def getFileId(filepath, matchedFilesdict):
from fup.utils.commun import delPunctuationMarks
file = filepath.split('\\')[-1]
#print('getFileIdfunc: ', file, matchedFilesdict)
for kid, vfname in matchedFilesdict.items():
if delPunctuationMarks(vfname) == delPunctuationMarks(file):
#print(kid, vfname)
return kid, vfname
def checkFileInfo(fileinfo):
import re
import pandas as pd
from fup.utils.dbwrap import sql2df
from fup.helpers.files import delDirsnotindb
from fup.utils.commun import delPunctuationMarks
#print("fileinfo ",fileinfo)
histdf = sql2df('fileshistory')
filedict = {}
for k, v in fileinfo.items():
filedict[k] = [v]
filedf = pd.DataFrame.from_dict(filedict)
#print("yuhuu filedict", filedict)
merged_name = filedf.merge(histdf,
left_on=['FileName'],
right_on=['FileName'],
suffixes=('', '_y'))
colstodel = [
col for col in merged_name.columns.tolist() if re.search('_y', col)
]
for col in colstodel:
merged_name.drop(col, axis=1, inplace=True)
merged_size = filedf.merge(histdf,
left_on=['FileSizeBytes'],
right_on=['FileSizeBytes'],
suffixes=('', '_y'))
colstodel = [
col for col in merged_size.columns.tolist() if re.search('_y', col)
]
for col in colstodel:
merged_size.drop(col, axis=1, inplace=True)
merged_mtime = filedf.merge(histdf,
left_on=['ModificationDate'],
right_on=['ModificationDate'],
suffixes=('', '_y'))
colstodel = [
col for col in merged_mtime.columns.tolist() if re.search('_y', col)
]
for col in colstodel:
merged_mtime.drop(col, axis=1, inplace=True)
if (merged_name.shape[0] == 0):
return True
elif (merged_name.shape[0] == 0) and (merged_size.shape[0] == 0):
return True
elif (merged_name.shape[0] == 0) and (merged_size.shape[0]
== 0) and (merged_mtime.shape[0]
== 0):
return True
else:
try:
filename_merge = merged_name['FileName'].tolist()[0]
for fname in histdf['FileName']:
if delPunctuationMarks(fname) == delPunctuationMarks(
filename_merge):
histdf_filtered = histdf[histdf['FileName'] == fname]
filename_hist = histdf_filtered['FileName'].tolist()
batchid_hist = histdf_filtered['AddedInBatch'].tolist()
fileid_hist = histdf_filtered['FileID'].tolist()
delDirsnotindb()
response = "File '{}' was probably added before! Check BID_{}, FID_{}".format(
filename_hist[0], batchid_hist[0], fileid_hist[0])
#print(response)
return response
except Exception as e:
return str(
"Probably files in NEW are already inserted. Got: {}".format(
e))