mii/AzooKeyKanaKanjiConverter
1
0
Fork 0
mirror of https://github.com/mii443/AzooKeyKanaKanjiConverter.git synced 2025-08-22 15:05:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #51 from ensan-hcl/feature/simplified_prediction

Browse Source 
[Feature] 予測変換用の辞書検索を単純化
This commit is contained in:
Miwa / Ensan
2024-02-29 01:56:02 +09:00
committed by GitHub
parent 81c3324a66 bf1cb13631
commit 77bc115345
1 changed files with 21 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
Sources/KanaKanjiConverterModule/DicdataStore/DicdataStore.swift
View File

@ -420,57 +420,29 @@ public final class DicdataStore {
if count == .zero {
return []
}
// 1文字に対する予測変換は検索が難しいので、特別に用意した辞書を用いて実施する
if count == 1 {
do {
let csvString = try String(contentsOf: requestOptions.dictionaryResourceURL.appendingPathComponent("p/p_\(key).csv", isDirectory: false), encoding: String.Encoding.utf8)
let csvLines = csvString.split(separator: "\n")
let csvData = csvLines.map {$0.split(separator: ",", omittingEmptySubsequences: false)}
let dicdata: [DicdataElement] = csvData
.map {self.parseLoudstxt2FormattedEntry(from: $0)}
.filter { Self.predictionUsable[$0.rcid] }
return dicdata
} catch {
debug("ファイルが存在しません: \(error)")
return []
}
} else if count == 2 {
var result: [DicdataElement] = []
let first = String(key.first!)
let charIDs = key.map(self.character2charId)
// 最大700件に絞ることによって低速化を回避する。
let prefixIndices = self.prefixMatchLOUDS(identifier: first, charIDs: charIDs, depth: 5).prefix(700)
result.append(
contentsOf: self.getDicdataFromLoudstxt3(identifier: first, indices: Set(prefixIndices))
.filter { Self.predictionUsable[$0.rcid] }
)
let userDictIndices = self.prefixMatchLOUDS(identifier: "user", charIDs: charIDs, depth: 5).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "user", indices: Set(userDictIndices)))
if learningManager.enabled {
let memoryDictIndices = self.prefixMatchLOUDS(identifier: "memory", charIDs: charIDs, depth: 5).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "memory", indices: Set(memoryDictIndices)))
result.append(contentsOf: self.learningManager.temporaryPrefixMatch(charIDs: charIDs))
}
return result
// 最大700件に絞ることによって低速化を回避する。
var result: [DicdataElement] = []
let first = String(key.first!)
let charIDs = key.map(self.character2charId)
// 1, 2文字に対する予測変換は候補数が大きいので、depth（〜文字数）を制限する
let depth = if count == 1 || count == 2 {
5
} else {
var result: [DicdataElement] = []
let first = String(key.first!)
let charIDs = key.map(self.character2charId)
// 最大700件に絞ることによって低速化を回避する。
let prefixIndices = self.prefixMatchLOUDS(identifier: first, charIDs: charIDs).prefix(700)
result.append(
contentsOf: self.getDicdataFromLoudstxt3(identifier: first, indices: Set(prefixIndices))
.filter { Self.predictionUsable[$0.rcid] }
)
let userDictIndices = self.prefixMatchLOUDS(identifier: "user", charIDs: charIDs).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "user", indices: Set(userDictIndices)))
if learningManager.enabled {
let memoryDictIndices = self.prefixMatchLOUDS(identifier: "memory", charIDs: charIDs).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "memory", indices: Set(memoryDictIndices)))
result.append(contentsOf: self.learningManager.temporaryPrefixMatch(charIDs: charIDs))
}
return result
Int.max
}
let prefixIndices = self.prefixMatchLOUDS(identifier: first, charIDs: charIDs, depth: depth).prefix(700)
result.append(
contentsOf: self.getDicdataFromLoudstxt3(identifier: first, indices: Set(consume prefixIndices))
.filter { Self.predictionUsable[$0.rcid] }
)
let userDictIndices = self.prefixMatchLOUDS(identifier: "user", charIDs: charIDs, depth: depth).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "user", indices: Set(consume userDictIndices)))
if learningManager.enabled {
let memoryDictIndices = self.prefixMatchLOUDS(identifier: "memory", charIDs: charIDs).prefix(700)
result.append(contentsOf: self.getDicdataFromLoudstxt3(identifier: "memory", indices: Set(consume memoryDictIndices)))
result.append(contentsOf: self.learningManager.temporaryPrefixMatch(charIDs: charIDs))
}
return result
}
private func parseLoudstxt2FormattedEntry(from dataString: [some StringProtocol]) -> DicdataElement {