U eR @sdZddlZddlZddlZddlmZddlmZmZm Z e e Z ddddd d d d d ddddg Z GdddeZd&ddZd'eeeeedddZddZddZddZdd ZddZdd Zd(d d Zd!d Zd"d Zd#dZd$dZd%dZdS))z A set of functions useful for customizing bibtex fields. You can find inspiration from these functions to design yours. Each of them takes a record and return the modified record. N)str)latex_to_unicodestring_to_latexprotect_uppercase splitnamegetnamesauthoreditorjournalkeywordlinkpage_double_hyphendoitypeconvert_to_unicodehomogenize_latex_encodingadd_plaintext_fieldsc@seZdZdZdS) InvalidNamez[Exception raised by :py:func:`customization.splitname` when an invalid name is input. N)__name__ __module__ __qualname____doc__rrx/mounts/lovelace/software/anaconda3/envs/qiime2-shotgun-2023.9/lib/python3.8/site-packages/bibtexparser/customization.pyrsrTcCstd}gg}gg}g}d}d}d}d} d} t|} | D]} | dkrt| } | |krf|| | } nN|r|d}| } d} n"|dkr| r| rd}nd}|| || q8| d kr|d7}|| d}d} d} q8d}| d kr,|r|d8}n |r td ||dd d} d} || q8|r| rH| svd} n.| rv|dkrv| rv| rrd}nd}|| q8| d ks| |kr|r|dd |g}|d|d}d} d} | d kr8t |dkr|g|gq8|r8td|q8|| |dkr8| r8| r8d}q8d}q8|rt|rXtd||rt|d |d8}qX|r|dd ||d||dst |dkr|rtd|| d| d|rt dd|DsiSggggd}t |dkr|d}t |dkr6||d<nt |dkrf|dd|d<|dd|d<n|d}d|kr| dt |}|ddd d d}|dkr|d8}|d||d<|||d|d<||dd|d<n |dd|d<|dd|d<n|d}|r2|dr2||d<t |dkr`|d}|r`|dr`||d<|d}t |dkr||d<nv|d}d|krt ||ddd d}|t |krd}|dd||d<|d|d|d<n |d|d<|S)a Break a name into its constituent parts: First, von, Last, and Jr. :param string name: a string containing a single name :param Boolean strict_mode: whether to use strict mode :returns: dictionary of constituent parts :raises `customization.InvalidName`: If an invalid name is given and ``strict_mode = True``. In BibTeX, a name can be represented in any of three forms: * First von Last * von Last, First * von Last, Jr, First This function attempts to split a given name into its four parts. The returned dictionary has keys of ``first``, ``last``, ``von`` and ``jr``. Each value is a list of the words making up that part; this may be an empty list. If the input has no non-whitespace characters, a blank dictionary is returned. It is capable of detecting some errors with the input name. If the ``strict_mode`` parameter is ``True``, which is the default, this results in a :class:`customization.InvalidName` exception being raised. If it is ``False``, the function continues, working around the error as best it can. The errors that can be detected are listed below along with the handling for non-strict mode: * Name finishes with a trailing comma: delete the comma * Too many parts (e.g., von Last, Jr, First, Error): merge extra parts into First * Unterminated opening brace: add closing brace to end of input * Unmatched closing brace: add opening brace at start of word z ~ rFTN\{}z(Unmatched closing brace in name {{{0}}}.,z$Too many commas in the name {{{0}}}.z/Unterminated opening brace in the name {{{0}}}.z&Trailing comma at end of name {{{0}}}.css|]}t|VqdSN)bool).0sectionrrr szsplitname..)firstlastvonjrr(r'r)r*)setiternextappendisalphaisupperrformatinsertjoinlenpopanyindex)name strict_mode whitespacesectionsZcaseswordcaselevelZ bracestartZ controlseqZ specialcharZnameitercharescapedpartsZp0ZfirstlZlastlr'r*r(Zlcasessplitrrrrs(                           )textopeningclosingignore_escapedreturnc CsHg}g}|rd|}d|}t||D]}||dq(t||D]}|d|dqLt|dkrt|dkriSt|t|krtd|d|dt||ddd }i}g} |D]P}|dkr| |qt| dkrtd |d |d | } d||| <qt| dkrDtd |d| d |S)af Find matching 'brackets'. :param text: The string to consider. :param opening: The opening bracket (e.g. "(", "[", "{"). :param closing: The closing bracket (e.g. ")", "]", "}"). :param ignore_escaped: Ignore escaped bracket (e.g. "\(", "\[", "\{", "\)", "\]", "\}"). :return: Dictionary with ``{index_opening: index_closing}`` z(?Qzfind_matching..)keyz No closing z at: dz No opening z at )refinditerr0spanr6 IndexErrorsortedr7) rErFrGrHabrKbracketsretstackjrrr find_matching.s4 r[c Csg}|D]}|}t|dkr$qd|kr\|dd}|d}dd|dD}nd|kr*d|kr*zt|dd}Wn"tk r||YqYnXg}d}d}||kr||}n|d7}|t|krڐq2||dkr|||||d}q|t|dkr|||d qn|}|}d d|D}|d krZ|}|D] } | d kr^|d|}q^||d d|q|S)a^Convert people names as surname, firstnames or surname, initials. :param names: a list of names :type names: list :returns: list -- Correctly formated names .. Note:: This function is known to be too simple to handle properly the complex rules. We would like to enhance this in forthcoming releases. rrrcSsg|] }|qSrstripr$rKrrr zszgetnames..rr NcSsg|]}|ddqS).z. )replacer]r^rrrr_s)Zjnrr*Zjunior)Zbenvanderdelalez, )r]r6rDr[rSr0r7r5) namesZ tidynamesZ namestringZ namesplitr(ZfirstsrWstartrKitemrrrresL            cCsLd|krH|drBtddtjd|dddtjdD|d<n|d=|S)z Split author field into a list of "Name, Surname". :param record: the record. :type record: dict :returns: dict -- the modified record. rcSsg|] }|qSrr\r^rrrr_szauthor..z\ and\  r`)flags)rrPrDrb IGNORECASErecordrrrrs cCsZd|krV|drPtdd|ddddD|d<dd|dD|d<n|d=|S)z Turn the editor field into a dict composed of the original editor name and a editor id (without coma or blank). :param record: the record. :type record: dict :returns: dict -- the modified record. r cSsg|] }|qSrr\r^rrrr_szeditor..rkr`z and cSs.g|]&}||dddddddqS)rr r`rar:IDrbr^rrrr_s)rrbrDrnrrrr s ( csfd|krbddddddg}|D]D|dkrfdd |dD}|d d |d |d<q|S) z Separate pages by a double hyphen (--). :param record: the record. :type record: dict :returns: dict -- the modified record. Zpagesu‐u‑u–u—-u−csg|]}|qSrr\r^ separatorrrr_sz&page_double_hyphen..rz--r)rD)ro separatorsprrtrr s  cCsd|kr|d|d<|S)z Put the type into lower case. :param record: the record. :type record: dict :returns: dict -- the modified record. r)lowerrnrrrrs cCsBd|kr>|dr>|d|dddddddd|d<|S)z Turn the journal field into a dict composed of the original journal name and a journal id (without coma or blank). :param record: the record. :type record: dict :returns: dict -- the modified record. r rr r`rarprrrnrrrr s  ,|;cCs2d|kr.ddt||dddD|d<|S)z Split keyword field into a list. :param record: the record. :type record: dict :param sep: pattern used for the splitting regexp. :type record: string, optional :returns: dict -- the modified record. r cSsg|] }|qSrr\r^rrrr_szkeyword..rkr )rPrDrb)roseprrrr s &cCsd|krdd|ddD}g|d<|D]h}|d}d|di}t|dkr^|d|d <t|d krv|d |d <t|ddkr,|d|q,|S) h :param record: the record. :type record: dict :returns: dict -- the modified record. r cSsg|]}|ddqS)z r`)r]rbr^rrrr_szlink..rkr`urlrranchorr+r3)rDr6r0)rolinksr rCZlinkobjrrrr s      cCsld|krhd|krg|d<d}|dD]}d|kr$d}q$|rh|d}|drTd|}|d|dd|S)r{rr TF10zhttps://doi.org/)r|r}) startswithr0)roZnodoirjr rrrr"s  cCsn|D]d}t||tr.dd||D||<qt||trXdd||D||<qt||||<q|S)z Convert accent from latex to unicode style. :param record: the record. :type record: dict :returns: dict -- the modified record. cSsg|] }t|qSrrr$xrrrr_Csz&convert_to_unicode..cSsi|]\}}|t|qSrr)r$kvrrr Gsz&convert_to_unicode..) isinstancelistdictitemsrrovalrrrr9s  cCst|}|D]}|dkr td|t||trJdd||D||<n0t||trjt||||<ntd|t |dkr tdtd||t ||||<td ||q |S) z Homogenize the latex enconding style for bibtex This function is experimental. :param record: the record. :type record: dict :returns: dict -- the modified record. )rqzApply string_to_latex to: %scSsg|] }t|qSr)rrrrrr_`sz-homogenize_latex_encoding..zDUnable to homogenize latex encoding for %s: Expected string or list,titlezProtect uppercase in titlez Before: %sz After: %s) rloggerdebugrrrrwarningswarnRuntimeWarningrrrrrrOs&     csddt|D]}d|}||||<t||trN||||<qt||tr|fdd||D||<qt||trfdd||D||<q|S)a% For each field in the record, add a `plain_` field containing the plaintext, stripped from braces and similar. See https://github.com/sciunto-org/python-bibtexparser/issues/116. :param record: the record. :type record: dict :returns: dict -- the modified record. cSsdD]}||d}q|S)N)rrr rr)stringstrippedrrr _strip_string{sz+add_plaintext_fields.._strip_stringzplain_{}csi|]\}}||qSrr)r$subkeyvaluerrrrsz(add_plaintext_fields..csg|] }|qSrr)r$rrrrr_sz(add_plaintext_fields..)rkeysr3rrrr)rorNZ plain_keyrrrrps       )T)T)ry) rloggingrPrbuiltinsrZbibtexparser.latexencrrr getLoggerrr__all__ ValueErrorrrr#rr[rrr r rr r r rrrrrrrrsN     79 !