korsygfhrtzangaiide
Elepffwdsff
/
lib64
/
python2.7
/
site-packages
/
mercurial
/
Upload FileeE
HOME
� Hq�Qc @ sm d d l Z d d l Z d d l Z d d l Z d � Z i d � d 6d � d 6e d 6Z yI e j j d � Z e s� e j � p� d Z e j e d � � � Z n Wn e j k r� d Z n Xe j j d d � Z d Z d e f d � � YZ d � Z d � Z e j j d d � d k r$d p'd Z d � Z d � Z d � Z d � Z d � Z d � Z d � Z d S( i����Nc C sx y t j Wn t k r) t j � d SXt j t j � } t j t j d � t j t j � } t j t j | � | S( s� On darwin, getpreferredencoding ignores the locale environment and always returns mac-roman. http://bugs.python.org/issue6202 fixes this for Python 2.7 and up. This is the same corrected code for earlier Python versions. However, we can't use a version check for this method, as some distributions patch Python to fix this. Instead, we use it as a 'fixer' for the mac-roman encoding, as it is unlikely that this encoding is the actually expected. i t ( t localet CODESETt AttributeErrort getdefaultlocalet setlocalet LC_CTYPEt nl_langinfo( t oldloct result( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt _getpreferredencoding s c C s d S( Nt ascii( ( ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt <lambda>$ s t 646c C s d S( NR ( ( ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyR % s s ANSI_X3.4-1968s mac-romant HGENCODINGR c C s t S( N( t encoding( ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyR - s t HGENCODINGMODEt stricts ISO-8859-1t localstrc B s e Z d Z d � Z d � Z RS( sd This class allows strings that are unmodified to be round-tripped to the local encoding and backc C s t j | | � } | | _ | S( N( t strt __new__t _utf8( t clst ut lt s( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyR 6 s c C s t | j � S( N( t hashR ( t self( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt __hash__: s ( t __name__t __module__t __doc__R R ( ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyR 3 s c C s) y� y[ | j d � } t d k r% | S| j t d � } | | j t � k rP | St | | � SWn� t k r� yT | j t � } | j t d � } | | j t � k r� | St | j d � | � SWq� t k r� | j d d � } | j t d � SXn XWn( t k r$} t j | d d �� n Xd S( s� Convert a string from internal UTF-8 to local encoding All internal strings should be UTF-8 but some repos before the implementation of locale support may contain latin1 or possibly other character sets. We attempt to decode everything strictly using UTF-8, then Latin-1, and failing that, we use UTF-8 and replace unknown characters. The localstr class is used to cache the known UTF-8 encoding of strings next to their local representation to allow lossless round-trip conversion back to UTF-8. >>> u = 'foo: \xc3\xa4' # utf-8 >>> l = tolocal(u) >>> l 'foo: ?' >>> fromlocal(l) 'foo: \xc3\xa4' >>> u2 = 'foo: \xc3\xa1' >>> d = { l: 1, tolocal(u2): 2 } >>> len(d) # no collision 2 >>> 'foo: ?' in d False >>> l1 = 'foo: \xe4' # historical latin1 fallback >>> l = tolocal(l1) >>> l 'foo: ?' >>> fromlocal(l) # magically in utf-8 'foo: \xc3\xa4' s UTF-8t replaces utf-8t hints! please check your locale settingsN( t decodeR t encodeR t UnicodeDecodeErrort fallbackencodingt LookupErrort errort Abort( R R t rt k( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt tolocal= s* " c C s� t | t � r | j Sy | j t t � j d � SWnw t k r� } | t d | j d � | j d !} t j d | | f � � n( t k r� } t j | d d �� n Xd S( s� Convert a string from the local character encoding to UTF-8 We attempt to decode strings using the encoding mode set by HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown characters will cause an error message. Other modes include 'replace', which replaces unknown characters with a special Unicode character, and 'ignore', which drops the character. s utf-8i i s decoding near '%s': %s!R! s! please check your locale settingsN( t isinstanceR R R" R t encodingmodeR# R$ t maxt startR' R( R& ( R t instt subR* ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt fromlocalz s $ t HGENCODINGAMBIGUOUSt narrowt widet WFAt WFc C s t | j t d � � S( sC Find the column width of a string for display in the local encodingR ( t ucolwidthR" R ( R ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt colwidth� s c C s] t t d d � } | d k rS t g | D]$ } | | � t k rF d pI d ^ q( � St | � S( s5 Find the column width of a Unicode string for displayt east_asian_widthi i N( t getattrt unicodedatat Nonet sumR5 t len( t dt eawt c( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyR8 � s 5c C sK xD t | | t | � � D]) } | | | !} t | � | k r | Sq Wd S( sO Use colwidth to find a c-column substring of s starting at byte index startN( t xrangeR? R9 ( R R/ RB t xt t( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt getcols� s c C s� y | j d � | j � SWn t k r. n Xyc t | t � rV | j j d � } n | j t t � } | j � } | | k r� | S| j t � SWn? t k r� | j � St k r� } t j | d d �� n Xd S( s9 best-effort encoding-aware case-folding of local string sR s utf-8R! s! please check your locale settingsN( R" t lowerR$ R, R R R R- R# t UnicodeErrorR& R' R( ( R R t luR* ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyRG � s" c C s� y | j d � | j � SWn t k r. n Xyc t | t � rV | j j d � } n | j t t � } | j � } | | k r� | S| j t � SWn? t k r� | j � St k r� } t j | d d �� n Xd S( s9 best-effort encoding-aware case-folding of local string sR s utf-8R! s! please check your locale settingsN( R" t upperR$ R, R R R R- R# RH R& R' R( ( R R t uuR* ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyRJ � s" c C s� t | t � r | j Sy | j d � r, | SWn� t k r� | j d d � j d � } d } d } x_ | D]W } | | | d !| k r� | | 7} | d 7} qk | t d t | � � j d � 7} qk W| SXd S( s� convert a local, possibly-binary string into UTF-8b This is intended as a generic method to preserve data when working with schemes like JSON and XML that have no provision for arbitrary byte strings. As Mercurial often doesn't know what encoding data is in, we use so-called UTF-8b. If a string is already valid UTF-8 (or ASCII), it passes unmodified. Otherwise, unsupported bytes are mapped to UTF-16 surrogate range, uDC00-uDCFF. Principles of operation: - ASCII and UTF-8 data successfully round-trips and is understood by Unicode-oriented clients - filenames and file contents in arbitrary other encodings can have be round-tripped or recovered by clueful clients - local strings that have a cached known UTF-8 encoding (aka localstr) get sent as UTF-8 so Unicode-oriented clients get the Unicode data they want - because we must preserve UTF-8 bytestring in places such as filenames, metadata can't be roundtripped without help (Note: "UTF-8b" often refers to decoding a mix of valid UTF-8 and arbitrary bytes into an internal Unicode format that can be re-encoded back into the original. Here we are exposing the internal surrogate encoding as a UTF-8 string.) s utf-8t ignoreR i i i � N( R, R R R" R$ R# t unichrt ord( R t s2R) t posRB ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt toutf8b� s 'c C s� d | k r | S| j d � } d } xT | D]L } t | � d @d k re | t t | � d @� 7} q, | | j d � 7} q, W| S( st Given a UTF-8b string, return a local, possibly-binary string. return the original binary string. This is a round-trip process for strings like filenames, but metadata that's was passed through tolocal will remain in UTF-8. >>> m = "\xc3\xa9\x99abcd" >>> n = toutf8b(m) >>> n '\xc3\xa9\xed\xb2\x99abcd' >>> fromutf8b(n) == m True s �s utf-8R i � i � i� ( R" RN t chrR# ( R R R) RB ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt fromutf8b s ( R' R< R t osR t _encodingfixerst environt getR t getpreferredencodingt ErrorR- R% R R R+ R2 R5 R9 R8 RF RG RJ RQ RS ( ( ( s8 /usr/lib64/python2.7/site-packages/mercurial/encoding.pyt <module> s6 $ = 1