VimPlug/jedi-fork
1
0
Fork 0
forked from VimPlug/jedi
Code Pull Requests Activity

Rework the parser so we can use arbitrary start nodes of the syntax.

Browse Source 
This also includes a rework for error recovery in the parser. This is now just possible for file_input parsing, which means for full files.
Includes also a refactoring of the tokenizer. No more do we have to add an additional newline, because it now works correctly (removes certain confusion.
This commit is contained in:
Dave Halter
2015-12-20 22:25:41 +01:00
parent 9a93d599da
commit c4906e0e3f
22 changed files with 246 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files
jedi/parser/__init__.py
+149 -120
View File
@@ -81,92 +81,87 @@ class ParserSyntaxError(object):
class Parser(object):
"""
This class is used to parse a Python file, it then divides them into a
class structure of different scopes.
AST_MAPPING = {
'expr_stmt': pt.ExprStmt,
'classdef': pt.Class,
'funcdef': pt.Function,
'file_input': pt.Module,
'import_name': pt.ImportName,
'import_from': pt.ImportFrom,
'break_stmt': pt.KeywordStatement,
'continue_stmt': pt.KeywordStatement,
'return_stmt': pt.ReturnStmt,
'raise_stmt': pt.KeywordStatement,
'yield_expr': pt.YieldExpr,
'del_stmt': pt.KeywordStatement,
'pass_stmt': pt.KeywordStatement,
'global_stmt': pt.GlobalStmt,
'nonlocal_stmt': pt.KeywordStatement,
'print_stmt': pt.KeywordStatement,
'assert_stmt': pt.AssertStmt,
'if_stmt': pt.IfStmt,
'with_stmt': pt.WithStmt,
'for_stmt': pt.ForStmt,
'while_stmt': pt.WhileStmt,
'try_stmt': pt.TryStmt,
'comp_for': pt.CompFor,
'decorator': pt.Decorator,
'lambdef': pt.Lambda,
'old_lambdef': pt.Lambda,
'lambdef_nocond': pt.Lambda,
}
: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 top_module: Use this module as a parent instead of `self.module`.
"""
def __init__(self, grammar, source, module_path=None, tokenizer=None):
self._ast_mapping = {
'expr_stmt': pt.ExprStmt,
'classdef': pt.Class,
'funcdef': pt.Function,
'file_input': pt.Module,
'import_name': pt.ImportName,
'import_from': pt.ImportFrom,
'break_stmt': pt.KeywordStatement,
'continue_stmt': pt.KeywordStatement,
'return_stmt': pt.ReturnStmt,
'raise_stmt': pt.KeywordStatement,
'yield_expr': pt.YieldExpr,
'del_stmt': pt.KeywordStatement,
'pass_stmt': pt.KeywordStatement,
'global_stmt': pt.GlobalStmt,
'nonlocal_stmt': pt.KeywordStatement,
'print_stmt': pt.KeywordStatement,
'assert_stmt': pt.AssertStmt,
'if_stmt': pt.IfStmt,
'with_stmt': pt.WithStmt,
'for_stmt': pt.ForStmt,
'while_stmt': pt.WhileStmt,
'try_stmt': pt.TryStmt,
'comp_for': pt.CompFor,
'decorator': pt.Decorator,
'lambdef': pt.Lambda,
'old_lambdef': pt.Lambda,
'lambdef_nocond': pt.Lambda,
}
class ParserError(Exception):
pass
self.syntax_errors = []
def __init__(self, grammar, source, start, tokenizer=None):
start_number = grammar.symbol2number[start]
self._global_names = []
self._omit_dedent_list = []
self._indent_counter = 0
self._last_failed_start_pos = (0, 0)
# TODO do print absolute import detection here.
#try:
# del python_grammar_no_print_statement.keywords["print"]
#except KeyError:
# pass # Doesn't exist in the Python 3 grammar.
#if self.options["print_function"]:
# python_grammar = pygram.python_grammar_no_print_statement
#else:
self._used_names = {}
self._scope_names_stack = [{}]
self._error_statement_stacks = []
added_newline = False
# The Python grammar needs a newline at the end of each statement.
if not source.endswith('\n'):
source += '\n'
added_newline = True
self._last_failed_start_pos = (0, 0)
self._global_names = []
# For the fast parser.
self.position_modifier = pt.PositionModifier()
p = PgenParser(grammar, self.convert_node, self.convert_leaf,
self.error_recovery)
tokenizer = tokenizer or tokenize.source_tokens(source)
self.module = p.parse(self._tokenize(tokenizer))
if self.module.type != 'file_input':
# If there's only one statement, we get back a non-module. That's
# not what we want, we want a module, so we add it here:
self.module = self.convert_node(grammar,
grammar.symbol2number['file_input'],
[self.module])
if added_newline:
self.remove_last_newline()
self.module.used_names = self._used_names
self.module.path = module_path
self.module.global_names = self._global_names
self.module.error_statement_stacks = self._error_statement_stacks
added_newline = False
# The Python grammar needs a newline at the end of each statement.
if not source.endswith('\n') and start == 'file_input':
source += '\n'
added_newline = True
p = PgenParser(grammar, self.convert_node, self.convert_leaf,
self.error_recovery, start_number)
if tokenizer is None:
tokenizer = tokenize.source_tokens(source)
try:
self._parsed = p.parse(self._tokenize(tokenizer))
except Parser.ParserError:
self._parsed = None
else:
if start == 'file_input' != self._parsed.type:
# If there's only one statement, we get back a non-module. That's
# not what we want, we want a module, so we add it here:
self._parsed = self.convert_node(grammar,
grammar.symbol2number['file_input'],
[self._parsed])
if added_newline:
self.remove_last_newline()
def get_parsed_node(self):
return self._parsed
def _tokenize(self, tokenizer):
for typ, value, start_pos, prefix in tokenizer:
if typ == OP:
typ = token.opmap[value]
yield typ, value, prefix, start_pos
def error_recovery(self, *args, **kwargs):
raise Parser.ParserError
def convert_node(self, grammar, type, children):
"""
@@ -178,7 +173,7 @@ class Parser(object):
"""
symbol = grammar.number2symbol[type]
try:
new_node = self._ast_mapping[symbol](children)
new_node = Parser.AST_MAPPING[symbol](children)
except KeyError:
new_node = pt.Node(symbol, children)
@@ -231,6 +226,83 @@ class Parser(object):
else:
return pt.Operator(self.position_modifier, value, start_pos, prefix)
def remove_last_newline(self):
"""
In all of this we need to work with _start_pos, because if we worked
with start_pos, we would need to check the position_modifier as well
(which is accounted for in the start_pos property).
"""
endmarker = self._parsed.children[-1]
# The newline is either in the endmarker as a prefix or the previous
# leaf as a newline token.
if endmarker.prefix.endswith('\n'):
endmarker.prefix = endmarker.prefix[:-1]
last_line = re.sub('.*\n', '', endmarker.prefix)
endmarker._start_pos = endmarker._start_pos[0] - 1, len(last_line)
else:
try:
newline = endmarker.get_previous()
except IndexError:
return # This means that the parser is empty.
while True:
if newline.value == '':
# Must be a DEDENT, just continue.
try:
newline = newline.get_previous()
except IndexError:
# If there's a statement that fails to be parsed, there
# will be no previous leaf. So just ignore it.
break
elif newline.value != '\n':
# This may happen if error correction strikes and removes
# a whole statement including '\n'.
break
else:
newline.value = ''
if self._last_failed_start_pos > newline._start_pos:
# It may be the case that there was a syntax error in a
# function. In that case error correction removes the
# right newline. So we use the previously assigned
# _last_failed_start_pos variable to account for that.
endmarker._start_pos = self._last_failed_start_pos
else:
endmarker._start_pos = newline._start_pos
break
class ParserWithRecovery(Parser):
"""
This class is used to parse a Python file, it then divides them into a
class structure of different scopes.
: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
"""
def __init__(self, grammar, source, module_path=None, tokenizer=None):
self.syntax_errors = []
self._omit_dedent_list = []
self._indent_counter = 0
# TODO do print absolute import detection here.
#try:
# del python_grammar_no_print_statement.keywords["print"]
#except KeyError:
# pass # Doesn't exist in the Python 3 grammar.
#if self.options["print_function"]:
# python_grammar = pygram.python_grammar_no_print_statement
#else:
super(ParserWithRecovery, self).__init__(grammar, source, 'file_input', tokenizer)
self.module = self._parsed
self.module.used_names = self._used_names
self.module.path = module_path
self.module.global_names = self._global_names
self.module.error_statement_stacks = self._error_statement_stacks
def error_recovery(self, grammar, stack, typ, value, start_pos, prefix,
add_token_callback):
"""
@@ -349,46 +421,3 @@ class Parser(object):
def __repr__(self):
return "<%s: %s>" % (type(self).__name__, self.module)
def remove_last_newline(self):
"""
In all of this we need to work with _start_pos, because if we worked
with start_pos, we would need to check the position_modifier as well
(which is accounted for in the start_pos property).
"""
endmarker = self.module.children[-1]
# The newline is either in the endmarker as a prefix or the previous
# leaf as a newline token.
if endmarker.prefix.endswith('\n'):
endmarker.prefix = endmarker.prefix[:-1]
last_line = re.sub('.*\n', '', endmarker.prefix)
endmarker._start_pos = endmarker._start_pos[0] - 1, len(last_line)
else:
try:
newline = endmarker.get_previous()
except IndexError:
return # This means that the parser is empty.
while True:
if newline.value == '':
# Must be a DEDENT, just continue.
try:
newline = newline.get_previous()
except IndexError:
# If there's a statement that fails to be parsed, there
# will be no previous leaf. So just ignore it.
break
elif newline.value != '\n':
# This may happen if error correction strikes and removes
# a whole statement including '\n'.
break
else:
newline.value = ''
if self._last_failed_start_pos > newline._start_pos:
# It may be the case that there was a syntax error in a
# function. In that case error correction removes the
# right newline. So we use the previously assigned
# _last_failed_start_pos variable to account for that.
endmarker._start_pos = self._last_failed_start_pos
else:
endmarker._start_pos = newline._start_pos
break
jedi/parser/fast.py
+7 -6
View File
@@ -8,7 +8,7 @@ from itertools import chain
from jedi._compatibility import use_metaclass
from jedi import settings
from jedi.parser import Parser
from jedi.parser import ParserWithRecovery
from jedi.parser import tree
from jedi import cache
from jedi import debug
@@ -52,8 +52,9 @@ class FastModule(tree.Module):
return "<fast.%s: %s@%s-%s>" % (type(self).__name__, self.name,
self.start_pos[0], self.end_pos[0])
# To avoid issues with with the `parser.Parser`, we need setters that do
# nothing, because if pickle comes along and sets those values.
# To avoid issues with with the `parser.ParserWithRecovery`, we need
# setters that do nothing, because if pickle comes along and sets those
# values.
@global_names.setter
def global_names(self, value):
pass
@@ -99,10 +100,10 @@ class CachedFastParser(type):
""" This is a metaclass for caching `FastParser`. """
def __call__(self, grammar, source, module_path=None):
if not settings.fast_parser:
return Parser(grammar, source, module_path)
return ParserWithRecovery(grammar, source, module_path)
pi = cache.parser_cache.get(module_path, None)
if pi is None or isinstance(pi.parser, Parser):
if pi is None or isinstance(pi.parser, ParserWithRecovery):
p = super(CachedFastParser, self).__call__(grammar, source, module_path)
else:
p = pi.parser # pi is a `cache.ParserCacheItem`
@@ -432,7 +433,7 @@ class FastParser(use_metaclass(CachedFastParser)):
else:
tokenizer = FastTokenizer(parser_code)
self.number_parsers_used += 1
p = Parser(self._grammar, parser_code, self.module_path, tokenizer=tokenizer)
p = ParserWithRecovery(self._grammar, parser_code, self.module_path, tokenizer=tokenizer)
end = line_offset + p.module.end_pos[0]
used_lines = self._lines[line_offset:end - 1]
jedi/parser/pgen2/parse.py
+1 -3
View File
@@ -60,7 +60,7 @@ class PgenParser(object):
"""
def __init__(self, grammar, convert_node, convert_leaf, error_recovery):
def __init__(self, grammar, convert_node, convert_leaf, error_recovery, start):
"""Constructor.
The grammar argument is a grammar.Grammar instance; see the
@@ -90,8 +90,6 @@ class PgenParser(object):
self.convert_node = convert_node
self.convert_leaf = convert_leaf
# Prepare for parsing.
start = self.grammar.start
# Each stack entry is a tuple: (dfa, state, node).
# A node is a tuple: (type, children),
# where children is a list of nodes or None
jedi/parser/tokenize.py
+7 -3
View File
@@ -149,7 +149,7 @@ ALWAYS_BREAK_TOKENS = (';', 'import', 'from', 'class', 'def', 'try', 'except',
def source_tokens(source):
"""Generate tokens from a the source code (string)."""
source = source + '\n' # end with \n, because the parser needs it
source = source
readline = StringIO(source).readline
return generate_tokens(readline)
@@ -165,6 +165,7 @@ def generate_tokens(readline):
paren_level = 0 # count parentheses
indents = [0]
lnum = 0
max = 0
numchars = '0123456789'
contstr = ''
contline = None
@@ -282,9 +283,12 @@ def generate_tokens(readline):
paren_level -= 1
yield OP, token, spos, prefix
end_pos = (lnum, max - 1)
if new_line:
end_pos = lnum + 1, 0
else:
end_pos = lnum, max - 1
# As the last position we just take the maximally possible position. We
# remove -1 for the last new line.
for indent in indents[1:]:
yield DEDENT, '', end_pos, ''
yield ENDMARKER, '', end_pos, prefix
yield ENDMARKER, '', end_pos, additional_prefix
jedi/parser/tree.py
+2 -2
View File
@@ -14,8 +14,8 @@ The easiest way to play with this module is to use :class:`parsing.Parser`.
:attr:`parsing.Parser.module` holds an instance of :class:`Module`:
>>> from jedi._compatibility import u
>>> from jedi.parser import Parser, load_grammar
>>> parser = Parser(load_grammar(), u('import os'), 'example.py')
>>> from jedi.parser import ParserWithRecovery, load_grammar
>>> parser = ParserWithRecovery(load_grammar(), u('import os'), 'example.py')
>>> submodule = parser.module
>>> submodule
<Module: example.py@1-1>
jedi/parser/user_context.py
+2 -2
View File
@@ -4,7 +4,7 @@ import keyword
from jedi import cache
from jedi import common
from jedi.parser import tokenize, Parser
from jedi.parser import tokenize, ParserWithRecovery
from jedi._compatibility import u
from jedi.parser.fast import FastParser
from jedi.parser import tree
@@ -284,7 +284,7 @@ class UserContextParser(object):
# Don't pickle that module, because the main module is changing quickly
cache.save_parser(self._path, parser, pickling=False)
else:
parser = Parser(self._grammar, self._source, self._path)
parser = ParserWithRecovery(self._grammar, self._source, self._path)
self._parser_done_callback(parser)
return parser