re-common 2.0.1__py3-none-any.whl → 10.0.1__py3-none-any.whl

re_common/baselibrary/tools/merge_gz_file.py

@@ -0,0 +1,165 @@
+"""
+多文件合并到压缩文件
+方法一：按行读取写入
+方法二: 按块读取写入
+
+"""
+
+###########################################
+# 同项目调用基础包
+import os
+import sys
+
+filepath = os.path.abspath(__file__)
+pathlist = filepath.split(os.sep)
+pathlist = pathlist[:-4]
+TopPath = os.sep.join(pathlist)
+sys.path.insert(0, TopPath)
+
+############################################
+
+import time
+import gzip
+
+from re_common.baselibrary.utils.basedir import BaseDir
+from re_common.baselibrary.utils.basefile import BaseFile
+
+
+class MergeGzFile(object):
+    def __init__(self):
+        self.outPathFile = None
+        self.a_num = 1000
+        self.b_num = 20000
+
+        self.a_size = 1024 * 1024 * 1024
+        self.block_size = 2 * 1024 * 1024 * 1024
+
+
+    def get_outpathfile(self,dst):
+        BaseDir.create_dir(dst)
+        now_time = time.strftime('%Y%m%d', time.localtime())
+        self.filename = "{}.gz".format(now_time)
+        self.outPathFile = BaseFile.get_new_path(dst,self.filename)
+        return self.outPathFile
+
+
+    def line_all_2_one_gz(self,src,dst,dst_size=None,a_num=None,b_num=None):
+        """
+        :param src: 输入路径
+        :param dst: 输出路径
+        :param dst_size:  指定输出文件的最大值
+        :param a_num:  打印条数的取值（默认1000条输出一次信息）
+        :param b_num:  打印路径的取值（默认20000条输出一次信息）
+        :return:
+        """
+        # 程序开始时间
+        StartTime = time.time()
+        if a_num is None:
+            a_num = self.a_num
+        if b_num is None:
+            b_num = self.b_num
+        count_all = 0
+        dst_count = 0
+        src_file_num = 0
+        src_file_location = 0
+        if self.outPathFile is None:
+            self.get_outpathfile(dst)
+
+        f = gzip.open(self.outPathFile, "wb")
+
+        for files in BaseDir.get_dir_all_files(src):
+            src_file_num += 1
+
+        for files in BaseDir.get_dir_all_files(src):
+            # 处理每个文件的开始时间
+            start_time = time.time()
+            src_file_location += 1
+            print("next source_path:"+files)
+
+            count = 0
+            for line in BaseFile.read_file_rb_mode_yield(files):
+                count += 1
+                count_all +=1
+                dst_count +=1
+
+                f.write(line)
+
+                if count % a_num == 1:
+                    print("process_src:%d/%d, Time total:%s, source_count: %d, dst_count: %d, allcount: %d" % (src_file_location, src_file_num, (repr(time.time() - start_time)), count, dst_count, count_all))
+                if count % b_num == 1:
+                    print("source_path: %s , dst_path:%s" % (files,self.outPathFile))
+                if dst_size is not None:
+                    if BaseFile.get_file_size(self.outPathFile) >= dst_size:
+                        f.close()
+                        print("cut dst file, now:source_count: %d,dst_count: %d, allcount: %d" % (count, dst_count, count_all))
+                        dst_count = 0
+                        self.outPathFile = BaseFile.change_file(self.outPathFile, size=dst_size,ending='gz')
+                        # self.outPathFile = self.outPathFile.replace(".big_json",'.gz')
+                        f = gzip.open(self.outPathFile, "wb")
+                        print("new dst_path: %s" % self.outPathFile)
+
+            print("finish one file;Time total:%s, process_src:%d/%d, source_count: %d, dst_count: %d, allcount: %d" % (repr(time.time() - start_time),src_file_location, src_file_num,count, dst_count, count_all))
+        # 程序结束花费时间时间
+        print('\nProce Over\nTime total:' + repr(time.time() - StartTime) + '\n')
+
+    def block_all_2_one_gz(self,src,dst,dst_size=None,block_size=None,a_size=None):
+        """
+        按块读取小文件，并写入文件
+        :param src: 输入路径
+        :param dst: 输出路径
+        :param source_size: 输入文件大于source_size，就直接复制过去
+        :param dst_size: 指定输出文件的最大值（但是需要操作完一个输入文件后判断大小）
+        :param block_size: 按块读取的值
+        :param a_size: 打印路径的取值（默认1G大小输出一次信息）
+        :return:
+        """
+        # 程序开始时间
+        StartTime = time.time()
+        src_file_num = 0
+        src_all_size = 0
+        src_file_location = 0
+        if a_size is None:
+            a_size = self.a_size
+        if block_size is None:
+            block_size = self.block_size
+
+        if self.outPathFile is None:
+            self.get_outpathfile(dst)
+
+        f = gzip.open(self.outPathFile, "wb")
+
+        for files in BaseDir.get_dir_all_files(src):
+            src_file_num += 1
+        for files in BaseDir.get_dir_all_files(src):
+            # 处理每个文件的开始时间
+            src_all_size += BaseFile.get_file_size(files)
+            dst_file_size = 0
+            start_time = time.time()
+            src_file_location += 1
+            print("next source_path:" + files)
+
+            for block in BaseFile.read_file_rb_block(files,BLOCK_SIZE=block_size):
+                f.write(block)
+
+            if BaseFile.get_file_size(self.outPathFile) % a_size == 1:
+                print("process_src:%d/%d, dst_size:%d, src_size:%d, src_all_size:%d, Time total:%.2f/%.2f" % (src_file_location, src_file_num, dst_file_size ,BaseFile.get_file_size(files), src_all_size, (time.time() - start_time),(time.time() - StartTime) ))
+            dst_file_size = BaseFile.get_file_size(self.outPathFile)
+            print("finish one file;process_src:%d/%d, dst_size:%d, src_size:%d, src_all_size:%d, Time total:%.2f/%.2f" % (src_file_location, src_file_num, dst_file_size ,BaseFile.get_file_size(files), src_all_size, (time.time() - start_time),(time.time() - StartTime) ))
+            if dst_size is not None:
+                if BaseFile.get_file_size(self.outPathFile) >= dst_size:
+                    f.close()
+                    self.outPathFile = BaseFile.change_file(self.outPathFile, size=dst_size,ending='gz')
+                    f = gzip.open(self.outPathFile, "wb")
+                    print("new dst_path: %s" % self.outPathFile)
+                    dst_file_size = 0
+            # 程序结束花费时间时间
+        print('\nProce Over\nTime total:' + repr(time.time() - StartTime) + '\n')
+
+
+if __name__ == '__main__':
+    old_path = r'\\192.168.31.188\download\cnki_qk\download\get_ref\input'
+    new_path = r'\\192.168.31.188\download\cnki_qk\download\get_ref\output'
+    a = MergeGzFile()
+    a.line_all_2_one_gz(old_path,new_path,dst_size=1024*1024*100)
+    # a.block_all_2_one(old_path,new_path,dst_size=1024*1024*10)
+

re_common/baselibrary/tools/mhdfstools/down_hdfs_files.py

@@ -0,0 +1,42 @@
+import sys
+
+from re_common.baselibrary.baseabs import BaseAbs
+from re_common.baselibrary.utils.basehdfs import BaseHDFS
+
+
+class DownHdfs(object):
+
+    def __init__(self, toml_file):
+        self.toml_file = toml_file
+        self.dicts = {}
+        self.basehdfs = None
+
+    def read_toml(self):
+        dicts = BaseAbs.get_config_factory().toml_factory().set_config_path(
+            self.toml_file).read_file_remove_bom().get_dicts()
+        self.dicts = dicts
+        return self
+
+    def set_basehdfs(self, i=0):
+        self.basehdfs = BaseHDFS()
+        self.basehdfs.hdfsdir = self.dicts["PathPair"][i][0]
+        self.basehdfs.localdir = self.dicts["PathPair"][i][1]
+        self.basehdfs.user_name = self.dicts["UserName"]
+        self.basehdfs.namenode = self.dicts["NameNode"]
+        return self
+
+    def down_files(self):
+        self.basehdfs.get_client()
+        self.basehdfs.get_all_files_num()
+        self.basehdfs.get_all_files()
+
+    def use(self):
+        self.read_toml()
+        for i in range(len(self.dicts["PathPair"])):
+            self.set_basehdfs(i)
+            self.down_files()
+
+
+if __name__ == "__main__":
+    a = sys.argv[1]
+    DownHdfs(a).use()

re_common/baselibrary/tools/mhdfstools/hdfst.py

@@ -0,0 +1,42 @@
+from re_common.baselibrary.baseabs import BaseAbs
+from re_common.baselibrary.utils.basehdfs import BaseHDFS
+
+
+class HdfsTools(object):
+    def __init__(self):
+        self.toml_file = "config_down.toml"
+        self.dicts = {}
+        self.basehdfs = None
+
+    def read_toml(self):
+        dicts = BaseAbs.get_config_factory().toml_factory().set_config_path(
+            self.toml_file).read_file_remove_bom().get_dicts()
+        self.dicts = dicts
+        return self
+
+    def set_basehdfs(self, i=0):
+        self.basehdfs = BaseHDFS()
+        self.basehdfs.hdfsdir = self.dicts["PathPair"][i][0]
+        self.basehdfs.localdir = self.dicts["PathPair"][i][1]
+        self.basehdfs.user_name = self.dicts["UserName"]
+        self.basehdfs.namenode = self.dicts["NameNode"]
+        return self
+
+    def builder(self):
+        self.basehdfs.get_client()
+
+    def create_dirs(self):
+        self.basehdfs.get_client()
+        print(self.basehdfs.mk_hdfs_dirs(r"/RawData/wanfang/qk/ref/big_json/20200421"))
+
+
+    def exists(self):
+        print(self.basehdfs.exists(r"/RawData/wanfang/qk/ref/big_json/20200421"))
+
+    def run(self):
+        self.read_toml()
+        self.set_basehdfs()
+        self.builder()
+        self.exists()
+
+HdfsTools().run()

re_common/baselibrary/tools/mhdfstools/up_hdfs_files.py

@@ -0,0 +1,38 @@
+from re_common.baselibrary.baseabs import BaseAbs
+from re_common.baselibrary.utils.basehdfs import BaseHDFS
+
+
+class DownHdfs(object):
+
+    def __init__(self):
+        self.toml_file = "config_up.toml"
+        self.dicts = {}
+        self.basehdfs = None
+
+    def read_toml(self):
+        dicts = BaseAbs.get_config_factory().toml_factory().set_config_path(
+            self.toml_file).read_file_remove_bom().get_dicts()
+        self.dicts = dicts
+        return self
+
+    def set_basehdfs(self, i=0):
+        self.basehdfs = BaseHDFS()
+        self.basehdfs.localdir = self.dicts["PathPair"][i][0]
+        self.basehdfs.hdfsdir = self.dicts["PathPair"][i][1]
+        self.basehdfs.user_name = self.dicts["UserName"]
+        self.basehdfs.namenode = self.dicts["NameNode"]
+        return self
+
+    def up_files(self):
+        self.basehdfs.get_client()
+        self.basehdfs.get_all_files_num()
+        self.basehdfs.up_all_files()
+
+    def use(self):
+        self.read_toml()
+        for i in range(len(self.dicts["PathPair"])):
+            self.set_basehdfs(i)
+            self.up_files()
+
+
+DownHdfs().use()

re_common/baselibrary/tools/mongo_tools.py

@@ -0,0 +1,50 @@
+import time
+
+from re_common.baselibrary.utils.basemotor import BaseMotor
+from re_common.baselibrary.utils.basepymongo import BasePyMongo
+
+
+class MongoTools(object):
+    def __init__(self, conn_str, db_name, col):
+        self.conn_str = conn_str
+        self.db_name = db_name
+        self.col = col
+        self.bs_conn = None
+
+    def conn_mongo_base(self):
+        self.bs_conn = BasePyMongo(self.conn_str)
+        self.bs_conn.use_db(self.db_name)
+        self.bs_conn.create_col(self.col)
+
+    def conn_mongo_motor(self):
+        self.bs_conn = BaseMotor()
+        self.bs_conn.AsyncIOMotorClient(self.conn_str, self.db_name)
+        self.bs_conn.get_col(self.col)
+
+    def get_first_id(self, query):
+        for item in self.bs_conn.find({"sub_db_id": "00075", "_id": {"$lt": ""}},
+                                      {"_id": 1}).skip(0).limit(1):
+            return item["_id"]
+
+    def get_ids(self, ids, query):
+        count = 0
+        while True:
+            lists = []
+            query_temp = query.update({"_id": {"$gt": ids}})
+            for i in self.bs_conn.find(query_temp, {"_id": 1}).sort([("_id", 1)]).limit(1000000):
+                count = count + 1
+                ids = i["_id"]
+                lists.append((i["_id"]))
+                if len(lists) % 10000 == 1:
+                    print(len(lists))
+
+
+if __name__ == "__main__":
+    # mt = MongoTools(
+    #     conn_str="mongodb://datahouse:vipdatacenter@192.168.31.243:32920/data_warehouse.base_obj_meta_a?authSource=data_warehouse",
+    #     db_name="data_warehouse", col="base_obj_meta_a")
+    mt = MongoTools(
+        conn_str="mongodb://datahouse:vipdatacenter@192.168.31.208:32920,192.168.31.206:32920,192.168.31.243:32920/data_warehouse.base_obj_meta_a?authSource=data_warehouse",
+        db_name="data_warehouse", col="base_obj_meta_a")
+    mt.conn_mongo_base()
+    print(mt.get_first_id({"sub_db_id": "00075"}))

re_common/baselibrary/tools/move_file.py

@@ -0,0 +1,170 @@
+import time
+
+from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun2
+from re_common.baselibrary.mthread.mythreading import ThreadInfo
+from re_common.baselibrary.utils.basedir import BaseDir
+from re_common.baselibrary.utils.basefile import BaseFile
+from re_common.baselibrary.utils.basequeue import BaseQueue
+from re_common.facade.now import get_streamlogger, get_filelogger
+
+
+def copy_one_file(fullname, sources_path, dst_path):
+    """
+    复制文件 不会删除
+    :param fullname:
+    :param sources_path:
+    :param dst_path:
+    :return:
+    """
+    fullname_size = BaseFile.get_file_size(fullname)
+    # 替换前面的路径得到新文件的路劲
+    dst_file = fullname.replace(sources_path, dst_path)
+    # 目录不存在就创建目录
+    dst_dir = BaseDir.get_file_dir_absolute(dst_file)
+    BaseDir.create_dir(dst_dir)
+
+    if BaseFile.is_file_exists(dst_file):
+        dst_dir_size = BaseFile.get_file_size(dst_file)
+        if fullname_size == dst_dir_size:
+            return True
+    # 复制文件
+    BaseFile.copy_file_to_file(fullname, dst_file)
+    dst_dir_size = BaseFile.get_file_size(dst_file)
+    # 文件大小一致才删除源文件
+    # 大小一致性对比不能用于windows 和 liunx之间的传输，两者会存在差异性
+    print(fullname_size,dst_dir_size)
+    if fullname_size == dst_dir_size:
+        return True
+    else:
+        return False
+
+
+def move_one_file(fullname, sources_path, dst_path):
+    """
+    移动文件，会删除源文件
+    :param fullname:
+    :param sources_path:
+    :param dst_path:
+    :return:
+    """
+    fullname_size = BaseFile.get_file_size(fullname)
+    # 替换前面的路径得到新文件的路劲
+    dst_file = fullname.replace(sources_path, dst_path)
+    # 目录不存在就创建目录
+    dst_dir = BaseDir.get_file_dir_absolute(dst_file)
+    BaseDir.create_dir(dst_dir)
+    if BaseFile.is_file_exists(dst_file):
+        dst_dir_size = BaseFile.get_file_size(dst_file)
+        if fullname_size == dst_dir_size:
+            BaseFile.remove_file(fullname)
+    # 复制文件
+    BaseFile.copy_file_to_file(fullname, dst_file)
+    dst_dir_size = BaseFile.get_file_size(dst_file)
+    # 文件大小一致才删除源文件
+    if fullname_size == dst_dir_size:
+        BaseFile.remove_file(fullname)
+
+
+def move_file(sources_path, dst_path):
+    """
+    移动文件，会删除源文件
+    :param sources_path:
+    :param dst_path:
+    :return:
+    """
+    k = 0
+    for fullname in BaseDir.get_dir_all_files(sources_path):
+        k += 1
+        move_one_file(fullname, sources_path, dst_path)
+        if k % 1000 == 0:
+            print("已经拷贝{}个文件".format(k))
+    print("已经拷贝{}个文件".format(k))
+
+
+class MoveFile(object):
+
+    def __init__(self):
+        self.sources_path = ''
+        self.dst_path = ''
+
+
+class MoveFileThread(MThreadingRun2):
+    def __init__(self, num, mf):
+        super(MoveFileThread, self).__init__(num)
+        self.mf = mf
+        self.k = 0
+        self.file_logger = get_filelogger(r"F:\fun2\log")
+        self.thread_pool.work_queue = BaseQueue(1000)
+
+    def create_dir(self):
+        """
+        先创建所有目录,防止在多线程中创建目录冲突
+        :return:
+        """
+        for dir in BaseDir.get_dir_all_dir(self.mf.sources_path):
+            new_dir = dir.replace(self.mf.sources_path, self.mf.dst_path)
+            print(new_dir)
+            BaseDir.create_dir(new_dir)
+
+    def set_task(self, threadval, *args, **kwargs):
+        self.create_dir()
+        for fullname in BaseDir.get_dir_all_files(self.mf.sources_path):
+            self.k = self.k + 1
+            self.add_job(self.func, fullname)
+            if self.k % 1000 == 0:
+                print("已经拷贝{}个文件".format(self.k))
+        while self.get_thread_stat():
+            time.sleep(1)
+
+    def get_thread_stat(self):
+        """
+        如果是False代表所有的线程都在等待任务，说明所有工作都已经完成
+        :return:
+        """
+        for k, v in self.thread_pool.thread_pool_dicts.items():
+            threadinfo = v
+            thread = threadinfo.get_thread()
+            if thread.runstatus is not False:
+                return True
+        return False
+
+    def deal_results(self, threadval, *args, **kwargs):
+        time.sleep(60)
+
+    def setProxy(self, threadval, proxysList=None):
+        time.sleep(60)
+
+    def is_break(self):
+        time.sleep(5)
+        if self.thread_pool.work_queue.is_empty() and self.thread_pool.result_queue.is_empty() and not self.get_thread_stat():
+            for k, v in self.thread_pool.thread_pool_dicts.items():
+                if k == self.etn.taskthreadname:
+                    threadinfo = v
+                    thread = threadinfo.get_thread()
+                    if thread.is_alive():
+                        return False
+            return True
+        else:
+            return False
+
+    def thread_pool_hook(self, threadinfo: ThreadInfo):
+        # 设置代理线程不重启，默认会重启
+        if threadinfo.get_thread_name() == self.etn.taskthreadname:
+            threadinfo.set_is_restart(False)
+        return {}
+
+    def fun(self, threadval, *args, **kwargs):
+        fullname = args[0]
+        copy_one_file(fullname, self.mf.sources_path, self.mf.dst_path)
+            # self.file_logger.info(fullname + "\n")
+
+
+if __name__ == "__main__":
+    mf = MoveFile()
+    mf.sources_path = r"F:\fun2\test_gif"
+    # mf.dst_path = r"F:\fun2\test_gif2"
+    mf.dst_path = r"\\192.168.31.123\home\cjvip\qinym\soopat\image"
+    # mf.dst_path = r"\\192.168.31.177\down_data\test"
+
+    mft = MoveFileThread(30, mf)
+    mft.run()

re_common/baselibrary/tools/move_mongo/mongo_table_to_file.py

@@ -0,0 +1,63 @@
+import asyncio
+import gzip
+import json
+
+from re_common.baselibrary.utils.basefile import BaseFile
+from re_common.baselibrary.utils.basegzip import BaseGzip
+from re_common.baselibrary.utils.basemotor import BaseMotor
+
+
+class Configs(object):
+
+    def __init__(self):
+        self.mgdb_conn_motor = "mongodb://cjrw:vipdatacenter@192.168.31.243:32920,192.168.31.206:32920,192.168.31.208:32920/?authSource=htmljson"
+        self.mgdb_db = "htmljson"
+        self.mgdb_col = "other"
+        self.filepath = r"F:\fun3\up\detail\mbalib.big_json.gz"
+        self.query = {}
+        self.feild = None
+        self.one_file_num = 100000
+
+
+class MongoToFile(object):
+    def __init__(self, conf):
+        self.conf = conf
+        self.file_open = None
+        self.i = 0
+
+    def init_conn_mongodb(self):
+        self.bs = BaseMotor()
+        self.bs.AsyncIOMotorClient(
+            self.conf.mgdb_conn_motor,
+            self.conf.mgdb_db)
+        self.bs.get_col(self.conf.mgdb_col)
+
+    def open_file(self):
+        i = BaseGzip.get_gz_line_num(self.conf.filepath)
+        if i >= self.conf.one_file_num:
+            self.conf.filepath = BaseFile.get_new_filename(self.conf.filepath)
+        self.file_open = gzip.open(self.conf.filepath, "wb")
+
+    def close_file(self):
+        self.file_open.close()
+
+    def asyncio_run(self):
+        asyncio.get_event_loop().run_until_complete(
+            self.bs.find(self.dic_deal, self.conf.query, self.conf.feild))
+        self.close_file()
+
+    def hook_doc(self, doc):
+        return doc
+
+    async def dic_deal(self, doc):
+        doc = self.hook_doc(doc)
+        line = json.dumps(doc, ensure_ascii=False) + '\n'
+        lines = line.encode()
+        self.file_open.write(lines)
+        self.i = self.i + 1
+        print(self.i)
+        if self.i >= self.conf.one_file_num:
+            self.close_file()
+            self.conf.filepath = BaseFile.get_new_filename(self.conf.filepath)
+            self.open_file()
+            self.i = 0