This commit is contained in:
Mai Gillmann
2019-12-17 14:09:10 +01:00
parent 66e908fc8a
commit 4791d00a43
2122 changed files with 423791 additions and 0 deletions
@@ -0,0 +1,72 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2009-2018 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
"""Parse SQL statements."""
# Setup namespace
from sqlparse import sql
from sqlparse import cli
from sqlparse import engine
from sqlparse import tokens
from sqlparse import filters
from sqlparse import formatter
from sqlparse.compat import text_type
__version__ = '0.3.0'
__all__ = ['engine', 'filters', 'formatter', 'sql', 'tokens', 'cli']
def parse(sql, encoding=None):
"""Parse sql and return a list of statements.
:param sql: A string containing one or more SQL statements.
:param encoding: The encoding of the statement (optional).
:returns: A tuple of :class:`~sqlparse.sql.Statement` instances.
"""
return tuple(parsestream(sql, encoding))
def parsestream(stream, encoding=None):
"""Parses sql statements from file-like object.
:param stream: A file-like object.
:param encoding: The encoding of the stream contents (optional).
:returns: A generator of :class:`~sqlparse.sql.Statement` instances.
"""
stack = engine.FilterStack()
stack.enable_grouping()
return stack.run(stream, encoding)
def format(sql, encoding=None, **options):
"""Format *sql* according to *options*.
Available options are documented in :ref:`formatting`.
In addition to the formatting options this function accepts the
keyword "encoding" which determines the encoding of the statement.
:returns: The formatted SQL statement as string.
"""
stack = engine.FilterStack()
options = formatter.validate_options(options)
stack = formatter.build_filter_stack(stack, options)
stack.postprocess.append(filters.SerializerUnicode())
return u''.join(stack.run(sql, encoding))
def split(sql, encoding=None):
"""Split *sql* into single statements.
:param sql: A string containing one or more SQL statements.
:param encoding: The encoding of the statement (optional).
:returns: A list of strings.
"""
stack = engine.FilterStack()
return [text_type(stmt).strip() for stmt in stack.run(sql, encoding)]
@@ -0,0 +1,23 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (C) 2009-2018 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
"""Entrypoint module for `python -m sqlparse`.
Why does this file exist, and why __main__? For more info, read:
- https://www.python.org/dev/peps/pep-0338/
- https://docs.python.org/2/using/cmdline.html#cmdoption-m
- https://docs.python.org/3/using/cmdline.html#cmdoption-m
"""
import sys
from sqlparse.cli import main
if __name__ == '__main__':
sys.exit(main())
@@ -0,0 +1,41 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2009-2018 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
from sqlparse.filters.others import SerializerUnicode
from sqlparse.filters.others import StripCommentsFilter
from sqlparse.filters.others import StripWhitespaceFilter
from sqlparse.filters.others import SpacesAroundOperatorsFilter
from sqlparse.filters.output import OutputPHPFilter
from sqlparse.filters.output import OutputPythonFilter
from sqlparse.filters.tokens import KeywordCaseFilter
from sqlparse.filters.tokens import IdentifierCaseFilter
from sqlparse.filters.tokens import TruncateStringFilter
from sqlparse.filters.reindent import ReindentFilter
from sqlparse.filters.right_margin import RightMarginFilter
from sqlparse.filters.aligned_indent import AlignedIndentFilter
__all__ = [
'SerializerUnicode',
'StripCommentsFilter',
'StripWhitespaceFilter',
'SpacesAroundOperatorsFilter',
'OutputPHPFilter',
'OutputPythonFilter',
'KeywordCaseFilter',
'IdentifierCaseFilter',
'TruncateStringFilter',
'ReindentFilter',
'RightMarginFilter',
'AlignedIndentFilter',
]
@@ -0,0 +1,61 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2009-2018 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
from sqlparse import tokens as T
from sqlparse.compat import text_type
class _CaseFilter(object):
ttype = None
def __init__(self, case=None):
case = case or 'upper'
self.convert = getattr(text_type, case)
def process(self, stream):
for ttype, value in stream:
if ttype in self.ttype:
value = self.convert(value)
yield ttype, value
class KeywordCaseFilter(_CaseFilter):
ttype = T.Keyword
class IdentifierCaseFilter(_CaseFilter):
ttype = T.Name, T.String.Symbol
def process(self, stream):
for ttype, value in stream:
if ttype in self.ttype and value.strip()[0] != '"':
value = self.convert(value)
yield ttype, value
class TruncateStringFilter(object):
def __init__(self, width, char):
self.width = width
self.char = char
def process(self, stream):
for ttype, value in stream:
if ttype != T.Literal.String.Single:
yield ttype, value
continue
if value[:2] == "''":
inner = value[2:-2]
quote = "''"
else:
inner = value[1:-1]
quote = "'"
if len(inner) > self.width:
value = ''.join((quote, inner[:self.width], self.char, quote))
yield ttype, value
@@ -0,0 +1,123 @@
# -*- coding: utf-8 -*-
#
# Copyright (C) 2009-2018 the sqlparse authors and contributors
# <see AUTHORS file>
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
import itertools
import re
from collections import deque
from contextlib import contextmanager
from sqlparse.compat import text_type
# This regular expression replaces the home-cooked parser that was here before.
# It is much faster, but requires an extra post-processing step to get the
# desired results (that are compatible with what you would expect from the
# str.splitlines() method).
#
# It matches groups of characters: newlines, quoted strings, or unquoted text,
# and splits on that basis. The post-processing step puts those back together
# into the actual lines of SQL.
SPLIT_REGEX = re.compile(r"""
(
(?: # Start of non-capturing group
(?:\r\n|\r|\n) | # Match any single newline, or
[^\r\n'"]+ | # Match any character series without quotes or
# newlines, or
"(?:[^"\\]|\\.)*" | # Match double-quoted strings, or
'(?:[^'\\]|\\.)*' # Match single quoted strings
)
)
""", re.VERBOSE)
LINE_MATCH = re.compile(r'(\r\n|\r|\n)')
def split_unquoted_newlines(stmt):
"""Split a string on all unquoted newlines.
Unlike str.splitlines(), this will ignore CR/LF/CR+LF if the requisite
character is inside of a string."""
text = text_type(stmt)
lines = SPLIT_REGEX.split(text)
outputlines = ['']
for line in lines:
if not line:
continue
elif LINE_MATCH.match(line):
outputlines.append('')
else:
outputlines[-1] += line
return outputlines
def remove_quotes(val):
"""Helper that removes surrounding quotes from strings."""
if val is None:
return
if val[0] in ('"', "'") and val[0] == val[-1]:
val = val[1:-1]
return val
def recurse(*cls):
"""Function decorator to help with recursion
:param cls: Classes to not recurse over
:return: function
"""
def wrap(f):
def wrapped_f(tlist):
for sgroup in tlist.get_sublists():
if not isinstance(sgroup, cls):
wrapped_f(sgroup)
f(tlist)
return wrapped_f
return wrap
def imt(token, i=None, m=None, t=None):
"""Helper function to simplify comparisons Instance, Match and TokenType
:param token:
:param i: Class or Tuple/List of Classes
:param m: Tuple of TokenType & Value. Can be list of Tuple for multiple
:param t: TokenType or Tuple/List of TokenTypes
:return: bool
"""
clss = i
types = [t, ] if t and not isinstance(t, list) else t
mpatterns = [m, ] if m and not isinstance(m, list) else m
if token is None:
return False
elif clss and isinstance(token, clss):
return True
elif mpatterns and any(token.match(*pattern) for pattern in mpatterns):
return True
elif types and any(token.ttype in ttype for ttype in types):
return True
else:
return False
def consume(iterator, n):
"""Advance the iterator n-steps ahead. If n is none, consume entirely."""
deque(itertools.islice(iterator, n), maxlen=0)
@contextmanager
def offset(filter_, n=0):
filter_.offset += n
yield
filter_.offset -= n
@contextmanager
def indent(filter_, n=1):
filter_.indent += n
yield
filter_.indent -= n