文章架构:
以下是我创建的文章架构。
class ArticleSchema(SchemaClass):
title = TEXT(
phrase=True, sortable=True, stored=True,
field_boost=2.0, spelling=True, analyzer=StemmingAnalyzer())
keywords = KEYWORD(
commas=True, field_boost=1.5, lowercase=True)
authors = KEYWORD(stored=True, commas=True, lowercase=True)
content = TEXT(spelling=True, analyzer=StemmingAnalyzer())
summary = TEXT(spelling=True, analyzer=StemmingAnalyzer())
published_time = DATETIME(stored=True, sortable=True)
permalink = STORED
thumbnail = STORED
article_id = ID(unique=True, stored=True)
topic = TEXT(spelling=True, stored=True)
series_id = STORED
tags = KEYWORD(commas=True, lowercase=True)
搜索查询
FIELD_TIME = 'published_time'
FIELD_TITLE = 'title'
FIELD_PUBLISHER = 'authors'
FIELD_KEYWORDS = 'keywords'
FIELD_CONTENT = 'content'
FIELD_TOPIC = 'topic'
def search_query(search_term=None, page=1, result_len=10):
'''Search the provided query.'''
if not search_term or search_term == '':
return None, 0
if not index.exists_in(INDEX_DIR, indexname=INDEX_NAME):
return None, 0
ix = get_index()
parser = qparser.MultifieldParser(
[FIELD_TITLE, FIELD_PUBLISHER, FIELD_KEYWORDS, FIELD_TOPIC],
ix.schema)
query = parser.parse(search_term)
query.normalize()
search_results = []
with ix.searcher() as searcher:
results = searcher.search_page(
query,
pagenum=page,
pagelen=result_len,
sortedby=[sorting_timestamp, scores],
reverse=True,
terms=True
)
if results.scored_length() > 0:
for hit in results:
search_results.append(append_to(hit))
return (search_results, results.pagecount)
parser = qparser.MultifieldParser(
[FIELD_TITLE, FIELD_PUBLISHER, FIELD_TOPIC],
ix.schema, termclass=FuzzyTerm)
parser.add_plugin(qparser.FuzzyTermPlugin())
query = parser.parse(search_term)
query.normalize()
search_results = []
with ix.searcher() as searcher:
results = searcher.search_page(
query,
pagenum=page,
pagelen=result_len,
sortedby=[sorting_timestamp, scores],
reverse=True,
terms=True
)
if results.scored_length() > 0:
for hit in results:
search_results.append(append_to(hit))
return (search_results, results.pagecount)
return None, 0
当我尝试标题搜索工作时,但对于作者和关键字,搜索无法正常工作。我无法理解我在这里做错了什么。我从api获取数据然后运行索引。一切正常。但是,当我搜索authors
和keywords
等关键字时,它无效。
答案 0 :(得分:0)
authors
和keywords
都属于KEYWORD
类型,它不支持词组搜索,这意味着您应该使用完全关键字或其衍生产品进行搜索,因为您使用的是词干分析器。
对于authors
,我认为您应该使用TEXT
。
来自whoosh的文档
<强> whoosh.fields.KEYWORD 强>
此类型适用于以空格或逗号分隔的关键字。这个 type是索引和可搜索的(并且可选地存储)。为了节省空间, 它不支持短语搜索。