bug fix & refactoring

setup.py

@@ -3,16 +3,17 @@
 from setuptools import setup, find_packages
 import os
 import sys
+import smart.info
 def read(fname):
     return open(os.path.join(os.path.dirname(__file__), fname)).read() 
 args    = {
-    "name":"smart-top",
-    "version":"1.0.6",
-    "author":"The Phi Technology LLC","author_email":"info@the-phi.com",
-    "license":"MIT",
+    "name":smart.info.__app_name__,
+    "version":smart.info.__version__,
+    "author":smart.info.__author__,"author_email":"info@the-phi.com",
+    "license":smart.info.__license__,
     "packages":["smart","smart.top","smart.folder","smart.logger"]}
 args["keywords"]=['mongodb','couchdb','rabbitmq','file','read','write','s3','sqlite']
-args["install_requires"] = ['pandas','numpy','requests','data-transport@git+https://healthcareio.the-phi.com/git/code/transport.git']
+args["install_requires"] = ['pandas','numpy','requests','data-transport@git+https://github.com/lnyemba/data-transport.git']
 args["url"] =   "https://dev.the-phi.com/git/steve/smart-top.git"
 args['scripts'] = ['bin/smart-top']
 # args['entry_point'] = {'console-scripts':['smart-top=smart-top:main']}

smart/__init__.py

@@ -7,9 +7,124 @@ usage:
 dependencies :
     data-transport  pip install git+https://dev.the-phi.com/git/steve/data-transport.git
 """
+import smart
 import smart.top
 import smart.folder
+import smart.top
 import smart.logger
+import smart.files
+import uuid
+import typer
+import smart.info
+import json
+import os
+import transport
+import shutil
+from datetime import datetime
+_cli = typer.Typer()
+
+@_cli.command(name='top')
+def apply_apps (app:str=None,user:str=None):
+    """
+    This function looks at applications/commands running on the system
+    """
+    
+    _df = smart.top.read()
+    _id = 'apps' if not app else app
+    if app  :
+        _index = _df.name == app
+        if _index.sum() :
+            _df = _df[_index]
+    post(_df,_id)
+    
+@_cli.command(name='archive')
+def _archive():
+    """
+    This function will archive the database, by renaming it into
+    """
+    
+    _suffix = datetime.now()
+    _suffix = "-".join([str(_value) for _value in [_suffix.year,_suffix.month,_suffix.day,_suffix.hour,_suffix.minute]])
+    _path = os.sep.join([smart.info.__home__,smart.info.__database__]) 
+    _src = _path + '.db3'
+    if os.path.exists(_src):
+        _target = _path +'-archived-on-'+ _suffix+'.db3'
+        shutil.move(_src,_target)
+        _msg = f"""Archive created successfully at:
+        {_target}"""
+    else:
+        _msg = """
+        Archive function is not available at this time, please try after logs have been stored
+        """
+    print(_msg)
+@_cli.command(name='folder')
+def apply_folder(path:str):
+    """
+    This function will read the content of a folder and generate a 
+    """
+    _df = smart.folder.read(path=path)
+    # print (_df)
+    post(_df,'folders')
+    pass
+@_cli.command (name='files')
+def apply_files(folder:str) :
+    _df = smart.files.read(folder)
+    post(_df,'files')
+@_cli.command(name='register')
+def apply_signup (email:str,key:str=None,provider:str='sqlite') :
+    _config = {"system":{"email":email,"uid":str(uuid.uuid4()),"version":smart.info.__version__},"store":{"provider":provider,"context":"write"}}
+    _db = smart.info.__database__
+    if provider in ['sqlite','sqlite3'] :
+        _db = os.sep.join([smart.info.__home__,_db+'.db3'])
+        _config['store']['database'] = _db
+    else:
+        _config['store']['database'] = _db
+    #
+    # Let us store this in a folder
+    _PATH = smart.info.__home__
+    _verb = "written"
+    if not os.path.exists(_PATH) :
+        os.mkdir(_PATH)
+    else:
+        _verb = "updated"
+    f = open(os.sep.join([_PATH,'config.json']),'w')
+    f.write(json.dumps(_config))
+    f.close()
+    _msg = f"""
+        The configuration file was {_verb} successfully at {smart.info.__home__}
+        data store: 
+            provider {provider}
+            database {_db}
+
+        If your database has security enabled, consider updating "{smart.info.__home__}{os.sep}config.json" For appropriate security
+        Visit https://github.com/lnyemba/data-transport for more information
+    """
+    print ()
+    print (_msg)
+    pass
+def post(_df,_table):
+    """
+    Store data in a given location 
+    """
+    _path = os.sep.join([smart.info.__home__,'config.json'])
+    f = open (_path)
+    _config = json.loads(f.read())
+    f.close()
+    _store = _config['store']
+    if _store['provider'] in ['mongodb','mongo','couch','couchdb'] :
+        _store['collection'] = _table
+    else:
+        _store['table'] = _table
+   
+        
+    writer = transport.factory.instance(**_store)
+    writer.write(_df)
+    if hasattr(writer,'close') :
+        writer.close()
+
+if __name__ == '__main__' :
+    _cli()
+
 # from transport import factory
 
 # class logger :

smart/__main__.py

@@ -0,0 +1 @@
+__init__.py

smart/alert/__init__.py

@@ -1,15 +0,0 @@
-"""
-This file will submit an alert to either a mailbox given a set of parameters, this will perform as following :
-    - as-a-service
-    - embedded
-"""
-
-check = None
-def post(**args):
-    """
-    This function will submit a report to a given target provided some input 
-    :key    will perform as-a-service
-    :data   data that will be submitted to smtp/queue server
-    :smtp   will send the file to a mailbox
-    """
-    pass

smart/files/__init__.py

@@ -0,0 +1,65 @@
+"""
+This file will submit an alert to either a mailbox given a set of parameters, this will perform as following :
+    - as-a-service
+    - embedded
+"""
+import os
+import pandas as pd
+import subprocess
+import glob
+from datetime import datetime
+
+def post(**args):
+    """
+    This function will submit a report to a given target provided some input 
+    :key    will perform as-a-service
+    :data   data that will be submitted to smtp/queue server
+    :smtp   will send the file to a mailbox
+    """
+    pass
+def parse(_stream):
+    """
+    :stream     single from the output command that has been executed
+    """
+    _blocks = _stream.replace('  ',' ').split(' ')
+    if len(_blocks) > 6 :
+        _user = _blocks[1]
+        _group= _blocks[2]
+        _size = _blocks[3]  # if units are not specified please interpet this as bytes
+        _date = "-".join(_blocks[4:6])
+        _time = _blocks[6]
+        _name = _blocks[-1]
+        if ':' not in _time :
+            _date = _date+' '+_time
+            _time = '00:00'
+        else:
+            _date = _date+'-'+str(datetime.now().year)
+        _name = _blocks[-1]
+        return {'user':_user,'date':_date,'time':_time,'size':_size,'content':None,'name':_name}
+def apply(_cmd, parser=None):
+    handler = subprocess.Popen(_cmd,shell=True,stdout=subprocess.PIPE,encoding='utf-8')	    		
+    stream = handler.communicate()[0].split('\n')
+    stream =  [line.strip() for line in stream]
+    if not parser :
+        # print (dict(zip(['hash','names'],stream[0].split())))
+        
+        stream = [ line.strip().replace('  ',' ').split(' ') for line in stream if len(line.strip().split()) == 2]
+        return pd.DataFrame([dict(zip(['content','name'],line)) for line in stream])
+        # return pd.DataFrame([ line.split() for line in stream ])
+        
+        # return pd.DataFrame( dict(zip(['checksum','name'],[line.strip().split(' '))) for line in stream if line.strip() != '']) )
+    else:
+        return pd.DataFrame([ parser(line.strip()) for line in stream if line.strip() != ''])
+def read (path):
+    """
+    This function will read files in a folder and provide has expressions of the files
+    """
+    _cmd = ["""find :path -type f -exec md5sum "{}" + """ , """find :path -type f -exec ls -lh "{}" + |grep -E " .*$" -o """]
+    _df = apply(_cmd[0].replace(":path",path))
+    _data= apply(_cmd[1].replace(":path",path),parse)
+    if _data.shape[0] == _df.shape[0] :
+        _data['content'] = _df.content
+    return _data
+    
+
+read('/home/steve/tmp/logs')

smart/folder/__init__.py

@@ -9,6 +9,8 @@ import os
 import pandas as pd
 import io
 import datetime
+import glob
+
 class Util :
     def size(self,stream):
         
@@ -58,8 +60,9 @@ def read(**args):
 
         r = dict(r, **rows)
     N = 0 if not os.path.exists(args['path']) else len( os.listdir(args['path']))
+    path = args['path'] if args['path'].endswith('/')else args['path']+os.sep
     r['path'] = args['path']
-    r['files']= N
+    r['files']= len([filename for filename in glob.iglob(path+'**/**', recursive=True)])
     r['name'] = args['path'].split(os.sep)[-1:][0]
     r['node'] = os.uname()[1]
     r['date'] = datetime.datetime.now().strftime('%m-%d-%Y')

smart/folder/__main__.py

@@ -1,2 +1,2 @@
 import smart.folder
-print (smart.folder.read(path='/home/steve/dev/data/vumc/aou'))
+print (smart.folder.read(path='/home/steve/tmp/logs'))

smart/info.py

@@ -0,0 +1,15 @@
+import os
+__app_name__= "smart-logger"
+__version__ = "1.0-RC"
+__author__ = "Steve L. Nyemba, info@the-phi.com"
+__home__ = os.sep.join([os.environ['HOME'],'.smart-logger'])
+__database__='smart_logs'
+__license__= """
+Copyright 2017 - 2023, The Phi Technology
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+"""

smart/top/__init__.py

@@ -29,10 +29,10 @@ class Util:
             name = p[0]
             args = " ".join(p[1:])
         else:
-            name = cmd.split('/')[len(cmd.split(os.sep))-1]
+            name = cmd.split(os.sep)[len(cmd.split(os.sep))-1]
             args = " ".join(stream[index:]) if index > 0 else ""
         
-        return [name,cmd,args]        
+        return [name,cmd.replace('"',"\\'"),args.replace('"',"\\'")]        
     def parse(self,rows,xchar=';'):
         """
         This function parses the document returned by the execution of the command returns a document that will have to be parsed and formatted
@@ -42,7 +42,6 @@ class Util:
         ARGS_INDEX = 6
         
         for item in rows :
-            
             if rows.index(item) != 0 :
                 parts = item.split(xchar)
                 row = parts[:TIME_INDEX]
@@ -64,7 +63,6 @@ def read(**args) :
     cmd     = "ps -eo pid,user,pmem,pcpu,stat,etime,args|awk 'OFS=\";\" {$1=$1; if($5 > 9) print }'"
     xchar   = ";"
     try:
-        
         handler = subprocess.Popen(cmd,shell=True,stdout=subprocess.PIPE)			
         stream = handler.communicate()[0]        
         if sys.version_info[0] > 2 :
@@ -86,22 +84,22 @@ def read(**args) :
         df['node'] = np.repeat(os.uname()[1],df.shape[0])
         df.columns =['pid','user','mem','cpu','status','started','name','cmd','args','date','time','node']
         
-        
         #
         # We should filter the name of the apps we are interested in here (returning the full logs )
         # @TODO: Add filter here to handle filter on different columns
         #
 
-        if 'name' in args :
+        if 'name' in args and args['name']:
             names = args['name'].split(',')
             r = pd.DataFrame()
             for name in names :
                 # tmp = df[df.name == name.strip() ]
-                ii = df.apply(lambda row: row['name'] == name.strip() or (name.strip() in str(row['name'])),axis=1).tolist()
+                # ii = df.apply(lambda row: row['name'] == name.strip() or (name.strip() in str(row['name'])),axis=1).tolist()
+                ii = df.apply(lambda row: type(row['cmd']) ==str and name.strip() in row['cmd'],axis=1).tolist()
                 tmp= df[ii]
                 # tmp.index = np.arange(tmp.shape[0])
                 if tmp.empty:
-                    tmp = {"pid":None,"user":None,"mem":0,"cpu":0,"status":"-100","started":None,"name":_name,"cmd":None,"args":None,"date":d,"time":t,"node":n}
+                    tmp = {"pid":None,"user":None,"mem":0,"cpu":0,"status":"-100","started":None,"name":name,"cmd":None,"args":None,"date":d,"time":t,"node":n}
                     
                 else:
                     r = r.append(tmp,ignore_index=False)
@@ -112,8 +110,8 @@ def read(**args) :
         # For security reasons lets has the args columns with an MD5 or sha256
         #
         
-        if not df.empty and 'args' in df : 
-            df.args = [hashlib.md5(str(value).encode('utf-8')).hexdigest() for value in df.args.tolist()]
+        # if not df.empty and 'args' in df : 
+        #     df.args = [hashlib.md5(str(value).encode('utf-8')).hexdigest() for value in df.args.tolist()]
         STATUS = {'R':'RUNNING','Z':'DEAD','D':'STASIS','S':'SLEEP','Sl':'SLEEP','Ss':'SLEEP','W':'PAGING','T':'DEAD'}
         df.status = df.status.apply(lambda value: STATUS.get(value,'UNKNOWN'))
         if 'cols' in args :

smart/top/__main__.py

@@ -32,6 +32,7 @@ if len(sys.argv) > 1:
                 
         
         i += 2
+
 if __name__ == '__main__' :
     try:
         if 'help' in SYS_ARGS :
@@ -50,7 +51,9 @@ if __name__ == '__main__' :
             df = pd.DataFrame()
             if 'folder' in SYS_ARGS :
                 for path in SYS_ARGS['folder'].split(',') :
-                    df = df.append(smart.folder.read(path=path))
+                    #df = df.concat(smart.folder.read(path=path))
+                    _df = smart.folder.read(path=path)
+                    df = _df if df.shape[0] == 0 else pd.concat(df,_df)
                 cols = df.columns.tolist()
             else:
                 df =  smart.top.read()
@@ -73,7 +76,8 @@ if __name__ == '__main__' :
                 
             # df = pd.DataFrame(smart.top.read(name='fire'))    
             
-            log = log.append(df)
+            #log = log.append(df)
+            log = df if log.shape[0] ==0 else pd.concat(log,df)
             if not df.empty :
                 print (df[cols])
             if 'watch' in SYS_ARGS :