shlex — Parse Shell-style Syntaxes

解析引用字符串

# shlex_example.py
import shlex
import sys

if len(sys.argv) != 2:
    print('Please specify one filename on the command line.')
    sys.exit(1)

filename = sys.argv[1]
with open(filename, 'r') as f:
    body = f.read()
print('ORIGINAL: {!r}'.format(body))
print()

print('TOKENS:')
lexer = shlex.shlex(body)
for token in lexer:
    print('{!r}'.format(token))

Making Safe Strings for Shells

# shlex_quote.py
import shlex

examples = [
    "Embedded'SingleQuote",
    'Embedded"DoubleQuote',
    'Embedded Space',
    '~SpecialCharacter',
    r'Back\slash',
]

for s in examples:
    print('ORIGINAL : {}'.format(s))
    print('QUOTED   : {}'.format(shlex.quote(s)))
    print()

Embedded Comments

把字符串分解为令牌

# shlex_split.py
import shlex

text = """This text has "quoted parts" inside it."""
print('ORIGINAL: {!r}'.format(text))
print()

print('TOKENS:')
print(shlex.split(text))

包含其他来源的令牌

# shlex_source.py
import shlex

text = "This text says to source quotes.txt before continuing."
print('ORIGINAL: {!r}'.format(text))
print()

lexer = shlex.shlex(text)
lexer.wordchars += '.'
lexer.source = 'source'

print('TOKENS:')
for token in lexer:
    print('{!r}'.format(token))

控制解析器

# shlex_table.py
import shlex

text = """|Col 1||Col 2||Col 3|"""
print('ORIGINAL: {!r}'.format(text))
print()

lexer = shlex.shlex(text)
lexer.quotes = '|'

print('TOKENS:')
for token in lexer:
    print('{!r}'.format(token))

# shlex_whitespace.py
import shlex
import sys

if len(sys.argv) != 2:
    print('Please specify one filename on the command line.')
    sys.exit(1)

filename = sys.argv[1]
with open(filename, 'r') as f:
    body = f.read()
print('ORIGINAL: {!r}'.format(body))
print()

print('TOKENS:')
lexer = shlex.shlex(body)
lexer.whitespace += '.,'
for token in lexer:
    print('{!r}'.format(token))

错误处理

# shlex_errors.py
import shlex

text = """This line is ok.
This line has an "unfinished quote.
This line is ok, too.
"""

print('ORIGINAL: {!r}'.format(text))
print()

lexer = shlex.shlex(text)

print('TOKENS:')
try:
    for token in lexer:
        print('{!r}'.format(token))
except ValueError as err:
    first_line_of_error = lexer.token.splitlines()[0]
    print('ERROR: {} {}'.format(lexer.error_leader(), err))
    print('following {!r}'.format(first_line_of_error))

POSIX vs. Non-POSIX Parsing

# shlex_posix.py
import shlex

examples = [
    'Do"Not"Separate',
    '"Do"Separate',
    'Escaped \e Character not in quotes',
    'Escaped "\e" Character in double quotes',
    "Escaped '\e' Character in single quotes",
    r"Escaped '\'' \"\'\" single quote",
    r'Escaped "\"" \'\"\' double quote',
    "\"'Strip extra layer of quotes'\"",
]

for s in examples:
    print('ORIGINAL : {!r}'.format(s))
    print('non-POSIX: ', end='')

    non_posix_lexer = shlex.shlex(s, posix=False)
    try:
        print('{!r}'.format(list(non_posix_lexer)))
    except ValueError as err:
        print('error({})'.format(err))

    print('POSIX    : ', end='')
    posix_lexer = shlex.shlex(s, posix=True)
    try:
        print('{!r}'.format(list(posix_lexer)))
    except ValueError as err:
        print('error({})'.format(err))

    print()