def parse(self, source_desc, scope, pxd, full_module_name):
if not isinstance(source_desc, FileSourceDescriptor):
raise RuntimeError("Only file sources for code supported")
source_filename = source_desc.filename
scope.cpp = self.cpp
# Parse the given source file and return a parse tree.
try:
f = Utils.open_source_file(source_filename, "rU")
try:
import Parsing
s = PyrexScanner(f,
source_desc,
source_encoding=f.encoding,
scope=scope,
context=self)
tree = Parsing.p_module(s, pxd, full_module_name)
finally:
f.close()
except UnicodeDecodeError, msg:
#import traceback
#traceback.print_exc()
error((
source_desc, 0, 0
), "Decoding error, missing or incorrect coding=<encoding-name> at top of source (%s)"
% msg)
def parse_from_strings(name,
code,
pxds={},
level=None,
initial_pos=None,
context=None,
allow_struct_enum_decorator=False):
"""
Utility method to parse a (unicode) string of code. This is mostly
used for internal Cython compiler purposes (creating code snippets
that transforms should emit, as well as unit testing).
code - a unicode string containing Cython (module-level) code
name - a descriptive name for the code source (to use in error messages etc.)
RETURNS
The tree, i.e. a ModuleNode. The ModuleNode's scope attribute is
set to the scope used when parsing.
"""
if context is None:
context = StringParseContext(name)
# Since source files carry an encoding, it makes sense in this context
# to use a unicode string so that code fragments don't have to bother
# with encoding. This means that test code passed in should not have an
# encoding header.
assert isinstance(code, unicode), "unicode code snippets only please"
encoding = "UTF-8"
module_name = name
if initial_pos is None:
initial_pos = (name, 1, 0)
code_source = StringSourceDescriptor(name, code)
scope = context.find_module(module_name, pos=initial_pos, need_pxd=0)
buf = StringIO(code)
scanner = PyrexScanner(buf,
code_source,
source_encoding=encoding,
scope=scope,
context=context,
initial_pos=initial_pos)
ctx = Parsing.Ctx(allow_struct_enum_decorator=allow_struct_enum_decorator)
if level is None:
tree = Parsing.p_module(scanner, 0, module_name, ctx=ctx)
tree.scope = scope
tree.is_pxd = False
else:
tree = Parsing.p_code(scanner, level=level, ctx=ctx)
tree.scope = scope
return tree
def parse(self, source_filename, scope, pxd):
# Parse the given source file and return a parse tree.
f = open(source_filename, "rU")
s = PyrexScanner(f, source_filename, scope=scope, context=self)
try:
tree = Parsing.p_module(s, pxd)
finally:
f.close()
if Errors.num_errors > 0:
raise CompileError
return tree
def parse(self, source_desc, scope, pxd, full_module_name):
if not isinstance(source_desc, FileSourceDescriptor):
raise RuntimeError("Only file sources for code supported")
source_filename = source_desc.filename
scope.cpp = self.cpp
# Parse the given source file and return a parse tree.
num_errors = Errors.num_errors
try:
f = Utils.open_source_file(source_filename, "rU")
try:
import Parsing
s = PyrexScanner(f,
source_desc,
source_encoding=f.encoding,
scope=scope,
context=self)
tree = Parsing.p_module(s, pxd, full_module_name)
finally:
f.close()
except UnicodeDecodeError, e:
#import traceback
#traceback.print_exc()
line = 1
column = 0
msg = e.args[-1]
position = e.args[2]
encoding = e.args[0]
f = open(source_filename, "rb")
try:
byte_data = f.read()
finally:
f.close()
# FIXME: make this at least a little less inefficient
for idx, c in enumerate(byte_data):
if c in (ord('\n'), '\n'):
line += 1
column = 0
if idx == position:
break
column += 1
error(
(source_desc, line, column),
"Decoding error, missing or incorrect coding=<encoding-name> "
"at top of source (cannot decode with encoding %r: %s)" %
(encoding, msg))