mirror of
https://github.com/silverstripe/silverstripe-textextraction
synced 2024-10-22 11:06:00 +02:00
ENH PHP 8.1 compatibility
This commit is contained in:
parent
77fecc4c53
commit
df8b17ab85
@ -42,7 +42,7 @@ class Cache implements FileTextCache, Flushable
|
|||||||
*/
|
*/
|
||||||
protected function getKey(File $file)
|
protected function getKey(File $file)
|
||||||
{
|
{
|
||||||
return md5($file->getFilename());
|
return md5($file->getFilename() ?? '');
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
@ -58,7 +58,7 @@ abstract class FileTextExtractor
|
|||||||
arsort($classPriorities);
|
arsort($classPriorities);
|
||||||
|
|
||||||
// Save classes
|
// Save classes
|
||||||
$sortedClasses = array_keys($classPriorities);
|
$sortedClasses = array_keys($classPriorities ?? []);
|
||||||
return self::$sorted_extractor_classes = $sortedClasses;
|
return self::$sorted_extractor_classes = $sortedClasses;
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -81,7 +81,7 @@ abstract class FileTextExtractor
|
|||||||
*/
|
*/
|
||||||
public static function for_file($file)
|
public static function for_file($file)
|
||||||
{
|
{
|
||||||
if (!$file || (is_string($file) && !file_exists($file))) {
|
if (!$file || (is_string($file) && !file_exists($file ?? ''))) {
|
||||||
return null;
|
return null;
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -137,11 +137,11 @@ abstract class FileTextExtractor
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Remove any existing temp files with this name
|
// Remove any existing temp files with this name
|
||||||
if (file_exists($path)) {
|
if (file_exists($path ?? '')) {
|
||||||
unlink($path);
|
unlink($path ?? '');
|
||||||
}
|
}
|
||||||
|
|
||||||
$bytesWritten = file_put_contents($path, $file->getStream());
|
$bytesWritten = file_put_contents($path ?? '', $file->getStream());
|
||||||
if (false === $bytesWritten) {
|
if (false === $bytesWritten) {
|
||||||
throw new Exception(static::class . '->getPathFromFile() failed to write temporary file');
|
throw new Exception(static::class . '->getPathFromFile() failed to write temporary file');
|
||||||
}
|
}
|
||||||
|
@ -34,7 +34,7 @@ class HTMLTextExtractor extends FileTextExtractor
|
|||||||
*/
|
*/
|
||||||
public function supportsExtension($extension)
|
public function supportsExtension($extension)
|
||||||
{
|
{
|
||||||
return in_array(strtolower($extension), ["html", "htm", "xhtml"]);
|
return in_array(strtolower($extension ?? ''), ["html", "htm", "xhtml"]);
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
@ -43,7 +43,7 @@ class HTMLTextExtractor extends FileTextExtractor
|
|||||||
*/
|
*/
|
||||||
public function supportsMime($mime)
|
public function supportsMime($mime)
|
||||||
{
|
{
|
||||||
return strtolower($mime) === 'text/html';
|
return strtolower($mime ?? '') === 'text/html';
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
@ -56,7 +56,7 @@ class HTMLTextExtractor extends FileTextExtractor
|
|||||||
*/
|
*/
|
||||||
public function getContent($file)
|
public function getContent($file)
|
||||||
{
|
{
|
||||||
$content = $file instanceof File ? $file->getString() : file_get_contents($file);
|
$content = $file instanceof File ? $file->getString() : file_get_contents($file ?? '');
|
||||||
|
|
||||||
// Yes, yes, regex'ing HTML is evil.
|
// Yes, yes, regex'ing HTML is evil.
|
||||||
// Since we don't care about well-formedness or markup here, it does the job.
|
// Since we don't care about well-formedness or markup here, it does the job.
|
||||||
@ -82,9 +82,9 @@ class HTMLTextExtractor extends FileTextExtractor
|
|||||||
'@</?((frameset)|(frame)|(iframe))@iu',
|
'@</?((frameset)|(frame)|(iframe))@iu',
|
||||||
],
|
],
|
||||||
[' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', "$0", "$0", "$0", "$0", "$0", "$0", "$0", "$0"],
|
[' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', "$0", "$0", "$0", "$0", "$0", "$0", "$0", "$0"],
|
||||||
$content
|
$content ?? ''
|
||||||
);
|
);
|
||||||
|
|
||||||
return strip_tags($content);
|
return strip_tags($content ?? '');
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -33,18 +33,18 @@ class PDFTextExtractor extends FileTextExtractor
|
|||||||
public function isAvailable()
|
public function isAvailable()
|
||||||
{
|
{
|
||||||
$bin = $this->bin('pdftotext');
|
$bin = $this->bin('pdftotext');
|
||||||
return $bin && file_exists($bin) && is_executable($bin);
|
return $bin && file_exists($bin ?? '') && is_executable($bin ?? '');
|
||||||
}
|
}
|
||||||
|
|
||||||
public function supportsExtension($extension)
|
public function supportsExtension($extension)
|
||||||
{
|
{
|
||||||
return strtolower($extension) === 'pdf';
|
return strtolower($extension ?? '') === 'pdf';
|
||||||
}
|
}
|
||||||
|
|
||||||
public function supportsMime($mime)
|
public function supportsMime($mime)
|
||||||
{
|
{
|
||||||
return in_array(
|
return in_array(
|
||||||
strtolower($mime),
|
strtolower($mime ?? ''),
|
||||||
[
|
[
|
||||||
'application/pdf',
|
'application/pdf',
|
||||||
'application/x-pdf',
|
'application/x-pdf',
|
||||||
@ -72,7 +72,7 @@ class PDFTextExtractor extends FileTextExtractor
|
|||||||
// Find program in each path
|
// Find program in each path
|
||||||
foreach ($locations as $location) {
|
foreach ($locations as $location) {
|
||||||
$path = "{$location}/{$program}";
|
$path = "{$location}/{$program}";
|
||||||
if (file_exists($path)) {
|
if (file_exists($path ?? '')) {
|
||||||
return $path;
|
return $path;
|
||||||
}
|
}
|
||||||
if (file_exists($path . '.exe')) {
|
if (file_exists($path . '.exe')) {
|
||||||
@ -86,7 +86,7 @@ class PDFTextExtractor extends FileTextExtractor
|
|||||||
|
|
||||||
public function getContent($file)
|
public function getContent($file)
|
||||||
{
|
{
|
||||||
if (!$file || (is_string($file) && !file_exists($file))) {
|
if (!$file || (is_string($file) && !file_exists($file ?? ''))) {
|
||||||
// no file
|
// no file
|
||||||
return '';
|
return '';
|
||||||
}
|
}
|
||||||
@ -108,7 +108,7 @@ class PDFTextExtractor extends FileTextExtractor
|
|||||||
}
|
}
|
||||||
|
|
||||||
$path = $file instanceof File ? $this->getPathFromFile($file) : $file;
|
$path = $file instanceof File ? $this->getPathFromFile($file) : $file;
|
||||||
exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path)), $content, $err);
|
exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path ?? '')), $content, $err);
|
||||||
|
|
||||||
if ($err) {
|
if ($err) {
|
||||||
throw new Exception(sprintf(
|
throw new Exception(sprintf(
|
||||||
@ -141,6 +141,6 @@ class PDFTextExtractor extends FileTextExtractor
|
|||||||
'st' => 'st'
|
'st' => 'st'
|
||||||
];
|
];
|
||||||
|
|
||||||
return str_replace(array_keys($mapping), array_values($mapping), $input);
|
return str_replace(array_keys($mapping ?? []), array_values($mapping ?? []), $input ?? '');
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -80,7 +80,7 @@ class SolrCellTextExtractor extends FileTextExtractor
|
|||||||
public function supportsExtension($extension)
|
public function supportsExtension($extension)
|
||||||
{
|
{
|
||||||
return in_array(
|
return in_array(
|
||||||
strtolower($extension),
|
strtolower($extension ?? ''),
|
||||||
[
|
[
|
||||||
'pdf', 'doc', 'docx', 'xls', 'xlsx',
|
'pdf', 'doc', 'docx', 'xls', 'xlsx',
|
||||||
'epub', 'rtf', 'odt', 'fodt', 'ods', 'fods',
|
'epub', 'rtf', 'odt', 'fodt', 'ods', 'fods',
|
||||||
@ -106,12 +106,12 @@ class SolrCellTextExtractor extends FileTextExtractor
|
|||||||
*/
|
*/
|
||||||
public function getContent($file)
|
public function getContent($file)
|
||||||
{
|
{
|
||||||
if (!$file || (is_string($file) && !file_exists($file))) {
|
if (!$file || (is_string($file) && !file_exists($file ?? ''))) {
|
||||||
// no file
|
// no file
|
||||||
return '';
|
return '';
|
||||||
}
|
}
|
||||||
|
|
||||||
$fileName = $file instanceof File ? $file->getFilename() : basename($file);
|
$fileName = $file instanceof File ? $file->getFilename() : basename($file ?? '');
|
||||||
$client = $this->getHttpClient();
|
$client = $this->getHttpClient();
|
||||||
|
|
||||||
// Get and validate base URL
|
// Get and validate base URL
|
||||||
@ -121,7 +121,7 @@ class SolrCellTextExtractor extends FileTextExtractor
|
|||||||
}
|
}
|
||||||
|
|
||||||
try {
|
try {
|
||||||
$stream = $file instanceof File ? $file->getStream() : fopen($file, 'r');
|
$stream = $file instanceof File ? $file->getStream() : fopen($file ?? '', 'r');
|
||||||
/** @var Response $response */
|
/** @var Response $response */
|
||||||
$response = $client
|
$response = $client
|
||||||
->post($baseUrl, [
|
->post($baseUrl, [
|
||||||
@ -154,7 +154,7 @@ class SolrCellTextExtractor extends FileTextExtractor
|
|||||||
$matches = [];
|
$matches = [];
|
||||||
// Use preg match to avoid SimpleXML running out of memory on large text nodes
|
// Use preg match to avoid SimpleXML running out of memory on large text nodes
|
||||||
preg_match(
|
preg_match(
|
||||||
sprintf('/\<str name\="%s"\>(.*?)\<\/str\>/s', preg_quote($fileName)),
|
sprintf('/\<str name\="%s"\>(.*?)\<\/str\>/s', preg_quote($fileName ?? '')),
|
||||||
(string)$response->getBody(),
|
(string)$response->getBody(),
|
||||||
$matches
|
$matches
|
||||||
);
|
);
|
||||||
|
@ -86,7 +86,7 @@ class TikaServerTextExtractor extends FileTextExtractor
|
|||||||
{
|
{
|
||||||
return $this->getServerEndpoint()
|
return $this->getServerEndpoint()
|
||||||
&& $this->getClient()->isAvailable()
|
&& $this->getClient()->isAvailable()
|
||||||
&& version_compare($this->getVersion(), '1.7') >= 0;
|
&& version_compare($this->getVersion() ?? '', '1.7') >= 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
@ -116,7 +116,7 @@ class TikaServerTextExtractor extends FileTextExtractor
|
|||||||
|
|
||||||
// Check aliases
|
// Check aliases
|
||||||
foreach ($this->supportedMimes as $info) {
|
foreach ($this->supportedMimes as $info) {
|
||||||
if (isset($info['alias']) && in_array($mime, $info['alias'])) {
|
if (isset($info['alias']) && in_array($mime, $info['alias'] ?? [])) {
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@ -130,7 +130,7 @@ class TikaServerTextExtractor extends FileTextExtractor
|
|||||||
$content = $this->getClient()->tika($tempFile);
|
$content = $this->getClient()->tika($tempFile);
|
||||||
//Cleanup temp file
|
//Cleanup temp file
|
||||||
if ($file instanceof File) {
|
if ($file instanceof File) {
|
||||||
unlink($tempFile);
|
unlink($tempFile ?? '');
|
||||||
}
|
}
|
||||||
return $content;
|
return $content;
|
||||||
}
|
}
|
||||||
|
@ -29,7 +29,7 @@ class TikaTextExtractor extends FileTextExtractor
|
|||||||
$code = $this->runShell('tika --version', $stdout);
|
$code = $this->runShell('tika --version', $stdout);
|
||||||
|
|
||||||
// Parse output
|
// Parse output
|
||||||
if (!$code && preg_match('/Apache Tika (?<version>[\.\d]+)/', $stdout, $matches)) {
|
if (!$code && preg_match('/Apache Tika (?<version>[\.\d]+)/', $stdout ?? '', $matches)) {
|
||||||
return $matches['version'];
|
return $matches['version'];
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -54,14 +54,14 @@ class TikaTextExtractor extends FileTextExtractor
|
|||||||
];
|
];
|
||||||
// Invoke command
|
// Invoke command
|
||||||
$pipes = [];
|
$pipes = [];
|
||||||
$proc = proc_open($command, $descriptorSpecs, $pipes);
|
$proc = proc_open($command ?? '', $descriptorSpecs ?? [], $pipes);
|
||||||
|
|
||||||
if (!is_resource($proc)) {
|
if (!is_resource($proc)) {
|
||||||
return 255;
|
return 255;
|
||||||
}
|
}
|
||||||
|
|
||||||
// Send content as input
|
// Send content as input
|
||||||
fwrite($pipes[0], $input);
|
fwrite($pipes[0], $input ?? '');
|
||||||
fclose($pipes[0]);
|
fclose($pipes[0]);
|
||||||
|
|
||||||
// Get output
|
// Get output
|
||||||
@ -78,11 +78,11 @@ class TikaTextExtractor extends FileTextExtractor
|
|||||||
{
|
{
|
||||||
$mode = $this->config()->get('output_mode');
|
$mode = $this->config()->get('output_mode');
|
||||||
$path = $file instanceof File ? $this->getPathFromFile($file) : $file;
|
$path = $file instanceof File ? $this->getPathFromFile($file) : $file;
|
||||||
$command = sprintf('tika %s %s', $mode, escapeshellarg($path));
|
$command = sprintf('tika %s %s', $mode, escapeshellarg($path ?? ''));
|
||||||
$code = $this->runShell($command, $output);
|
$code = $this->runShell($command, $output);
|
||||||
//Cleanup temp file
|
//Cleanup temp file
|
||||||
if ($file instanceof File) {
|
if ($file instanceof File) {
|
||||||
unlink($path);
|
unlink($path ?? '');
|
||||||
}
|
}
|
||||||
|
|
||||||
if ($code == 0) {
|
if ($code == 0) {
|
||||||
@ -123,8 +123,8 @@ class TikaTextExtractor extends FileTextExtractor
|
|||||||
}
|
}
|
||||||
|
|
||||||
// Check if the mime type is inside the result
|
// Check if the mime type is inside the result
|
||||||
$pattern = sprintf('/\b(%s)\b/', preg_quote($mime, '/'));
|
$pattern = sprintf('/\b(%s)\b/', preg_quote($mime ?? '', '/'));
|
||||||
|
|
||||||
return (bool)preg_match($pattern, $supportedTypes);
|
return (bool)preg_match($pattern ?? '', $supportedTypes ?? '');
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -80,7 +80,7 @@ class TikaRestClient extends Client
|
|||||||
|
|
||||||
// Parse output
|
// Parse output
|
||||||
if ($response->getStatusCode() == 200
|
if ($response->getStatusCode() == 200
|
||||||
&& preg_match('/Apache Tika (?<version>[\.\d]+)/', $response->getBody(), $matches)
|
&& preg_match('/Apache Tika (?<version>[\.\d]+)/', $response->getBody() ?? '', $matches)
|
||||||
) {
|
) {
|
||||||
$version = $matches['version'];
|
$version = $matches['version'];
|
||||||
}
|
}
|
||||||
@ -129,7 +129,7 @@ class TikaRestClient extends Client
|
|||||||
'headers' => [
|
'headers' => [
|
||||||
'Accept' => 'text/plain',
|
'Accept' => 'text/plain',
|
||||||
],
|
],
|
||||||
'body' => file_get_contents($file),
|
'body' => file_get_contents($file ?? ''),
|
||||||
])
|
])
|
||||||
);
|
);
|
||||||
$text = $response->getBody();
|
$text = $response->getBody();
|
||||||
|
Loading…
Reference in New Issue
Block a user