U d3@s dZddlZddlZddlZddlZddlmZddl Z ddl m Z m Z m Z m Z mZmZedZdddd d d Ze eefed d dZe eefed ddZe ed ddZe eefe d ddZeed ddZd?e eefeedddZe jd@e eefdeedddZe jdAe eefeeedddZdBe eefe eee eefdd dZdCe eefeee eeefd"d#d$ZeedfZ e jeed d%d&Z!e jeed d'd&Z!e jddd d(d&Z!e deefe ed d)d&Z!eedfZ"e jeed d*d+Z#e jeed d,d+Z#e jddd d-d+Z#e deefe ed d.d+Z#e#Z$e#Z%e#Z&e e d/d0d1Z'ee#d2Z(d!d3d!d4d5gfe eefee eeegeffeeeed6d7d8Z)e j*ed9d:d;Z+e eefd<d=d>Z,e,Z-dS)DzEscaping/unescaping methods for HTML, JSON, URLs, and others. Also includes a few other miscellaneous string manipulation functions that have crept in over time. N) unicode_type)UnionAnyOptionalDictListCallablez[&<>"']z&z<z>z"z')&<>"')valuereturncCstddt|S)a0Escapes a string so it is valid within HTML or XML. Escapes the characters ``<``, ``>``, ``"``, ``'``, and ``&``. When used in attribute values the escaped strings must be enclosed in quotes. .. versionchanged:: 3.2 Added the single quote to the list of escaped characters. cSst|dS)Nr)_XHTML_ESCAPE_DICTgroup)matchr2/tmp/pip-unpacked-wheel-fekwu36z/tornado/escape.py7zxhtml_escape..)_XHTML_ESCAPE_REsub to_basestringrrrr xhtml_escape+s rcCstdtt|S)z!Un-escapes an XML-escaped string.z &(#?)(\w+?);)rer_convert_entity_unicoderrrrxhtml_unescape;srcCst|ddS)z%JSON-encodes the given Python object.zReplace all sequences of whitespace chars with a single space.z [\x00-\x20]+ )rrstriprrrrsqueezeVsr(T)rplusrcCs |r tjjntjj}|t|S)aiReturns a URL-encoded version of the given value. If ``plus`` is true (the default), spaces will be represented as "+" instead of "%20". This is appropriate for query strings but not for the path component of a URL. Note that this default is the reverse of Python's urllib module. .. versionadded:: 3.1 The ``plus`` argument )urllibparse quote_plusquoteutf8)rr)r-rrr url_escape[s r/)rencodingr)rcCsdSNrrr0r)rrr url_unescapejsr3utf-8cCsdSr1rr2rrrr3oscCsP|dkr(|rt|dd}tj|S|r4tjjntjj}|t||dSdS)a^Decodes the given value from a URL. The argument may be either a byte or unicode string. If encoding is None, the result will be a byte string. Otherwise, the result is a unicode string in the specified encoding. If ``plus`` is true (the default), plus signs will be interpreted as spaces (literal plus signs must be represented as "%2B"). This is appropriate for query strings and form-encoded values but not for the path component of a URL. Note that this default is the reverse of Python's urllib module. .. versionadded:: 3.1 The ``plus`` argument N+r&)r0)rr"r*r+unquote_to_bytes unquote_plusunquote)rr0r)r8rrrr3vs  F)qskeep_blank_valuesstrict_parsingrcCsVt|tr|d}tjj|||ddd}i}|D]\}}dd|D||<q6|S)a/Parses a query string like urlparse.parse_qs, but takes bytes and returns the values as byte strings. Keys still become type str (interpreted as latin1 in python3!) because it's too painful to keep them as byte strings in python3 and in practice they're nearly always ascii anyway. latin1strict)r0errorscSsg|]}|dqS)r<)encode.0irrr sz"parse_qs_bytes..) isinstancebytesdecoder*r+parse_qsitems)r9r:r;resultencodedkvrrrparse_qs_bytess  rMcCsdSr1rrrrrr.sr.cCsdSr1rrrrrr.scCsdSr1rrrrrr.scCs2t|tr|St|ts(tdt||dS)zConverts a string argument to a byte string. If the argument is already a byte string or None, it is returned unchanged. Otherwise it must be a unicode string and is encoded as utf8. (Expected bytes, unicode, or None; got %rr4)rD _UTF8_TYPESr TypeErrortyper?rrrrr.s   cCsdSr1rrrrr to_unicodesrRcCsdSr1rrrrrrRscCsdSr1rrrrrrRscCs2t|tr|St|ts(tdt||dS)zConverts a string argument to a unicode string. If the argument is already a unicode string or None, it is returned unchanged. Otherwise it must be a byte string and is decoded as utf8. rNr4)rD_TO_UNICODE_TYPESrErPrQrFrrrrrRs   )objrcCsrt|tr tdd|DSt|trsz$recursive_unicode..css|]}t|VqdSr1rUr@rrrrWscss|]}t|VqdSr1rUr@rrrrWsN)rDdictrHlisttuplerErR)rTrrrrVs    rVz\b((?:([\w-]+):(/{1,3})|www[.])(?:(?:(?:[^\s&()]|&|")*(?:[^!"#$%&'()*+,.:;<=>?@\[\]^`{|}~\s]))|(?:\((?:[^\s&()]|&|")*\)))+)httphttps)textshorten extra_paramsrequire_protocolpermitted_protocolsrcsLrtsdtjtdfdd }tt|}t||S)aConverts plain text into HTML with links. For example: ``linkify("Hello http://tornadoweb.org!")`` would return ``Hello http://tornadoweb.org!`` Parameters: * ``shorten``: Long urls will be shortened for display. * ``extra_params``: Extra text to include in the link tag, or a callable taking the link as an argument and returning the extra text e.g. ``linkify(text, extra_params='rel="nofollow" class="external"')``, or:: def extra_params_cb(url): if url.startswith("http://example.com"): return 'class="internal"' else: return 'class="external" rel="nofollow"' linkify(text, extra_params=extra_params_cb) * ``require_protocol``: Only linkify urls which include a protocol. If this is False, urls such as www.facebook.com will also be linkified. * ``permitted_protocols``: List (or set) of protocols which should be linkified, e.g. ``linkify(text, permitted_protocols=["http", "ftp", "mailto"])``. It is very unsafe to include protocols such as ``javascript``. r&mrc s|d}|d}r |s |S|r0|kr0|S|d}|sFd|}tr`d|}n}d}r|t||kr||}|rt|dt|dpd}nd}||dd }t|dkr|d||dd |ddd d dd d}t||d kr"|d|}||kr||d} | |dkrP|d| }|d7}t|t|krp|}n |d|7}d|||fS)Nzhttp://r&r[r/?.g?r z...z title="%s"z%s)rcallabler'lensplitrfind) rdurlprotohrefparamsmax_lenZ before_clipZ proto_lenpartsampr`rbrar_rr make_link:sN      "     zlinkify..make_link) rnr'typingMatchstrrr_URL_REr)r^r_r`rarbrzrryrlinkifys $  > rrccCs|ddkrzP|ddddkrHtt|ddddWStt|dWSWn"tk rd|dYSXzt|dWStk rd|dYSXdS)Nre#rfxz&#%s;z&%s;)rlowerchrint ValueError_HTML_UNICODE_MAPKeyError)rdrrrr|sr)rcCs*i}tjjD]\}}t|||<q|Sr1)htmlentitiesname2codepointrHr)Z unicode_mapnamerrrr_build_unicode_mapsr)T)T)r4T)r4T)FF).__doc__ html.entitiesrr r urllib.parser*Z tornado.utilrr{rrrrrrcompilerrr}rErrr#r%r(boolr/overloadr3rMrQrOr.rSrRrZ native_strrrVr~rr|rrrrrrrs                i