parser

Documentation

Index

• type CsvParser
  • func (x CsvParser) ConvertDemo(unprocessed []byte) (Demo, error)
  • func (x CsvParser) ConvertSource(i []byte) (Source, error)
• type CsvRow
• type Demo
  • func ConvertDemo(unprocessed []byte, t DocumentType) (Demo, error)
• type DocXParser
  • func (t DocXParser) ConvertDemo(i []byte) (Demo, error)
  • func (t DocXParser) ConvertSource(unprocessed []byte) (Source, error)
• type DocumentType
• type Paragraph
• type Parser
  • func NewParser(t DocumentType) (Parser, error)
• type Sentence
• type Source
  • func ConvertSource(unprocessed []byte, t DocumentType) (Source, error)
• type TxtParser
  • func (t TxtParser) ConvertDemo(bytes []byte) (Demo, error)
  • func (t TxtParser) ConvertSource(unprocessed []byte) (Source, error)
• type XlsxParser
  • func (x XlsxParser) ConvertDemo(unprocessed []byte) (Demo, error)
  • func (x XlsxParser) ConvertSource(i []byte) (Source, error)

Types

type CsvParser

type CsvParser struct {
}

func (CsvParser) ConvertDemo

func (x CsvParser) ConvertDemo(unprocessed []byte) (Demo, error)

func (CsvParser) ConvertSource

func (x CsvParser) ConvertSource(i []byte) (Source, error)

type CsvRow

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

type Demo

type Demo = swagger.Demo

func ConvertDemo

func ConvertDemo(unprocessed []byte, t DocumentType) (Demo, error)

/ ConvertDemo

type DocXParser

type DocXParser struct {
}

DocxParser implements the converter interface

func (DocXParser) ConvertDemo

func (t DocXParser) ConvertDemo(i []byte) (Demo, error)

func (DocXParser) ConvertSource

func (t DocXParser) ConvertSource(unprocessed []byte) (Source, error)

Convert unzips the docx file, finds the content (document.xml), parses the xml tree, and finally walks the xml tree in a top down fashion

type DocumentType

type DocumentType int

const (
	Text DocumentType = iota
	DocX
	Xlsx
	Csv
)

type Paragraph

type Paragraph = swagger.Paragraph

type Parser

type Parser interface {
	ConvertSource([]byte) (Source, error)
	ConvertDemo([]byte) (Demo, error)
}

func NewParser

func NewParser(t DocumentType) (Parser, error)

GetParser returns the matching parser for the filetype or error if there is no correct parser

type Sentence

type Sentence = swagger.Sentence

type Source

type Source = swagger.Source

func ConvertSource

func ConvertSource(unprocessed []byte, t DocumentType) (Source, error)

ConvertSource takes the bytes from a file and the file type and generates a simple intermediate representation which can be manipulated.

type TxtParser

type TxtParser struct {
}

func (TxtParser) ConvertDemo

func (t TxtParser) ConvertDemo(bytes []byte) (Demo, error)

func (TxtParser) ConvertSource

func (t TxtParser) ConvertSource(unprocessed []byte) (Source, error)

Convert for the TxtParser does not fail since it simply reads from the start of the bytes to the end It makes fairly arbitrary choices for how to handle certain datatypes.

type XlsxParser

type XlsxParser struct {
}

func (XlsxParser) ConvertDemo

func (x XlsxParser) ConvertDemo(unprocessed []byte) (Demo, error)

func (XlsxParser) ConvertSource

func (x XlsxParser) ConvertSource(i []byte) (Source, error)