|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
import os,json,sys
STREAM = "EXPRESS"
JSON_NAME = "certif.json"
def splitByTag(line,tags=["td","th"]):
values = []
pos = 0
while pos > -1:
firstTag=None
firstTagPos=len(line)
for tag in tags:
posTag=line.find("<"+tag,pos)
if posTag<firstTagPos and posTag>-1:
firstTag=tag
firstTagPos=posTag
if not firstTag:
break
tag=firstTag
posStartTag = line.find("<"+tag,pos)
posStartContent = line.find(">",posStartTag)+1
posEnd = line.find("</"+tag,posStartContent)
pos = posEnd
values.append(line[posStartContent:posEnd])
return values
def getComment(line):
tag="<span title=\""
startComment=line.find(tag)+len(tag)
stopComment=line.find("\"",startComment)
return(line[startComment:stopComment])
def getRunQuality(fName=JSON_NAME):
runQuality = {}
if os.path.isfile(fName):
with open(fName) as f:
runQuality=json.load(f)
return runQuality
def getHTMLtable(fName=".certif_temp.html"):
table=""
title =""
with open(fName,"r") as certifFile:
certifRaw = certifFile.read()
if len(certifRaw)<100:
return(0,0)
title = certifRaw[certifRaw.find("<title>")+len("<title>"):certifRaw.find("</title>")]
table=certifRaw.split("table>")[1]
return(title,table)
def generateJSON():
# Getting certification HTML file
os.system("wget http://vocms061.cern.ch/event_display/RunList/status.Collisions17.html -O .certif_temp.html > /dev/null 2>&1")
if not os.path.isfile(".certif_temp.html"):
print("Unable to download file")
return(1)
runQuality = getRunQuality()
if runQuality == {}:
print("Warning, no %s found. Creating new list."%JSON_NAME)
(title,table)=getHTMLtable()
if table==0:
print("Error, Unable to download run table.")
return(1)
runQuality["Last update"] = title[title.find("(")+1:title.find(")")]
#Clean table and split per line
table.replace("\n","").replace("<tr>","")
table=table.split("</tr>")
lenExpected = -1 #Expected width of line
colNumber = 0 #Column id to read status
for line in table:
entry = splitByTag(line)
if lenExpected < 0 :
lenExpected = len(entry)
for i in range(len(entry)):
if STREAM.lower() in entry[i].lower():
colNumber = i
else:
if len(entry)==lenExpected:
comment=getComment(entry[colNumber])
runQuality[entry[0]]={"qual":entry[colNumber][:4],"comment":comment}
elif len(entry)>0:
print("Error, unrecognized line !")
return 1
with open(JSON_NAME,'w') as data_file:
data_file.write(json.dumps(runQuality))
os.system("rm .certif_temp.html")
return(0)
def get():
if generateJSON()!=0:
print("ERROR, JSON file not updated... Loading old file.")
if not JSON_NAME in os.listdir("."):
print("ERROR, no JSON file available...")
return({})
else:
return getRunQuality()
def checkRun(runNumber, runQuality):
if not str(runNumber) in runQuality.keys():
print("WARNING : no certification info for run %s"%runNumber)
return(0)
else:
print("Data certification for run %s is %s"%(runNumber,runQuality[str(runNumber)]["qual"]))
if not "GOOD" in runQuality[str(runNumber)]["qual"]:
print("Reason : %s"%runQuality[str(runNumber)]["comment"])
return("GOOD" in runQuality[str(runNumber)]["qual"])
if __name__ == "__main__":
generateJSON()
qual = get()
for key in qual.keys():
checkRun(int(key),qual)
|