1
0
forked from VimPlug/jedi

Added a grammar param to the parser.

This commit is contained in:
Dave Halter
2014-11-24 01:10:39 +01:00
parent c152a1c58b
commit 9f45f18ad1
14 changed files with 60 additions and 44 deletions

View File

@@ -15,7 +15,7 @@ import sys
from itertools import chain
from jedi._compatibility import next, unicode, builtins
from jedi.parser import Parser
from jedi.parser import Parser, load_grammar
from jedi.parser.tokenize import source_tokens
from jedi.parser import tree as pr
from jedi.parser.user_context import UserContext, UserContextParser
@@ -100,9 +100,11 @@ class Script(object):
cache.clear_time_caches()
debug.reset_time()
self._grammar = load_grammar('grammar3.4')
self._user_context = UserContext(self.source, self._pos)
self._parser = UserContextParser(self.source, path, self._pos, self._user_context)
self._evaluator = Evaluator()
self._parser = UserContextParser(self._grammar, self.source, path,
self._pos, self._user_context)
self._evaluator = Evaluator(self._grammar)
debug.speed('init')
@property
@@ -277,7 +279,7 @@ class Script(object):
def _get_under_cursor_stmt(self, cursor_txt):
tokenizer = source_tokens(cursor_txt, line_offset=self._pos[0] - 1)
r = Parser(cursor_txt, no_docstr=True, tokenizer=tokenizer)
r = Parser(self._grammar, cursor_txt, tokenizer=tokenizer)
try:
# Take the last statement available.
stmt = r.module.statements[-1]
@@ -674,11 +676,10 @@ def defined_names(source, path=None, encoding='utf-8'):
:rtype: list of classes.Definition
"""
parser = Parser(
common.source_to_unicode(source, encoding),
module_path=path,
)
return classes.defined_names(Evaluator(), parser.module)
grammar = load_grammar('grammar3.4')
parser = Parser(grammar, common.source_to_unicode(source, encoding),
module_path=path)
return classes.defined_names(Evaluator(grammar), parser.module)
def names(source=None, path=None, encoding='utf-8', all_scopes=False,

View File

@@ -60,7 +60,7 @@ def usages(evaluator, definition_names, mods):
compare_definitions = compare_array(definition_names)
mods |= set([d.get_parent_until() for d in definition_names])
definitions = []
for m in imports.get_modules_containing_name(mods, search_name):
for m in imports.get_modules_containing_name(evaluator, mods, search_name):
try:
check_names = m.used_names[search_name]
except KeyError:

View File

@@ -91,7 +91,8 @@ from jedi.evaluate.helpers import FakeStatement, deep_ast_copy, call_of_name
class Evaluator(object):
def __init__(self):
def __init__(self, grammar):
self._grammar = grammar
self.memoize_cache = {} # for memoize decorators
self.import_cache = {} # like `sys.modules`.
self.compiled_cache = {} # see `compiled.create()`

View File

@@ -8,8 +8,7 @@ import os
import inspect
from jedi._compatibility import is_py3, builtins, unicode
from jedi.parser import Parser
from jedi.parser import tokenize
from jedi.parser import Parser, load_grammar
from jedi.parser.tree import Class
from jedi.evaluate.helpers import FakeName
@@ -31,7 +30,8 @@ def _load_faked_module(module):
except IOError:
modules[module_name] = None
return
module = Parser(unicode(source), module_name).module
grammar = load_grammar('grammar3.4')
module = Parser(grammar, unicode(source), module_name).module
modules[module_name] = module
if module_name == 'builtins' and not is_py3:

View File

@@ -127,7 +127,7 @@ def _evaluate_for_statement_string(evaluator, string, module):
# (e.g., 'threading' in 'threading.Thread').
string = 'import %s\n' % element + string
p = Parser(code % indent_block(string), no_docstr=True)
p = Parser(evaluator.grammar, code % indent_block(string), no_docstr=True)
pseudo_cls = p.module.subscopes[0]
try:
stmt = pseudo_cls.statements[-1]

View File

@@ -174,7 +174,7 @@ def search_params(evaluator, param):
try:
result = []
# This is like backtracking: Get the first possible result.
for mod in imports.get_modules_containing_name([current_module], func_name):
for mod in imports.get_modules_containing_name(evaluator, [current_module], func_name):
result = get_params_for_module(mod)
if result:
break

View File

@@ -492,8 +492,8 @@ def get_names_of_scope(evaluator, scope, position=None, star_search=True, includ
the current scope is function:
>>> from jedi._compatibility import u
>>> from jedi.parser import Parser
>>> parser = Parser(u('''
>>> from jedi.parser import Parser, load_grammar
>>> parser = Parser(load_grammar('python3.4'), u('''
... x = ['a', 'b', 'c']
... def func():
... y = None

View File

@@ -184,7 +184,7 @@ class ImportWrapper2(pr.Base):
rel_path = os.path.join(self._importer.get_relative_path(),
'__init__.py')
if os.path.exists(rel_path):
m = _load_module(rel_path)
m = _load_module(self.evaluator, rel_path)
names += m.get_defined_names()
else:
# flask
@@ -590,9 +590,9 @@ class _Importer(object):
else:
source = current_namespace[0].read()
current_namespace[0].close()
return _load_module(path, source, sys_path=sys_path), rest
return _load_module(self.evaluator, path, source, sys_path=sys_path), rest
else:
return _load_module(name=path, sys_path=sys_path), rest
return _load_module(self.evaluator, name=path, sys_path=sys_path), rest
def follow_imports(evaluator, scopes):
@@ -633,7 +633,7 @@ def remove_star_imports(evaluator, scope, ignored_modules=()):
return set(modules)
def _load_module(path=None, source=None, name=None, sys_path=None):
def _load_module(evaluator, path=None, source=None, name=None, sys_path=None):
def load(source):
dotted_path = path and compiled.dotted_from_fs_path(path, sys_path)
if path is not None and path.endswith('.py') \
@@ -644,7 +644,7 @@ def _load_module(path=None, source=None, name=None, sys_path=None):
else:
return compiled.load_module(path, name)
p = path or name
p = fast.FastParser(common.source_to_unicode(source), p)
p = fast.FastParser(evaluator.grammar, common.source_to_unicode(source), p)
cache.save_parser(path, name, p)
return p.module
@@ -652,7 +652,7 @@ def _load_module(path=None, source=None, name=None, sys_path=None):
return load(source) if cached is None else cached.module
def get_modules_containing_name(mods, name):
def get_modules_containing_name(evaluator, mods, name):
"""
Search a name in the directories of modules.
"""
@@ -669,7 +669,7 @@ def get_modules_containing_name(mods, name):
with open(path, 'rb') as f:
source = source_to_unicode(f.read())
if name in source:
return _load_module(path, source)
return _load_module(evaluator, path, source)
# skip non python modules
mods = set(m for m in mods if not isinstance(m, compiled.CompiledObject))

View File

@@ -227,7 +227,7 @@ def collections_namedtuple(evaluator, obj, params):
)
# Parse source
generated_class = Parser(unicode(source)).module.subscopes[0]
generated_class = Parser(evaluator.grammar, unicode(source)).module.subscopes[0]
return [er.Class(evaluator, generated_class)]

View File

@@ -140,7 +140,7 @@ def sys_path_with_modifications(evaluator, module):
except IOError:
pass
else:
p = Parser(common.source_to_unicode(source), module_path)
p = Parser(evaluator.grammar, common.source_to_unicode(source), module_path)
for path in _check_module(p.module):
if path not in buildout_paths:
buildout_paths.add(path)

View File

@@ -15,16 +15,14 @@ within the statement. This lowers memory usage and cpu time and reduces the
complexity of the ``Parser`` (there's another parser sitting inside
``Statement``, which produces ``Array`` and ``Call``).
"""
import keyword
import logging
import os
from jedi._compatibility import next, unicode
from jedi import debug
from jedi._compatibility import next
from jedi import common
from jedi.parser import tree as pt
from jedi.parser import tokenize
from jedi.parser import pytree
from jedi.parser.pgen2 import Driver
from jedi.parser import pgen2
OPERATOR_KEYWORDS = 'and', 'for', 'if', 'else', 'in', 'is', 'lambda', 'not', 'or'
@@ -33,20 +31,33 @@ STATEMENT_KEYWORDS = 'assert', 'del', 'global', 'nonlocal', 'raise', \
'return', 'yield', 'pass', 'continue', 'break'
_loaded_grammars = {}
def load_grammar(file):
global _loaded_grammars
path = os.path.join(os.path.dirname(__file__), file) + '.txt'
try:
return _loaded_grammars[path]
except KeyError:
return _loaded_grammars.setdefault(path, pgen2.load_grammar(path))
class Parser(object):
"""
This class is used to parse a Python file, it then divides them into a
class structure of different scopes.
:param source: The codebase for the parser.
:type source: str
:param grammar: The grammar object of pgen2. Loaded by load_grammar.
:param source: The codebase for the parser. Must be unicode.
:param module_path: The path of the module in the file system, may be None.
:type module_path: str
:param no_docstr: If True, a string at the beginning is not a docstr.
:param top_module: Use this module as a parent instead of `self.module`.
"""
def __init__(self, source, module_path=None, no_docstr=False,
tokenizer=None, top_module=None):
def __init__(self, grammar, source, module_path=None, tokenizer=None):
"""
This is the way I imagine a parser describing the init function
"""
if not source.endswith('\n'):
source += '\n'
@@ -90,8 +101,8 @@ class Parser(object):
self.used_names = {}
self.scope_names_stack = [{}]
logger = logging.getLogger("Jedi-Parser")
d = Driver(pytree.python_grammar, self.convert_node, self.convert_leaf,
self.error_recovery, logger=logger)
d = pgen2.Driver(grammar, self.convert_node,
self.convert_leaf, self.error_recovery, logger=logger)
self.module = d.parse_string(source).get_parent_until()
self.module.used_names = self.used_names

View File

@@ -56,13 +56,13 @@ class Module(pr.Module, pr.Simple):
class CachedFastParser(type):
""" This is a metaclass for caching `FastParser`. """
def __call__(self, source, module_path=None):
def __call__(self, grammar, source, module_path=None):
if not settings.fast_parser:
return Parser(source, module_path)
return Parser(grammar, source, module_path)
pi = cache.parser_cache.get(module_path, None)
if pi is None or isinstance(pi.parser, Parser):
p = super(CachedFastParser, self).__call__(source, module_path)
p = super(CachedFastParser, self).__call__(grammar, source, module_path)
else:
p = pi.parser # pi is a `cache.ParserCacheItem`
p.update(source)
@@ -186,8 +186,9 @@ class FastParser(use_metaclass(CachedFastParser)):
_keyword_re = re.compile('^[ \t]*(def|class|@|%s)' % '|'.join(tokenize.FLOWS))
def __init__(self, code, module_path=None):
def __init__(self, grammar, code, module_path=None):
# set values like `pr.Module`.
self._grammar = grammar
self.module_path = module_path
self.current_node = None

View File

@@ -18,6 +18,7 @@ from . import pgen2
# The grammar file
_GRAMMAR_FILE = os.path.join(os.path.dirname(__file__), "grammar3.4.txt")
python_grammar = pgen2.load_grammar(_GRAMMAR_FILE)
class Symbols(object):

View File

@@ -202,7 +202,8 @@ class UserContext(object):
class UserContextParser(object):
def __init__(self, source, path, position, user_context):
def __init__(self, grammar, source, path, position, user_context):
self._grammar = grammar
self._source = source
self._path = path and os.path.abspath(path)
self._position = position
@@ -211,7 +212,7 @@ class UserContextParser(object):
@cache.underscore_memoization
def _parser(self):
cache.invalidate_star_import_cache(self._path)
parser = FastParser(self._source, self._path)
parser = FastParser(self._grammar, self._source, self._path)
# Don't pickle that module, because the main module is changing quickly
cache.save_parser(self._path, None, parser, pickling=False)
return parser