diff --git a/src/DjangoBlog-master/blog/documents.py b/src/DjangoBlog-master/blog/documents.py index 0f1db7b..96cfb4a 100644 --- a/src/DjangoBlog-master/blog/documents.py +++ b/src/DjangoBlog-master/blog/documents.py @@ -7,21 +7,21 @@ from elasticsearch_dsl.connections import connections from blog.models import Article -ELASTICSEARCH_ENABLED = hasattr(settings, 'ELASTICSEARCH_DSL') +ELASTICSEARCH_ENABLED = hasattr(settings, 'ELASTICSEARCH_DSL') #ZNY 检查是否配置了Elasticsearch -if ELASTICSEARCH_ENABLED: - connections.create_connection( - hosts=[settings.ELASTICSEARCH_DSL['default']['hosts']]) - from elasticsearch import Elasticsearch +if ELASTICSEARCH_ENABLED: #ZNY 如果Elasticsearch已启用 + connections.create_connection( #ZNY 创建Elasticsearch连接 + hosts=[settings.ELASTICSEARCH_DSL['default']['hosts']]) #ZNY 从配置中获取主机地址 + from elasticsearch import Elasticsearch #ZNY 导入Elasticsearch客户端 - es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) - from elasticsearch.client import IngestClient + es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) #ZNY 创建Elasticsearch实例 + from elasticsearch.client import IngestClient #ZNY 导入Ingest客户端 - c = IngestClient(es) + c = IngestClient(es) #ZNY 创建Ingest客户端实例 try: - c.get_pipeline('geoip') - except elasticsearch.exceptions.NotFoundError: - c.put_pipeline('geoip', body='''{ + c.get_pipeline('geoip') #ZNY 尝试获取geoip管道 + except elasticsearch.exceptions.NotFoundError: #ZNY 如果geoip管道不存在 + c.put_pipeline('geoip', body='''{ #ZNY 创建geoip管道 "description" : "Add geoip info", "processors" : [ { @@ -30,184 +30,184 @@ if ELASTICSEARCH_ENABLED: } } ] - }''') + }''') #ZNY 定义geoip处理管道配置 -class GeoIp(InnerDoc): - continent_name = Keyword() - country_iso_code = Keyword() - country_name = Keyword() - location = GeoPoint() +class GeoIp(InnerDoc): #ZNY 定义GeoIP内嵌文档类 + continent_name = Keyword() #ZNY 大洲名称 + country_iso_code = Keyword() #ZNY 国家ISO代码 + country_name = Keyword() #ZNY 国家名称 + location = GeoPoint() #ZNY 地理位置坐标 -class UserAgentBrowser(InnerDoc): - Family = Keyword() - Version = Keyword() +class UserAgentBrowser(InnerDoc): #ZNY 定义用户代理浏览器信息类 + Family = Keyword() #ZNY 浏览器家族 + Version = Keyword() #ZNY 浏览器版本 -class UserAgentOS(UserAgentBrowser): - pass +class UserAgentOS(UserAgentBrowser): #ZNY 定义用户代理操作系统信息类，继承自浏览器类 + pass #ZNY 继承父类字段 -class UserAgentDevice(InnerDoc): - Family = Keyword() - Brand = Keyword() - Model = Keyword() +class UserAgentDevice(InnerDoc): #ZNY 定义用户代理设备信息类 + Family = Keyword() #ZNY 设备家族 + Brand = Keyword() #ZNY 设备品牌 + Model = Keyword() #ZNY 设备型号 -class UserAgent(InnerDoc): - browser = Object(UserAgentBrowser, required=False) - os = Object(UserAgentOS, required=False) - device = Object(UserAgentDevice, required=False) - string = Text() - is_bot = Boolean() +class UserAgent(InnerDoc): #ZNY 定义完整的用户代理信息类 + browser = Object(UserAgentBrowser, required=False) #ZNY 浏览器信息对象 + os = Object(UserAgentOS, required=False) #ZNY 操作系统信息对象 + device = Object(UserAgentDevice, required=False) #ZNY 设备信息对象 + string = Text() #ZNY 原始用户代理字符串 + is_bot = Boolean() #ZNY 是否为机器人 -class ElapsedTimeDocument(Document): - url = Keyword() - time_taken = Long() - log_datetime = Date() - ip = Keyword() - geoip = Object(GeoIp, required=False) - useragent = Object(UserAgent, required=False) +class ElapsedTimeDocument(Document): #ZNY 定义性能耗时文档类 + url = Keyword() #ZNY 请求URL + time_taken = Long() #ZNY 耗时（毫秒） + log_datetime = Date() #ZNY 日志时间 + ip = Keyword() #ZNY IP地址 + geoip = Object(GeoIp, required=False) #ZNY GeoIP地理位置信息 + useragent = Object(UserAgent, required=False) #ZNY 用户代理信息 - class Index: - name = 'performance' - settings = { - "number_of_shards": 1, - "number_of_replicas": 0 + class Index: #ZNY 定义索引配置 + name = 'performance' #ZNY 索引名称 + settings = { #ZNY 索引设置 + "number_of_shards": 1, #ZNY 分片数量 + "number_of_replicas": 0 #ZNY 副本数量 } - class Meta: - doc_type = 'ElapsedTime' + class Meta: #ZNY 元数据配置 + doc_type = 'ElapsedTime' #ZNY 文档类型 -class ElaspedTimeDocumentManager: +class ElaspedTimeDocumentManager: #ZNY 性能耗时文档管理器类 @staticmethod - def build_index(): - from elasticsearch import Elasticsearch - client = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) - res = client.indices.exists(index="performance") - if not res: - ElapsedTimeDocument.init() + def build_index(): #ZNY 构建索引静态方法 + from elasticsearch import Elasticsearch #ZNY 导入Elasticsearch + client = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) #ZNY 创建客户端 + res = client.indices.exists(index="performance") #ZNY 检查索引是否存在 + if not res: #ZNY 如果索引不存在 + ElapsedTimeDocument.init() #ZNY 初始化性能耗时文档索引 @staticmethod - def delete_index(): - from elasticsearch import Elasticsearch - es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) - es.indices.delete(index='performance', ignore=[400, 404]) + def delete_index(): #ZNY 删除索引静态方法 + from elasticsearch import Elasticsearch #ZNY 导入Elasticsearch + es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) #ZNY 创建客户端 + es.indices.delete(index='performance', ignore=[400, 404]) #ZNY 删除性能索引，忽略特定错误 @staticmethod - def create(url, time_taken, log_datetime, useragent, ip): - ElaspedTimeDocumentManager.build_index() - ua = UserAgent() - ua.browser = UserAgentBrowser() - ua.browser.Family = useragent.browser.family - ua.browser.Version = useragent.browser.version_string - - ua.os = UserAgentOS() - ua.os.Family = useragent.os.family - ua.os.Version = useragent.os.version_string - - ua.device = UserAgentDevice() - ua.device.Family = useragent.device.family - ua.device.Brand = useragent.device.brand - ua.device.Model = useragent.device.model - ua.string = useragent.ua_string - ua.is_bot = useragent.is_bot - - doc = ElapsedTimeDocument( - meta={ - 'id': int( + def create(url, time_taken, log_datetime, useragent, ip): #ZNY 创建性能记录静态方法 + ElaspedTimeDocumentManager.build_index() #ZNY 确保索引存在 + ua = UserAgent() #ZNY 创建用户代理对象 + ua.browser = UserAgentBrowser() #ZNY 创建浏览器信息对象 + ua.browser.Family = useragent.browser.family #ZNY 设置浏览器家族 + ua.browser.Version = useragent.browser.version_string #ZNY 设置浏览器版本 + + ua.os = UserAgentOS() #ZNY 创建操作系统信息对象 + ua.os.Family = useragent.os.family #ZNY 设置操作系统家族 + ua.os.Version = useragent.os.version_string #ZNY 设置操作系统版本 + + ua.device = UserAgentDevice() #ZNY 创建设备信息对象 + ua.device.Family = useragent.device.family #ZNY 设置设备家族 + ua.device.Brand = useragent.device.brand #ZNY 设置设备品牌 + ua.device.Model = useragent.device.model #ZNY 设置设备型号 + ua.string = useragent.ua_string #ZNY 设置原始用户代理字符串 + ua.is_bot = useragent.is_bot #ZNY 设置是否为机器人 + + doc = ElapsedTimeDocument( #ZNY 创建性能耗时文档 + meta={ #ZNY 文档元数据 + 'id': int( #ZNY 使用时间戳作为文档ID round( time.time() * 1000)) }, - url=url, - time_taken=time_taken, - log_datetime=log_datetime, - useragent=ua, ip=ip) - doc.save(pipeline="geoip") - - -class ArticleDocument(Document): - body = Text(analyzer='ik_max_word', search_analyzer='ik_smart') - title = Text(analyzer='ik_max_word', search_analyzer='ik_smart') - author = Object(properties={ - 'nickname': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), - 'id': Integer() + url=url, #ZNY 设置URL + time_taken=time_taken, #ZNY 设置耗时 + log_datetime=log_datetime, #ZNY 设置日志时间 + useragent=ua, ip=ip) #ZNY 设置用户代理和IP + doc.save(pipeline="geoip") #ZNY 保存文档并使用geoip管道处理 + + +class ArticleDocument(Document): #ZNY 定义文章文档类 + body = Text(analyzer='ik_max_word', search_analyzer='ik_smart') #ZNY 正文，使用IK中文分词器 + title = Text(analyzer='ik_max_word', search_analyzer='ik_smart') #ZNY 标题，使用IK中文分词器 + author = Object(properties={ #ZNY 作者对象 + 'nickname': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), #ZNY 作者昵称 + 'id': Integer() #ZNY 作者ID }) - category = Object(properties={ - 'name': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), - 'id': Integer() + category = Object(properties={ #ZNY 分类对象 + 'name': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), #ZNY 分类名称 + 'id': Integer() #ZNY 分类ID }) - tags = Object(properties={ - 'name': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), - 'id': Integer() + tags = Object(properties={ #ZNY 标签对象 + 'name': Text(analyzer='ik_max_word', search_analyzer='ik_smart'), #ZNY 标签名称 + 'id': Integer() #ZNY 标签ID }) - pub_time = Date() - status = Text() - comment_status = Text() - type = Text() - views = Integer() - article_order = Integer() - - class Index: - name = 'blog' - settings = { - "number_of_shards": 1, - "number_of_replicas": 0 + pub_time = Date() #ZNY 发布时间 + status = Text() #ZNY 文章状态 + comment_status = Text() #ZNY 评论状态 + type = Text() #ZNY 文章类型 + views = Integer() #ZNY 浏览量 + article_order = Integer() #ZNY 文章排序 + + class Index: #ZNY 定义索引配置 + name = 'blog' #ZNY 索引名称 + settings = { #ZNY 索引设置 + "number_of_shards": 1, #ZNY 分片数量 + "number_of_replicas": 0 #ZNY 副本数量 } - class Meta: - doc_type = 'Article' + class Meta: #ZNY 元数据配置 + doc_type = 'Article' #ZNY 文档类型 -class ArticleDocumentManager(): +class ArticleDocumentManager(): #ZNY 文章文档管理器类 - def __init__(self): - self.create_index() + def __init__(self): #ZNY 初始化方法 + self.create_index() #ZNY 创建索引 - def create_index(self): - ArticleDocument.init() + def create_index(self): #ZNY 创建索引方法 + ArticleDocument.init() #ZNY 初始化文章文档索引 - def delete_index(self): - from elasticsearch import Elasticsearch - es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) - es.indices.delete(index='blog', ignore=[400, 404]) + def delete_index(self): #ZNY 删除索引方法 + from elasticsearch import Elasticsearch #ZNY 导入Elasticsearch + es = Elasticsearch(settings.ELASTICSEARCH_DSL['default']['hosts']) #ZNY 创建客户端 + es.indices.delete(index='blog', ignore=[400, 404]) #ZNY 删除博客索引，忽略特定错误 - def convert_to_doc(self, articles): - return [ - ArticleDocument( + def convert_to_doc(self, articles): #ZNY 将文章转换为文档方法 + return [ #ZNY 返回文档列表 + ArticleDocument( #ZNY 创建文章文档 meta={ - 'id': article.id}, - body=article.body, - title=article.title, - author={ - 'nickname': article.author.username, - 'id': article.author.id}, - category={ - 'name': article.category.name, - 'id': article.category.id}, - tags=[ + 'id': article.id}, #ZNY 使用文章ID作为文档ID + body=article.body, #ZNY 设置正文 + title=article.title, #ZNY 设置标题 + author={ #ZNY 设置作者信息 + 'nickname': article.author.username, #ZNY 作者用户名 + 'id': article.author.id}, #ZNY 作者ID + category={ #ZNY 设置分类信息 + 'name': article.category.name, #ZNY 分类名称 + 'id': article.category.id}, #ZNY 分类ID + tags=[ #ZNY 设置标签列表 { - 'name': t.name, - 'id': t.id} for t in article.tags.all()], - pub_time=article.pub_time, - status=article.status, - comment_status=article.comment_status, - type=article.type, - views=article.views, - article_order=article.article_order) for article in articles] - - def rebuild(self, articles=None): - ArticleDocument.init() - articles = articles if articles else Article.objects.all() - docs = self.convert_to_doc(articles) - for doc in docs: - doc.save() - - def update_docs(self, docs): - for doc in docs: - doc.save() + 'name': t.name, #ZNY 标签名称 + 'id': t.id} for t in article.tags.all()], #ZNY 遍历所有标签 + pub_time=article.pub_time, #ZNY 设置发布时间 + status=article.status, #ZNY 设置文章状态 + comment_status=article.comment_status, #ZNY 设置评论状态 + type=article.type, #ZNY 设置文章类型 + views=article.views, #ZNY 设置浏览量 + article_order=article.article_order) for article in articles] #ZNY 设置文章排序 + + def rebuild(self, articles=None): #ZNY 重建索引方法 + ArticleDocument.init() #ZNY 重新初始化索引 + articles = articles if articles else Article.objects.all() #ZNY 获取所有文章或指定文章 + docs = self.convert_to_doc(articles) #ZNY 转换为文档格式 + for doc in docs: #ZNY 遍历所有文档 + doc.save() #ZNY 保存文档到Elasticsearch + + def update_docs(self, docs): #ZNY 更新文档方法 + for doc in docs: #ZNY 遍历文档列表 + doc.save() #ZNY 保存更新后的文档