floraachy
/
vChewing-macOS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

UPE // UTF8 Surrogate Pair Issue Fix. 

- We don't use RegEx to remove the trailing spaces of each lines anymore. Reason: Swift built-in RegEx relies on NSRange which has no UTF8 surrogate pair support, leading to incorrectly-calculated modification spot when dealing with lines that contains surrogate-pair characters.
- Also optimized the format-consolidating process.
This commit is contained in:
ShikiSuen 2022-02-26 14:28:03 +08:00
parent 9a8c720632
commit f971339f3e
1 changed files with 19 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
UserPhraseEditor/StringExtension.swift
View File

@ -28,26 +28,31 @@ extension String {
} }
mutating func formatConsolidate(HYPY2BPMF: Bool) { mutating func formatConsolidate(HYPY2BPMF: Bool) {
// Step 1: Consolidating formats per line. // Step 1: Consolidating formats per line.
var arrData = self.components(separatedBy: "\n") var strProcessed = self
var varLineData = "" // 預處理格式
var strProcessed = "" strProcessed = strProcessed.replacingOccurrences(of: " #MACOS", with: "") // 去掉 macOS 標記
for lineData in arrData { strProcessed = strProcessed.replacingOccurrences(of: "　", with: " ") // CJKWhiteSpace (\x{3000}) to ASCII Space
varLineData = lineData strProcessed = strProcessed.replacingOccurrences(of: " ", with: " ") // NonBreakWhiteSpace (\x{A0}) to ASCII Space
varLineData.regReplace(pattern: "　", replaceWith: " ") // CJKWhiteSpace to ASCIISpace strProcessed = strProcessed.replacingOccurrences(of: "\t", with: " ") // Tab to ASCII Space
varLineData.regReplace(pattern: " ", replaceWith: " ") // NonBreakWhiteSpace to ASCIISpace strProcessed.regReplace(pattern: "\\f", replaceWith: "\n") // Form Feed to LF
varLineData.regReplace(pattern: "\\s+", replaceWith: " ") // Consolidating Consecutive Spaves strProcessed = strProcessed.replacingOccurrences(of: "\r", with: "\n") // CR to LF
varLineData.regReplace(pattern: "^\\s", replaceWith: "") // Trim Leading Space strProcessed.regReplace(pattern: " +", replaceWith: " ") // 統整連續空格為一個 ASCII 空格
varLineData.regReplace(pattern: "\\s$", replaceWith: "") // Trim Trailing Space strProcessed.regReplace(pattern: "\\n+", replaceWith: "\n") // 統整連續 LF 為一個 LF
strProcessed += varLineData strProcessed = strProcessed.replacingOccurrences(of: " \n", with: "\n") // 去除行尾空格
strProcessed += "\n" strProcessed = strProcessed.replacingOccurrences(of: "\n ", with: "\n") // 去除行首空格
if strProcessed.prefix(1) == " " { // 去除檔案開頭空格
strProcessed.removeFirst()
} }
if strProcessed.suffix(1) == " " { // 去除檔案結尾空格
strProcessed.removeLast()
}
var arrData = [""]
if HYPY2BPMF { if HYPY2BPMF {
// Step 0: Convert HanyuPinyin to Bopomofo. // Step 0: Convert HanyuPinyin to Bopomofo.
arrData = strProcessed.components(separatedBy: "\n") arrData = strProcessed.components(separatedBy: "\n")
strProcessed = "" // Reset its value strProcessed = "" // Reset its value
for lineData in arrData { for lineData in arrData {
varLineData = lineData var varLineData = lineData
// 漢語拼音轉注音，得先從最長的可能的拼音組合開始轉起， // 漢語拼音轉注音，得先從最長的可能的拼音組合開始轉起，
// 這樣等轉換到更短的可能的漢語拼音組合時就不會出錯。 // 這樣等轉換到更短的可能的漢語拼音組合時就不會出錯。
// 依此類推，聲調放在最後來轉換。 // 依此類推，聲調放在最後來轉換。