tashaphyne

package module

v0.2.0 Latest Latest Go to latest Published: Feb 6, 2025 License: MIT Imports: 5 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/maa3x/tashaphyne

Links

Open Source Insights

README ¶

tashaphyne

The Go port of Tashaphyne Arabic Light Stemmer

Documentation ¶

Index ¶

Constants
Variables
func In[T comparable](needle T, haystack ...T) bool
func IsStop(s string) bool
func IsVerbStamp(s string) bool
func Max[T cmp.Ordered](values ...T) (m T)
func Min[T cmp.Ordered](values ...T) (m T)
func NormalizeHamza(s string) string
func NormalizeLamAlef(s string) string
func NormalizeSearchText(s string) string
func NormalizeSpellErrors(s string) string
func StopStem(s string) string
func StripTashkeel(s string) string
func StripTatweel(s string) string
func VerbStamp(s Runes) string
type Runes
- func (r Runes) Append(s string) Runes
- func (r Runes) At(pos int) string
- func (r Runes) Contains(sub string) bool
- func (r Runes) HasPrefix(prefix string) bool
- func (r Runes) HasSuffix(suffix string) bool
- func (r Runes) In(values ...string) bool
- func (r Runes) IndexOf(s string) int
- func (r Runes) LastIndexOf(s string) int
- func (r Runes) Prepend(s string) Runes
- func (r Runes) Replace(old, new string) Runes
- func (r Runes) ReplaceRegex(re *regexp.Regexp, new string) Runes
- func (r Runes) Slice(from, to int) Runes
- func (r Runes) SliceFrom(from int) Runes
- func (r Runes) SliceTo(to int) Runes
- func (r Runes) String() string
- func (r Runes) StripTashkeel() Runes
type Stemmer
- func New() *Stemmer
- func (s *Stemmer) LightStem(word string) string
type StopWord

Constants ¶

View Source

const (
	Comma          = "\u060C"
	Semicolon      = "\u061B"
	Question       = "\u061F"
	Hamza          = "\u0621"
	AlefMadda      = "\u0622"
	AlefHamzaAbove = "\u0623"
	WawHamza       = "\u0624"
	AlefHamzaBelow = "\u0625"
	YehHamza       = "\u0626"
	Alef           = "\u0627"
	Beh            = "\u0628"
	TehMarbuta     = "\u0629"
	Teh            = "\u062a"
	Theh           = "\u062b"
	Jeem           = "\u062c"
	Hah            = "\u062d"
	Khah           = "\u062e"
	Dal            = "\u062f"
	Thal           = "\u0630"
	Reh            = "\u0631"
	Zain           = "\u0632"
	Seen           = "\u0633"
	Sheen          = "\u0634"
	Sad            = "\u0635"
	Dad            = "\u0636"
	Tah            = "\u0637"
	Zah            = "\u0638"
	Ain            = "\u0639"
	Ghain          = "\u063a"
	Tatweel        = "\u0640"
	Feh            = "\u0641"
	Qaf            = "\u0642"
	Kaf            = "\u0643"
	Lam            = "\u0644"
	Meem           = "\u0645"
	Noon           = "\u0646"
	Heh            = "\u0647"
	Waw            = "\u0648"
	AlefMaksura    = "\u0649"
	Yeh            = "\u064a"
	MaddaAbove     = "\u0653"
	HamzaAbove     = "\u0654"
	HamzaBelow     = "\u0655"
	Zero           = "\u0660"
	One            = "\u0661"
	Two            = "\u0662"
	Three          = "\u0663"
	Four           = "\u0664"
	Five           = "\u0665"
	Six            = "\u0666"
	Seven          = "\u0667"
	Eight          = "\u0668"
	Nine           = "\u0669"
	Percent        = "\u066a"
	Decimal        = "\u066b"
	Thousands      = "\u066c"
	Star           = "\u066d"
	MiniAlef       = "\u0670"
	AlefWasla      = "\u0671"
	FullStop       = "\u06d4"
	ByteOrderMark  = "\ufeff"

	// Diacritics
	Fathatan = "\u064b"
	Dammatan = "\u064c"
	Kasratan = "\u064d"
	Fatha    = "\u064e"
	Damma    = "\u064f"
	Kasra    = "\u0650"
	Shadda   = "\u0651"
	Sukun    = "\u0652"

	// Ligatures
	LamAlef                 = "\ufefb"
	LamAlefHamzaAbove       = "\ufef7"
	LamAlefHamzaBelow       = "\ufef9"
	LamAlefMaddaAbove       = "\ufef5"
	SimpleLamAlef           = "\u0644\u0627"
	SimpleLamAlefHamzaAbove = "\u0644\u0623"
	SimpleLamAlefHamzaBelow = "\u0644\u0625"
	SimpleLamAlefMaddaAbove = "\u0644\u0622"
)

View Source

const (
	DefaultPrefixLetters = "مأسفلونيتاكب"
	DefaultSuffixLetters = "امتةكنهوي"
	DefaultInfixLetters  = "اتويطد"
	DefaultMaxPrefix     = 6
	DefaultMaxSuffix     = 5
	DefaultMinStem       = 3
	DefaultJoker         = "*"
	Verb                 = "verb"
	Noun                 = "noun"
)

Variables ¶

View Source

var (
	AffixList          = append(VerbAffixList, NounAffixList...)
	StemmingPrefixList = append(VerbPrefixList, NounPrefixList...)
	StemmingSuffixList = append(VerbSuffixList, NounSuffixList...)
)

View Source

var (
	DefaultPrefixList = []string{} /* 242 elements not displayed */
	DefaultSuffixList = []string{} /* 294 elements not displayed */
)

View Source

var NounAffixList = []string{}/* 2177 elements not displayed */

View Source

var NounPrefixList = []string{
	"",
	"آل",
	"أ",
	"أب",
	"أبال",
	"أف",
	"أفال",
	"أفب",
	"أفبال",
	"أفك",
	"أفكال",
	"أفل",
	"أفلل",
	"أك",
	"أكال",
	"أل",
	"ألل",
	"أو",
	"أوال",
	"أوب",
	"أوبال",
	"أوك",
	"أوكال",
	"أول",
	"أولل",
	"ال",
	"ب",
	"بال",
	"ف",
	"فال",
	"فب",
	"فبال",
	"فك",
	"فكال",
	"فل",
	"فلل",
	"ك",
	"كال",
	"ل",
	"لل",
	"و",
	"وال",
	"وب",
	"وبال",
	"وك",
	"وكال",
	"ول",
	"ولل",
}

View Source

var NounSuffixList = []string{}/* 102 elements not displayed */

View Source

var Roots = []string{} /* 7504 elements not displayed */

View Source

var StopWords = map[string]StopWord{}/* 10339 elements not displayed */

View Source

var VerbAffixList = []string{}/* 3879 elements not displayed */

View Source

var VerbPrefixList = []string{
	"",
	"أ",
	"أأ",
	"أت",
	"أسأ",
	"أست",
	"أسن",
	"أسي",
	"أف",
	"أفأ",
	"أفت",
	"أفسأ",
	"أفست",
	"أفسن",
	"أفسي",
	"أفن",
	"أفي",
	"أن",
	"أو",
	"أوأ",
	"أوت",
	"أوسأ",
	"أوست",
	"أوسن",
	"أوسي",
	"أولأ",
	"أولت",
	"أولن",
	"أولي",
	"أون",
	"أوي",
	"أي",
	"ا",
	"ت",
	"سأ",
	"ست",
	"سن",
	"سي",
	"ف",
	"فأ",
	"فا",
	"فت",
	"فسأ",
	"فست",
	"فسن",
	"فسي",
	"فل",
	"فلأ",
	"فلت",
	"فلن",
	"فلي",
	"فن",
	"في",
	"ل",
	"لأ",
	"لت",
	"لن",
	"لي",
	"ن",
	"و",
	"وأ",
	"وا",
	"وت",
	"وسأ",
	"وست",
	"وسن",
	"وسي",
	"ول",
	"ولأ",
	"ولت",
	"ولن",
	"ولي",
	"ون",
	"وي",
	"ي",
}

View Source

var VerbSuffixList = []string{}/* 160 elements not displayed */

View Source

var Verbs map[string]struct{}

Functions ¶

func In ¶

func In[T comparable](needle T, haystack ...T) bool

func IsStop ¶

func IsStop(s string) bool

func IsVerbStamp ¶

func IsVerbStamp(s string) bool

func Max ¶

func Max[T cmp.Ordered](values ...T) (m T)

func Min ¶

func Min[T cmp.Ordered](values ...T) (m T)

func NormalizeHamza ¶

func NormalizeHamza(s string) string

func NormalizeLamAlef ¶

func NormalizeLamAlef(s string) string

func NormalizeSearchText ¶

func NormalizeSearchText(s string) string

func NormalizeSpellErrors ¶

func NormalizeSpellErrors(s string) string

func StopStem ¶

func StopStem(s string) string

func StripTashkeel ¶

func StripTashkeel(s string) string

func StripTatweel ¶

func StripTatweel(s string) string

func VerbStamp ¶

func VerbStamp(s Runes) string

Types ¶

type Runes ¶

type Runes []rune

func (Runes) Append ¶

func (r Runes) Append(s string) Runes

func (Runes) At ¶

func (r Runes) At(pos int) string

func (Runes) Contains ¶

func (r Runes) Contains(sub string) bool

func (Runes) HasPrefix ¶

func (r Runes) HasPrefix(prefix string) bool

func (Runes) HasSuffix ¶

func (r Runes) HasSuffix(suffix string) bool

func (Runes) In ¶

func (r Runes) In(values ...string) bool

func (Runes) IndexOf ¶

func (r Runes) IndexOf(s string) int

func (Runes) LastIndexOf ¶

func (r Runes) LastIndexOf(s string) int

func (Runes) Prepend ¶

func (r Runes) Prepend(s string) Runes

func (Runes) Replace ¶

func (r Runes) Replace(old, new string) Runes

func (Runes) ReplaceRegex ¶

func (r Runes) ReplaceRegex(re *regexp.Regexp, new string) Runes

func (Runes) Slice ¶

func (r Runes) Slice(from, to int) Runes

func (Runes) SliceFrom ¶

func (r Runes) SliceFrom(from int) Runes

func (Runes) SliceTo ¶

func (r Runes) SliceTo(to int) Runes

func (Runes) String ¶

func (r Runes) String() string

func (Runes) StripTashkeel ¶

func (r Runes) StripTashkeel() Runes

type Stemmer ¶

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

func New ¶

func New() *Stemmer

func (*Stemmer) LightStem ¶

func (s *Stemmer) LightStem(word string) string

type StopWord ¶

type StopWord struct {
	Word      string `json:"word,omitempty"`
	Procletic string `json:"procletic,omitempty"`
	Tags      string `json:"tags,omitempty"`
	Vocalized string `json:"vocalized,omitempty"`
	Stem      string `json:"stem,omitempty"`
	Type      string `json:"type,omitempty"`
	Original  string `json:"original,omitempty"`
	Encletic  string `json:"encletic,omitempty"`
}

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL