Refactored to class

This commit is contained in:
Kevin Veen-Birkenbach 2023-09-14 18:00:43 +02:00
parent ab609af3bd
commit 1fbf43bfeb

170
scan.py
View File

@ -3,76 +3,110 @@ import argparse
import re
import zlib
def remove_comments(content, file_type):
"""Remove comments from the content based on file type."""
if file_type == ".py":
# Remove Python single line comments
content = re.sub(r'^\s*#.*\n?', '', content, flags=re.MULTILINE)
# Remove triple double-quote and triple single-quote docstrings
content = re.sub(r'\"\"\"(.*?)\"\"\"', '', content, flags=re.DOTALL)
content = re.sub(r"\'\'\'(.*?)\'\'\'", '', content, flags=re.DOTALL)
elif file_type == ".js" or file_type == ".c" or file_type == ".cpp" or file_type == ".h":
# Remove C-style comments (// and /* */)
content = re.sub(r'\s*//.*', '', content)
content = re.sub(r'/\*.*?\*/', '', content, flags=re.DOTALL)
# Add more file types and their comment styles as needed
return content.strip()
class CodeProcessor:
PYTHON = ".py"
JS = ".js"
C = ".c"
CPP = ".cpp"
H = ".h"
def compress_code(content):
"""Compress code using zlib."""
return zlib.compress(content.encode())
@staticmethod
def remove_comments(content, file_type):
"""Remove comments based on file type."""
comment_patterns = {
CodeProcessor.PYTHON: [
(r'^\s*#.*\n?', ''),
(r'\"\"\"(.*?)\"\"\"', ''),
(r"\'\'\'(.*?)\'\'\'", '')
],
CodeProcessor.JS: [
(r'\s*//.*', ''),
(r'/\*.*?\*/', '')
],
CodeProcessor.C: [
(r'\s*//.*', ''),
(r'/\*.*?\*/', '')
],
CodeProcessor.CPP: [
(r'\s*//.*', ''),
(r'/\*.*?\*/', '')
],
CodeProcessor.H: [
(r'\s*//.*', ''),
(r'/\*.*?\*/', '')
]
}
def filter_directories(dirs, ignore_strings, ignore_hidden):
"""Filter out directories based on ignore criteria."""
if ignore_hidden:
dirs[:] = [d for d in dirs if not d.startswith('.')]
dirs[:] = [d for d in dirs if not any(ig in d for ig in ignore_strings)]
patterns = comment_patterns.get(file_type, [])
for pattern, repl in patterns:
content = re.sub(pattern, repl, content, flags=re.DOTALL)
return content.strip()
def should_print_file(file_path, file_filters, ignore_strings, ignore_hidden, include_strings):
"""Determine if a file should be printed based on filters."""
if ignore_hidden and os.path.basename(file_path).startswith('.'):
return False
if file_filters and not any(file_path.endswith(file_type) for file_type in file_filters):
return False
if any(ignore_str in file_path for ignore_str in ignore_strings):
return False
if include_strings and not any(include_str in file_path for include_str in include_strings):
return False
return True
@staticmethod
def compress(content):
"""Compress code using zlib."""
return zlib.compress(content.encode())
def print_file_content(file_path, no_comments, compress):
"""Print the content of a file."""
try:
with open(file_path, 'r') as f:
content = f.read()
if no_comments:
file_type = os.path.splitext(file_path)[1]
content = remove_comments(content, file_type)
print(f"======== File Path: {file_path} ========")
if compress:
compressed_content = compress_code(content)
print(f"======== Compressed Code ========")
print(compressed_content)
else:
print(content)
print("==================================\n")
except UnicodeDecodeError:
print(f"Warning: Could not read file due to encoding issues: {file_path}")
exit(1)
def handle_directory(directory, file_filters, ignore_strings, ignore_hidden, verbose, no_comments, compress, strings):
"""Handle scanning and printing for directories."""
for root, dirs, files in os.walk(directory):
filter_directories(dirs, ignore_strings, ignore_hidden)
for file in files:
if should_print_file(os.path.join(root, file), file_filters, ignore_strings, ignore_hidden, strings):
print_file_content(os.path.join(root, file), no_comments, compress)
elif verbose:
print(f"Skipped file: {file}")
class DirectoryHandler:
@staticmethod
def filter_directories(dirs, ignore_strings, ignore_hidden):
"""Filter out directories based on ignore criteria."""
if ignore_hidden:
dirs[:] = [d for d in dirs if not d.startswith('.')]
dirs[:] = [d for d in dirs if not any(ig in d for ig in ignore_strings)]
@staticmethod
def should_print_file(file_path, file_filters, ignore_strings, ignore_hidden, include_strings):
"""Determine if a file should be printed."""
if ignore_hidden and os.path.basename(file_path).startswith('.'):
return False
if file_filters and not any(file_path.endswith(file_type) for file_type in file_filters):
return False
if any(ignore_str in file_path for ignore_str in ignore_strings):
return False
if include_strings and not any(include_str in file_path for include_str in include_strings):
return False
return True
@staticmethod
def print_file_content(file_path, no_comments, compress):
"""Print the content of a file."""
try:
with open(file_path, 'r') as f:
content = f.read()
if no_comments:
file_type = os.path.splitext(file_path)[1]
content = CodeProcessor.remove_comments(content, file_type)
print(f"======== File Path: {file_path} ========")
if compress:
compressed_content = CodeProcessor.compress(content)
print(f"======== Compressed Code ========")
print(compressed_content)
else:
print(content)
print("==================================\n")
except UnicodeDecodeError:
print(f"Warning: Could not read file due to encoding issues: {file_path}")
exit(1)
@staticmethod
def handle_directory(directory, **kwargs):
"""Handle scanning and printing for directories."""
for root, dirs, files in os.walk(directory):
DirectoryHandler.filter_directories(dirs, kwargs['ignore_strings'], kwargs['ignore_hidden'])
for file in files:
if DirectoryHandler.should_print_file(os.path.join(root, file), kwargs['file_filters'], kwargs['ignore_strings'], kwargs['ignore_hidden'], kwargs['strings']):
DirectoryHandler.print_file_content(os.path.join(root, file), kwargs['no_comments'], kwargs['compress'])
elif kwargs['verbose']:
print(f"Skipped file: {file}")
@staticmethod
def handle_file(file_path, **kwargs):
"""Handle scanning and printing for individual files."""
DirectoryHandler.print_file_content(file_path, kwargs['no_comments'], kwargs['compress'])
def handle_file(file_path, file_filters, ignore_strings, ignore_hidden, no_comments, compress):
"""Handle scanning and printing for individual files."""
print_file_content(file_path, no_comments, compress)
def main():
parser = argparse.ArgumentParser(description="Scan directories and print/compile file contents.")
@ -85,15 +119,15 @@ def main():
parser.add_argument("-s", "--strings", nargs='+', default=[], help="Only display files whose paths contain one of these strings.")
parser.add_argument("--compress", action='store_true', help="Compress code (for Python files).")
args = parser.parse_args()
for path in args.paths:
if os.path.isdir(path):
handle_directory(path, args.filetype, args.ignore, args.ignore_hidden, args.verbose, args.no_comments, args.compress, args.strings)
DirectoryHandler.handle_directory(path, file_filters=args.filetype, ignore_strings=args.ignore, ignore_hidden=args.ignore_hidden, verbose=args.verbose, no_comments=args.no_comments, compress=args.compress, strings=args.strings)
elif os.path.isfile(path):
handle_file(path, args.filetype, args.ignore, args.ignore_hidden, args.no_comments, args.compress)
DirectoryHandler.handle_file(path, file_filters=args.filetype, ignore_strings=args.ignore, ignore_hidden=args.ignore_hidden, no_comments=args.no_comments, compress=args.compress)
else:
print(f"Error: {path} is neither a valid file nor a directory.")
exit(1)
if __name__ == "__main__":
main()
main()