValue .= $char; |
|
110
|
5 |
|
$escaping = false; |
|
111
|
|
|
|
|
112
|
5 |
|
continue; |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
13 |
|
if ($char === '\\' && $inQuotes) { |
|
116
|
5 |
|
$escaping = true; |
|
117
|
5 |
|
$currentValue .= $char; |
|
118
|
|
|
|
|
119
|
5 |
|
continue; |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
13 |
|
if ($char === '"') { |
|
123
|
7 |
|
$inQuotes = !$inQuotes; |
|
|
|
|
|
|
124
|
|
|
// For quoted values, we include the quotes for later processing |
|
125
|
7 |
|
$currentValue .= $char; |
|
126
|
13 |
|
} elseif ($char === ',' && !$inQuotes) { |
|
127
|
|
|
// End of value |
|
128
|
10 |
|
$result[] = self::processPostgresValue($currentValue); |
|
129
|
10 |
|
$currentValue = ''; |
|
130
|
|
|
} else { |
|
131
|
13 |
|
$currentValue .= $char; |
|
132
|
|
|
} |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
// Add the last value |
|
136
|
13 |
|
if ($currentValue !== '') { |
|
137
|
12 |
|
$result[] = self::processPostgresValue($currentValue); |
|
138
|
|
|
} |
|
139
|
|
|
|
|
140
|
13 |
|
return $result; |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
|
|
/** |
|
144
|
|
|
* Process a single value from a PostgreSQL array. |
|
145
|
|
|
*/ |
|
146
|
13 |
|
private static function processPostgresValue(string $value): mixed |
|
147
|
|
|
{ |
|
148
|
13 |
|
$value = \trim($value); |
|
149
|
|
|
|
|
150
|
13 |
|
if (self::isNullValue($value)) { |
|
151
|
1 |
|
return null; |
|
152
|
|
|
} |
|
153
|
|
|
|
|
154
|
13 |
|
if (self::isBooleanValue($value)) { |
|
155
|
1 |
|
return self::processBooleanValue($value); |
|
156
|
|
|
} |
|
157
|
|
|
|
|
158
|
12 |
|
if (self::isQuotedString($value)) { |
|
159
|
7 |
|
return self::processQuotedString($value); |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
8 |
|
if (self::isNumericValue($value)) { |
|
163
|
|
|
return self::processNumericValue($value); |
|
164
|
|
|
} |
|
165
|
|
|
|
|
166
|
|
|
// For unquoted strings, return as is |
|
167
|
8 |
|
return $value; |
|
168
|
|
|
} |
|
169
|
|
|
|
|
170
|
13 |
|
private static function isNullValue(string $value): bool |
|
171
|
|
|
{ |
|
172
|
13 |
|
return $value === 'NULL' || $value === 'null'; |
|
173
|
|
|
} |
|
174
|
|
|
|
|
175
|
13 |
|
private static function isBooleanValue(string $value): bool |
|
176
|
|
|
{ |
|
177
|
13 |
|
return \in_array($value, ['true', 't', 'false', 'f'], true); |
|
178
|
|
|
} |
|
179
|
|
|
|
|
180
|
1 |
|
private static function processBooleanValue(string $value): bool |
|
181
|
|
|
{ |
|
182
|
1 |
|
return $value === 'true' || $value === 't'; |
|
183
|
|
|
} |
|
184
|
|
|
|
|
185
|
12 |
|
private static function isQuotedString(string $value): bool |
|
186
|
|
|
{ |
|
187
|
12 |
|
return \strlen($value) >= 2 && $value[0] === '"' && $value[\strlen($value) - 1] === '"'; |
|
188
|
|
|
} |
|
189
|
|
|
|
|
190
|
7 |
|
private static function processQuotedString(string $value): string |
|
191
|
|
|
{ |
|
192
|
|
|
// Remove the quotes and unescape the string |
|
193
|
7 |
|
$unquoted = \substr($value, 1, -1); |
|
194
|
|
|
|
|
195
|
7 |
|
return self::unescapeString($unquoted); |
|
196
|
|
|
} |
|
197
|
|
|
|
|
198
|
8 |
|
private static function isNumericValue(string $value): bool |
|
199
|
|
|
{ |
|
200
|
8 |
|
return \is_numeric($value); |
|
201
|
|
|
} |
|
202
|
|
|
|
|
203
|
|
|
private static function processNumericValue(string $value): float|int |
|
204
|
|
|
{ |
|
205
|
|
|
// Convert to int or float as appropriate |
|
206
|
|
|
if (\str_contains($value, '.') || \stripos($value, 'e') !== false) { |
|
207
|
|
|
return (float) $value; |
|
208
|
|
|
} |
|
209
|
|
|
|
|
210
|
|
|
return (int) $value; |
|
211
|
|
|
} |
|
212
|
|
|
|
|
213
|
7 |
|
private static function unescapeString(string $value): string |
|
214
|
|
|
{ |
|
215
|
|
|
/** |
|
216
|
|
|
* PostgreSQL array escaping rules: |
|
217
|
|
|
* \\ -> \ (escaped backslash becomes literal backslash) |
|
218
|
|
|
* \" -> " (escaped quote becomes literal quote) |
|
219
|
|
|
* Everything else remains as-is |
|
220
|
|
|
*/ |
|
221
|
7 |
|
$result = ''; |
|
222
|
7 |
|
$length = \strlen($value); |
|
223
|
7 |
|
$position = 0; |
|
224
|
|
|
|
|
225
|
7 |
|
while ($position < $length) { |
|
226
|
7 |
|
if ($value[$position] === '\\' && $position + 1 < $length) { |
|
227
|
5 |
|
$nextChar = $value[$position + 1]; |
|
228
|
|
|
|
|
229
|
5 |
|
if ($nextChar === '\\') { |
|
230
|
|
|
// \\ -> \ |
|
231
|
1 |
|
$result .= '\\'; |
|
232
|
1 |
|
$position += 2; |
|
233
|
4 |
|
} elseif ($nextChar === '"') { |
|
234
|
|
|
// \" -> " |
|
235
|
3 |
|
$result .= '"'; |
|
236
|
3 |
|
$position += 2; |
|
237
|
|
|
} else { |
|
238
|
|
|
// \ followed by anything else - keep the backslash |
|
239
|
3 |
|
$result .= '\\'; |
|
240
|
3 |
|
$position++; |
|
241
|
|
|
} |
|
242
|
|
|
} else { |
|
243
|
7 |
|
$result .= $value[$position]; |
|
244
|
7 |
|
$position++; |
|
245
|
|
|
} |
|
246
|
|
|
} |
|
247
|
|
|
|
|
248
|
7 |
|
return $result; |
|
249
|
|
|
} |
|
250
|
|
|
} |
|
251
|
|
|
|