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

[Experimental] ConvertGraphを実装し、その上での完全一致変換を実装 (#47)

Browse Source 
* ConvertGraphを実装し、その上での完全一致変換を実装

* 名前空間を汚染していたので修正

* Implementation completed (without test)

* move directory to use default dictionary

* fix implementations to enable conversion

* add test cases

* Backward searchで発見された候補を明示的に削除

* fix tests

* simplify
This commit is contained in:
Miwa / Ensan
2024-02-24 23:21:44 +09:00
committed by GitHub
parent 52fc9ae4c2
commit 0795b8cf84
15 changed files with 706 additions and 327 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
Sources/KanaKanjiConverterModule/DicdataStore/DicdataStore.swift
View File

@ -102,6 +102,10 @@ public final class DicdataStore {
}
}
func character2charId(_ character: Character) -> UInt8 {
self.charsID[character, default: .max]
}
private func reloadMemory() {
self.loudses.removeValue(forKey: "memory")
self.importedLoudses.remove("memory")
@ -143,7 +147,7 @@ public final class DicdataStore {
return Self.getPenalty(data: data) < -d
}
private func loadLOUDS(identifier: String) -> LOUDS? {
func loadLOUDS(identifier: String) -> LOUDS? {
if importedLoudses.contains(identifier) {
return self.loudses[identifier]
}
@ -213,7 +217,7 @@ public final class DicdataStore {
var stringToInfo = inputData.getRangesWithTypos(fromIndex, rightIndexRange: toIndexLeft ..< toIndexRight)
// MARK: 検索対象を列挙していく。
let stringSet = stringToInfo.keys.map {($0, $0.map {self.charsID[$0, default: .max]})}
let stringSet = stringToInfo.keys.map {($0, $0.map(self.character2charId))}
let (minCharIDsCount, maxCharIDsCount) = stringSet.lazy.map {$0.1.count}.minAndMax() ?? (0, -1)
// 先頭の文字: そこで検索したい文字列の集合
let group = [Character: [([Character], [UInt8])]].init(grouping: stringSet, by: {$0.0.first!})
@ -318,7 +322,7 @@ public final class DicdataStore {
// MARK: 検索によって得たindicesから辞書データを実際に取り出していく
// 先頭の文字: そこで検索したい文字列の集合
let strings = string2penalty.keys.map {
(key: $0, charIDs: $0.map {self.charsID[$0, default: .max]})
(key: $0, charIDs: $0.map(self.character2charId))
}
let group = [Character: [(key: [Character], charIDs: [UInt8])]].init(grouping: strings, by: {$0.key.first!})
@ -433,7 +437,7 @@ public final class DicdataStore {
} else if count == 2 {
var result: [DicdataElement] = []
let first = String(key.first!)
let charIDs = key.map {self.charsID[$0, default: .max]}
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(
@ -451,7 +455,7 @@ public final class DicdataStore {
} else {
var result: [DicdataElement] = []
let first = String(key.first!)
let charIDs = key.map {self.charsID[$0, default: .max]}
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(