def test_wordcollector():
    doc = utils.new_document(b('test data'), settings)
    doc['file'] = 'dummy'
    parser.parse(FILE_CONTENTS, doc)

    ix = IndexBuilder(None, 'en', {}, None)
    ix.feed('filename', 'title', doc)
    assert 'boson' not in ix._mapping
    assert 'fermion' in ix._mapping

def get_js_index(app, curdoc):
    """
    Get the JS index of a sub-doc from the file
    """
    from sphinx.search import IndexBuilder, languages
    # FIXME: find the correct lang
    indexer = IndexBuilder(app.env, 'en',
                           app.config.html_search_options)
    indexfile = os.path.join(app.outdir, curdoc, 'searchindex.js')
    try:
        f = open(indexfile, 'rb')
    except IOError:
        app.info("")
        app.warn("Unable to fetch %s "%indexfile)
        return None
    indexer.load(f, sphinx.search.js_index)
    f.close()
    return indexer

def get_js_index(app, curdoc):
    """
    Get the JS index of a sub-doc from the file
    """
    from sphinx.search import IndexBuilder, languages

    # FIXME: find the correct lang
    sphinx_version = __import__("sphinx").__version__
    if sphinx_version < "1.2":
        indexer = IndexBuilder(app.env, "en", app.config.html_search_options)
    else:
        indexer = IndexBuilder(app.env, "en", app.config.html_search_options, scoring=None)
    indexfile = os.path.join(app.outdir, curdoc, "searchindex.js")
    try:
        f = open(indexfile, "rb")
    except IOError:
        app.info("")
        app.warn("Unable to fetch %s " % indexfile)
        return None
    indexer.load(f, sphinx.search.js_index)
    f.close()
    return indexer

def test_IndexBuilder():
    domain = DummyDomain([('objname', 'objdispname', 'objtype', 'docname', '#anchor', 1),
                          ('objname2', 'objdispname2', 'objtype2', 'docname2', '', -1)])
    env = DummyEnvironment('1.0', {'dummy': domain})
    doc = utils.new_document(b'test data', settings)
    doc['file'] = 'dummy'
    parser.parse(FILE_CONTENTS, doc)

    # feed
    index = IndexBuilder(env, 'en', {}, None)
    index.feed('docname', 'filename', 'title', doc)
    index.feed('docname2', 'filename2', 'title2', doc)
    assert index._titles == {'docname': 'title', 'docname2': 'title2'}
    assert index._filenames == {'docname': 'filename', 'docname2': 'filename2'}
    assert index._mapping == {
        'fermion': {'docname', 'docname2'},
        'comment': {'docname', 'docname2'},
        'non': {'docname', 'docname2'},
        'index': {'docname', 'docname2'},
        'test': {'docname', 'docname2'}
    }
    assert index._title_mapping == {'section_titl': {'docname', 'docname2'}}
    assert index._objtypes == {}
    assert index._objnames == {}

    # freeze
    assert index.freeze() == {
        'docnames': ('docname', 'docname2'),
        'envversion': '1.0',
        'filenames': ['filename', 'filename2'],
        'objects': {'': {'objdispname': (0, 0, 1, '#anchor')}},
        'objnames': {0: ('dummy', 'objtype', 'objtype')},
        'objtypes': {0: 'dummy:objtype'},
        'terms': {'comment': [0, 1],
                  'fermion': [0, 1],
                  'index': [0, 1],
                  'non': [0, 1],
                  'test': [0, 1]},
        'titles': ('title', 'title2'),
        'titleterms': {'section_titl': [0, 1]}
    }
    assert index._objtypes == {('dummy', 'objtype'): 0}
    assert index._objnames == {0: ('dummy', 'objtype', 'objtype')}

    # dump / load
    stream = BytesIO()
    index.dump(stream, 'pickle')
    stream.seek(0)

    index2 = IndexBuilder(env, 'en', {}, None)
    index2.load(stream, 'pickle')

    assert index2._titles == index._titles
    assert index2._filenames == index._filenames
    assert index2._mapping == index._mapping
    assert index2._title_mapping == index._title_mapping
    assert index2._objtypes == {}
    assert index2._objnames == {}

    # freeze after load
    assert index2.freeze() == index.freeze()
    assert index2._objtypes == index._objtypes
    assert index2._objnames == index._objnames

    # prune
    index.prune(['docname2'])
    assert index._titles == {'docname2': 'title2'}
    assert index._filenames == {'docname2': 'filename2'}
    assert index._mapping == {
        'fermion': {'docname2'},
        'comment': {'docname2'},
        'non': {'docname2'},
        'index': {'docname2'},
        'test': {'docname2'}
    }
    assert index._title_mapping == {'section_titl': {'docname2'}}
    assert index._objtypes == {('dummy', 'objtype'): 0}
    assert index._objnames == {0: ('dummy', 'objtype', 'objtype')}

    # freeze after prune
    assert index.freeze() == {
        'docnames': ('docname2',),
        'envversion': '1.0',
        'filenames': ['filename2'],
        'objects': {},
        'objnames': {0: ('dummy', 'objtype', 'objtype')},
        'objtypes': {0: 'dummy:objtype'},
        'terms': {'comment': 0,
                  'fermion': 0,
                  'index': 0,
                  'non': 0,
                  'test': 0},
        'titles': ('title2',),
        'titleterms': {'section_titl': 0}
    }
    assert index._objtypes == {('dummy', 'objtype'): 0}
    assert index._objnames == {0: ('dummy', 'objtype', 'objtype')}

#.........这里部分代码省略.........
            except EnvironmentError:
                # source doesn't exist anymore
                pass

    def render_partial(self, node):
        """Utility: Render a lone doctree node."""
        if node is None:
            return {'fragment': ''}
        doc = new_document(b'<partial node>')
        doc.append(node)

        if self._publisher is None:
            self._publisher = Publisher(
                source_class = DocTreeInput,
                destination_class=StringOutput)
            self._publisher.set_components('standalone',
                                           'restructuredtext', 'pseudoxml')

        pub = self._publisher

        pub.reader = DoctreeReader()
        pub.writer = HTMLWriter(self)
        pub.process_programmatic_settings(
            None, {'output_encoding': 'unicode'}, None)
        pub.set_source(doc, None)
        pub.set_destination(None, None)
        pub.publish()
        return pub.writer.parts

    def prepare_writing(self, docnames):
        # create the search indexer
        self.indexer = None
        if self.search:
            from sphinx.search import IndexBuilder, languages
            lang = self.config.html_search_language or self.config.language
            if not lang or lang not in languages:
                lang = 'en'
            self.indexer = IndexBuilder(self.env, lang,
                                        self.config.html_search_options,
                                        self.config.html_search_scorer)
            self.load_indexer(docnames)

        self.docwriter = HTMLWriter(self)
        self.docsettings = OptionParser(
            defaults=self.env.settings,
            components=(self.docwriter,),
            read_config_files=True).get_default_values()
        self.docsettings.compact_lists = bool(self.config.html_compact_lists)

        # determine the additional indices to include
        self.domain_indices = []
        # html_domain_indices can be False/True or a list of index names
        indices_config = self.config.html_domain_indices
        if indices_config:
            for domain_name in sorted(self.env.domains):
                domain = self.env.domains[domain_name]
                for indexcls in domain.indices:
                    indexname = '%s-%s' % (domain.name, indexcls.name)
                    if isinstance(indices_config, list):
                        if indexname not in indices_config:
                            continue
                    # deprecated config value
                    if indexname == 'py-modindex' and \
                       not self.config.html_use_modindex:
                        continue
                    content, collapse = indexcls(domain).generate()

    def prepare_writing(self, docnames):
        # create the search indexer
        self.indexer = None
        if self.search:
            from sphinx.search import IndexBuilder, languages
            lang = self.config.html_search_language or self.config.language
            if not lang or lang not in languages:
                lang = 'en'
            self.indexer = IndexBuilder(self.env, lang,
                                        self.config.html_search_options,
                                        self.config.html_search_scorer)
            self.load_indexer(docnames)

        self.docwriter = HTMLWriter(self)
        self.docsettings = OptionParser(
            defaults=self.env.settings,
            components=(self.docwriter,),
            read_config_files=True).get_default_values()
        self.docsettings.compact_lists = bool(self.config.html_compact_lists)

        # determine the additional indices to include
        self.domain_indices = []
        # html_domain_indices can be False/True or a list of index names
        indices_config = self.config.html_domain_indices
        if indices_config:
            for domain_name in sorted(self.env.domains):
                domain = self.env.domains[domain_name]
                for indexcls in domain.indices:
                    indexname = '%s-%s' % (domain.name, indexcls.name)
                    if isinstance(indices_config, list):
                        if indexname not in indices_config:
                            continue
                    # deprecated config value
                    if indexname == 'py-modindex' and \
                       not self.config.html_use_modindex:
                        continue
                    content, collapse = indexcls(domain).generate()
                    if content:
                        self.domain_indices.append(
                            (indexname, indexcls, content, collapse))

        # format the "last updated on" string, only once is enough since it
        # typically doesn't include the time of day
        lufmt = self.config.html_last_updated_fmt
        if lufmt is not None:
            self.last_updated = format_date(lufmt or _('MMM dd, YYYY'),
                                            language=self.config.language)
        else:
            self.last_updated = None

        logo = self.config.html_logo and \
            path.basename(self.config.html_logo) or ''

        favicon = self.config.html_favicon and \
            path.basename(self.config.html_favicon) or ''
        if favicon and os.path.splitext(favicon)[1] != '.ico':
            self.warn('html_favicon is not an .ico file')

        if not isinstance(self.config.html_use_opensearch, string_types):
            self.warn('html_use_opensearch config value must now be a string')

        self.relations = self.env.collect_relations()

        rellinks = []
        if self.get_builder_config('use_index', 'html'):
            rellinks.append(('genindex', _('General Index'), 'I', _('index')))
        for indexname, indexcls, content, collapse in self.domain_indices:
            # if it has a short name
            if indexcls.shortname:
                rellinks.append((indexname, indexcls.localname,
                                 '', indexcls.shortname))

        if self.config.html_style is not None:
            stylename = self.config.html_style
        elif self.theme:
            stylename = self.theme.get_confstr('theme', 'stylesheet')
        else:
            stylename = 'default.css'

        self.globalcontext = dict(
            embedded = self.embedded,
            project = self.config.project,
            release = self.config.release,
            version = self.config.version,
            last_updated = self.last_updated,
            copyright = self.config.copyright,
            master_doc = self.config.master_doc,
            use_opensearch = self.config.html_use_opensearch,
            docstitle = self.config.html_title,
            shorttitle = self.config.html_short_title,
            show_copyright = self.config.html_show_copyright,
            show_sphinx = self.config.html_show_sphinx,
            has_source = self.config.html_copy_source,
            show_source = self.config.html_show_sourcelink,
            file_suffix = self.out_suffix,
            script_files = self.script_files,
            language = self.config.language,
            css_files = self.css_files,
            sphinx_version = __display_version__,
            style = stylename,
#.........这里部分代码省略.........