def extractpoline(line):
"""Remove quote and unescape line from po file.
@param line: a quoted line from a po file (msgid or msgstr)
"""
extracted = quote.extractwithoutquotes(line, '"', '"', '\\', includeescapes=unescapehandler)[0]
return extracted
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
# The quote characters should be the first and last characters in the
# string. Of course there could also be quote characters within the string.
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source,
quotechar,
quotechar,
allowreentry=False)
extracted = extracted.decode('utf-8')
if quotechar == "'":
extracted = extracted.replace("'", "'")
extracted = extracted.replace(""", "\"")
extracted = extracted.replace(""", "\"")
# FIXME these should probably be handled with a lookup
extracted = extracted.replace("»", u"»")
extracted = extracted.replace("%", "%")
extracted = extracted.replace("%", "%")
extracted = extracted.replace("%", "%")
#extracted = extracted.replace("<", "<") # Not really so useful.
#extracted = extracted.replace(">", ">") # Not really so useful.
return extracted
def extractpoline(line):
"""Remove quote and unescape line from po file.
:param line: a quoted line from a po file (msgid or msgstr)
.. deprecated:: 1.10
Replaced by :func:`unescape`. :func:`extractpoline` is kept to allow
tests of correctness, and in case of external users.
"""
extracted = quote.extractwithoutquotes(line, '"', '"', '\\', includeescapes=unescapehandler)[0]
return extracted
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source, quotechar, quotechar, allowreentry=False)
if quotechar == "'" and "'" in extracted:
extracted = extracted.replace("'", "'")
# the quote characters should be the first and last characters in the string
# of course there could also be quote characters within the string; not handled here
return extracted
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
# The quote characters should be the first and last characters in the
# string. Of course there could also be quote characters within the string.
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source, quotechar, quotechar, allowreentry=False)
extracted = extracted.decode('utf-8')
if quotechar == "'":
extracted = extracted.replace("'", "'")
extracted = quote.entitydecode(extracted, _DTD_NAME2CODEPOINT)
return extracted
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source,
quotechar,
quotechar,
allowreentry=False)
if quotechar == "'" and "'" in extracted:
extracted = extracted.replace("'", "'")
# the quote characters should be the first and last characters in the string
# of course there could also be quote characters within the string; not handled here
return extracted
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
# The quote characters should be the first and last characters in the
# string. Of course there could also be quote characters within the string.
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source,
quotechar,
quotechar,
allowreentry=False)
if quotechar == "'":
extracted = extracted.replace("'", "'")
return quote.entitydecode(extracted, _DTD_NAME2CODEPOINT)
def unquotefromdtd(source):
"""unquotes a quoted dtd definition"""
# extract the string, get rid of quoting
if len(source) == 0:
source = '""'
# The quote characters should be the first and last characters in the
# string. Of course there could also be quote characters within the string.
quotechar = source[0]
extracted, quotefinished = quote.extractwithoutquotes(source, quotechar, quotechar, allowreentry=False)
extracted = extracted.decode('utf-8')
if quotechar == "'":
extracted = extracted.replace("'", "'")
extracted = extracted.replace(""", "\"")
extracted = extracted.replace(""", "\"")
# FIXME these should probably be handled with a lookup
extracted = extracted.replace("»", "»")
extracted = extracted.replace("%", "%")
extracted = extracted.replace("%", "%")
extracted = extracted.replace("%", "%")
#extracted = extracted.replace("<", "<") # Not really so useful.
#extracted = extracted.replace(">", ">") # Not really so useful.
return extracted
def test_extractwithoutquotes_passfunc():
"""tests the extractwithoutquotes function with a function for includeescapes as a parameter"""
assert quote.extractwithoutquotes(
"<test \\r \\n \\t \\\\>", "<", ">", "\\", 0, isnewlineortabescape
) == ("test r \\n \\t \\", False)
def test_extractwithoutquotes():
"""tests the extractwithoutquotes function"""
assert quote.extractwithoutquotes("the <quoted> part", "<", ">", "\\", 0) == (
"quoted",
False,
)
assert quote.extractwithoutquotes("the 'quoted' part", "'", "'", "\\", 0) == (
"quoted",
False,
)
assert quote.extractwithoutquotes(
"the 'isn\\'t escaping fun' part", "'", "'", "\\", 0
) == ("isn\\'t escaping fun", False)
assert quote.extractwithoutquotes("the 'isn\\'t something ", "'", "'", "\\", 0) == (
"isn\\'t something ",
True,
)
assert quote.extractwithoutquotes("<quoted>\\", "<", ">", "\\", 0) == (
"quoted",
False,
)
assert quote.extractwithoutquotes("<quoted>\\\\<again>", "<", ">", "\\", 0) == (
"quotedagain",
False,
)
assert quote.extractwithoutquotes(
"<quoted><again\\\\", "<", ">", "\\", 0, True
) == ("quotedagain\\\\", True)
# don't include escapes...
assert quote.extractwithoutquotes(
"the 'isn\\'t escaping fun' part", "'", "'", "\\", 0, False
) == ("isn't escaping fun", False)
assert quote.extractwithoutquotes(
"the 'isn\\'t something ", "'", "'", "\\", 0, False
) == ("isn't something ", True)
assert quote.extractwithoutquotes("<quoted\\", "<", ">", "\\", 0, False) == (
"quoted",
True,
)
assert quote.extractwithoutquotes(
"<quoted><again\\\\", "<", ">", "\\", 0, False
) == ("quotedagain\\", True)
# escaping of quote char
assert quote.extractwithoutquotes("<quoted\\>", "<", ">", "\\", 0, False) == (
"quoted>",
True,
)
def test_extractwithoutquotes_passfunc():
"""tests the extractwithoutquotes function with a function for includeescapes as a parameter"""
assert quote.extractwithoutquotes("<test \\r \\n \\t \\\\>", "<", ">", "\\", 0, isnewlineortabescape) == ("test r \\n \\t \\", False)
def test_extractwithoutquotes():
"""tests the extractwithoutquotes function"""
assert quote.extractwithoutquotes("the <quoted> part", "<", ">", "\\", 0) == ("quoted", False)
assert quote.extractwithoutquotes("the 'quoted' part", "'", "'", "\\", 0) == ("quoted", False)
assert quote.extractwithoutquotes("the 'isn\\'t escaping fun' part", "'", "'", "\\", 0) == ("isn\\'t escaping fun", False)
assert quote.extractwithoutquotes("the 'isn\\'t something ", "'", "'", "\\", 0) == ("isn\\'t something ", True)
assert quote.extractwithoutquotes("<quoted>\\", "<", ">", "\\", 0) == ("quoted", False)
assert quote.extractwithoutquotes("<quoted>\\\\<again>", "<", ">", "\\", 0) == ("quotedagain", False)
assert quote.extractwithoutquotes("<quoted><again\\\\", "<", ">", "\\", 0, True) == ("quotedagain\\\\", True)
# don't include escapes...
assert quote.extractwithoutquotes("the 'isn\\'t escaping fun' part", "'", "'", "\\", 0, False) == ("isn't escaping fun", False)
assert quote.extractwithoutquotes("the 'isn\\'t something ", "'", "'", "\\", 0, False) == ("isn't something ", True)
assert quote.extractwithoutquotes("<quoted\\", "<", ">", "\\", 0, False) == ("quoted", True)
assert quote.extractwithoutquotes("<quoted><again\\\\", "<", ">", "\\", 0, False) == ("quotedagain\\", True)
# escaping of quote char
assert quote.extractwithoutquotes("<quoted\\>", "<", ">", "\\", 0, False) == ("quoted>", True)
