clerk/internal/lsp/lsputil/utf16.go (view raw)
| 1 | package lsputil |
| 2 | |
| 3 | import "unicode/utf8" |
| 4 | |
| 5 | // Utf16Col returns the UTF-16 code unit column (0-based) for a byte offset |
| 6 | // within the given line content (without newline). |
| 7 | func Utf16Col(line string, byteOffset int) int { |
| 8 | if byteOffset <= 0 { |
| 9 | return 0 |
| 10 | } |
| 11 | if byteOffset > len(line) { |
| 12 | byteOffset = len(line) |
| 13 | } |
| 14 | col := 0 |
| 15 | for i := 0; i < byteOffset; { |
| 16 | r, size := utf8.DecodeRuneInString(line[i:]) |
| 17 | if r == utf8.RuneError && size <= 1 { |
| 18 | break |
| 19 | } |
| 20 | col += utf16Len(r) |
| 21 | i += size |
| 22 | } |
| 23 | return col |
| 24 | } |
| 25 | |
| 26 | // Utf16Len returns the UTF-16 code unit length of content[offset:end]. |
| 27 | func Utf16Len(content string, offset, end int) int { |
| 28 | if offset < 0 { |
| 29 | offset = 0 |
| 30 | } |
| 31 | if end > len(content) { |
| 32 | end = len(content) |
| 33 | } |
| 34 | if offset >= end { |
| 35 | return 0 |
| 36 | } |
| 37 | n := 0 |
| 38 | for i := offset; i < end; { |
| 39 | r, size := utf8.DecodeRuneInString(content[i:]) |
| 40 | if r == utf8.RuneError && size <= 1 { |
| 41 | break |
| 42 | } |
| 43 | n += utf16Len(r) |
| 44 | i += size |
| 45 | } |
| 46 | return n |
| 47 | } |
| 48 | |
| 49 | // LineCol converts a byte offset in content to 0-based line number and |
| 50 | // UTF-16 code unit column. |
| 51 | func LineCol(content string, offset int) (line int, col int) { |
| 52 | if offset <= 0 { |
| 53 | return 0, 0 |
| 54 | } |
| 55 | if offset > len(content) { |
| 56 | offset = len(content) |
| 57 | } |
| 58 | lineStart := 0 |
| 59 | lineNum := 0 |
| 60 | for i := 0; i < len(content); { |
| 61 | r, size := utf8.DecodeRuneInString(content[i:]) |
| 62 | if r == utf8.RuneError && size <= 1 { |
| 63 | break |
| 64 | } |
| 65 | if r == '\n' { |
| 66 | if offset < i+size { |
| 67 | col = Utf16Col(content[lineStart:offset], offset-lineStart) |
| 68 | return lineNum, col |
| 69 | } |
| 70 | lineStart = i + size |
| 71 | lineNum++ |
| 72 | i += size |
| 73 | continue |
| 74 | } |
| 75 | if r == '\r' { |
| 76 | // skip \r\n |
| 77 | if i+1 < len(content) && content[i+1] == '\n' { |
| 78 | size++ |
| 79 | } |
| 80 | if offset < i+size { |
| 81 | col = Utf16Col(content[lineStart:offset], offset-lineStart) |
| 82 | return lineNum, col |
| 83 | } |
| 84 | lineStart = i + size |
| 85 | lineNum++ |
| 86 | i += size |
| 87 | continue |
| 88 | } |
| 89 | if i+size > offset { |
| 90 | col = Utf16Col(content[lineStart:offset], offset-lineStart) |
| 91 | return lineNum, col |
| 92 | } |
| 93 | i += size |
| 94 | } |
| 95 | col = Utf16Col(content[lineStart:], len(content)-lineStart) |
| 96 | return lineNum, col |
| 97 | } |
| 98 | |
| 99 | // utf16Len returns the number of UTF-16 code units for a rune. |
| 100 | func utf16Len(r rune) int { |
| 101 | if r >= 0x10000 && r <= 0x10FFFF { |
| 102 | return 2 |
| 103 | } |
| 104 | return 1 |
| 105 | } |