import json
import os
import re
import shutil
import threading
import warnings
from django.conf import settings
from django.core.exceptions import ImproperlyConfigured
from django.utils.datetime_safe import date, datetime
from django.utils.encoding import force_str
from haystack.backends import (
BaseEngine,
BaseSearchBackend,
BaseSearchQuery,
EmptyResults,
log_query,
)
from haystack.constants import (
DJANGO_CT,
DJANGO_ID,
FUZZY_WHOOSH_MAX_EDITS,
FUZZY_WHOOSH_MIN_PREFIX,
ID,
)
from haystack.exceptions import MissingDependency, SearchBackendError, SkipDocument
from haystack.inputs import Clean, Exact, PythonData, Raw
from haystack.models import SearchResult
from haystack.utils import get_identifier, get_model_ct
from haystack.utils import log as logging
from haystack.utils.app_loading import haystack_get_model
from .chinese_anlyzer import ChineseAnalyzer
try:
import whoosh
except ImportError:
raise MissingDependency(
"The 'whoosh' backend requires the installation of 'Whoosh'. Please refer to the documentation."
)
# Handle minimum requirement.
if not hasattr(whoosh, "__version__") or whoosh.__version__ < (2, 5, 0):
raise MissingDependency("The 'whoosh' backend requires version 2.5.0 or greater.")
# Bubble up the correct error.
from whoosh import index
from whoosh.analysis import StemmingAnalyzer
from whoosh.fields import BOOLEAN, DATETIME
from whoosh.fields import ID as WHOOSH_ID
from whoosh.fields import IDLIST, KEYWORD, NGRAM, NGRAMWORDS, NUMERIC, TEXT, Schema
from whoosh.filedb.filestore import FileStorage, RamStorage
from whoosh.highlight import ContextFragmenter, HtmlFormatter
from whoosh.highlight import highlight as whoosh_highlight
from whoosh.qparser import FuzzyTermPlugin, QueryParser
from whoosh.searching import ResultsPage
from whoosh.sorting import Count, DateRangeFacet, FieldFacet
from whoosh.support.relativedelta import relativedelta as RelativeDelta
from whoosh.writing import AsyncWriter
DATETIME_REGEX = re.compile(
r"^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})T(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})(\.\d{3,"
r"6}Z?)?$"
)
LOCALS = threading.local()
LOCALS.RAM_STORE = None
class WhooshHtmlFormatter(HtmlFormatter):
"""
This is a HtmlFormatter simpler than the whoosh.HtmlFormatter.
We use it to have consistent results across backends. Specifically,
Solr, Xapian and Elasticsearch are using this formatting.
"""
template = "<%(tag)s>%(t)s</%(tag)s>"
class WhooshSearchBackend(BaseSearchBackend):
# Word reserved by Whoosh for special use.
RESERVED_WORDS = ("AND", "NOT", "OR", "TO")
# Characters reserved by Whoosh for special use.
# The '\\' must come first, so as not to overwrite the other slash replacements.
RESERVED_CHARACTERS = (
"\\",
"+",
"-",
"&&",
"||",
"!",
"(",
")",
"{",
"}",
"[",
"]",
"^",
'"',
"~",
"*",
"?",
":",
".",
)
def __init__(self, connection_alias, **connection_options):
super().__init__(connection_alias, **connection_options)
self.setup_complete = False
self.use_file_storage = True
self.post_limit = getattr(connection_options, "POST_LIMIT", 128 * 1024 * 1024)
self.path = connection_options.get("PATH")
if connection_options.get("STORAGE", "file") != "file":
self.use_file_storage = False
if self.use_file_storage and not self.path:
raise ImproperlyConfigured(
"You must specify a 'PATH' in your settings for connection '%s'."
% connection_alias
)
self.log = logging.getLogger("haystack")
def setup(self):
"""
Defers loading until needed.
"""
from haystack import connections
new_index = False
# Make sure the index is there.
if self.use_file_storage and not os.path.exists(self.path):
os.makedirs(self.path)
new_index = True
if self.use_file_storage and not os.access(self.path, os.W_OK):
raise IOError(
"The path to your Whoosh index '%s' is not writable for the current user/group."
% self.path
)
if self.use_file_storage:
self.storage = FileStorage(self.path)
else:
global LOCALS
if getattr(LOCALS, "RAM_STORE", None) is None:
LOCALS.RAM_STORE = RamStorage()
self.storage = LOCALS.RAM_STORE
self.content_field_name, self.schema = self.build_schema(
connections[self.connection_alias].get_unified_index().all_searchfields()
)
self.parser = QueryParser(self.content_field_name, schema=self.schema)
self.parser.add_plugins([FuzzyTermPlugin])
if new_index is True:
self.index = self.storage.create_index(self.schema)
else:
try:
self.index = self.storage.open_index(schema=self.schema)
except index.EmptyIndexError:
self.index = self.storage.create_index(self.schema)
self.setup_complete = True
def build_schema(self, fields):
schema_fields = {
ID: WHOOSH_ID(stored=True, unique=True),
DJANGO_CT: WHOOSH_ID(stored=True),
DJANGO_ID: WHOOSH_ID(stored=True),
}
# Grab the number of keys that are hard-coded into Haystack.
# We'll use this to (possibly) fail slightly more gracefully later.
initial_key_count = len(schema_fields)
content_field_name = ""
for _, field_class in fields.items():
if field_class.is_multivalued:
if field_class.indexed is False:
schema_fields[field_class.index_fieldname] = IDLIST(
stored=True, field_boost=field_class.boost
)
else:
schema_fields[field_class.index_fieldname] = KEYWORD(
stored=True,
commas=True,
scorable=True,
field_boost=field_class.boost,
)
elif field_class.field_type in ["date", "datetime"]:
schema_fields[field_class.index_fieldname] = DATETIME(
stored=field_class.stored, sortable=True
)
elif field_class.field_type == "integer":
schema_fields[field_class.index_fieldname] = NUMERIC(
stored=field_class.stored,
numtype=int,
field_boost=field_class.boost,
)
elif field_class.field_type == "float":
schema_fields[field_class.index_fieldname] = NUMERIC(
stored=field_class.stored,
numtype=float,
field_boost=field_class.boost,
)
elif field_class.field_type == "boolean":
# Field boost isn't supported on BOOLEAN as of 1.8.2.
schema_fields[field_class.index_fieldname] = BOOLEAN(
stored=field_class.stored
)
elif field_class.field_type == "ngram":
schema_fields[field_class.index_fieldname] = NGRAM(
minsize=3,
maxsize=15,
stored=field_class.stored,
field_boost=field_class.boost,
)
elif field_class.field_type == "edge_ngram":
schema_fields[field_class.index_fieldname] = NGRAMWORDS(
minsize=2,
maxsize=15,
at="start",
stored=field_class.stored,
field_boost=field_class.boost,
)
else:
没有合适的资源?快使用搜索试试~ 我知道了~
一个开源深度强化学习训练平台
共405个文件
py:143个
vue:53个
go:39个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 134 浏览量
2023-12-12
15:06:11
上传
评论
收藏 39.27MB ZIP 举报
温馨提示
一个开源深度强化学习训练平台
资源推荐
资源详情
资源评论
收起资源包目录
一个开源深度强化学习训练平台 (405个子文件)
.eslintrc.cjs 317B
nginx.conf 1KB
index.css 21KB
index.css 18KB
im.css 9KB
profile.css 9KB
upload.css 9KB
index.css 8KB
user-style.css 8KB
permission.css 7KB
file.css 7KB
monokai.css 6KB
checkbox.css 6KB
app-card.css 3KB
profile-style.css 3KB
blog.css 2KB
github-card.css 2KB
home.css 2KB
base.css 2KB
error.css 2KB
service.css 2KB
user.css 2KB
bootstrap-alert.css 2KB
index.css 1KB
pagination.css 1KB
applications.css 1KB
home.css 920B
anim.css 765B
geoip.css 731B
main.css 570B
font-family.css 470B
media-flip.css 446B
Dockerfile 530B
.dockerignore 63B
.gitignore 816B
.gitkeep 0B
.gitkeep 0B
.gitkeep 0B
api.go 19KB
user.go 7KB
api.go 6KB
cert.go 6KB
avatar.go 5KB
mysql.go 4KB
google.go 4KB
adapter.go 4KB
wechat.go 3KB
auth.go 3KB
github.go 3KB
captcha.go 3KB
alipay.go 3KB
base.go 2KB
payment.go 2KB
base.go 2KB
throttle.go 2KB
2fa.go 2KB
main.go 2KB
encrypt.go 2KB
http.go 2KB
smtp.go 2KB
adapter.go 1KB
mail.go 1KB
utils.go 1KB
api.go 1KB
cors.go 995B
code.go 794B
random.go 753B
redis.go 742B
validation.go 700B
ctx.go 530B
router.go 523B
package.go 510B
authentication.go 439B
debug.go 331B
router.go 305B
bulitins.go 266B
main.go 79B
dashboard.html 23KB
index.html 13KB
geoip.html 12KB
upload.html 7KB
profile.html 5KB
article.html 4KB
home.html 4KB
404.html 4KB
index.html 4KB
index.html 4KB
change.html 2KB
register.html 2KB
login.html 2KB
bind.html 2KB
applications.html 2KB
index.html 2KB
permission.html 2KB
registration.html 2KB
mail.html 2KB
verify.html 1KB
reset.html 1KB
index.html 765B
error.html 729B
共 405 条
- 1
- 2
- 3
- 4
- 5
资源评论
Java程序员-张凯
- 粉丝: 1w+
- 资源: 6746
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功