def __escape_z__(): InvalidTokenBuilder.__escape_z__() WhitespaceTokenBuilder.__escape_z__() NewlineTokenBuilder.__escape_z__() EscapedStringTokenBuilder.__escape_z__() PrefixedStringTokenBuilder.__escape_z__() SuffixedStringTokenBuilder.__escape_z__() IntegerTokenBuilder.__escape_z__() IntegerExponentTokenBuilder.__escape_z__() PrefixedIntegerTokenBuilder.__escape_z__() SuffixedIntegerTokenBuilder.__escape_z__() RealTokenBuilder.__escape_z__() RealExponentTokenBuilder.__escape_z__() SuffixedRealTokenBuilder.__escape_z__() IdentifierTokenBuilder.__escape_z__() PrefixedIdentifierTokenBuilder.__escape_z__() CaseInsensitiveListTokenBuilder.__escape_z__() CaseSensitiveListTokenBuilder.__escape_z__() SingleCharacterTokenBuilder.__escape_z__() SlashSlashCommentTokenBuilder.__escape_z__() SlashStarCommentTokenBuilder.__escape_z__() ClassTypeTokenBuilder.__escape_z__() HexRealExponentTokenBuilder.__escape_z__() NestedCommentTokenBuilder.__escape_z__() return 'Escape ?Z'
def __escape_z__(): InvalidTokenBuilder.__escape_z__() WhitespaceTokenBuilder.__escape_z__() NewlineTokenBuilder.__escape_z__() EscapedStringTokenBuilder.__escape_z__() PrefixedStringTokenBuilder.__escape_z__() IntegerTokenBuilder.__escape_z__() IntegerExponentTokenBuilder.__escape_z__() PrefixedIntegerTokenBuilder.__escape_z__() SuffixedIntegerTokenBuilder.__escape_z__() RealTokenBuilder.__escape_z__() AssemblyCommentTokenBuilder.__escape_z__() return 'Escape ?Z'
def __escape_z__():
InvalidTokenBuilder.__escape_z__()
WhitespaceTokenBuilder.__escape_z__()
NewlineTokenBuilder.__escape_z__()
EscapedStringTokenBuilder.__escape_z__()
PrefixedStringTokenBuilder.__escape_z__()
PrefixedRawStringTokenBuilder.__escape_z__()
IntegerTokenBuilder.__escape_z__()
IntegerExponentTokenBuilder.__escape_z__()
RealTokenBuilder.__escape_z__()
RealExponentTokenBuilder.__escape_z__()
IdentifierTokenBuilder.__escape_z__()
PrefixedIdentifierTokenBuilder.__escape_z__()
CaseInsensitiveListTokenBuilder.__escape_z__()
CaseSensitiveListTokenBuilder.__escape_z__()
SingleCharacterTokenBuilder.__escape_z__()
LeadToEndOfLineTokenBuilder.__escape_z__()
TripleQuoteStringTokenBuilder.__escape_z__()
RawTripleQuoteCommentTokenBuilder.__escape_z__()
return 'Escape ?Z'
def __escape_z__():
InvalidTokenBuilder.__escape_z__()
WhitespaceTokenBuilder.__escape_z__()
NewlineTokenBuilder.__escape_z__()
EscapedStringTokenBuilder.__escape_z__()
PrefixedStringTokenBuilder.__escape_z__()
IntegerTokenBuilder.__escape_z__()
IntegerExponentTokenBuilder.__escape_z__()
RealTokenBuilder.__escape_z__()
RealExponentTokenBuilder.__escape_z__()
IdentifierTokenBuilder.__escape_z__()
CaseInsensitiveListTokenBuilder.__escape_z__()
CaseSensitiveListTokenBuilder.__escape_z__()
BlockTokenBuilder.__escape_z__()
TripleQuoteStringTokenBuilder.__escape_z__()
SlashSlashCommentTokenBuilder.__escape_z__()
TripleSlashCommentTokenBuilder.__escape_z__()
LeadToEndOfLineTokenBuilder.__escape_z__()
NullTokenBuilder.__escape_z__()
ClassTypeTokenBuilder.__escape_z__()
return 'Escape ?Z'
def __escape_z__():
InvalidTokenBuilder.__escape_z__()
WhitespaceTokenBuilder.__escape_z__()
NewlineTokenBuilder.__escape_z__()
StuffedQuoteStringTokenBuilder.__escape_z__()
PrefixedStringTokenBuilder.__escape_z__()
IntegerTokenBuilder.__escape_z__()
IntegerExponentTokenBuilder.__escape_z__()
RealTokenBuilder.__escape_z__()
RealExponentTokenBuilder.__escape_z__()
CaseInsensitiveListTokenBuilder.__escape_z__()
CaseSensitiveListTokenBuilder.__escape_z__()
SingleCharacterTokenBuilder.__escape_z__()
LeadToEndOfLineTokenBuilder.__escape_z__()
BlockTokenBuilder.__escape_z__()
CobolIdentifierTokenBuilder.__escape_z__()
PictureTokenBuilder.__escape_z__()
CRPictureTokenBuilder.__escape_z__()
CobolPreprocessorTokenBuilder.__escape_z__()
AsteriskCommentTokenBuilder.__escape_z__()
return 'Escape ?Z'
def __escape_z__():
InvalidTokenBuilder.__escape_z__()
WhitespaceTokenBuilder.__escape_z__()
NewlineTokenBuilder.__escape_z__()
EscapedStringTokenBuilder.__escape_z__()
PrefixedStringTokenBuilder.__escape_z__()
IntegerTokenBuilder.__escape_z__()
IntegerExponentTokenBuilder.__escape_z__()
PrefixedIntegerTokenBuilder.__escape_z__()
SuffixedIntegerTokenBuilder.__escape_z__()
RealTokenBuilder.__escape_z__()
IdentifierTokenBuilder.__escape_z__()
CaseInsensitiveListTokenBuilder.__escape_z__()
CaseSensitiveListTokenBuilder.__escape_z__()
LeadToEndOfLineTokenBuilder.__escape_z__()
SingleCharacterTokenBuilder.__escape_z__()
LabelTokenBuilder.__escape_z__()
AssemblyCommentTokenBuilder.__escape_z__()
MultilineCommentTokenBuilder.__escape_z__()
HashQuoteCharTokenBuilder.__escape_z__()
return 'Escape ?Z'
def __init__(self, code):
super().__init__()
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder(None)
integer_exponent_tb = IntegerExponentTokenBuilder(None)
real_tb = RealTokenBuilder(False, False, None)
real_exponent_tb = RealExponentTokenBuilder(False, False, 'E', None)
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
directive_tb = DirectiveTokenBuilder()
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 10)
prefixed_string_tb = PrefixedStringTokenBuilder('@', False, quotes)
operand_types.append('string')
class_type_tb = ClassTypeTokenBuilder()
operand_types.append('class')
slash_slash_comment_tb = SlashSlashCommentTokenBuilder()
slash_star_comment_tb = SlashStarCommentTokenBuilder()
directives = [
'#define', '#undef', '#ifdef', '#ifndef', '#if', '#endif', '#else',
'#elif', '#import', '#line', '#include'
]
line_continuation_tb = SingleCharacterTokenBuilder(
'\\', 'line continuation', False)
c_preprocessor_tb = CaseSensitiveListTokenBuilder(
directives, 'preprocessor', False)
c_warning_tb = LeadToEndOfLineTokenBuilder('#warning', True,
'preprocessor')
c_error_tb = LeadToEndOfLineTokenBuilder('#error', True,
'preprocessor')
c_pragma_tb = LeadToEndOfLineTokenBuilder('#pragma', True,
'preprocessor')
terminators_tb = SingleCharacterTokenBuilder(';',
'statement terminator',
False)
known_operators = [
'+', '-', '*', '/', '%', '=', '==', '!=', '>', '>=', '<', '<=',
'+=', '-=', '*=', '/=', '%=', '&=', '|=', '^=', '<<=', '>>=', '!',
'&', '|', '<<', '>>', '~', '.', '->', '++', '--', '&&', '||', '^',
'?', '##'
]
self.unary_operators = [
'+', '-', '*', '!', '&', '^', '~', '++', '--', '##'
]
self.postfix_operators = ['++', '--', '&', '->', '*', '^']
groupers = ['(', ')', ',', '[', ']', '{', '}', ':']
group_starts = ['(', '[', ',', '{']
group_ends = [')', ']', '}']
group_mids = [',', ':']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
keywords = [
'atomic', 'break', 'bycopy', 'byref', 'case', 'continue',
'default', 'do', 'else', 'for', 'goto', 'if', 'IMP', 'in',
'inline', 'inout', 'nonatomic', 'oneway', 'out', 'Protocol',
'restrict', 'retain', 'return', 'SEL', 'sizeof', 'switch',
'typedef', 'while', '@interface', '@end', '@implementation',
'@protocol', '@class', '@public', '@protected', '@private',
'@property', '@try', '@throw', '@catch()', '@finally',
'@synthesize', '@dynamic', '@selector'
]
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'auto', 'char', 'const', 'double', 'enum', 'extern', 'float', 'id',
'int', 'long', 'register', 'short', 'signed', 'static', 'struct',
'union', 'unsigned', 'void', 'volatile', '_Bool', '_Complex',
'_Imaginary', 'BOOL', 'Class'
]
types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
values = ['self', 'super', 'nil', 'YES', 'NO', 'NULL', '...']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, line_continuation_tb, terminators_tb,
integer_tb, integer_exponent_tb, real_tb, real_exponent_tb,
keyword_tb, types_tb, values_tb, groupers_tb, known_operator_tb,
directive_tb, identifier_tb, class_type_tb, string_tb,
prefixed_string_tb, slash_slash_comment_tb, slash_star_comment_tb,
c_preprocessor_tb, c_warning_tb, c_error_tb, c_pragma_tb,
self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid')
# tokens = Examiner.combine_identifier_colon(tokens, ['statement terminator', 'newline'], ['{'], ['whitespace', 'comment', 'line description'])
self.tokens = tokens
self.convert_identifiers_to_labels()
self.convert_values_to_operators()
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_all_lines(tokens)
self.calc_token_confidence()
self.calc_token_2_confidence(['*', ';'])
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends,
allow_pairs)
self.calc_operator_4_confidence(tokens, num_operators,
group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'string', 'symbol']
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_paired_blockers_confidence(['{'], ['}'])
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, block_comment_limit):
super().__init__()
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
line_continuation_tb = SingleCharacterTokenBuilder(
'\\', 'line continuation', False)
integer_tb = IntegerTokenBuilder('_')
integer_exponent_tb = IntegerExponentTokenBuilder('_')
real_tb = RealTokenBuilder(False, True, '_')
real_exponent_tb = RealExponentTokenBuilder(False, True, 'E', '_')
octal_integer_tb = PrefixedIntegerTokenBuilder('0o', True, '01234567_')
hex_integer_tb = PrefixedIntegerTokenBuilder(
'0x', True, '0123456789ABCDEFabcdef_')
binary_integer_tb = PrefixedIntegerTokenBuilder('0b', True, '01_')
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
lifetime_tb = IdentifierTokenBuilder("'", extras)
attribute_tb = RustAttributeTokenBuilder()
quotes = ['"']
string_tb = EscapedStringTokenBuilder(quotes, 10)
bstring_tb = PrefixedStringTokenBuilder('b', True, quotes)
rstring_tb = RustRawStringTokenBuilder()
operand_types.append('string')
char_tb = SingleCharStringTokenBuilder()
class_type_tb = ClassTypeTokenBuilder()
operand_types.append('class')
slash_slash_comment_tb = SlashSlashCommentTokenBuilder()
slash_star_comment_tb = NestedCommentTokenBuilder(
'/*', '*/', block_comment_limit)
terminators_tb = SingleCharacterTokenBuilder(';',
'statement terminator',
False)
known_operators = [
'+', '-', '*', '/', '%', '^', '!', '&', '|', '&&', '||', '<<',
'>>', '+=', '-=', '*=', '/=', '%=', '^=', '&=', '|-', '<<=', '>>=',
'=', '==', '!=', '>', '<', '>=', '<=', '@', '.', '..', '...', '->',
'#', '$', '?', 'in', '&mut'
]
self.unary_operators = ['+', '-', '*', '!', '&', '&mut']
self.postfix_operators = []
groupers = ['(', ')', ',', '[', ']', '{', '}', ':', '::', '=>']
group_starts = ['(', '[', ',', '{']
group_mids = [',', ':', '::', '=>']
group_ends = [')', ']', '}', ')|']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
keywords = [
'as', 'break', 'const', 'continue', 'crate'
'else', 'enum', 'extern', 'fn', 'for', 'if', 'impl', 'let', 'loop',
'match', 'mod', 'move', 'mut', 'pub', 'ref', 'return', 'static',
'struct', 'trait', 'type', 'unsafe', 'use', 'where', 'while'
]
keywords_2018 = ['dyn', 'union', 'static']
keywords_future = [
'abstract', 'become', 'box', 'do', 'final', 'macro', 'override',
'priv', 'typeof', 'unsized', 'virtual', 'yield', 'async', 'await',
'try'
]
keywords += keywords_2018
keywords += keywords_future
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'Self', 'u8', 'i8', 'u16', 'i16', 'u32', 'i32', 'u64', 'i64',
'u128', 'i128', 'usize', 'isize', 'f32', 'f64'
]
types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
values = ['self', 'true', 'false', 'super', '_']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, line_continuation_tb, terminators_tb,
integer_tb, integer_exponent_tb, octal_integer_tb, hex_integer_tb,
binary_integer_tb, real_tb, real_exponent_tb, keyword_tb, types_tb,
values_tb, groupers_tb, known_operator_tb, identifier_tb, char_tb,
lifetime_tb, class_type_tb, attribute_tb, string_tb, bstring_tb,
rstring_tb, slash_slash_comment_tb, slash_star_comment_tb,
self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid')
self.tokens = self.combine_numbers_and_adjacent_types(tokens)
self.convert_operators_to_identifiers()
self.convert_bars_to_groups()
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_all_lines(tokens)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends,
allow_pairs)
self.calc_operator_4_confidence(tokens, num_operators,
group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'symbol']
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_paired_blockers_confidence(['{'], ['}'])
self.calc_line_format_confidence()
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, tab_size):
super().__init__()
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder("'")
integer_exponent_tb = IntegerExponentTokenBuilder("'")
real_tb = RealTokenBuilder(True, True, None)
hex_integer_1_tb = PrefixedIntegerTokenBuilder(
'$', False, '0123456789abcdefABCDEF')
hex_integer_2_tb = PrefixedIntegerTokenBuilder(
'#$', False, '0123456789abcdefABCDEF')
hex_integer_3_tb = PrefixedIntegerTokenBuilder(
'&', False, '0123456789abcdefABCDEF')
hex_integer_h_tb = SuffixedIntegerTokenBuilder(['h'], False,
'abcdefABCDEF')
binary_integer_tb = PrefixedIntegerTokenBuilder('0b', False, '01')
suffixed_integer_tb = SuffixedIntegerTokenBuilder(
['Q', 'A', 'O', 'D', 'B'], False, None)
operand_types.append('number')
leads = '_$#.'
extras = '_$#.'
identifier_tb = IbmAsmIdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 0)
hex_string_tb = PrefixedStringTokenBuilder('X', False, quotes)
char_string_tb = PrefixedStringTokenBuilder('C', False, quotes)
operand_types.append('string')
known_operators = ['+', '-', '*', '/', '=', '&', '#', '?']
self.unary_operators = ['+', '-', '=', '&', '#', '?']
self.postfix_operators = []
groupers = ['(', ')', ',', '[', ']', '{', '}', ':', '<', '>']
group_starts = ['(', '[', ',', '{', '<']
group_ends = [')', ']', '}', '>']
group_mids = [',']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
# keywords = []
# keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
# types = []
# types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
values = ['*']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
comment_tb = AssemblyCommentTokenBuilder(';*')
title_directive_tb = LeadToEndOfLineTokenBuilder(
'TITLE', False, 'directive')
subtitle_directive_tb = LeadToEndOfLineTokenBuilder(
'SUBTTL', False, 'directive')
include_directive_tb = LeadToEndOfLineTokenBuilder(
'INCLUDE', False, 'directive')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, integer_tb, integer_exponent_tb,
hex_integer_1_tb, hex_integer_2_tb, hex_integer_3_tb,
hex_integer_h_tb, binary_integer_tb, suffixed_integer_tb, real_tb,
values_tb, groupers_tb, known_operator_tb, title_directive_tb,
subtitle_directive_tb, include_directive_tb, identifier_tb,
string_tb, hex_string_tb, char_string_tb, comment_tb,
self.unknown_operator_tb, invalid_token_builder
]
opcode_tokenbuilders = [identifier_tb, invalid_token_builder]
args_tokenbuilders = [
integer_tb, integer_exponent_tb, hex_integer_1_tb,
hex_integer_2_tb, hex_integer_3_tb, hex_integer_h_tb,
binary_integer_tb, suffixed_integer_tb, real_tb, values_tb,
groupers_tb, known_operator_tb, identifier_tb, string_tb,
hex_string_tb, char_string_tb, comment_tb,
self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
opcode_tokenizer = Tokenizer(opcode_tokenbuilders)
args_tokenizer = Tokenizer(args_tokenbuilders)
# tokenize as free-format
tokens_free = tokenizer.tokenize(code)
tokens_free = Examiner.combine_adjacent_identical_tokens(
tokens_free, 'invalid operator')
tokens_free = Examiner.combine_adjacent_identical_tokens(
tokens_free, 'invalid')
tokens_free = Examiner.convert_values_to_operators(
tokens_free, known_operators)
self.tokens = tokens_free
self.convert_asm_identifiers_to_labels()
self.calc_statistics()
statistics_free = self.statistics
self.statistics = {}
self.calc_confidences(operand_types, group_starts, group_mids,
group_ends, None)
self.calc_line_length_confidence(code, self.max_expected_line)
confidences_free = self.confidences
self.confidences = {}
errors_free = self.errors
self.errors = []
# tokenize as space-format
opcode_extras = '.&=,()+-*/'
label_leads = '.&$@'
label_mids = '.&$#@'
label_ends = ':,'
comment_leads = '*;!'
line_comment_leads = ''
use_line_id = False
tokens_space, indents = Tokenizer.tokenize_asm_code(
code, tab_size, opcode_tokenizer, opcode_extras, args_tokenizer,
label_leads, label_mids, label_ends, comment_leads,
line_comment_leads, use_line_id)
tokens_space = Examiner.combine_adjacent_identical_tokens(
tokens_space, 'invalid operator')
tokens_space = Examiner.combine_adjacent_identical_tokens(
tokens_space, 'invalid')
tokens_space = Examiner.combine_identifier_colon(
tokens_space, ['newline'], [], [])
tokens_space = Tokenizer.combine_number_and_adjacent_identifier(
tokens_space)
tokens_space = Examiner.convert_values_to_operators(
tokens_space, known_operators)
self.tokens = tokens_space
self.convert_asm_identifiers_to_labels()
self.calc_statistics()
statistics_space = self.statistics
self.statistics = {}
self.calc_confidences(operand_types, group_starts, group_mids,
group_ends, indents)
self.calc_line_length_confidence(code, self.max_expected_line)
confidences_space = self.confidences
self.confidences = {}
errors_space = self.errors
self.errors = []
# select the better of free-format and spaced-format
confidence_free = 1.0
for key in confidences_free:
factor = confidences_free[key]
confidence_free *= factor
confidence_space = 1.0
for key in confidences_space:
factor = confidences_space[key]
confidence_space *= factor
if confidence_space > confidence_free:
self.tokens = tokens_space
self.statistics = statistics_space
self.confidences = confidences_space
self.errors = errors_space
else:
self.tokens = tokens_free
self.statistics = statistics_free
self.confidences = confidences_free
self.errors = errors_free
def __init__(self, code, tab_size, processor):
super().__init__()
self.newlines_important = 'always'
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder("'")
integer_exponent_tb = IntegerExponentTokenBuilder("'")
real_tb = RealTokenBuilder(True, True, None)
hex_integer_1_tb = PrefixedIntegerTokenBuilder('$', False, '0123456789abcdefABCDEF')
hex_integer_2_tb = PrefixedIntegerTokenBuilder('#$', False, '0123456789abcdefABCDEF')
hex_integer_3_tb = PrefixedIntegerTokenBuilder('&', False, '0123456789abcdefABCDEF')
hex_integer_h_tb = SuffixedIntegerTokenBuilder(['h'], False, 'abcdefABCDEF')
binary_integer_tb = PrefixedIntegerTokenBuilder('0b', False, '01')
suffixed_integer_tb = SuffixedIntegerTokenBuilder(['Q', 'A', 'O', 'D', 'B'], False, None)
operand_types.append('number')
leads = '$#.@&'
extras = '$#.@&'
identifier_tb = IbmAsmIdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 0)
hex_string_tb = PrefixedStringTokenBuilder('X', False, quotes)
char_string_tb = PrefixedStringTokenBuilder('C', False, quotes)
operand_types.append('string')
known_operators = [
'+', '-', '*', '/', '=', '&', '#', '?', "'"
]
self.unary_operators = [
'+', '-', '=', '&', '#', '?', "'"
]
self.postfix_operators = []
groupers = ['(', ')', ',', '[', ']', '{', '}', ':', '<', '>']
group_starts = ['(', '[', ',', '{', '<']
group_ends = [')', ']', '}', '>']
group_mids = [',']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(known_operators, 'operator', False)
preprocessors = [
'MACRO', 'MEND'
]
preprocessor_tb = CaseInsensitiveListTokenBuilder(preprocessors, 'preprocesssor', False)
directives = [
'CSECT',
'DC', 'DROP', 'DS',
'EJECT', 'END', 'ENTRY', 'EQU', 'EXTRN',
'FREEMAIN',
'GETMAIN', 'GLOBAL',
'NAM', 'NAME',
'ORG',
'PAGE', 'PARAM', 'PROC', 'PUBLIC',
'RETURN',
'STIMER',
'TITLE', 'SUBTTL',
'USING'
]
directive_tb = CaseInsensitiveListTokenBuilder(directives, 'directive', False)
keywords = []
keywords_360 = [
'A', 'ABEND', 'AD', 'ADR', 'AE', 'AER', 'AH', 'AL', 'ALR', 'AP', 'AR',
'AU', 'AUR', 'AW', 'AWR', 'AXR',
'B', 'BAL', 'BALR', 'BAS', 'BASR', 'BC', 'BCR', 'BCT', 'BCTR',
'BE', 'BH', 'BL', 'BM', 'BNE', 'BNH', 'BNL', 'BNM', 'BNP', 'BNO', 'BNZ',
'BO', 'BP', 'BR', 'BXH', 'BXLE', 'BZ',
'C', 'CD', 'CDR', 'CE', 'CER', 'CH', 'CL', 'CLC', 'CLI', 'CLR', 'CP',
'CR', 'CVB', 'CVD',
'D', 'DD', 'DDR', 'DE', 'DER', 'DIAGNOSE', 'DP', 'DR',
'ED', 'EDMK', 'EX',
'HDR', 'HER', 'HIO',
'IC', 'ISK',
'L',
'LA', 'LCR', 'LCDR', 'LCER', 'LD', 'LDR',
'LE', 'LER', 'LH', 'LM',
'LNDR', 'LNER', 'LNR',
'LPDR', 'LPER', 'LPR', 'LPSW', 'LR', 'LRDR', 'LRER',
'LTDR', 'LTER', 'LTR',
'M', 'MD', 'MDR', 'ME', 'MER', 'MH', 'MP', 'MR', 'MVC', 'MVI',
'MVN', 'MVO', 'MVZ', 'MXD', 'MXDR', 'MXR',
'N', 'NC', 'NI', 'NOP', 'NOPR', 'NR',
'O', 'OC', 'OI', 'OR',
'PACK',
'RDD',
'S', 'SD', 'SDR', 'SE', 'SER', 'SH', 'SIO',
'SL', 'SLA', 'SLDA', 'SLDL', 'SLL', 'SLR',
'SP', 'SPM',
'SR', 'SRA', 'SRDL', 'SRP',
'SSK', 'SSM', 'SRDA', 'SRL',
'ST', 'STC', 'STD', 'STE', 'STH', 'STM', 'SU', 'SUR', 'SVC',
'SW', 'SWR', 'SXR',
'TCH', 'TIO', 'TM', 'TR', 'TRT', 'TS',
'UNPK', 'UNPKU',
'WRD',
'X', 'XC', 'XI', 'XR',
'ZAP'
]
keywords_370 = [
'BRXH', 'BRXLE',
'CLCL',
'HDV',
'LAM', 'LEDR',
'MS', 'MVCL',
'RIO',
'SIOF', 'STAM',
'VA', 'VACD', 'VACDR', 'VACE', 'VACER',
'VAD', 'VADQ', 'VADR', 'VADS',
'VAE', 'VAEQ', 'VAER', 'VAES',
'VAQ', 'VAR', 'VAS',
'VC', 'VCD', 'VCDQ', 'VCDR', 'VCDS',
'VCE', 'VCEQ', 'VCER', 'VCES',
'VCQ', 'VCR', 'VCS',
'VDD', 'VDDQ', 'VDDR', 'VDDS',
'VDE', 'VDEQ', 'VDER', 'VDES',
'VL', 'VLCDR', 'VLCER', 'VLCR',
'VLD', 'VLDQ', 'VLDR', 'VLEQ', 'VLH', 'VLINT',
'VLM', 'VLMD', 'VLMDQ', 'VLMDR', 'VLMEQ', 'VLMQ', 'VLMR',
'VLNDR', 'VLNER', 'VLNR', 'VLPDR', 'VLPER', 'VLPR',
'VLQ', 'VLR', 'VLY', 'VLYD', 'VLZDR', 'VLZR',
'VM', 'VMAD', 'VMADQ', 'VMADS', 'VMAE', 'VMAEQ', 'VMAES',
'VMCD', 'VMCE', 'VMCER',
'VMD', 'VMDQ', 'VMDR', 'VMDS',
'VME', 'VMEQ', 'VMER', 'VMES',
'VMQ', 'VMR', 'VMS', 'VMSD', 'VMSDQ', 'VMSDS', 'VMSE', 'VMSEQ', 'VMSES',
'VN', 'VNQ', 'VNR', 'VNS',
'VO', 'VOQ', 'VOR', 'VOS',
'VS', 'VSD', 'VSDQ', 'VSDR', 'VSDS',
'VSE', 'VSEQ', 'VSER', 'VSES',
'VSQD', 'VSQDR', 'VSQE', 'VSQER',
'VSQ', 'VSR', 'VSS', 'VST', 'VSTD', 'VSTE', 'VSTH', 'VSTKD', 'VSTMD',
'VTAD', 'VTAE', 'VTSD', 'VTSE',
'VX', 'VXQ', 'VXR', 'VXS',
'VMXSE', 'VMNSE', 'VMXAE', 'VLELE', 'VSELE', 'VMXDS', 'VMNSD', 'VMXAD',
'VLELD', 'VXELD', 'VSPSD', 'VAPSD', 'VTVM', 'VCVM', 'VCZVM', 'VCOVM',
'VXVC', 'VXVMM', 'VRRS', 'VRSVC', 'VRSV', 'VLVM', 'VLCVM', 'VSTVM', 'VNVM',
'VOVM', 'VXVM', ' VSRSV', 'VMRSV', 'VSRRS', 'VLVCA', 'VRCL', 'VSVMM',
'VLVXA', 'VSVTP', 'VACSV', 'VACRS',
'STNSM', 'SOTSM', 'SIOP', 'MC', 'LRA', 'CONCS', 'DISCS', 'STIDP', 'SCK',
'SPT', 'STPT', 'SPKA', 'IPK', 'PTLB', 'SPX', 'STPX', 'STAP', 'RRB',
'PC', 'SAC', 'IPTE',
'IVSK', 'IAC', 'SSAR', 'EPAR', 'ESAR', 'PT', 'ISKE', 'RRBE', 'SSKE', 'TB',
'STCTL', 'LCTL', 'CS', 'CDS', 'CLM', 'STCM', 'ICM',
'MVCK', 'MVCP', 'MVCS', 'VLI', 'VSTI', 'VLID', 'VSTID', 'VSRL',
'VSLL', 'VLBIX', 'LASP', 'TPROT', 'STRAG',
'MVCSK', 'MVCDK', 'DPFET', 'MVHHI', 'MVGHI', 'MVHI', 'CHHSI', 'CLHHSI',
'CGHSI', 'CLGHSI', 'CHSI', 'CLFHSI', 'TBEGIN', 'TBEGINC', 'MVCIN', 'UNPKA'
]
keywords_390 = [
'BASSM', 'BSG', 'BSM',
'CLRCH', 'CMPS', 'CLRIO', 'CMSG',
'LAE', 'LXDR',
'MDE',
'PFPO', 'PR', 'PTFF',
'SAM24', 'SAM31', 'SCKPF',
'TAM', 'TMPS', 'TMSG', 'TRACE', 'TRAP2',
'TMH',' TMLH', 'TML', 'TMLL', 'TMHH', 'TMHL',
'BRC', 'BRAS', 'BRCT', 'BRCTG',
'LHI', 'LGHI',
'AHI', 'AGHI',
'MHI', 'MGHI',
'CHI', 'CGHI',
'MVCLE', 'CLCLE',
'UPT',
'SIE', 'PCF', 'CFC', 'DEP', 'DCTP', 'MAD', 'MUN', 'STCAP', 'SERVC',
'IPM', 'DXR', 'PGIN', 'PGOUT', 'CSCH', 'HSCH', 'MSCH', 'SSCH', 'STSCH', 'TSCH',
'TPI', 'SAL', 'RSCH', 'STCRW', 'STCPS', 'RCHP', 'SCHM', 'STZP', 'SZP',
'TPZI', 'BAKR', 'CKSM', 'MADS', 'SQDR', 'STURA', 'MSTA', 'PALB', 'EREG',
'ESTA', 'LURA', 'TAR', 'SQDR', 'SAR', 'EAR', 'CSP', 'MSR', 'MVPG', 'MVST',
'CUSE', 'BSG', 'CLST', 'SRST', 'XSCH', 'RP', 'STCKE', 'SACF', 'STSI',
'SRNM', 'STFPC', 'LFPC', 'TRE', 'CUUTF', 'CUTFU', 'STFL', 'LPSWE',
'TRAP4', 'LPEBR', 'LNEBR', 'LTEBR', 'LCEBR', 'LDEBR', 'LXDBR', 'LDEBR',
'MXDBR', 'KEBR', 'CEBR', 'AEBR', 'SEBR', 'MDEBR', 'DEBR', 'MAEBR',
'MSEBR', 'LPDBR', 'LCDBR', 'SQEBR', 'MEEBR', 'KDBR', 'CDBR', 'ADBR',
'MDBR', 'DDBR', 'SDBR', 'LDER', 'LXDR', 'MAER', 'MSER', 'SQXR', 'MEER',
'MADR', 'MSDR', 'LPXBR', 'LNXBR', 'LTXBR', 'LCXBR', 'LCXBR', 'LEDBR',
'LDXBR', 'LEXBR', 'FIXBR', 'KXBR', 'CXBR', 'AXBR', 'SXBR', 'MXBR', 'DXBR',
'TBEDR', 'TBDR', 'DIEBR', 'FIEBR', 'THDER', 'DIDBR', 'FIDBR', 'LPXR',
'LNXR', 'LTXR', 'LCXR', 'LXR', 'LEXR', 'FIXR', 'CXR', 'LZER', 'LZDR',
'LZXR', 'FIER', 'FIDR', 'SFPC', 'EFPC', 'CEFBR', 'CDFBR', 'CXFBR', 'CEGBR',
'CEFR', 'CDFR', 'CXFR', 'CFDR', 'CFXR', 'CEGR', 'CDGR', 'CXGR', 'CGER', 'CGDR', 'CGXR',
'CDGBR', 'CXGBR', 'CGDBR', 'CGEBR', 'CGXBR',
'LMC', 'LPGR', 'LNGR', 'LTGR', 'LCGR', 'LGC', 'LURAG', 'AGR', 'SGR',
'ALGR', 'SLGR', 'MSGR', 'DSGR', 'EREGG', 'LRVGR', 'LPGFR', 'LNGFR',
'LTGFR', 'LCGFR', 'LGFR', 'LLGFR', 'LLGTR', 'AGFR', 'SGFR', 'ALGFR',
'SLGFR', 'MSGFR', 'DSGFR', 'LRVR', 'CGR', 'CLGR', 'STURG', 'CGFR',
'CLGFR', 'BCTGR', 'NGR', 'OGR', 'XGR', 'MLGR', 'DLGR', 'ALCGR', 'SLBGR',
'EPSW', 'TRTT', 'TRTO', 'TROT', 'TROO', 'MLR', 'DLR', 'ALCR', 'SLBR', 'ESEA',
'LARL', 'LGFI', 'BRCL', 'BRASL', 'XIHF', 'XILF', 'IIHF', 'IILF',
'NIHF', 'NILF', 'OIHF', 'OILF', 'LLIHF', 'LLILF', 'LLHRL', 'LGHRL',
'LHRL', 'AGFI', 'AFI', 'ALGFI', 'ALFI', 'CGFI', 'CFI', 'LLGFRL', 'STRL',
'EXRL', 'PFDRL', 'CGHRL','CHRL', 'CLGHRL', 'CLHRL', 'CGRL', 'CLGRL',
'CRL', 'CLGFRL', 'CLRL', 'MVCOS', 'ECTG', 'CSST', 'PKU',
'LRAG', 'LG', 'AG', 'SG', 'ALG', 'SLG', 'MSG', 'DSG', 'CVBG',
'LRVG', 'LGF', 'LGH', 'LLGF', 'LLGT', 'AGF', 'SGF', 'ALGF', 'SLGF',
'MSGF', 'DSGF', 'LRV', 'LRVH', 'CG', 'CLG', 'STG', 'CVDG', 'STRVG',
'CGF', 'CLGF', 'STRV', 'STRVH', 'BCTG', 'NG', 'OG', 'XG', 'MLG',
'DLG', 'ALCG', 'SLBG', 'STPQ', 'LPQ', 'LLGC', 'LLGH', 'ML', 'DL',
'ALC', 'SLB', 'PKA',
'DIL', 'BDIL', 'ANUM', 'COMP', 'MCPU', 'MIO', 'BIFLAG', 'MULDIV',
'LMG', 'SRAG', 'SLAG', 'SRLG', 'SLLG', 'TRACG', 'RLLG', 'RLL',
'CLMH', 'CLMY', 'CLT', 'CLTH', 'CLTL', 'CLTNE', 'CLTE', 'CLTNL',
'CLTNH', 'STMG', 'STCTG', 'STMH', 'STCMH', 'LCTLG', 'CSG', 'CDSG',
'BXHG', 'BXLEG', 'ICMH', 'MVCLU', 'CLCLU', 'LMH', 'LMY', 'TP',
'SRAK', 'SLAK', 'SRLK', 'SRLK', 'LOCG', 'BRXHG', 'BRXLG', 'LDEB',
'LXDB', 'LXEB', 'MXDB', 'KEB', 'CEB', 'AEB', 'SEB', 'MDEB', 'DEB',
'MAEB', 'MSEB', 'TCEB', 'TCDB', 'TCXB', 'SQEB', 'SQDB', 'MEEB',
'KDB', 'CDB', 'ADB', 'SDB', 'MDB', 'DDB', 'MADB', 'MSDB', 'LDE',
'LXD', 'LXE', 'SQE', 'SQD', 'MEE', 'PLO', 'LMD'
]
keywords_z = [
'IIHH', 'IIHL', 'IILH', 'IILL',
'LLIHH', 'LLIHL', 'LLILH', 'LLILL',
'NIHH', 'NIHL', 'NILH', 'NILL',
'OIHH', 'OIHL', 'OILH', 'OILL',
'SAM64'
]
if processor in ['360', '370', '390', 'system-z']:
keywords += keywords_360
if processor in ['370', '390', 'system-z']:
keywords += keywords_370
if processor in ['390', 'system-z']:
keywords += keywords_390
if processor in ['system-z']:
keywords += keywords_z
opcode_tb = CaseInsensitiveListTokenBuilder(keywords, 'keyword', False)
registers = [
'R0', 'R1', 'R2', 'R3', 'R4', 'R5', 'R6', 'R7', 'R8', 'R9', 'R10',
'R11', 'R12', 'R13', 'R14', 'R15',
'FP0', 'FP2', 'FP4', 'FP6'
]
register_tb = CaseInsensitiveListTokenBuilder(registers, 'register', True)
values = ['*']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
comment_tb = LeadToEndOfLineTokenBuilder('!', False, 'comment')
line_comment_tb = AssemblyCommentTokenBuilder('*')
include_directive_tb = LeadToEndOfLineTokenBuilder('INCLUDE', False, 'directive')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb,
whitespace_tb,
integer_tb,
integer_exponent_tb,
hex_integer_1_tb,
hex_integer_2_tb,
hex_integer_3_tb,
hex_integer_h_tb,
binary_integer_tb,
suffixed_integer_tb,
real_tb,
values_tb,
groupers_tb,
known_operator_tb,
register_tb,
opcode_tb,
directive_tb,
include_directive_tb,
preprocessor_tb,
identifier_tb,
string_tb,
hex_string_tb,
char_string_tb,
comment_tb,
line_comment_tb,
self.unknown_operator_tb,
invalid_token_builder
]
opcode_tokenbuilders = [
whitespace_tb,
opcode_tb,
directive_tb,
include_directive_tb,
preprocessor_tb,
identifier_tb,
self.unknown_operator_tb,
invalid_token_builder
]
args_tokenbuilders = [
whitespace_tb,
integer_tb,
integer_exponent_tb,
hex_integer_1_tb,
hex_integer_2_tb,
hex_integer_3_tb,
hex_integer_h_tb,
binary_integer_tb,
suffixed_integer_tb,
real_tb,
values_tb,
groupers_tb,
known_operator_tb,
register_tb,
identifier_tb,
string_tb,
hex_string_tb,
char_string_tb,
comment_tb,
line_comment_tb,
self.unknown_operator_tb,
invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
opcode_tokenizer = Tokenizer(opcode_tokenbuilders)
args_tokenizer = Tokenizer(args_tokenbuilders)
# tokenize as free-format
tokens_free = tokenizer.tokenize(code)
tokens_free = Examiner.combine_adjacent_identical_tokens(tokens_free, 'invalid operator')
tokens_free = Examiner.combine_adjacent_identical_tokens(tokens_free, 'invalid')
tokens_free = AssemblyIBMExaminer.convert_keywords_to_identifiers(tokens_free)
tokens_free = Examiner.convert_values_to_operators(tokens_free, known_operators)
self.tokens = tokens_free
self.convert_asm_identifiers_to_labels()
self.convert_asm_keywords_to_identifiers()
self.calc_statistics()
statistics1 = self.statistics
self.statistics = {}
self.calc_confidences(operand_types, group_starts, group_mids, group_ends, None)
self.calc_line_length_confidence(code, self.max_expected_line)
confidences_free = self.confidences
self.confidences = {}
errors_free = self.errors
self.errors = []
# tokenize as space-format
opcode_extras = '.&=,()+-*/'
label_leads = '.&$@'
label_mids = '.&$#@'
label_ends = ':,'
comment_leads = '!'
line_comment_leads = '*'
use_line_id = True
tokens_space, indents = Tokenizer.tokenize_asm_code(code, tab_size, opcode_tokenizer, opcode_extras, args_tokenizer, label_leads, label_mids, label_ends, comment_leads, line_comment_leads, use_line_id)
tokens_space = Examiner.combine_adjacent_identical_tokens(tokens_space, 'invalid operator')
tokens_space = Examiner.combine_adjacent_identical_tokens(tokens_space, 'invalid')
tokens_space = Examiner.combine_identifier_colon(tokens_space, ['newline'], [], [])
tokens_space = Tokenizer.combine_number_and_adjacent_identifier(tokens_space)
tokens_space = AssemblyIBMExaminer.convert_opcodes_to_keywords(tokens_space, keywords)
tokens_space = AssemblyIBMExaminer.convert_keywords_to_identifiers(tokens_space)
tokens_space = Examiner.convert_values_to_operators(tokens_space, known_operators)
self.tokens = tokens_space
self.convert_asm_identifiers_to_labels()
self.convert_asm_keywords_to_identifiers()
self.calc_statistics()
statistics2 = self.statistics
self.statistics = {}
self.calc_confidences(operand_types, group_starts, group_mids, group_ends, indents)
self.calc_line_length_confidence(code, self.max_expected_line)
confidences_space = self.confidences
self.confidences = {}
errors_space = self.errors
self.errors = []
# select the better of free-format and spaced-format
confidence_free = 1.0
for key in confidences_free:
factor = confidences_free[key]
confidence_free *= factor
confidence_space = 1.0
for key in confidences_space:
factor = confidences_space[key]
confidence_space *= factor
if confidence_space > confidence_free:
self.tokens = tokens_space
self.statistics = statistics2
self.confidences = confidences_space
self.errors = errors_space
else:
self.tokens = tokens_free
self.statistics = statistics1
self.confidences = confidences_free
self.errors = errors_free
def __init__(self, code):
super().__init__()
self.newlines_important = 'always'
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
stmt_separator_tb = SingleCharacterTokenBuilder(
';', 'statement separator', False)
integer_tb = IntegerTokenBuilder('_')
integer_exponent_tb = IntegerExponentTokenBuilder('_')
real_tb = RealTokenBuilder(False, False, '_')
real_exponent_tb = RealExponentTokenBuilder(False, False, 'E', '_')
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
decorator_tb = PrefixedIdentifierTokenBuilder('@', 'decorator', False)
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 0)
raw_string_tb = PrefixedRawStringTokenBuilder('r', True, quotes)
byte_string_tb = PrefixedStringTokenBuilder('b', True, quotes)
unicode_string_tb = PrefixedStringTokenBuilder('u', True, quotes)
fast_string_tb = PrefixedStringTokenBuilder('f', True, quotes)
operand_types.append('string')
triple_quote_comment_tb = TripleQuoteStringTokenBuilder(quotes)
raw_triple_quote_comment_tb = RawTripleQuoteCommentTokenBuilder()
hash_comment_tb = LeadToEndOfLineTokenBuilder('#', True, 'comment')
known_operators = [
'+', '-', '*', '/', '%', '@', '=', ':=', '==', '>', '>=', '<',
'<=', '+=', '-=', '*=', '/=', '%=', '&=', '|=', '^=', '<<=', '>>=',
'&', '|', '~', '<<', '>>', '**', '.', ':', '++', '--', 'and', 'or',
'in', 'is', 'not'
]
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
self.unary_operators = ['+', '-', 'not', '~', '++', '--', '.']
self.postfix_operators = ['++', '--', ':']
self.adjective_operators = ['not']
self.keyword_postfix = [':']
groupers = ['(', ')', ',', '[', ']', '{', '}']
group_starts = ['(', '[', ',', '{']
group_mids = [',']
group_ends = [')', ']', '}']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
continuation_chars = ['\\']
line_continuation_tb = CaseInsensitiveListTokenBuilder(
continuation_chars, 'line continuation', False)
keywords = [
'as', 'assert', 'break', 'case', 'class', 'continue', 'def', 'del',
'elif', 'else', 'except', 'finally', 'for', 'from', 'global', 'if',
'import', 'lambda', 'match', 'nonlocal', 'pass', 'print', 'raise',
'return', 'try', 'while', 'while', 'with', 'yield'
]
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
values = ['False', 'None', 'True']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, line_continuation_tb, stmt_separator_tb,
integer_tb, integer_exponent_tb, real_tb, real_exponent_tb,
keyword_tb, values_tb, known_operator_tb, groupers_tb,
identifier_tb, decorator_tb, string_tb, raw_string_tb,
byte_string_tb, unicode_string_tb, fast_string_tb, hash_comment_tb,
triple_quote_comment_tb, raw_triple_quote_comment_tb,
self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
self.tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid')
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_parens_continued_lines(tokens)
tokens = Examiner.join_operator_continued_lines(
tokens, self.postfix_operators)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = [['not', 'in']]
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends,
allow_pairs)
self.calc_operator_4_confidence(tokens, num_operators,
group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = [
'number', 'string', 'identifier', 'variable', 'symbol'
]
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_line_format_confidence()
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, variant):
super().__init__()
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder(None)
integer_exponent_tb = IntegerExponentTokenBuilder(None)
real_tb = RealTokenBuilder(True, True, None)
real_exponent_tb = RealExponentTokenBuilder(True, True, 'E', None)
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
class_type_tb = ClassTypeTokenBuilder()
operand_types.append('class')
quotes = ['"']
string_tb = EscapedStringTokenBuilder(quotes, 0)
triple_quote_string_tb = TripleQuoteStringTokenBuilder(quotes)
prefixed_string_tb = PrefixedStringTokenBuilder('@', False, quotes)
char_tb = FsharpCharTokenBuilder(["'", "’"])
operand_types.append('string')
slash_slash_comment_tb = NullTokenBuilder()
parens_star_comment_tb = BlockTokenBuilder('(*', '*)', 'comment')
triple_slash_comment_tb = NullTokenBuilder()
if variant in ['fsharp']:
slash_slash_comment_tb = SlashSlashCommentTokenBuilder()
triple_slash_comment_tb = TripleSlashCommentTokenBuilder()
directives = [
'#if', '#else', '#elif', '#endif', '#define', '#undef', '#line',
'#region', '#endregion', '#pragma'
]
preprocessor_tb = CaseSensitiveListTokenBuilder(
directives, 'preprocessor', False)
c_warning_tb = LeadToEndOfLineTokenBuilder('#warning', True,
'preprocessor')
c_error_tb = LeadToEndOfLineTokenBuilder('#error', True,
'preprocessor')
known_operators = [
'and', 'as', 'in', 'mod', 'not', 'of', 'or', 'when', '::', '+',
'-', '*', '/', '+.', '-.', '*.', '/.', '=', "'", '->', '>', '<',
'>=', '<=', '==', '^', '||', '.', '#'
]
known_operators_fsharp = [
'new', '!', '!=', '%', '%%', '%?', '&', '&&', '&&&', '(|', '|)',
'*?', '**', '+?', '-?', '->', '..', '.. ..', '/?', ':', ':=', ':/',
'<<', '<<<', '<-', '<>', '<>?', '<=?', '<|', '<||', '<|||', '<@',
'@>', '<@@', '@@>', '=?', '==', '>?', '>>', '>>>', '>=?', '?',
'|||', '^^^', '?>=', '?>', '?<=', '?<', '?=', '?<>', '?+', '?-',
'?*', '?/', '>=?', '>?', '<=?', '<?', '=?', '<>?', '+?', '-?',
'*?', '/?', '?>=?', '?>?', '?<=?', '?<?', '?=?', '?<>?', '?+?',
'?-?', '?*?', '?/?', '@', '|>', '||>', '|||>', '~~', '~~~', '~-',
'~+', ':>', ':?>', "'"
]
if variant in ['fsharp']:
known_operators += known_operators_fsharp
self.unary_operators = ['new', 'not', "'", '-']
self.postfix_operators = ["'"]
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
groupers = [
'(', ')', ',', '[', ']', '{', '}', 'begin', 'end', ';', '|'
]
groupers_fsharp = ['[|', '|]', '[<', '>]', '^']
if variant in ['fsharp']:
groupers += groupers_fsharp
# group_starts = ['(', '[', ',', '{', '[|', '[<']
group_mids = [',', ';', '^', '|']
group_ends = [')', ']', '}', '|]', '>]']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
keywords = [
'assert', 'class', 'def', 'do', 'done', 'downto', 'else',
'exception', 'failwith', 'for', 'fun', 'function', 'if', 'inherit',
'lazy', 'let', 'match', 'method', 'module', 'object', 'open',
'raise', 'rec', 'sig', 'then', 'to', 'try', 'type', 'val',
'virtual', 'while', 'with'
]
keywords_fsharp = [
'abstract', 'break', 'default', 'delegate', 'downcast', 'elif',
'extern', 'finally', 'fixed', 'global', 'inline', 'interface',
'internal', 'let!', 'match!', 'member', 'mutable', 'namespace',
'override', 'private', 'public', 'return', 'return!', 'upcast',
'use', 'use!', 'yield', 'yield!'
]
if variant in ['fsharp']:
keywords += keywords_fsharp
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'bool', 'byte', 'char', 'double', 'float', 'int', 'list', 'long',
'number', 'object', 'range', 'string', 'struct', 'union', 'unit',
'void'
]
types_fsharp = [
'decimal', 'sbyte', 'short', 'uint', 'ulong', 'ushort', 'void'
]
if variant in ['fsharp']:
types += types_fsharp
types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
values = ['base', 'false', 'null', 'true', '_']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, integer_tb, integer_exponent_tb,
real_tb, real_exponent_tb, keyword_tb, types_tb, values_tb,
known_operator_tb, groupers_tb, identifier_tb, class_type_tb,
string_tb, triple_quote_string_tb, prefixed_string_tb, char_tb,
triple_slash_comment_tb, slash_slash_comment_tb,
parens_star_comment_tb, preprocessor_tb, c_error_tb, c_warning_tb,
self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
self.tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid')
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_all_lines(tokens)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends,
allow_pairs)
# self.calc_operator_4_confidence(tokens, num_operators, group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'string', 'symbol']
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
# self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_paired_blockers_confidence(['{'], ['}'])
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, year):
super().__init__()
if year is not None and year not in ['90', '1990', '95', '1995', '2003', '2008']:
raise CodeStatException('Unknown year for language')
operand_types = []
kind_integer_tb = KindIntegerTokenBuilder()
kind_real_tb = KindRealTokenBuilder()
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
bang_comment_tb = LeadToEndOfLineTokenBuilder('!', False, 'comment')
quotes = ["'", '"', "’"]
string_tb = StuffedQuoteStringTokenBuilder(quotes, False)
binary_string_tb = PrefixedStringTokenBuilder('B', False, quotes)
octal_string_tb = PrefixedStringTokenBuilder('O', False, quotes)
hex_string_tb = PrefixedStringTokenBuilder('Z', False, quotes)
operand_types.append('string')
known_operators = [
'=', '+', '-', '*', '/', '**',
'==', '>', '>=', '<', '<=', '/=',
'.EQ.', '.NE.', '.LT.', '.LE.', '.GT.', '.GE.',
'.AND.', '.OR.', '.NOT.', '.EQV.', '.NEQV.',
':', '::', '=>', '%'
]
known_operator_tb = CaseInsensitiveListTokenBuilder(known_operators, 'operator', False)
self.unary_operators = [
'+', '-'
]
user_operator_tb = UserDefinedOperatorTokenBuilder()
continuation_tb = SingleCharacterTokenBuilder('&', 'line continuation', False)
stmt_separator_tb = SingleCharacterTokenBuilder(';', 'statement separator', False)
groupers = ['(', ')', ',', '[', ']']
# group_starts = ['(', '[', ',', '{']
group_mids = [',']
# group_ends = [')', ']', '}']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
keywords = [
'IF', 'THEN', 'ELSE', 'ENDIF', 'END IF', 'GO', 'TO', 'GOTO', 'GO TO',
'READ', 'WRITE', 'BACKSPACE', 'REWIND', 'ENDFILE', 'FORMAT', 'PRINT',
'DO', 'CONTINUE',
'PROGRAM', 'SUBROUTINE', 'FUNCTION', 'BLOCK DATA',
'IMPLICIT', 'SAVE',
'COMMON', 'DIMENSION', 'EQUIVALENCE', 'DATA', 'EXTERNAL',
'CALL', 'RETURN', 'STOP', 'END',
'INQUIRE', 'INTRINSIC', 'PARAMETER',
'allocate', 'case', 'contains', 'cycle', 'deallocate',
'elsewhere', 'exit', 'include', 'interface', 'intent', 'kind', 'module',
'namelist', 'nullify', 'only', 'operator', 'optional', 'pointer',
'private', 'procedure', 'public', 'recursive', 'result', 'select',
'sequence', 'target', 'type', 'use', 'while', 'where',
'enddo', 'end do', 'none'
]
keywords_95 = [
'FORALL', 'PURE', 'ELEMENTAL'
]
keywords_2003 = [
'abstract', 'allocatable', 'associate', 'bind', 'class', 'enum', 'end enum',
'import', 'protected', 'select type', 'type guard', 'value', 'wait'
]
keywords_2008 = [
'block', 'contiguous'
]
if year in ['95', '2003', '2008']:
keywords += keywords_95
if year in ['2003', '2008']:
keywords += keywords_2003
if year in ['2008']:
keywords += keywords_2008
keyword_tb = CaseInsensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'INTEGER', 'REAL', 'COMPLEX', 'DOUBLE PRECISION', 'DOUBLEPRECISION',
'DOUBLE', 'PRECISION', 'LOGICAL', 'CHARACTER'
]
types_tb = CaseInsensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
tokenbuilders = [
self.newline_tb,
self.whitespace_tb,
continuation_tb,
stmt_separator_tb,
self.integer_tb,
self.integer_exponent_tb,
kind_integer_tb,
self.real_tb,
self.real_exponent_tb,
self.double_exponent_tb,
kind_real_tb,
keyword_tb,
types_tb,
known_operator_tb,
user_operator_tb,
groupers_tb,
identifier_tb,
string_tb,
binary_string_tb,
octal_string_tb,
hex_string_tb,
bang_comment_tb,
self.jcl_tb,
self.unknown_operator_tb,
self.invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid operator')
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid')
tokens = Examiner.combine_identifier_colon(tokens, ['newline'], [], ['whitespace', 'comment', 'line description'])
self.tokens = tokens
self.convert_identifiers_to_labels()
self.convert_numbers_to_lineNumbers()
self.convert_stars_to_io_channels()
self.calc_statistics()
tokens = self.source_tokens()
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
# self.calc_operator_3_confidence(tokens, num_operators, group_ends, allow_pairs)
# self.calc_operator_4_confidence(tokens, num_operators, group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'string', 'identifier', 'variable', 'symbol']
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, block_comment_limit):
super().__init__()
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder("'")
integer_exponent_tb = IntegerExponentTokenBuilder("'")
hex_integer_tb = PrefixedIntegerTokenBuilder('0x', False, '0123456789abcdefABCDEF_')
binary_integer_tb = PrefixedIntegerTokenBuilder('0b', False, '01_')
suffixed_integer_tb = SuffixedIntegerTokenBuilder(['U', 'L', 'LU', 'UL'], False, None)
real_tb = RealTokenBuilder(False, False, "'")
suffixed_real_tb = SuffixedRealTokenBuilder(False, False, ['f', 'l', 'i'], False, None)
real_exponent_tb = RealExponentTokenBuilder(False, False, 'E', "'")
hex_real_tb = HexRealExponentTokenBuilder()
operand_types.append('number')
leads = '_'
extras = '_'
identifier_tb = IdentifierTokenBuilder(leads, extras)
operand_types.append('identifier')
attribute_tb = PrefixedIdentifierTokenBuilder('@', 'attribute', False)
operand_types.append('attribute')
# string suffix: c,w,d
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 0)
r_string_tb = PrefixedStringTokenBuilder('r', True, quotes)
backtick_string_tb = EscapedStringTokenBuilder(['`'], 0)
x_string_tb = PrefixedStringTokenBuilder('x', True, quotes)
q_string_tb = PrefixedStringTokenBuilder('q', True, quotes)
# q{} string
cwd_string_tb = SuffixedStringTokenBuilder(quotes, 'cwd', False)
operand_types.append('string')
class_type_tb = ClassTypeTokenBuilder()
operand_types.append('class')
slash_slash_comment_tb = SlashSlashCommentTokenBuilder()
slash_star_comment_tb = SlashStarCommentTokenBuilder()
slash_plus_comment_tb = NestedCommentTokenBuilder('/+', '+/', block_comment_limit)
line_continuation_tb = SingleCharacterTokenBuilder('\\', 'line continuation', False)
terminators_tb = SingleCharacterTokenBuilder(';', 'statement terminator', False)
known_operators = [
'/', '/=', '.', '..', '...', '&', '&=', '&&', '|', '|=', '||',
'-', '-=', '--', '+', '+=', '++', '<', '<=', '<<', '<<=', '>', '>=',
'>>=', '>>>=', '>>', '>>>', '!', '!=', '?', ',', ':', '$',
'=', '==', '*', '*=', '%', '%=', '^', '^=', '^^', '^^=', '~', '~=',
'@', '=>', '#',
'new', 'delete',
'typeof', 'is'
]
self.unary_operators = [
'+', '-', '*',
'!', '&', '~',
'++', '--', ':',
'new', 'delete',
'typeof', 'is'
]
self.postfix_operators = [
'++', '--', '&', ':'
]
groupers = ['(', ')', ',', '[', ']', '{', '}']
group_starts = ['(', '[', ',', '{']
group_mids = [',']
group_ends = [')', ']', '}']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(known_operators, 'operator', False)
keywords = [
'abstract', 'alias', 'align', 'asm', 'assert', 'auto',
'body', 'break', 'case', 'cast', 'catch', 'class', 'const', 'continue',
'debug', 'default', 'delegate', 'deprecated', 'do',
'else', 'enum', 'export', 'extern',
'final', 'finally', 'for', 'foreach', 'foreach_reverse', 'function',
'goto',
'if', 'immutable', 'import', 'in', 'inout', 'interface', 'invariant',
'lazy',
'macro', 'mixin', 'module',
'nothrow',
'out', 'override',
'package', 'pragma', 'private', 'protected', 'public', 'pure',
'ref', 'return',
'scope', 'shared', 'static', 'struct', 'switch', 'synchronized',
'template', 'throw', 'try', 'typeid',
'union', 'unittest', 'version', 'while', 'with',
'__gshared', '__traits', '__vector', '__parameters'
]
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'bool', 'byte', 'cdouble', 'cent', 'cfloat', 'char', 'creal',
'dchar', 'double', 'float', 'idouble', 'ifloat', 'int', 'ireal',
'long', 'real', 'short', 'ubyte', 'ucent', 'uint', 'ulong', 'ushort',
'void', 'wchar'
]
types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
values = [
'false', 'null', 'super', 'this', 'true',
'__FILE__', '__FILE_FULL_PATH__', '__MODULE__', '__LINE__',
'__FUNCTION__', '__PRETTY_FUNCTION__',
'__DATE__', '__EOF__', '__TIME__','__TIMESTAMP__',
'__VENDOR__', '__VERSION__'
]
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb,
whitespace_tb,
line_continuation_tb,
terminators_tb,
integer_tb,
integer_exponent_tb,
hex_integer_tb,
binary_integer_tb,
suffixed_integer_tb,
real_tb,
real_exponent_tb,
suffixed_real_tb,
hex_real_tb,
keyword_tb,
types_tb,
values_tb,
groupers_tb,
known_operator_tb,
identifier_tb,
attribute_tb,
class_type_tb,
string_tb,
r_string_tb,
x_string_tb,
backtick_string_tb,
q_string_tb,
cwd_string_tb,
slash_slash_comment_tb,
slash_star_comment_tb,
slash_plus_comment_tb,
self.unknown_operator_tb,
invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid operator')
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid')
tokens = Examiner.combine_identifier_colon(tokens, ['statement terminator', 'newline'], ['{'], ['whitespace', 'comment'])
self.tokens = tokens
self.convert_identifiers_to_labels()
number_suffixes = ['f', 'F', 'i', 'I', 'u', 'U', 'l', 'L', 'ul', 'uL', 'Ul', 'UL', 'lu', 'lU', 'Lu', 'LU']
tokens = self.combine_tokens_and_adjacent_types(tokens, 'number', 'identifier', number_suffixes)
string_suffixes = ['c', 'w', 'd']
self.tokens = self.combine_tokens_and_adjacent_types(tokens, 'string', 'identifier', string_suffixes)
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_all_lines(tokens)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends, allow_pairs)
self.calc_operator_4_confidence(tokens, num_operators, group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'symbol']
self.calc_operand_n_confidence(tokens, operand_types_2, 2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_paired_blockers_confidence(['{'], ['}'])
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, block_comment_limit):
super().__init__()
self.newlines_important = 'parens'
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder(None)
integer_exponent_tb = IntegerExponentTokenBuilder(None)
hex_integer_tb = PrefixedIntegerTokenBuilder('0x', False,
'0123456789abcdefABCDEF')
real_tb = RealTokenBuilder(False, False, None)
real_exponent_tb = RealExponentTokenBuilder(False, False, 'E', None)
imaginary_tb = SuffixedRealTokenBuilder(False, False, ['im', 'cx'],
True, None)
operand_types.append('number')
leads = '_'
extras = '_'
suffixes = '!'
identifier_tb = SuffixedIdentifierTokenBuilder(leads, extras, suffixes)
operand_types.append('identifier')
symbol_tb = PrefixedIdentifierTokenBuilder(':', 'symbol', True)
operand_types.append('symbol')
attribute_tb = PrefixedIdentifierTokenBuilder('@', 'attribute', False)
operand_types.append('attribute')
dollar_sign_tb = SingleCharacterTokenBuilder('$', 'identifier', True)
quotes = ['"', "'", "’"]
string_tb = EscapedStringTokenBuilder(quotes, 0)
raw_string_tb = PrefixedRawStringTokenBuilder('raw', True, quotes)
b_string_tb = PrefixedStringTokenBuilder('b', True, quotes)
triple_quote_string_tb = TripleQuoteStringTokenBuilder(quotes)
operand_types.append('string')
comment_tb = LeadToEndOfLineTokenBuilder('#', True, 'comment')
nested_comment_tb = NestedCommentTokenBuilder('#=', '=#',
block_comment_limit)
line_continuation_tb = SingleCharacterTokenBuilder(
'\\', 'line continuation', False)
terminators_tb = SingleCharacterTokenBuilder(';',
'statement terminator',
False)
known_operators = [
'where', 'in', 'isa', '′', "'", '+', '-', '*', '/', '\\', '^', '%',
'//', '<<', '>>', '<<<', '>>>', ':', '=', '==', '!=', '===', '!==',
'+=', '-=', '*=', '/=', '^=', '%=', '<', '>', '<=', '>=', '~', '&',
'|', '!', '&&', '||', '?', '.', '<:', '>:', '::', '->', '...',
'..', '∀', '≤', '≥', '⊻', '⊽', '⊼'
]
# 0x391 through 0x3a9 (capital)
# 0x3b1 through 0x3c9 (small)
greek_letters = [
'α', 'β', 'γ', 'δ', 'ε', 'ζ', 'η', 'θ', 'ι', 'κ', 'λ', 'μ', 'ν',
'ξ', 'ο', 'π', 'ρ', 'ς', 'σ', 'τ', 'υ', 'φ', 'χ', 'ψ', 'ω'
]
greek_letter_tb = CaseSensitiveListTokenBuilder(
greek_letters, 'identifier', True)
self.unary_operators = [
'isa', '+', '-', '~', '!', '.', ':', '::', "'", '<:', '>:', 'in',
'..'
]
self.postfix_operators = ['...', '′']
groupers = ['(', ')', ',', '[', ']', '{', '}']
# group_starts = ['(', '[', ',', '{']
group_mids = [',']
group_ends = [')', ']', '}']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
keywords = [
'baremodule', 'begin', 'break', 'catch', 'const', 'continue', 'do',
'else', 'elseif', 'end', 'export', 'finally', 'for', 'function',
'global', 'if', 'import', 'let', 'local', 'macro', 'module',
'quote', 'return', 'struct', 'try', 'using', 'while', 'abstract',
'mutable', 'primitive', 'type'
]
keyword_tb = CaseSensitiveListTokenBuilder(keywords, 'keyword', False)
types = [
'Int8', 'UInt8', 'Int16', 'UInt16', 'Int32', 'UInt32', 'Int64',
'UInt64', 'Int128', 'UInt128', 'Float16', 'Float32', 'Float64',
'Bool', 'Char'
]
types_tb = CaseSensitiveListTokenBuilder(types, 'type', True)
operand_types.append('type')
values = ['false', 'true']
values_tb = CaseSensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb, whitespace_tb, line_continuation_tb, terminators_tb,
integer_tb, integer_exponent_tb, hex_integer_tb, real_tb,
real_exponent_tb, imaginary_tb, keyword_tb, types_tb, values_tb,
groupers_tb, known_operator_tb, identifier_tb, symbol_tb,
attribute_tb, dollar_sign_tb, greek_letter_tb, string_tb,
raw_string_tb, b_string_tb, triple_quote_string_tb, comment_tb,
nested_comment_tb, self.unknown_operator_tb, invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
tokens = Examiner.combine_adjacent_identical_tokens(tokens, 'invalid')
tokens = JuliaExaminer.split_symbols_to_operators_identifiers(
tokens, group_ends)
self.tokens = tokens
self.convert_keywords_to_identifiers()
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_parens_continued_lines(tokens)
tokens = Examiner.join_operator_continued_lines(
tokens, self.postfix_operators)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
self.calc_operator_3_confidence(tokens, num_operators, group_ends,
allow_pairs)
# self.calc_operator_4_confidence(tokens, num_operators, group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
operand_types_2 = ['number', 'identifier', 'symbol']
self.calc_operand_confidence(tokens, operand_types_2)
self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_paired_blockers_confidence(['{'], ['}'])
self.calc_line_length_confidence(code, self.max_expected_line)
def __init__(self, code, year, extension):
super().__init__()
if year is not None and year not in ['2002', '2014']:
raise CodeStatException('Unknown year for language')
operand_types = []
whitespace_tb = WhitespaceTokenBuilder()
newline_tb = NewlineTokenBuilder()
integer_tb = IntegerTokenBuilder(None)
integer_exponent_tb = IntegerExponentTokenBuilder(None)
real_tb = RealTokenBuilder(False, True, None)
real_exponent_tb = RealExponentTokenBuilder(False, True, 'E', None)
identifier_tb = CobolIdentifierTokenBuilder()
quotes = ['"', "'", "’"]
string_tb = StuffedQuoteStringTokenBuilder(quotes, False)
n_string_tb = PrefixedStringTokenBuilder('N', False, quotes)
nx_string_tb = PrefixedStringTokenBuilder('NX', False, quotes)
picture_tb = PictureTokenBuilder()
cr_picture_tb = CRPictureTokenBuilder()
inline_comment_tb = LeadToEndOfLineTokenBuilder('*>', True, 'comment')
star_comment_tb = AsteriskCommentTokenBuilder()
terminators_tb = SingleCharacterTokenBuilder('.',
'statement terminator',
False)
known_operators = [
'ADD', 'SUBTRACT', 'MULTIPLY', 'DIVIDE', '+', '-', '*', '/', '**',
'=', '<>', '>', '>=', '<', '<=', 'AND', 'OR', 'NOT', 'B-AND',
'B-NOT', 'B-OR', 'B-XOR', ':'
]
known_operator_tb = CaseSensitiveListTokenBuilder(
known_operators, 'operator', False)
self.unary_operators = ['+', '-', 'NOT']
groupers = ['(', ')', ',']
group_starts = ['(']
group_mids = [',']
# group_ends = [')']
groupers_tb = CaseInsensitiveListTokenBuilder(groupers, 'group', False)
keywords = [
'ACCEPT', 'ACCESS', 'ADD', 'ADDRESS', 'ADVANCING', 'AFTER', 'ALL',
'ALPHABET', 'ALPHABETIC', 'ALPHABETIC-LOWER', 'ALPHABETIC-UPPER',
'ALPHANUMERIC', 'ALPHANUMERIC-EDITED', 'ALSO', 'ALTER',
'ALTERNATE', 'AND', 'ANY', 'APPLY', 'ARE', 'AREA', 'AREAS',
'ASCENDING', 'ASSIGN', 'AT', 'AUTHOR', 'BEFORE', 'BEGINNING',
'BELL', 'BINARY', 'BLOCK', 'BOTTOM', 'BY', 'BYTE-LENGTH', 'CALL',
'CANCEL', 'CBL', 'CD', 'CF', 'CH', 'CHARACTER', 'CHARACTERS',
'CLOCK-UNITS', 'CLOSE', 'COBOL', 'CODE', 'CODE-SET', 'COL',
'COLLATING', 'COLS', 'COLUMN', 'COMMA', 'COMMON', 'COMMUNICATION',
'COMP', 'COMPUTATIONAL', 'COMPUTE', 'CONFIGURATION', 'CONTAINS',
'CONTENT', 'CONTINUE', 'CONTROL', 'CONTROLS', 'CONVERTING', 'COPY',
'CORR', 'CORRESPONDING', 'COUNT', 'CURRENCY', 'DATA', 'DATE',
'DATE-COMPILED', 'DATE-WRITTEN', 'DAY', 'DAY-OF-WEEK', 'DE',
'DEBUG-CONTENTS', 'DEBUG-ITEM', 'DEBUG-LINE', 'DEBUG-NAME',
'DEBUG-SUB-1', 'DEBUG-SUB-2', 'DEBUG-SUB-3', 'DECIMAL-POINT',
'DECLARATIVES', 'DELETE', 'DELIMITED', 'DELIMITER', 'DEPENDING',
'DESCENDING', 'DESTINATION', 'DISABLE', 'DIVIDE', 'DIVISION',
'DOWN', 'DUPLICATES', 'DYNAMIC', 'EGI', 'ELSE', 'EMI', 'ENABLE',
'END', 'END-ACCEPT', 'END-ADD', 'END-CALL', 'END-COMPUTE',
'END-DELETE', 'END-DISPLAY', 'END-DIVIDE', 'END-EVALUATE',
'END-EXEC', 'END-IF', 'END-MULTIPLY', 'END-OF-PAGE', 'END-PERFORM',
'END-READ', 'END-RECEIVE', 'END-RETURN', 'END-REWRITE',
'END-SEARCH', 'END-START', 'END-STRING', 'END-SUBTRACT',
'END-UNSTRING', 'END-WRITE', 'ENTER', 'ENVIRONMENT', 'EOL', 'EOP',
'EQUAL', 'ERROR', 'ESI', 'EVALUATE', 'EVERY', 'EXCEPTION', 'EXEC',
'EXIT', 'EXTEND', 'EXTERNAL', 'FD', 'FILE', 'FILE-CONTROL',
'FILLER', 'FINAL', 'FIRST', 'FOOTING', 'FOR', 'FROM', 'FULL',
'GENERATE', 'GIVING', 'GLOBAL', 'GO', 'GOBACK', 'GREATER', 'GROUP',
'HEADING', 'HIGH-VALUE', 'HIGH-VALUES', 'I-O', 'I-O-CONTROL',
'IDENTIFICATION', 'IF', 'IN', 'INDEX', 'INDEXED', 'INDICATE',
'INITIAL', 'INITIALIZE', 'INITIATE', 'INPUT', 'INPUT-OUTPUT',
'INSPECT', 'INSTALLATION', 'INTO', 'INVALID', 'IS', 'JUST',
'JUSTIFIED', 'KEY', 'LABEL', 'LAST', 'LEADING', 'LEFT', 'LENGTH',
'LESS', 'LIMIT', 'LIMITS', 'LINAGE', 'LINAGE-COUNTER', 'LINE',
'LINE-COUNTER', 'LINES', 'LINKAGE', 'LOCK', 'LOW-VALUE',
'LOW-VALUES', 'MEMORY', 'MERGE', 'MESSAGE', 'MODE', 'MODULES',
'MOVE', 'MULTIPLE', 'MULTIPLY', 'NATIVE', 'NEGATIVE', 'NEXT',
'NOT', 'NUMBER', 'NUMBERS', 'NUMERIC', 'NUMERIC-EDITED',
'OBJECT-COMPUTER', 'OCCURS', 'OF', 'OMITTED', 'OPEN', 'OPTIONAL',
'OR', 'ORDER', 'ORGANIZATION', 'OTHER', 'OUTPUT', 'OVERFLOW',
'PACKED-DECIMAL', 'PADDING', 'PAGE', 'PAGE-COUNTER', 'PARAGRAPH',
'PERFORM', 'PF', 'PH', 'PIC', 'PICTURE', 'PLUS', 'POINTER',
'POSITION', 'POSITIVE', 'PRINTING', 'PROCEDURE', 'PROCEDURES',
'PROCEED', 'PROGRAM', 'PROGRAM-ID', 'PURGE', 'QUEUE', 'QUOTE',
'QUOTES', 'RANDOM', 'RD', 'READ', 'RECEIVE', 'RECORD', 'RECORDS',
'REDEFINES', 'REEL', 'REFERENCE', 'RELATIVE', 'RELEASE',
'REMAINDER', 'REMOVAL', 'RENAMES', 'REPLACE', 'REPLACING',
'REPORT', 'REPORTING', 'REPORTS', 'RERUN', 'RESERVE', 'RESET',
'RESUME', 'RETRY', 'RETURN', 'REVERSED', 'REWIND', 'REWRITE', 'RF',
'RH', 'RIGHT', 'ROUNDED', 'RUN', 'SAME', 'SD', 'SEARCH', 'SECTION',
'SECURE', 'SECURITY', 'SEGMENT', 'SEGMENT-LIMIT', 'SELECT', 'SEND',
'SENTENCE', 'SEPARATE', 'SEQUENCE', 'SEQUENTIAL', 'SET', 'SIGN',
'SIZE', 'SORT', 'SORT-MERGE', 'SOURCE', 'SOURCE-COMPUTER',
'SPECIAL-NAMES', 'STANDARD', 'STANDARD-1', 'STANDARD-2', 'START',
'STATUS', 'STOP', 'STRING', 'SUB-QUEUE-1', 'SUB-QUEUE-2',
'SUB-QUEUE-3', 'SUBTRACT', 'SUM', 'SUPPRESS', 'SYMBOLIC', 'SYNC',
'SYNCHRONIZED', 'TABLE', 'TALLY', 'TALLYING', 'TAPE', 'TERMINAL',
'TERMINATE', 'TEST', 'TEXT', 'THAN', 'THEN', 'THROUGH', 'THRU',
'TIME', 'TIMES', 'TITLE', 'TO', 'TOP', 'TRAILING', 'TYPE', 'UNIT',
'UNSTRING', 'UNTIL', 'UP', 'UPON', 'USAGE', 'USE', 'USING',
'VALUE', 'VALUES', 'VARYING', 'WHEN', 'WITH', 'WORDS',
'WORKING-STORAGE', 'WRITE'
]
keywords_2002 = [
'ACTIVE-CLASS',
'ALIGNED',
'ALLOCATE',
'ANYCASE',
'ARITHMETIC',
'AUTO',
'AUTOMATIC',
'BACKGROUND-COLOR',
'BASED',
'BASIS',
'BINARY-CHAR',
'BINARY-DOUBLE',
'BINARY-LONG',
'BINARY-SHORT',
'BIT',
'BLINK',
'BOOLEAN',
'CENTER',
'CLASS',
'CLASS-ID',
'CLASSIFICATION',
'COLUMNS',
'COM-REG',
'CONDITION',
'CONSTANT',
'CRT',
'CURSOR',
'CYCLE',
'DATA-POINTER',
'DBCS',
'DEBUGGING',
'DETAIL',
'DISPLAY',
'DISPLAY-1',
'DISPLAY-OF',
'EC',
'EGCS',
'EJECT',
'END-INVOKE',
'ENDING',
'ENTRY-CONVENTION',
'ENTRY-FIELD',
'EO',
'EOS',
'ERASE',
'EXCEPTION-OBJECT',
'EXCLUSIVE',
'EXPANDS',
'EXTERN',
'FACTORY',
'FLOAT-EXTENDED',
'FLOAT-LONG',
'FLOAT-SHORT',
'FOREGROUND-COLOR',
'FOREVER',
'FORMAT',
'FREE',
'FUNCTION',
'FUNCTION-ID',
'GET',
'GROUP-USAGE',
'HIGHLIGHT',
'IGNORING',
'IMPLEMENTS',
'INHERITS',
'INITIALIZED',
'INSERT',
'INTERFACE',
'INTERFACE-ID',
'INTRINSIC',
'INVOKE',
'KANJI',
'LC_ALL',
'LC_COLLATE',
'LC_CTYPE',
'LC_MESSAGES',
'LC_MONEY',
'LC_NUMERIC',
'LC_TIME',
'LOCAL-STORAGE',
'LOCALE',
'LOWLIGHT',
'MANUAL',
'METACLASS',
'METHOD',
'METHOD-ID',
'MINUS',
'MORE-LABELS',
'NATIONAL',
'NATIONAL-EDITED',
'NATIONAL-OF',
'NATIVE_BINARY',
'NESTED',
'NEW',
'NONE',
'NORMAL',
'OBJECT',
'OBJECT-REFERENCE',
'ONLY',
'OPTIONS',
'OVERRIDE',
'PHYSICAL',
'PRESENT',
'PREVIOUS',
'PROCEDURE-POINTER',
'PROCESSING',
'PROGRAM-POINTER',
'PROPERTY',
'PROTOTYPE',
'RAISE',
'RAISING',
'READY',
'RECURSIVE',
'REFERENCES',
'RELATION',
'RELOAD',
'REPOSITORY',
'REQUIRED',
'RETURN-CODE',
'RETURNING',
'ROUNDING',
'SCREEN',
'SECONDS',
'SERVICE',
'SHARING',
'SHIFT-IN',
'SHIFT-OUT',
'SIGNED',
'SKIP1',
'SKIP2',
'SKIP3',
'SORT-CONTROL',
'SORT-CORE-SIZE',
'SORT-FILE-SIZE',
'SORT-MESSAGE',
'SORT-MODE-SIZE',
'SORT-RETURN',
'SOURCES',
'STATEMENT',
'STEP',
'STRONG',
'SYMBOL',
'SYSTEM-DEFAULT',
'TRACE',
'TYPEDEF',
'UCS-4',
'UNDERLINE',
'UNIVERSAL',
'UNLOCK',
'UNSIGNED',
'USER-DEFAULT',
'UTF-16',
'UTF-8',
'VAL-STATUS',
'VALID',
'VALIDATE',
'VALIDATE-STATUS',
'WHEN-COMPILED',
'WRITE-ONLY',
'YYYYDDD',
'YYYYMMDD',
]
keywords_2014 = [
'AWAY-FROM-ZERO', 'NEAREST-AWAY-FROM-ZERO', 'NEAREST-EVEN',
'NEAREST-TOWARD-ZERO', 'TOWARD-GREATER', 'TOWARD-LESSER',
'CAPACITY', 'FLOAT-BINARY-128', 'FLOAT-BINARY-32',
'FLOAT-BINARY-64', 'FLOAT-DECIMAL-16', 'FLOAT-DECIMAL-34',
'FLOAT-INFINITY', 'FLOAT-NOT-A-NUMBER', 'FUNCTION-POINTER',
'INTERMEDIATE', 'PHYSICAL', 'PREFIXED', 'PROHIBITED', 'SHORT',
'STANDARD-BINARY', 'STANDARD-DECIMAL', 'TRUNCATION'
]
keywords_ibm = ['ABSENT', 'ID', 'PASSWORD', 'UNBOUNDED']
keywords_gnu = [
'ARGUMENT-NUMBER', 'ARGUMENT-VALUE', 'ASCII', 'BINARY-C-LONG',
'BINARY-SEQUENTIAL', 'CARD-PUNCH', 'CARD-READER', 'CASSETTE',
'CHAIN', 'CHAINING', 'COLOR', 'COMMAND-LINE', 'COMMIT', 'COMP-1',
'COMP-2', 'COMP-3', 'COMP-4', 'COMP-5', 'COMP-6', 'COMP-X',
'COMPUTATIONAL-1', 'COMPUTATIONAL-2', 'COMPUTATIONAL-3',
'COMPUTATIONAL-4', 'COMPUTATIONAL-5', 'COMPUTATIONAL-6',
'COMPUTATIONAL-X', 'CONVERSION', 'CRT-UNDER', 'DISC', 'DISK',
'EBCDIC', 'ECHO', 'END-CHAIN', 'ENTRY', 'ENVIRONMENT-NAME',
'ENVIRONMENT-VALUE', 'ESCAPE', 'F', 'FILE-ID', 'FIXED',
'FLOAT-DECIMAL-7', 'ID', 'IGNORE', 'KEPT', 'KEYBOARD',
'LEFT-JUSTIFY', 'LEFTLINE', 'LINE-SEQUENTIAL', 'LOWER',
'MAGNETIC-TAPE', 'NAME', 'NO-ECHO', 'NOTHING', 'OVERLINE', 'PRINT',
'PRINTER', 'PRINTER-1', 'PROCEDURE-POINTER', 'PROCEDURES',
'PROMPT', 'PROTECTED', 'RECORDING', 'REVERSE', 'RIGHT-JUSTIFY',
'ROLLBACK', 'S', 'SCROLL', 'SIGNED-INT', 'SIGNED-LONG',
'SIGNED-SHORT', 'SPACE-FILL', 'STATIC', 'STDCALL', 'SYSTEM-OFFSET',
'TAB', 'TIME-OUT', 'TRAILING-SIGN', 'U', 'UNSIGNED-INT',
'UNSIGNED-LONG', 'UNSIGNED-SHORT', 'UPDATE', 'UPPER', 'USER', 'V',
'VARIABLE', 'WAIT', 'WRAP', 'ZERO-FILL'
]
keywords_acu = [
'3-D', 'ACTION', 'ACTIVE-X', 'ADJUSTABLE-COLUMNS', 'ALIGNMENT',
'AUTO-DECIMAL', 'AUTO-SPIN', 'BACKGROUND-HIGH', 'BACKGROUND-LOW',
'BACKGROUND-STANDARD', 'BAR', 'BITMAP', 'BITMAP-END',
'BITMAP-HANDLE', 'BITMAP-NUMBER', 'BITMAP-START',
'BITMAP-TRAILING', 'BITMAP-TRANSPARENT-COLOR', 'BITMAP-WIDTH',
'BOX', 'BOXED', 'BUSY', 'BUTTONS', 'CALENDAR-FONT',
'CANCEL-BUTTON', 'CELL', 'CELL-COLOR', 'CELL-DATA', 'CELL-FONT',
'CELL-PROTECTION', 'CENTERED-HEADING', 'CENTURY-DATE', 'CHECK-BOX',
'CLEAR-SELECTION', 'CLINE', 'CLINES', 'COLORS', 'COLUMN-COLOR',
'COLUMN-DIVIDERS', 'COLUMN-FONT', 'COLUMN-HEADINGS',
'COLUMN-PROTECTION', 'COMBO-BOX', 'COPY-SELECTION', 'CSIZE',
'CURSOR-COL', 'CURSOR-COLOR', 'CURSOR-FRAME-WIDTH', 'CURSOR-ROW',
'CURSOR-X', 'CURSOR-Y', 'CUSTOM-PRINT-TEMPLATE', 'DASHED',
'DATA-COLUMNS', 'DATA-TYPES', 'DATE-ENTRY', 'DEFAULT-BUTTON',
'DEFAULT-FONT', 'DESTROY', 'DISPLAY-COLUMNS', 'DISPLAY-FORMAT',
'DOTDASH', 'DOTTED', 'DOUBLE', 'DRAG-COLOR', 'DROP-DOWN',
'DROP-LIST', 'END-COLOR', 'END-MODIFY', 'ENGRAVED',
'ENSURE-VISIBLE', 'ENTRY-FIELD', 'ENTRY-REASON', 'ESCAPE-BUTTON',
'EVENT', 'EVENT-LIST', 'EXCEPTION-VALUE', 'EXPAND',
'EXTERNAL-FORM', 'FILE-NAME', 'FILE-POS', 'FILL-COLOR',
'FILL-COLOR-2', 'FILL-PERCENT', 'FINISH-REASON', 'FIXED-FONT',
'FIXED-WIDTH', 'FLAT', 'FLAT-BUTTONS', 'FLOAT', 'FLOATING', 'FONT',
'FRAME', 'FRAMED', 'FULL-HEIGHT', 'GRID', 'GO-BACK', 'GO-FORWARD',
'GO-HOME', 'GO-SEARCH', 'GRAPHICAL', 'GRID', 'GROUP-VALUE',
'HANDLE', 'HAS-CHILDREN', 'HEADING-COLOR', 'HEADING-DIVIDER-COLOR',
'HEADING-FONT', 'HEAVY', 'HEIGHT-IN-CELLS', 'HIDDEN-DATA',
'HIGH-COLOR', 'HOT-TRACK', 'HSCROLL', 'HSCROLL-POS', 'ICON',
'IDENTIFIED', 'INDEPENDENT', 'INQUIRE', 'INSERTION-INDEX',
'INSERTION-ROWS', 'ITEM', 'ITEM-TEXT', 'ITEM-TO-ADD',
'ITEM-TO-DELETE', 'ITEM-TO-EMPTY', 'ITEM-VALUE', 'LABEL',
'LABEL-OFFSET', 'LARGE-FONT', 'LARGE-OFFSET', 'LAST-ROW',
'LAYOUT-DATA', 'LAYOUT-MANAGER', 'LEADING-SHIFT', 'LEFT-TEXT',
'LINES-AT-ROOT', 'LIST-BOX', 'LM-RESIZE', 'LONG-DATE', 'LOW-COLOR',
'LOWERED', 'MASS-UPDATE', 'MAX-LINES', 'MAX-PROGRESS', 'MAX-TEXT',
'MAX-VAL', 'MEDIUM-FONT', 'MENU', 'MIN-VAL', 'MODIFY', 'MULTILINE',
'NAVIGATE-URL', 'NEXT-ITEM', 'NO-AUTOSEL', 'NO-AUTO-DEFAULT',
'NO-BOX', 'NO-DIVIDERS', 'NO-F4', 'NO-FOCUS', 'NO-GROUP-TAB',
'NO-KEY-LETTER', 'NO-SEARCH', 'NO-UPDOWN', 'NOTAB', 'NOTIFY',
'NOTIFY-CHANGE', 'NOTIFY-DBLCLICK', 'NOTIFY-SELCHANGE',
'NUM-COL-HEADINGS', 'NUM-ROWS', 'OK-BUTTON', 'OVERLAP-LEFT',
'OVERLAP-TOP', 'PAGE-SETUP', 'PAGED', 'PARENT', 'PERMANENT',
'PIXEL', 'PLACEMENT', 'POP-UP', 'POSITION-SHIFT',
'PRINT-NO-PROMPT', 'PRINT-PREVIEW', 'PRIORITY', 'PROGRESS',
'PROPERTIES', 'PROPERTY', 'PUSH-BUTTON', 'QUERY-INDEX',
'RADIO-BUTTON', 'RAISED', 'READ-ONLY', 'RECORD-DATA',
'RECORD-TO-ADD', 'RECORD-TO-DELETE', 'REFRESH', 'REGION-COLOR',
'RESET-GRID', 'RESET-LIST', 'RESET-TABS', 'RIGHT-ALIGN', 'RIMMED',
'ROW-COLOR', 'ROW-COLOR-PATTERN', 'ROW-DIVIDERS', 'ROW-FONT',
'ROW-HEADINGS', 'ROW-PROTECTION', 'SAVE-AS', 'SAVE-AS-NO-PROMPT',
'SCROLL-BAR', 'SEARCH-OPTIONS', 'SEARCH-TEXT', 'SELECT-ALL',
'SELECTION-INDEX', 'SELECTION-TEXT', 'SELF-ACT', 'SEPARATION',
'SHADING', 'SHADOW', 'SHORT-DATE', 'SHOW-LINES', 'SHOW-NONE',
'SHOW-SEL-ALWAYS', 'SMALL-FONT', 'SORT-ORDER', 'SPINNER', 'SQUARE',
'START-X', 'START-Y', 'STATIC-LIST', 'STATUS-BAR', 'STATUS-TEXT',
'STYLE', 'SUBWINDOW', 'TAB-TO-ADD', 'TAB-TO-DELETE', 'TEMPORARY',
'TERMINATION-VALUE', 'THREAD', 'THREADS', 'THUMB-POSITION',
'TILED-HEADINGS', 'TITLE', 'TITLE-POSITION', 'TRADITIONAL-FONT',
'TRAILING-SHIFT', 'TRANSPARENT', 'TREE-VIEW', 'UNFRAMED',
'UNSORTED', 'USE-ALT', 'USE-RETURN', 'USE TAB', 'VALUE-FORMAT',
'VARIANT', 'VERTICAL', 'VERY-HEAVY', 'VIRTUAL-WIDTH', 'VPADDING',
'VSCROLL', 'VSCROLL-BAR', 'VSCROLL-POS', 'VTOP', 'WEB-BROWSER',
'WIDTH', 'WIDTH-IN-CELLS', 'WINDOW', 'X', 'Y'
]
if year in ['2002', '2014']:
keywords += keywords_2002
if year == '2014':
keywords += keywords_2014
if extension.lower() == 'acu':
keywords += keywords_acu
if extension.lower() == 'ibm':
keywords += keywords_ibm
if extension.lower() == 'gnu':
keywords += keywords_gnu
keyword_tb = CaseInsensitiveListTokenBuilder(keywords, 'keyword',
False)
values = [
'BLANK', 'SPACE', 'SPACES', 'ZERO', 'ZEROES', 'ZEROS', 'FALSE',
'NO', 'OFF', 'ON', 'TRUE'
]
values_2002 = ['NULL', 'NULLS', 'SELF', 'SUPER']
if year in ['2002', '2014']:
values += values_2002
value_tb = CaseInsensitiveListTokenBuilder(values, 'value', True)
operand_types.append('value')
cobol_preprocessor_tb = CobolPreprocessorTokenBuilder()
exec_tb = BlockTokenBuilder('EXEC', 'END-EXEC', 'exec block')
invalid_token_builder = InvalidTokenBuilder()
tokenbuilders = [
newline_tb,
whitespace_tb,
terminators_tb,
integer_tb,
integer_exponent_tb,
real_tb,
real_exponent_tb,
picture_tb,
cr_picture_tb,
keyword_tb,
star_comment_tb, # before operator, to catch single star as comment
known_operator_tb,
groupers_tb,
value_tb,
identifier_tb,
string_tb,
n_string_tb,
nx_string_tb,
inline_comment_tb,
cobol_preprocessor_tb,
exec_tb,
self.unknown_operator_tb,
invalid_token_builder
]
tokenizer = Tokenizer(tokenbuilders)
tokens = tokenizer.tokenize(code)
tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid operator')
self.tokens = Examiner.combine_adjacent_identical_tokens(
tokens, 'invalid')
self.convert_numbers_to_pictures()
self.convert_numbers_to_levels()
self.calc_statistics()
tokens = self.source_tokens()
tokens = Examiner.join_all_lines(tokens)
self.calc_token_confidence()
self.calc_token_2_confidence()
num_operators = self.count_my_tokens(['operator', 'invalid operator'])
if num_operators > 0:
self.calc_operator_confidence(num_operators)
allow_pairs = []
self.calc_operator_2_confidence(tokens, num_operators, allow_pairs)
# self.calc_operator_3_confidence(tokens, num_operators, group_ends, allow_pairs)
self.calc_operator_4_confidence(tokens, num_operators,
group_starts, allow_pairs)
self.calc_group_confidence(tokens, group_mids)
# self.calc_operand_n_confidence(tokens, operand_types, 2)
# self.calc_operand_n_confidence(tokens, operand_types, 4)
self.calc_keyword_confidence()
self.calc_line_length_confidence(code, self.max_expected_line)
self.calc_picture_confidence()
expected_keyword_confidence = self.check_expected_keywords()
self.confidences['expected_keywords'] = expected_keyword_confidence