https://www.unicode.org/Public/15.1.0/ucd/EquivalentUnifiedIdeograph.
2E81 ; 5382 # CJK RADICAL CLIFF
2E82 ; 4E5B # CJK RADICAL SECOND ONE
# ...
2ED5 ; 28E0F # CJK RADICAL MOUND ONE
2E8C..2E8D ; 5C0F # [2] CJK RADICAL SMALL ONE..CJK RADICAL SMALL TWO
| package main | |
| import ( | |
| "fmt" | |
| "regexp" | |
| "strconv" | |
| "strings" | |
| ) | |
| func main() { | |
| EquivalentUnifiedIdeograph() | |
| } | |
| func EquivalentUnifiedIdeograph() { | |
| const data = ` | |
| 2E81 ; 5382 # CJK RADICAL CLIFF | |
| 2E82 ; 4E5B # CJK RADICAL SECOND ONE | |
| # ... | |
| 2ED5 ; 28E0F # CJK RADICAL MOUND ONE | |
| 2E8C..2E8D ; 5C0F # [2] CJK RADICAL SMALL ONE..CJK RADICAL SMALL TWO | |
| ` | |
| lines := strings.Split(data, "\n") | |
| re := regexp.MustCompile(`(\w+(?:\.\.\w+)?)\s*;\s*(\w+)\s*#\s*(.+)`) | |
| for _, line := range lines { | |
| if strings.HasPrefix(line, "#") || line == "" { | |
| // 跳過註解或者空行 | |
| continue | |
| } | |
| m := re.FindStringSubmatch(line) | |
| if strings.Contains(m[1], "..") { | |
| // 表示是一個區間 | |
| elem := strings.Split(m[1], "..") | |
| start := str2hex(elem[0]) | |
| end := str2hex(elem[1]) | |
| for codepoint := start; codepoint <= end; codepoint++ { | |
| fmt.Printf("%c (%04X)\t%c (%04X)\t%s\n", | |
| rune(codepoint), codepoint, | |
| rune(str2hex(m[2])), str2hex(m[2]), | |
| m[3], | |
| ) | |
| } | |
| } else { | |
| fmt.Printf("%c (%04X)\t%c (%04X)\t%s\n", | |
| rune(str2hex(m[1])), m[1], | |
| rune(str2hex(m[2])), str2hex(m[2]), | |
| m[3], | |
| ) | |
| } | |
| } | |
| } | |
| func str2hex(str string) int64 { | |
| out, err := strconv.ParseInt(str, | |
| 16, // 字串的基底是指16進位 | |
| 32, // 32 bit就夠用了 | |
| ) | |
| if err != nil { | |
| panic(err) | |
| } | |
| return out | |
| } |