另一个答案只考虑没有缩进的行包含全局变量声明。虽然这有效地排除了函数和类定义的主体，但它错过了在 if 声明中定义的全局变量。这样的声明并不少见，例如，对于因使用的操作系统而异的常量等。
正如问题下的 cmets 所述，任何静态分析都必然是不完美的，因为 Python 的动态特性使得除非程序实际执行，否则无法完全准确地确定哪些变量是全局定义的。
因此，以下也只是一个近似值。但是，它确实考虑了上面列出的ifs 中的全局变量定义。由于这最好通过实际分析源文件的解析树来完成，因此 bash 脚本不再是合适的选择。不过，方便的是，Python 本身允许通过这里使用的 ast 包轻松访问解析树。
from argparse import ArgumentParser, SUPPRESS
import ast
from collections import Counter
from re import match as re_startswith
import os
import subprocess
import sys
# extract variable information from assign statements
def process_assign(target, results):
if isinstance(target, ast.Name):
results.append((target.lineno, target.col_offset, target.id))
elif isinstance(target, ast.Tuple):
for child in ast.iter_child_nodes(target):
process_assign(child, results)
# extract variable information from delete statements
def process_delete(target, results):
if isinstance(target, ast.Name):
results[:] = filter(lambda t: t[2] != target.id, results)
elif isinstance(target, ast.Tuple):
for child in ast.iter_child_nodes(target):
process_delete(child, results)
# recursively walk the parse tree of the source file
def process_node(node, results):
if isinstance(node, ast.Assign):
for target in node.targets:
process_assign(target, results)
elif isinstance(node, ast.Delete):
for target in node.targets:
process_delete(target, results)
elif type(node) not in [ast.FunctionDef, ast.ClassDef]:
for child in ast.iter_child_nodes(node):
process_node(child, results)
def get_arg_parser():
# create the parser to configure
parser = ArgumentParser(usage=SUPPRESS, add_help=False)
# run etags to find out about the supported command line parameters
dashlines = list(filter(lambda line: re_startswith('\\s*-', line),
subprocess.check_output(['etags', '-h'],
encoding='utf-8').split('\n')))
# ignore lines that start with a dash but don't have the right
# indentation
most_common_indent = max([(v,k) for k,v in
Counter([line.index('-') for line in dashlines]).items()])[1]
arglines = filter(lambda line: line.index('-') == most_common_indent, dashlines)
for argline in arglines:
# the various 'argline' entries contain the command line
# arguments for etags, sometimes more than one separated by
# commas.
for arg in argline.split(','):
if 'or' in arg:
arg = arg[:arg.index('or')]
if ' ' in arg or '=' in arg:
arg = arg[:min(arg.index(' ') if ' ' in arg else len(arg),
arg.index('=') if '=' in arg else len(arg))]
action='store'
else:
action='store_true'
arg = arg.strip()
if arg and not (arg == '-h' or arg == '--help'):
parser.add_argument(arg, action=action)
# we know we need files to run on
parser.add_argument('files', nargs='*', metavar='file')
# the parser is configured now to accept all of etags' arguments
return parser
if __name__ == '__main__':
# construct a parser for the command line arguments, unless
# -h/-help/--help is given in which case we just print the help
# screen
etags_args = sys.argv[1:]
if '-h' in etags_args or '-help' in etags_args or '--help' in etags_args:
unknown_args = True
else:
argparser = get_arg_parser()
known_ns, unknown_args = argparser.parse_known_args()
# if something's wrong with the command line arguments, print
# etags' help screen and exit
if unknown_args:
subprocess.run(['etags', '-h'], encoding='utf-8')
sys.exit(1)
# we base the output filename on the TAGS file name. Other than
# that, we only care about the actual filenames to parse, and all
# other command line arguments are simply passed to etags later on
tags_file = 'TAGS2' if hasattr(known_ns, 'o') is None else known_ns.o + '2'
filenames = known_ns.files
if filenames:
# TAGS file sections, one per source file
sections = []
# process all files to populate the 'sections' list
for filename in filenames:
# read source file
offsets = [0]; lines = []
offsets, lines = [0], []
with open(filename, 'r') as f:
for line in f.readlines():
offsets.append(offsets[-1] + len(bytes(line, 'utf-8')))
lines.append(line)
offsets = offsets[:-1]
# parse source file
source = ''.join(lines)
root_node = ast.parse(source, filename)
# extract global variable definitions
vardefs = []
process_node(root_node, vardefs)
# create TAGS file section
sections.append("")
for lineno, column, varname in vardefs:
line = lines[lineno-1]
offset = offsets[lineno-1]
end = line.index('=') if '=' in line else -1
sections[-1] += f"{line[:end]}\x7f{varname}\x01{lineno},{offset + column - 1}\n"
# write TAGS file
with open(tags_file, 'w') as f:
for filename, section in zip(filenames, sections):
if section:
f.write("\x0c\n")
f.write(filename)
f.write(",")
f.write(str(len(bytes(section, 'utf-8'))))
f.write("\n")
f.write(section)
f.write("\n")
# make sure etags includes the newly created file
etags_args += ['-i', tags_file]
# now run the actual etags to take care of all other definitions
try:
cp = subprocess.run(['etags'] + etags_args, encoding='utf-8')
status = cp.returncode
except:
status = 1
# if etags did not finish successfully, remove the tags_file
if status != 0:
try:
os.remove(tags_file)
except FileNotFoundError:
# nothing to be removed
pass
与其他答案一样，此脚本旨在替代标准 etags，因为它在内部调用后者。因此它也接受所有etags'命令行参数（但目前不尊重-a）。
建议用别名修改自己的shell的init文件，例如在~/.bashrc中添加以下行：
alias etags+=python3 -u /path/to/script.py
其中/path/to/script.py 是保存上述代码的文件的路径。有了这样的别名，您可以简单地调用
etags+ /path/to/file
等等