src

Go monorepo.
git clone git://code.dwrz.net/src
Log | Files | Refs

word.go (2656B)


      1 package uniseg
      2 
      3 import "unicode/utf8"
      4 
      5 // FirstWord returns the first word found in the given byte slice according to
      6 // the rules of [Unicode Standard Annex #29, Word Boundaries]. This function can
      7 // be called continuously to extract all words from a byte slice, as illustrated
      8 // in the example below.
      9 //
     10 // If you don't know the current state, for example when calling the function
     11 // for the first time, you must pass -1. For consecutive calls, pass the state
     12 // and rest slice returned by the previous call.
     13 //
     14 // The "rest" slice is the sub-slice of the original byte slice "b" starting
     15 // after the last byte of the identified word. If the length of the "rest" slice
     16 // is 0, the entire byte slice "b" has been processed. The "word" byte slice is
     17 // the sub-slice of the input slice containing the identified word.
     18 //
     19 // Given an empty byte slice "b", the function returns nil values.
     20 //
     21 // [Unicode Standard Annex #29, Word Boundaries]: http://unicode.org/reports/tr29/#Word_Boundaries
     22 func FirstWord(b []byte, state int) (word, rest []byte, newState int) {
     23 	// An empty byte slice returns nothing.
     24 	if len(b) == 0 {
     25 		return
     26 	}
     27 
     28 	// Extract the first rune.
     29 	r, length := utf8.DecodeRune(b)
     30 	if len(b) <= length { // If we're already past the end, there is nothing else to parse.
     31 		return b, nil, wbAny
     32 	}
     33 
     34 	// If we don't know the state, determine it now.
     35 	if state < 0 {
     36 		state, _ = transitionWordBreakState(state, r, b[length:], "")
     37 	}
     38 
     39 	// Transition until we find a boundary.
     40 	var boundary bool
     41 	for {
     42 		r, l := utf8.DecodeRune(b[length:])
     43 		state, boundary = transitionWordBreakState(state, r, b[length+l:], "")
     44 
     45 		if boundary {
     46 			return b[:length], b[length:], state
     47 		}
     48 
     49 		length += l
     50 		if len(b) <= length {
     51 			return b, nil, wbAny
     52 		}
     53 	}
     54 }
     55 
     56 // FirstWordInString is like [FirstWord] but its input and outputs are strings.
     57 func FirstWordInString(str string, state int) (word, rest string, newState int) {
     58 	// An empty byte slice returns nothing.
     59 	if len(str) == 0 {
     60 		return
     61 	}
     62 
     63 	// Extract the first rune.
     64 	r, length := utf8.DecodeRuneInString(str)
     65 	if len(str) <= length { // If we're already past the end, there is nothing else to parse.
     66 		return str, "", wbAny
     67 	}
     68 
     69 	// If we don't know the state, determine it now.
     70 	if state < 0 {
     71 		state, _ = transitionWordBreakState(state, r, nil, str[length:])
     72 	}
     73 
     74 	// Transition until we find a boundary.
     75 	var boundary bool
     76 	for {
     77 		r, l := utf8.DecodeRuneInString(str[length:])
     78 		state, boundary = transitionWordBreakState(state, r, nil, str[length+l:])
     79 
     80 		if boundary {
     81 			return str[:length], str[length:], state
     82 		}
     83 
     84 		length += l
     85 		if len(str) <= length {
     86 			return str, "", wbAny
     87 		}
     88 	}
     89 }