fileconvt

Documentation

Index

• Constants
• func ConvertDoc(r io.Reader) (string, map[string]string, error)
• func ConvertDocx(r io.Reader) (string, string, string, map[string]string, error)
• func ConvertGB2312toUTF8(meta map[string]string) (map[string]string, error)
• func ConvertHtml(reader io.Reader) (pageText string, err error)
• func ConvertOds(file io.ReaderAt, size int64, writer io.Writer, limit int64) (written int64, err error)
• func ConvertOdt(r io.Reader) (string, map[string]string, error)
• func ConvertPDF(path string) (string, map[string]string, error)
• func ConvertPDF_O(path string) (BodyResult, MetaResult, error)
• func ConvertPpt(r io.Reader) (string, map[string]string, error)
• func ConvertPptx(r io.Reader) (string, map[string]string, error)
• func ConvertRTF(fileName string) (string, map[string]string, error)
• func ConvertXML(r io.Reader) (string, map[string]string, error)
• func ConvertXlsO(reader io.ReadSeeker, writer io.Writer, size int64) (written int64, err error)
• func ConvertXlsx(file io.ReaderAt, size int64, writer io.Writer, limit int64, rowLimit int) (written int64, err error)
• func DocxXMLToText(r io.Reader) (string, error)
• func GenSection(sep string) string
• func GetOffice2k3Meta(r io.Reader) (map[string]string, error)
• func GetXlsxText(r io.Reader) (string, string, string, map[string]string, error)
• func HTML2TextAndLinks(reader io.Reader, baseURL string) (pageText string, links []string, err error)
• func IsFileXLS(data []byte) bool
• func IsFileXLSX(data []byte) bool
• func ODS2Cells(file io.ReaderAt, size int64) (cells []string, err error)
• func PrintFileText(header string, footer string, body string, meta map[string]string) bool
• func Tidy(r io.Reader, xmlIn bool) ([]byte, error)
• func XLS2Cells(reader io.ReadSeeker) (cells []string, err error)
• func XLSX2Cells(file io.ReaderAt, size int64, rowLimit int) (cells []string, err error)
• func XMLToMap(r io.Reader) (map[string]string, error)
• func XMLToText(r io.Reader, breaks []string, skip []string, strict bool) (string, error)
• type BodyResult
• type LocalFile
  • func NewLocalFile(r io.Reader) (*LocalFile, error)
  • func (l *LocalFile) Done()
• type MetaResult

Constants

const SizeLimit = 20 * 1024 * 1024

Functions

func ConvertDoc

func ConvertDoc(r io.Reader) (string, map[string]string, error)

ConvertDoc converts an MS Word .doc to text.

func ConvertDocx

func ConvertDocx(r io.Reader) (string, string, string, map[string]string, error)

ConvertDocx converts an MS Word docx file to text: header, footer, body, meta

func ConvertGB2312toUTF8

func ConvertGB2312toUTF8(meta map[string]string) (map[string]string, error)

func ConvertHtml

func ConvertHtml(reader io.Reader) (pageText string, err error)

func ConvertOds

func ConvertOds(file io.ReaderAt, size int64, writer io.Writer, limit int64) (written int64, err error)

func ConvertOdt

func ConvertOdt(r io.Reader) (string, map[string]string, error)

func ConvertPDF

func ConvertPDF(path string) (string, map[string]string, error)

func ConvertPDF_O

func ConvertPDF_O(path string) (BodyResult, MetaResult, error)

func ConvertPpt

func ConvertPpt(r io.Reader) (string, map[string]string, error)

ConvertDoc converts an MS Word .doc to text.

func ConvertPptx

func ConvertPptx(r io.Reader) (string, map[string]string, error)

ConvertPptx converts an MS PowerPoint pptx file to text.

func ConvertRTF

func ConvertRTF(fileName string) (string, map[string]string, error)

ConvertRTF converts RTF files to text.

func ConvertXML

func ConvertXML(r io.Reader) (string, map[string]string, error)

ConvertXML converts an XML file to text.

func ConvertXlsO

func ConvertXlsO(reader io.ReadSeeker, writer io.Writer, size int64) (written int64, err error)

func ConvertXlsx

func ConvertXlsx(file io.ReaderAt, size int64, writer io.Writer, limit int64, rowLimit int) (written int64, err error)

XLSX2Text extracts text of an Excel sheet Size is the full size of the input file. Limit is the output limit in bytes. rowLimit defines how many rows per sheet to extract. -1 means unlimited. This exists as protection against some XLSX files that may use excessive amount of memory.

func DocxXMLToText

func DocxXMLToText(r io.Reader) (string, error)

DocxXMLToText converts Docx XML into plain text.

func GenSection

func GenSection(sep string) string

https://www.fileformat.info/info/unicode/char/3000/index.htm UTF-8 (hex) 0xE3 0x80 0x80 (e38080)

func GetOffice2k3Meta

func GetOffice2k3Meta(r io.Reader) (map[string]string, error)

func GetXlsxText

func GetXlsxText(r io.Reader) (string, string, string, map[string]string, error)

func HTML2TextAndLinks

func HTML2TextAndLinks(reader io.Reader, baseURL string) (pageText string, links []string, err error)

HTML2TextAndLinks extracts the text from the HTML and all links from <a> and <img> tags of a HTML If the base URL is provided, relative links will be converted to absolute ones.

func IsFileXLS

func IsFileXLS(data []byte) bool

IsFileXLS checks if the data indicates a XLS file XLS has a signature of D0 CF 11 E0 A1 B1 1A E1

func IsFileXLSX

func IsFileXLSX(data []byte) bool

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

func ODS2Cells

func ODS2Cells(file io.ReaderAt, size int64) (cells []string, err error)

ODS2Cells converts an ODS file to individual cells Size is the full size of the input file.

func PrintFileText

func PrintFileText(header string, footer string, body string, meta map[string]string) bool

func Tidy

func Tidy(r io.Reader, xmlIn bool) ([]byte, error)

Tidy attempts to tidy up XML.

func XLS2Cells

func XLS2Cells(reader io.ReadSeeker) (cells []string, err error)

XLS2Cells converts an XLS file to individual cells

func XLSX2Cells

func XLSX2Cells(file io.ReaderAt, size int64, rowLimit int) (cells []string, err error)

XLSX2Cells converts an XLSX file to individual cells Size is the full size of the input file. rowLimit defines how many rows per sheet to extract. -1 means unlimited. This exists as protection against some XLSX files that may use excessive amount of memory.

func XMLToMap

func XMLToMap(r io.Reader) (map[string]string, error)

XMLToMap converts XML to a nested string map.

func XMLToText

func XMLToText(r io.Reader, breaks []string, skip []string, strict bool) (string, error)

XMLToText converts XML to plain text given how to treat elements.

Types

type BodyResult

type BodyResult struct {
	// contains filtered or unexported fields
}

type LocalFile

type LocalFile struct {
	*os.File
	// contains filtered or unexported fields
}

wraps an *os.File

func NewLocalFile

func NewLocalFile(r io.Reader) (*LocalFile, error)

NewLocalFile ensures that there is a file which contains the data provided by r. If r is actually an instance of *os.File then this file is used, otherwise a temporary file is created and the data from r copied into it. Callers must call Done() when the LocalFile is no longer needed to ensure all resources are cleaned up.

func (*LocalFile) Done

func (l *LocalFile) Done()

Done cleans up all resources.

type MetaResult

type MetaResult struct {
	// contains filtered or unexported fields
}