def test_php_escaping_double_quote():
"""Test the helper escaping funtions for 'double quotes'"""
# Decoding - PHP -> Python
assert php.phpdecode("'", quotechar='"') == "'" # we do nothing with single quotes
assert php.phpdecode(r"\n", quotechar='"') == "\n" # See table of escaped characters
assert php.phpdecode(r"\r", quotechar='"') == "\r" # See table of escaped characters
assert php.phpdecode(r"\t", quotechar='"') == "\t" # See table of escaped characters
assert php.phpdecode(r"\v", quotechar='"') == "\v" # See table of escaped characters
assert php.phpdecode(r"\f", quotechar='"') == "\f" # See table of escaped characters
assert php.phpdecode(r"\\", quotechar='"') == "\\" # See table of escaped characters
#assert php.phpdecode(r"\$", quotechar='"') == "$" # See table of escaped characters - this may cause confusion with actual variables in roundtripping
assert php.phpdecode(r"\$", quotechar='"') == "\\$" # Just to check that we don't unescape this
assert php.phpdecode(r'\"', quotechar='"') == '"' # See table of escaped characters
assert php.phpdecode(r'\117\143\164\141\154', quotechar='"') == 'Octal' # Octal: \[0-7]{1,3}
assert php.phpdecode(r'\x48\x65\x78', quotechar='"') == 'Hex' # Hex: \x[0-9A-Fa-f]{1,2}
assert php.phpdecode(r'\117\\c\164\141\154', quotechar='"') == 'O\ctal' # Mixed
# Decoding - special examples
assert php.phpdecode(r"Don't escape me here\'s", quotechar='"') == r"Don't escape me here\'s" # See bug #589
assert php.phpdecode("Line1\nLine2") == "Line1\nLine2" # Preserve newlines in multiline messages
assert php.phpdecode("Line1\r\nLine2") == "Line1\r\nLine2" # DOS PHP files
# Encoding - Python -> PHP
assert php.phpencode("'", quotechar='"') == "'"
assert php.phpencode("\n", quotechar='"') == "\n" # See table of escaped characters - we leave newlines unescaped so that we can try best to preserve pretty printing. See bug 588
assert php.phpencode("\r", quotechar='"') == r"\r" # See table of escaped characters
assert php.phpencode("\t", quotechar='"') == r"\t" # See table of escaped characters
assert php.phpencode("\v", quotechar='"') == r"\v" # See table of escaped characters
assert php.phpencode("\f", quotechar='"') == r"\f" # See table of escaped characters
assert php.phpencode(r"\\", quotechar='"') == r"\\" # See table of escaped characters
#assert php.phpencode("\$", quotechar='"') == "$" # See table of escaped characters - this may cause confusion with actual variables in roundtripping
assert php.phpencode("\$", quotechar='"') == r"\$" # Just to check that we don't unescape this
assert php.phpencode('"', quotechar='"') == r'\"'
assert php.phpencode(r"Don't escape me here\'s", quotechar='"') == r"Don't escape me here\'s" # See bug #589
def test_php_escaping_double_quote():
"""Test the helper escaping funtions for 'double quotes'"""
# Decoding - PHP -> Python
assert php.phpdecode(
"'", quotechar='"') == "'" # we do nothing with single quotes
assert php.phpdecode(
r"\n", quotechar='"') == "\n" # See table of escaped characters
assert php.phpdecode(
r"\r", quotechar='"') == "\r" # See table of escaped characters
assert php.phpdecode(
r"\t", quotechar='"') == "\t" # See table of escaped characters
assert php.phpdecode(
r"\v", quotechar='"') == "\v" # See table of escaped characters
assert php.phpdecode(
r"\f", quotechar='"') == "\f" # See table of escaped characters
assert php.phpdecode(
r"\\", quotechar='"') == "\\" # See table of escaped characters
#assert php.phpdecode(r"\$", quotechar='"') == "$" # See table of escaped characters - this may cause confusion with actual variables in roundtripping
assert php.phpdecode(
r"\$",
quotechar='"') == "\\$" # Just to check that we don't unescape this
assert php.phpdecode(
r'\"', quotechar='"') == '"' # See table of escaped characters
assert php.phpdecode(r'\117\143\164\141\154',
quotechar='"') == 'Octal' # Octal: \[0-7]{1,3}
assert php.phpdecode(r'\x48\x65\x78',
quotechar='"') == 'Hex' # Hex: \x[0-9A-Fa-f]{1,2}
assert php.phpdecode(r'\117\\c\164\141\154',
quotechar='"') == 'O\ctal' # Mixed
# Decoding - special examples
assert php.phpdecode(
r"Don't escape me here\'s",
quotechar='"') == r"Don't escape me here\'s" # See bug #589
assert php.phpdecode(
"Line1\nLine2"
) == "Line1\nLine2" # Preserve newlines in multiline messages
assert php.phpdecode("Line1\r\nLine2") == "Line1\r\nLine2" # DOS PHP files
# Encoding - Python -> PHP
assert php.phpencode("'", quotechar='"') == "'"
assert php.phpencode(
"\n", quotechar='"'
) == "\n" # See table of escaped characters - we leave newlines unescaped so that we can try best to preserve pretty printing. See bug 588
assert php.phpencode(
"\r", quotechar='"') == r"\r" # See table of escaped characters
assert php.phpencode(
"\t", quotechar='"') == r"\t" # See table of escaped characters
assert php.phpencode(
"\v", quotechar='"') == r"\v" # See table of escaped characters
assert php.phpencode(
"\f", quotechar='"') == r"\f" # See table of escaped characters
assert php.phpencode(
r"\\", quotechar='"') == r"\\" # See table of escaped characters
#assert php.phpencode("\$", quotechar='"') == "$" # See table of escaped characters - this may cause confusion with actual variables in roundtripping
assert php.phpencode(
"\$",
quotechar='"') == r"\$" # Just to check that we don't unescape this
assert php.phpencode('"', quotechar='"') == r'\"'
assert php.phpencode(
r"Don't escape me here\'s",
quotechar='"') == r"Don't escape me here\'s" # See bug #589
def test_php_escaping_single_quote():
"""
Test the helper escaping funtions for 'single quotes'
The tests are built mostly from examples from the PHP
`string type definition <http://www.php.net/manual/en/language.types.string.php#language.types.string.syntax.single>`_.
"""
# Decoding - PHP -> Python
assert php.phpdecode(
r"\'"
) == r"'" # To specify a literal single quote, escape it with a backslash (\).
assert php.phpdecode(r'"') == r'"'
assert php.phpdecode(
r"\\'"
) == r"\'" # To specify a literal backslash before a single quote, or at the end of the string, double it (\\)
assert php.phpdecode(
r"\x"
) == r"\x" # Note that attempting to escape any other character will print the backslash too.
assert php.phpdecode(r'\t') == r'\t'
assert php.phpdecode(r'\n') == r'\n'
assert php.phpdecode(
r"this is a simple string") == r"this is a simple string"
assert php.phpdecode("""You can also have embedded newlines in
strings this way as it is
okay to do""") == """You can also have embedded newlines in
strings this way as it is
okay to do"""
assert php.phpdecode(r"This will not expand: \n a newline"
) == r"This will not expand: \n a newline"
assert php.phpdecode(r'Arnold once said: "I\'ll be back"'
) == r'''Arnold once said: "I'll be back"'''
assert php.phpdecode(r'You deleted C:\\*.*?') == r"You deleted C:\*.*?"
assert php.phpdecode(r'You deleted C:\*.*?') == r"You deleted C:\*.*?"
assert php.phpdecode(
r'\117\143\164\141\154'
) == r'\117\143\164\141\154' # We don't handle Octal like " does
assert php.phpdecode(
r'\x48\x65\x78') == r'\x48\x65\x78' # Don't handle Hex either
# Should implement for false interpretation of double quoted data.
# Encoding - Python -> PHP
assert php.phpencode(
r"'"
) == r"\'" # To specify a literal single quote, escape it with a backslash (\).
assert php.phpencode(
r"\'"
) == r"\\'" # To specify a literal backslash before a single quote, or at the end of the string, double it (\\)
assert php.phpencode(r'"') == r'"'
assert php.phpencode(
r"\x"
) == r"\x" # Note that attempting to escape any other character will print the backslash too.
assert php.phpencode(r"\t") == r"\t"
assert php.phpencode(r"\n") == r"\n"
assert php.phpencode(r"""String with
newline""") == r"""String with
newline"""
assert php.phpencode(r"This will not expand: \n a newline"
) == r"This will not expand: \n a newline"
assert php.phpencode(r'''Arnold once said: "I'll be back"'''
) == r'''Arnold once said: "I\'ll be back"'''
assert php.phpencode(r'You deleted C:\*.*?') == r"You deleted C:\*.*?"
def test_php_escaping_single_quote():
"""Test the helper escaping funtions for 'single quotes'
The tests are built mostly from examples from the PHP
`string type definition <http://www.php.net/manual/en/language.types.string.php#language.types.string.syntax.single>`_.
"""
# Decoding - PHP -> Python
assert php.phpdecode(r"\'") == r"'" # To specify a literal single quote, escape it with a backslash (\).
assert php.phpdecode(r'"') == r'"'
assert (
php.phpdecode(r"\\'") == r"\'"
) # To specify a literal backslash before a single quote, or at the end of the string, double it (\\)
assert (
php.phpdecode(r"\x") == r"\x"
) # Note that attempting to escape any other character will print the backslash too.
assert php.phpdecode(r"\t") == r"\t"
assert php.phpdecode(r"\n") == r"\n"
assert php.phpdecode(r"this is a simple string") == r"this is a simple string"
assert (
php.phpdecode(
"""You can also have embedded newlines in
strings this way as it is
okay to do"""
)
== """You can also have embedded newlines in
strings this way as it is
okay to do"""
)
assert php.phpdecode(r"This will not expand: \n a newline") == r"This will not expand: \n a newline"
assert php.phpdecode(r'Arnold once said: "I\'ll be back"') == r'''Arnold once said: "I'll be back"'''
assert php.phpdecode(r"You deleted C:\\*.*?") == r"You deleted C:\*.*?"
assert php.phpdecode(r"You deleted C:\*.*?") == r"You deleted C:\*.*?"
assert php.phpdecode(r"\117\143\164\141\154") == r"\117\143\164\141\154" # We don't handle Octal like " does
assert php.phpdecode(r"\x48\x65\x78") == r"\x48\x65\x78" # Don't handle Hex either
# Should implement for false interpretation of double quoted data.
# Encoding - Python -> PHP
assert php.phpencode(r"'") == r"\'" # To specify a literal single quote, escape it with a backslash (\).
assert (
php.phpencode(r"\'") == r"\\'"
) # To specify a literal backslash before a single quote, or at the end of the string, double it (\\)
assert php.phpencode(r'"') == r'"'
assert (
php.phpencode(r"\x") == r"\x"
) # Note that attempting to escape any other character will print the backslash too.
assert php.phpencode(r"\t") == r"\t"
assert php.phpencode(r"\n") == r"\n"
assert (
php.phpencode(
r"""String with
newline"""
)
== r"""String with
newline"""
)
assert php.phpencode(r"This will not expand: \n a newline") == r"This will not expand: \n a newline"
assert php.phpencode(r'''Arnold once said: "I'll be back"''') == r'''Arnold once said: "I\'ll be back"'''
assert php.phpencode(r"You deleted C:\*.*?") == r"You deleted C:\*.*?"
def convertline(self, line):
line = unicode(line, 'utf-8')
returnline = ""
# handle multiline msgid if we're in one
if self.inmultilinemsgid:
# see if there's more
endpos = line.rfind("%s;" % self.quotechar)
# if there was no '; or the quote is escaped, we have to continue
if endpos >= 0 and line[endpos-1] != '\\':
self.inmultilinemsgid = False
# if we're echoing...
if self.inecho:
returnline = line
# otherwise, this could be a comment
elif line.strip()[:2] == '//' or line.strip()[:2] == '/*':
returnline = quote.rstripeol(line)+eol
else:
line = quote.rstripeol(line)
equalspos = line.find('=')
hashpos = line.find("#")
# if no equals, just repeat it
if equalspos == -1:
returnline = quote.rstripeol(line)+eol
elif 0 <= hashpos < equalspos:
# Assume that this is a '#' comment line
returnline = quote.rstripeol(line)+eol
# otherwise, this is a definition
else:
# now deal with the current string...
key = line[:equalspos].strip()
lookupkey = key.replace(" ", "")
# Calculate space around the equal sign
prespace = line[len(line[:equalspos].rstrip()):equalspos]
postspacestart = len(line[equalspos+1:])
postspaceend = len(line[equalspos+1:].lstrip())
postspace = line[equalspos+1:equalspos+(postspacestart-postspaceend)+1]
self.quotechar = line[equalspos+(postspacestart-postspaceend)+1]
inlinecomment_pos = line.rfind("%s;" % self.quotechar)
if inlinecomment_pos > -1:
inlinecomment = line[inlinecomment_pos+2:]
else:
inlinecomment = ""
if self.inputdict.has_key(lookupkey):
self.inecho = False
value = php.phpencode(self.inputdict[lookupkey], self.quotechar)
if isinstance(value, str):
value = value.decode('utf8')
returnline = key + prespace + "=" + postspace + self.quotechar + value + self.quotechar + ';' + inlinecomment + eol
else:
self.inecho = True
returnline = line+eol
# no string termination means carry string on to next line
endpos = line.rfind("%s;" % self.quotechar)
# if there was no '; or the quote is escaped, we have to continue
if endpos == -1 or line[endpos-1] == '\\':
self.inmultilinemsgid = True
if isinstance(returnline, unicode):
returnline = returnline.encode('utf-8')
return returnline
def convertline(self, line):
line = six.text_type(line, 'utf-8')
returnline = ""
# handle multiline msgid if we're in one
if self.inmultilinemsgid:
# see if there's more
endpos = line.rfind("%s%s" % (self.quotechar, self.enddel))
# if there was no '; or the quote is escaped, we have to continue
if endpos >= 0 and line[endpos - 1] != '\\':
self.inmultilinemsgid = False
# if we're echoing...
if self.inecho:
returnline = line
# otherwise, this could be a comment
elif line.strip()[:2] == '//' or line.strip()[:2] == '/*':
returnline = quote.rstripeol(line) + eol
elif line.lower().replace(" ", "").find('array(') != -1:
self.inarray = True
self.prename = line[:line.find('=')].strip() + "->"
self.equaldel = "=>"
self.enddel = ","
returnline = quote.rstripeol(line) + eol
elif self.inarray and line.find(');') != -1:
self.inarray = False
self.equaldel = "="
self.enddel = ";"
self.prename = ""
returnline = quote.rstripeol(line) + eol
else:
line = quote.rstripeol(line)
equalspos = line.find(self.equaldel)
hashpos = line.find("#")
# if no equals, just repeat it
if equalspos == -1:
returnline = quote.rstripeol(line) + eol
elif 0 <= hashpos < equalspos:
# Assume that this is a '#' comment line
returnline = quote.rstripeol(line) + eol
# otherwise, this is a definition
else:
# now deal with the current string...
key = line[:equalspos].rstrip()
lookupkey = self.prename + key.lstrip()
# Calculate space around the equal sign
prespace = line[len(line[:equalspos].rstrip()):equalspos]
postspacestart = len(line[equalspos + len(self.equaldel):])
postspaceend = len(line[equalspos +
len(self.equaldel):].lstrip())
postspace = line[equalspos + len(self.equaldel):equalspos +
(postspacestart - postspaceend) +
len(self.equaldel)]
self.quotechar = line[equalspos +
(postspacestart - postspaceend) +
len(self.equaldel)]
inlinecomment_pos = line.rfind("%s%s" %
(self.quotechar, self.enddel))
if inlinecomment_pos > -1:
inlinecomment = line[inlinecomment_pos + 2:]
else:
inlinecomment = ""
if lookupkey in self.inputstore.locationindex:
unit = self.inputstore.locationindex[lookupkey]
if ((unit.isfuzzy() and not self.includefuzzy)
or len(unit.target) == 0):
value = unit.source
else:
value = unit.target
value = php.phpencode(value, self.quotechar)
self.inecho = False
if isinstance(value, bytes):
value = value.decode('utf8')
params = {
"key": key,
"pre": prespace,
"del": self.equaldel,
"post": postspace,
"quote": self.quotechar,
"value": value,
"enddel": self.enddel,
"comment": inlinecomment,
"eol": eol,
}
returnline = ("%(key)s%(pre)s%(del)s%(post)s%(quote)s"
"%(value)s%(quote)s%(enddel)s%(comment)s"
"%(eol)s" % params)
else:
self.inecho = True
returnline = line + eol
# no string termination means carry string on to next line
endpos = line.rfind("%s%s" % (self.quotechar, self.enddel))
# if there was no '; or the quote is escaped, we have to
# continue
if endpos == -1 or line[endpos - 1] == '\\':
self.inmultilinemsgid = True
if isinstance(returnline, six.text_type):
returnline = returnline.encode('utf-8')
return returnline
def convertline(self, line):
line = unicode(line, 'utf-8')
returnline = ""
# handle multiline msgid if we're in one
if self.inmultilinemsgid:
# see if there's more
endpos = line.rfind("%s%s" % (self.quotechar, self.enddel))
# if there was no '; or the quote is escaped, we have to continue
if endpos >= 0 and line[endpos-1] != '\\':
self.inmultilinemsgid = False
# if we're echoing...
if self.inecho:
returnline = line
# otherwise, this could be a comment
elif line.strip()[:2] == '//' or line.strip()[:2] == '/*':
returnline = quote.rstripeol(line) + eol
elif line.find('array(') != -1:
self.inarray = True
self.prename = line[:line.find('=')].strip() + "->"
self.equaldel = "=>"
self.enddel = ","
returnline = quote.rstripeol(line) + eol
elif self.inarray and line.find(');') != -1:
self.inarray = False
self.equaldel = "="
self.enddel = ";"
self.prename = ""
returnline = quote.rstripeol(line) + eol
else:
line = quote.rstripeol(line)
equalspos = line.find(self.equaldel)
hashpos = line.find("#")
# if no equals, just repeat it
if equalspos == -1:
returnline = quote.rstripeol(line) + eol
elif 0 <= hashpos < equalspos:
# Assume that this is a '#' comment line
returnline = quote.rstripeol(line) + eol
# otherwise, this is a definition
else:
# now deal with the current string...
key = line[:equalspos].rstrip()
lookupkey = self.prename + key.lstrip()
# Calculate space around the equal sign
prespace = line[len(line[:equalspos].rstrip()):equalspos]
postspacestart = len(line[equalspos+len(self.equaldel):])
postspaceend = len(line[equalspos+len(self.equaldel):].lstrip())
postspace = line[equalspos+len(self.equaldel):equalspos+(postspacestart-postspaceend)+len(self.equaldel)]
self.quotechar = line[equalspos+(postspacestart-postspaceend)+len(self.equaldel)]
inlinecomment_pos = line.rfind("%s%s" % (self.quotechar,
self.enddel))
if inlinecomment_pos > -1:
inlinecomment = line[inlinecomment_pos+2:]
else:
inlinecomment = ""
if lookupkey in self.inputstore.locationindex:
unit = self.inputstore.locationindex[lookupkey]
if (unit.isfuzzy() and not self.includefuzzy) or len(unit.target) == 0:
value = unit.source
else:
value = unit.target
value = php.phpencode(value, self.quotechar)
self.inecho = False
if isinstance(value, str):
value = value.decode('utf8')
returnline = "%(key)s%(pre)s%(del)s%(post)s%(quote)s%(value)s%(quote)s%(enddel)s%(comment)s%(eol)s" % {
"key": key,
"pre": prespace, "del": self.equaldel,
"post": postspace,
"quote": self.quotechar, "value": value,
"enddel": self.enddel,
"comment": inlinecomment, "eol": eol,
}
else:
self.inecho = True
returnline = line + eol
# no string termination means carry string on to next line
endpos = line.rfind("%s%s" % (self.quotechar, self.enddel))
# if there was no '; or the quote is escaped, we have to
# continue
if endpos == -1 or line[endpos-1] == '\\':
self.inmultilinemsgid = True
if isinstance(returnline, unicode):
returnline = returnline.encode('utf-8')
return returnline
