fold.go

Documentation: github.com/evanphx/json-patch/v5/internal/json

     1  // Copyright 2013 The Go Authors. All rights reserved.
     2  // Use of this source code is governed by a BSD-style
     3  // license that can be found in the LICENSE file.
     4  
     5  package json
     6  
     7  import (
     8  	"bytes"
     9  	"unicode/utf8"
    10  )
    11  
    12  const (
    13  	caseMask     = ^byte(0x20) // Mask to ignore case in ASCII.
    14  	kelvin       = '\u212a'
    15  	smallLongEss = '\u017f'
    16  )
    17  
    18  // foldFunc returns one of four different case folding equivalence
    19  // functions, from most general (and slow) to fastest:
    20  //
    21  // 1) bytes.EqualFold, if the key s contains any non-ASCII UTF-8
    22  // 2) equalFoldRight, if s contains special folding ASCII ('k', 'K', 's', 'S')
    23  // 3) asciiEqualFold, no special, but includes non-letters (including _)
    24  // 4) simpleLetterEqualFold, no specials, no non-letters.
    25  //
    26  // The letters S and K are special because they map to 3 runes, not just 2:
    27  //   - S maps to s and to U+017F 'ſ' Latin small letter long s
    28  //   - k maps to K and to U+212A 'K' Kelvin sign
    29  //
    30  // See https://play.golang.org/p/tTxjOc0OGo
    31  //
    32  // The returned function is specialized for matching against s and
    33  // should only be given s. It's not curried for performance reasons.
    34  func foldFunc(s []byte) func(s, t []byte) bool {
    35  	nonLetter := false
    36  	special := false // special letter
    37  	for _, b := range s {
    38  		if b >= utf8.RuneSelf {
    39  			return bytes.EqualFold
    40  		}
    41  		upper := b & caseMask
    42  		if upper < 'A' || upper > 'Z' {
    43  			nonLetter = true
    44  		} else if upper == 'K' || upper == 'S' {
    45  			// See above for why these letters are special.
    46  			special = true
    47  		}
    48  	}
    49  	if special {
    50  		return equalFoldRight
    51  	}
    52  	if nonLetter {
    53  		return asciiEqualFold
    54  	}
    55  	return simpleLetterEqualFold
    56  }
    57  
    58  // equalFoldRight is a specialization of bytes.EqualFold when s is
    59  // known to be all ASCII (including punctuation), but contains an 's',
    60  // 'S', 'k', or 'K', requiring a Unicode fold on the bytes in t.
    61  // See comments on foldFunc.
    62  func equalFoldRight(s, t []byte) bool {
    63  	for _, sb := range s {
    64  		if len(t) == 0 {
    65  			return false
    66  		}
    67  		tb := t[0]
    68  		if tb < utf8.RuneSelf {
    69  			if sb != tb {
    70  				sbUpper := sb & caseMask
    71  				if 'A' <= sbUpper && sbUpper <= 'Z' {
    72  					if sbUpper != tb&caseMask {
    73  						return false
    74  					}
    75  				} else {
    76  					return false
    77  				}
    78  			}
    79  			t = t[1:]
    80  			continue
    81  		}
    82  		// sb is ASCII and t is not. t must be either kelvin
    83  		// sign or long s; sb must be s, S, k, or K.
    84  		tr, size := utf8.DecodeRune(t)
    85  		switch sb {
    86  		case 's', 'S':
    87  			if tr != smallLongEss {
    88  				return false
    89  			}
    90  		case 'k', 'K':
    91  			if tr != kelvin {
    92  				return false
    93  			}
    94  		default:
    95  			return false
    96  		}
    97  		t = t[size:]
    98  
    99  	}
   100  	return len(t) == 0
   101  }
   102  
   103  // asciiEqualFold is a specialization of bytes.EqualFold for use when
   104  // s is all ASCII (but may contain non-letters) and contains no
   105  // special-folding letters.
   106  // See comments on foldFunc.
   107  func asciiEqualFold(s, t []byte) bool {
   108  	if len(s) != len(t) {
   109  		return false
   110  	}
   111  	for i, sb := range s {
   112  		tb := t[i]
   113  		if sb == tb {
   114  			continue
   115  		}
   116  		if ('a' <= sb && sb <= 'z') || ('A' <= sb && sb <= 'Z') {
   117  			if sb&caseMask != tb&caseMask {
   118  				return false
   119  			}
   120  		} else {
   121  			return false
   122  		}
   123  	}
   124  	return true
   125  }
   126  
   127  // simpleLetterEqualFold is a specialization of bytes.EqualFold for
   128  // use when s is all ASCII letters (no underscores, etc) and also
   129  // doesn't contain 'k', 'K', 's', or 'S'.
   130  // See comments on foldFunc.
   131  func simpleLetterEqualFold(s, t []byte) bool {
   132  	if len(s) != len(t) {
   133  		return false
   134  	}
   135  	for i, b := range s {
   136  		if b&caseMask != t[i]&caseMask {
   137  			return false
   138  		}
   139  	}
   140  	return true
   141  }
   142
View as plain text