ltxmlharvest

README

ltxmlharvest

A new harvester for latexml-produced xhtml

Documentation

Overview

Package ltxmlharvest provides a MathWebSearch harvester for documents outputted by latexml

Index

• func HarvestFS(fsys fs.FS, accept func(path string) bool, uri func(path string) string, ...)
• func HarvestReader(reader io.Reader, URI string, writer io.WriteCloser) error
• type Harvest
  • func HarvestFragments(jobs []Job, logger *log.Logger) Harvest
  • func (harvest Harvest) Len() int
  • func (harvest Harvest) Less(i, j int) bool
  • func (harvest Harvest) MarshalXML(e *xml.Encoder, start xml.StartElement) error
  • func (harvest Harvest) Swap(i, j int)
  • func (harvest Harvest) WriteTo(writer io.Writer) (n int64, err error)
• type HarvestFormula
  • func ReadFormula(math *etree.Element) (HarvestFormula, error)
• type HarvestFragment
  • func (frag HarvestFragment) MarshalXML(e *xml.Encoder, start xml.StartElement) error
  • func (f *HarvestFragment) ReadFrom(reader io.Reader) (n int64, err error)
• type Job
  • func JobFromFile(fsys fs.FS, path string, URI string) Job
  • func (job Job) Do(wg *sync.WaitGroup, n int, fragments chan<- HarvestFragment, ...) (err error)

Functions

func HarvestFS

func HarvestFS(fsys fs.FS, accept func(path string) bool, uri func(path string) string, writer func(path string, harvest Harvest) error, logger *log.Logger)

HarvestFS recursively harvests all files in fs.FS. Each directory will be grouped into a single harvest.

func HarvestReader

func HarvestReader(reader io.Reader, URI string, writer io.WriteCloser) error

HarvestReader harvests a single reader and writes the output to writer

Types

type Harvest

type Harvest []HarvestFragment

Harvest represents a single harvest. It implements sort.Interface

func HarvestFragments

func HarvestFragments(jobs []Job, logger *log.Logger) Harvest

HarvestFragments executes jobs and writes them to logger

func (Harvest) Len

func (harvest Harvest) Len() int

func (Harvest) Less

func (harvest Harvest) Less(i, j int) bool

func (Harvest) MarshalXML

func (harvest Harvest) MarshalXML(e *xml.Encoder, start xml.StartElement) error

MarshalXML marshals this harvest into xml form

func (Harvest) Swap

func (harvest Harvest) Swap(i, j int)

func (Harvest) WriteTo

func (harvest Harvest) WriteTo(writer io.Writer) (n int64, err error)

WriteTo writes this harvest into writer and returns (0, error)

type HarvestFormula

type HarvestFormula struct {
	// ID of this formula
	ID string

	// Dual (Content + Presentation) MathML contained in this document
	// Content and Presentation should be linked using "xref" attributes.
	// May use "m" and "mws" namespaces.
	DualMathML string

	// Content MathML corresponding to the DualMathML above.
	// Must use the "m" namespace.
	ContentMathML string
}

HarvestFormula represents a single formula found within the harvest

func ReadFormula

func ReadFormula(math *etree.Element) (HarvestFormula, error)

ReadFormula parses a formula based on element

type HarvestFragment

type HarvestFragment struct {
	// ID is an internal, but unique, id of this harvest fragment
	// typically just the running id of this fragment
	ID string

	// URI is the URI of the corresponding document
	URI string

	// XHTMLContent of this document, substiuting "math" + id for formulae
	XHTMLContent string

	// List of formulae within the harvest
	Formulae []HarvestFormula
}

HarvestFragment represents a single document fragment within a harvest

func (HarvestFragment) MarshalXML

func (frag HarvestFragment) MarshalXML(e *xml.Encoder, start xml.StartElement) error

MarshalXML marshals this document into xml

func (*HarvestFragment) ReadFrom

func (f *HarvestFragment) ReadFrom(reader io.Reader) (n int64, err error)

type Job

type Job struct {
	Reader func() (io.ReadCloser, error)
	URI    string
}

Job describes a job for the harvester

func JobFromFile

func JobFromFile(fsys fs.FS, path string, URI string) Job

JobFromFile creates a new Job from a file and a uribase

func (Job) Do

func (job Job) Do(wg *sync.WaitGroup, n int, fragments chan<- HarvestFragment, logger *log.Logger) (err error)