优化项目结构、优化 maven 结构

This commit is contained in:
chenkailing
2021-02-10 00:58:13 +08:00
parent 28d3e05ca9
commit 2542a24675
3610 changed files with 77 additions and 180 deletions

View File

@@ -0,0 +1,31 @@
"""Package for parsing and compiling Python source code
There are several functions defined at the top level that are imported
from modules contained in the package.
parse(buf, mode="exec") -> AST
Converts a string containing Python source code to an abstract
syntax tree (AST). The AST is defined in compiler.ast.
parseFile(path) -> AST
The same as parse(open(path))
walk(ast, visitor, verbose=None)
Does a pre-order walk over the ast using the visitor instance.
See compiler.visitor for details.
compile(source, filename, mode, flags=None, dont_inherit=None)
Returns a code object. A replacement for the builtin compile() function.
compileFile(filename)
Generates a .pyc file by compiling filename.
"""
import warnings
warnings.warn("The compiler package is deprecated and removed in Python 3.x.",
DeprecationWarning, stacklevel=2)
from compiler.transformer import parse, parseFile
from compiler.visitor import walk
from compiler.pycodegen import compile, compileFile

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,23 @@
# operation flags
OP_ASSIGN = 'OP_ASSIGN'
OP_DELETE = 'OP_DELETE'
OP_APPLY = 'OP_APPLY'
SC_LOCAL = 1
SC_GLOBAL_IMPLICIT = 2
SC_GLOBAL_EXPLICIT = 3
SC_FREE = 4
SC_CELL = 5
SC_UNKNOWN = 6
CO_OPTIMIZED = 0x0001
CO_NEWLOCALS = 0x0002
CO_VARARGS = 0x0004
CO_VARKEYWORDS = 0x0008
CO_NESTED = 0x0010
CO_GENERATOR = 0x0020
CO_GENERATOR_ALLOWED = 0
CO_FUTURE_DIVISION = 0x2000
CO_FUTURE_ABSIMPORT = 0x4000
CO_FUTURE_WITH_STATEMENT = 0x8000
CO_FUTURE_PRINT_FUNCTION = 0x10000

View File

@@ -0,0 +1,74 @@
"""Parser for future statements
"""
from compiler import ast, walk
def is_future(stmt):
"""Return true if statement is a well-formed future statement"""
if not isinstance(stmt, ast.From):
return 0
if stmt.modname == "__future__":
return 1
else:
return 0
class FutureParser:
features = ("nested_scopes", "generators", "division",
"absolute_import", "with_statement", "print_function",
"unicode_literals")
def __init__(self):
self.found = {} # set
def visitModule(self, node):
stmt = node.node
for s in stmt.nodes:
if not self.check_stmt(s):
break
def check_stmt(self, stmt):
if is_future(stmt):
for name, asname in stmt.names:
if name in self.features:
self.found[name] = 1
else:
raise SyntaxError, \
"future feature %s is not defined" % name
stmt.valid_future = 1
return 1
return 0
def get_features(self):
"""Return list of features enabled by future statements"""
return self.found.keys()
class BadFutureParser:
"""Check for invalid future statements"""
def visitFrom(self, node):
if hasattr(node, 'valid_future'):
return
if node.modname != "__future__":
return
raise SyntaxError, "invalid future statement " + repr(node)
def find_futures(node):
p1 = FutureParser()
p2 = BadFutureParser()
walk(node, p1)
walk(node, p2)
return p1.get_features()
if __name__ == "__main__":
import sys
from compiler import parseFile, walk
for file in sys.argv[1:]:
print file
tree = parseFile(file)
v = FutureParser()
walk(tree, v)
print v.found
print

View File

@@ -0,0 +1,73 @@
def flatten(tup):
elts = []
for elt in tup:
if isinstance(elt, tuple):
elts = elts + flatten(elt)
else:
elts.append(elt)
return elts
class Set:
def __init__(self):
self.elts = {}
def __len__(self):
return len(self.elts)
def __contains__(self, elt):
return elt in self.elts
def add(self, elt):
self.elts[elt] = elt
def elements(self):
return self.elts.keys()
def has_elt(self, elt):
return elt in self.elts
def remove(self, elt):
del self.elts[elt]
def copy(self):
c = Set()
c.elts.update(self.elts)
return c
class Stack:
def __init__(self):
self.stack = []
self.pop = self.stack.pop
def __len__(self):
return len(self.stack)
def push(self, elt):
self.stack.append(elt)
def top(self):
return self.stack[-1]
def __getitem__(self, index): # needed by visitContinue()
return self.stack[index]
MANGLE_LEN = 256 # magic constant from compile.c
def mangle(name, klass):
if not name.startswith('__'):
return name
if len(name) + 2 >= MANGLE_LEN:
return name
if name.endswith('__'):
return name
try:
i = 0
while klass[i] == '_':
i = i + 1
except IndexError:
return name
klass = klass[i:]
tlen = len(klass) + len(name)
if tlen > MANGLE_LEN:
klass = klass[:MANGLE_LEN-tlen]
return "_%s%s" % (klass, name)
def set_filename(filename, tree):
"""Set the filename attribute to filename on every node in tree"""
worklist = [tree]
while worklist:
node = worklist.pop(0)
node.filename = filename
worklist.extend(node.getChildNodes())

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,462 @@
"""Module symbol-table generator"""
from compiler import ast
from compiler.consts import SC_LOCAL, SC_GLOBAL_IMPLICIT, SC_GLOBAL_EXPLICIT, \
SC_FREE, SC_CELL, SC_UNKNOWN
from compiler.misc import mangle
import types
import sys
MANGLE_LEN = 256
class Scope:
# XXX how much information do I need about each name?
def __init__(self, name, module, klass=None):
self.name = name
self.module = module
self.defs = {}
self.uses = {}
self.globals = {}
self.params = {}
self.frees = {}
self.cells = {}
self.children = []
# nested is true if the class could contain free variables,
# i.e. if it is nested within another function.
self.nested = None
self.generator = None
self.klass = None
if klass is not None:
for i in range(len(klass)):
if klass[i] != '_':
self.klass = klass[i:]
break
def __repr__(self):
return "<%s: %s>" % (self.__class__.__name__, self.name)
def mangle(self, name):
if self.klass is None:
return name
return mangle(name, self.klass)
def add_def(self, name):
self.defs[self.mangle(name)] = 1
def add_use(self, name):
self.uses[self.mangle(name)] = 1
def add_global(self, name):
name = self.mangle(name)
if name in self.uses or name in self.defs:
pass # XXX warn about global following def/use
if name in self.params:
raise SyntaxError, "%s in %s is global and parameter" % \
(name, self.name)
self.globals[name] = 1
self.module.add_def(name)
def add_param(self, name):
name = self.mangle(name)
self.defs[name] = 1
self.params[name] = 1
def get_names(self):
d = {}
d.update(self.defs)
d.update(self.uses)
d.update(self.globals)
return d.keys()
def add_child(self, child):
self.children.append(child)
def get_children(self):
return self.children
def DEBUG(self):
print >> sys.stderr, self.name, self.nested and "nested" or ""
print >> sys.stderr, "\tglobals: ", self.globals
print >> sys.stderr, "\tcells: ", self.cells
print >> sys.stderr, "\tdefs: ", self.defs
print >> sys.stderr, "\tuses: ", self.uses
print >> sys.stderr, "\tfrees:", self.frees
def check_name(self, name):
"""Return scope of name.
The scope of a name could be LOCAL, GLOBAL, FREE, or CELL.
"""
if name in self.globals:
return SC_GLOBAL_EXPLICIT
if name in self.cells:
return SC_CELL
if name in self.defs:
return SC_LOCAL
if self.nested and (name in self.frees or name in self.uses):
return SC_FREE
if self.nested:
return SC_UNKNOWN
else:
return SC_GLOBAL_IMPLICIT
def get_free_vars(self):
if not self.nested:
return ()
free = {}
free.update(self.frees)
for name in self.uses.keys():
if name not in self.defs and name not in self.globals:
free[name] = 1
return free.keys()
def handle_children(self):
for child in self.children:
frees = child.get_free_vars()
globals = self.add_frees(frees)
for name in globals:
child.force_global(name)
def force_global(self, name):
"""Force name to be global in scope.
Some child of the current node had a free reference to name.
When the child was processed, it was labelled a free
variable. Now that all its enclosing scope have been
processed, the name is known to be a global or builtin. So
walk back down the child chain and set the name to be global
rather than free.
Be careful to stop if a child does not think the name is
free.
"""
self.globals[name] = 1
if name in self.frees:
del self.frees[name]
for child in self.children:
if child.check_name(name) == SC_FREE:
child.force_global(name)
def add_frees(self, names):
"""Process list of free vars from nested scope.
Returns a list of names that are either 1) declared global in the
parent or 2) undefined in a top-level parent. In either case,
the nested scope should treat them as globals.
"""
child_globals = []
for name in names:
sc = self.check_name(name)
if self.nested:
if sc == SC_UNKNOWN or sc == SC_FREE \
or isinstance(self, ClassScope):
self.frees[name] = 1
elif sc == SC_GLOBAL_IMPLICIT:
child_globals.append(name)
elif isinstance(self, FunctionScope) and sc == SC_LOCAL:
self.cells[name] = 1
elif sc != SC_CELL:
child_globals.append(name)
else:
if sc == SC_LOCAL:
self.cells[name] = 1
elif sc != SC_CELL:
child_globals.append(name)
return child_globals
def get_cell_vars(self):
return self.cells.keys()
class ModuleScope(Scope):
__super_init = Scope.__init__
def __init__(self):
self.__super_init("global", self)
class FunctionScope(Scope):
pass
class GenExprScope(Scope):
__super_init = Scope.__init__
__counter = 1
def __init__(self, module, klass=None):
i = self.__counter
self.__counter += 1
self.__super_init("generator expression<%d>"%i, module, klass)
self.add_param('.0')
def get_names(self):
keys = Scope.get_names(self)
return keys
class LambdaScope(FunctionScope):
__super_init = Scope.__init__
__counter = 1
def __init__(self, module, klass=None):
i = self.__counter
self.__counter += 1
self.__super_init("lambda.%d" % i, module, klass)
class ClassScope(Scope):
__super_init = Scope.__init__
def __init__(self, name, module):
self.__super_init(name, module, name)
class SymbolVisitor:
def __init__(self):
self.scopes = {}
self.klass = None
# node that define new scopes
def visitModule(self, node):
scope = self.module = self.scopes[node] = ModuleScope()
self.visit(node.node, scope)
visitExpression = visitModule
def visitFunction(self, node, parent):
if node.decorators:
self.visit(node.decorators, parent)
parent.add_def(node.name)
for n in node.defaults:
self.visit(n, parent)
scope = FunctionScope(node.name, self.module, self.klass)
if parent.nested or isinstance(parent, FunctionScope):
scope.nested = 1
self.scopes[node] = scope
self._do_args(scope, node.argnames)
self.visit(node.code, scope)
self.handle_free_vars(scope, parent)
def visitGenExpr(self, node, parent):
scope = GenExprScope(self.module, self.klass);
if parent.nested or isinstance(parent, FunctionScope) \
or isinstance(parent, GenExprScope):
scope.nested = 1
self.scopes[node] = scope
self.visit(node.code, scope)
self.handle_free_vars(scope, parent)
def visitGenExprInner(self, node, scope):
for genfor in node.quals:
self.visit(genfor, scope)
self.visit(node.expr, scope)
def visitGenExprFor(self, node, scope):
self.visit(node.assign, scope, 1)
self.visit(node.iter, scope)
for if_ in node.ifs:
self.visit(if_, scope)
def visitGenExprIf(self, node, scope):
self.visit(node.test, scope)
def visitLambda(self, node, parent, assign=0):
# Lambda is an expression, so it could appear in an expression
# context where assign is passed. The transformer should catch
# any code that has a lambda on the left-hand side.
assert not assign
for n in node.defaults:
self.visit(n, parent)
scope = LambdaScope(self.module, self.klass)
if parent.nested or isinstance(parent, FunctionScope):
scope.nested = 1
self.scopes[node] = scope
self._do_args(scope, node.argnames)
self.visit(node.code, scope)
self.handle_free_vars(scope, parent)
def _do_args(self, scope, args):
for name in args:
if type(name) == types.TupleType:
self._do_args(scope, name)
else:
scope.add_param(name)
def handle_free_vars(self, scope, parent):
parent.add_child(scope)
scope.handle_children()
def visitClass(self, node, parent):
parent.add_def(node.name)
for n in node.bases:
self.visit(n, parent)
scope = ClassScope(node.name, self.module)
if parent.nested or isinstance(parent, FunctionScope):
scope.nested = 1
if node.doc is not None:
scope.add_def('__doc__')
scope.add_def('__module__')
self.scopes[node] = scope
prev = self.klass
self.klass = node.name
self.visit(node.code, scope)
self.klass = prev
self.handle_free_vars(scope, parent)
# name can be a def or a use
# XXX a few calls and nodes expect a third "assign" arg that is
# true if the name is being used as an assignment. only
# expressions contained within statements may have the assign arg.
def visitName(self, node, scope, assign=0):
if assign:
scope.add_def(node.name)
else:
scope.add_use(node.name)
# operations that bind new names
def visitFor(self, node, scope):
self.visit(node.assign, scope, 1)
self.visit(node.list, scope)
self.visit(node.body, scope)
if node.else_:
self.visit(node.else_, scope)
def visitFrom(self, node, scope):
for name, asname in node.names:
if name == "*":
continue
scope.add_def(asname or name)
def visitImport(self, node, scope):
for name, asname in node.names:
i = name.find(".")
if i > -1:
name = name[:i]
scope.add_def(asname or name)
def visitGlobal(self, node, scope):
for name in node.names:
scope.add_global(name)
def visitAssign(self, node, scope):
"""Propagate assignment flag down to child nodes.
The Assign node doesn't itself contains the variables being
assigned to. Instead, the children in node.nodes are visited
with the assign flag set to true. When the names occur in
those nodes, they are marked as defs.
Some names that occur in an assignment target are not bound by
the assignment, e.g. a name occurring inside a slice. The
visitor handles these nodes specially; they do not propagate
the assign flag to their children.
"""
for n in node.nodes:
self.visit(n, scope, 1)
self.visit(node.expr, scope)
def visitAssName(self, node, scope, assign=1):
scope.add_def(node.name)
def visitAssAttr(self, node, scope, assign=0):
self.visit(node.expr, scope, 0)
def visitSubscript(self, node, scope, assign=0):
self.visit(node.expr, scope, 0)
for n in node.subs:
self.visit(n, scope, 0)
def visitSlice(self, node, scope, assign=0):
self.visit(node.expr, scope, 0)
if node.lower:
self.visit(node.lower, scope, 0)
if node.upper:
self.visit(node.upper, scope, 0)
def visitAugAssign(self, node, scope):
# If the LHS is a name, then this counts as assignment.
# Otherwise, it's just use.
self.visit(node.node, scope)
if isinstance(node.node, ast.Name):
self.visit(node.node, scope, 1) # XXX worry about this
self.visit(node.expr, scope)
# prune if statements if tests are false
_const_types = types.StringType, types.IntType, types.FloatType
def visitIf(self, node, scope):
for test, body in node.tests:
if isinstance(test, ast.Const):
if type(test.value) in self._const_types:
if not test.value:
continue
self.visit(test, scope)
self.visit(body, scope)
if node.else_:
self.visit(node.else_, scope)
# a yield statement signals a generator
def visitYield(self, node, scope):
scope.generator = 1
self.visit(node.value, scope)
def list_eq(l1, l2):
return sorted(l1) == sorted(l2)
if __name__ == "__main__":
import sys
from compiler import parseFile, walk
import symtable
def get_names(syms):
return [s for s in [s.get_name() for s in syms.get_symbols()]
if not (s.startswith('_[') or s.startswith('.'))]
for file in sys.argv[1:]:
print file
f = open(file)
buf = f.read()
f.close()
syms = symtable.symtable(buf, file, "exec")
mod_names = get_names(syms)
tree = parseFile(file)
s = SymbolVisitor()
walk(tree, s)
# compare module-level symbols
names2 = s.scopes[tree].get_names()
if not list_eq(mod_names, names2):
print
print "oops", file
print sorted(mod_names)
print sorted(names2)
sys.exit(-1)
d = {}
d.update(s.scopes)
del d[tree]
scopes = d.values()
del d
for s in syms.get_symbols():
if s.is_namespace():
l = [sc for sc in scopes
if sc.name == s.get_name()]
if len(l) > 1:
print "skipping", s.get_name()
else:
if not list_eq(get_names(s.get_namespace()),
l[0].get_names()):
print s.get_name()
print sorted(get_names(s.get_namespace()))
print sorted(l[0].get_names())
sys.exit(-1)

View File

@@ -0,0 +1,46 @@
"""Check for errs in the AST.
The Python parser does not catch all syntax errors. Others, like
assignments with invalid targets, are caught in the code generation
phase.
The compiler package catches some errors in the transformer module.
But it seems clearer to write checkers that use the AST to detect
errors.
"""
from compiler import ast, walk
def check(tree, multi=None):
v = SyntaxErrorChecker(multi)
walk(tree, v)
return v.errors
class SyntaxErrorChecker:
"""A visitor to find syntax errors in the AST."""
def __init__(self, multi=None):
"""Create new visitor object.
If optional argument multi is not None, then print messages
for each error rather than raising a SyntaxError for the
first.
"""
self.multi = multi
self.errors = 0
def error(self, node, msg):
self.errors = self.errors + 1
if self.multi is not None:
print "%s:%s: %s" % (node.filename, node.lineno, msg)
else:
raise SyntaxError, "%s (%s:%s)" % (msg, node.filename, node.lineno)
def visitAssign(self, node):
# the transformer module handles many of these
pass
## for target in node.nodes:
## if isinstance(target, ast.AssList):
## if target.lineno is None:
## target.lineno = node.lineno
## self.error(target, "can't assign to list comprehension")

View File

@@ -0,0 +1,113 @@
from compiler import ast
# XXX should probably rename ASTVisitor to ASTWalker
# XXX can it be made even more generic?
class ASTVisitor:
"""Performs a depth-first walk of the AST
The ASTVisitor will walk the AST, performing either a preorder or
postorder traversal depending on which method is called.
methods:
preorder(tree, visitor)
postorder(tree, visitor)
tree: an instance of ast.Node
visitor: an instance with visitXXX methods
The ASTVisitor is responsible for walking over the tree in the
correct order. For each node, it checks the visitor argument for
a method named 'visitNodeType' where NodeType is the name of the
node's class, e.g. Class. If the method exists, it is called
with the node as its sole argument.
The visitor method for a particular node type can control how
child nodes are visited during a preorder walk. (It can't control
the order during a postorder walk, because it is called _after_
the walk has occurred.) The ASTVisitor modifies the visitor
argument by adding a visit method to the visitor; this method can
be used to visit a child node of arbitrary type.
"""
VERBOSE = 0
def __init__(self):
self.node = None
self._cache = {}
def default(self, node, *args):
for child in node.getChildNodes():
self.dispatch(child, *args)
def dispatch(self, node, *args):
self.node = node
klass = node.__class__
meth = self._cache.get(klass, None)
if meth is None:
className = klass.__name__
meth = getattr(self.visitor, 'visit' + className, self.default)
self._cache[klass] = meth
## if self.VERBOSE > 0:
## className = klass.__name__
## if self.VERBOSE == 1:
## if meth == 0:
## print "dispatch", className
## else:
## print "dispatch", className, (meth and meth.__name__ or '')
return meth(node, *args)
def preorder(self, tree, visitor, *args):
"""Do preorder walk of tree using visitor"""
self.visitor = visitor
visitor.visit = self.dispatch
self.dispatch(tree, *args) # XXX *args make sense?
class ExampleASTVisitor(ASTVisitor):
"""Prints examples of the nodes that aren't visited
This visitor-driver is only useful for development, when it's
helpful to develop a visitor incrementally, and get feedback on what
you still have to do.
"""
examples = {}
def dispatch(self, node, *args):
self.node = node
meth = self._cache.get(node.__class__, None)
className = node.__class__.__name__
if meth is None:
meth = getattr(self.visitor, 'visit' + className, 0)
self._cache[node.__class__] = meth
if self.VERBOSE > 1:
print "dispatch", className, (meth and meth.__name__ or '')
if meth:
meth(node, *args)
elif self.VERBOSE > 0:
klass = node.__class__
if klass not in self.examples:
self.examples[klass] = klass
print
print self.visitor
print klass
for attr in dir(node):
if attr[0] != '_':
print "\t", "%-12.12s" % attr, getattr(node, attr)
print
return self.default(node, *args)
# XXX this is an API change
_walker = ASTVisitor
def walk(tree, visitor, walker=None, verbose=None):
if walker is None:
walker = _walker()
if verbose is not None:
walker.VERBOSE = verbose
walker.preorder(tree, visitor)
return walker.visitor
def dumpNode(node):
print node.__class__
for attr in dir(node):
if attr[0] != '_':
print "\t", "%-10.10s" % attr, getattr(node, attr)