Implement naming package, new IdentifierIntroduction.qll, unicode funcs.

Author: MichaelRFairhurst

cpp/common/src/codingstandards/cpp/Identifiers.qll

@@ -8,7 +8,11 @@ class FunctionLikeMacro extends Macro {
 
   string getParameter(int i) {
     result =
-      this.getHead().regexpCapture("[_a-zA-Z0-9]+\\s*\\(([^\\)]*)\\)", 1).splitAt(",", i).trim()
+      this.getHead()
+          .regexpCapture("[_a-zA-Z0-9]+\\s*\\(([^\\)]*)\\)", 1)
+          .splitAt(",", i)
+          .trim()
+          .replaceAll("...", "")
   }
 
   string getAParameter() { result = getParameter(_) }

cpp/common/src/codingstandards/cpp/Macro.qll

@@ -0,0 +1,65 @@
+import codeql.util.Numbers
+
+/**
+ * Provides properties of a Unicode code point, where the property is of 'enumeration', 'catalog',
+ * or 'string-valued' type, however, the only supported property is `NFC_QC`.
+ *
+ * For example, `Block` is an enumeration property, `Line_Break` is a catalog property, and
+ * `Uppercase_Mapping` is a string-valued property.
+ *
+ * For boolean properties, see `unicodeHasBooleanProperty`, and for numeric properties, see
+ * `unicodeHasNumericProperty`.
+ */
+extensible predicate unicodeHasProperty(int codePoint, string propertyName, string propertyValue);
+
+/**
+ * Holds when the Unicode code point's boolean property of the given name is true.
+ *
+ * For example, `Alphabetic` is a boolean property that can be true or false for a code point.
+ *
+ * For other types of properties, see `unicodeHasProperty`.
+ */
+extensible predicate unicodeHasBooleanProperty(int codePoint, string propertyName);
+
+bindingset[input]
+int unescapedCodePointAt(string input, int index) {
+  exists(string match |
+    match = input.regexpFind("(\\\\u[0-9a-fA-F]{4}|.)", index, _) and
+    if match.matches("\\u%")
+    then result = parseHexInt(match.substring(2, match.length()))
+    else result = match.codePointAt(0)
+  )
+}
+
+bindingset[input]
+string unescapeUnicode(string input) {
+  result =
+    concat(int code, int idx |
+      code = unescapedCodePointAt(input, idx)
+    |
+      code.toUnicode() order by idx
+    )
+}
+
+bindingset[id]
+predicate nonUax44IdentifierCodepoint(string id, int index) {
+  exists(int codePoint |
+    codePoint = id.codePointAt(index) and
+    (
+      not unicodeHasBooleanProperty(codePoint, "XID_Start") and
+      not unicodeHasBooleanProperty(codePoint, "XID_Continue")
+      or
+      index = 0 and
+      not unicodeHasBooleanProperty(codePoint, "XID_Start")
+    )
+  )
+}
+
+bindingset[id]
+predicate nonNfcNormalizedCodepoint(string id, int index, string noOrMaybe) {
+  exists(int codePoint |
+    codePoint = id.codePointAt(index) and
+    unicodeHasProperty(codePoint, "NFC_QC", noOrMaybe) and
+    noOrMaybe = ["N", "M"]
+  )
+}

cpp/common/src/codingstandards/cpp/Unicode.qll

@@ -0,0 +1,26 @@
+//** THIS FILE IS AUTOGENERATED, DO NOT MODIFY DIRECTLY.  **/
+import cpp
+import RuleMetadata
+import codingstandards.cpp.exclusions.RuleMetadata
+
+newtype Naming2Query = TPoorlyFormedIdentifierQuery()
+
+predicate isNaming2QueryMetadata(Query query, string queryId, string ruleId, string category) {
+  query =
+    // `Query` instance for the `poorlyFormedIdentifier` query
+    Naming2Package::poorlyFormedIdentifierQuery() and
+  queryId =
+    // `@id` for the `poorlyFormedIdentifier` query
+    "cpp/misra/poorly-formed-identifier" and
+  ruleId = "RULE-5-10-1" and
+  category = "required"
+}
+
+module Naming2Package {
+  Query poorlyFormedIdentifierQuery() {
+    //autogenerate `Query` type
+    result =
+      // `Query` type for `poorlyFormedIdentifier` query
+      TQueryCPP(TNaming2PackageQuery(TPoorlyFormedIdentifierQuery()))
+  }
+}

cpp/common/src/codingstandards/cpp/exclusions/cpp/Naming2.qll

@@ -35,6 +35,7 @@ import Loops
 import Macros
 import MoveForward
 import Naming
+import Naming2
 import Null
 import OperatorInvariants
 import Operators
@@ -90,6 +91,7 @@ newtype TCPPQuery =
   TMacrosPackageQuery(MacrosQuery q) or
   TMoveForwardPackageQuery(MoveForwardQuery q) or
   TNamingPackageQuery(NamingQuery q) or
+  TNaming2PackageQuery(Naming2Query q) or
   TNullPackageQuery(NullQuery q) or
   TOperatorInvariantsPackageQuery(OperatorInvariantsQuery q) or
   TOperatorsPackageQuery(OperatorsQuery q) or
@@ -145,6 +147,7 @@ predicate isQueryMetadata(Query query, string queryId, string ruleId, string cat
   isMacrosQueryMetadata(query, queryId, ruleId, category) or
   isMoveForwardQueryMetadata(query, queryId, ruleId, category) or
   isNamingQueryMetadata(query, queryId, ruleId, category) or
+  isNaming2QueryMetadata(query, queryId, ruleId, category) or
   isNullQueryMetadata(query, queryId, ruleId, category) or
   isOperatorInvariantsQueryMetadata(query, queryId, ruleId, category) or
   isOperatorsQueryMetadata(query, queryId, ruleId, category) or