Page Menu
Home
Phorge
Search
Configure Global Search
Log In
Files
F2895039
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Award Token
Flag For Later
Advanced/Developer...
View Handle
View Hovercard
Size
54 KB
Referenced Files
None
Subscribers
None
View Options
diff --git a/src/applications/files/remarkup/PhabricatorRemarkupRuleEmbedFile.php b/src/applications/files/remarkup/PhabricatorRemarkupRuleEmbedFile.php
index 81a242c098..116d46111a 100644
--- a/src/applications/files/remarkup/PhabricatorRemarkupRuleEmbedFile.php
+++ b/src/applications/files/remarkup/PhabricatorRemarkupRuleEmbedFile.php
@@ -1,236 +1,188 @@
<?php
-/**
- * @group markup
- */
final class PhabricatorRemarkupRuleEmbedFile
- extends PhutilRemarkupRule {
+ extends PhabricatorRemarkupRuleObject {
- const KEY_RULE_EMBED_FILE = 'rule.embed.file';
const KEY_EMBED_FILE_PHIDS = 'phabricator.embedded-file-phids';
- public function apply($text) {
- return preg_replace_callback(
- "@{F(\d+)([^}]+?)?}@",
- array($this, 'markupEmbedFile'),
- $text);
+ protected function getObjectNamePrefix() {
+ return 'F';
}
- public function markupEmbedFile($matches) {
+ protected function loadObjects(array $ids) {
+ $engine = $this->getEngine();
- $file = null;
- if ($matches[1]) {
- // TODO: This is pretty inefficient if there are a bunch of files.
- // TODO: (T603) This isn't policy-aware and should be extending
- // PhabricatorRemarkupRuleObject.
- $file = id(new PhabricatorFile())->load($matches[1]);
- }
+ $viewer = $engine->getConfig('viewer');
+ $objects = id(new PhabricatorFileQuery())
+ ->setViewer($viewer)
+ ->withIDs($ids)
+ ->execute();
- if (!$file) {
- return $matches[0];
+ $phids_key = self::KEY_EMBED_FILE_PHIDS;
+ $phids = $engine->getTextMetadata($phids_key, array());
+ foreach (mpull($objects, 'getPHID') as $phid) {
+ $phids[] = $phid;
}
+ $engine->setTextMetadata($phids_key, $phids);
- $engine = $this->getEngine();
+ return $objects;
+ }
- if ($engine->isTextMode()) {
- return $engine->storeText($file->getBestURI());
- }
+ protected function renderObjectEmbed($object, $handle, $options) {
+ $options = $this->getFileOptions($options) + array(
+ 'name' => $object->getName(),
+ );
+
+ $is_viewable_image = $object->isViewableImage();
+ $is_audio = $object->isAudio();
+ $force_link = ($options['layout'] == 'link');
- $phid = $file->getPHID();
+ $options['viewable'] = ($is_viewable_image || $is_audio);
- $token = $engine->storeText('');
- $metadata_key = self::KEY_RULE_EMBED_FILE;
- $metadata = $engine->getTextMetadata($metadata_key, array());
- $bundle = array('token' => $token);
+ if ($is_viewable_image && !$force_link) {
+ return $this->renderImageFile($object, $handle, $options);
+ } else if ($is_audio && !$force_link) {
+ return $this->renderAudioFile($object, $handle, $options);
+ } else {
+ return $this->renderFileLink($object, $handle, $options);
+ }
+ }
+ private function getFileOptions($option_string) {
$options = array(
'size' => 'thumb',
'layout' => 'left',
'float' => false,
- 'name' => null,
);
- if (!empty($matches[2])) {
- $matches[2] = trim($matches[2], ', ');
+ if ($option_string) {
+ $option_string = trim($option_string, ', ');
$parser = new PhutilSimpleOptions();
- $options = $parser->parse($matches[2]) + $options;
+ $options = $parser->parse($option_string) + $options;
}
- $file_name = coalesce($options['name'], $file->getName());
- $options['name'] = $file_name;
- $is_viewable_image = $file->isViewableImage();
- $is_audio = $file->isAudio();
+ return $options;
+ }
+
+ private function renderImageFile(
+ PhabricatorFile $file,
+ PhabricatorObjectHandle $handle,
+ array $options) {
+
+ require_celerity_resource('lightbox-attachment-css');
$attrs = array();
- if ($is_viewable_image) {
- switch ((string)$options['size']) {
- case 'full':
- $attrs['src'] = $file->getBestURI();
- $options['image_class'] = null;
- $file_data = $file->getMetadata();
- $height = idx($file_data, PhabricatorFile::METADATA_IMAGE_HEIGHT);
- if ($height) {
- $attrs['height'] = $height;
- }
- $width = idx($file_data, PhabricatorFile::METADATA_IMAGE_WIDTH);
- if ($width) {
- $attrs['width'] = $width;
- }
+ $image_class = null;
+ switch ((string)$options['size']) {
+ case 'full':
+ $attrs += array(
+ 'src' => $file->getBestURI(),
+ 'width' => $file->getImageWidth(),
+ 'height' => $file->getImageHeight(),
+ );
+ break;
+ case 'thumb':
+ default:
+ $attrs['src'] = $file->getPreview220URI();
+ $dimensions =
+ PhabricatorImageTransformer::getPreviewDimensions($file, 220);
+ $attrs['width'] = $dimensions['sdx'];
+ $attrs['height'] = $dimensions['sdy'];
+ $image_class = 'phabricator-remarkup-embed-image';
+ break;
+ }
+
+ $img = phutil_tag('img', $attrs);
+
+ $embed = javelin_tag(
+ 'a',
+ array(
+ 'href' => $file->getBestURI(),
+ 'class' => $image_class,
+ 'sigil' => 'lightboxable',
+ 'meta' => array(
+ 'phid' => $file->getPHID(),
+ 'uri' => $file->getBestURI(),
+ 'viewable' => true,
+ ),
+ ),
+ $img);
+
+ switch ($options['layout']) {
+ case 'right':
+ case 'center':
+ case 'inline':
+ case 'left':
+ $layout_class = 'phabricator-remarkup-embed-layout-'.$options['layout'];
+ break;
+ default:
+ $layout_class = 'phabricator-remarkup-embed-layout-left';
+ break;
+ }
+
+ if ($options['float']) {
+ switch ($options['layout']) {
+ case 'center':
+ case 'inline':
break;
- case 'thumb':
+ case 'right':
+ $layout_class .= ' phabricator-remarkup-embed-float-right';
+ break;
+ case 'left':
default:
- $attrs['src'] = $file->getPreview220URI();
- $dimensions =
- PhabricatorImageTransformer::getPreviewDimensions($file, 220);
- $attrs['width'] = $dimensions['sdx'];
- $attrs['height'] = $dimensions['sdy'];
- $options['image_class'] = 'phabricator-remarkup-embed-image';
+ $layout_class .= ' phabricator-remarkup-embed-float-left';
break;
}
}
- $bundle['attrs'] = $attrs;
- $bundle['options'] = $options;
-
- $bundle['meta'] = array(
- 'phid' => $file->getPHID(),
- 'viewable' => $is_viewable_image,
- 'audio' => $is_audio,
- 'uri' => $file->getBestURI(),
- 'dUri' => $file->getDownloadURI(),
- 'name' => $options['name'],
- 'mime' => $file->getMimeType(),
- );
-
- if ($is_audio) {
- $bundle['meta'] += array(
- 'autoplay' => idx($options, 'autoplay'),
- 'loop' => idx($options, 'loop'),
- );
- }
-
- $metadata[$phid][] = $bundle;
- $engine->setTextMetadata($metadata_key, $metadata);
- return $token;
+ return phutil_tag(
+ 'div',
+ array(
+ 'class' => $layout_class,
+ ),
+ $embed);
}
- public function didMarkupText() {
- $engine = $this->getEngine();
-
- $metadata_key = self::KEY_RULE_EMBED_FILE;
- $metadata = $engine->getTextMetadata($metadata_key, array());
-
- if (!$metadata) {
- return;
+ private function renderAudioFile(
+ PhabricatorFile $file,
+ PhabricatorObjectHandle $handle,
+ array $options) {
+
+ if (idx($options, 'autoplay')) {
+ $preload = 'auto';
+ $autoplay = 'autoplay';
+ } else {
+ $preload = 'none';
+ $autoplay = null;
}
- $file_phids = array();
- foreach ($metadata as $phid => $bundles) {
- foreach ($bundles as $data) {
-
- $options = $data['options'];
- $meta = $data['meta'];
-
- $is_image = idx($meta, 'viewable');
- $is_audio = idx($meta, 'audio');
-
- if ((!$is_image && !$is_audio) || $options['layout'] == 'link') {
- $link = id(new PhabricatorFileLinkView())
- ->setFilePHID($meta['phid'])
- ->setFileName($meta['name'])
- ->setFileDownloadURI($meta['dUri'])
- ->setFileViewURI($meta['uri'])
- ->setFileViewable($meta['viewable']);
- $embed = $link->render();
- $engine->overwriteStoredText($data['token'], $embed);
- continue;
- }
-
- if ($is_audio) {
- if (idx($options, 'autoplay')) {
- $preload = 'auto';
- $autoplay = 'autoplay';
- } else {
- $preload = 'none';
- $autoplay = null;
- }
-
- $link = phutil_tag(
- 'audio',
- array(
- 'controls' => 'controls',
- 'preload' => $preload,
- 'autoplay' => $autoplay,
- 'loop' => idx($options, 'loop') ? 'loop' : null,
- ),
- phutil_tag(
- 'source',
- array(
- 'src' => $meta['uri'],
- 'type' => $meta['mime'],
- )));
- $engine->overwriteStoredText($data['token'], $link);
- continue;
- }
-
- require_celerity_resource('lightbox-attachment-css');
- $img = phutil_tag('img', $data['attrs']);
-
- $embed = javelin_tag(
- 'a',
- array(
- 'href' => $meta['uri'],
- 'class' => $options['image_class'],
- 'sigil' => 'lightboxable',
- 'mustcapture' => true,
- 'meta' => $meta,
- ),
- $img);
-
- $layout_class = null;
- switch ($options['layout']) {
- case 'right':
- case 'center':
- case 'inline':
- case 'left':
- $layout_class = 'phabricator-remarkup-embed-layout-'.
- $options['layout'];
- break;
- default:
- $layout_class = 'phabricator-remarkup-embed-layout-left';
- break;
- }
-
- if ($options['float']) {
- switch ($options['layout']) {
- case 'center':
- case 'inline':
- break;
- case 'right':
- $layout_class .= ' phabricator-remarkup-embed-float-right';
- break;
- case 'left':
- default:
- $layout_class .= ' phabricator-remarkup-embed-float-left';
- break;
- }
- }
-
- if ($layout_class) {
- $embed = phutil_tag(
- 'div',
- array(
- 'class' => $layout_class,
- ),
- $embed);
- }
-
- $engine->overwriteStoredText($data['token'], $embed);
- }
- $file_phids[] = $phid;
- }
- $engine->setTextMetadata(self::KEY_EMBED_FILE_PHIDS, $file_phids);
- $engine->setTextMetadata($metadata_key, array());
+ return phutil_tag(
+ 'audio',
+ array(
+ 'controls' => 'controls',
+ 'preload' => $preload,
+ 'autoplay' => $autoplay,
+ 'loop' => idx($options, 'loop') ? 'loop' : null,
+ ),
+ phutil_tag(
+ 'source',
+ array(
+ 'src' => $file->getBestURI(),
+ 'type' => $file->getMimeType(),
+ )));
+ }
+
+ private function renderFileLink(
+ PhabricatorFile $file,
+ PhabricatorObjectHandle $handle,
+ array $options) {
+
+ return id(new PhabricatorFileLinkView())
+ ->setFilePHID($file->getPHID())
+ ->setFileName($options['name'])
+ ->setFileDownloadURI($file->getDownloadURI())
+ ->setFileViewURI($file->getBestURI())
+ ->setFileViewable($options['viewable']);
}
}
diff --git a/src/applications/files/storage/PhabricatorFile.php b/src/applications/files/storage/PhabricatorFile.php
index c25bbdc835..fd50087c95 100644
--- a/src/applications/files/storage/PhabricatorFile.php
+++ b/src/applications/files/storage/PhabricatorFile.php
@@ -1,916 +1,930 @@
<?php
/**
* @group file
*/
final class PhabricatorFile extends PhabricatorFileDAO
implements
PhabricatorTokenReceiverInterface,
PhabricatorSubscribableInterface,
PhabricatorPolicyInterface {
const STORAGE_FORMAT_RAW = 'raw';
const METADATA_IMAGE_WIDTH = 'width';
const METADATA_IMAGE_HEIGHT = 'height';
protected $phid;
protected $name;
protected $mimeType;
protected $byteSize;
protected $authorPHID;
protected $secretKey;
protected $contentHash;
protected $metadata = array();
protected $mailKey;
protected $storageEngine;
protected $storageFormat;
protected $storageHandle;
protected $ttl;
protected $isExplicitUpload = 1;
protected $viewPolicy = PhabricatorPolicies::POLICY_USER;
private $objects = self::ATTACHABLE;
private $objectPHIDs = self::ATTACHABLE;
public function getConfiguration() {
return array(
self::CONFIG_AUX_PHID => true,
self::CONFIG_SERIALIZATION => array(
'metadata' => self::SERIALIZATION_JSON,
),
) + parent::getConfiguration();
}
public function generatePHID() {
return PhabricatorPHID::generateNewPHID(
PhabricatorFilePHIDTypeFile::TYPECONST);
}
public function save() {
if (!$this->getSecretKey()) {
$this->setSecretKey($this->generateSecretKey());
}
if (!$this->getMailKey()) {
$this->setMailKey(Filesystem::readRandomCharacters(20));
}
return parent::save();
}
public static function readUploadedFileData($spec) {
if (!$spec) {
throw new Exception("No file was uploaded!");
}
$err = idx($spec, 'error');
if ($err) {
throw new PhabricatorFileUploadException($err);
}
$tmp_name = idx($spec, 'tmp_name');
$is_valid = @is_uploaded_file($tmp_name);
if (!$is_valid) {
throw new Exception("File is not an uploaded file.");
}
$file_data = Filesystem::readFile($tmp_name);
$file_size = idx($spec, 'size');
if (strlen($file_data) != $file_size) {
throw new Exception("File size disagrees with uploaded size.");
}
self::validateFileSize(strlen($file_data));
return $file_data;
}
public static function newFromPHPUpload($spec, array $params = array()) {
$file_data = self::readUploadedFileData($spec);
$file_name = nonempty(
idx($params, 'name'),
idx($spec, 'name'));
$params = array(
'name' => $file_name,
) + $params;
return self::newFromFileData($file_data, $params);
}
public static function newFromXHRUpload($data, array $params = array()) {
self::validateFileSize(strlen($data));
return self::newFromFileData($data, $params);
}
private static function validateFileSize($size) {
$limit = PhabricatorEnv::getEnvConfig('storage.upload-size-limit');
if (!$limit) {
return;
}
$limit = phabricator_parse_bytes($limit);
if ($size > $limit) {
throw new PhabricatorFileUploadException(-1000);
}
}
/**
* Given a block of data, try to load an existing file with the same content
* if one exists. If it does not, build a new file.
*
* This method is generally used when we have some piece of semi-trusted data
* like a diff or a file from a repository that we want to show to the user.
* We can't just dump it out because it may be dangerous for any number of
* reasons; instead, we need to serve it through the File abstraction so it
* ends up on the CDN domain if one is configured and so on. However, if we
* simply wrote a new file every time we'd potentially end up with a lot
* of redundant data in file storage.
*
* To solve these problems, we use file storage as a cache and reuse the
* same file again if we've previously written it.
*
* NOTE: This method unguards writes.
*
* @param string Raw file data.
* @param dict Dictionary of file information.
*/
public static function buildFromFileDataOrHash(
$data,
array $params = array()) {
$file = id(new PhabricatorFile())->loadOneWhere(
'name = %s AND contentHash = %s LIMIT 1',
self::normalizeFileName(idx($params, 'name')),
self::hashFileContent($data));
if (!$file) {
$unguarded = AphrontWriteGuard::beginScopedUnguardedWrites();
$file = PhabricatorFile::newFromFileData($data, $params);
unset($unguarded);
}
return $file;
}
public static function newFileFromContentHash($hash, $params) {
// Check to see if a file with same contentHash exist
$file = id(new PhabricatorFile())->loadOneWhere(
'contentHash = %s LIMIT 1', $hash);
if ($file) {
// copy storageEngine, storageHandle, storageFormat
$copy_of_storage_engine = $file->getStorageEngine();
$copy_of_storage_handle = $file->getStorageHandle();
$copy_of_storage_format = $file->getStorageFormat();
$copy_of_byteSize = $file->getByteSize();
$copy_of_mimeType = $file->getMimeType();
$file_name = idx($params, 'name');
$file_name = self::normalizeFileName($file_name);
$file_ttl = idx($params, 'ttl');
$authorPHID = idx($params, 'authorPHID');
$new_file = new PhabricatorFile();
$new_file->setName($file_name);
$new_file->setByteSize($copy_of_byteSize);
$new_file->setAuthorPHID($authorPHID);
$new_file->setTtl($file_ttl);
$new_file->setContentHash($hash);
$new_file->setStorageEngine($copy_of_storage_engine);
$new_file->setStorageHandle($copy_of_storage_handle);
$new_file->setStorageFormat($copy_of_storage_format);
$new_file->setMimeType($copy_of_mimeType);
$new_file->copyDimensions($file);
$new_file->save();
return $new_file;
}
return $file;
}
private static function buildFromFileData($data, array $params = array()) {
$selector = PhabricatorEnv::newObjectFromConfig('storage.engine-selector');
if (isset($params['storageEngines'])) {
$engines = $params['storageEngines'];
} else {
$selector = PhabricatorEnv::newObjectFromConfig(
'storage.engine-selector');
$engines = $selector->selectStorageEngines($data, $params);
}
assert_instances_of($engines, 'PhabricatorFileStorageEngine');
if (!$engines) {
throw new Exception("No valid storage engines are available!");
}
$file = new PhabricatorFile();
$data_handle = null;
$engine_identifier = null;
$exceptions = array();
foreach ($engines as $engine) {
$engine_class = get_class($engine);
try {
list($engine_identifier, $data_handle) = $file->writeToEngine(
$engine,
$data,
$params);
// We stored the file somewhere so stop trying to write it to other
// places.
break;
} catch (PhabricatorFileStorageConfigurationException $ex) {
// If an engine is outright misconfigured (or misimplemented), raise
// that immediately since it probably needs attention.
throw $ex;
} catch (Exception $ex) {
phlog($ex);
// If an engine doesn't work, keep trying all the other valid engines
// in case something else works.
$exceptions[$engine_class] = $ex;
}
}
if (!$data_handle) {
throw new PhutilAggregateException(
"All storage engines failed to write file:",
$exceptions);
}
$file_name = idx($params, 'name');
$file_name = self::normalizeFileName($file_name);
$file_ttl = idx($params, 'ttl');
// If for whatever reason, authorPHID isn't passed as a param
// (always the case with newFromFileDownload()), store a ''
$authorPHID = idx($params, 'authorPHID');
$file->setName($file_name);
$file->setByteSize(strlen($data));
$file->setAuthorPHID($authorPHID);
$file->setTtl($file_ttl);
$file->setContentHash(self::hashFileContent($data));
$file->setStorageEngine($engine_identifier);
$file->setStorageHandle($data_handle);
// TODO: This is probably YAGNI, but allows for us to do encryption or
// compression later if we want.
$file->setStorageFormat(self::STORAGE_FORMAT_RAW);
$file->setIsExplicitUpload(idx($params, 'isExplicitUpload') ? 1 : 0);
if (isset($params['mime-type'])) {
$file->setMimeType($params['mime-type']);
} else {
$tmp = new TempFile();
Filesystem::writeFile($tmp, $data);
$file->setMimeType(Filesystem::getMimeType($tmp));
}
try {
$file->updateDimensions(false);
} catch (Exception $ex) {
// Do nothing
}
$file->save();
return $file;
}
public static function newFromFileData($data, array $params = array()) {
$hash = self::hashFileContent($data);
$file = self::newFileFromContentHash($hash, $params);
if ($file) {
return $file;
}
return self::buildFromFileData($data, $params);
}
public function migrateToEngine(PhabricatorFileStorageEngine $engine) {
if (!$this->getID() || !$this->getStorageHandle()) {
throw new Exception(
"You can not migrate a file which hasn't yet been saved.");
}
$data = $this->loadFileData();
$params = array(
'name' => $this->getName(),
);
list($new_identifier, $new_handle) = $this->writeToEngine(
$engine,
$data,
$params);
$old_engine = $this->instantiateStorageEngine();
$old_handle = $this->getStorageHandle();
$this->setStorageEngine($new_identifier);
$this->setStorageHandle($new_handle);
$this->save();
$old_engine->deleteFile($old_handle);
return $this;
}
private function writeToEngine(
PhabricatorFileStorageEngine $engine,
$data,
array $params) {
$engine_class = get_class($engine);
$data_handle = $engine->writeFile($data, $params);
if (!$data_handle || strlen($data_handle) > 255) {
// This indicates an improperly implemented storage engine.
throw new PhabricatorFileStorageConfigurationException(
"Storage engine '{$engine_class}' executed writeFile() but did ".
"not return a valid handle ('{$data_handle}') to the data: it ".
"must be nonempty and no longer than 255 characters.");
}
$engine_identifier = $engine->getEngineIdentifier();
if (!$engine_identifier || strlen($engine_identifier) > 32) {
throw new PhabricatorFileStorageConfigurationException(
"Storage engine '{$engine_class}' returned an improper engine ".
"identifier '{$engine_identifier}': it must be nonempty ".
"and no longer than 32 characters.");
}
return array($engine_identifier, $data_handle);
}
public static function newFromFileDownload($uri, array $params = array()) {
// Make sure we're allowed to make a request first
if (!PhabricatorEnv::getEnvConfig('security.allow-outbound-http')) {
throw new Exception("Outbound HTTP requests are disabled!");
}
$uri = new PhutilURI($uri);
$protocol = $uri->getProtocol();
switch ($protocol) {
case 'http':
case 'https':
break;
default:
// Make sure we are not accessing any file:// URIs or similar.
return null;
}
$timeout = 5;
list($file_data) = id(new HTTPSFuture($uri))
->setTimeout($timeout)
->resolvex();
$params = $params + array(
'name' => basename($uri),
);
return self::newFromFileData($file_data, $params);
}
public static function normalizeFileName($file_name) {
$pattern = "@[\\x00-\\x19#%&+!~'\$\"\/=\\\\?<> ]+@";
$file_name = preg_replace($pattern, '_', $file_name);
$file_name = preg_replace('@_+@', '_', $file_name);
$file_name = trim($file_name, '_');
$disallowed_filenames = array(
'.' => 'dot',
'..' => 'dotdot',
'' => 'file',
);
$file_name = idx($disallowed_filenames, $file_name, $file_name);
return $file_name;
}
public function delete() {
// We want to delete all the rows which mark this file as the transformation
// of some other file (since we're getting rid of it). We also delete all
// the transformations of this file, so that a user who deletes an image
// doesn't need to separately hunt down and delete a bunch of thumbnails and
// resizes of it.
$outbound_xforms = id(new PhabricatorFileQuery())
->setViewer(PhabricatorUser::getOmnipotentUser())
->withTransforms(
array(
array(
'originalPHID' => $this->getPHID(),
'transform' => true,
),
))
->execute();
foreach ($outbound_xforms as $outbound_xform) {
$outbound_xform->delete();
}
$inbound_xforms = id(new PhabricatorTransformedFile())->loadAllWhere(
'transformedPHID = %s',
$this->getPHID());
$this->openTransaction();
foreach ($inbound_xforms as $inbound_xform) {
$inbound_xform->delete();
}
$ret = parent::delete();
$this->saveTransaction();
// Check to see if other files are using storage
$other_file = id(new PhabricatorFile())->loadAllWhere(
'storageEngine = %s AND storageHandle = %s AND
storageFormat = %s AND id != %d LIMIT 1',
$this->getStorageEngine(),
$this->getStorageHandle(),
$this->getStorageFormat(),
$this->getID());
// If this is the only file using the storage, delete storage
if (!$other_file) {
$engine = $this->instantiateStorageEngine();
try {
$engine->deleteFile($this->getStorageHandle());
} catch (Exception $ex) {
// In the worst case, we're leaving some data stranded in a storage
// engine, which is fine.
phlog($ex);
}
}
return $ret;
}
public static function hashFileContent($data) {
return sha1($data);
}
public function loadFileData() {
$engine = $this->instantiateStorageEngine();
$data = $engine->readFile($this->getStorageHandle());
switch ($this->getStorageFormat()) {
case self::STORAGE_FORMAT_RAW:
$data = $data;
break;
default:
throw new Exception("Unknown storage format.");
}
return $data;
}
public function getViewURI() {
if (!$this->getPHID()) {
throw new Exception(
"You must save a file before you can generate a view URI.");
}
$name = phutil_escape_uri($this->getName());
$path = '/file/data/'.$this->getSecretKey().'/'.$this->getPHID().'/'.$name;
return PhabricatorEnv::getCDNURI($path);
}
public function getInfoURI() {
return '/file/info/'.$this->getPHID().'/';
}
public function getBestURI() {
if ($this->isViewableInBrowser()) {
return $this->getViewURI();
} else {
return $this->getInfoURI();
}
}
public function getDownloadURI() {
$uri = id(new PhutilURI($this->getViewURI()))
->setQueryParam('download', true);
return (string) $uri;
}
public function getProfileThumbURI() {
$path = '/file/xform/thumb-profile/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getThumb60x45URI() {
$path = '/file/xform/thumb-60x45/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getThumb160x120URI() {
$path = '/file/xform/thumb-160x120/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getPreview140URI() {
$path = '/file/xform/preview-140/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getPreview220URI() {
$path = '/file/xform/preview-220/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getThumb220x165URI() {
$path = '/file/xform/thumb-220x165/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function getThumb280x210URI() {
$path = '/file/xform/thumb-280x210/'.$this->getPHID().'/'
.$this->getSecretKey().'/';
return PhabricatorEnv::getCDNURI($path);
}
public function isViewableInBrowser() {
return ($this->getViewableMimeType() !== null);
}
public function isViewableImage() {
if (!$this->isViewableInBrowser()) {
return false;
}
$mime_map = PhabricatorEnv::getEnvConfig('files.image-mime-types');
$mime_type = $this->getMimeType();
return idx($mime_map, $mime_type);
}
public function isAudio() {
if (!$this->isViewableInBrowser()) {
return false;
}
$mime_map = PhabricatorEnv::getEnvConfig('files.audio-mime-types');
$mime_type = $this->getMimeType();
return idx($mime_map, $mime_type);
}
public function isTransformableImage() {
// NOTE: The way the 'gd' extension works in PHP is that you can install it
// with support for only some file types, so it might be able to handle
// PNG but not JPEG. Try to generate thumbnails for whatever we can. Setup
// warns you if you don't have complete support.
$matches = null;
$ok = preg_match(
'@^image/(gif|png|jpe?g)@',
$this->getViewableMimeType(),
$matches);
if (!$ok) {
return false;
}
switch ($matches[1]) {
case 'jpg';
case 'jpeg':
return function_exists('imagejpeg');
break;
case 'png':
return function_exists('imagepng');
break;
case 'gif':
return function_exists('imagegif');
break;
default:
throw new Exception('Unknown type matched as image MIME type.');
}
}
public static function getTransformableImageFormats() {
$supported = array();
if (function_exists('imagejpeg')) {
$supported[] = 'jpg';
}
if (function_exists('imagepng')) {
$supported[] = 'png';
}
if (function_exists('imagegif')) {
$supported[] = 'gif';
}
return $supported;
}
protected function instantiateStorageEngine() {
return self::buildEngine($this->getStorageEngine());
}
public static function buildEngine($engine_identifier) {
$engines = self::buildAllEngines();
foreach ($engines as $engine) {
if ($engine->getEngineIdentifier() == $engine_identifier) {
return $engine;
}
}
throw new Exception(
"Storage engine '{$engine_identifier}' could not be located!");
}
public static function buildAllEngines() {
$engines = id(new PhutilSymbolLoader())
->setType('class')
->setConcreteOnly(true)
->setAncestorClass('PhabricatorFileStorageEngine')
->selectAndLoadSymbols();
$results = array();
foreach ($engines as $engine_class) {
$results[] = newv($engine_class['name'], array());
}
return $results;
}
public function getViewableMimeType() {
$mime_map = PhabricatorEnv::getEnvConfig('files.viewable-mime-types');
$mime_type = $this->getMimeType();
$mime_parts = explode(';', $mime_type);
$mime_type = trim(reset($mime_parts));
return idx($mime_map, $mime_type);
}
public function getDisplayIconForMimeType() {
$mime_map = PhabricatorEnv::getEnvConfig('files.icon-mime-types');
$mime_type = $this->getMimeType();
return idx($mime_map, $mime_type, 'docs_file');
}
public function validateSecretKey($key) {
return ($key == $this->getSecretKey());
}
public function generateSecretKey() {
return Filesystem::readRandomCharacters(20);
}
public function updateDimensions($save = true) {
if (!$this->isViewableImage()) {
throw new Exception(
"This file is not a viewable image.");
}
if (!function_exists("imagecreatefromstring")) {
throw new Exception(
"Cannot retrieve image information.");
}
$data = $this->loadFileData();
$img = imagecreatefromstring($data);
if ($img === false) {
throw new Exception(
"Error when decoding image.");
}
$this->metadata[self::METADATA_IMAGE_WIDTH] = imagesx($img);
$this->metadata[self::METADATA_IMAGE_HEIGHT] = imagesy($img);
if ($save) {
$this->save();
}
return $this;
}
public function copyDimensions(PhabricatorFile $file) {
$metadata = $file->getMetadata();
$width = idx($metadata, self::METADATA_IMAGE_WIDTH);
if ($width) {
$this->metadata[self::METADATA_IMAGE_WIDTH] = $width;
}
$height = idx($metadata, self::METADATA_IMAGE_HEIGHT);
if ($height) {
$this->metadata[self::METADATA_IMAGE_HEIGHT] = $height;
}
return $this;
}
public static function getMetadataName($metadata) {
switch ($metadata) {
case self::METADATA_IMAGE_WIDTH:
$name = pht('Width');
break;
case self::METADATA_IMAGE_HEIGHT:
$name = pht('Height');
break;
default:
$name = ucfirst($metadata);
break;
}
return $name;
}
/**
* Load (or build) the {@class:PhabricatorFile} objects for builtin file
* resources. The builtin mechanism allows files shipped with Phabricator
* to be treated like normal files so that APIs do not need to special case
* things like default images or deleted files.
*
* Builtins are located in `resources/builtin/` and identified by their
* name.
*
* @param PhabricatorUser Viewing user.
* @param list<string> List of builtin file names.
* @return dict<string, PhabricatorFile> Dictionary of named builtins.
*/
public static function loadBuiltins(PhabricatorUser $user, array $names) {
$specs = array();
foreach ($names as $name) {
$specs[] = array(
'originalPHID' => PhabricatorPHIDConstants::PHID_VOID,
'transform' => 'builtin:'.$name,
);
}
$files = id(new PhabricatorFileQuery())
->setViewer($user)
->withTransforms($specs)
->execute();
$files = mpull($files, null, 'getName');
$root = dirname(phutil_get_library_root('phabricator'));
$root = $root.'/resources/builtin/';
$build = array();
foreach ($names as $name) {
if (isset($files[$name])) {
continue;
}
// This is just a sanity check to prevent loading arbitrary files.
if (basename($name) != $name) {
throw new Exception("Invalid builtin name '{$name}'!");
}
$path = $root.$name;
if (!Filesystem::pathExists($path)) {
throw new Exception("Builtin '{$path}' does not exist!");
}
$data = Filesystem::readFile($path);
$params = array(
'name' => $name,
'ttl' => time() + (60 * 60 * 24 * 7),
);
$unguarded = AphrontWriteGuard::beginScopedUnguardedWrites();
$file = PhabricatorFile::newFromFileData($data, $params);
$xform = id(new PhabricatorTransformedFile())
->setOriginalPHID(PhabricatorPHIDConstants::PHID_VOID)
->setTransform('builtin:'.$name)
->setTransformedPHID($file->getPHID())
->save();
unset($unguarded);
$file->attachObjectPHIDs(array());
$file->attachObjects(array());
$files[$name] = $file;
}
return $files;
}
/**
* Convenience wrapper for @{method:loadBuiltins}.
*
* @param PhabricatorUser Viewing user.
* @param string Single builtin name to load.
* @return PhabricatorFile Corresponding builtin file.
*/
public static function loadBuiltin(PhabricatorUser $user, $name) {
return idx(self::loadBuiltins($user, array($name)), $name);
}
public function getObjects() {
return $this->assertAttached($this->objects);
}
public function attachObjects(array $objects) {
$this->objects = $objects;
return $this;
}
public function getObjectPHIDs() {
return $this->assertAttached($this->objectPHIDs);
}
public function attachObjectPHIDs(array $object_phids) {
$this->objectPHIDs = $object_phids;
return $this;
}
+ public function getImageHeight() {
+ if (!$this->isViewableImage()) {
+ return null;
+ }
+ return idx($this->metadata, self::METADATA_IMAGE_HEIGHT);
+ }
+
+ public function getImageWidth() {
+ if (!$this->isViewableImage()) {
+ return null;
+ }
+ return idx($this->metadata, self::METADATA_IMAGE_WIDTH);
+ }
+
/* -( PhabricatorPolicyInterface Implementation )-------------------------- */
public function getCapabilities() {
return array(
PhabricatorPolicyCapability::CAN_VIEW,
PhabricatorPolicyCapability::CAN_EDIT,
);
}
public function getPolicy($capability) {
// TODO: Implement proper per-object policies.
return PhabricatorPolicies::POLICY_USER;
}
public function hasAutomaticCapability($capability, PhabricatorUser $viewer) {
$viewer_phid = $viewer->getPHID();
if ($viewer_phid) {
if ($this->getAuthorPHID() == $viewer_phid) {
return true;
}
}
switch ($capability) {
case PhabricatorPolicyCapability::CAN_VIEW:
// If you can see any object this file is attached to, you can see
// the file.
return (count($this->getObjects()) > 0);
}
return false;
}
public function describeAutomaticCapability($capability) {
$out = array();
$out[] = pht('The user who uploaded a file can always view and edit it.');
switch ($capability) {
case PhabricatorPolicyCapability::CAN_VIEW:
$out[] = pht(
'Files attached to objects are visible to users who can view '.
'those objects.');
break;
}
return $out;
}
/* -( PhabricatorSubscribableInterface Implementation )-------------------- */
public function isAutomaticallySubscribed($phid) {
return ($this->authorPHID == $phid);
}
/* -( PhabricatorTokenReceiverInterface )---------------------------------- */
public function getUsersToNotifyOfTokenGiven() {
return array(
$this->getAuthorPHID(),
);
}
}
diff --git a/src/infrastructure/markup/PhabricatorMarkupEngine.php b/src/infrastructure/markup/PhabricatorMarkupEngine.php
index 1f1fb88f95..f909c81c07 100644
--- a/src/infrastructure/markup/PhabricatorMarkupEngine.php
+++ b/src/infrastructure/markup/PhabricatorMarkupEngine.php
@@ -1,566 +1,566 @@
<?php
/**
* Manages markup engine selection, configuration, application, caching and
* pipelining.
*
* @{class:PhabricatorMarkupEngine} can be used to render objects which
* implement @{interface:PhabricatorMarkupInterface} in a batched, cache-aware
* way. For example, if you have a list of comments written in remarkup (and
* the objects implement the correct interface) you can render them by first
* building an engine and adding the fields with @{method:addObject}.
*
* $field = 'field:body'; // Field you want to render. Each object exposes
* // one or more fields of markup.
*
* $engine = new PhabricatorMarkupEngine();
* foreach ($comments as $comment) {
* $engine->addObject($comment, $field);
* }
*
* Now, call @{method:process} to perform the actual cache/rendering
* step. This is a heavyweight call which does batched data access and
* transforms the markup into output.
*
* $engine->process();
*
* Finally, do something with the results:
*
* $results = array();
* foreach ($comments as $comment) {
* $results[] = $engine->getOutput($comment, $field);
* }
*
* If you have a single object to render, you can use the convenience method
* @{method:renderOneObject}.
*
* @task markup Markup Pipeline
* @task engine Engine Construction
*/
final class PhabricatorMarkupEngine {
private $objects = array();
private $viewer;
- private $version = 7;
+ private $version = 8;
/* -( Markup Pipeline )---------------------------------------------------- */
/**
* Convenience method for pushing a single object through the markup
* pipeline.
*
* @param PhabricatorMarkupInterface The object to render.
* @param string The field to render.
* @param PhabricatorUser User viewing the markup.
* @return string Marked up output.
* @task markup
*/
public static function renderOneObject(
PhabricatorMarkupInterface $object,
$field,
PhabricatorUser $viewer) {
return id(new PhabricatorMarkupEngine())
->setViewer($viewer)
->addObject($object, $field)
->process()
->getOutput($object, $field);
}
/**
* Queue an object for markup generation when @{method:process} is
* called. You can retrieve the output later with @{method:getOutput}.
*
* @param PhabricatorMarkupInterface The object to render.
* @param string The field to render.
* @return this
* @task markup
*/
public function addObject(PhabricatorMarkupInterface $object, $field) {
$key = $this->getMarkupFieldKey($object, $field);
$this->objects[$key] = array(
'object' => $object,
'field' => $field,
);
return $this;
}
/**
* Process objects queued with @{method:addObject}. You can then retrieve
* the output with @{method:getOutput}.
*
* @return this
* @task markup
*/
public function process() {
$keys = array();
foreach ($this->objects as $key => $info) {
if (!isset($info['markup'])) {
$keys[] = $key;
}
}
if (!$keys) {
return;
}
$objects = array_select_keys($this->objects, $keys);
// Build all the markup engines. We need an engine for each field whether
// we have a cache or not, since we still need to postprocess the cache.
$engines = array();
foreach ($objects as $key => $info) {
$engines[$key] = $info['object']->newMarkupEngine($info['field']);
$engines[$key]->setConfig('viewer', $this->viewer);
}
// Load or build the preprocessor caches.
$blocks = $this->loadPreprocessorCaches($engines, $objects);
$blocks = mpull($blocks, 'getCacheData');
$this->engineCaches = $blocks;
// Finalize the output.
foreach ($objects as $key => $info) {
$engine = $engines[$key];
$field = $info['field'];
$object = $info['object'];
$output = $engine->postprocessText($blocks[$key]);
$output = $object->didMarkupText($field, $output, $engine);
$this->objects[$key]['output'] = $output;
}
return $this;
}
/**
* Get the output of markup processing for a field queued with
* @{method:addObject}. Before you can call this method, you must call
* @{method:process}.
*
* @param PhabricatorMarkupInterface The object to retrieve.
* @param string The field to retrieve.
* @return string Processed output.
* @task markup
*/
public function getOutput(PhabricatorMarkupInterface $object, $field) {
$key = $this->getMarkupFieldKey($object, $field);
$this->requireKeyProcessed($key);
return $this->objects[$key]['output'];
}
/**
* Retrieve engine metadata for a given field.
*
* @param PhabricatorMarkupInterface The object to retrieve.
* @param string The field to retrieve.
* @param string The engine metadata field to retrieve.
* @param wild Optional default value.
* @task markup
*/
public function getEngineMetadata(
PhabricatorMarkupInterface $object,
$field,
$metadata_key,
$default = null) {
$key = $this->getMarkupFieldKey($object, $field);
$this->requireKeyProcessed($key);
return idx($this->engineCaches[$key]['metadata'], $metadata_key, $default);
}
/**
* @task markup
*/
private function requireKeyProcessed($key) {
if (empty($this->objects[$key])) {
throw new Exception(
"Call addObject() before using results (key = '{$key}').");
}
if (!isset($this->objects[$key]['output'])) {
throw new Exception(
"Call process() before using results.");
}
}
/**
* @task markup
*/
private function getMarkupFieldKey(
PhabricatorMarkupInterface $object,
$field) {
return $object->getMarkupFieldKey($field).'@'.$this->version;
}
/**
* @task markup
*/
private function loadPreprocessorCaches(array $engines, array $objects) {
$blocks = array();
$use_cache = array();
foreach ($objects as $key => $info) {
if ($info['object']->shouldUseMarkupCache($info['field'])) {
$use_cache[$key] = true;
}
}
if ($use_cache) {
try {
$blocks = id(new PhabricatorMarkupCache())->loadAllWhere(
'cacheKey IN (%Ls)',
array_keys($use_cache));
$blocks = mpull($blocks, null, 'getCacheKey');
} catch (Exception $ex) {
phlog($ex);
}
}
foreach ($objects as $key => $info) {
if (isset($blocks[$key])) {
// If we already have a preprocessing cache, we don't need to rebuild
// it.
continue;
}
$text = $info['object']->getMarkupText($info['field']);
$data = $engines[$key]->preprocessText($text);
// NOTE: This is just debugging information to help sort out cache issues.
// If one machine is misconfigured and poisoning caches you can use this
// field to hunt it down.
$metadata = array(
'host' => php_uname('n'),
);
$blocks[$key] = id(new PhabricatorMarkupCache())
->setCacheKey($key)
->setCacheData($data)
->setMetadata($metadata);
if (isset($use_cache[$key])) {
// This is just filling a cache and always safe, even on a read pathway.
$unguarded = AphrontWriteGuard::beginScopedUnguardedWrites();
$blocks[$key]->replace();
unset($unguarded);
}
}
return $blocks;
}
/**
* Set the viewing user. Used to implement object permissions.
*
* @param PhabricatorUser The viewing user.
* @return this
* @task markup
*/
public function setViewer(PhabricatorUser $viewer) {
$this->viewer = $viewer;
return $this;
}
/* -( Engine Construction )------------------------------------------------ */
/**
* @task engine
*/
public static function newManiphestMarkupEngine() {
return self::newMarkupEngine(array(
));
}
/**
* @task engine
*/
public static function newPhrictionMarkupEngine() {
return self::newMarkupEngine(array(
'header.generate-toc' => true,
));
}
/**
* @task engine
*/
public static function newPhameMarkupEngine() {
return self::newMarkupEngine(array(
'macros' => false,
));
}
/**
* @task engine
*/
public static function newFeedMarkupEngine() {
return self::newMarkupEngine(
array(
'macros' => false,
'youtube' => false,
));
}
/**
* @task engine
*/
public static function newDifferentialMarkupEngine(array $options = array()) {
return self::newMarkupEngine(array(
'custom-inline' => PhabricatorEnv::getEnvConfig(
'differential.custom-remarkup-rules'),
'custom-block' => PhabricatorEnv::getEnvConfig(
'differential.custom-remarkup-block-rules'),
'differential.diff' => idx($options, 'differential.diff'),
));
}
/**
* @task engine
*/
public static function newDiffusionMarkupEngine(array $options = array()) {
return self::newMarkupEngine(array(
));
}
/**
* @task engine
*/
public static function getEngine($ruleset = 'default') {
static $engines = array();
if (isset($engines[$ruleset])) {
return $engines[$ruleset];
}
$engine = null;
switch ($ruleset) {
case 'default':
$engine = self::newMarkupEngine(array());
break;
case 'diviner':
$engine = self::newMarkupEngine(array());
$engine->setConfig('preserve-linebreaks', false);
// $engine->setConfig('diviner.renderer', new DivinerDefaultRenderer());
$engine->setConfig('header.generate-toc', true);
break;
default:
throw new Exception("Unknown engine ruleset: {$ruleset}!");
}
$engines[$ruleset] = $engine;
return $engine;
}
/**
* @task engine
*/
private static function getMarkupEngineDefaultConfiguration() {
return array(
'pygments' => PhabricatorEnv::getEnvConfig('pygments.enabled'),
'youtube' => PhabricatorEnv::getEnvConfig(
'remarkup.enable-embedded-youtube'),
'custom-inline' => array(),
'custom-block' => array(),
'differential.diff' => null,
'header.generate-toc' => false,
'macros' => true,
'uri.allowed-protocols' => PhabricatorEnv::getEnvConfig(
'uri.allowed-protocols'),
'syntax-highlighter.engine' => PhabricatorEnv::getEnvConfig(
'syntax-highlighter.engine'),
'preserve-linebreaks' => true,
);
}
/**
* @task engine
*/
public static function newMarkupEngine(array $options) {
$options += self::getMarkupEngineDefaultConfiguration();
$engine = new PhutilRemarkupEngine();
$engine->setConfig('preserve-linebreaks', $options['preserve-linebreaks']);
$engine->setConfig('pygments.enabled', $options['pygments']);
$engine->setConfig(
'uri.allowed-protocols',
$options['uri.allowed-protocols']);
$engine->setConfig('differential.diff', $options['differential.diff']);
$engine->setConfig('header.generate-toc', $options['header.generate-toc']);
$engine->setConfig(
'syntax-highlighter.engine',
$options['syntax-highlighter.engine']);
$rules = array();
$rules[] = new PhutilRemarkupRuleEscapeRemarkup();
$rules[] = new PhutilRemarkupRuleMonospace();
$custom_rule_classes = $options['custom-inline'];
if ($custom_rule_classes) {
foreach ($custom_rule_classes as $custom_rule_class) {
$rules[] = newv($custom_rule_class, array());
}
}
$rules[] = new PhutilRemarkupRuleDocumentLink();
if ($options['youtube']) {
$rules[] = new PhabricatorRemarkupRuleYoutube();
}
$applications = PhabricatorApplication::getAllInstalledApplications();
foreach ($applications as $application) {
foreach ($application->getRemarkupRules() as $rule) {
$rules[] = $rule;
}
}
$rules[] = new PhutilRemarkupRuleHyperlink();
if ($options['macros']) {
$rules[] = new PhabricatorRemarkupRuleImageMacro();
$rules[] = new PhabricatorRemarkupRuleMeme();
}
$rules[] = new PhutilRemarkupRuleBold();
$rules[] = new PhutilRemarkupRuleItalic();
$rules[] = new PhutilRemarkupRuleDel();
$blocks = array();
$blocks[] = new PhutilRemarkupEngineRemarkupQuotesBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupLiteralBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupHeaderBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupHorizontalRuleBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupListBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupCodeBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupNoteBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupTableBlockRule();
$blocks[] = new PhutilRemarkupEngineRemarkupSimpleTableBlockRule();
$custom_block_rule_classes = $options['custom-block'];
if ($custom_block_rule_classes) {
foreach ($custom_block_rule_classes as $custom_block_rule_class) {
$blocks[] = newv($custom_block_rule_class, array());
}
}
$blocks[] = new PhutilRemarkupEngineRemarkupDefaultBlockRule();
foreach ($blocks as $block) {
$block->setMarkupRules($rules);
}
$engine->setBlockRules($blocks);
return $engine;
}
public static function extractPHIDsFromMentions(array $content_blocks) {
$mentions = array();
$engine = self::newDifferentialMarkupEngine();
$engine->setConfig('viewer', PhabricatorUser::getOmnipotentUser());
foreach ($content_blocks as $content_block) {
$engine->markupText($content_block);
$phids = $engine->getTextMetadata(
PhabricatorRemarkupRuleMention::KEY_MENTIONED,
array());
$mentions += $phids;
}
return $mentions;
}
public static function extractFilePHIDsFromEmbeddedFiles(
array $content_blocks) {
$files = array();
$engine = self::newDifferentialMarkupEngine();
$engine->setConfig('viewer', PhabricatorUser::getOmnipotentUser());
foreach ($content_blocks as $content_block) {
$engine->markupText($content_block);
$ids = $engine->getTextMetadata(
PhabricatorRemarkupRuleEmbedFile::KEY_EMBED_FILE_PHIDS,
array());
$files += $ids;
}
return $files;
}
/**
* Produce a corpus summary, in a way that shortens the underlying text
* without truncating it somewhere awkward.
*
* TODO: We could do a better job of this.
*
* @param string Remarkup corpus to summarize.
* @return string Summarized corpus.
*/
public static function summarize($corpus) {
// Major goals here are:
// - Don't split in the middle of a character (utf-8).
// - Don't split in the middle of, e.g., **bold** text, since
// we end up with hanging '**' in the summary.
// - Try not to pick an image macro, header, embedded file, etc.
// - Hopefully don't return too much text. We don't explicitly limit
// this right now.
$blocks = preg_split("/\n *\n\s*/", trim($corpus));
$best = null;
foreach ($blocks as $block) {
// This is a test for normal spaces in the block, i.e. a heuristic to
// distinguish standard paragraphs from things like image macros. It may
// not work well for non-latin text. We prefer to summarize with a
// paragraph of normal words over an image macro, if possible.
$has_space = preg_match('/\w\s\w/', $block);
// This is a test to find embedded images and headers. We prefer to
// summarize with a normal paragraph over a header or an embedded object,
// if possible.
$has_embed = preg_match('/^[{=]/', $block);
if ($has_space && !$has_embed) {
// This seems like a good summary, so return it.
return $block;
}
if (!$best) {
// This is the first block we found; if everything is garbage just
// use the first block.
$best = $block;
}
}
return $best;
}
}
File Metadata
Details
Attached
Mime Type
text/x-diff
Expires
Jan 19 2025, 20:51 (6 w, 1 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
1128624
Default Alt Text
(54 KB)
Attached To
Mode
rP Phorge
Attached
Detach File
Event Timeline
Log In to Comment