From 069283e349b2e8dd324446aa5c30253a0993f1a3 Mon Sep 17 00:00:00 2001
From: mathieui <mathieui@mathieui.net>
Date: Mon, 28 Apr 2014 00:20:57 +0200
Subject: =?UTF-8?q?Don=E2=80=99t=20escape=20backslashes=20unless=20we=20ar?=
 =?UTF-8?q?e=20inside=20a=20quoted=20string=20and=20the=20next=20char=20is?=
 =?UTF-8?q?=20a=20quote?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Sadly, we can’t doctest stuff with backslashes because it drives doctest
crazy.
---
 src/common.py       |  2 ++
 src/poezio_shlex.py | 21 ++++-----------------
 2 files changed, 6 insertions(+), 17 deletions(-)

(limited to 'src')

diff --git a/src/common.py b/src/common.py
index e9fe05c8..20700258 100644
--- a/src/common.py
+++ b/src/common.py
@@ -319,6 +319,8 @@ def shell_split(st):
     ['toto', 'titi']
     >>> shell_split('toto ""')
     ['toto', '']
+    >>> shell_split('to"to titi "a" b')
+    ['to"to', 'titi', 'a', 'b']
     >>> shell_split('"toto titi" toto ""')
     ['toto titi', 'toto', '']
     >>> shell_split('toto "titi')
diff --git a/src/poezio_shlex.py b/src/poezio_shlex.py
index 086b0707..032baeee 100644
--- a/src/poezio_shlex.py
+++ b/src/poezio_shlex.py
@@ -102,6 +102,7 @@ class shlex(object):
         escapedstate = ' '
         token_start = 0
         token_end = -1
+        # read one char from the stream at once
         while True:
             nextchar = self.instream.read(1)
             if nextchar == '\n':
@@ -126,13 +127,6 @@ class shlex(object):
                         break   # emit current token
                     else:
                         continue
-                elif nextchar in self.commenters:
-                    self.instream.readline()
-                    self.lineno = self.lineno + 1
-                elif self.posix and nextchar in self.escape:
-                    token_start = self.instream.tell() - 1
-                    escapedstate = 'a'
-                    self.state = nextchar
                 elif nextchar in self.wordchars:
                     token_start = self.instream.tell() - 1
                     self.token = nextchar
@@ -181,10 +175,8 @@ class shlex(object):
                     # XXX what error should be raised here?
                     token_end = self.instream.tell()
                     break
-                # In posix shells, only the quote itself or the escape
-                # character may be escaped within quotes.
-                if escapedstate in self.quotes and \
-                   nextchar != self.state and nextchar != escapedstate:
+                # only the quote may be escaped
+                if escapedstate in self.quotes and nextchar != escapedstate:
                     self.token = self.token + self.state
                 self.token = self.token + nextchar
                 self.state = escapedstate
@@ -202,13 +194,8 @@ class shlex(object):
                         break   # emit current token
                     else:
                         continue
-                elif self.posix and nextchar in self.quotes:
-                    self.state = nextchar
-                elif self.posix and nextchar in self.escape:
-                    escapedstate = 'a'
-                    self.state = nextchar
                 elif nextchar in self.wordchars or nextchar in self.quotes \
-                    or self.whitespace_split:
+                        or self.whitespace_split:
                     self.token = self.token + nextchar
                 else:
                     self.pushback.appendleft(nextchar)
-- 
cgit v1.2.3