fix: CFI module — 11 issues from code review

Phase 1 (correctness): - #1: rawValue changed from stored to computed property, eliminating stale cache risk - #2: tokenSamples/textMarker unified to UTF-16 offsets, fixing emoji/CJK positioning - #3: makeOffsetCFI now accepts optional contentPath parameter Phase 2 (robustness): - #4: Resolver uses fixed index access instead of last(where:) for manifest/spine steps - #5: HTML comments and CDATA stripped before regex matching - #6: Text assertion parser handles backslash escapes (\[ \] \) - #7: Token matching uses prefix/suffix with length ratio constraints - #8: makeOffsetRangeCFI validates startOffset <= endOffset Phase 3 (code quality): - #9: Shared internal nilIfEmpty extension in RDEPUBCFIUtilities.swift - #10: RDEPUBCFIMap has markerByPath index dictionary for O(1) lookup - #11: parseRange unified to use try (not try?) for parent parsing Review fixes: - Documented init(rawValue:) parameter is ignored (computed property) - Fixed escape unescaping to handle \\ → \ correctly - Lowered token minLength threshold from 4 to 2 Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-18 13:25:17 +08:00
parent 6ed3fcb071
commit f50495ad91
15 changed files with 1959 additions and 49 deletions
@@ -0,0 +1,52 @@
+import Foundation
+
+public struct RDEPUBCFI: Codable, Equatable, Hashable {
+    public var packagePath: RDEPUBCFIPath
+    public var contentPath: RDEPUBCFIPath
+    public var characterOffset: Int?
+    public var sideBias: RDEPUBCFISideBias?
+    public var textAssertion: RDEPUBCFITextAssertion?
+
+    /// Always computed from components — no stale cached value risk.
+    public var rawValue: String {
+        RDEPUBCFISerializer.serialize(self)
+    }
+
+    /// Initialize from components. The `rawValue` parameter is ignored — rawValue is always
+    /// computed from the components. To parse a CFI string, use `RDEPUBCFIParser.parse(_:)`.
+    public init(
+        rawValue: String = "",
+        packagePath: RDEPUBCFIPath = RDEPUBCFIPath(),
+        contentPath: RDEPUBCFIPath = RDEPUBCFIPath(),
+        characterOffset: Int? = nil,
+        sideBias: RDEPUBCFISideBias? = nil,
+        textAssertion: RDEPUBCFITextAssertion? = nil
+    ) {
+        self.packagePath = packagePath
+        self.contentPath = contentPath
+        self.characterOffset = characterOffset
+        self.sideBias = sideBias
+        self.textAssertion = textAssertion
+    }
+
+    public init(from decoder: Decoder) throws {
+        let container = try decoder.singleValueContainer()
+        let rawValue = try container.decode(String.self)
+        let parsed = try RDEPUBCFIParser.parse(rawValue)
+        self.packagePath = parsed.packagePath
+        self.contentPath = parsed.contentPath
+        self.characterOffset = parsed.characterOffset
+        self.sideBias = parsed.sideBias
+        self.textAssertion = parsed.textAssertion
+    }
+
+    public func encode(to encoder: Encoder) throws {
+        var container = encoder.singleValueContainer()
+        try container.encode(rawValue)
+    }
+}
+
+public enum RDEPUBCFISideBias: String, Codable, Equatable, Hashable {
+    case before = "b"
+    case after = "a"
+}