25945556987

Committed 15 May 2026 11:04PM UTC coverage: 97.998% (-0.6%) from 98.554%

Build # 25945556987

Build Type

Pull #128

github

Committed by

web-flow

Commit Message

Merge ce9326ed2 into fddd87e19

Pull Request Pull Request #128: Filter composition ordering

Coverage Stats

750 of 796 new or added lines in 22 files covered. (94.22%)

9 existing lines in 3 files now uncovered.

5433 of 5544 relevant lines covered (98.0%)

588.63 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

97.83

/src/PropertyProcessor/Filter/CompositionBranchClassifier.php

<?php

declare(strict_types=1);

namespace PHPModelGenerator\PropertyProcessor\Filter;

use PHPModelGenerator\Draft\Draft;
use PHPModelGenerator\Utils\TypeCheck;
use PHPModelGenerator\Utils\TypeConverter;

/**
 * Classifies a single composition branch as Input, Output, Mixed, or Empty with
 * respect to the type-spaces of a transforming filter T: InputTypes → OutputTypes.
 *
 * Classification rules:
 *   - Input  — every constraint targets the filter's input type-space.
 *   - Output — every constraint targets the filter's output type-space.
 *   - Mixed  — constraints span both type-spaces.
 *   - Empty  — the branch imposes no structural constraints (empty schema `{}`).
 *
 * Ambiguous keywords (registered only on the 'any' type, or not registered at all)
 * are treated as non-constraining and do not shift the branch away from a unanimous
 * single-space classification. When ALL keywords in a branch are ambiguous, the
 * liberal policy applies and the branch is classified as Input.
 */
class CompositionBranchClassifier
{
    /**
     * JSON Schema composition keywords that may contain nested branch schemas.
     * Each is classified recursively rather than via the Draft type registry.
     */
    private const array NESTED_COMPOSITION_KEYWORDS = ['allOf', 'anyOf', 'oneOf', 'not'];

    /**
     * @param Draft    $draft       The active Draft instance used to resolve keyword type-spaces.
     * @param string[] $inputTypes  PHP type names accepted by the transforming filter
     *                              (e.g. ['string']).
     * @param string[] $outputTypes PHP type names returned by the transforming filter
     *                              (e.g. ['DateTime']).
     */
    public function __construct(
        private readonly Draft $draft,
        private readonly array $inputTypes,
        private readonly array $outputTypes,
    ) {}

    /**
     * Classify a single schema keyword by looking up which Draft-registered types carry it
     * and mapping those types onto the filter's input / output type-spaces.
     *
     * Composition keywords ('allOf', 'anyOf', 'oneOf', 'not') and the structural 'type' keyword
     * are not handled here — call classify() for full branch analysis.  Returns TypeSpace::Empty
     * for keywords registered only on the 'any' pseudo-type (e.g. 'enum', 'filter') or for
     * keywords not registered at all (e.g. '$schema', 'description').
     */
    public function classifySchemaKey(string $key): TypeSpace
    {
        $phpTypeNames = array_values(array_filter(
            array_map(
                static fn(string $draftType): string => TypeConverter::jsonSchemaToPHP($draftType),
                $this->draft->getTypesForKeyword($key),
            ),
            static fn(string $type): bool => $type !== 'any',
        ));

        return empty($phpTypeNames) ? TypeSpace::Empty : $this->resolveTypeSpace($phpTypeNames);
    }

    /**
     * Classify a single composition branch schema.
     *
     * @param array<string, mixed> $branchSchema Decoded JSON object for one branch.
     */
    public function classify(array $branchSchema): TypeSpace
    {
        if (empty($branchSchema)) {
            return TypeSpace::Empty;
        }

        $hasInput  = false;
        $hasOutput = false;

        foreach ($branchSchema as $keyword => $value) {
            $contribution = $this->classifyKeyword($keyword, $value);

            if ($contribution === TypeSpace::Mixed) {
                return TypeSpace::Mixed;
            }

            match ($contribution) {
                TypeSpace::Input  => $hasInput  = true,
                TypeSpace::Output => $hasOutput = true,
                default           => null,  // Empty — no constraint, skip
            };
        }

        return match (true) {
            $hasInput && $hasOutput => TypeSpace::Mixed,
            $hasInput               => TypeSpace::Input,
            $hasOutput              => TypeSpace::Output,
            default                 => TypeSpace::Input,  // all ambiguous: liberal policy
        };
    }

    /**
     * Determine the type-space contribution of a single keyword within a branch.
     *
     * The 'type' keyword is always classified as Input: it asserts raw JSON value structure
     * and must validate against the unfiltered input regardless of the filter's output type.
     * Combining 'type' with output-targeted constraints (e.g. minimum/maximum) in the same
     * branch therefore produces TypeSpace::Mixed, which is correctly rejected as unresolvable.
     *
     * Composition keywords ('allOf', 'anyOf', 'oneOf', 'not') are classified recursively via
     * classifyNestedComposition() — call classify() for full branch analysis.
     *
     * Returns TypeSpace::Empty when the keyword carries no spatial information
     * (registered only on 'any', not registered at all, or an unrecognised key).
     */
    private function classifyKeyword(string $keyword, mixed $value): TypeSpace
    {
        if ($keyword === 'type') {
            return TypeSpace::Input;
        }

        if (in_array($keyword, self::NESTED_COMPOSITION_KEYWORDS, true)) {
            return $this->classifyNestedComposition($keyword, $value);
        }

        // Derive the spatial contribution from the Draft type registry.
        $draftTypeNames = $this->draft->getTypesForKeyword($keyword);

        if (empty($draftTypeNames)) {
            // Keyword not registered in any type (e.g. $schema, title, description).
            return TypeSpace::Empty;
        }

        // Convert JSON Schema type names to PHP type names and discard the 'any'
        // pseudo-type — it is not spatially specific (e.g. enum, const, filter).
        $phpTypeNames = array_values(array_filter(
            array_map(
                static fn(string $draftType): string => TypeConverter::jsonSchemaToPHP($draftType),
                $draftTypeNames,
            ),
            static fn(string $type): bool => $type !== 'any',
        ));

        return empty($phpTypeNames) ? TypeSpace::Empty : $this->resolveTypeSpace($phpTypeNames);
    }

    /**
     * Classify nested composition keywords (allOf, anyOf, oneOf, not) by recursing
     * into their inner branch schemas.
     */
    private function classifyNestedComposition(string $keyword, mixed $value): TypeSpace
    {
        if ($keyword === 'not') {
            return !is_array($value) ? TypeSpace::Empty : $this->classify($value);
        }

        // allOf, anyOf, oneOf: value must be an array of branch schemas.
        if (!is_array($value)) {
            return TypeSpace::Empty;
        }

        $nonEmpty = array_values(array_filter(
            array_map(
                fn(mixed $branch): TypeSpace => is_array($branch)
                    ? $this->classify($branch)
                    : TypeSpace::Empty,
                $value,
            ),
            static fn(TypeSpace $space): bool => $space !== TypeSpace::Empty,
        ));

        if (empty($nonEmpty)) {
            return TypeSpace::Empty;
        }

        $hasMixed  = in_array(TypeSpace::Mixed, $nonEmpty, true);
        $hasInput  = in_array(TypeSpace::Input, $nonEmpty, true);
        $hasOutput = in_array(TypeSpace::Output, $nonEmpty, true);

        return match (true) {
            $hasMixed || ($hasInput && $hasOutput) => TypeSpace::Mixed,
            $hasInput                              => TypeSpace::Input,
            default                                => TypeSpace::Output,
        };
    }

    /**
     * Map a list of PHP type names onto the Input / Output / Mixed / Empty TypeSpace
     * based on whether they overlap with the filter's declared input and output types.
     *
     * Non-primitive class names in the declared output types are expanded to include
     * 'object', so that object-targeted Draft keywords (e.g. minProperties) classify as
     * output-space when the filter returns a class instance.
     *
     * 'int' and 'float' are treated as equivalent for overlap detection (JSON Schema:
     * integer is a subtype of number). Number-typed Draft keywords such as 'minimum' and
     * 'maximum' register under the 'number' → PHP 'float' type, so they must classify as
     * output-space for filters that return 'int', and as input-space for filters that
     * accept 'int'.
     *
     * @param string[] $phpTypeNames
     */
    private function resolveTypeSpace(array $phpTypeNames): TypeSpace
    {
        return $this->classifyAgainstSpaces($phpTypeNames, $this->getEffectiveOutputTypes());
    }

    /**
     * Core classification: map a list of PHP type names onto the Input / Output / Mixed /
     * Empty TypeSpace based on whether they overlap with the filter's input types and the
     * given output type list.
     *
     * @param string[] $phpTypeNames
     * @param string[] $outputTypes
     */
    private function classifyAgainstSpaces(array $phpTypeNames, array $outputTypes): TypeSpace
    {
        $inInput  = !empty(array_intersect($phpTypeNames, $this->expandNumericTypes($this->inputTypes)));
        $inOutput = !empty(array_intersect($phpTypeNames, $this->expandNumericTypes($outputTypes)));

        return match (true) {
            $inInput && $inOutput => TypeSpace::Mixed,
            $inInput              => TypeSpace::Input,
            $inOutput             => TypeSpace::Output,
            default               => TypeSpace::Empty,
        };
    }

    /**
     * Expand a set of PHP type names so that 'int' and 'float' are treated as
     * interchangeable for overlap detection.
     *
     * JSON Schema defines integer as a subtype of number. In the Draft type registry
     * 'number' maps to PHP 'float', so number-typed keywords (minimum, maximum, …)
     * carry 'float' as their type name. A filter that returns 'int' should still make
     * those keywords classify as output-space; a filter that accepts 'int' should make
     * them classify as input-space.
     *
     * @param string[] $types
     * @return string[]
     */
    private function expandNumericTypes(array $types): array
    {
        $hasInt   = in_array('int', $types, true);
        $hasFloat = in_array('float', $types, true);

        if ($hasInt && !$hasFloat) {
            $types[] = 'float';
        } elseif ($hasFloat && !$hasInt) {
            $types[] = 'int';
        }

        return $types;
    }

    /**
     * Expand the declared output types to include 'object' when any output type is a
     * non-primitive class name. This allows object-type Draft keywords (e.g. minProperties,
     * properties) to be classified as output-targeted when the filter returns a class instance.
     *
     * The 'type' keyword is deliberately excluded from this expansion: it validates raw JSON
     * value structure and must classify against the declared output types only (see
     * classifyKeyword). This method is used only for non-'type' structural keywords.
     *
     * @return string[]
     */
    private function getEffectiveOutputTypes(): array
    {
        return array_values(array_unique(array_merge(
            $this->outputTypes,
            array_map(
                static fn(string $type): string => !TypeCheck::isPrimitive($type) && $type !== 'null'
                    ? 'object'
                    : $type,
                $this->outputTypes,
            ),
        )));
    }
}

1	<?php
2
3	declare(strict_types=1);
4
5	namespace PHPModelGenerator\PropertyProcessor\Filter;
6
7	use PHPModelGenerator\Draft\Draft;
8	use PHPModelGenerator\Utils\TypeCheck;
9	use PHPModelGenerator\Utils\TypeConverter;
10
11	/**
12	* Classifies a single composition branch as Input, Output, Mixed, or Empty with
13	* respect to the type-spaces of a transforming filter T: InputTypes → OutputTypes.
14	*
15	* Classification rules:
16	* - Input — every constraint targets the filter's input type-space.
17	* - Output — every constraint targets the filter's output type-space.
18	* - Mixed — constraints span both type-spaces.
19	* - Empty — the branch imposes no structural constraints (empty schema `{}`).
20	*
21	* Ambiguous keywords (registered only on the 'any' type, or not registered at all)
22	* are treated as non-constraining and do not shift the branch away from a unanimous
23	* single-space classification. When ALL keywords in a branch are ambiguous, the
24	* liberal policy applies and the branch is classified as Input.
25	*/
26	class CompositionBranchClassifier
27	{
28	/**
29	* JSON Schema composition keywords that may contain nested branch schemas.
30	* Each is classified recursively rather than via the Draft type registry.
31	*/
32	private const array NESTED_COMPOSITION_KEYWORDS = ['allOf', 'anyOf', 'oneOf', 'not'];
33
34	/**
35	* @param Draft $draft The active Draft instance used to resolve keyword type-spaces.
36	* @param string[] $inputTypes PHP type names accepted by the transforming filter
37	* (e.g. ['string']).
38	* @param string[] $outputTypes PHP type names returned by the transforming filter
39	* (e.g. ['DateTime']).
40	*/
41	public function __construct(	178✔
42	private readonly Draft $draft,
43	private readonly array $inputTypes,
44	private readonly array $outputTypes,
45	) {}	178✔
46
47	/**
48	* Classify a single schema keyword by looking up which Draft-registered types carry it
49	* and mapping those types onto the filter's input / output type-spaces.
50	*
51	* Composition keywords ('allOf', 'anyOf', 'oneOf', 'not') and the structural 'type' keyword
52	* are not handled here — call classify() for full branch analysis. Returns TypeSpace::Empty
53	* for keywords registered only on the 'any' pseudo-type (e.g. 'enum', 'filter') or for
54	* keywords not registered at all (e.g. '$schema', 'description').
55	*/
56	public function classifySchemaKey(string $key): TypeSpace	2✔
57	{
58	$phpTypeNames = array_values(array_filter(	2✔
59	array_map(	2✔
60	static fn(string $draftType): string => TypeConverter::jsonSchemaToPHP($draftType),	2✔
61	$this->draft->getTypesForKeyword($key),	2✔
62	),	2✔
63	static fn(string $type): bool => $type !== 'any',	2✔
64	));	2✔
65
66	return empty($phpTypeNames) ? TypeSpace::Empty : $this->resolveTypeSpace($phpTypeNames);	2✔
67	}
68
69	/**
70	* Classify a single composition branch schema.
71	*
72	* @param array<string, mixed> $branchSchema Decoded JSON object for one branch.
73	*/
74	public function classify(array $branchSchema): TypeSpace	87✔
75	{
76	if (empty($branchSchema)) {	87✔
77	return TypeSpace::Empty;	4✔
78	}
79
80	$hasInput = false;	84✔
81	$hasOutput = false;	84✔
82
83	foreach ($branchSchema as $keyword => $value) {	84✔
84	$contribution = $this->classifyKeyword($keyword, $value);	84✔
85
86	if ($contribution === TypeSpace::Mixed) {	84✔
87	return TypeSpace::Mixed;	2✔
88	}
89
90	match ($contribution) {
91	TypeSpace::Input => $hasInput = true,	84✔
92	TypeSpace::Output => $hasOutput = true,	49✔
93	default => null, // Empty — no constraint, skip	18✔
94	};
95	}
96
97	return match (true) {
98	$hasInput && $hasOutput => TypeSpace::Mixed,	84✔
99	$hasInput => TypeSpace::Input,	78✔
100	$hasOutput => TypeSpace::Output,	43✔
101	default => TypeSpace::Input, // all ambiguous: liberal policy	84✔
102	};
103	}
104
105	/**
106	* Determine the type-space contribution of a single keyword within a branch.
107	*
108	* The 'type' keyword is always classified as Input: it asserts raw JSON value structure
109	* and must validate against the unfiltered input regardless of the filter's output type.
110	* Combining 'type' with output-targeted constraints (e.g. minimum/maximum) in the same
111	* branch therefore produces TypeSpace::Mixed, which is correctly rejected as unresolvable.
112	*
113	* Composition keywords ('allOf', 'anyOf', 'oneOf', 'not') are classified recursively via
114	* classifyNestedComposition() — call classify() for full branch analysis.
115	*
116	* Returns TypeSpace::Empty when the keyword carries no spatial information
117	* (registered only on 'any', not registered at all, or an unrecognised key).
118	*/
119	private function classifyKeyword(string $keyword, mixed $value): TypeSpace	84✔
120	{
121	if ($keyword === 'type') {	84✔
122	return TypeSpace::Input;	29✔
123	}
124
125	if (in_array($keyword, self::NESTED_COMPOSITION_KEYWORDS, true)) {	75✔
126	return $this->classifyNestedComposition($keyword, $value);	11✔
127	}
128
129	// Derive the spatial contribution from the Draft type registry.
130	$draftTypeNames = $this->draft->getTypesForKeyword($keyword);	72✔
131
132	if (empty($draftTypeNames)) {	72✔
133	// Keyword not registered in any type (e.g. $schema, title, description).
134	return TypeSpace::Empty;	4✔
135	}
136
137	// Convert JSON Schema type names to PHP type names and discard the 'any'
138	// pseudo-type — it is not spatially specific (e.g. enum, const, filter).
139	$phpTypeNames = array_values(array_filter(	68✔
140	array_map(	68✔
141	static fn(string $draftType): string => TypeConverter::jsonSchemaToPHP($draftType),	68✔
142	$draftTypeNames,	68✔
143	),	68✔
144	static fn(string $type): bool => $type !== 'any',	68✔
145	));	68✔
146
147	return empty($phpTypeNames) ? TypeSpace::Empty : $this->resolveTypeSpace($phpTypeNames);	68✔
148	}
149
150	/**
151	* Classify nested composition keywords (allOf, anyOf, oneOf, not) by recursing
152	* into their inner branch schemas.
153	*/
154	private function classifyNestedComposition(string $keyword, mixed $value): TypeSpace	11✔
155	{
156	if ($keyword === 'not') {	11✔
157	return !is_array($value) ? TypeSpace::Empty : $this->classify($value);	2✔
158	}
159
160	// allOf, anyOf, oneOf: value must be an array of branch schemas.
161	if (!is_array($value)) {	9✔
NEW 162	return TypeSpace::Empty;	×
163	}
164
165	$nonEmpty = array_values(array_filter(	9✔
166	array_map(	9✔
167	fn(mixed $branch): TypeSpace => is_array($branch)	9✔
168	? $this->classify($branch)	9✔
169	: TypeSpace::Empty,	9✔
170	$value,	9✔
171	),	9✔
172	static fn(TypeSpace $space): bool => $space !== TypeSpace::Empty,	9✔
173	));	9✔
174
175	if (empty($nonEmpty)) {	9✔
176	return TypeSpace::Empty;	1✔
177	}
178
179	$hasMixed = in_array(TypeSpace::Mixed, $nonEmpty, true);	8✔
180	$hasInput = in_array(TypeSpace::Input, $nonEmpty, true);	8✔
181	$hasOutput = in_array(TypeSpace::Output, $nonEmpty, true);	8✔
182
183	return match (true) {
184	$hasMixed \|\| ($hasInput && $hasOutput) => TypeSpace::Mixed,	8✔
185	$hasInput => TypeSpace::Input,	6✔
186	default => TypeSpace::Output,	8✔
187	};
188	}
189
190	/**
191	* Map a list of PHP type names onto the Input / Output / Mixed / Empty TypeSpace
192	* based on whether they overlap with the filter's declared input and output types.
193	*
194	* Non-primitive class names in the declared output types are expanded to include
195	* 'object', so that object-targeted Draft keywords (e.g. minProperties) classify as
196	* output-space when the filter returns a class instance.
197	*
198	* 'int' and 'float' are treated as equivalent for overlap detection (JSON Schema:
199	* integer is a subtype of number). Number-typed Draft keywords such as 'minimum' and
200	* 'maximum' register under the 'number' → PHP 'float' type, so they must classify as
201	* output-space for filters that return 'int', and as input-space for filters that
202	* accept 'int'.
203	*
204	* @param string[] $phpTypeNames
205	*/
206	private function resolveTypeSpace(array $phpTypeNames): TypeSpace	68✔
207	{
208	return $this->classifyAgainstSpaces($phpTypeNames, $this->getEffectiveOutputTypes());	68✔
209	}
210
211	/**
212	* Core classification: map a list of PHP type names onto the Input / Output / Mixed /
213	* Empty TypeSpace based on whether they overlap with the filter's input types and the
214	* given output type list.
215	*
216	* @param string[] $phpTypeNames
217	* @param string[] $outputTypes
218	*/
219	private function classifyAgainstSpaces(array $phpTypeNames, array $outputTypes): TypeSpace	68✔
220	{
221	$inInput = !empty(array_intersect($phpTypeNames, $this->expandNumericTypes($this->inputTypes)));	68✔
222	$inOutput = !empty(array_intersect($phpTypeNames, $this->expandNumericTypes($outputTypes)));	68✔
223
224	return match (true) {
225	$inInput && $inOutput => TypeSpace::Mixed,	68✔
226	$inInput => TypeSpace::Input,	68✔
227	$inOutput => TypeSpace::Output,	44✔
228	default => TypeSpace::Empty,	68✔
229	};
230	}
231
232	/**
233	* Expand a set of PHP type names so that 'int' and 'float' are treated as
234	* interchangeable for overlap detection.
235	*
236	* JSON Schema defines integer as a subtype of number. In the Draft type registry
237	* 'number' maps to PHP 'float', so number-typed keywords (minimum, maximum, …)
238	* carry 'float' as their type name. A filter that returns 'int' should still make
239	* those keywords classify as output-space; a filter that accepts 'int' should make
240	* them classify as input-space.
241	*
242	* @param string[] $types
243	* @return string[]
244	*/
245	private function expandNumericTypes(array $types): array	68✔
246	{
247	$hasInt = in_array('int', $types, true);	68✔
248	$hasFloat = in_array('float', $types, true);	68✔
249
250	if ($hasInt && !$hasFloat) {	68✔
251	$types[] = 'float';	15✔
252	} elseif ($hasFloat && !$hasInt) {	68✔
NEW 253	$types[] = 'int';	×
254	}
255
256	return $types;	68✔
257	}
258
259	/**
260	* Expand the declared output types to include 'object' when any output type is a
261	* non-primitive class name. This allows object-type Draft keywords (e.g. minProperties,
262	* properties) to be classified as output-targeted when the filter returns a class instance.
263	*
264	* The 'type' keyword is deliberately excluded from this expansion: it validates raw JSON
265	* value structure and must classify against the declared output types only (see
266	* classifyKeyword). This method is used only for non-'type' structural keywords.
267	*
268	* @return string[]
269	*/
270	private function getEffectiveOutputTypes(): array	68✔
271	{
272	return array_values(array_unique(array_merge(	68✔
273	$this->outputTypes,	68✔
274	array_map(	68✔
275	static fn(string $type): string => !TypeCheck::isPrimitive($type) && $type !== 'null'	68✔
276	? 'object'	53✔
277	: $type,	68✔
278	$this->outputTypes,	68✔
279	),	68✔
280	)));	68✔
281	}
282	}

wol-soft / php-json-schema-model-generator / 25945556987

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous