Add ignore tag to the match.py script

cmake/match.py

@@ -5,77 +5,138 @@
 # See LICENSE.TXT
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
-# check if all lines match in a file
-# lines in a match file can contain regex inside of double curly braces {{}}
+# Check if all input file content matches match file content.
+# Lines in a match file can contain regex inside of double curly braces {{}}.
+# Regex patterns are limited to single line.
+#
+# List of available special tags:
+# {{OPT}} - makes content in the same line as the tag optional
+# {{IGNORE}} - ignores all content until next match or end of input file
+# Special tags are mutually exclusive and are expected to be located at the start of a line.
+#
 
 import sys
 import re
+from enum import Enum
 
 
 ## @brief print the whole content of input and match files
-def print_content(input_lines, match_lines):
+def print_content(input_lines, match_lines, ignored_lines):
  print("--- Input Lines " + "-" * 64)
  print("".join(input_lines).strip())
  print("--- Match Lines " + "-" * 64)
  print("".join(match_lines).strip())
+ print("--- Ignored Lines " + "-" * 62)
+ print("".join(ignored_lines).strip())
  print("-" * 80)
 
 
-if len(sys.argv) != 3:
- print("Usage: python match.py <input_file> <match_file>")
- sys.exit(1)
-
-input_file = sys.argv[1]
-match_file = sys.argv[2]
-
-with open(input_file, 'r') as input, open(match_file, 'r') as match:
- input_lines = input.readlines()
- match_lines = match.readlines()
-
-if len(match_lines) < len(input_lines):
- print(f"Match length < input length (input: {len(input_lines)}, match: {len(match_lines)})")
- print_content(input_lines, match_lines)
- sys.exit(1)
-
-input_idx = 0
-opt = "{{OPT}}"
-for i, match_line in enumerate(match_lines):
- if match_line.startswith(opt):
- optional_line = True
- match_line = match_line[len(opt):]
- else:
- optional_line = False
-
- # split into parts at {{ }}
- match_parts = re.split(r'\{{(.*?)\}}', match_line.strip())
- pattern = ""
- for j, part in enumerate(match_parts):
- if j % 2 == 0:
- pattern += re.escape(part)
- else:
- pattern += part
+def print_incorrect_match(match_line, present, expected):
+ print("Line " + str(match_line) + " does not match")
+ print("is: " + present)
+ print("expected: " + expected)
 
- # empty input file or end of input file, from now on match file must be optional
- if not input_lines:
- if optional_line is True:
- continue
- else:
- print("End of input file or empty file.")
- print("expected: " + match_line.strip())
- sys.exit(1)
 
- input_line = input_lines[input_idx].strip()
- if not re.fullmatch(pattern, input_line):
- if optional_line is True:
- continue
- else:
- print("Line " + str(i+1) + " does not match")
- print("is: " + input_line)
- print("expected: " + match_line.strip())
- print_content(input_lines, match_lines)
+## @brief pattern matching script status values
+class Status(Enum):
+ INPUT_END = 1
+ MATCH_END = 2
+ INPUT_AND_MATCH_END = 3
+ PROCESSING = 4
+
+
+## @brief check matching script status
+def check_status(input_lines, match_lines):
+ if not input_lines and not match_lines:
+ return Status.INPUT_AND_MATCH_END
+ elif not input_lines:
+ return Status.INPUT_END
+ elif not match_lines:
+ return Status.MATCH_END
+ return Status.PROCESSING
+
+
+## @brief pattern matching tags.
+## Tags are expected to be at the start of the line.
+class Tag(Enum):
+ OPT = "{{OPT}}" # makes the line optional
+ IGNORE = "{{IGNORE}}" # ignores all input until next match or end of input file
+
+
+## @brief main function for the match file processing script
+def main():
+ if len(sys.argv) != 3:
+ print("Usage: python match.py <input_file> <match_file>")
+ sys.exit(1)
+
+ input_file = sys.argv[1]
+ match_file = sys.argv[2]
+
+ with open(input_file, 'r') as input, open(match_file, 'r') as match:
+ input_lines = input.readlines()
+ match_lines = match.readlines()
+
+ ignored_lines = []
+
+ input_idx = 0
+ match_idx = 0
+ tag_in_effect = None
+ status = Status.PROCESSING
+ while status == Status.PROCESSING:
+ status = check_status(input_lines[input_idx:], match_lines[match_idx:])
+ if status == Status.INPUT_AND_MATCH_END:
+ sys.exit(0)
+ elif status == Status.MATCH_END:
+ # last line of the match file is {{IGNORE}} tag, stop processing
+ if tag_in_effect == Tag.IGNORE:
+ sys.exit(0)
+ else:
+ print_incorrect_match(match_idx + 1, input_lines[input_idx].strip(), "");
+ print_content(input_lines, match_lines, ignored_lines)
+ sys.exit(1)
+ elif status == Status.INPUT_END:
+ print_incorrect_match(match_idx + 1, "", match_lines[match_idx].strip());
+ print_content(input_lines, match_lines, ignored_lines)
  sys.exit(1)
- else:
- if (input_idx == len(input_lines) - 1):
- input_lines = []
  else:
- input_idx += 1
+ input_line = input_lines[input_idx].strip()
+
+ match_line = match_lines[match_idx]
+ if match_line.startswith(Tag.OPT.value):
+ tag_in_effect = Tag.OPT
+ match_line = match_line[len(Tag.OPT.value):]
+ elif match_line.startswith(Tag.IGNORE.value):
+ tag_in_effect = Tag.IGNORE
+ match_idx += 1
+ continue
+
+ # split into parts at {{ }}
+ match_parts = re.split(r'\{{(.*?)\}}', match_line.strip())
+ pattern = ""
+ for j, part in enumerate(match_parts):
+ if j % 2 == 0:
+ pattern += re.escape(part)
+ else:
+ pattern += part
+
+ if not re.fullmatch(pattern, input_line):
+ if tag_in_effect == Tag.OPT:
+ match_idx += 1
+ tag_in_effect = None
+ continue
+ elif tag_in_effect == Tag.IGNORE:
+ ignored_lines.append(input_line + "\n")
+ input_idx += 1
+ continue
+ else:
+ print_incorrect_match(match_idx + 1, input_line, match_line.strip())
+ print_content(input_lines, match_lines, ignored_lines)
+ sys.exit(1)
+
+ input_idx += 1
+ match_idx += 1
+ tag_in_effect = None
+
+
+if __name__ == "__main__":
+ main()