opencrucible

README

opencrucible

Detect type and extract text from different file type. Similar to Tika Project but in Golang.

List of formats read:

Format	FileParser	MIME Type	Metadata
TXT	X	text/plain; charset=utf-8
RTF	X	text/rtf
DOC (partial)	X	application/x-ole-storage
ODT	X	application/vnd.oasis.opendocument.text	X
DOCX	X	application/vnd.openxmlformats-officedocument.wordprocessingml.document	X
PPTX	X	application/vnd.openxmlformats-officedocument.presentationml.presentation	X
PDF	X	application/pdf	X

Documentation

Index

• Constants
• func DOCFileParseToString(FileToParse string) (string, error)
• func DOCX2Text(file io.ReaderAt, size int64) (string, error)
• func DOCXFileParseToString(FileToParse string) (string, error)
• func DetectFileType(StreamToDetect []byte) (string, string, error)
• func DetectFileTypeMIME(StreamToDetect []byte) (string, string, error)
• func IsFileDOCX(data []byte) bool
• func IsFilePPTX(data []byte) bool
• func ODTFileParseToString(FileToParse string) (string, error)
• func ODTParseToString(StreamToParse []byte) (string, error)
• func OfficeFileMetadata(FileToParse string) (*metagoffice.XMLContent, error)
• func OpenOfficeFileMetadata(FileToParse string) (*metagopenoffice.OpenOfficeXML, error)
• func PDFFileMetadata(FileToParse string) (*pdf_parser.PdfInfo, error)
• func PDFFileParseToString(FileToParse string) (string, error)
• func PPTX2Text(file io.ReaderAt, size int64) (string, error)
• func PPTXFileParseToString(FileToParse string) (string, error)
• func RTFFileParseToString(FileToParse string) (string, error)
• func RTFParseToString(StreamToParse []byte) (string, error)
• func TXTFileParseToString(FileToParse string) (string, error)
• func TXTParseToString(StreamToParse []byte) (string, error)
• type PPTXDocument
  • func (doc PPTXDocument) AsText() (text string)
• type PPTXSlide
• type SlideNumberSorter
  • func (a SlideNumberSorter) Len() int
  • func (a SlideNumberSorter) Less(i, j int) bool
  • func (a SlideNumberSorter) Swap(i, j int)
• type WordDocument
  • func WordParse(doc string) (WordDocument, error)
  • func (w WordDocument) AsText() string
• type WordParagraph
• type WordRow
• type WordStyle

Constants

const Version = "0.0.7"

Version exposes the current package version.

Functions

func DOCFileParseToString

func DOCFileParseToString(FileToParse string) (string, error)

func DOCX2Text

func DOCX2Text(file io.ReaderAt, size int64) (string, error)

DOCX2Text extracts text of a Word document Size is the full size of the input file.

func DOCXFileParseToString

func DOCXFileParseToString(FileToParse string) (string, error)

func DetectFileType

func DetectFileType(StreamToDetect []byte) (string, string, error)

func DetectFileTypeMIME

func DetectFileTypeMIME(StreamToDetect []byte) (string, string, error)

func IsFileDOCX

func IsFileDOCX(data []byte) bool

IsFileDOCX checks if the data indicates a DOCX file DOCX has a signature of 50 4B 03 04

func IsFilePPTX

func IsFilePPTX(data []byte) bool

IsFilePPTX checks if the data indicates a PPTX file PPTX has a signature of 50 4B 03 04 Warning: This collides with ZIP, DOCX and other zip-based files.

func ODTFileParseToString

func ODTFileParseToString(FileToParse string) (string, error)

func ODTParseToString

func ODTParseToString(StreamToParse []byte) (string, error)

func OfficeFileMetadata

func OfficeFileMetadata(FileToParse string) (*metagoffice.XMLContent, error)

func OpenOfficeFileMetadata

func OpenOfficeFileMetadata(FileToParse string) (*metagopenoffice.OpenOfficeXML, error)

See for return: https://stackoverflow.com/questions/50697914/return-nil-for-a-struct-in-go

func PDFFileMetadata

func PDFFileMetadata(FileToParse string) (*pdf_parser.PdfInfo, error)

See: https://www.lazy-tech.net/project/pdf_metadata_parsing_golang

func PDFFileParseToString

func PDFFileParseToString(FileToParse string) (string, error)

func PPTX2Text

func PPTX2Text(file io.ReaderAt, size int64) (string, error)

PPTX2Text extracts text of a PowerPoint document Size is the full size of the input file.

func PPTXFileParseToString

func PPTXFileParseToString(FileToParse string) (string, error)

func RTFFileParseToString

func RTFFileParseToString(FileToParse string) (string, error)

func RTFParseToString

func RTFParseToString(StreamToParse []byte) (string, error)

func TXTFileParseToString

func TXTFileParseToString(FileToParse string) (string, error)

func TXTParseToString

func TXTParseToString(StreamToParse []byte) (string, error)

Types

type PPTXDocument

type PPTXDocument struct {
	Slides []PPTXSlide
}

PPTXDocument is a PPTX document loaded into memory

func (PPTXDocument) AsText

func (doc PPTXDocument) AsText() (text string)

AsText returns the text on all slides

type PPTXSlide

type PPTXSlide struct {
	SlideNumber int
	//ThumbnailBase64 string
	TextContent string
}

PPTXSlide is a single PPTX slide

type SlideNumberSorter

type SlideNumberSorter []PPTXSlide

SlideNumberSorter is used for sorting

func (SlideNumberSorter) Len

func (a SlideNumberSorter) Len() int

func (SlideNumberSorter) Less

func (a SlideNumberSorter) Less(i, j int) bool

func (SlideNumberSorter) Swap

func (a SlideNumberSorter) Swap(i, j int)

type WordDocument

type WordDocument struct {
	Paragraphs []WordParagraph
}

WordDocument is a full word doc

func WordParse

func WordParse(doc string) (WordDocument, error)

WordParse parses a word file

func (WordDocument) AsText

func (w WordDocument) AsText() string

AsText returns all text in the document

type WordParagraph

type WordParagraph struct {
	Style WordStyle `xml:"pPr>pStyle"`
	Rows  []WordRow `xml:"r"`
}

WordParagraph is a single paragraph

type WordRow

type WordRow struct {
	Text string `xml:"t"`
}

WordRow ...

type WordStyle

type WordStyle struct {
	Val string `xml:"val,attr"`
}

WordStyle ...