add RustPython parser

based on RustPython 67b338863ee6f16b0df0a7d1aa9debba55284651
This commit is contained in:
Sebastien Bourdeauducq 2021-11-03 16:34:05 +08:00
parent e89bc93b5f
commit 80c7bc1cbd
45 changed files with 8740 additions and 0 deletions

13
nac3ast/Cargo.toml Normal file
View File

@ -0,0 +1,13 @@
[package]
name = "rustpython-ast"
version = "0.1.0"
authors = ["RustPython Team"]
edition = "2018"
[features]
default = ["constant-optimization", "fold"]
constant-optimization = ["fold"]
fold = []
[dependencies]
num-bigint = "0.4.0"

125
nac3ast/Python.asdl Normal file
View File

@ -0,0 +1,125 @@
-- ASDL's 4 builtin types are:
-- identifier, int, string, constant
module Python
{
mod = Module(stmt* body, type_ignore* type_ignores)
| Interactive(stmt* body)
| Expression(expr body)
| FunctionType(expr* argtypes, expr returns)
stmt = FunctionDef(identifier name, arguments args,
stmt* body, expr* decorator_list, expr? returns,
string? type_comment)
| AsyncFunctionDef(identifier name, arguments args,
stmt* body, expr* decorator_list, expr? returns,
string? type_comment)
| ClassDef(identifier name,
expr* bases,
keyword* keywords,
stmt* body,
expr* decorator_list)
| Return(expr? value)
| Delete(expr* targets)
| Assign(expr* targets, expr value, string? type_comment)
| AugAssign(expr target, operator op, expr value)
-- 'simple' indicates that we annotate simple name without parens
| AnnAssign(expr target, expr annotation, expr? value, bool simple)
-- use 'orelse' because else is a keyword in target languages
| For(expr target, expr iter, stmt* body, stmt* orelse, string? type_comment)
| AsyncFor(expr target, expr iter, stmt* body, stmt* orelse, string? type_comment)
| While(expr test, stmt* body, stmt* orelse)
| If(expr test, stmt* body, stmt* orelse)
| With(withitem* items, stmt* body, string? type_comment)
| AsyncWith(withitem* items, stmt* body, string? type_comment)
| Raise(expr? exc, expr? cause)
| Try(stmt* body, excepthandler* handlers, stmt* orelse, stmt* finalbody)
| Assert(expr test, expr? msg)
| Import(alias* names)
| ImportFrom(identifier? module, alias* names, int level)
| Global(identifier* names)
| Nonlocal(identifier* names)
| Expr(expr value)
| Pass | Break | Continue
-- col_offset is the byte offset in the utf8 string the parser uses
attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
-- BoolOp() can use left & right?
expr = BoolOp(boolop op, expr* values)
| NamedExpr(expr target, expr value)
| BinOp(expr left, operator op, expr right)
| UnaryOp(unaryop op, expr operand)
| Lambda(arguments args, expr body)
| IfExp(expr test, expr body, expr orelse)
| Dict(expr?* keys, expr* values)
| Set(expr* elts)
| ListComp(expr elt, comprehension* generators)
| SetComp(expr elt, comprehension* generators)
| DictComp(expr key, expr value, comprehension* generators)
| GeneratorExp(expr elt, comprehension* generators)
-- the grammar constrains where yield expressions can occur
| Await(expr value)
| Yield(expr? value)
| YieldFrom(expr value)
-- need sequences for compare to distinguish between
-- x < 4 < 3 and (x < 4) < 3
| Compare(expr left, cmpop* ops, expr* comparators)
| Call(expr func, expr* args, keyword* keywords)
| FormattedValue(expr value, conversion_flag? conversion, expr? format_spec)
| JoinedStr(expr* values)
| Constant(constant value, string? kind)
-- the following expression can appear in assignment context
| Attribute(expr value, identifier attr, expr_context ctx)
| Subscript(expr value, expr slice, expr_context ctx)
| Starred(expr value, expr_context ctx)
| Name(identifier id, expr_context ctx)
| List(expr* elts, expr_context ctx)
| Tuple(expr* elts, expr_context ctx)
-- can appear only in Subscript
| Slice(expr? lower, expr? upper, expr? step)
-- col_offset is the byte offset in the utf8 string the parser uses
attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
expr_context = Load | Store | Del
boolop = And | Or
operator = Add | Sub | Mult | MatMult | Div | Mod | Pow | LShift
| RShift | BitOr | BitXor | BitAnd | FloorDiv
unaryop = Invert | Not | UAdd | USub
cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn
comprehension = (expr target, expr iter, expr* ifs, bool is_async)
excepthandler = ExceptHandler(expr? type, identifier? name, stmt* body)
attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
arguments = (arg* posonlyargs, arg* args, arg? vararg, arg* kwonlyargs,
expr?* kw_defaults, arg? kwarg, expr* defaults)
arg = (identifier arg, expr? annotation, string? type_comment)
attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
-- keyword arguments supplied to call (NULL identifier for **kwargs)
keyword = (identifier? arg, expr value)
attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
-- import name with optional 'as' alias.
alias = (identifier name, identifier? asname)
withitem = (expr context_expr, expr? optional_vars)
type_ignore = TypeIgnore(int lineno, string tag)
}

385
nac3ast/asdl.py Normal file
View File

@ -0,0 +1,385 @@
#-------------------------------------------------------------------------------
# Parser for ASDL [1] definition files. Reads in an ASDL description and parses
# it into an AST that describes it.
#
# The EBNF we're parsing here: Figure 1 of the paper [1]. Extended to support
# modules and attributes after a product. Words starting with Capital letters
# are terminals. Literal tokens are in "double quotes". Others are
# non-terminals. Id is either TokenId or ConstructorId.
#
# module ::= "module" Id "{" [definitions] "}"
# definitions ::= { TypeId "=" type }
# type ::= product | sum
# product ::= fields ["attributes" fields]
# fields ::= "(" { field, "," } field ")"
# field ::= TypeId ["?" | "*"] [Id]
# sum ::= constructor { "|" constructor } ["attributes" fields]
# constructor ::= ConstructorId [fields]
#
# [1] "The Zephyr Abstract Syntax Description Language" by Wang, et. al. See
# http://asdl.sourceforge.net/
#-------------------------------------------------------------------------------
from collections import namedtuple
import re
__all__ = [
'builtin_types', 'parse', 'AST', 'Module', 'Type', 'Constructor',
'Field', 'Sum', 'Product', 'VisitorBase', 'Check', 'check']
# The following classes define nodes into which the ASDL description is parsed.
# Note: this is a "meta-AST". ASDL files (such as Python.asdl) describe the AST
# structure used by a programming language. But ASDL files themselves need to be
# parsed. This module parses ASDL files and uses a simple AST to represent them.
# See the EBNF at the top of the file to understand the logical connection
# between the various node types.
builtin_types = {'identifier', 'string', 'int', 'constant', 'bool', 'conversion_flag'}
class AST:
def __repr__(self):
raise NotImplementedError
class Module(AST):
def __init__(self, name, dfns):
self.name = name
self.dfns = dfns
self.types = {type.name: type.value for type in dfns}
def __repr__(self):
return 'Module({0.name}, {0.dfns})'.format(self)
class Type(AST):
def __init__(self, name, value):
self.name = name
self.value = value
def __repr__(self):
return 'Type({0.name}, {0.value})'.format(self)
class Constructor(AST):
def __init__(self, name, fields=None):
self.name = name
self.fields = fields or []
def __repr__(self):
return 'Constructor({0.name}, {0.fields})'.format(self)
class Field(AST):
def __init__(self, type, name=None, seq=False, opt=False):
self.type = type
self.name = name
self.seq = seq
self.opt = opt
def __str__(self):
if self.seq:
extra = "*"
elif self.opt:
extra = "?"
else:
extra = ""
return "{}{} {}".format(self.type, extra, self.name)
def __repr__(self):
if self.seq:
extra = ", seq=True"
elif self.opt:
extra = ", opt=True"
else:
extra = ""
if self.name is None:
return 'Field({0.type}{1})'.format(self, extra)
else:
return 'Field({0.type}, {0.name}{1})'.format(self, extra)
class Sum(AST):
def __init__(self, types, attributes=None):
self.types = types
self.attributes = attributes or []
def __repr__(self):
if self.attributes:
return 'Sum({0.types}, {0.attributes})'.format(self)
else:
return 'Sum({0.types})'.format(self)
class Product(AST):
def __init__(self, fields, attributes=None):
self.fields = fields
self.attributes = attributes or []
def __repr__(self):
if self.attributes:
return 'Product({0.fields}, {0.attributes})'.format(self)
else:
return 'Product({0.fields})'.format(self)
# A generic visitor for the meta-AST that describes ASDL. This can be used by
# emitters. Note that this visitor does not provide a generic visit method, so a
# subclass needs to define visit methods from visitModule to as deep as the
# interesting node.
# We also define a Check visitor that makes sure the parsed ASDL is well-formed.
class VisitorBase(object):
"""Generic tree visitor for ASTs."""
def __init__(self):
self.cache = {}
def visit(self, obj, *args):
klass = obj.__class__
meth = self.cache.get(klass)
if meth is None:
methname = "visit" + klass.__name__
meth = getattr(self, methname, None)
self.cache[klass] = meth
if meth:
try:
meth(obj, *args)
except Exception as e:
print("Error visiting %r: %s" % (obj, e))
raise
class Check(VisitorBase):
"""A visitor that checks a parsed ASDL tree for correctness.
Errors are printed and accumulated.
"""
def __init__(self):
super(Check, self).__init__()
self.cons = {}
self.errors = 0
self.types = {}
def visitModule(self, mod):
for dfn in mod.dfns:
self.visit(dfn)
def visitType(self, type):
self.visit(type.value, str(type.name))
def visitSum(self, sum, name):
for t in sum.types:
self.visit(t, name)
def visitConstructor(self, cons, name):
key = str(cons.name)
conflict = self.cons.get(key)
if conflict is None:
self.cons[key] = name
else:
print('Redefinition of constructor {}'.format(key))
print('Defined in {} and {}'.format(conflict, name))
self.errors += 1
for f in cons.fields:
self.visit(f, key)
def visitField(self, field, name):
key = str(field.type)
l = self.types.setdefault(key, [])
l.append(name)
def visitProduct(self, prod, name):
for f in prod.fields:
self.visit(f, name)
def check(mod):
"""Check the parsed ASDL tree for correctness.
Return True if success. For failure, the errors are printed out and False
is returned.
"""
v = Check()
v.visit(mod)
for t in v.types:
if t not in mod.types and not t in builtin_types:
v.errors += 1
uses = ", ".join(v.types[t])
print('Undefined type {}, used in {}'.format(t, uses))
return not v.errors
# The ASDL parser itself comes next. The only interesting external interface
# here is the top-level parse function.
def parse(filename):
"""Parse ASDL from the given file and return a Module node describing it."""
with open(filename) as f:
parser = ASDLParser()
return parser.parse(f.read())
# Types for describing tokens in an ASDL specification.
class TokenKind:
"""TokenKind is provides a scope for enumerated token kinds."""
(ConstructorId, TypeId, Equals, Comma, Question, Pipe, Asterisk,
LParen, RParen, LBrace, RBrace) = range(11)
operator_table = {
'=': Equals, ',': Comma, '?': Question, '|': Pipe, '(': LParen,
')': RParen, '*': Asterisk, '{': LBrace, '}': RBrace}
Token = namedtuple('Token', 'kind value lineno')
class ASDLSyntaxError(Exception):
def __init__(self, msg, lineno=None):
self.msg = msg
self.lineno = lineno or '<unknown>'
def __str__(self):
return 'Syntax error on line {0.lineno}: {0.msg}'.format(self)
def tokenize_asdl(buf):
"""Tokenize the given buffer. Yield Token objects."""
for lineno, line in enumerate(buf.splitlines(), 1):
for m in re.finditer(r'\s*(\w+|--.*|.)', line.strip()):
c = m.group(1)
if c[0].isalpha():
# Some kind of identifier
if c[0].isupper():
yield Token(TokenKind.ConstructorId, c, lineno)
else:
yield Token(TokenKind.TypeId, c, lineno)
elif c[:2] == '--':
# Comment
break
else:
# Operators
try:
op_kind = TokenKind.operator_table[c]
except KeyError:
raise ASDLSyntaxError('Invalid operator %s' % c, lineno)
yield Token(op_kind, c, lineno)
class ASDLParser:
"""Parser for ASDL files.
Create, then call the parse method on a buffer containing ASDL.
This is a simple recursive descent parser that uses tokenize_asdl for the
lexing.
"""
def __init__(self):
self._tokenizer = None
self.cur_token = None
def parse(self, buf):
"""Parse the ASDL in the buffer and return an AST with a Module root.
"""
self._tokenizer = tokenize_asdl(buf)
self._advance()
return self._parse_module()
def _parse_module(self):
if self._at_keyword('module'):
self._advance()
else:
raise ASDLSyntaxError(
'Expected "module" (found {})'.format(self.cur_token.value),
self.cur_token.lineno)
name = self._match(self._id_kinds)
self._match(TokenKind.LBrace)
defs = self._parse_definitions()
self._match(TokenKind.RBrace)
return Module(name, defs)
def _parse_definitions(self):
defs = []
while self.cur_token.kind == TokenKind.TypeId:
typename = self._advance()
self._match(TokenKind.Equals)
type = self._parse_type()
defs.append(Type(typename, type))
return defs
def _parse_type(self):
if self.cur_token.kind == TokenKind.LParen:
# If we see a (, it's a product
return self._parse_product()
else:
# Otherwise it's a sum. Look for ConstructorId
sumlist = [Constructor(self._match(TokenKind.ConstructorId),
self._parse_optional_fields())]
while self.cur_token.kind == TokenKind.Pipe:
# More constructors
self._advance()
sumlist.append(Constructor(
self._match(TokenKind.ConstructorId),
self._parse_optional_fields()))
return Sum(sumlist, self._parse_optional_attributes())
def _parse_product(self):
return Product(self._parse_fields(), self._parse_optional_attributes())
def _parse_fields(self):
fields = []
self._match(TokenKind.LParen)
while self.cur_token.kind == TokenKind.TypeId:
typename = self._advance()
is_seq, is_opt = self._parse_optional_field_quantifier()
id = (self._advance() if self.cur_token.kind in self._id_kinds
else None)
fields.append(Field(typename, id, seq=is_seq, opt=is_opt))
if self.cur_token.kind == TokenKind.RParen:
break
elif self.cur_token.kind == TokenKind.Comma:
self._advance()
self._match(TokenKind.RParen)
return fields
def _parse_optional_fields(self):
if self.cur_token.kind == TokenKind.LParen:
return self._parse_fields()
else:
return None
def _parse_optional_attributes(self):
if self._at_keyword('attributes'):
self._advance()
return self._parse_fields()
else:
return None
def _parse_optional_field_quantifier(self):
is_seq, is_opt = False, False
if self.cur_token.kind == TokenKind.Question:
is_opt = True
self._advance()
if self.cur_token.kind == TokenKind.Asterisk:
is_seq = True
self._advance()
return is_seq, is_opt
def _advance(self):
""" Return the value of the current token and read the next one into
self.cur_token.
"""
cur_val = None if self.cur_token is None else self.cur_token.value
try:
self.cur_token = next(self._tokenizer)
except StopIteration:
self.cur_token = None
return cur_val
_id_kinds = (TokenKind.ConstructorId, TokenKind.TypeId)
def _match(self, kind):
"""The 'match' primitive of RD parsers.
* Verifies that the current token is of the given kind (kind can
be a tuple, in which the kind must match one of its members).
* Returns the value of the current token
* Reads in the next token
"""
if (isinstance(kind, tuple) and self.cur_token.kind in kind or
self.cur_token.kind == kind
):
value = self.cur_token.value
self._advance()
return value
else:
raise ASDLSyntaxError(
'Unmatched {} (found {})'.format(kind, self.cur_token.kind),
self.cur_token.lineno)
def _at_keyword(self, keyword):
return (self.cur_token.kind == TokenKind.TypeId and
self.cur_token.value == keyword)

609
nac3ast/asdl_rs.py Executable file
View File

@ -0,0 +1,609 @@
#! /usr/bin/env python
"""Generate Rust code from an ASDL description."""
import os
import sys
import textwrap
import json
from argparse import ArgumentParser
from pathlib import Path
import asdl
TABSIZE = 4
AUTOGEN_MESSAGE = "// File automatically generated by {}.\n\n"
builtin_type_mapping = {
'identifier': 'Ident',
'string': 'String',
'int': 'usize',
'constant': 'Constant',
'bool': 'bool',
'conversion_flag': 'ConversionFlag',
}
assert builtin_type_mapping.keys() == asdl.builtin_types
def get_rust_type(name):
"""Return a string for the C name of the type.
This function special cases the default types provided by asdl.
"""
if name in asdl.builtin_types:
return builtin_type_mapping[name]
else:
return "".join(part.capitalize() for part in name.split("_"))
def is_simple(sum):
"""Return True if a sum is a simple.
A sum is simple if its types have no fields, e.g.
unaryop = Invert | Not | UAdd | USub
"""
for t in sum.types:
if t.fields:
return False
return True
def asdl_of(name, obj):
if isinstance(obj, asdl.Product) or isinstance(obj, asdl.Constructor):
fields = ", ".join(map(str, obj.fields))
if fields:
fields = "({})".format(fields)
return "{}{}".format(name, fields)
else:
if is_simple(obj):
types = " | ".join(type.name for type in obj.types)
else:
sep = "\n{}| ".format(" " * (len(name) + 1))
types = sep.join(
asdl_of(type.name, type) for type in obj.types
)
return "{} = {}".format(name, types)
class EmitVisitor(asdl.VisitorBase):
"""Visit that emits lines"""
def __init__(self, file):
self.file = file
self.identifiers = set()
super(EmitVisitor, self).__init__()
def emit_identifier(self, name):
name = str(name)
if name in self.identifiers:
return
self.emit("_Py_IDENTIFIER(%s);" % name, 0)
self.identifiers.add(name)
def emit(self, line, depth):
if line:
line = (" " * TABSIZE * depth) + line
self.file.write(line + "\n")
class TypeInfo:
def __init__(self, name):
self.name = name
self.has_userdata = None
self.children = set()
self.boxed = False
def __repr__(self):
return f"<TypeInfo: {self.name}>"
def determine_userdata(self, typeinfo, stack):
if self.name in stack:
return None
stack.add(self.name)
for child, child_seq in self.children:
if child in asdl.builtin_types:
continue
childinfo = typeinfo[child]
child_has_userdata = childinfo.determine_userdata(typeinfo, stack)
if self.has_userdata is None and child_has_userdata is True:
self.has_userdata = True
stack.remove(self.name)
return self.has_userdata
class FindUserdataTypesVisitor(asdl.VisitorBase):
def __init__(self, typeinfo):
self.typeinfo = typeinfo
super().__init__()
def visitModule(self, mod):
for dfn in mod.dfns:
self.visit(dfn)
stack = set()
for info in self.typeinfo.values():
info.determine_userdata(self.typeinfo, stack)
def visitType(self, type):
self.typeinfo[type.name] = TypeInfo(type.name)
self.visit(type.value, type.name)
def visitSum(self, sum, name):
info = self.typeinfo[name]
if is_simple(sum):
info.has_userdata = False
else:
if len(sum.types) > 1:
info.boxed = True
if sum.attributes:
# attributes means Located, which has the `custom: U` field
info.has_userdata = True
for variant in sum.types:
self.add_children(name, variant.fields)
def visitProduct(self, product, name):
info = self.typeinfo[name]
if product.attributes:
# attributes means Located, which has the `custom: U` field
info.has_userdata = True
if len(product.fields) > 2:
info.boxed = True
self.add_children(name, product.fields)
def add_children(self, name, fields):
self.typeinfo[name].children.update((field.type, field.seq) for field in fields)
def rust_field(field_name):
if field_name == 'type':
return 'type_'
else:
return field_name
class TypeInfoEmitVisitor(EmitVisitor):
def __init__(self, file, typeinfo):
self.typeinfo = typeinfo
super().__init__(file)
def has_userdata(self, typ):
return self.typeinfo[typ].has_userdata
def get_generics(self, typ, *generics):
if self.has_userdata(typ):
return [f"<{g}>" for g in generics]
else:
return ["" for g in generics]
class StructVisitor(TypeInfoEmitVisitor):
"""Visitor to generate typedefs for AST."""
def visitModule(self, mod):
for dfn in mod.dfns:
self.visit(dfn)
def visitType(self, type, depth=0):
self.visit(type.value, type.name, depth)
def visitSum(self, sum, name, depth):
if is_simple(sum):
self.simple_sum(sum, name, depth)
else:
self.sum_with_constructors(sum, name, depth)
def emit_attrs(self, depth):
self.emit("#[derive(Debug, PartialEq)]", depth)
def simple_sum(self, sum, name, depth):
rustname = get_rust_type(name)
self.emit_attrs(depth)
self.emit(f"pub enum {rustname} {{", depth)
for variant in sum.types:
self.emit(f"{variant.name},", depth + 1)
self.emit("}", depth)
self.emit("", depth)
def sum_with_constructors(self, sum, name, depth):
typeinfo = self.typeinfo[name]
generics, generics_applied = self.get_generics(name, "U = ()", "U")
enumname = rustname = get_rust_type(name)
# all the attributes right now are for location, so if it has attrs we
# can just wrap it in Located<>
if sum.attributes:
enumname = rustname + "Kind"
self.emit_attrs(depth)
self.emit(f"pub enum {enumname}{generics} {{", depth)
for t in sum.types:
self.visit(t, typeinfo, depth + 1)
self.emit("}", depth)
if sum.attributes:
self.emit(f"pub type {rustname}<U = ()> = Located<{enumname}{generics_applied}, U>;", depth)
self.emit("", depth)
def visitConstructor(self, cons, parent, depth):
if cons.fields:
self.emit(f"{cons.name} {{", depth)
for f in cons.fields:
self.visit(f, parent, "", depth + 1)
self.emit("},", depth)
else:
self.emit(f"{cons.name},", depth)
def visitField(self, field, parent, vis, depth):
typ = get_rust_type(field.type)
fieldtype = self.typeinfo.get(field.type)
if fieldtype and fieldtype.has_userdata:
typ = f"{typ}<U>"
# don't box if we're doing Vec<T>, but do box if we're doing Vec<Option<Box<T>>>
if fieldtype and fieldtype.boxed and (not field.seq or field.opt):
typ = f"Box<{typ}>"
if field.opt:
typ = f"Option<{typ}>"
if field.seq:
typ = f"Vec<{typ}>"
name = rust_field(field.name)
self.emit(f"{vis}{name}: {typ},", depth)
def visitProduct(self, product, name, depth):
typeinfo = self.typeinfo[name]
generics, generics_applied = self.get_generics(name, "U = ()", "U")
dataname = rustname = get_rust_type(name)
if product.attributes:
dataname = rustname + "Data"
self.emit_attrs(depth)
self.emit(f"pub struct {dataname}{generics} {{", depth)
for f in product.fields:
self.visit(f, typeinfo, "pub ", depth + 1)
self.emit("}", depth)
if product.attributes:
# attributes should just be location info
self.emit(f"pub type {rustname}<U = ()> = Located<{dataname}{generics_applied}, U>;", depth);
self.emit("", depth)
class FoldTraitDefVisitor(TypeInfoEmitVisitor):
def visitModule(self, mod, depth):
self.emit("pub trait Fold<U> {", depth)
self.emit("type TargetU;", depth + 1)
self.emit("type Error;", depth + 1)
self.emit("fn map_user(&mut self, user: U) -> Result<Self::TargetU, Self::Error>;", depth + 2)
for dfn in mod.dfns:
self.visit(dfn, depth + 2)
self.emit("}", depth)
def visitType(self, type, depth):
name = type.name
apply_u, apply_target_u = self.get_generics(name, "U", "Self::TargetU")
enumname = get_rust_type(name)
self.emit(f"fn fold_{name}(&mut self, node: {enumname}{apply_u}) -> Result<{enumname}{apply_target_u}, Self::Error> {{", depth)
self.emit(f"fold_{name}(self, node)", depth + 1)
self.emit("}", depth)
class FoldImplVisitor(TypeInfoEmitVisitor):
def visitModule(self, mod, depth):
self.emit("fn fold_located<U, F: Fold<U> + ?Sized, T, MT>(folder: &mut F, node: Located<T, U>, f: impl FnOnce(&mut F, T) -> Result<MT, F::Error>) -> Result<Located<MT, F::TargetU>, F::Error> {", depth)
self.emit("Ok(Located { custom: folder.map_user(node.custom)?, location: node.location, node: f(folder, node.node)? })", depth + 1)
self.emit("}", depth)
for dfn in mod.dfns:
self.visit(dfn, depth)
def visitType(self, type, depth=0):
self.visit(type.value, type.name, depth)
def visitSum(self, sum, name, depth):
apply_t, apply_u, apply_target_u = self.get_generics(name, "T", "U", "F::TargetU")
enumname = get_rust_type(name)
is_located = bool(sum.attributes)
self.emit(f"impl<T, U> Foldable<T, U> for {enumname}{apply_t} {{", depth)
self.emit(f"type Mapped = {enumname}{apply_u};", depth + 1)
self.emit("fn fold<F: Fold<T, TargetU = U> + ?Sized>(self, folder: &mut F) -> Result<Self::Mapped, F::Error> {", depth + 1)
self.emit(f"folder.fold_{name}(self)", depth + 2)
self.emit("}", depth + 1)
self.emit("}", depth)
self.emit(f"pub fn fold_{name}<U, F: Fold<U> + ?Sized>(#[allow(unused)] folder: &mut F, node: {enumname}{apply_u}) -> Result<{enumname}{apply_target_u}, F::Error> {{", depth)
if is_located:
self.emit("fold_located(folder, node, |folder, node| {", depth)
enumname += "Kind"
self.emit("match node {", depth + 1)
for cons in sum.types:
fields_pattern = self.make_pattern(cons.fields)
self.emit(f"{enumname}::{cons.name} {{ {fields_pattern} }} => {{", depth + 2)
self.gen_construction(f"{enumname}::{cons.name}", cons.fields, depth + 3)
self.emit("}", depth + 2)
self.emit("}", depth + 1)
if is_located:
self.emit("})", depth)
self.emit("}", depth)
def visitProduct(self, product, name, depth):
apply_t, apply_u, apply_target_u = self.get_generics(name, "T", "U", "F::TargetU")
structname = get_rust_type(name)
is_located = bool(product.attributes)
self.emit(f"impl<T, U> Foldable<T, U> for {structname}{apply_t} {{", depth)
self.emit(f"type Mapped = {structname}{apply_u};", depth + 1)
self.emit("fn fold<F: Fold<T, TargetU = U> + ?Sized>(self, folder: &mut F) -> Result<Self::Mapped, F::Error> {", depth + 1)
self.emit(f"folder.fold_{name}(self)", depth + 2)
self.emit("}", depth + 1)
self.emit("}", depth)
self.emit(f"pub fn fold_{name}<U, F: Fold<U> + ?Sized>(#[allow(unused)] folder: &mut F, node: {structname}{apply_u}) -> Result<{structname}{apply_target_u}, F::Error> {{", depth)
if is_located:
self.emit("fold_located(folder, node, |folder, node| {", depth)
structname += "Data"
fields_pattern = self.make_pattern(product.fields)
self.emit(f"let {structname} {{ {fields_pattern} }} = node;", depth + 1)
self.gen_construction(structname, product.fields, depth + 1)
if is_located:
self.emit("})", depth)
self.emit("}", depth)
def make_pattern(self, fields):
return ",".join(rust_field(f.name) for f in fields)
def gen_construction(self, cons_path, fields, depth):
self.emit(f"Ok({cons_path} {{", depth)
for field in fields:
name = rust_field(field.name)
self.emit(f"{name}: Foldable::fold({name}, folder)?,", depth + 1)
self.emit("})", depth)
class FoldModuleVisitor(TypeInfoEmitVisitor):
def visitModule(self, mod):
depth = 0
self.emit('#[cfg(feature = "fold")]', depth)
self.emit("pub mod fold {", depth)
self.emit("use super::*;", depth + 1)
self.emit("use crate::fold_helpers::Foldable;", depth + 1)
FoldTraitDefVisitor(self.file, self.typeinfo).visit(mod, depth + 1)
FoldImplVisitor(self.file, self.typeinfo).visit(mod, depth + 1)
self.emit("}", depth)
class ClassDefVisitor(EmitVisitor):
def visitModule(self, mod):
for dfn in mod.dfns:
self.visit(dfn)
def visitType(self, type, depth=0):
self.visit(type.value, type.name, depth)
def visitSum(self, sum, name, depth):
for cons in sum.types:
self.visit(cons, sum.attributes, depth)
def visitConstructor(self, cons, attrs, depth):
self.gen_classdef(cons.name, cons.fields, attrs, depth)
def visitProduct(self, product, name, depth):
self.gen_classdef(name, product.fields, product.attributes, depth)
def gen_classdef(self, name, fields, attrs, depth):
structname = "Node" + name
self.emit(f'#[pyclass(module = "_ast", name = {json.dumps(name)}, base = "AstNode")]', depth)
self.emit(f"struct {structname};", depth)
self.emit("#[pyimpl(flags(HAS_DICT, BASETYPE))]", depth)
self.emit(f"impl {structname} {{", depth)
self.emit(f"#[extend_class]", depth + 1)
self.emit("fn extend_class_with_fields(ctx: &PyContext, class: &PyTypeRef) {", depth + 1)
fields = ",".join(f"ctx.new_str({json.dumps(f.name)})" for f in fields)
self.emit(f'class.set_str_attr("_fields", ctx.new_list(vec![{fields}]));', depth + 2)
attrs = ",".join(f"ctx.new_str({json.dumps(attr.name)})" for attr in attrs)
self.emit(f'class.set_str_attr("_attributes", ctx.new_list(vec![{attrs}]));', depth + 2)
self.emit("}", depth + 1)
self.emit("}", depth)
class ExtendModuleVisitor(EmitVisitor):
def visitModule(self, mod):
depth = 0
self.emit("pub fn extend_module_nodes(vm: &VirtualMachine, module: &PyObjectRef) {", depth)
self.emit("extend_module!(vm, module, {", depth + 1)
for dfn in mod.dfns:
self.visit(dfn, depth + 2)
self.emit("})", depth + 1)
self.emit("}", depth)
def visitType(self, type, depth):
self.visit(type.value, type.name, depth)
def visitSum(self, sum, name, depth):
for cons in sum.types:
self.visit(cons, depth)
def visitConstructor(self, cons, depth):
self.gen_extension(cons.name, depth)
def visitProduct(self, product, name, depth):
self.gen_extension(name, depth)
def gen_extension(self, name, depth):
self.emit(f"{json.dumps(name)} => Node{name}::make_class(&vm.ctx),", depth)
class TraitImplVisitor(EmitVisitor):
def visitModule(self, mod):
for dfn in mod.dfns:
self.visit(dfn)
def visitType(self, type, depth=0):
self.visit(type.value, type.name, depth)
def visitSum(self, sum, name, depth):
enumname = get_rust_type(name)
if sum.attributes:
enumname += "Kind"
self.emit(f"impl NamedNode for ast::{enumname} {{", depth)
self.emit(f"const NAME: &'static str = {json.dumps(name)};", depth + 1)
self.emit("}", depth)
self.emit(f"impl Node for ast::{enumname} {{", depth)
self.emit("fn ast_to_object(self, _vm: &VirtualMachine) -> PyObjectRef {", depth + 1)
self.emit("match self {", depth + 2)
for variant in sum.types:
self.constructor_to_object(variant, enumname, depth + 3)
self.emit("}", depth + 2)
self.emit("}", depth + 1)
self.emit("fn ast_from_object(_vm: &VirtualMachine, _object: PyObjectRef) -> PyResult<Self> {", depth + 1)
self.gen_sum_fromobj(sum, name, enumname, depth + 2)
self.emit("}", depth + 1)
self.emit("}", depth)
def constructor_to_object(self, cons, enumname, depth):
fields_pattern = self.make_pattern(cons.fields)
self.emit(f"ast::{enumname}::{cons.name} {{ {fields_pattern} }} => {{", depth)
self.make_node(cons.name, cons.fields, depth + 1)
self.emit("}", depth)
def visitProduct(self, product, name, depth):
structname = get_rust_type(name)
if product.attributes:
structname += "Data"
self.emit(f"impl NamedNode for ast::{structname} {{", depth)
self.emit(f"const NAME: &'static str = {json.dumps(name)};", depth + 1)
self.emit("}", depth)
self.emit(f"impl Node for ast::{structname} {{", depth)
self.emit("fn ast_to_object(self, _vm: &VirtualMachine) -> PyObjectRef {", depth + 1)
fields_pattern = self.make_pattern(product.fields)
self.emit(f"let ast::{structname} {{ {fields_pattern} }} = self;", depth + 2)
self.make_node(name, product.fields, depth + 2)
self.emit("}", depth + 1)
self.emit("fn ast_from_object(_vm: &VirtualMachine, _object: PyObjectRef) -> PyResult<Self> {", depth + 1)
self.gen_product_fromobj(product, name, structname, depth + 2)
self.emit("}", depth + 1)
self.emit("}", depth)
def make_node(self, variant, fields, depth):
lines = []
self.emit(f"let _node = AstNode.into_ref_with_type(_vm, Node{variant}::static_type().clone()).unwrap();", depth)
if fields:
self.emit("let _dict = _node.as_object().dict().unwrap();", depth)
for f in fields:
self.emit(f"_dict.set_item({json.dumps(f.name)}, {rust_field(f.name)}.ast_to_object(_vm), _vm).unwrap();", depth)
self.emit("_node.into_object()", depth)
def make_pattern(self, fields):
return ",".join(rust_field(f.name) for f in fields)
def gen_sum_fromobj(self, sum, sumname, enumname, depth):
if sum.attributes:
self.extract_location(sumname, depth)
self.emit("let _cls = _object.class();", depth)
self.emit("Ok(", depth)
for cons in sum.types:
self.emit(f"if _cls.is(Node{cons.name}::static_type()) {{", depth)
self.gen_construction(f"{enumname}::{cons.name}", cons, sumname, depth + 1)
self.emit("} else", depth)
self.emit("{", depth)
msg = f'format!("expected some sort of {sumname}, but got {{}}",_vm.to_repr(&_object)?)'
self.emit(f"return Err(_vm.new_type_error({msg}));", depth + 1)
self.emit("})", depth)
def gen_product_fromobj(self, product, prodname, structname, depth):
if product.attributes:
self.extract_location(prodname, depth)
self.emit("Ok(", depth)
self.gen_construction(structname, product, prodname, depth + 1)
self.emit(")", depth)
def gen_construction(self, cons_path, cons, name, depth):
self.emit(f"ast::{cons_path} {{", depth)
for field in cons.fields:
self.emit(f"{rust_field(field.name)}: {self.decode_field(field, name)},", depth + 1)
self.emit("}", depth)
def extract_location(self, typename, depth):
row = self.decode_field(asdl.Field('int', 'lineno'), typename)
column = self.decode_field(asdl.Field('int', 'col_offset'), typename)
self.emit(f"let _location = ast::Location::new({row}, {column});", depth)
def wrap_located_node(self, depth):
self.emit(f"let node = ast::Located::new(_location, node);", depth)
def decode_field(self, field, typename):
name = json.dumps(field.name)
if field.opt and not field.seq:
return f"get_node_field_opt(_vm, &_object, {name})?.map(|obj| Node::ast_from_object(_vm, obj)).transpose()?"
else:
return f"Node::ast_from_object(_vm, get_node_field(_vm, &_object, {name}, {json.dumps(typename)})?)?"
class ChainOfVisitors:
def __init__(self, *visitors):
self.visitors = visitors
def visit(self, object):
for v in self.visitors:
v.visit(object)
v.emit("", 0)
def write_ast_def(mod, typeinfo, f):
f.write('pub use crate::location::Location;\n')
f.write('pub use crate::constant::*;\n')
f.write('\n')
f.write('type Ident = String;\n')
f.write('\n')
StructVisitor(f, typeinfo).emit_attrs(0)
f.write('pub struct Located<T, U = ()> {\n')
f.write(' pub location: Location,\n')
f.write(' pub custom: U,\n')
f.write(' pub node: T,\n')
f.write('}\n')
f.write('\n')
f.write('impl<T> Located<T> {\n')
f.write(' pub fn new(location: Location, node: T) -> Self {\n')
f.write(' Self { location, custom: (), node }\n')
f.write(' }\n')
f.write('}\n')
f.write('\n')
c = ChainOfVisitors(StructVisitor(f, typeinfo),
FoldModuleVisitor(f, typeinfo))
c.visit(mod)
def write_ast_mod(mod, f):
f.write('use super::*;\n')
f.write('\n')
c = ChainOfVisitors(ClassDefVisitor(f),
TraitImplVisitor(f),
ExtendModuleVisitor(f))
c.visit(mod)
def main(input_filename, ast_mod_filename, ast_def_filename, dump_module=False):
auto_gen_msg = AUTOGEN_MESSAGE.format("/".join(Path(__file__).parts[-2:]))
mod = asdl.parse(input_filename)
if dump_module:
print('Parsed Module:')
print(mod)
if not asdl.check(mod):
sys.exit(1)
typeinfo = {}
FindUserdataTypesVisitor(typeinfo).visit(mod)
with ast_def_filename.open("w") as def_file, \
ast_mod_filename.open("w") as mod_file:
def_file.write(auto_gen_msg)
write_ast_def(mod, typeinfo, def_file)
mod_file.write(auto_gen_msg)
write_ast_mod(mod, mod_file)
print(f"{ast_def_filename}, {ast_mod_filename} regenerated.")
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument("input_file", type=Path)
parser.add_argument("-M", "--mod-file", type=Path, required=True)
parser.add_argument("-D", "--def-file", type=Path, required=True)
parser.add_argument("-d", "--dump-module", action="store_true")
args = parser.parse_args()
main(args.input_file, args.mod_file, args.def_file, args.dump_module)

1136
nac3ast/src/ast_gen.rs Normal file

File diff suppressed because it is too large Load Diff

210
nac3ast/src/constant.rs Normal file
View File

@ -0,0 +1,210 @@
use num_bigint::BigInt;
#[derive(Debug, PartialEq)]
pub enum Constant {
None,
Bool(bool),
Str(String),
Bytes(Vec<u8>),
Int(BigInt),
Tuple(Vec<Constant>),
Float(f64),
Complex { real: f64, imag: f64 },
Ellipsis,
}
impl From<String> for Constant {
fn from(s: String) -> Constant {
Self::Str(s)
}
}
impl From<Vec<u8>> for Constant {
fn from(b: Vec<u8>) -> Constant {
Self::Bytes(b)
}
}
impl From<bool> for Constant {
fn from(b: bool) -> Constant {
Self::Bool(b)
}
}
impl From<BigInt> for Constant {
fn from(i: BigInt) -> Constant {
Self::Int(i)
}
}
/// Transforms a value prior to formatting it.
#[derive(Copy, Clone, Debug, PartialEq)]
#[repr(u8)]
pub enum ConversionFlag {
/// Converts by calling `str(<value>)`.
Str = b's',
/// Converts by calling `ascii(<value>)`.
Ascii = b'a',
/// Converts by calling `repr(<value>)`.
Repr = b'r',
}
impl ConversionFlag {
pub fn try_from_byte(b: u8) -> Option<Self> {
match b {
b's' => Some(Self::Str),
b'a' => Some(Self::Ascii),
b'r' => Some(Self::Repr),
_ => None,
}
}
}
#[cfg(feature = "constant-optimization")]
#[derive(Default)]
pub struct ConstantOptimizer {
_priv: (),
}
#[cfg(feature = "constant-optimization")]
impl ConstantOptimizer {
#[inline]
pub fn new() -> Self {
Self { _priv: () }
}
}
#[cfg(feature = "constant-optimization")]
impl<U> crate::fold::Fold<U> for ConstantOptimizer {
type TargetU = U;
type Error = std::convert::Infallible;
#[inline]
fn map_user(&mut self, user: U) -> Result<Self::TargetU, Self::Error> {
Ok(user)
}
fn fold_expr(&mut self, node: crate::Expr<U>) -> Result<crate::Expr<U>, Self::Error> {
match node.node {
crate::ExprKind::Tuple { elts, ctx } => {
let elts = elts
.into_iter()
.map(|x| self.fold_expr(x))
.collect::<Result<Vec<_>, _>>()?;
let expr = if elts
.iter()
.all(|e| matches!(e.node, crate::ExprKind::Constant { .. }))
{
let tuple = elts
.into_iter()
.map(|e| match e.node {
crate::ExprKind::Constant { value, .. } => value,
_ => unreachable!(),
})
.collect();
crate::ExprKind::Constant {
value: Constant::Tuple(tuple),
kind: None,
}
} else {
crate::ExprKind::Tuple { elts, ctx }
};
Ok(crate::Expr {
node: expr,
custom: node.custom,
location: node.location,
})
}
_ => crate::fold::fold_expr(self, node),
}
}
}
#[cfg(test)]
mod tests {
#[cfg(feature = "constant-optimization")]
#[test]
fn test_constant_opt() {
use super::*;
use crate::fold::Fold;
use crate::*;
let location = Location::new(0, 0);
let custom = ();
let ast = Located {
location,
custom,
node: ExprKind::Tuple {
ctx: ExprContext::Load,
elts: vec![
Located {
location,
custom,
node: ExprKind::Constant {
value: BigInt::from(1).into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant {
value: BigInt::from(2).into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Tuple {
ctx: ExprContext::Load,
elts: vec![
Located {
location,
custom,
node: ExprKind::Constant {
value: BigInt::from(3).into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant {
value: BigInt::from(4).into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant {
value: BigInt::from(5).into(),
kind: None,
},
},
],
},
},
],
},
};
let new_ast = ConstantOptimizer::new()
.fold_expr(ast)
.unwrap_or_else(|e| match e {});
assert_eq!(
new_ast,
Located {
location,
custom,
node: ExprKind::Constant {
value: Constant::Tuple(vec![
BigInt::from(1).into(),
BigInt::from(2).into(),
Constant::Tuple(vec![
BigInt::from(3).into(),
BigInt::from(4).into(),
BigInt::from(5).into(),
])
]),
kind: None
},
}
);
}
}

View File

@ -0,0 +1,72 @@
use crate::constant;
use crate::fold::Fold;
pub(crate) trait Foldable<T, U> {
type Mapped;
fn fold<F: Fold<T, TargetU = U> + ?Sized>(
self,
folder: &mut F,
) -> Result<Self::Mapped, F::Error>;
}
impl<T, U, X> Foldable<T, U> for Vec<X>
where
X: Foldable<T, U>,
{
type Mapped = Vec<X::Mapped>;
fn fold<F: Fold<T, TargetU = U> + ?Sized>(
self,
folder: &mut F,
) -> Result<Self::Mapped, F::Error> {
self.into_iter().map(|x| x.fold(folder)).collect()
}
}
impl<T, U, X> Foldable<T, U> for Option<X>
where
X: Foldable<T, U>,
{
type Mapped = Option<X::Mapped>;
fn fold<F: Fold<T, TargetU = U> + ?Sized>(
self,
folder: &mut F,
) -> Result<Self::Mapped, F::Error> {
self.map(|x| x.fold(folder)).transpose()
}
}
impl<T, U, X> Foldable<T, U> for Box<X>
where
X: Foldable<T, U>,
{
type Mapped = Box<X::Mapped>;
fn fold<F: Fold<T, TargetU = U> + ?Sized>(
self,
folder: &mut F,
) -> Result<Self::Mapped, F::Error> {
(*self).fold(folder).map(Box::new)
}
}
macro_rules! simple_fold {
($($t:ty),+$(,)?) => {
$(impl<T, U> $crate::fold_helpers::Foldable<T, U> for $t {
type Mapped = Self;
#[inline]
fn fold<F: Fold<T, TargetU = U> + ?Sized>(
self,
_folder: &mut F,
) -> Result<Self::Mapped, F::Error> {
Ok(self)
}
})+
};
}
simple_fold!(
usize,
String,
bool,
constant::Constant,
constant::ConversionFlag
);

53
nac3ast/src/impls.rs Normal file
View File

@ -0,0 +1,53 @@
use crate::{Constant, ExprKind};
impl<U> ExprKind<U> {
/// Returns a short name for the node suitable for use in error messages.
pub fn name(&self) -> &'static str {
match self {
ExprKind::BoolOp { .. } | ExprKind::BinOp { .. } | ExprKind::UnaryOp { .. } => {
"operator"
}
ExprKind::Subscript { .. } => "subscript",
ExprKind::Await { .. } => "await expression",
ExprKind::Yield { .. } | ExprKind::YieldFrom { .. } => "yield expression",
ExprKind::Compare { .. } => "comparison",
ExprKind::Attribute { .. } => "attribute",
ExprKind::Call { .. } => "function call",
ExprKind::Constant { value, .. } => match value {
Constant::Str(_)
| Constant::Int(_)
| Constant::Float(_)
| Constant::Complex { .. }
| Constant::Bytes(_) => "literal",
Constant::Tuple(_) => "tuple",
Constant::Bool(_) | Constant::None => "keyword",
Constant::Ellipsis => "ellipsis",
},
ExprKind::List { .. } => "list",
ExprKind::Tuple { .. } => "tuple",
ExprKind::Dict { .. } => "dict display",
ExprKind::Set { .. } => "set display",
ExprKind::ListComp { .. } => "list comprehension",
ExprKind::DictComp { .. } => "dict comprehension",
ExprKind::SetComp { .. } => "set comprehension",
ExprKind::GeneratorExp { .. } => "generator expression",
ExprKind::Starred { .. } => "starred",
ExprKind::Slice { .. } => "slice",
ExprKind::JoinedStr { values } => {
if values
.iter()
.any(|e| matches!(e.node, ExprKind::JoinedStr { .. }))
{
"f-string expression"
} else {
"literal"
}
}
ExprKind::FormattedValue { .. } => "f-string expression",
ExprKind::Name { .. } => "name",
ExprKind::Lambda { .. } => "lambda",
ExprKind::IfExp { .. } => "conditional expression",
ExprKind::NamedExpr { .. } => "named expression",
}
}
}

11
nac3ast/src/lib.rs Normal file
View File

@ -0,0 +1,11 @@
mod ast_gen;
mod constant;
#[cfg(feature = "fold")]
mod fold_helpers;
mod impls;
mod location;
pub use ast_gen::*;
pub use location::Location;
pub type Suite<U = ()> = Vec<Stmt<U>>;

79
nac3ast/src/location.rs Normal file
View File

@ -0,0 +1,79 @@
//! Datatypes to support source location information.
use std::fmt;
/// A location somewhere in the sourcecode.
#[derive(Clone, Copy, Debug, Default, PartialEq)]
pub struct Location {
row: usize,
column: usize,
}
impl fmt::Display for Location {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "line {} column {}", self.row, self.column)
}
}
impl Location {
pub fn visualize<'a>(
&self,
line: &'a str,
desc: impl fmt::Display + 'a,
) -> impl fmt::Display + 'a {
struct Visualize<'a, D: fmt::Display> {
loc: Location,
line: &'a str,
desc: D,
}
impl<D: fmt::Display> fmt::Display for Visualize<'_, D> {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"{}\n{}\n{arrow:>pad$}",
self.desc,
self.line,
pad = self.loc.column,
arrow = "",
)
}
}
Visualize {
loc: *self,
line,
desc,
}
}
}
impl Location {
pub fn new(row: usize, column: usize) -> Self {
Location { row, column }
}
pub fn row(&self) -> usize {
self.row
}
pub fn column(&self) -> usize {
self.column
}
pub fn reset(&mut self) {
self.row = 1;
self.column = 1;
}
pub fn go_right(&mut self) {
self.column += 1;
}
pub fn go_left(&mut self) {
self.column -= 1;
}
pub fn newline(&mut self) {
self.row += 1;
self.column = 1;
}
}

27
nac3parser/Cargo.toml Normal file
View File

@ -0,0 +1,27 @@
[package]
name = "rustpython-parser"
version = "0.1.2"
description = "Parser for python code."
authors = [ "RustPython Team" ]
build = "build.rs"
repository = "https://github.com/RustPython/RustPython"
license = "MIT"
edition = "2018"
[build-dependencies]
lalrpop = "0.19.6"
[dependencies]
rustpython-ast = { path = "../ast" }
lalrpop-util = "0.19.6"
log = "0.4.1"
num-bigint = "0.4.0"
num-traits = "0.2"
unic-emoji-char = "0.9"
unic-ucd-ident = "0.9"
unicode_names2 = "0.4"
phf = { version = "0.9", features = ["macros"] }
ahash = "0.7.2"
[dev-dependencies]
insta = "1.5"

66
nac3parser/README.md Normal file
View File

@ -0,0 +1,66 @@
# RustPython/parser
This directory has the code for python lexing, parsing and generating Abstract Syntax Trees (AST).
The steps are:
- Lexical analysis: splits the source code into tokens.
- Parsing and generating the AST: transforms those tokens into an AST. Uses `LALRPOP`, a Rust parser generator framework.
This crate is published on [https://docs.rs/rustpython-parser](https://docs.rs/rustpython-parser).
We wrote [a blog post](https://rustpython.github.io/2020/04/02/thing-explainer-parser.html) with screenshots and an explanation to help you understand the steps by seeing them in action.
For more information on LALRPOP, here is a link to the [LALRPOP book](https://github.com/lalrpop/lalrpop).
There is a readme in the `src` folder with the details of each file.
## Directory content
`build.rs`: The build script.
`Cargo.toml`: The config file.
The `src` directory has:
**lib.rs**
This is the crate's root.
**lexer.rs**
This module takes care of lexing python source text. This means source code is translated into separate tokens.
**parser.rs**
A python parsing module. Use this module to parse python code into an AST. There are three ways to parse python code. You could parse a whole program, a single statement, or a single expression.
**ast.rs**
Implements abstract syntax tree (AST) nodes for the python language. Roughly equivalent to [the python AST](https://docs.python.org/3/library/ast.html).
**python.lalrpop**
Python grammar.
**token.rs**
Different token definitions. Loosely based on token.h from CPython source.
**errors.rs**
Define internal parse error types. The goal is to provide a matching and a safe error API, masking errors from LALR.
**fstring.rs**
Format strings.
**function.rs**
Collection of functions for parsing parameters, arguments.
**location.rs**
Datatypes to support source location information.
**mode.rs**
Execution mode check. Allowed modes are `exec`, `eval` or `single`.
## How to use
For example, one could do this:
```
use rustpython_parser::{parser, ast};
let python_source = "print('Hello world')";
let python_ast = parser::parse_expression(python_source).unwrap();
```

3
nac3parser/build.rs Normal file
View File

@ -0,0 +1,3 @@
fn main() {
lalrpop::process_root().unwrap()
}

239
nac3parser/src/error.rs Normal file
View File

@ -0,0 +1,239 @@
//! Define internal parse error types
//! The goal is to provide a matching and a safe error API, maksing errors from LALR
use lalrpop_util::ParseError as LalrpopError;
use crate::ast::Location;
use crate::token::Tok;
use std::error::Error;
use std::fmt;
/// Represents an error during lexical scanning.
#[derive(Debug, PartialEq)]
pub struct LexicalError {
pub error: LexicalErrorType,
pub location: Location,
}
#[derive(Debug, PartialEq)]
pub enum LexicalErrorType {
StringError,
UnicodeError,
NestingError,
IndentationError,
TabError,
TabsAfterSpaces,
DefaultArgumentError,
PositionalArgumentError,
DuplicateKeywordArgumentError,
UnrecognizedToken { tok: char },
FStringError(FStringErrorType),
LineContinuationError,
Eof,
OtherError(String),
}
impl fmt::Display for LexicalErrorType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
LexicalErrorType::StringError => write!(f, "Got unexpected string"),
LexicalErrorType::FStringError(error) => write!(f, "Got error in f-string: {}", error),
LexicalErrorType::UnicodeError => write!(f, "Got unexpected unicode"),
LexicalErrorType::NestingError => write!(f, "Got unexpected nesting"),
LexicalErrorType::IndentationError => {
write!(f, "unindent does not match any outer indentation level")
}
LexicalErrorType::TabError => {
write!(f, "inconsistent use of tabs and spaces in indentation")
}
LexicalErrorType::TabsAfterSpaces => {
write!(f, "Tabs not allowed as part of indentation after spaces")
}
LexicalErrorType::DefaultArgumentError => {
write!(f, "non-default argument follows default argument")
}
LexicalErrorType::DuplicateKeywordArgumentError => {
write!(f, "keyword argument repeated")
}
LexicalErrorType::PositionalArgumentError => {
write!(f, "positional argument follows keyword argument")
}
LexicalErrorType::UnrecognizedToken { tok } => {
write!(f, "Got unexpected token {}", tok)
}
LexicalErrorType::LineContinuationError => {
write!(f, "unexpected character after line continuation character")
}
LexicalErrorType::Eof => write!(f, "unexpected EOF while parsing"),
LexicalErrorType::OtherError(msg) => write!(f, "{}", msg),
}
}
}
// TODO: consolidate these with ParseError
#[derive(Debug, PartialEq)]
pub struct FStringError {
pub error: FStringErrorType,
pub location: Location,
}
#[derive(Debug, PartialEq)]
pub enum FStringErrorType {
UnclosedLbrace,
UnopenedRbrace,
ExpectedRbrace,
InvalidExpression(Box<ParseErrorType>),
InvalidConversionFlag,
EmptyExpression,
MismatchedDelimiter,
ExpressionNestedTooDeeply,
}
impl fmt::Display for FStringErrorType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
FStringErrorType::UnclosedLbrace => write!(f, "Unclosed '{{'"),
FStringErrorType::UnopenedRbrace => write!(f, "Unopened '}}'"),
FStringErrorType::ExpectedRbrace => write!(f, "Expected '}}' after conversion flag."),
FStringErrorType::InvalidExpression(error) => {
write!(f, "Invalid expression: {}", error)
}
FStringErrorType::InvalidConversionFlag => write!(f, "Invalid conversion flag"),
FStringErrorType::EmptyExpression => write!(f, "Empty expression"),
FStringErrorType::MismatchedDelimiter => write!(f, "Mismatched delimiter"),
FStringErrorType::ExpressionNestedTooDeeply => {
write!(f, "expressions nested too deeply")
}
}
}
}
impl From<FStringError> for LalrpopError<Location, Tok, LexicalError> {
fn from(err: FStringError) -> Self {
lalrpop_util::ParseError::User {
error: LexicalError {
error: LexicalErrorType::FStringError(err.error),
location: err.location,
},
}
}
}
/// Represents an error during parsing
#[derive(Debug, PartialEq)]
pub struct ParseError {
pub error: ParseErrorType,
pub location: Location,
}
#[derive(Debug, PartialEq)]
pub enum ParseErrorType {
/// Parser encountered an unexpected end of input
Eof,
/// Parser encountered an extra token
ExtraToken(Tok),
/// Parser encountered an invalid token
InvalidToken,
/// Parser encountered an unexpected token
UnrecognizedToken(Tok, Option<String>),
/// Maps to `User` type from `lalrpop-util`
Lexical(LexicalErrorType),
}
/// Convert `lalrpop_util::ParseError` to our internal type
impl From<LalrpopError<Location, Tok, LexicalError>> for ParseError {
fn from(err: LalrpopError<Location, Tok, LexicalError>) -> Self {
match err {
// TODO: Are there cases where this isn't an EOF?
LalrpopError::InvalidToken { location } => ParseError {
error: ParseErrorType::Eof,
location,
},
LalrpopError::ExtraToken { token } => ParseError {
error: ParseErrorType::ExtraToken(token.1),
location: token.0,
},
LalrpopError::User { error } => ParseError {
error: ParseErrorType::Lexical(error.error),
location: error.location,
},
LalrpopError::UnrecognizedToken { token, expected } => {
// Hacky, but it's how CPython does it. See PyParser_AddToken,
// in particular "Only one possible expected token" comment.
let expected = if expected.len() == 1 {
Some(expected[0].clone())
} else {
None
};
ParseError {
error: ParseErrorType::UnrecognizedToken(token.1, expected),
location: token.0,
}
}
LalrpopError::UnrecognizedEOF { location, .. } => ParseError {
error: ParseErrorType::Eof,
location,
},
}
}
}
impl fmt::Display for ParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{} at {}", self.error, self.location)
}
}
impl fmt::Display for ParseErrorType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match *self {
ParseErrorType::Eof => write!(f, "Got unexpected EOF"),
ParseErrorType::ExtraToken(ref tok) => write!(f, "Got extraneous token: {:?}", tok),
ParseErrorType::InvalidToken => write!(f, "Got invalid token"),
ParseErrorType::UnrecognizedToken(ref tok, ref expected) => {
if *tok == Tok::Indent {
write!(f, "unexpected indent")
} else if expected.as_deref() == Some("Indent") {
write!(f, "expected an indented block")
} else {
write!(f, "Got unexpected token {}", tok)
}
}
ParseErrorType::Lexical(ref error) => write!(f, "{}", error),
}
}
}
impl Error for ParseErrorType {}
impl ParseErrorType {
pub fn is_indentation_error(&self) -> bool {
match self {
ParseErrorType::Lexical(LexicalErrorType::IndentationError) => true,
ParseErrorType::UnrecognizedToken(token, expected) => {
*token == Tok::Indent || expected.clone() == Some("Indent".to_owned())
}
_ => false,
}
}
pub fn is_tab_error(&self) -> bool {
matches!(
self,
ParseErrorType::Lexical(LexicalErrorType::TabError)
| ParseErrorType::Lexical(LexicalErrorType::TabsAfterSpaces)
)
}
}
impl std::ops::Deref for ParseError {
type Target = ParseErrorType;
fn deref(&self) -> &Self::Target {
&self.error
}
}
impl Error for ParseError {
fn source(&self) -> Option<&(dyn Error + 'static)> {
None
}
}

405
nac3parser/src/fstring.rs Normal file
View File

@ -0,0 +1,405 @@
use std::iter;
use std::mem;
use std::str;
use crate::ast::{Constant, ConversionFlag, Expr, ExprKind, Location};
use crate::error::{FStringError, FStringErrorType, ParseError};
use crate::parser::parse_expression;
use self::FStringErrorType::*;
struct FStringParser<'a> {
chars: iter::Peekable<str::Chars<'a>>,
str_location: Location,
}
impl<'a> FStringParser<'a> {
fn new(source: &'a str, str_location: Location) -> Self {
Self {
chars: source.chars().peekable(),
str_location,
}
}
#[inline]
fn expr(&self, node: ExprKind) -> Expr {
Expr::new(self.str_location, node)
}
fn parse_formatted_value(&mut self) -> Result<Vec<Expr>, FStringErrorType> {
let mut expression = String::new();
let mut spec = None;
let mut delims = Vec::new();
let mut conversion = None;
let mut pred_expression_text = String::new();
let mut trailing_seq = String::new();
while let Some(ch) = self.chars.next() {
match ch {
// can be integrated better with the remainign code, but as a starting point ok
// in general I would do here a tokenizing of the fstrings to omit this peeking.
'!' if self.chars.peek() == Some(&'=') => {
expression.push_str("!=");
self.chars.next();
}
'=' if self.chars.peek() == Some(&'=') => {
expression.push_str("==");
self.chars.next();
}
'>' if self.chars.peek() == Some(&'=') => {
expression.push_str(">=");
self.chars.next();
}
'<' if self.chars.peek() == Some(&'=') => {
expression.push_str("<=");
self.chars.next();
}
'!' if delims.is_empty() && self.chars.peek() != Some(&'=') => {
if expression.trim().is_empty() {
return Err(EmptyExpression);
}
conversion = Some(match self.chars.next() {
Some('s') => ConversionFlag::Str,
Some('a') => ConversionFlag::Ascii,
Some('r') => ConversionFlag::Repr,
Some(_) => {
return Err(InvalidConversionFlag);
}
None => {
return Err(ExpectedRbrace);
}
});
if let Some(&peek) = self.chars.peek() {
if peek != '}' && peek != ':' {
return Err(ExpectedRbrace);
}
} else {
return Err(ExpectedRbrace);
}
}
// match a python 3.8 self documenting expression
// format '{' PYTHON_EXPRESSION '=' FORMAT_SPECIFIER? '}'
'=' if self.chars.peek() != Some(&'=') && delims.is_empty() => {
pred_expression_text = expression.to_string(); // safe expression before = to print it
}
':' if delims.is_empty() => {
let mut nested = false;
let mut in_nested = false;
let mut spec_expression = String::new();
while let Some(&next) = self.chars.peek() {
match next {
'{' => {
if in_nested {
return Err(ExpressionNestedTooDeeply);
}
in_nested = true;
nested = true;
self.chars.next();
continue;
}
'}' => {
if in_nested {
in_nested = false;
self.chars.next();
}
break;
}
_ => (),
}
spec_expression.push(next);
self.chars.next();
}
if in_nested {
return Err(UnclosedLbrace);
}
spec = Some(if nested {
Box::new(
self.expr(ExprKind::FormattedValue {
value: Box::new(
parse_fstring_expr(&spec_expression)
.map_err(|e| InvalidExpression(Box::new(e.error)))?,
),
conversion: None,
format_spec: None,
}),
)
} else {
Box::new(self.expr(ExprKind::Constant {
value: spec_expression.to_owned().into(),
kind: None,
}))
})
}
'(' | '{' | '[' => {
expression.push(ch);
delims.push(ch);
}
')' => {
if delims.pop() != Some('(') {
return Err(MismatchedDelimiter);
}
expression.push(ch);
}
']' => {
if delims.pop() != Some('[') {
return Err(MismatchedDelimiter);
}
expression.push(ch);
}
'}' if !delims.is_empty() => {
if delims.pop() != Some('{') {
return Err(MismatchedDelimiter);
}
expression.push(ch);
}
'}' => {
if expression.is_empty() {
return Err(EmptyExpression);
}
let ret = if pred_expression_text.is_empty() {
vec![self.expr(ExprKind::FormattedValue {
value: Box::new(
parse_fstring_expr(&expression)
.map_err(|e| InvalidExpression(Box::new(e.error)))?,
),
conversion,
format_spec: spec,
})]
} else {
vec![
self.expr(ExprKind::Constant {
value: Constant::Str(pred_expression_text + "="),
kind: None,
}),
self.expr(ExprKind::Constant {
value: trailing_seq.into(),
kind: None,
}),
self.expr(ExprKind::FormattedValue {
value: Box::new(
parse_fstring_expr(&expression)
.map_err(|e| InvalidExpression(Box::new(e.error)))?,
),
conversion,
format_spec: spec,
}),
]
};
return Ok(ret);
}
'"' | '\'' => {
expression.push(ch);
for next in &mut self.chars {
expression.push(next);
if next == ch {
break;
}
}
}
' ' if !pred_expression_text.is_empty() => {
trailing_seq.push(ch);
}
_ => {
expression.push(ch);
}
}
}
Err(UnclosedLbrace)
}
fn parse(mut self) -> Result<Expr, FStringErrorType> {
let mut content = String::new();
let mut values = vec![];
while let Some(ch) = self.chars.next() {
match ch {
'{' => {
if let Some('{') = self.chars.peek() {
self.chars.next();
content.push('{');
} else {
if !content.is_empty() {
values.push(self.expr(ExprKind::Constant {
value: mem::take(&mut content).into(),
kind: None,
}));
}
values.extend(self.parse_formatted_value()?);
}
}
'}' => {
if let Some('}') = self.chars.peek() {
self.chars.next();
content.push('}');
} else {
return Err(UnopenedRbrace);
}
}
_ => {
content.push(ch);
}
}
}
if !content.is_empty() {
values.push(self.expr(ExprKind::Constant {
value: content.into(),
kind: None,
}))
}
let s = match values.len() {
0 => self.expr(ExprKind::Constant {
value: String::new().into(),
kind: None,
}),
1 => values.into_iter().next().unwrap(),
_ => self.expr(ExprKind::JoinedStr { values }),
};
Ok(s)
}
}
fn parse_fstring_expr(source: &str) -> Result<Expr, ParseError> {
let fstring_body = format!("({})", source);
parse_expression(&fstring_body)
}
/// Parse an fstring from a string, located at a certain position in the sourcecode.
/// In case of errors, we will get the location and the error returned.
pub fn parse_located_fstring(source: &str, location: Location) -> Result<Expr, FStringError> {
FStringParser::new(source, location)
.parse()
.map_err(|error| FStringError { error, location })
}
#[cfg(test)]
mod tests {
use super::*;
fn parse_fstring(source: &str) -> Result<Expr, FStringErrorType> {
FStringParser::new(source, Location::default()).parse()
}
#[test]
fn test_parse_fstring() {
let source = "{a}{ b }{{foo}}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_nested_spec() {
let source = "{foo:{spec}}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_not_nested_spec() {
let source = "{foo:spec}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_empty_fstring() {
insta::assert_debug_snapshot!(parse_fstring("").unwrap());
}
#[test]
fn test_fstring_parse_selfdocumenting_base() {
let src = "{user=}";
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_fstring_parse_selfdocumenting_base_more() {
let src = "mix {user=} with text and {second=}";
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_fstring_parse_selfdocumenting_format() {
let src = "{user=:>10}";
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_invalid_fstring() {
assert_eq!(parse_fstring("{5!a"), Err(ExpectedRbrace));
assert_eq!(parse_fstring("{5!a1}"), Err(ExpectedRbrace));
assert_eq!(parse_fstring("{5!"), Err(ExpectedRbrace));
assert_eq!(parse_fstring("abc{!a 'cat'}"), Err(EmptyExpression));
assert_eq!(parse_fstring("{!a"), Err(EmptyExpression));
assert_eq!(parse_fstring("{ !a}"), Err(EmptyExpression));
assert_eq!(parse_fstring("{5!}"), Err(InvalidConversionFlag));
assert_eq!(parse_fstring("{5!x}"), Err(InvalidConversionFlag));
assert_eq!(parse_fstring("{a:{a:{b}}"), Err(ExpressionNestedTooDeeply));
assert_eq!(parse_fstring("{a:b}}"), Err(UnopenedRbrace));
assert_eq!(parse_fstring("}"), Err(UnopenedRbrace));
assert_eq!(parse_fstring("{a:{b}"), Err(UnclosedLbrace));
assert_eq!(parse_fstring("{"), Err(UnclosedLbrace));
assert_eq!(parse_fstring("{}"), Err(EmptyExpression));
// TODO: check for InvalidExpression enum?
assert!(parse_fstring("{class}").is_err());
}
#[test]
fn test_parse_fstring_not_equals() {
let source = "{1 != 2}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_equals() {
let source = "{42 == 42}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_selfdoc_prec_space() {
let source = "{x =}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_selfdoc_trailing_space() {
let source = "{x= }";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_yield_expr() {
let source = "{yield}";
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
}

View File

@ -0,0 +1,96 @@
use ahash::RandomState;
use std::collections::HashSet;
use crate::ast;
use crate::error::{LexicalError, LexicalErrorType};
pub struct ArgumentList {
pub args: Vec<ast::Expr>,
pub keywords: Vec<ast::Keyword>,
}
type ParameterDefs = (Vec<ast::Arg>, Vec<ast::Arg>, Vec<ast::Expr>);
type ParameterDef = (ast::Arg, Option<ast::Expr>);
pub fn parse_params(
params: (Vec<ParameterDef>, Vec<ParameterDef>),
) -> Result<ParameterDefs, LexicalError> {
let mut posonly = Vec::with_capacity(params.0.len());
let mut names = Vec::with_capacity(params.1.len());
let mut defaults = vec![];
let mut try_default = |name: &ast::Arg, default| {
if let Some(default) = default {
defaults.push(default);
} else if !defaults.is_empty() {
// Once we have started with defaults, all remaining arguments must
// have defaults
return Err(LexicalError {
error: LexicalErrorType::DefaultArgumentError,
location: name.location,
});
}
Ok(())
};
for (name, default) in params.0 {
try_default(&name, default)?;
posonly.push(name);
}
for (name, default) in params.1 {
try_default(&name, default)?;
names.push(name);
}
Ok((posonly, names, defaults))
}
type FunctionArgument = (Option<(ast::Location, Option<String>)>, ast::Expr);
pub fn parse_args(func_args: Vec<FunctionArgument>) -> Result<ArgumentList, LexicalError> {
let mut args = vec![];
let mut keywords = vec![];
let mut keyword_names = HashSet::with_capacity_and_hasher(func_args.len(), RandomState::new());
for (name, value) in func_args {
match name {
Some((location, name)) => {
if let Some(keyword_name) = &name {
if keyword_names.contains(keyword_name) {
return Err(LexicalError {
error: LexicalErrorType::DuplicateKeywordArgumentError,
location,
});
}
keyword_names.insert(keyword_name.clone());
}
keywords.push(ast::Keyword::new(
location,
ast::KeywordData {
arg: name,
value: Box::new(value),
},
));
}
None => {
// Allow starred args after keyword arguments.
if !keywords.is_empty() && !is_starred(&value) {
return Err(LexicalError {
error: LexicalErrorType::PositionalArgumentError,
location: value.location,
});
}
args.push(value);
}
}
}
Ok(ArgumentList { args, keywords })
}
fn is_starred(exp: &ast::Expr) -> bool {
matches!(exp.node, ast::ExprKind::Starred { .. })
}

1757
nac3parser/src/lexer.rs Normal file

File diff suppressed because it is too large Load Diff

37
nac3parser/src/lib.rs Normal file
View File

@ -0,0 +1,37 @@
//! This crate can be used to parse python sourcecode into a so
//! called AST (abstract syntax tree).
//!
//! The stages involved in this process are lexical analysis and
//! parsing. The lexical analysis splits the sourcecode into
//! tokens, and the parsing transforms those tokens into an AST.
//!
//! For example, one could do this:
//!
//! ```
//! use rustpython_parser::{parser, ast};
//!
//! let python_source = "print('Hello world')";
//! let python_ast = parser::parse_expression(python_source).unwrap();
//!
//! ```
#![doc(html_logo_url = "https://raw.githubusercontent.com/RustPython/RustPython/master/logo.png")]
#![doc(html_root_url = "https://docs.rs/rustpython-parser/")]
#[macro_use]
extern crate log;
use lalrpop_util::lalrpop_mod;
pub use rustpython_ast as ast;
pub mod error;
mod fstring;
mod function;
pub mod lexer;
pub mod mode;
pub mod parser;
lalrpop_mod!(
#[allow(clippy::all)]
#[allow(unused)]
python
);
pub mod token;

40
nac3parser/src/mode.rs Normal file
View File

@ -0,0 +1,40 @@
use crate::token::Tok;
#[derive(Clone, Copy)]
pub enum Mode {
Module,
Interactive,
Expression,
}
impl Mode {
pub(crate) fn to_marker(self) -> Tok {
match self {
Self::Module => Tok::StartModule,
Self::Interactive => Tok::StartInteractive,
Self::Expression => Tok::StartExpression,
}
}
}
impl std::str::FromStr for Mode {
type Err = ModeParseError;
fn from_str(s: &str) -> Result<Self, ModeParseError> {
match s {
"exec" | "single" => Ok(Mode::Module),
"eval" => Ok(Mode::Expression),
_ => Err(ModeParseError { _priv: () }),
}
}
}
#[derive(Debug)]
pub struct ModeParseError {
_priv: (),
}
impl std::fmt::Display for ModeParseError {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
write!(f, r#"mode should be "exec", "eval", or "single""#)
}
}

167
nac3parser/src/parser.rs Normal file
View File

@ -0,0 +1,167 @@
//! Python parsing.
//!
//! Use this module to parse python code into an AST.
//! There are three ways to parse python code. You could
//! parse a whole program, a single statement, or a single
//! expression.
use std::iter;
use crate::ast;
use crate::error::ParseError;
use crate::lexer;
pub use crate::mode::Mode;
use crate::python;
/*
* Parse python code.
* Grammar may be inspired by antlr grammar for python:
* https://github.com/antlr/grammars-v4/tree/master/python3
*/
/// Parse a full python program, containing usually multiple lines.
pub fn parse_program(source: &str) -> Result<ast::Suite, ParseError> {
parse(source, Mode::Module).map(|top| match top {
ast::Mod::Module { body, .. } => body,
_ => unreachable!(),
})
}
/// Parses a python expression
///
/// # Example
/// ```
/// extern crate num_bigint;
/// use rustpython_parser::{parser, ast};
/// let expr = parser::parse_expression("1 + 2").unwrap();
///
/// assert_eq!(
/// expr,
/// ast::Expr {
/// location: ast::Location::new(1, 3),
/// custom: (),
/// node: ast::ExprKind::BinOp {
/// left: Box::new(ast::Expr {
/// location: ast::Location::new(1, 1),
/// custom: (),
/// node: ast::ExprKind::Constant {
/// value: ast::Constant::Int(1.into()),
/// kind: None,
/// }
/// }),
/// op: ast::Operator::Add,
/// right: Box::new(ast::Expr {
/// location: ast::Location::new(1, 5),
/// custom: (),
/// node: ast::ExprKind::Constant {
/// value: ast::Constant::Int(2.into()),
/// kind: None,
/// }
/// })
/// }
/// },
/// );
///
/// ```
pub fn parse_expression(source: &str) -> Result<ast::Expr, ParseError> {
parse(source, Mode::Expression).map(|top| match top {
ast::Mod::Expression { body } => *body,
_ => unreachable!(),
})
}
// Parse a given source code
pub fn parse(source: &str, mode: Mode) -> Result<ast::Mod, ParseError> {
let lxr = lexer::make_tokenizer(source);
let marker_token = (Default::default(), mode.to_marker(), Default::default());
let tokenizer = iter::once(Ok(marker_token)).chain(lxr);
python::TopParser::new()
.parse(tokenizer)
.map_err(ParseError::from)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_parse_empty() {
let parse_ast = parse_program("").unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_hello() {
let source = String::from("print('Hello world')");
let parse_ast = parse_program(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_2() {
let source = String::from("print('Hello world', 2)");
let parse_ast = parse_program(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_kwargs() {
let source = String::from("my_func('positional', keyword=2)");
let parse_ast = parse_program(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_if_elif_else() {
let source = String::from("if 1: 10\nelif 2: 20\nelse: 30");
let parse_ast = parse_program(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_lambda() {
let source = "lambda x, y: x * y"; // lambda(x, y): x * y";
let parse_ast = parse_program(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_tuples() {
let source = "a, b = 4, 5";
insta::assert_debug_snapshot!(parse_program(&source).unwrap());
}
#[test]
fn test_parse_class() {
let source = "\
class Foo(A, B):
def __init__(self):
pass
def method_with_default(self, arg='default'):
pass";
insta::assert_debug_snapshot!(parse_program(&source).unwrap());
}
#[test]
fn test_parse_dict_comprehension() {
let source = String::from("{x1: x2 for y in z}");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_list_comprehension() {
let source = String::from("[x for y in z]");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_double_list_comprehension() {
let source = String::from("[x for y, y2 in z for a in b if a < 5 if a > 10]");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,63 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"user=",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "user",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
],
},
}

View File

@ -0,0 +1,137 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"mix ",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"user=",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "user",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
" with text and ",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"second=",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "second",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
],
},
}

View File

@ -0,0 +1,77 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"user=",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "user",
ctx: Load,
},
},
conversion: None,
format_spec: Some(
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
">10",
),
kind: None,
},
},
),
},
},
],
},
}

View File

@ -0,0 +1,17 @@
---
source: parser/src/fstring.rs
expression: "parse_fstring(\"\").unwrap()"
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
}

View File

@ -0,0 +1,72 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "a",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 3,
},
custom: (),
node: Name {
id: "b",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"{foo}",
),
kind: None,
},
},
],
},
}

View File

@ -0,0 +1,56 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 5,
},
custom: (),
node: Compare {
left: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Constant {
value: Int(
42,
),
kind: None,
},
},
ops: [
Eq,
],
comparators: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Constant {
value: Int(
42,
),
kind: None,
},
},
],
},
},
conversion: None,
format_spec: None,
},
}

View File

@ -0,0 +1,49 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "foo",
ctx: Load,
},
},
conversion: None,
format_spec: Some(
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "spec",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
),
},
}

View File

@ -0,0 +1,56 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 4,
},
custom: (),
node: Compare {
left: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Constant {
value: Int(
1,
),
kind: None,
},
},
ops: [
NotEq,
],
comparators: [
Located {
location: Location {
row: 1,
column: 7,
},
custom: (),
node: Constant {
value: Int(
2,
),
kind: None,
},
},
],
},
},
conversion: None,
format_spec: None,
},
}

View File

@ -0,0 +1,40 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "foo",
ctx: Load,
},
},
conversion: None,
format_spec: Some(
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"spec",
),
kind: None,
},
},
),
},
}

View File

@ -0,0 +1,63 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"x =",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "x",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
],
},
}

View File

@ -0,0 +1,63 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: JoinedStr {
values: [
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
"x=",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: Constant {
value: Str(
" ",
),
kind: None,
},
},
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "x",
ctx: Load,
},
},
conversion: None,
format_spec: None,
},
},
],
},
}

View File

@ -0,0 +1,25 @@
---
source: parser/src/fstring.rs
expression: parse_ast
---
Located {
location: Location {
row: 0,
column: 0,
},
custom: (),
node: FormattedValue {
value: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Yield {
value: None,
},
},
conversion: None,
format_spec: None,
},
}

View File

@ -0,0 +1,160 @@
---
source: parser/src/parser.rs
expression: parse_program(&source).unwrap()
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: ClassDef {
name: "Foo",
bases: [
Located {
location: Location {
row: 1,
column: 11,
},
custom: (),
node: Name {
id: "A",
ctx: Load,
},
},
Located {
location: Location {
row: 1,
column: 14,
},
custom: (),
node: Name {
id: "B",
ctx: Load,
},
},
],
keywords: [],
body: [
Located {
location: Location {
row: 2,
column: 2,
},
custom: (),
node: FunctionDef {
name: "__init__",
args: Arguments {
posonlyargs: [],
args: [
Located {
location: Location {
row: 2,
column: 15,
},
custom: (),
node: ArgData {
arg: "self",
annotation: None,
type_comment: None,
},
},
],
vararg: None,
kwonlyargs: [],
kw_defaults: [],
kwarg: None,
defaults: [],
},
body: [
Located {
location: Location {
row: 3,
column: 3,
},
custom: (),
node: Pass,
},
],
decorator_list: [],
returns: None,
type_comment: None,
},
},
Located {
location: Location {
row: 4,
column: 2,
},
custom: (),
node: FunctionDef {
name: "method_with_default",
args: Arguments {
posonlyargs: [],
args: [
Located {
location: Location {
row: 4,
column: 26,
},
custom: (),
node: ArgData {
arg: "self",
annotation: None,
type_comment: None,
},
},
Located {
location: Location {
row: 4,
column: 32,
},
custom: (),
node: ArgData {
arg: "arg",
annotation: None,
type_comment: None,
},
},
],
vararg: None,
kwonlyargs: [],
kw_defaults: [],
kwarg: None,
defaults: [
Located {
location: Location {
row: 4,
column: 37,
},
custom: (),
node: Constant {
value: Str(
"default",
),
kind: None,
},
},
],
},
body: [
Located {
location: Location {
row: 5,
column: 3,
},
custom: (),
node: Pass,
},
],
decorator_list: [],
returns: None,
type_comment: None,
},
},
],
decorator_list: [],
},
},
]

View File

@ -0,0 +1,63 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: DictComp {
key: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "x1",
ctx: Load,
},
},
value: Located {
location: Location {
row: 1,
column: 6,
},
custom: (),
node: Name {
id: "x2",
ctx: Load,
},
},
generators: [
Comprehension {
target: Located {
location: Location {
row: 1,
column: 13,
},
custom: (),
node: Name {
id: "y",
ctx: Load,
},
},
iter: Located {
location: Location {
row: 1,
column: 18,
},
custom: (),
node: Name {
id: "z",
ctx: Load,
},
},
ifs: [],
is_async: false,
},
],
},
}

View File

@ -0,0 +1,179 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: ListComp {
elt: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "x",
ctx: Load,
},
},
generators: [
Comprehension {
target: Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Tuple {
elts: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Name {
id: "y",
ctx: Load,
},
},
Located {
location: Location {
row: 1,
column: 11,
},
custom: (),
node: Name {
id: "y2",
ctx: Load,
},
},
],
ctx: Load,
},
},
iter: Located {
location: Location {
row: 1,
column: 17,
},
custom: (),
node: Name {
id: "z",
ctx: Load,
},
},
ifs: [],
is_async: false,
},
Comprehension {
target: Located {
location: Location {
row: 1,
column: 23,
},
custom: (),
node: Name {
id: "a",
ctx: Load,
},
},
iter: Located {
location: Location {
row: 1,
column: 28,
},
custom: (),
node: Name {
id: "b",
ctx: Load,
},
},
ifs: [
Located {
location: Location {
row: 1,
column: 35,
},
custom: (),
node: Compare {
left: Located {
location: Location {
row: 1,
column: 33,
},
custom: (),
node: Name {
id: "a",
ctx: Load,
},
},
ops: [
Lt,
],
comparators: [
Located {
location: Location {
row: 1,
column: 37,
},
custom: (),
node: Constant {
value: Int(
5,
),
kind: None,
},
},
],
},
},
Located {
location: Location {
row: 1,
column: 44,
},
custom: (),
node: Compare {
left: Located {
location: Location {
row: 1,
column: 42,
},
custom: (),
node: Name {
id: "a",
ctx: Load,
},
},
ops: [
Gt,
],
comparators: [
Located {
location: Location {
row: 1,
column: 46,
},
custom: (),
node: Constant {
value: Int(
10,
),
kind: None,
},
},
],
},
},
],
is_async: false,
},
],
},
}

View File

@ -0,0 +1,5 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[]

View File

@ -0,0 +1,125 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: If {
test: Located {
location: Location {
row: 1,
column: 4,
},
custom: (),
node: Constant {
value: Int(
1,
),
kind: None,
},
},
body: [
Located {
location: Location {
row: 1,
column: 7,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 1,
column: 7,
},
custom: (),
node: Constant {
value: Int(
10,
),
kind: None,
},
},
},
},
],
orelse: [
Located {
location: Location {
row: 2,
column: 1,
},
custom: (),
node: If {
test: Located {
location: Location {
row: 2,
column: 6,
},
custom: (),
node: Constant {
value: Int(
2,
),
kind: None,
},
},
body: [
Located {
location: Location {
row: 2,
column: 9,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 2,
column: 9,
},
custom: (),
node: Constant {
value: Int(
20,
),
kind: None,
},
},
},
},
],
orelse: [
Located {
location: Location {
row: 3,
column: 7,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 3,
column: 7,
},
custom: (),
node: Constant {
value: Int(
30,
),
kind: None,
},
},
},
},
],
},
},
],
},
},
]

View File

@ -0,0 +1,78 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Call {
func: Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Name {
id: "my_func",
ctx: Load,
},
},
args: [
Located {
location: Location {
row: 1,
column: 10,
},
custom: (),
node: Constant {
value: Str(
"positional",
),
kind: None,
},
},
],
keywords: [
Located {
location: Location {
row: 1,
column: 23,
},
custom: (),
node: KeywordData {
arg: Some(
"keyword",
),
value: Located {
location: Location {
row: 1,
column: 31,
},
custom: (),
node: Constant {
value: Int(
2,
),
kind: None,
},
},
},
},
],
},
},
},
},
]

View File

@ -0,0 +1,90 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Lambda {
args: Arguments {
posonlyargs: [],
args: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: ArgData {
arg: "x",
annotation: None,
type_comment: None,
},
},
Located {
location: Location {
row: 1,
column: 11,
},
custom: (),
node: ArgData {
arg: "y",
annotation: None,
type_comment: None,
},
},
],
vararg: None,
kwonlyargs: [],
kw_defaults: [],
kwarg: None,
defaults: [],
},
body: Located {
location: Location {
row: 1,
column: 16,
},
custom: (),
node: BinOp {
left: Located {
location: Location {
row: 1,
column: 14,
},
custom: (),
node: Name {
id: "x",
ctx: Load,
},
},
op: Mult,
right: Located {
location: Location {
row: 1,
column: 18,
},
custom: (),
node: Name {
id: "y",
ctx: Load,
},
},
},
},
},
},
},
},
]

View File

@ -0,0 +1,52 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: ListComp {
elt: Located {
location: Location {
row: 1,
column: 2,
},
custom: (),
node: Name {
id: "x",
ctx: Load,
},
},
generators: [
Comprehension {
target: Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Name {
id: "y",
ctx: Load,
},
},
iter: Located {
location: Location {
row: 1,
column: 13,
},
custom: (),
node: Name {
id: "z",
ctx: Load,
},
},
ifs: [],
is_async: false,
},
],
},
}

View File

@ -0,0 +1,65 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 1,
column: 6,
},
custom: (),
node: Call {
func: Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Name {
id: "print",
ctx: Load,
},
},
args: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Constant {
value: Str(
"Hello world",
),
kind: None,
},
},
Located {
location: Location {
row: 1,
column: 22,
},
custom: (),
node: Constant {
value: Int(
2,
),
kind: None,
},
},
],
keywords: [],
},
},
},
},
]

View File

@ -0,0 +1,51 @@
---
source: parser/src/parser.rs
expression: parse_ast
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Expr {
value: Located {
location: Location {
row: 1,
column: 6,
},
custom: (),
node: Call {
func: Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Name {
id: "print",
ctx: Load,
},
},
args: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Constant {
value: Str(
"Hello world",
),
kind: None,
},
},
],
keywords: [],
},
},
},
},
]

View File

@ -0,0 +1,91 @@
---
source: parser/src/parser.rs
expression: parse_program(&source).unwrap()
---
[
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Assign {
targets: [
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Tuple {
elts: [
Located {
location: Location {
row: 1,
column: 1,
},
custom: (),
node: Name {
id: "a",
ctx: Load,
},
},
Located {
location: Location {
row: 1,
column: 4,
},
custom: (),
node: Name {
id: "b",
ctx: Load,
},
},
],
ctx: Load,
},
},
],
value: Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Tuple {
elts: [
Located {
location: Location {
row: 1,
column: 8,
},
custom: (),
node: Constant {
value: Int(
4,
),
kind: None,
},
},
Located {
location: Location {
row: 1,
column: 11,
},
custom: (),
node: Constant {
value: Int(
5,
),
kind: None,
},
},
],
ctx: Load,
},
},
type_comment: None,
},
},
]

227
nac3parser/src/token.rs Normal file
View File

@ -0,0 +1,227 @@
//! Different token definitions.
//! Loosely based on token.h from CPython source:
use num_bigint::BigInt;
use std::fmt::{self, Write};
/// Python source code can be tokenized in a sequence of these tokens.
#[derive(Clone, Debug, PartialEq)]
pub enum Tok {
Name { name: String },
Int { value: BigInt },
Float { value: f64 },
Complex { real: f64, imag: f64 },
String { value: String, is_fstring: bool },
Bytes { value: Vec<u8> },
Newline,
Indent,
Dedent,
StartModule,
StartInteractive,
StartExpression,
EndOfFile,
Lpar,
Rpar,
Lsqb,
Rsqb,
Colon,
Comma,
Semi,
Plus,
Minus,
Star,
Slash,
Vbar, // '|'
Amper, // '&'
Less,
Greater,
Equal,
Dot,
Percent,
Lbrace,
Rbrace,
EqEqual,
NotEqual,
LessEqual,
GreaterEqual,
Tilde,
CircumFlex,
LeftShift,
RightShift,
DoubleStar,
DoubleStarEqual, // '**='
PlusEqual,
MinusEqual,
StarEqual,
SlashEqual,
PercentEqual,
AmperEqual, // '&='
VbarEqual,
CircumflexEqual, // '^='
LeftShiftEqual,
RightShiftEqual,
DoubleSlash, // '//'
DoubleSlashEqual,
ColonEqual,
At,
AtEqual,
Rarrow,
Ellipsis,
// Keywords (alphabetically):
False,
None,
True,
And,
As,
Assert,
Async,
Await,
Break,
Class,
Continue,
Def,
Del,
Elif,
Else,
Except,
Finally,
For,
From,
Global,
If,
Import,
In,
Is,
Lambda,
Nonlocal,
Not,
Or,
Pass,
Raise,
Return,
Try,
While,
With,
Yield,
}
impl fmt::Display for Tok {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
use Tok::*;
match self {
Name { name } => write!(f, "'{}'", name),
Int { value } => write!(f, "'{}'", value),
Float { value } => write!(f, "'{}'", value),
Complex { real, imag } => write!(f, "{}j{}", real, imag),
String { value, is_fstring } => {
if *is_fstring {
write!(f, "f")?
}
write!(f, "{:?}", value)
}
Bytes { value } => {
write!(f, "b\"")?;
for i in value {
match i {
9 => f.write_str("\\t")?,
10 => f.write_str("\\n")?,
13 => f.write_str("\\r")?,
32..=126 => f.write_char(*i as char)?,
_ => write!(f, "\\x{:02x}", i)?,
}
}
f.write_str("\"")
}
Newline => f.write_str("Newline"),
Indent => f.write_str("Indent"),
Dedent => f.write_str("Dedent"),
StartModule => f.write_str("StartProgram"),
StartInteractive => f.write_str("StartInteractive"),
StartExpression => f.write_str("StartExpression"),
EndOfFile => f.write_str("EOF"),
Lpar => f.write_str("'('"),
Rpar => f.write_str("')'"),
Lsqb => f.write_str("'['"),
Rsqb => f.write_str("']'"),
Colon => f.write_str("':'"),
Comma => f.write_str("','"),
Semi => f.write_str("';'"),
Plus => f.write_str("'+'"),
Minus => f.write_str("'-'"),
Star => f.write_str("'*'"),
Slash => f.write_str("'/'"),
Vbar => f.write_str("'|'"),
Amper => f.write_str("'&'"),
Less => f.write_str("'<'"),
Greater => f.write_str("'>'"),
Equal => f.write_str("'='"),
Dot => f.write_str("'.'"),
Percent => f.write_str("'%'"),
Lbrace => f.write_str("'{'"),
Rbrace => f.write_str("'}'"),
EqEqual => f.write_str("'=='"),
NotEqual => f.write_str("'!='"),
LessEqual => f.write_str("'<='"),
GreaterEqual => f.write_str("'>='"),
Tilde => f.write_str("'~'"),
CircumFlex => f.write_str("'^'"),
LeftShift => f.write_str("'<<'"),
RightShift => f.write_str("'>>'"),
DoubleStar => f.write_str("'**'"),
DoubleStarEqual => f.write_str("'**='"),
PlusEqual => f.write_str("'+='"),
MinusEqual => f.write_str("'-='"),
StarEqual => f.write_str("'*='"),
SlashEqual => f.write_str("'/='"),
PercentEqual => f.write_str("'%='"),
AmperEqual => f.write_str("'&='"),
VbarEqual => f.write_str("'|='"),
CircumflexEqual => f.write_str("'^='"),
LeftShiftEqual => f.write_str("'<<='"),
RightShiftEqual => f.write_str("'>>='"),
DoubleSlash => f.write_str("'//'"),
DoubleSlashEqual => f.write_str("'//='"),
At => f.write_str("'@'"),
AtEqual => f.write_str("'@='"),
Rarrow => f.write_str("'->'"),
Ellipsis => f.write_str("'...'"),
False => f.write_str("'False'"),
None => f.write_str("'None'"),
True => f.write_str("'True'"),
And => f.write_str("'and'"),
As => f.write_str("'as'"),
Assert => f.write_str("'assert'"),
Async => f.write_str("'async'"),
Await => f.write_str("'await'"),
Break => f.write_str("'break'"),
Class => f.write_str("'class'"),
Continue => f.write_str("'continue'"),
Def => f.write_str("'def'"),
Del => f.write_str("'del'"),
Elif => f.write_str("'elif'"),
Else => f.write_str("'else'"),
Except => f.write_str("'except'"),
Finally => f.write_str("'finally'"),
For => f.write_str("'for'"),
From => f.write_str("'from'"),
Global => f.write_str("'global'"),
If => f.write_str("'if'"),
Import => f.write_str("'import'"),
In => f.write_str("'in'"),
Is => f.write_str("'is'"),
Lambda => f.write_str("'lambda'"),
Nonlocal => f.write_str("'nonlocal'"),
Not => f.write_str("'not'"),
Or => f.write_str("'or'"),
Pass => f.write_str("'pass'"),
Raise => f.write_str("'raise'"),
Return => f.write_str("'return'"),
Try => f.write_str("'try'"),
While => f.write_str("'while'"),
With => f.write_str("'with'"),
Yield => f.write_str("'yield'"),
ColonEqual => f.write_str("':='"),
}
}
}