From 2773927a240dc406881a5ee1aa6055152f68175f Mon Sep 17 00:00:00 2001
From: lusiyi <gitea@fake.local>
Date: Wed, 22 Feb 2023 18:12:37 +0800
Subject: [PATCH] =?UTF-8?q?=E5=A2=9E=E5=8A=A0milestone=E5=8E=86=E5=8F=B2?=
 =?UTF-8?q?=E8=AE=B0=E5=BD=95=E7=94=9F=E6=88=90=E5=8A=9F=E8=83=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../generate_milestone_history_data.py        | 134 ++++++++++++++++++
 sql/01_2022-08-09.sql                         |  29 ++++
 2 files changed, 163 insertions(+)
 create mode 100644 project_evaluation_analysis/generate_milestone_history_data.py

diff --git a/project_evaluation_analysis/generate_milestone_history_data.py b/project_evaluation_analysis/generate_milestone_history_data.py
new file mode 100644
index 0000000..3908def
--- /dev/null
+++ b/project_evaluation_analysis/generate_milestone_history_data.py
@@ -0,0 +1,134 @@
+import sys
+import os
+
+import config
+
+curPath = os.path.abspath(os.path.dirname(__file__))
+rootPath = os.path.split(curPath)[0]
+sys.path.append(rootPath)
+
+import warnings
+from datetime import datetime,timedelta
+from utils import get_conn, get_month_date
+warnings.filterwarnings("ignore")
+
+def execute_sql(sql:str):
+    conn = get_conn()
+    curs = conn.cursor()
+    curs.execute(sql)
+    conn.commit()
+    conn.close()
+def record_milestone_history():
+    #每次调用此函数，默认记录当前日期的里程碑数据，然后回顾最近2个月的数据，若2个月之前的数据不存在，则以随机数的方式生成填充，并在is_test字段标记为true
+
+    # 查看当前历史表中已经有的数据
+    now = datetime.now()
+    today_str=now.strftime('%Y-%m-%d')
+    today=datetime.strptime(today_str,'%Y-%m-%d')
+    delta = timedelta(days=60)
+    begin_date=now-delta
+    begin_date_str=begin_date.strftime('%Y-%m-%d')
+    # 取出数据库中已有的最后一天的日期
+    last_date_sql=f'''SELECT max(date) as last_date from (
+SELECT date from ai_milestone_history where date>'{begin_date_str}' GROUP BY date order by date
+) as a'''
+
+    conn = get_conn()
+    curs = conn.cursor()
+    curs.execute(last_date_sql)
+    last_date=curs.fetchone()[0]
+    last_date_str=""
+    if last_date is None:
+        last_date_str=(today-timedelta(days=60)).strftime('%Y-%m-%d')
+    else:
+        last_date_str=last_date.strftime('%Y-%m-%d')
+    #last_date_str='2023-02-01'
+    if last_date_str==today_str:
+        config.logger.info("当前日期的milestone数据已存在，跳过生成")
+        return
+
+    last_date=datetime.strptime(last_date_str,'%Y-%m-%d')
+
+    delta=timedelta(days=1)
+    generate_day=last_date+delta
+    config.logger.info(f"开始生成{generate_day}到{today}的数据")
+    while generate_day<today:
+        insert_test_milestone(generate_day)
+        generate_day = generate_day + delta
+
+    insert_today_milestone(today)
+    config.logger.info("milestone历史数据记录完成")
+
+
+
+def insert_test_milestone(generate_day:datetime):
+    generate_day_str=generate_day.strftime('%Y-%m-%d')
+    generate_sql=f"""
+    insert into ai_milestone_history(date,
+	milestone_id,
+	repo_id,
+	NAME,
+	CONTENT,
+	is_closed,
+	num_issues,
+	num_closed_issues,
+	completeness,
+	deadline_unix,
+	closed_date_unix,
+	is_test)
+    SELECT
+	'{generate_day_str}' as date,
+	ID AS milestone_id,
+	repo_id,
+	NAME,
+	CONTENT,
+	is_closed,
+	ceil(num_issues+random()*10) as num_issues,
+	ceil(num_closed_issues+random()*10) as num_closed_issues,
+	ceil(completeness+random()*10) as completeness,
+	deadline_unix,
+	closed_date_unix,
+	true as is_test 
+FROM
+	milestone
+    """
+
+    execute_sql(generate_sql)
+
+def insert_today_milestone(generate_day:datetime):
+    generate_day_str = generate_day.strftime('%Y-%m-%d')
+    generate_sql = f"""
+        insert into ai_milestone_history(date,
+    	milestone_id,
+    	repo_id,
+    	NAME,
+    	CONTENT,
+    	is_closed,
+    	num_issues,
+    	num_closed_issues,
+    	completeness,
+    	deadline_unix,
+    	closed_date_unix,
+    	is_test)
+        SELECT
+    	'{generate_day_str}' as date,
+    	ID AS milestone_id,
+    	repo_id,
+    	NAME,
+    	CONTENT,
+    	is_closed,
+    	num_issues,
+    	num_closed_issues,
+    	completeness,
+    	deadline_unix,
+    	closed_date_unix,
+    	false as is_test 
+    FROM
+    	milestone
+        """
+
+    execute_sql(generate_sql)
+
+if __name__ == '__main__':
+    # 生成测试数据
+    record_milestone_history()
\ No newline at end of file
diff --git a/sql/01_2022-08-09.sql b/sql/01_2022-08-09.sql
index a32e0e9..e9e73eb 100644
--- a/sql/01_2022-08-09.sql
+++ b/sql/01_2022-08-09.sql
@@ -107,3 +107,32 @@ CREATE TABLE "public"."ai_user_portraint_detail" (
     "created_unix" int8
   );
 
+DROP TABLE IF EXISTS "public"."ai_milestone_history";
+CREATE TABLE "public"."ai_milestone_history" (
+  "milestone_id" int8,
+  "repo_id" int8,
+  "name" varchar(255) COLLATE "pg_catalog"."default",
+  "content" text COLLATE "pg_catalog"."default",
+  "is_closed" bool,
+  "num_issues" int4,
+  "num_closed_issues" int4,
+  "completeness" int4,
+  "deadline_unix" int8,
+  "closed_date_unix" int8,
+  "id" int8 NOT NULL GENERATED BY DEFAULT AS IDENTITY (
+INCREMENT 1
+MINVALUE  1
+MAXVALUE 9223372036854775807
+START 1
+CACHE 1
+),
+  "date" date NOT NULL,
+  "is_test" bool
+)
+;
+COMMENT ON COLUMN "public"."ai_milestone_history"."date" IS '记录日期';
+
+-- ----------------------------
+-- Primary Key structure for table ai_milestone_history
+-- ----------------------------
+ALTER TABLE "public"."ai_milestone_history" ADD CONSTRAINT "ai_milestone_history_pkey" PRIMARY KEY ("id");
\ No newline at end of file