|
|
|
@@ -8,6 +8,7 @@ from draw.Iinstruction import *
|
|
|
|
logging.warning("""Because the Interpreter is still WIP, some Java language features are not supported. These include:
|
|
|
|
logging.warning("""Because the Interpreter is still WIP, some Java language features are not supported. These include:
|
|
|
|
*else if statements
|
|
|
|
*else if statements
|
|
|
|
*for loops
|
|
|
|
*for loops
|
|
|
|
|
|
|
|
*Constructors (will be ignored)
|
|
|
|
Please remove these features from the source code as they will result in incorrect behaviour""")
|
|
|
|
Please remove these features from the source code as they will result in incorrect behaviour""")
|
|
|
|
|
|
|
|
|
|
|
|
class Function_scope(Iterable):
|
|
|
|
class Function_scope(Iterable):
|
|
|
|
@@ -32,8 +33,8 @@ class JavaInterpreter:
|
|
|
|
with open(filepath) as file:
|
|
|
|
with open(filepath) as file:
|
|
|
|
if not file.readable():
|
|
|
|
if not file.readable():
|
|
|
|
raise InterpreterException(f"Unable to read input file {filepath}")
|
|
|
|
raise InterpreterException(f"Unable to read input file {filepath}")
|
|
|
|
self.src = file.read()
|
|
|
|
self._src = file.read()
|
|
|
|
self.lines = [] # to be filled in later
|
|
|
|
self._lines = [] # to be filled in later
|
|
|
|
self._init_regex()
|
|
|
|
self._init_regex()
|
|
|
|
self._recompile_regex()
|
|
|
|
self._recompile_regex()
|
|
|
|
|
|
|
|
|
|
|
|
@@ -46,56 +47,63 @@ class JavaInterpreter:
|
|
|
|
|
|
|
|
|
|
|
|
if additional_tags:
|
|
|
|
if additional_tags:
|
|
|
|
if "comments" in additional_tags.keys():
|
|
|
|
if "comments" in additional_tags.keys():
|
|
|
|
self.comment_tags.extend(additional_tags["comments"])
|
|
|
|
if tags := additional_tags["comments"]:
|
|
|
|
|
|
|
|
self._comment_tags.extend(tags)
|
|
|
|
if "ignore" in additional_tags.keys():
|
|
|
|
if "ignore" in additional_tags.keys():
|
|
|
|
self.remove_tags.extend(additional_tags["ignore"])
|
|
|
|
if tags := additional_tags["ignore"]:
|
|
|
|
|
|
|
|
self._remove_tags.extend(tags)
|
|
|
|
if "types" in additional_tags.keys():
|
|
|
|
if "types" in additional_tags.keys():
|
|
|
|
self.type_tags.extend(additional_tags["types"])
|
|
|
|
if tags := additional_tags["types"]:
|
|
|
|
self.function_tags.extend(additional_tags["types"])
|
|
|
|
self._type_tags.extend(tags)
|
|
|
|
|
|
|
|
self._function_tags.extend(tags)
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
self._init_regex()
|
|
|
|
self._init_regex()
|
|
|
|
self._recompile_regex()
|
|
|
|
self._recompile_regex()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def load_instruction_scopes(self):
|
|
|
|
|
|
|
|
self._remove_keywords()
|
|
|
|
|
|
|
|
return self._get_function_scopes()
|
|
|
|
|
|
|
|
|
|
|
|
def _init_regex(self):
|
|
|
|
def _init_regex(self):
|
|
|
|
"""Initialize all tag lists to their default state"""
|
|
|
|
"""Initialize all tag lists to their default state"""
|
|
|
|
|
|
|
|
|
|
|
|
self.comment_tags = ["//", "#", "--"] #dont ask why a java interpreter supports lua and python style comments
|
|
|
|
self._comment_tags = ["//", "#", "--"] #dont ask why a java interpreter supports lua and python style comments
|
|
|
|
self.remove_tags = ['\n', "public", "private", "protected", "final"]
|
|
|
|
self._remove_tags = ['\n', "public", "private", "protected", "final"]
|
|
|
|
self.type_tags = ["byte", "short", "int", "long", "float", "double", "boolean", "char", "String"]
|
|
|
|
self._type_tags = ["byte", "short", "int", "long", "float", "double", "boolean", "char", "String"]
|
|
|
|
self.function_tags = ["void"]
|
|
|
|
self._function_tags = ["void"]
|
|
|
|
self.function_tags.extend(self.type_tags)
|
|
|
|
self._function_tags.extend(self._type_tags)
|
|
|
|
|
|
|
|
|
|
|
|
def _recompile_regex(self):
|
|
|
|
def _recompile_regex(self):
|
|
|
|
"""recompile all regex's using the new tag lists"""
|
|
|
|
"""recompile all regex's using the new tag lists"""
|
|
|
|
comment_regex = r"""^("""
|
|
|
|
comment_regex = r"""^("""
|
|
|
|
for tag in self.comment_tags:
|
|
|
|
for tag in self._comment_tags:
|
|
|
|
comment_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
comment_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
self.comment_pattern = re.compile(comment_regex[:-1]+").*", flags=re.MULTILINE)
|
|
|
|
self._comment_pattern = re.compile(comment_regex[:-1]+").*", flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
remove_regex = r"""^("""
|
|
|
|
remove_regex = r"""^("""
|
|
|
|
for tag in self.remove_tags:
|
|
|
|
for tag in self._remove_tags:
|
|
|
|
remove_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
remove_regex+= fr"""{re.escape(tag)}|"""
|
|
|
|
self.remove_pattern = re.compile(remove_regex[:-1]+')', flags=re.MULTILINE)
|
|
|
|
self._remove_pattern = re.compile(remove_regex[:-1]+')', flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
variable_regex = r"""^("""
|
|
|
|
variable_regex = r"""^("""
|
|
|
|
for tag in self.type_tags:
|
|
|
|
for tag in self._type_tags:
|
|
|
|
variable_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
variable_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
self.variable_pattern = re.compile(variable_regex[:-1]+")(.*=|.*;)(.*)", flags=re.MULTILINE)
|
|
|
|
self._variable_pattern = re.compile(variable_regex[:-1]+")(.*=|.*;)(.*)", flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
function_regex = r"""^(?P<return_type>"""
|
|
|
|
function_regex = r"""^(?P<return_type>"""
|
|
|
|
for tag in self.function_tags:
|
|
|
|
for tag in self._function_tags:
|
|
|
|
function_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
function_regex += fr"""{re.escape(tag)}|"""
|
|
|
|
self.function_pattern = re.compile(function_regex[:-1]+")(?P<name>.*)[(](?P<args>.*)[)][^;]", flags=re.MULTILINE)
|
|
|
|
self._function_pattern = re.compile(function_regex[:-1]+")(?P<name>.*)[(](?P<args>.*)[)][^;]", flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
def _check_src(self, idx: int, tag: str) -> bool:
|
|
|
|
def _check_src(self, idx: int, tag: str) -> bool:
|
|
|
|
if idx >= len(self.lines):
|
|
|
|
if idx >= len(self._lines):
|
|
|
|
return False
|
|
|
|
return False
|
|
|
|
return tag in self.lines[idx]
|
|
|
|
return tag in self._lines[idx]
|
|
|
|
|
|
|
|
|
|
|
|
def _check_line_start(self, idx: int, tag: str) -> bool:
|
|
|
|
def _check_line_start(self, idx: int, tag: str) -> bool:
|
|
|
|
if idx >= len(self.lines):
|
|
|
|
if idx >= len(self._lines):
|
|
|
|
return False
|
|
|
|
return False
|
|
|
|
return self.lines[idx].startswith(tag)
|
|
|
|
return self._lines[idx].startswith(tag)
|
|
|
|
|
|
|
|
|
|
|
|
def _get_scope_start_offset(self, i: int) -> int:
|
|
|
|
def _get_scope_start_offset(self, i: int) -> int:
|
|
|
|
if self._check_src(i, "{"):
|
|
|
|
if self._check_src(i, "{"):
|
|
|
|
@@ -145,12 +153,12 @@ class JavaInterpreter:
|
|
|
|
|
|
|
|
|
|
|
|
instruction_txt = None
|
|
|
|
instruction_txt = None
|
|
|
|
if self._check_line_start(idx, "}while("):
|
|
|
|
if self._check_line_start(idx, "}while("):
|
|
|
|
end_line = self.lines[idx]
|
|
|
|
end_line = self._lines[idx]
|
|
|
|
bracket_index = end_line.rindex(')') #throws if contruct id ill-formed
|
|
|
|
bracket_index = end_line.rindex(')') #throws if contruct id ill-formed
|
|
|
|
instruction_txt = end_line[7:bracket_index]
|
|
|
|
instruction_txt = end_line[7:bracket_index]
|
|
|
|
elif self._check_line_start(idx+1, "while("):
|
|
|
|
elif self._check_line_start(idx+1, "while("):
|
|
|
|
idx += 1
|
|
|
|
idx += 1
|
|
|
|
end_line = self.lines[idx]
|
|
|
|
end_line = self._lines[idx]
|
|
|
|
bracket_index = end_line.rindex(')')
|
|
|
|
bracket_index = end_line.rindex(')')
|
|
|
|
instruction_txt = end_line[6:bracket_index]
|
|
|
|
instruction_txt = end_line[6:bracket_index]
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
@@ -159,7 +167,7 @@ class JavaInterpreter:
|
|
|
|
return while_instruction_back(instruction_txt, child_instructions), idx
|
|
|
|
return while_instruction_back(instruction_txt, child_instructions), idx
|
|
|
|
|
|
|
|
|
|
|
|
def _handle_variable(self, line: str, idx: int):
|
|
|
|
def _handle_variable(self, line: str, idx: int):
|
|
|
|
groups = self.variable_pattern.match(line).groups()
|
|
|
|
groups = self._variable_pattern.match(line).groups()
|
|
|
|
var_type = groups[0]
|
|
|
|
var_type = groups[0]
|
|
|
|
var_name = groups[1][:-1]
|
|
|
|
var_name = groups[1][:-1]
|
|
|
|
var_value = groups[2]
|
|
|
|
var_value = groups[2]
|
|
|
|
@@ -180,7 +188,7 @@ class JavaInterpreter:
|
|
|
|
logging.debug("Found do-while construct in line: %i", idx+1)
|
|
|
|
logging.debug("Found do-while construct in line: %i", idx+1)
|
|
|
|
return self._handle_do_while(line, idx)
|
|
|
|
return self._handle_do_while(line, idx)
|
|
|
|
|
|
|
|
|
|
|
|
elif self.variable_pattern.match(line):
|
|
|
|
elif self._variable_pattern.match(line):
|
|
|
|
logging.debug("Found variable in line %i", idx+1)
|
|
|
|
logging.debug("Found variable in line %i", idx+1)
|
|
|
|
return self._handle_variable(line, idx)
|
|
|
|
return self._handle_variable(line, idx)
|
|
|
|
|
|
|
|
|
|
|
|
@@ -191,8 +199,8 @@ class JavaInterpreter:
|
|
|
|
def _get_instructions_in_scope(self, idx: int=0) -> Tuple[List[Iinstruction], int]:
|
|
|
|
def _get_instructions_in_scope(self, idx: int=0) -> Tuple[List[Iinstruction], int]:
|
|
|
|
scope: List[Iinstruction] = []
|
|
|
|
scope: List[Iinstruction] = []
|
|
|
|
i = idx
|
|
|
|
i = idx
|
|
|
|
while i < len(self.lines):
|
|
|
|
while i < len(self._lines):
|
|
|
|
line = self.lines[i]
|
|
|
|
line = self._lines[i]
|
|
|
|
|
|
|
|
|
|
|
|
if self._check_src(i, '}'):
|
|
|
|
if self._check_src(i, '}'):
|
|
|
|
break
|
|
|
|
break
|
|
|
|
@@ -204,26 +212,24 @@ class JavaInterpreter:
|
|
|
|
return scope, i
|
|
|
|
return scope, i
|
|
|
|
|
|
|
|
|
|
|
|
def _remove_keywords(self):
|
|
|
|
def _remove_keywords(self):
|
|
|
|
self.src = self.src.replace(' ', '')
|
|
|
|
self.src = self._src.replace(' ', '')
|
|
|
|
self.src = self.comment_pattern.sub('', self.src)
|
|
|
|
self.src = self._comment_pattern.sub('', self.src)
|
|
|
|
self.src = self.remove_pattern.sub('', self.src)
|
|
|
|
self.src = self._remove_pattern.sub('', self.src)
|
|
|
|
self.lines = self.src.splitlines()
|
|
|
|
self._lines = self.src.splitlines()
|
|
|
|
|
|
|
|
|
|
|
|
def _get_function_info(self, match: Match[str]) -> Tuple[str, str, List[str]]:
|
|
|
|
def _get_function_info(self, match: Match[str]) -> Tuple[str, str, List[str]]:
|
|
|
|
groups = match.groupdict()
|
|
|
|
groups = match.groupdict()
|
|
|
|
ftype = groups["return_type"]
|
|
|
|
ftype = groups["return_type"]
|
|
|
|
fargs = groups["args"]
|
|
|
|
fargs = groups["args"].split(',')
|
|
|
|
fname = groups["name"]
|
|
|
|
fname = groups["name"]
|
|
|
|
return ftype, fname, fargs.split(',')
|
|
|
|
return ftype, fname, fargs
|
|
|
|
|
|
|
|
|
|
|
|
def _get_function_instructions(self, function_header: str) -> List[Iinstruction]:
|
|
|
|
def _get_function_instructions(self, function_header: str) -> List[Iinstruction]:
|
|
|
|
idx = self.lines.index(function_header)
|
|
|
|
idx = self._lines.index(function_header)
|
|
|
|
brace_offset = self._get_scope_start_offset(idx)
|
|
|
|
brace_offset = self._get_scope_start_offset(idx)
|
|
|
|
return self._get_instructions_in_scope(idx+brace_offset)[0]
|
|
|
|
return self._get_instructions_in_scope(idx+brace_offset)[0]
|
|
|
|
|
|
|
|
|
|
|
|
def _get_function_scopes(self) -> List[Function_scope]:
|
|
|
|
def _get_function_scope(self, match: re.Match[str]):
|
|
|
|
scopes = []
|
|
|
|
|
|
|
|
for match in self.function_pattern.finditer(self.src):
|
|
|
|
|
|
|
|
span = match.span()
|
|
|
|
span = match.span()
|
|
|
|
header = self.src[span[0]:span[1]].replace('\n', '')
|
|
|
|
header = self.src[span[0]:span[1]].replace('\n', '')
|
|
|
|
|
|
|
|
|
|
|
|
@@ -231,76 +237,9 @@ class JavaInterpreter:
|
|
|
|
|
|
|
|
|
|
|
|
child_instructions = self._get_function_instructions(header)
|
|
|
|
child_instructions = self._get_function_instructions(header)
|
|
|
|
|
|
|
|
|
|
|
|
scopes.append(Function_scope(child_instructions, name, rtype, args))
|
|
|
|
return Function_scope(child_instructions, name, rtype, args)
|
|
|
|
return scopes
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def load_instruction_scopes(self):
|
|
|
|
def _get_function_scopes(self) -> List[Function_scope]:
|
|
|
|
self._remove_keywords()
|
|
|
|
matches = self._function_pattern.finditer(self.src)
|
|
|
|
return self._get_function_scopes()
|
|
|
|
return list(map(self._get_function_scope, matches))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# COMMENT_PATTERN = re.compile(r"""^(//|#|--)""")
|
|
|
|
|
|
|
|
# REMOVE_KEYWORDS = [' ', "public", "private", "final", "protected"]
|
|
|
|
|
|
|
|
# VARIABLE_TAGS = ["byte", "short", "int", "long", "float", "double", "boolean", "char", "String"]
|
|
|
|
|
|
|
|
# FUNCTION_IDENTIFIERS = ["void"]
|
|
|
|
|
|
|
|
# FUNCTION_IDENTIFIERS.extend(VARIABLE_TAGS)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# WHILE_TAG = "solange " #german for 'while'. Change this depending on your language
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# REPLACE = dict((re.escape(k), '') for k in REMOVE_KEYWORDS)
|
|
|
|
|
|
|
|
# remove_pattern = re.compile("|".join(REPLACE.keys()), flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# variable_regex = "^("
|
|
|
|
|
|
|
|
# for kw in VARIABLE_TAGS:
|
|
|
|
|
|
|
|
# variable_regex += fr"""{kw}|"""
|
|
|
|
|
|
|
|
# variable_pattern = re.compile(variable_regex[0:-1]+")(.*=|.*;)(.*)", flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# function_regex = "^(?P<return_type>"
|
|
|
|
|
|
|
|
# for kw in FUNCTION_IDENTIFIERS:
|
|
|
|
|
|
|
|
# function_regex += fr"""{kw}|"""
|
|
|
|
|
|
|
|
# function_regex = function_regex[0:-1]+ ")(?P<name>.*)[(](?P<args>.*)[)][^;]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# function_pattern = re.compile(function_regex, flags=re.MULTILINE)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# def check_src(src: List[str], line_index: int, tag: str) -> bool:
|
|
|
|
|
|
|
|
# if line_index >= len(src):
|
|
|
|
|
|
|
|
# return False
|
|
|
|
|
|
|
|
# return tag in src[line_index]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# def check_line_start(src: List[str], line_index: int, tag: str) -> bool:
|
|
|
|
|
|
|
|
# if line_index >= len(src):
|
|
|
|
|
|
|
|
# return False
|
|
|
|
|
|
|
|
# return src[line_index].startswith(tag)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# def get_next_occurence_of(src: List[str], start_idx:int, tag:str) -> int:
|
|
|
|
|
|
|
|
# """Returns the index of the next occurence of tag in src from start_idx"""
|
|
|
|
|
|
|
|
# i = start_idx
|
|
|
|
|
|
|
|
# while i < len(src):
|
|
|
|
|
|
|
|
# if check_src(src, i, tag):
|
|
|
|
|
|
|
|
# break
|
|
|
|
|
|
|
|
# i += 1
|
|
|
|
|
|
|
|
# return i
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# def get_scope_start_offset(src: List[str], i: int) -> int:
|
|
|
|
|
|
|
|
# if check_src(src, i, "{"):
|
|
|
|
|
|
|
|
# return 1
|
|
|
|
|
|
|
|
# elif check_src(src, i+1, "{"):
|
|
|
|
|
|
|
|
# return 2
|
|
|
|
|
|
|
|
# raise ScopeNotFoundException("Unable to find scope start. Is the program ill-formed?")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# def get_function_scopes(src: str) -> List[Function_scope]:
|
|
|
|
|
|
|
|
# scopes = []
|
|
|
|
|
|
|
|
# lines = src.splitlines(True)
|
|
|
|
|
|
|
|
# for match in function_pattern.finditer(src):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# span = match.span()
|
|
|
|
|
|
|
|
# matched_str = src[span[0]:span[1]]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# rtype, name, args = get_function_info(match, matched_str)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# child_instructions = get_function_instructions(lines, matched_str)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# scopes.append(Function_scope(child_instructions, name, rtype, args))
|
|
|
|
|
|
|
|
# return scopes
|
|
|
|
|