gJdZddlZddlZddlmZddlmZddlddlm Z m Z m Z GddZ Gd d Z Gd d e Zy) z API for corpus readers. N) defaultdict)chain)*)FileSystemPathPointer PathPointerZipFilePathPointercxeZdZdZddZdZdZdZdZdZ d Z d Z dd Z dd Z d ZdZdZeedZy) CorpusReadera A base class for "corpus reader" classes, each of which can be used to read a specific corpus format. Each individual corpus reader instance is used to read a specific corpus, consisting of one or more files under a common root directory. Each file is identified by its ``file identifier``, which is the relative path to the file from the root directory. A separate subclass is defined for each corpus format. These subclasses define one or more methods that provide 'views' on the corpus contents, such as ``words()`` (for a list of words) and ``parsed_sents()`` (for a list of parsed sentences). Called with no arguments, these methods will return the contents of the entire corpus. For most corpora, these methods define one or more selection arguments, such as ``fileids`` or ``categories``, which can be used to select which portion of the corpus should be returned. Nc>t|trTt|tsDtjd|}|j \}}|r t ||}n't|}nt|ts tdt|tr t||}||_ ||_ d|_ d|_ d|_t|tr>i}|jD]+} |D]$} | \} } tj| | s| || <+-|}||_ ||_y)a. :type root: PathPointer or str :param root: A path pointer identifying the root directory for this corpus. If a string is specified, then it will be converted to a ``PathPointer`` automatically. :param fileids: A list of the files that make up this corpus. This list can either be specified explicitly, as a list of strings; or implicitly, as a regular expression over file paths. The absolute path for each file will be constructed by joining the reader's root to each file name. :param encoding: The default unicode encoding for the files that make up the corpus. The value of ``encoding`` can be any of the following: - A string: ``encoding`` is the encoding name for all files. - A dictionary: ``encoding[file_id]`` is the encoding name for the file whose identifier is ``file_id``. If ``file_id`` is not in ``encoding``, then the file contents will be processed using non-unicode byte strings. - A list: ``encoding`` should be a list of ``(regexp, encoding)`` tuples. The encoding for a file whose identifier is ``file_id`` will be the ``encoding`` value for the first tuple whose ``regexp`` matches the ``file_id``. If no tuple's ``regexp`` matches the ``file_id``, the file contents will be processed using non-unicode byte strings. - None: the file contents of all files will be processed using non-unicode byte strings. :param tagset: The name of the tagset used by this corpus, to be used for normalizing or converting the POS tags returned by the ``tagged_...()`` methods. z(.*\.zip)/?(.*)$|z0CorpusReader: expected a string or a PathPointerREADMELICENSEz citation.bibN) isinstancestrrrematchgroupsrr TypeErrorfind_corpus_fileids_fileids_root_readme_license _citationlist _encoding_tagset) selfrootfileidsencodingtagsetmzipfilezipentry encoding_dictfileidxregexpencs K/var/www/openai/venv/lib/python3.12/site-packages/nltk/corpus/reader/api.py__init__zCorpusReader.__init__)sB dC D+)F-t4A ! GX)'8<,T2D+.NO O gs #)$8G   1 ! ' h %M--!A$%MVSxx/03 f- "( %H! 9 ct|jtr:|jjjd|jj }nd|jj z}d|jjd|dS)N/z%s) rrrr#filenameentrypath __class____name__)rr3s r*__repr__zCorpusReader.__repr__uso djj"4 5jj((112!DJJ4D4D3EFD$**//)D4>>**+4xq99r,cy)z Load this corpus (if it has not already been loaded). This is used by LazyCorpusLoader as a simple method that can be used to make sure a corpus is loaded -- e.g., in case a user wants to do help(some_corpus). Nrs r* ensure_loadedzCorpusReader.ensure_loaded|s r,c|j|j5}|jcdddS#1swYyxYw)zN Return the contents of the corpus README file, if it exists. N)openrreadrfs r*readmezCorpusReader.readmes+YYt|| $668% $ $6?c|j|j5}|jcdddS#1swYyxYw)zO Return the contents of the corpus LICENSE file, if it exists. N)r<rr=r>s r*licensezCorpusReader.licenses+YYt}} %668& % %rAc|j|j5}|jcdddS#1swYyxYw)zT Return the contents of the corpus citation.bib file, if it exists. N)r<rr=r>s r*citationzCorpusReader.citations+YYt~~ &!668' & &rAc|jS)ze Return a list of file identifiers for the fileids that make up this corpus. )rr9s r*rzCorpusReader.fileidss }}r,c8|jj|S)z Return the absolute path for the given file. :type fileid: str :param fileid: The file identifier for the file whose path should be returned. :rtype: PathPointer )rjoin)rr&s r*abspathzCorpusReader.abspathszzv&&r,c | |j}nt|tr|g}|Dcgc]}|jj |}}|r5|r3t t ||Dcgc]}|j|c}|S|rt t ||S|r2t t ||Dcgc]}|j|c}S|Scc}wcc}wcc}w)a Return a list of the absolute paths for all fileids in this corpus; or for the given list of fileids, if specified. :type fileids: None or str or list :param fileids: Specifies the set of fileids for which paths should be returned. Can be None, for all fileids; a list of file identifiers, for a specified set of fileids; or a single file identifier, for a single file. Note that the return value is always a list of paths, even if ``fileids`` is a single file identifier. :param include_encoding: If true, then return a list of ``(path_pointer, encoding)`` tuples. :rtype: list(PathPointer) )rrrrrHrzipr )rrinclude_encodinginclude_fileidr?pathss r*abspathszCorpusReader.abspathss$ ?mmG  %iG-45W#W5 Eg#FgDMM!$4g#FPQ Q E7+, , Eg#FgDMM!$4g#FGH HL6$G$Gs"CC*Cc| |j}nt|tr|g}g}|D];}|j|5}|j |j ddd=t |S#1swYRxYw)z :param fileids: A list specifying the fileids that should be used. :return: the given file(s) as a single string. :rtype: str N)rrrr<appendr=concat)rrcontentsr?fps r*rawzCorpusReader.rawsm ?mmG  %iGA1 *hs A00A9 c||j|}|jj|j|}|S)a Return an open stream that can be used to read the given file. If the file's encoding is not None, then the stream will automatically decode the file's contents into unicode. :param file: The file identifier of the file to read. )r rrHr<)rfiler streams r*r<zCorpusReader.opens4==&&++H5 r,ct|jtr|jj|S|jS)z Return the unicode encoding for the given corpus file, if known. If the encoding is unknown, or if the given file should be processed using byte strings (str), then return None. )rrdictget)rrWs r*r zCorpusReader.encodings1 dnnd +>>%%d+ +>> !r,c|jSN)rr9s r* _get_rootzCorpusReader._get_roots zzr,zO The directory where this corpus is stored. :type: PathPointer)doc)utf8N)NFFr])r5 __module__ __qualname____doc__r+r6r:r@rCrErrIrOrUr<r r^propertyrr8r,r*r r s_$JX:  ' D  "   Dr,r cteZdZdZdZdZdZd dZd fd ZdZ d fd Z d fd Z d fd Z d fd Z xZS)CategorizedCorpusReadera A mixin class used to aid in the implementation of corpus readers for categorized corpora. This class defines the method ``categories()``, which returns a list of the categories for the corpus or for a specified set of fileids; and overrides ``fileids()`` to take a ``categories`` argument, restricting the set of fileids to be returned. Subclasses are expected to: - Call ``__init__()`` to set up the mapping. - Override all view methods to accept a ``categories`` parameter, which can be used *instead* of the ``fileids`` parameter, to select which fileids should be included in the returned view. c*d|_d|_d|_d|_d|_d|_d|vr|d|_|d=n@d|vr|d|_|d=n.d|vr|d|_|d=d|vr|d|_|d=n t dd|vsd|vsd|vr t dy)a/ Initialize this mapping based on keyword arguments, as follows: - cat_pattern: A regular expression pattern used to find the category for each file identifier. The pattern will be applied to each file identifier, and the first matching group will be used as the category label for that file. - cat_map: A dictionary, mapping from file identifiers to category labels. - cat_file: The name of a file that contains the mapping from file identifiers to categories. The argument ``cat_delimiter`` can be used to specify a delimiter. The corresponding argument will be deleted from ``kwargs``. If more than one argument is specified, an exception will be raised. N cat_patterncat_mapcat_file cat_delimiterz=Expected keyword argument cat_pattern or cat_map or cat_file.z7Specify exactly one of: cat_pattern, cat_map, cat_file.)_f2c_c2f_pattern_map_file _delimiter ValueError)rkwargss r*r+z CategorizedCorpusReader.__init__s*      F ""=1DM}% & y)DIy! 6 ! +DJz"&("("9?+R  F "i6&9Z6=QL >Rr,c ftt|_tt|_|jS|j D]C}t j|j|jd}|j||Ey|j<|jjD]\}}|D]}|j|| y|j|j|j5}|jD]}|j}|j!|j"d\}}||j%vrt'd|jd|d|j!|j"D]}|j|| dddyy#1swYyxYw)NzIn category mapping file z: z not found)rsetrlrmrnrrrgroup_addroitemsrpr< readlinesstripsplitrqrrr)rfile_idcategory categoriesr?lines r*_initzCategorizedCorpusReader._initKsW$ $ == $==88DMM7;AA!D '8,)YY "'+yy'8# *HIIgx0!+(9ZZ #4::&!KKMD::z5CategorizedCorpusReader.categories..us!@1$))A,)rlrsortedrmrrrvunion)rrs` r*rz"CategorizedCorpusReader.categoriesjsW 99  JJL ?$))$ $ gs #iGcii!@!@ABBr,cf|tSt|trPjj |j vrtj |Std|zjj ttjfd|DS)z Return a list of file identifiers for the files that make up this corpus, or that make up the given category(s) if specified. zCategory %s not foundc3<K|]}j|ywr])rm)rcrs r*rz2CategorizedCorpusReader.fileids..s%GJqdiilJr) superrrrrlrrmrrrrvr)rrr4s` r*rzCategorizedCorpusReader.fileidsws  7?$ $  C (yy  TYY&dii 344 !8:!EFFyy  #))%GJ%GHI Ir,cJ| | td||j|S|S)Nz'Specify fileids or categories, not both)rrr)rrrs r*_resolvez CategorizedCorpusReader._resolves3  :#9FG G  !<< + +Nr,cBt||j||Sr])rrUrrrrr4s r*rUzCategorizedCorpusReader.rawsw{4==*=>>r,cBt||j||Sr])rwordsrrs r*rzCategorizedCorpusReader.wordsw}T]]7J?@@r,cBt||j||Sr])rsentsrrs r*rzCategorizedCorpusReader.sentsrr,cBt||j||Sr])rparasrrs r*rzCategorizedCorpusReader.parasrr,r]NN)r5rarbrcr+rrxrrrrUrrr __classcell__)r4s@r*rfrfsF"1f56) CJ&?AAAAr,rfcreZdZdZdZdZdZdZddZddZ dd Z dd Z dd Z d Z dd ZdZddZdZy)SyntaxCorpusReaderaH An abstract base class for reading corpora consisting of syntactically parsed text. Subclasses should define: - ``__init__``, which specifies the location of the corpus and a method for detecting the sentence blocks in corpus files. - ``_read_block``, which reads a block from the input stream. - ``_word``, which takes a block and returns a list of list of words. - ``_tag``, which takes a block and returns a list of list of tagged words. - ``_parse``, which takes a block and returns a list of parsed sentences. ctr]NotImplementedErrorrss r*_parsezSyntaxCorpusReader._parse !##r,ctr]rrs r*_wordzSyntaxCorpusReader._wordrr,ctr]rrs r*_tagzSyntaxCorpusReader._tagrr,ctr]rrrXs r* _read_blockzSyntaxCorpusReader._read_blockrr,Nc |j}t|j|dDcgc]\}}t|||c}}Scc}}wNTr )_read_parsed_sent_blockrRrOStreamBackedCorpusViewrrreaderr&r)s r* parsed_sentszSyntaxCorpusReader.parsed_sentssT--$(==$#? #?KFC'vvD#?    A c fd}tj|dDcgc]\}}t|||c}}Scc}}w)Nc(j|Sr])_read_tagged_sent_blockrXrr!s r*rz/SyntaxCorpusReader.tagged_sents..reader//? ?r,TrrRrOrrrr!rr&r)s` ` r* tagged_sentszSyntaxCorpusReader.tagged_sentsR @$(==$#? #?KFC'vvD#?    A c |j}t|j|dDcgc]\}}t|||c}}Scc}}wr)_read_sent_blockrRrOrrs r*rzSyntaxCorpusReader.sentssT&&$(==$#? #?KFC'vvD#?    rc fd}tj|dDcgc]\}}t|||c}}Scc}}w)Nc(j|Sr])_read_tagged_word_blockrs r*rz/SyntaxCorpusReader.tagged_words..readerrr,Trrrs` ` r* tagged_wordszSyntaxCorpusReader.tagged_wordsrrc t|j|dDcgc]\}}t||j|c}}Scc}}wr)rRrOr_read_word_block)rrr&r)s r*rzSyntaxCorpusReader.wordssO$(==$#? #?KFC'vt/D/DsS#?    s"A c\ttj|j|Sr])rr from_iterablerrs r*rz#SyntaxCorpusReader._read_word_blocks#E''(=(=f(EFGGr,c^ttj|j||Sr])rrrr)rrXr!s r*rz*SyntaxCorpusReader._read_tagged_word_blocks%E''(D(DVV(TUVVr,c ttd|j|Dcgc]}|j|c}Scc}wr])rfilterrrrrXts r*rz#SyntaxCorpusReader._read_sent_blocks;F49I9I&9Q!R9QA$**Q-9Q!RSTT!RAc ttd|j|Dcgc]}|j||c}Scc}wr])rrrr)rrXr!rs r*rz*SyntaxCorpusReader._read_tagged_sent_blocksC 48H8H8PQ8P1$))Av.8PQ R  QsAc ttd|j|Dcgc]}|j|c}Scc}wr])rrrrrs r*rz*SyntaxCorpusReader._read_parsed_sent_blocks;F4$:J:J6:R!S:RQ$++a.:R!STUU!Srr]r)r5rarbrcrrrrrrrrrrrrrrr8r,r*rrsQ $$$$       HWU Vr,r)rcosr collectionsr itertoolsrnltk.corpus.reader.util nltk.datarrrr rfrr8r,r*rsM #%LLhh`VAVA~]V]Vr,