Documentation
¶
Index ¶
- type Condition
- type ConditionInterpreter
- type Criteria
- type CriteriaBuilder
- type Extractor
- type Filter
- type HtmlAttributeExtractor
- type HtmlFilter
- type HtmlTextExtractor
- type HtmlTokenAttributeInterpreter
- type HtmlTokenIterator
- type HtmlTokenTagInterpreter
- type JsonFilter
- type KeyValueExtractor
- type KeyValueInterpreter
- type Manager
- type Tracker
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Condition ¶
type Condition struct {
// contains filtered or unexported fields
}
Condition holds an optional key and value regex and determines if a value passes its requirements or not.
func NewCondition ¶
type ConditionInterpreter ¶
ConditionInterpreter functions as a Mediator for Condition, allowing the data to be typed and matched.
type Criteria ¶
type Criteria struct {
Extractor Extractor
Depth int
Parent *Criteria
Child *Criteria
// contains filtered or unexported fields
}
Criteria defines if a set of data passes its requirements or not, and can optionally extract the matched data using Extractor.
func NewCriteria ¶
func NewCriteria(extractor Extractor, interpreters ...ConditionInterpreter) *Criteria
type CriteriaBuilder ¶
type CriteriaBuilder struct {
// contains filtered or unexported fields
}
CriteriaBuilder simplifies the adding of children to a Criteria.
func NewCriteriaBuilder ¶
func NewCriteriaBuilder(c *Criteria) *CriteriaBuilder
func (*CriteriaBuilder) AddChild ¶
func (cb *CriteriaBuilder) AddChild(child *Criteria) *CriteriaBuilder
func (*CriteriaBuilder) Build ¶
func (cb *CriteriaBuilder) Build() *Criteria
type Filter ¶
Filter defines the ability to filter a type of data potentially extract any desired results using Criteria.
type HtmlAttributeExtractor ¶
type HtmlAttributeExtractor struct {
Clean *func(data map[string]any) map[string]any
// contains filtered or unexported fields
}
HtmlAttributeExtractor implements Extractor and extracts attributes from the given *html.Token. An optional Clean function can be provided which is run on the results found before they are returned.
type HtmlFilter ¶
type HtmlFilter struct {
*Tracker
}
HtmlFilter implements Filter and iterates over HTML using HtmlTokenIterator. As it walks through the HTML document it searches for any matching Criteria, and extracts any found data with if Criteria has an Extractor.
func NewHtmlFilter ¶
func NewHtmlFilter(criteria ...*Criteria) *HtmlFilter
func (*HtmlFilter) Clone ¶
func (hf *HtmlFilter) Clone() Filter
func (*HtmlFilter) Filter ¶
func (hf *HtmlFilter) Filter(s string) map[string]any
Filter iterates over all tags within the given HTML, and applies Criteria for every found start tag. Any fully matched Criteria that have an Extractor will extract data from the matched tag and return it once the filter is finished.
type HtmlTextExtractor ¶
type HtmlTextExtractor struct {
Clean *func(data map[string]any) map[string]any
// contains filtered or unexported fields
}
HtmlTextExtractor implements Extractor and extracts text from the *html.Token. An optional Clean function can be provided which is run on the results found before they are returned.
func NewHtmlTextExtractor ¶
type HtmlTokenAttributeInterpreter ¶
type HtmlTokenAttributeInterpreter struct {
// contains filtered or unexported fields
}
HtmlTokenAttributeInterpreter implements ConditionInterpreter and allows an instance of *html.Token to be parsed, and checks if any matching attributes are found.
func NewHtmlTokenAttributeInterpreter ¶
func NewHtmlTokenAttributeInterpreter(keyExpr string, valueExpr string) *HtmlTokenAttributeInterpreter
func (*HtmlTokenAttributeInterpreter) Interpret ¶
func (htai *HtmlTokenAttributeInterpreter) Interpret(data any) bool
Interpret implements ConditionInterpreter.Interpret.
type HtmlTokenIterator ¶
type HtmlTokenIterator struct {
// contains filtered or unexported fields
}
HtmlTokenIterator walks through a given HTML document using html.Tokenizer. The depth of the HTML document is also tracked and is available through Depth().
func (*HtmlTokenIterator) Depth ¶
func (ti *HtmlTokenIterator) Depth() int
func (*HtmlTokenIterator) Next ¶
func (ti *HtmlTokenIterator) Next() html.TokenType
func (*HtmlTokenIterator) Token ¶
func (ti *HtmlTokenIterator) Token() html.Token
type HtmlTokenTagInterpreter ¶
type HtmlTokenTagInterpreter struct {
// contains filtered or unexported fields
}
HtmlTokenTagInterpreter implements ConditionInterpreter and allows an instance of *html.Token to be parsed, and checks if its tag matches or not.
func NewHtmlTokenTagInterpreter ¶
func NewHtmlTokenTagInterpreter(expr string) *HtmlTokenTagInterpreter
func (*HtmlTokenTagInterpreter) Interpret ¶
func (htti *HtmlTokenTagInterpreter) Interpret(data any) bool
Interpret implements ConditionInterpreter.Interpret.
type JsonFilter ¶
type JsonFilter struct {
*Tracker
}
JsonFilter implements Filter and iterates over the given JSON, As it walks over the given JSON it uses Criteria to search for any matching data. These matches are optionally extracted using Extractor and returned once the Filter has finished running.
func NewJsonFilter ¶
func NewJsonFilter(criteria ...*Criteria) *JsonFilter
func (*JsonFilter) Clone ¶
func (jf *JsonFilter) Clone() Filter
type KeyValueExtractor ¶
type KeyValueExtractor struct {
Clean *func(data map[string]any) map[string]any
// contains filtered or unexported fields
}
KeyValueExtractor implements Extractor and extracts data based on the provided key and value regexes. An optional Clean function can be provided which is run on the results found before they are returned.
func NewKeyValueExtractor ¶
type KeyValueInterpreter ¶
type KeyValueInterpreter struct {
// contains filtered or unexported fields
}
KeyValueInterpreter implements ConditionInterpreter and allows a key value pair in the format map[string]any to be parsed.
func NewKeyValueInterpreter ¶
func NewKeyValueInterpreter(keyExpr string, valueExpr string) *KeyValueInterpreter
func (*KeyValueInterpreter) Interpret ¶
func (kvi *KeyValueInterpreter) Interpret(data any) bool
Interpret implements ConditionInterpreter.Interpret.
type Manager ¶
type Manager struct {
// contains filtered or unexported fields
}
Manager oversees all Filter instances manages workers to run them in using supervisor.Supervisor.
Source Files