base_parser: Update StripComment to consider quote groupings (#456)

Previous update to StripComment would ignore any pound signs that were
surrounded by quotes, but did not consider if the sign was inside two
quotes or between two sets of two quotes
(i.e. `" # "` vs `" 1 " # " 2 "`). This commit updates StripComment to
check this scenario and not strip if the pound sign is inside two
quotes.

edk2toollib/uefi/edk2/parsers/base_parser.py

@@ -8,7 +8,6 @@
 """Code to support parsing EDK2 files."""
 import logging
 import os
-import re
 from warnings import warn
 
 from edk2toollib.uefi.edk2 import path_utilities
@@ -795,7 +794,6 @@ def ResetParserState(self):
 
 class HashFileParser(BaseParser):
     """Base class for Edk2 build files that use # for comments."""
-    COMMENT_PATTERN = re.compile(r'(?<!["\'])#(?!["\'])')
 
     def __init__(self, log):
         """Inits an empty Parser for files that use # for comments.."""
@@ -807,7 +805,32 @@ def StripComment(self, line):
         Args:
           line (str): line with a comment (#)
         """
-        return re.split(self.COMMENT_PATTERN, line)[0].strip()
+        if "#" not in line:
+            return line.strip()
+
+        result = []
+        inside_quotes = False
+        quote_char = None
+        escaped = False
+
+        for char in line:
+            if char in ('"', "'") and not escaped:
+                if not inside_quotes:
+                    inside_quotes = True
+                    quote_char = char
+                elif char == quote_char:
+                    inside_quotes = False
+                    quote_char = None
+            elif char == '#' and not inside_quotes:
+                break
+            elif char == '\\' and not escaped:
+                escaped = True
+            else:
+                escaped = False
+
+            result.append(char)
+
+        return ''.join(result).rstrip()
 
     def ParseNewSection(self, line):
         """Parses a new section line.

tests.unit/parsers/test_hash_file_parser.py

@@ -47,6 +47,13 @@ def test_strip_comment(self):
             ("gMyPkgTokenSpaceGuid.MyThing|'Value'|VOID*|0x10000000", " # My Comment"),
             ('gMyPkgTokenSpaceGuid.MyThing|"Value"|VOID*|0x10000000', "# My Comment"),
             ('gMyPkgTokenSpaceGuid.MyThing|"#Value"|VOID*|0x10000000', "# My Comment"),
+            ('file_data = "DEFINE TEST DEFINE = \"DEFINE_VALUE\""', ' # "Test String" # Test String'),
+            ("file_data = 'DEFINE TEST DEFINE = \"DEFINE_VALUE\"'", ' # "Test String" # Test String'),
+            ('file_data = "DEFINE TEST DEFINE = \"DEFINE_VALUE\" \' more to check \'"', ' # "Test String" # Test String'),
+            ('file_data = \'DEFINE\" # TEMP \" UPDATE \'', "# Found a quote"),
+            (r'test = \"', r' # Temp \"'),
+            ('file_data = "DEFINE TEST DEFINE = \"DEFINE\\"_VALUE\""', ' # "Test String" # Test String'),
+            ('file_data = "DEFINE TEST DEFINE = \"DEFINE\\\'_VALUE\""', ' # "Test String" # Test String'),
         ]
 
         for line in lines_to_test: