rnhmjoj/qutebrowser
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

shlex: Assume posix=True

Browse Source
This commit is contained in:
Florian Bruhin 2014-11-03 21:35:47 +01:00
parent cab18c248c
commit 861705f655
1 changed files with 20 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
qutebrowser/utils/split.py
View File

@ -27,7 +27,7 @@ from io import StringIO
class ShellLexer: class ShellLexer:
"A lexical analyzer class for simple shell-like syntaxes." "A lexical analyzer class for simple shell-like syntaxes."
def __init__(self, instream=None, infile=None, posix=False): def __init__(self, instream=None, infile=None):
if isinstance(instream, str): if isinstance(instream, str):
instream = StringIO(instream) instream = StringIO(instream)
if instream is not None: if instream is not None:
@ -36,17 +36,12 @@ class ShellLexer:
else: else:
self.instream = sys.stdin self.instream = sys.stdin
self.infile = None self.infile = None
self.posix = posix self.eof = None
if posix:
self.eof = None
else:
self.eof = ''
self.commenters = '#' self.commenters = '#'
self.wordchars = ('abcdfeghijklmnopqrstuvwxyz' self.wordchars = ('abcdfeghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_') 'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_')
if self.posix: self.wordchars += ('ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ'
self.wordchars += ('ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ' 'ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ')
'ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ')
self.whitespace = ' \t\r\n' self.whitespace = ' \t\r\n'
self.whitespace_split = False self.whitespace_split = False
self.quotes = '\'"' self.quotes = '\'"'
@ -101,29 +96,27 @@ class ShellLexer:
elif nextchar in self.whitespace: elif nextchar in self.whitespace:
if self.debug >= 2: if self.debug >= 2:
print("shlex: I see whitespace in whitespace state") print("shlex: I see whitespace in whitespace state")
if self.token or (self.posix and quoted): if self.token or quoted:
break # emit current token break # emit current token
else: else:
continue continue
elif nextchar in self.commenters: elif nextchar in self.commenters:
self.instream.readline() self.instream.readline()
self.lineno = self.lineno + 1 self.lineno = self.lineno + 1
elif self.posix and nextchar in self.escape: elif nextchar in self.escape:
escapedstate = 'a' escapedstate = 'a'
self.state = nextchar self.state = nextchar
elif nextchar in self.wordchars: elif nextchar in self.wordchars:
self.token = nextchar self.token = nextchar
self.state = 'a' self.state = 'a'
elif nextchar in self.quotes: elif nextchar in self.quotes:
if not self.posix:
self.token = nextchar
self.state = nextchar self.state = nextchar
elif self.whitespace_split: elif self.whitespace_split:
self.token = nextchar self.token = nextchar
self.state = 'a' self.state = 'a'
else: else:
self.token = nextchar self.token = nextchar
if self.token or (self.posix and quoted): if self.token or quoted:
break # emit current token break # emit current token
else: else:
continue continue
@ -135,14 +128,9 @@ class ShellLexer:
# XXX what error should be raised here? # XXX what error should be raised here?
raise ValueError("No closing quotation") raise ValueError("No closing quotation")
if nextchar == self.state: if nextchar == self.state:
if not self.posix: self.state = 'a'
self.token = self.token + nextchar elif (nextchar in self.escape and
self.state = ' ' self.state in self.escapedquotes):
break
else:
self.state = 'a'
elif self.posix and nextchar in self.escape and \
self.state in self.escapedquotes:
escapedstate = self.state escapedstate = self.state
self.state = nextchar self.state = nextchar
else: else:
@ -168,22 +156,21 @@ class ShellLexer:
if self.debug >= 2: if self.debug >= 2:
print("shlex: I see whitespace in word state") print("shlex: I see whitespace in word state")
self.state = ' ' self.state = ' '
if self.token or (self.posix and quoted): if self.token or quoted:
break # emit current token break # emit current token
else: else:
continue continue
elif nextchar in self.commenters: elif nextchar in self.commenters:
self.instream.readline() self.instream.readline()
self.lineno = self.lineno + 1 self.lineno = self.lineno + 1
if self.posix: self.state = ' '
self.state = ' ' if self.token or quoted:
if self.token or (self.posix and quoted): break # emit current token
break # emit current token else:
else: continue
continue elif nextchar in self.quotes:
elif self.posix and nextchar in self.quotes:
self.state = nextchar self.state = nextchar
elif self.posix and nextchar in self.escape: elif nextchar in self.escape:
escapedstate = 'a' escapedstate = 'a'
self.state = nextchar self.state = nextchar
elif nextchar in self.wordchars or nextchar in self.quotes \ elif nextchar in self.wordchars or nextchar in self.quotes \
@ -200,7 +187,7 @@ class ShellLexer:
continue continue
result = self.token result = self.token
self.token = '' self.token = ''
if self.posix and not quoted and result == '': if not quoted and result == '':
result = None result = None
if self.debug > 1: if self.debug > 1:
if result: if result:
@ -223,7 +210,7 @@ def _get_lexer(s):
"""Get an shlex lexer for split.""" """Get an shlex lexer for split."""
if s is None: if s is None:
raise TypeError("Refusing to create a lexer with s=None!") raise TypeError("Refusing to create a lexer with s=None!")
lexer = ShellLexer(s, posix=True) lexer = ShellLexer(s)
lexer.whitespace_split = True lexer.whitespace_split = True
lexer.commenters = '' lexer.commenters = ''
return lexer return lexer