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

Use yield

Browse Source
This commit is contained in:
Florian Bruhin 2014-11-06 06:44:23 +01:00
parent 9591e86054
commit cb24ec58cc
1 changed files with 65 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

133
qutebrowser/utils/split.py
View File

@ -41,108 +41,101 @@ class ShellLexer:
self.escapedquotes = '"' self.escapedquotes = '"'
self.keep = False self.keep = False
def read_token(self): def reset(self):
self.quoted = False
self.escapedstate = ' '
self.token = ''
self.state = ' '
def __iter__(self):
"""Read a raw token from the input stream.""" """Read a raw token from the input stream."""
quoted = False self.quoted = False
escapedstate = ' ' self.escapedstate = ' '
token = '' self.token = ''
state = ' ' self.state = ' '
while True: while True:
try: try:
nextchar = next(self.iterator) nextchar = next(self.iterator)
except StopIteration: except StopIteration:
nextchar = None nextchar = None
log.shlexer.vdebug("in state {!r} I see character: {!r}".format( log.shlexer.vdebug("in state {!r} I see character: {!r}".format(
state, nextchar)) self.state, nextchar))
if state == ' ':
if nextchar is None: if nextchar is None:
break if self.state in self.escape and not self.keep:
elif nextchar in self.whitespace: self.token += self.state
if self.token or self.quoted:
yield self.token
return
elif self.state == ' ':
if nextchar in self.whitespace:
log.shlexer.vdebug("I see whitespace in whitespace state") log.shlexer.vdebug("I see whitespace in whitespace state")
if self.keep: if self.keep:
token += nextchar self.token += nextchar
if token or quoted: if self.token or self.quoted:
# emit current token # emit current token
break yield self.token
self.reset()
continue
else: else:
continue continue
elif nextchar in self.escape: elif nextchar in self.escape:
if self.keep: if self.keep:
token += nextchar self.token += nextchar
escapedstate = 'a' self.escapedstate = 'a'
state = nextchar self.state = nextchar
elif nextchar in self.quotes: elif nextchar in self.quotes:
if self.keep: if self.keep:
token += nextchar self.token += nextchar
state = nextchar self.state = nextchar
else: else:
token = nextchar self.token = nextchar
state = 'a' self.state = 'a'
elif state in self.quotes: elif self.state in self.quotes:
quoted = True self.quoted = True
if nextchar is None: if nextchar == self.state:
log.shlexer.vdebug("I see EOF in quotes state")
break
if nextchar == state:
if self.keep: if self.keep:
token += nextchar self.token += nextchar
state = 'a' self.state = 'a'
elif (nextchar in self.escape and elif (nextchar in self.escape and
state in self.escapedquotes): self.state in self.escapedquotes):
if self.keep: if self.keep:
token += nextchar self.token += nextchar
escapedstate = state self.escapedstate = self.state
state = nextchar self.state = nextchar
else: else:
token += nextchar self.token += nextchar
elif state in self.escape: elif self.state in self.escape:
if nextchar is None:
log.shlexer.vdebug("I see EOF in escape state")
if not self.keep:
token += state
break
# In posix shells, only the quote itself or the escape # In posix shells, only the quote itself or the escape
# character may be escaped within quotes. # character may be escaped within quotes.
if (escapedstate in self.quotes and nextchar != state and if (self.escapedstate in self.quotes and
nextchar != escapedstate and not self.keep): nextchar != self.state and
token += state nextchar != self.escapedstate and not self.keep):
token += nextchar self.token += self.state
state = escapedstate self.token += nextchar
elif state == 'a': self.state = self.escapedstate
if nextchar is None: elif self.state == 'a':
break if nextchar in self.whitespace:
elif nextchar in self.whitespace:
log.shlexer.vdebug("shlex: I see whitespace in word state") log.shlexer.vdebug("shlex: I see whitespace in word state")
state = ' ' self.state = ' '
if self.keep: if self.keep:
token += nextchar self.token += nextchar
if token or quoted: if self.token or self.quoted:
break # emit current token yield self.token
self.reset()
continue
else: else:
continue continue
elif nextchar in self.quotes: elif nextchar in self.quotes:
if self.keep: if self.keep:
token += nextchar self.token += nextchar
state = nextchar self.state = nextchar
elif nextchar in self.escape: elif nextchar in self.escape:
if self.keep: if self.keep:
token += nextchar self.token += nextchar
escapedstate = 'a' self.escapedstate = 'a'
state = nextchar self.state = nextchar
else: else:
token += nextchar self.token += nextchar
if not quoted and token == '':
token = None
log.shlexer.vdebug("token={!r}".format(token))
return token
def __iter__(self):
while True:
token = self.read_token()
if token is None:
return
else:
yield token
def split(s, keep=False): def split(s, keep=False):
@ -154,6 +147,8 @@ def split(s, keep=False):
lexer = ShellLexer(s) lexer = ShellLexer(s)
lexer.keep = keep lexer.keep = keep
tokens = list(lexer) tokens = list(lexer)
if not tokens:
return []
out = [] out = []
if tokens[0].isspace(): if tokens[0].isspace():
out.append(tokens[0] + tokens[1]) out.append(tokens[0] + tokens[1])