[SOAR-0001] Implement Encoding for Property Names (#89)

## Motivation

Encoding would help distinguish types properly. For eg. both `a b` and
`a_b` would be rendered as `a_b`. This change would make it render
`a20b` and `a_b` respectively.

## Modifications

Added a hexadecimal encoding for un-supported characters rather than
having just an underscore for everything.
Removed redundant keywords.

## Result
Proper differentiation between names as explained in the motivation,
along with that, it also reduces the reserved keywords set by removing
symbols and any keywords that prepend such symbols.

## Test Plan
Tested and verified for several combinations of special characters in
various positions in-between alphanumeric characters.

---------

Co-authored-by: Honza Dvorsky <[email protected]>

Author: denil-ct

Sources/_OpenAPIGeneratorCore/Translator/CommonTranslations/SwiftSafeNames.swift

@@ -74,11 +74,62 @@ fileprivate extension String {
     ///
     /// See the proposal SOAR-0001 for details.
     ///
-    /// In addition to replacing illegal characters with an underscores, also
+    /// For example, the string `$nake…` would be returned as `_dollar_nake_x2026_`, because
+    /// both the dollar and ellipsis sign are not valid characters in a Swift identifier.
+    /// So, it replaces such characters with their html entity equivalents or unicode hex representation,
+    /// in case it's not present in the `specialCharsMap`. It marks this replacement with `_` as a delimiter.
+    ///
+    /// In addition to replacing illegal characters, it also
     /// ensures that the identifier starts with a letter and not a number.
     var proposedSafeForSwiftCode: String {
-        // TODO: New logic proposed in SOAR-0001 goes here.
-        return ""
+        guard !isEmpty else {
+            return "_empty"
+        }
+
+        let firstCharSet: CharacterSet = .letters.union(.init(charactersIn: "_"))
+        let numbers: CharacterSet = .decimalDigits
+        let otherCharSet: CharacterSet = .alphanumerics.union(.init(charactersIn: "_"))
+
+        var sanitizedScalars: [Unicode.Scalar] = []
+        for (index, scalar) in unicodeScalars.enumerated() {
+            let allowedSet = index == 0 ? firstCharSet : otherCharSet
+            let outScalar: Unicode.Scalar
+            if allowedSet.contains(scalar) {
+                outScalar = scalar
+            } else if index == 0 && numbers.contains(scalar) {
+                sanitizedScalars.append("_")
+                outScalar = scalar
+            } else {
+                sanitizedScalars.append("_")
+                if let entityName = Self.specialCharsMap[scalar] {
+                    for char in entityName.unicodeScalars {
+                        sanitizedScalars.append(char)
+                    }
+                } else {
+                    sanitizedScalars.append("x")
+                    let hexString = String(scalar.value, radix: 16, uppercase: true)
+                    for char in hexString.unicodeScalars {
+                        sanitizedScalars.append(char)
+                    }
+                }
+                sanitizedScalars.append("_")
+                continue
+            }
+            sanitizedScalars.append(outScalar)
+        }
+
+        let validString = String(UnicodeScalarView(sanitizedScalars))
+
+        //Special case for a single underscore.
+        //We can't add it to the map as its a valid swift identifier in other cases.
+        if validString == "_" {
+            return "_underscore_"
+        }
+
+        guard Self.keywords.contains(validString) else {
+            return validString
+        }
+        return "_\(validString)"
     }
 
     /// A list of Swift keywords.
@@ -138,62 +189,6 @@ fileprivate extension String {
         "true",
         "try",
         "throws",
-        "__FILE__",
-        "__LINE__",
-        "__COLUMN__",
-        "__FUNCTION__",
-        "__DSO_HANDLE__",
-        "_",
-        "(",
-        ")",
-        "{",
-        "}",
-        "[",
-        "]",
-        "<",
-        ">",
-        ".",
-        ".",
-        ",",
-        "...",
-        ":",
-        ";",
-        "=",
-        "@",
-        "#",
-        "&",
-        "->",
-        "`",
-        "\\",
-        "!",
-        "?",
-        "?",
-        "\"",
-        "\'",
-        "\"\"\"",
-        "#keyPath",
-        "#line",
-        "#selector",
-        "#file",
-        "#fileID",
-        "#filePath",
-        "#column",
-        "#function",
-        "#dsohandle",
-        "#assert",
-        "#sourceLocation",
-        "#warning",
-        "#error",
-        "#if",
-        "#else",
-        "#elseif",
-        "#endif",
-        "#available",
-        "#unavailable",
-        "#fileLiteral",
-        "#imageLiteral",
-        "#colorLiteral",
-        ")",
         "yield",
         "String",
         "Error",
@@ -205,4 +200,40 @@ fileprivate extension String {
         "Protocol",
         "await",
     ]
+
+    /// A map of ASCII printable characters to their HTML entity names. Used to reduce collisions in generated names.
+    private static let specialCharsMap: [Unicode.Scalar: String] = [
+        " ": "space",
+        "!": "excl",
+        "\"": "quot",
+        "#": "num",
+        "$": "dollar",
+        "%": "percnt",
+        "&": "amp",
+        "'": "apos",
+        "(": "lpar",
+        ")": "rpar",
+        "*": "ast",
+        "+": "plus",
+        ",": "comma",
+        "-": "hyphen",
+        ".": "period",
+        "/": "sol",
+        ":": "colon",
+        ";": "semi",
+        "<": "lt",
+        "=": "equals",
+        ">": "gt",
+        "?": "quest",
+        "@": "commat",
+        "[": "lbrack",
+        "\\": "bsol",
+        "]": "rbrack",
+        "^": "hat",
+        "`": "grave",
+        "{": "lcub",
+        "|": "verbar",
+        "}": "rcub",
+        "~": "tilde",
+    ]
 }

Tests/OpenAPIGeneratorCoreTests/Extensions/Test_String.swift

@@ -39,4 +39,55 @@ final class Test_String: Test_Core {
             XCTAssertEqual(asSwiftSafeName(input), sanitized)
         }
     }
+
+    func testAsProposedSwiftName() {
+        let cases: [(String, String)] = [
+            // Simple
+            ("foo", "foo"),
+
+            // Starts with a number
+            ("3foo", "_3foo"),
+
+            // Keyword
+            ("default", "_default"),
+
+            // Reserved name
+            ("Type", "_Type"),
+
+            // Empty string
+            ("", "_empty"),
+
+            // Special Char in middle
+            ("inv@lidName", "inv_commat_lidName"),
+
+            // Special Char in first position
+            ("!nvalidName", "_excl_nvalidName"),
+
+            // Special Char in last position
+            ("invalidNam?", "invalidNam_quest_"),
+
+            // Valid underscore case
+            ("__user", "__user"),
+
+            // Invalid underscore case
+            ("_", "_underscore_"),
+
+            // Special character mixed with character not in map
+            ("$nake…", "_dollar_nake_x2026_"),
+
+            // Only special character
+            ("$", "_dollar_"),
+
+            // Only special character not in map
+            ("……", "_x2026__x2026_"),
+
+            // Non Latin Characters
+            ("$مرحبا", "_dollar_مرحبا"),
+        ]
+        let translator = makeTranslator(featureFlags: [.proposal0001])
+        let asSwiftSafeName: (String) -> String = translator.swiftSafeName
+        for (input, sanitized) in cases {
+            XCTAssertEqual(asSwiftSafeName(input), sanitized)
+        }
+    }
 }