def Tokens2Unicode(stream):
result = ""
for _, value in stream:
result += u(value)
return result
def _split_kwds(self, tlist):
split_words = ('FROM', 'STRAIGHT_JOIN$', 'JOIN$', 'AND', 'OR',
'GROUP', 'ORDER', 'UNION', 'VALUES',
'SET', 'BETWEEN', 'EXCEPT', 'HAVING')
def _next_token(i):
t = tlist.token_next_match(i, T.Keyword, split_words,
regex=True)
if t and t.value.upper() == 'BETWEEN':
t = _next_token(tlist.token_index(t) + 1)
if t and t.value.upper() == 'AND':
t = _next_token(tlist.token_index(t) + 1)
return t
idx = 0
token = _next_token(idx)
added = set()
while token:
prev = tlist.token_prev(tlist.token_index(token), False)
offset = 1
if prev and prev.is_whitespace() and prev not in added:
tlist.tokens.pop(tlist.token_index(prev))
offset += 1
uprev = u(prev)
if (prev and (uprev.endswith('\n') or uprev.endswith('\r'))):
nl = tlist.token_next(token)
else:
nl = self.nl()
added.add(nl)
tlist.insert_before(token, nl)
offset += 1
token = _next_token(tlist.token_index(nl) + offset)
def get_typecast(self):
"""Returns the typecast or ``None`` of this object as a string."""
marker = self.token_next_match(0, T.Punctuation, '::')
if marker is None:
return None
next_ = self.token_next(self.token_index(marker), False)
if next_ is None:
return None
return u(next_)
def split(sql, encoding=None):
"""Split *sql* into single statements.
:param sql: A string containting one or more SQL statements.
:param encoding: The encoding of the statement (optional).
:returns: A list of strings.
"""
stack = engine.FilterStack()
stack.split_statements = True
return [u(stmt).strip() for stmt in stack.run(sql, encoding)]
def process(self, stack, stmt):
self.count += 1
if self.count > 1:
varname = '%s%d' % (self.varname, self.count)
else:
varname = self.varname
has_nl = len(u(stmt).strip().splitlines()) > 1
stmt.tokens = self._process(stmt.tokens, varname, has_nl)
return stmt
def process(self, stack, stmt):
if isinstance(stmt, sql.Statement):
self._curr_stmt = stmt
self._process(stmt)
if isinstance(stmt, sql.Statement):
if self._last_stmt is not None:
if u(self._last_stmt).endswith('\n'):
nl = '\n'
else:
nl = '\n\n'
stmt.tokens.insert(
0, sql.Token(T.Whitespace, nl))
if self._last_stmt != stmt:
self._last_stmt = stmt
def _process(self, stack, group, stream):
for token in stream:
if token.is_whitespace() and '\n' in token.value:
if token.value.endswith('\n'):
self.line = ''
else:
self.line = token.value.splitlines()[-1]
elif (token.is_group()
and token.__class__ not in self.keep_together):
token.tokens = self._process(stack, token, token.tokens)
else:
val = u(token)
if len(self.line) + len(val) > self.width:
match = re.search('^ +', self.line)
if match is not None:
indent = match.group()
else:
indent = ''
yield sql.Token(T.Whitespace, '\n%s' % indent)
self.line = indent
self.line += val
yield token
def _get_repr_value(self):
raw = u(self)
if len(raw) > 7:
raw = raw[:6] + u'...'
return re.sub('\s+', ' ', raw)
def __str__(self):
if sys.version_info[0] == 3:
return self.value
else:
return u(self).encode('utf-8')
def _to_string(self):
if sys.version_info[0] == 3:
return ''.join(x.value for x in self.flatten())
else:
return ''.join(u(x) for x in self.flatten())
def process(self, stack, stmt):
raw = u(stmt)
lines = split_unquoted_newlines(raw)
res = '\n'.join(line.rstrip() for line in lines)
return res
def __init__(self, width, char):
self.width = max(width, 1)
self.char = u(char)
