def execute(self, src: (str, list, TextList),
person_names: list,
is_debug: bool=False) -> ResultData: # pragma: no cover
LOG.info('ANALYZER: start exec')
is_succeeded = True
error = None
basesrc = None
result = ResultData([], is_succeeded, error)
if isinstance(src, str):
basesrc = TextList(*get_content_from_text_file(src))
elif isinstance(src, TextList):
basesrc = src
elif isinstance(src, (list, tuple)):
basesrc = TextList(*src)
else:
msg = f'Invalid analyze source!: {src}'
LOG.critical(msg)
return ResultData(result, False, AnalyzerError(msg))
tmp = self._rid_tag(basesrc)
LOG.info('TOKENIZER: call')
result = assertion.is_instance(Tokenizer().execute(tmp, person_names), ResultData)
if not result.is_succeeded:
return result
tokens = assertion.is_instance(result.data, TokenList)
LOG.info('WORD_ANALYZER: call')
result = assertion.is_instance(WordAnalyzer().execute(tokens), ResultData)
if not result.is_succeeded:
return result
word_data = assertion.is_listlike(result.data)
LOG.info('PERCENT_ANALYZER: call')
result = assertion.is_instance(PercentAnalyzer().execute(tmp), ResultData)
if not result.is_succeeded:
return result
percent_data = assertion.is_listlike(result.data)
LOG.info('FREQUENCY_ANALYZER: call')
result = assertion.is_instance(FrequencyAnalyzer().execute(tokens), ResultData)
if not result.is_succeeded:
return result
freq_data = assertion.is_listlike(result.data)
LOG.info('Analyzer result output')
result_data = percent_data + ['\n---\n'] \
+ word_data + ['\n---\n'] \
+ freq_data
fname = 'result'
suffix = ''
extention = 'md'
builddir = 'build/results'
mode = OutputMode.CONSOLE if is_debug else OutputMode.FILE
data = TextList(*[f'{line}\n' for line in result_data])
Outputter().execute(data, mode, fname, suffix, extention, builddir)
return result
def _exec_internal(self, src: (TextList, list, tuple),
person_names: list) -> TokenList:
LOG.debug(f'-- src: {src}')
tmp = []
def _excepted(target: str):
return target in ('EOS', '', 't', 'ー')
def _is_exists_name(target: str):
for name in person_names:
if name == target:
return True
return False
_src = src.data if isinstance(src, TextList) else src
parsed = self._tagger.parse('\n'.join(
assertion.is_listlike(_src))).split('\n')
tokens = self._packed_from_parsed(parsed)
for token in tokens:
if _excepted(token[0]):
continue
elif len(token) == 1:
continue
if token[1] == WordClass.NOUN.conv_str():
if _is_exists_name(token[0]):
token[3] = '人名'
tmp.append(MecabData.conv(*token))
return TokenList(*tmp)
def has_rubi_exclusions(self, src: str, ex_words: (tuple, list)) -> bool:
''' Check whether the string has a exclusion rubi-words.
'''
for word in assertion.is_listlike(ex_words):
if assertion.is_str(word) in assertion.is_str(src):
return True
return False
def _output(self, src: list, config: StoryConfig) -> ResultData:
LOG.info('RUN: OUTPUT: start')
assertion.is_instance(config, StoryConfig)
result = ResultData(src, True, None)
prefixs = assertion.is_valid_length(
['', '_p', '', '_data', '_sc', '_ad'], len(CompileMode.get_all()))
extentions = assertion.is_valid_length(
['md', 'md', 'txt', 'md', 'md', 'md'], len(CompileMode.get_all()))
fmt_idx = 0
outputter = Outputter()
for fmt_data in assertion.is_listlike(src):
if fmt_data:
LOG.info(f'RUN: START: Outputter [{fmt_idx}]')
result = assertion.is_instance(
outputter.execute(fmt_data, config.output_mode,
config.filename, prefixs[fmt_idx],
extentions[fmt_idx], config.builddir),
ResultData)
if not result.is_succeeded:
LOG.error(f'Failure in Outputter [{fmt_idx}]!!')
return result
LOG.info(f'... SUCCESS: Outputter [{fmt_idx}]')
fmt_idx += 1
return result
def __init__(self, title: str):
LOG.info('CONFIG: initialize')
LOG.debug(f'-- title: {title}')
# for specific
self._title = assertion.is_str(title)
self._copy = assertion.is_str('__catch_copy__')
self._oneline = assertion.is_str('__one_line__')
self._outline = assertion.is_str('__story_outline__')
self._theme = assertion.is_str('__theme__')
self._genre = assertion.is_str('__genre__')
self._target = assertion.is_str('__target_age__')
self._size = assertion.is_str('__size__')
self._desc_size = assertion.is_int(0)
self._total_size = assertion.is_int(0)
self._desc_papers = assertion.is_int_or_float(0)
self._total_papers = assertion.is_int_or_float(0)
# for story
self._priority = assertion.is_int(__PRIORITY_DEFAULT__)
self._start = assertion.is_int(0)
self._end = assertion.is_int(-1)
self._base_date = datetime.date(2020, 1, 1)
self._base_time = datetime.time(12, 00)
self._version = assertion.is_tuple((0, 0, 1))
self._columns = assertion.is_int(20)
self._rows = assertion.is_int(20)
self._contest_info = assertion.is_str('')
self._caution = assertion.is_str('')
self._note = assertion.is_str('')
self._sites = assertion.is_listlike([])
self._taginfos = assertion.is_listlike([])
self._modified = datetime.date.today()
self._released = datetime.date(2020, 1, 1)
# for compile
self._is_data = assertion.is_bool(False)
self._is_plot = assertion.is_bool(False)
self._is_text = assertion.is_bool(False)
self._is_scenario = assertion.is_bool(False)
self._is_audiodrama = assertion.is_bool(False)
self._is_rubi = assertion.is_bool(False)
self._is_comment = assertion.is_bool(False)
self._is_console = assertion.is_bool(False)
self._format_mode = assertion.is_instance(FormatMode.DEFAULT,
FormatMode)
self._output_mode = assertion.is_instance(OutputMode.FILE, OutputMode)
self._filename = assertion.is_str('story')
self._builddir = assertion.is_str('build')
self._log_level = assertion.is_str('warn')
def test_is_listlike(self):
data = [
# (val, expect)
(True, [1,2,3], [1,2,3]),
(True, (1,2), (1,2)),
(False, 1, 1),
]
validate_with_fail(self, "is_listlike",
lambda v,expect: self.assertEqual(assertion.is_listlike(v), expect),
data)
def build_db(self, persons: ListLike, stages: ListLike, days: ListLike,
times: ListLike, items: ListLike, words: ListLike,
rubis: ListLike) -> None:
# TODO: 間違ったものの設定時はエラー出す
if assertion.is_listlike(persons):
self.set_persons(persons)
if assertion.is_listlike(stages):
self.set_stages(stages)
if assertion.is_listlike(days):
self.set_days(days)
if assertion.is_listlike(times):
self.set_times(times)
if assertion.is_listlike(items):
self.set_items(items)
if assertion.is_listlike(words):
self.set_words(words)
if assertion.is_listlike(rubis):
self.set_rubis(rubis)
def _packed_from_parsed(self, src: list) -> tuple:
return (re.split('[\t,]', v) for v in assertion.is_listlike(src))
def _set_objects(self, data: ListLike, func: Callable) -> None:
for line in assertion.is_listlike(data):
func(line[0], *line[1:])
def script_relieved_symbols(self, src: (list, tuple)) -> list:
return list(val for val in assertion.is_listlike(src) if not ('&' == val or '#' in val))
def script_relieved_strings(self, src: (list, tuple)) -> list:
return list(val for val in assertion.is_listlike(src) if isinstance(val, (int, str)))
def to_dialogue(self, src: (list, tuple), brackets: tuple=('「', '」')) -> str:
_ = "。".join(assertion.is_listlike(src))
return validate_string_duplicate_chopped(f'{brackets[0]}{_}{brackets[1]}')
def to_description(self, src: (list, tuple)) -> str:
_ = "。".join(assertion.is_listlike(src))
return validate_string_duplicate_chopped(f'{_}。')
def execute(self, src: TokenList) -> ResultData:
LOG.info('WORD_ANALYZER: start exec')
is_succeeded = True
error = None
tmp = assertion.is_listlike(self._exec_internal(src))
return ResultData(tmp, is_succeeded, error)
