o Xεi\#@sdZddlZddlZddlZddlZddlZddlZddlmZddl m Z ddl Z ddl m Z ddlmZddlmZedZe ejZGd d d eeZd d ZGd ddeZdejfddZedkrledSdS)zCommand-line interface to gruutN)Enum)Path) KNOWN_LANGS) TextProcessor) print_graphgruutc@s eZdZdZdZ dZ dZdS) StdinFormatzFormat of standard inputautolinesdocumentN)__name__ __module__ __qualname____doc__AUTOLINESDOCUMENTrrB/home/ubuntu/.local/lib/python3.10/site-packages/gruut/__main__.pyrsrc sdttjdkrtdgtttRtdntjddkr/ddlm }t|tdt j r=t j t jdnt j t jdt jrOd_tjjd }j r`t |jjrgj}n-tj}jtjkrvjrvtj}|tjkrtjg}ntj}t tj!rtd tj"d j#rt#j$tj%j&d }fd d}dfdd }nt'j(tj%dd}dd}ddd}||D]l\}}zG||jj) j*oԈj+ j, j- j. j/ j0 d \} } j rt1| | dddt|j2| | j3 j4 j5 d} || ||Wqt6y/} zt7|j8s%t9|| WYd} ~ qd} ~ wwdS)zMain entry pointz Languages:rz --version) __version__)levelespeak) default_lang model_prefixzReading input from stdin...)file delimiterc3s2tj|jd}|D] }|d}||fVq dS)Nrr)csvreader csv_delimiter)r r rowtextargsrr input_textcs  zmain..input_textNcsZt|}|jfdd|Dfdd|D}|j|||dS)Nc3s&|]}jdd|DVqdS)css|] }|jr|jVqdSN) is_spokenr#).0wrrr msz;main..output_sentences...N)word_separatorjoin)r)sentencer$rrr+ls  z1main..output_sentences..cs*g|]}|D] }|jrj|jqqSr)phonemesphoneme_separatorr-)r)r.r*r$rr rs z2main..output_sentences..)listappendsentence_separatorr-phoneme_word_separatorwriterow) sentenceswriter text_datar"r/r$rroutput_sentencesis zmain..output_sentencesT)flushcss|D]}|dfVqdSr'r)r linerrrr&s cSs"|D] }t|}||qdSr') dataclassesasdictwrite)r7r8r9r. sentence_dictrrrr:s  )ssmlpos phonemize post_processverbalize_numbersverbalize_currencyverbalize_datesverbalize_timescWstddd|DS)N css|]}t|VqdSr')str)r)arrrr+sz)main....)_LOGGERdebugr-) print_argsrrrszmain..) print_func) major_breaks minor_breaks punctuationsr'):lensysargvprintsortedr2rexitrrget_argsrMlogging basicConfigDEBUGINFOrLrrrlanguagesettingsr#rr stdin_formatrrArstdinreadosisattyfilenostderrrr8stdoutr! jsonlinesWriterno_pos no_lexiconno_g2pno_post_process no_numbers no_currencyno_datesno_timesrr7no_major_breaksno_minor_breaksno_punctuation Exception exceptionno_failTextProcessingError) rtext_processorr rar8r&r:r#r9graphrootr7err$rmain*s                r~c@seZdZdZdS)ryz3Raised when a line of input results in an exceptionN)r r rrrrrrrysryreturncCstjdd}|jddddd|jdd d d |jd d dd|jdddtDtjdd|jdd dd|jdd dd|jdd dd|jdd dd|jdd dd|jdd d d|jd!d d"d|jd#d d$d|jd%d d&d|jd'd d(d|jd)d d*d|jd+d d,d|jd-d d.d|jd/d0d1|jd2d d3d|jd4d5d6d|jd7d8d9d|jd:d;dd?d|jd@d;dAd|jdBd dCd|S)DzParse command-line argumentsr)progz-lz --languagezen-usz&Default language code (default: en-us))defaulthelpr#*z!Text to tokenize (default: stdin))nargsrz--ssml store_truezInput text is SSML)actionrz--stdin-formatcSsg|]}t|jqSr)rJvalue)r)vrrrr1szget_args..z$Format of stdin text (default: auto))choicesrrz --no-numbersz%Disable number replacement (1 -> one)z --no-currencyz/Disable currency replacement ($1 -> one dollar)z --no-dateszDDisable date replacement (4/1/2021 -> April first twenty twenty one)z --no-timesz4Disable time replacement (4:01pm -> four oh one P M)z--no-poszDisable part of speech taggerz --no-lexiconz Disable phoneme lexicon databasez--no-g2pz#Disable grapheme to phoneme guesserz--no-punctuationz2Don't output punctuations (quotes, brackets, etc.)z--no-major-breaksz9Don't output major breaks (periods, question marks, etc.)z--no-minor-breaksz4Don't output minor breaks (commas, semicolons, etc.)z--no-post-processz4Disable post-processing of sentences (e.g., liasons)z --no-failz Skip lines that result in errorsz--espeakz:Use eSpeak versions of lexicons (overrides --model-prefix)z--model-prefixzVSub-directory of gruut language data files with different lexicon, etc. (e.g., espeak))rz--csvz+Input text is id|text (see --csv-delimiter)z--csv-delimiter|z#Delimiter for input text with --csvz--sentence-separatorz. z/String used to separate sentences in CSV outputz--word-separatorrIz+String used to separate words in CSV outputz--phoneme-word-separator#z.String used to separate phonemes in CSV outputz--phoneme-separatorz4String used to separate words in CSV output phonemesz--debugzPrint DEBUG messages to console)argparseArgumentParser add_argumentrr parse_args)parserrrrrZs  rZ__main__)rrrr=r[rdrUenumrpathlibrri gruut.constrgruut.text_processorr gruut.utilsr getLoggerrL__file__parent_DIRrJrr~rvry NamespacerZr rrrrs.         y