icanhazwordz

README

icanhazwordz

does this string contain words?

package main

import (
	"fmt"

	"github.com/zricethezav/icanhazwordz"
)

func main() {
	searcher := icanhazwordz.NewSearcher(icanhazwordz.Filter{
		MinLength: 3,
		MaxLength: 4,
	})
	result := searcher.Find("The quick brown fox jumps over the lazy dog")
	for _, m := range result.Matches {
		fmt.Println(m.Word)
	}

    fmt.Println("---")
    seracher.Filter =
	searcher := icanhazwordz.NewSearcher(icanhazwordz.Filter{
		MinLength: 3,
		MaxLength: 4,
        PreferLongestNonOverlapping: true,
	})
	result := searcher.Find("The quick brown fox jumps over the lazy dog")
	for _, m := range result.Matches {
		fmt.Println(m.Word)
	}
}

Output:

the
brow
row
own
fox
jump
ump
over
the
laz
lazy
dog
---
the
brow
fox
jump
over
the
lazy
dog

Shoutout to the 🐐, github.com/BobuSumisu/aho-corasick

---

Folks, it's MIT

Documentation

Index

• Variables
• type Filter
• type Match
• type Result
• type Searcher
  • func NewSearcher(filter Filter) *Searcher
  • func (s *Searcher) Find(text string) Result
  • func (s *Searcher) GetWordCount() int
  • func (s *Searcher) GetWords() []string

Variables

var DefaultFilter = Filter{MinLength: 2, MaxLength: 0, PreferLongestNonOverlapping: false}

Default filter ignores single character words. If you want to include them, set MinLength to 1.

Types

type Filter

type Filter struct {
	MinLength                   int  // Minimum word length (inclusive)
	MaxLength                   int  // Maximum word length (inclusive, 0 means no limit)
	ExactLength                 int  // Exact word length (0 means no exact match required)
	PreferLongestNonOverlapping bool // Prefer longest non-overlapping matches. e.g. "hello" vs "hell"
}

Filter defines criteria for filtering words

type Match

type Match struct {
	Word     string `json:"word"`
	StartPos int    `json:"start_pos"`
	EndPos   int    `json:"end_pos"`
}

Match represents a found word match

type Result

type Result struct {
	WordCount   int      `json:"word_count"`
	UniqueWords []string `json:"unique_words"`
	Matches     []Match  `json:"matches"`
}

Result represents the result of English word detection

type Searcher

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

Searcher provides nltk English word detection with configurable filters

func NewSearcher

func NewSearcher(filter Filter) *Searcher

NewSearcher creates a new searcher with the specified word filters

func (*Searcher) Find

func (s *Searcher) Find(text string) Result

Find analyzes text using this searcher's word list

func (*Searcher) GetWordCount

func (s *Searcher) GetWordCount() int

GetWordCount returns the number of words in this searcher's dictionary

func (*Searcher) GetWords

func (s *Searcher) GetWords() []string

GetWords returns all words in this searcher's dictionary