Pdf
in package
Pop Pdf class
Tags
Table of Contents
Methods
- extractTextFromData() : string
- Extract text from raw data stream
- extractTextFromFile() : string
- Extract text from file
- getImageOnlyPages() : array<string|int, mixed>
- Get a per-page image-only classification for a PDF file
- getImageOnlyPagesFromData() : array<string|int, mixed>
- Get a per-page image-only classification for raw PDF data
- importFromFile() : AbstractDocument
- Import from an existing PDF file
- importFromHtml() : AbstractDocument
- Import from an HTML string
- importFromHtmlFile() : AbstractDocument
- Import from an HTML file
- importFromImages() : AbstractDocument
- Import from an existing PDF file
- importRawData() : AbstractDocument
- Import from raw data stream
- isImageOnlyData() : bool
- Determine if every page of raw PDF data is nothing but a single scanned/drawn image
- isImageOnlyDocument() : bool
- Determine if every page of a PDF file is nothing but a single scanned/drawn image
- merge() : AbstractDocument
- Merge PDF files into one document
- mergeRawData() : AbstractDocument
- Merge raw PDF data streams into one document
- outputToHttp() : void
- Output to HTTP response
- writeToFile() : void
- Write document to file
- allPagesImageOnly() : bool
- Determine if a set of per-page image-only results means the whole document is image-only
- classifyPages() : array<string|int, mixed>
- Classify every page of a parsed Extract\Document as image-only or not
- extractTextFromDocument() : string
- Extract text from a parsed Extract\Document, joining pages/runs
- extractTextFromPage() : string
- Extract text from a single page, joining runs by their separator
Methods
extractTextFromData()
Extract text from raw data stream
public
static extractTextFromData(string $data[, mixed $pages = null ][, int|null $pageLimit = null ]) : string
Parameters
- $data : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
stringextractTextFromFile()
Extract text from file
public
static extractTextFromFile(string $file[, mixed $pages = null ][, int|null $pageLimit = null ]) : string
Parameters
- $file : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
stringgetImageOnlyPages()
Get a per-page image-only classification for a PDF file
public
static getImageOnlyPages(string $file[, mixed $pages = null ][, int|null $pageLimit = null ]) : array<string|int, mixed>
Parameters
- $file : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
array<string|int, mixed>getImageOnlyPagesFromData()
Get a per-page image-only classification for raw PDF data
public
static getImageOnlyPagesFromData(string $data[, mixed $pages = null ][, int|null $pageLimit = null ]) : array<string|int, mixed>
Parameters
- $data : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
array<string|int, mixed>importFromFile()
Import from an existing PDF file
public
static importFromFile(string $file[, mixed $pages = null ]) : AbstractDocument
Parameters
- $file : string
- $pages : mixed = null
Return values
AbstractDocumentimportFromHtml()
Import from an HTML string
public
static importFromHtml(string $html[, Document $document = new Document() ]) : AbstractDocument
Parameters
- $html : string
- $document : Document = new Document()
Return values
AbstractDocumentimportFromHtmlFile()
Import from an HTML file
public
static importFromHtmlFile(string $htmlFile[, Document $document = new Document() ]) : AbstractDocument
Parameters
- $htmlFile : string
- $document : Document = new Document()
Return values
AbstractDocumentimportFromImages()
Import from an existing PDF file
public
static importFromImages(string|array<string|int, mixed> $images[, int $quality = 70 ]) : AbstractDocument
Parameters
- $images : string|array<string|int, mixed>
- $quality : int = 70
Tags
Return values
AbstractDocumentimportRawData()
Import from raw data stream
public
static importRawData(string $data[, mixed $pages = null ]) : AbstractDocument
Parameters
- $data : string
- $pages : mixed = null
Return values
AbstractDocumentisImageOnlyData()
Determine if every page of raw PDF data is nothing but a single scanned/drawn image
public
static isImageOnlyData(string $data[, mixed $pages = null ][, int|null $pageLimit = null ]) : bool
Parameters
- $data : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
boolisImageOnlyDocument()
Determine if every page of a PDF file is nothing but a single scanned/drawn image
public
static isImageOnlyDocument(string $file[, mixed $pages = null ][, int|null $pageLimit = null ]) : bool
Parameters
- $file : string
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
boolmerge()
Merge PDF files into one document
public
static merge(array<string|int, mixed> $files) : AbstractDocument
Parameters
- $files : array<string|int, mixed>
Return values
AbstractDocumentmergeRawData()
Merge raw PDF data streams into one document
public
static mergeRawData(array<string|int, mixed> $data) : AbstractDocument
Parameters
- $data : array<string|int, mixed>
Return values
AbstractDocumentoutputToHttp()
Output to HTTP response
public
static outputToHttp(Document $document[, string $filename = 'pop.pdf' ][, bool $forceDownload = false ][, array<string|int, mixed> $headers = [] ]) : void
Parameters
- $document : Document
- $filename : string = 'pop.pdf'
- $forceDownload : bool = false
- $headers : array<string|int, mixed> = []
writeToFile()
Write document to file
public
static writeToFile(Document $document[, string $filename = 'pop.pdf' ]) : void
Parameters
- $document : Document
- $filename : string = 'pop.pdf'
allPagesImageOnly()
Determine if a set of per-page image-only results means the whole document is image-only
protected
static allPagesImageOnly(array<string|int, mixed> $pages) : bool
Parameters
- $pages : array<string|int, mixed>
Return values
boolclassifyPages()
Classify every page of a parsed Extract\Document as image-only or not
protected
static classifyPages(Document $doc[, mixed $pages = null ][, int|null $pageLimit = null ]) : array<string|int, mixed>
Parameters
- $doc : Document
- $pages : mixed = null
- $pageLimit : int|null = null
Return values
array<string|int, mixed>extractTextFromDocument()
Extract text from a parsed Extract\Document, joining pages/runs
protected
static extractTextFromDocument(Document $doc, mixed $pages, int|null $pageLimit) : string
Parameters
- $doc : Document
- $pages : mixed
- $pageLimit : int|null
Return values
stringextractTextFromPage()
Extract text from a single page, joining runs by their separator
protected
static extractTextFromPage(Document $doc, PageInfo $page) : string