jiuyuan
/
test_ok1
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[svn r38262] Fixed support for tokenizing multi-line strings that use \ to span lines. 

--HG--
branch : trunk
This commit is contained in:
guido 2007-02-09 16:13:30 +01:00
parent aa4896fa04
commit 30608ea412
2 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
py/apigen/source/color.py
View File

@ -12,6 +12,7 @@ class PythonSchema(object):
'return', 'try', 'while', 'with', 'yield']
alt_keyword = ['as', 'assert', 'class', 'def', 'del', 'exec', 'from',
'global', 'import', 'lambda', 'pass', 'print']
linejoin = r'\\'
class Token(object):
data = None
@ -59,6 +60,12 @@ class Tokenizer(object):
self._re_strings_full.append(
re.compile(r'%s[^\\%s]+(\\.[^\\%s]*)*%s' % (d, d, d, d)))
self._re_strings_empty.append(re.compile('%s%s' % (d, d)))
if schema.linejoin:
j = schema.linejoin
for d in schema.string + schema.multiline_string:
self._re_strings_multiline.append(
(re.compile('%s.*%s' % (d, j)),
re.compile('.*?%s' % (d,))))
for d in schema.multiline_string:
self._re_strings_multiline.append((re.compile('%s.*' % (d,), re.S),
re.compile('.*?%s' % (d,))))
@ -105,6 +112,7 @@ class Tokenizer(object):
def _check_multiline_strings(self, data):
token = None
for start, end in self._re_strings_multiline:
print dir(start), end
m = start.match(data)
if m:
s = m.group(0)

9
py/apigen/source/testing/test_color.py
View File

@ -75,6 +75,15 @@ class TestTokenizer(object):
res = list(t.tokenize('bar'))
assert res == [Token('bar', type='word')]
def test_string_multiline_slash(self):
t = Tokenizer(PythonSchema)
res = list(t.tokenize("'foo\\"))
assert res == [Token("'foo\\", type='string')]
res = list(t.tokenize("bar'"))
assert res == [Token("bar'", type='string')]
res = list(t.tokenize("bar"))
assert res == [Token('bar', type='word')]
def test_string_following_printable(self):
assert self.tokens('."foo"') == [Token('.', type='unknown'),
Token('"foo"', type='string')]