Skip to content

Commit 2256557

Browse files
avvertixgithub-actions[bot]
avvertix
authored and
github-actions[bot]
committed
Fix styling
1 parent 070007c commit 2256557

File tree

7 files changed

+234
-255
lines changed

7 files changed

+234
-255
lines changed

‎src/DocumentFormat/DocumentNode.php‎

Lines changed: 109 additions & 115 deletions
Original file line numberDiff line numberDiff line change
@@ -1,115 +1,109 @@
1-
<?php
2-
3-
namespace OneOffTech\Parse\Client\DocumentFormat;
4-
5-
use Countable;
6-
use OneOffTech\Parse\Client\Exceptions\EmptyDocumentException;
7-
use OneOffTech\Parse\Client\Exceptions\InvalidDocumentFormatException;
8-
use RecursiveArrayIterator;
9-
use RecursiveIteratorIterator;
10-
11-
class DocumentNode implements Countable
12-
{
13-
14-
public function __construct(
15-
public readonly array $content,
16-
public readonly array $attributes = [],
17-
) {}
18-
19-
20-
public function type(): string
21-
{
22-
return 'doc';
23-
}
24-
25-
26-
/**
27-
* The number of pages in this document as extracted by the parser.
28-
*/
29-
public function count(): int
30-
{
31-
return count($this->content);
32-
}
33-
34-
/**
35-
* Test if the document is empty, i.e. contains no pages or has no textual content on any of the pages
36-
*/
37-
public function isEmpty(): bool
38-
{
39-
return $this->count() === 0 || !$this->hasContent();
40-
}
41-
42-
/**
43-
* Test if the document has discernible textual content on any of the pages
44-
*/
45-
public function hasContent(): bool
46-
{
47-
foreach (new RecursiveIteratorIterator(new RecursiveArrayIterator($this->content), RecursiveIteratorIterator::LEAVES_ONLY) as $key => $value) {
48-
if($key === 'text' && !empty($value)){
49-
return true;
50-
}
51-
}
52-
53-
return false;
54-
}
55-
56-
57-
/**
58-
* The pages in this document
59-
*
60-
* @return \OneOffTech\Parse\Client\DocumentFormat\PageNode[]
61-
*/
62-
public function pages(): array
63-
{
64-
return array_map(fn($page) => PageNode::fromArray($page), $this->content);
65-
}
66-
67-
public function text(): string
68-
{
69-
$text = [];
70-
71-
foreach (new RecursiveIteratorIterator(new RecursiveArrayIterator($this->content), RecursiveIteratorIterator::LEAVES_ONLY) as $key => $value) {
72-
if($key === 'text' && !empty($value)){
73-
$text[] = $value;
74-
}
75-
}
76-
77-
return join(PHP_EOL, $text);
78-
}
79-
80-
81-
/**
82-
* Throw exception if document has no textual content
83-
*
84-
* @throws OneOffTech\Parse\Client\Exceptions\EmptyDocumentException when document has no textual content
85-
*/
86-
public function throwIfNoContent(): self
87-
{
88-
if(!$this->hasContent()){
89-
throw new EmptyDocumentException("Document has no textual content.");
90-
}
91-
92-
return $this;
93-
}
94-
95-
96-
/**
97-
* Create a document node from associative array
98-
*/
99-
public static function fromArray(array $data): DocumentNode
100-
{
101-
if(!(isset($data['category']) && isset($data['content']))){
102-
throw new InvalidDocumentFormatException("Unexpected document structure. Missing category or content.");
103-
}
104-
105-
if($data['category'] !== 'doc'){
106-
throw new InvalidDocumentFormatException("Unexpected node category. Expecting [doc] found [{$data['category']}].");
107-
}
108-
109-
if(!is_array($data['content'])){
110-
throw new InvalidDocumentFormatException("Unexpected content format. Expecting [array].");
111-
}
112-
113-
return new DocumentNode($data['content'] ?? [], $data['attributes'] ?? []);
114-
}
115-
}
1+
<?php
2+
3+
namespace OneOffTech\Parse\Client\DocumentFormat;
4+
5+
use Countable;
6+
use OneOffTech\Parse\Client\Exceptions\EmptyDocumentException;
7+
use OneOffTech\Parse\Client\Exceptions\InvalidDocumentFormatException;
8+
use RecursiveArrayIterator;
9+
use RecursiveIteratorIterator;
10+
11+
class DocumentNode implements Countable
12+
{
13+
public function __construct(
14+
public readonly array $content,
15+
public readonly array $attributes = [],
16+
) {}
17+
18+
public function type(): string
19+
{
20+
return 'doc';
21+
}
22+
23+
/**
24+
* The number of pages in this document as extracted by the parser.
25+
*/
26+
public function count(): int
27+
{
28+
return count($this->content);
29+
}
30+
31+
/**
32+
* Test if the document is empty, i.e. contains no pages or has no textual content on any of the pages
33+
*/
34+
public function isEmpty(): bool
35+
{
36+
return $this->count() === 0 || ! $this->hasContent();
37+
}
38+
39+
/**
40+
* Test if the document has discernible textual content on any of the pages
41+
*/
42+
public function hasContent(): bool
43+
{
44+
foreach (new RecursiveIteratorIterator(new RecursiveArrayIterator($this->content), RecursiveIteratorIterator::LEAVES_ONLY) as $key => $value) {
45+
if ($key === 'text' && ! empty($value)) {
46+
return true;
47+
}
48+
}
49+
50+
return false;
51+
}
52+
53+
/**
54+
* The pages in this document
55+
*
56+
* @return \OneOffTech\Parse\Client\DocumentFormat\PageNode[]
57+
*/
58+
public function pages(): array
59+
{
60+
return array_map(fn ($page) => PageNode::fromArray($page), $this->content);
61+
}
62+
63+
public function text(): string
64+
{
65+
$text = [];
66+
67+
foreach (new RecursiveIteratorIterator(new RecursiveArrayIterator($this->content), RecursiveIteratorIterator::LEAVES_ONLY) as $key => $value) {
68+
if ($key === 'text' && ! empty($value)) {
69+
$text[] = $value;
70+
}
71+
}
72+
73+
return implode(PHP_EOL, $text);
74+
}
75+
76+
/**
77+
* Throw exception if document has no textual content
78+
*
79+
* @throws OneOffTech\Parse\Client\Exceptions\EmptyDocumentException when document has no textual content
80+
*/
81+
public function throwIfNoContent(): self
82+
{
83+
if (! $this->hasContent()) {
84+
throw new EmptyDocumentException('Document has no textual content.');
85+
}
86+
87+
return $this;
88+
}
89+
90+
/**
91+
* Create a document node from associative array
92+
*/
93+
public static function fromArray(array $data): DocumentNode
94+
{
95+
if (! (isset($data['category']) && isset($data['content']))) {
96+
throw new InvalidDocumentFormatException('Unexpected document structure. Missing category or content.');
97+
}
98+
99+
if ($data['category'] !== 'doc') {
100+
throw new InvalidDocumentFormatException("Unexpected node category. Expecting [doc] found [{$data['category']}].");
101+
}
102+
103+
if (! is_array($data['content'])) {
104+
throw new InvalidDocumentFormatException('Unexpected content format. Expecting [array].');
105+
}
106+
107+
return new DocumentNode($data['content'] ?? [], $data['attributes'] ?? []);
108+
}
109+
}

0 commit comments

Comments
 (0)