Lift some code out of parse_identifiers

Make parse_identifiers less complex. Pylint was complaining that it had too
many local variables, and it had a point.

* Lift the constants identifier_regex and exclusion_lines to class
  constants (renamed to uppercase because they're constants).
* Lift the per-file loop into a new function parse_identifiers_in_file.

No intended behavior change.

Signed-off-by: Gilles Peskine <Gilles.Peskine@arm.com>

tests/scripts/check_names.py

@@ -457,19 +457,7 @@ class CodeParser():
 
         return enum_consts
 
-    def parse_identifiers(self, include, exclude=None):
+    IDENTIFIER_REGEX = re.compile(
-        """
-        Parse all lines of a header where a function/enum/struct/union/typedef
-        identifier is declared, based on some regex and heuristics. Highly
-        dependent on formatting style.
-
-        Args:
-        * include: A List of glob expressions to look for files through.
-        * exclude: A List of glob expressions for excluding files.
-
-        Returns a List of Match objects with identifiers.
-        """
-        identifier_regex = re.compile(
         # Match " something(a" or " *something(a". Functions.
         # Assumptions:
         # - function definition from return type to one of its arguments is
@@ -485,7 +473,7 @@ class CodeParser():
         r"}? *(\w+)[;[].*"
     )
     # The regex below is indented for clarity.
-        exclusion_lines = re.compile(
+    EXCLUSION_LINES = re.compile(
         r"^("
             r"extern +\"C\"|" # pylint: disable=bad-continuation
             r"(typedef +)?(struct|union|enum)( *{)?$|"
@@ -496,11 +484,15 @@ class CodeParser():
         r")"
     )
 
-        files = self.get_files(include, exclude)
+    def parse_identifiers_in_file(self, header_file, identifiers):
-        self.log.debug("Looking for identifiers in {} files".format(len(files)))
+        """
+        Parse all lines of a header where a function/enum/struct/union/typedef
+        identifier is declared, based on some regex and heuristics. Highly
+        dependent on formatting style.
+
+        Append found matches to the list ``identifiers``.
+        """
 
-        identifiers = []
-        for header_file in files:
         with open(header_file, "r", encoding="utf-8") as header:
             in_block_comment = False
             # The previous line variable is used for concatenating lines
@@ -523,7 +515,7 @@ class CodeParser():
                     in_block_comment = True
                     line = line[:m.end(0)]
 
-                    if exclusion_lines.search(line):
+                if self.EXCLUSION_LINES.search(line):
                     previous_line = ""
                     continue
 
@@ -547,7 +539,7 @@ class CodeParser():
                 if line[0] == " ":
                     continue
 
-                    identifier = identifier_regex.search(line)
+                identifier = self.IDENTIFIER_REGEX.search(line)
 
                 if not identifier:
                     continue
@@ -564,6 +556,26 @@ class CodeParser():
                         identifier.span(),
                         group))
 
+    def parse_identifiers(self, include, exclude=None):
+        """
+        Parse all lines of a header where a function/enum/struct/union/typedef
+        identifier is declared, based on some regex and heuristics. Highly
+        dependent on formatting style.
+
+        Args:
+        * include: A List of glob expressions to look for files through.
+        * exclude: A List of glob expressions for excluding files.
+
+        Returns a List of Match objects with identifiers.
+        """
+
+        files = self.get_files(include, exclude)
+        self.log.debug("Looking for identifiers in {} files".format(len(files)))
+
+        identifiers = []
+        for header_file in files:
+            self.parse_identifiers_in_file(header_file, identifiers)
+
         return identifiers
 
     def parse_symbols(self):