def botszip(ta_from,endstatus,**argv):
''' zip file;
editype & messagetype are unchanged.
'''
ta_to = ta_from.copyta(status=endstatus)
tofilename = unicode(ta_to.idta)
pluginzipfilehandler = zipfile.ZipFile(botslib.abspathdata(filename=tofilename), 'w', zipfile.ZIP_DEFLATED)
pluginzipfilehandler.write(botslib.abspathdata(filename=ta_from.filename),ta_from.filename)
pluginzipfilehandler.close()
ta_to.update(statust=OK,filename=tofilename) #update outmessage transaction with ta_info;
def botsunzip(ta_from,endstatus,password=None,pass_non_zip=False,**argv):
''' unzip file;
editype & messagetype are unchanged.
'''
try:
z = zipfile.ZipFile(botslib.abspathdata(filename=ta_from.filename),mode='r')
except zipfile.BadZipfile:
botsglobal.logger.debug(_(u'File is not a zip-file.'))
if pass_non_zip: #just pass the file
botsglobal.logger.debug(_(u'"pass_non_zip" is True, just pass the file.'))
ta_to = ta_from.copyta(status=endstatus,statust=OK)
return
raise botslib.InMessageError(_(u'File is not a zip-file.'))
if password:
z.setpassword(password)
for f in z.infolist():
if f.filename[-1] == '/': #check if this is a dir; if so continue
continue
ta_to = ta_from.copyta(status=endstatus)
tofilename = str(ta_to.idta)
tofile = botslib.opendata(tofilename,'wb')
tofile.write(z.read(f.filename))
tofile.close()
ta_to.update(statust=OK,filename=tofilename) #update outmessage transaction with ta_info;
botsglobal.logger.debug(_(u' File written: "%s".'),tofilename)
def botsunzip(ta_from, endstatus, password=None, pass_non_zip=False, **argv):
''' unzip file;
editype & messagetype are unchanged.
'''
try:
z = zipfile.ZipFile(botslib.abspathdata(filename=ta_from.filename),
mode='r')
except zipfile.BadZipfile:
botsglobal.logger.debug(_(u'File is not a zip-file.'))
if pass_non_zip: #just pass the file
botsglobal.logger.debug(
_(u'"pass_non_zip" is True, just pass the file.'))
ta_to = ta_from.copyta(status=endstatus, statust=OK)
return
raise botslib.InMessageError(_(u'File is not a zip-file.'))
if password:
z.setpassword(password)
for f in z.infolist():
if f.filename[-1] == '/': #check if this is a dir; if so continue
continue
ta_to = ta_from.copyta(status=endstatus)
tofilename = str(ta_to.idta)
tofile = botslib.opendata(tofilename, 'wb')
tofile.write(z.read(f.filename))
tofile.close()
ta_to.update(
statust=OK,
filename=tofilename) #update outmessage transaction with ta_info;
botsglobal.logger.debug(_(u' File written: "%s".'), tofilename)
def initfromfile(self):
filename = botslib.abspathdata(self.ta_info['filename'])
self.ta_info['attributemarker'] = '__'
parser = ET.XMLParser()
etree = ET.ElementTree() #ElementTree: lexes, parses, makes etree; etree is quite similar to bots-node trees but conversion is needed
etreeroot = etree.parse(filename, parser)
self.root = self._etree2botstree(etreeroot) #convert etree to bots-nodes-tree
def handle_out_message(out_translated,ta_translated):
if out_translated.ta_info['statust'] == DONE: #if indicated in mappingscript the message should be discarded
botsglobal.logger.debug(_(u'No output file because mappingscript explicitly indicated this.'))
out_translated.ta_info['filename'] = ''
out_translated.ta_info['status'] = DISCARD
else:
botsglobal.logger.debug(_(u'Start writing output file editype "%(editype)s" messagetype "%(messagetype)s".'),out_translated.ta_info)
out_translated.writeall() #write result of translation.
out_translated.ta_info['filesize'] = os.path.getsize(botslib.abspathdata(out_translated.ta_info['filename'])) #get filesize
ta_translated.update(**out_translated.ta_info) #update outmessage transaction with ta_info; statust = OK
def write_outgoing(run):
outputdir = botslib.join(run.outpath)
botslib.dirshouldbethere(outputdir)
for outgoing in run.outgoing:
if not outgoing['error']:
try:
unique_filename = filename_formatter(run.outfilename,outgoing)
tofilepath = botslib.join(outputdir,unique_filename)
fromfilepath = botslib.abspathdata(outgoing['filename'])
shutil.move(fromfilepath,tofilepath)
except:
txt = botslib.txtexc()
outgoing.update({'error':txt})
else:
outgoing.update({'outfilename':tofilepath})
def read_incoming(run):
outputdir = botslib.join(run.inpath,run.infilename)
filelist = [filename for filename in glob.iglob(outputdir) if os.path.isfile(filename)]
filelist.sort()
for infilename in filelist:
try:
filename = transform.unique('bots_file_name')
abs_filename = botslib.abspathdata(filename)
shutil.copy(infilename,abs_filename) #move if to be delted
except:
txt = botslib.txtexc()
else:
txt = '' #no errors
finally:
run.incoming.append({'infilename':infilename,'filename':filename,'error':txt,'editype':run.translation['editype'],'messagetype':run.translation['messagetype']})
def write_outgoing(run):
outputdir = botslib.join(run.outpath)
botslib.dirshouldbethere(outputdir)
for outgoing in run.outgoing:
if not outgoing['error']:
try:
unique_filename = filename_formatter(run.outfilename, outgoing)
tofilepath = botslib.join(outputdir, unique_filename)
fromfilepath = botslib.abspathdata(outgoing['filename'])
shutil.move(fromfilepath, tofilepath)
except:
txt = botslib.txtexc()
outgoing.update({'error': txt})
else:
outgoing.update({'outfilename': tofilepath})
def handle_out_message(out_translated, ta_translated):
if out_translated.ta_info[
'statust'] == DONE: #if indicated in mappingscript the message should be discarded
botsglobal.logger.debug(
_(u'No output file because mappingscript explicitly indicated this.'
))
out_translated.ta_info['filename'] = ''
out_translated.ta_info['status'] = DISCARD
else:
botsglobal.logger.debug(
_(u'Start writing output file editype "%(editype)s" messagetype "%(messagetype)s".'
), out_translated.ta_info)
out_translated.writeall() #write result of translation.
out_translated.ta_info['filesize'] = os.path.getsize(
botslib.abspathdata(
out_translated.ta_info['filename'])) #get filesize
ta_translated.update(
**out_translated.ta_info
) #update outmessage transaction with ta_info; statust = OK
def read_incoming(run):
outputdir = botslib.join(run.inpath, run.infilename)
filelist = [
filename for filename in glob.iglob(outputdir)
if os.path.isfile(filename)
]
filelist.sort()
for infilename in filelist:
try:
filename = transform.unique('bots_file_name')
abs_filename = botslib.abspathdata(filename)
shutil.copy(infilename, abs_filename) #move if to be delted
except:
txt = botslib.txtexc()
else:
txt = '' #no errors
finally:
run.incoming.append({
'infilename': infilename,
'filename': filename,
'error': txt,
'editype': run.translation['editype'],
'messagetype': run.translation['messagetype']
})
def extractexcel(ta_from, endstatus, **argv):
''' extract excel file.
editype & messagetype are unchanged.
'''
#***functions used by extractexcel
#-------------------------------------------------------------------------------
def read_xls(infilename):
# Read excel first sheet into a 2-d array
book = xlrd.open_workbook(infilename)
sheet = book.sheet_by_index(0)
formatter = lambda (t, v): format_excelval(book, t, v, False)
xlsdata = []
for row in range(sheet.nrows):
(types, values) = (sheet.row_types(row), sheet.row_values(row))
xlsdata.append(map(formatter, zip(types, values)))
return xlsdata
#-------------------------------------------------------------------------------
def dump_csv(xlsdata, tofilename):
stream = botslib.opendata(tofilename, 'wb')
csvout = csv.writer(stream,
quotechar=quotechar,
delimiter=field_sep,
doublequote=doublequote,
escapechar=escape)
csvout.writerows(map(utf8ize, xlsdata))
stream.close()
#-------------------------------------------------------------------------------
def format_excelval(book, type, value, wanttupledate):
# Clean up the incoming excel data for some data types
returnrow = []
if type == 2:
if value == int(value):
value = int(value)
elif type == 3:
datetuple = xlrd.xldate_as_tuple(value, book.datemode)
value = datetuple if wanttupledate else tupledate_to_isodate(
datetuple)
elif type == 5:
value = xlrd.error_text_from_code[value]
return value
#-------------------------------------------------------------------------------
def tupledate_to_isodate(tupledate):
# Turns a gregorian (year, month, day, hour, minute, nearest_second) into a
# standard YYYY-MM-DDTHH:MM:SS ISO date.
(y, m, d, hh, mm, ss) = tupledate
nonzero = lambda n: n != 0
date = "%04d-%02d-%02d" % (y, m, d) if filter(nonzero,
(y, m, d)) else ''
time = "T%02d:%02d:%02d" % (hh, mm, ss) if filter(
nonzero, (hh, mm, ss)) or not date else ''
return date + time
#-------------------------------------------------------------------------------
def utf8ize(l):
# Make string-like things into utf-8, leave other things alone
return [
unicode(s).encode(charset) if hasattr(s, 'encode') else s
for s in l
]
#***end functions used by extractexcel
import xlrd
import csv
#get parameters for csv-format; defaults are as the csv defaults (in grammar.py)
charset = argv.get('charset', "utf-8")
quotechar = argv.get('quotechar', "'")
field_sep = argv.get('field_sep', ':')
escape = argv.get('escape', '')
if escape:
doublequote = False
else:
doublequote = True
try:
infilename = botslib.abspathdata(ta_from.filename)
xlsdata = read_xls(infilename)
ta_to = ta_from.copyta(status=endstatus)
tofilename = str(ta_to.idta)
dump_csv(xlsdata, tofilename)
ta_to.update(
statust=OK,
filename=tofilename) #update outmessage transaction with ta_info;
botsglobal.logger.debug(_(u' File written: "%s".'), tofilename)
except:
txt = botslib.txtexc()
botsglobal.logger.error(
_(u'Excel extraction failed, may not be an Excel file? Error:\n%s'
), txt)
raise botslib.InMessageError(_(
u'Excel extraction failed, may not be an Excel file? Error:\n$error'
),
error=txt)
def mergemessages(startstatus, endstatus, idroute, rootidta=None):
''' Merges and/or envelopes one or more messages to one file;
In db-ta: attribute 'merge' indicates message should be merged with similar messages; 'merge' is generated in translation from messagetype-grammar
If merge is False: 1 message per envelope - no merging, else append all similar messages to one file
Implementation as separate loops: one for merge&envelope, another for enveloping only
db-ta status TRANSLATED---->FILEOUT
'''
if rootidta is None:
rootidta = botsglobal.currentrun.get_minta4query()
#**********for messages only to envelope (no merging)
for row in botslib.query(
u'''SELECT editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,nrmessages,idroute,merge,idta,filename,rsrv3
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND idroute=%(idroute)s
ORDER BY idta
''', {
'rootidta': rootidta,
'status': startstatus,
'statust': OK,
'merge': False,
'idroute': idroute
}):
try:
ta_info = dict(row)
ta_fromfile = botslib.OldTransaction(
ta_info['idta']) #edi message to envelope
ta_tofile = ta_fromfile.copyta(
status=endstatus
) #edifile for enveloped message; attributes of not-enveloped message are copied...
ta_info['filename'] = unicode(
ta_tofile.idta) #create filename for enveloped message
botsglobal.logger.debug(
u'Envelope 1 message editype: %(editype)s, messagetype: %(messagetype)s.',
ta_info)
envelope(ta_info, [row['filename']])
ta_info['filesize'] = os.path.getsize(
botslib.abspathdata(ta_info['filename'])) #get filesize
except:
txt = botslib.txtexc()
ta_tofile.update(statust=ERROR, errortext=txt)
else:
ta_tofile.update(
statust=OK,
**ta_info) #selection is used to update enveloped message;
finally:
ta_fromfile.update(statust=DONE)
#**********for messages to merge & envelope
for row in botslib.query(
u'''SELECT editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3,sum(nrmessages) as nrmessages
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND idroute=%(idroute)s
GROUP BY editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3
ORDER BY editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3
''', {
'rootidta': rootidta,
'status': startstatus,
'statust': OK,
'merge': True,
'idroute': idroute
}):
try:
ta_info = dict(row)
ta_tofile = botslib.NewTransaction(
status=endstatus,
idroute=idroute) #edifile for enveloped messages
ta_info.update({
'idroute': idroute,
'merge': False,
'filename': unicode(ta_tofile.idta)
}) #SELECT/GROUP BY gives only values that are the grouped
filename_list = []
#gather individual idta and filenames
#explicitly allow formpartner/topartner to be None/NULL
for row2 in botslib.query(
u'''SELECT idta, filename
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND editype=%(editype)s
AND messagetype=%(messagetype)s
AND (frompartner=%(frompartner)s OR frompartner IS NULL)
AND (topartner=%(topartner)s OR topartner IS NULL)
AND testindicator=%(testindicator)s
AND charset=%(charset)s
ORDER BY idta
''', {
'rootidta': rootidta,
'status': startstatus,
'statust': OK,
'merge': True,
'editype': ta_info['editype'],
'messagetype': ta_info['messagetype'],
'frompartner': ta_info['frompartner'],
'topartner': ta_info['topartner'],
'testindicator': ta_info['testindicator'],
'charset': ta_info['charset'],
'rsrv3': ta_info['rsrv3']
}):
ta_fromfile = botslib.OldTransaction(
row2['idta']) #edi message to be merged/envelope
ta_fromfile.update(
child=ta_tofile.idta,
statust=DONE) #st child because of n->1 relation
filename_list.append(row2['filename'])
botsglobal.logger.debug(
u'Merge and envelope: editype: %(editype)s, messagetype: %(messagetype)s, %(nrmessages)s messages',
ta_info)
envelope(ta_info, filename_list)
ta_info['filesize'] = os.path.getsize(
botslib.abspathdata(ta_info['filename'])) #get filesize
except:
txt = botslib.txtexc()
ta_tofile.update(statust=ERROR, errortext=txt)
else:
ta_tofile.update(statust=OK, **ta_info)
def mergemessages(startstatus,endstatus,idroute,rootidta=None):
''' Merges and/or envelopes one or more messages to one file;
In db-ta: attribute 'merge' indicates message should be merged with similar messages; 'merge' is generated in translation from messagetype-grammar
If merge is False: 1 message per envelope - no merging, else append all similar messages to one file
Implementation as separate loops: one for merge&envelope, another for enveloping only
db-ta status TRANSLATED---->FILEOUT
'''
if rootidta is None:
rootidta = botsglobal.currentrun.get_minta4query()
#**********for messages only to envelope (no merging)
for row in botslib.query(u'''SELECT editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,nrmessages,idroute,merge,idta,filename,rsrv3
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND idroute=%(idroute)s
ORDER BY idta
''',
{'rootidta':rootidta,'status':startstatus,'statust':OK,'merge':False,'idroute':idroute}):
try:
ta_info = dict(row)
ta_fromfile = botslib.OldTransaction(ta_info['idta']) #edi message to envelope
ta_tofile = ta_fromfile.copyta(status=endstatus) #edifile for enveloped message; attributes of not-enveloped message are copied...
ta_info['filename'] = unicode(ta_tofile.idta) #create filename for enveloped message
botsglobal.logger.debug(u'Envelope 1 message editype: %(editype)s, messagetype: %(messagetype)s.',ta_info)
envelope(ta_info,[row['filename']])
ta_info['filesize'] = os.path.getsize(botslib.abspathdata(ta_info['filename'])) #get filesize
except:
txt = botslib.txtexc()
ta_tofile.update(statust=ERROR,errortext=txt)
else:
ta_tofile.update(statust=OK,**ta_info) #selection is used to update enveloped message;
finally:
ta_fromfile.update(statust=DONE)
#**********for messages to merge & envelope
for row in botslib.query(u'''SELECT editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3,sum(nrmessages) as nrmessages
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND idroute=%(idroute)s
GROUP BY editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3
ORDER BY editype,messagetype,frompartner,topartner,testindicator,charset,contenttype,envelope,rsrv3
''',
{'rootidta':rootidta,'status':startstatus,'statust':OK,'merge':True,'idroute':idroute}):
try:
ta_info = dict(row)
ta_tofile = botslib.NewTransaction(status=endstatus,idroute=idroute) #edifile for enveloped messages
ta_info.update({'idroute':idroute,'merge':False,'filename':unicode(ta_tofile.idta)}) #SELECT/GROUP BY gives only values that are the grouped
filename_list = []
#gather individual idta and filenames
#explicitly allow formpartner/topartner to be None/NULL
for row2 in botslib.query(u'''SELECT idta, filename
FROM ta
WHERE idta>%(rootidta)s
AND status=%(status)s
AND statust=%(statust)s
AND merge=%(merge)s
AND editype=%(editype)s
AND messagetype=%(messagetype)s
AND (frompartner=%(frompartner)s OR frompartner IS NULL)
AND (topartner=%(topartner)s OR topartner IS NULL)
AND testindicator=%(testindicator)s
AND charset=%(charset)s
ORDER BY idta
''',
{'rootidta':rootidta,'status':startstatus,'statust':OK,'merge':True,
'editype':ta_info['editype'],'messagetype':ta_info['messagetype'],'frompartner':ta_info['frompartner'],
'topartner':ta_info['topartner'],'testindicator':ta_info['testindicator'],'charset':ta_info['charset'],
'rsrv3':ta_info['rsrv3']}):
ta_fromfile = botslib.OldTransaction(row2['idta']) #edi message to be merged/envelope
ta_fromfile.update(child=ta_tofile.idta,statust=DONE) #st child because of n->1 relation
filename_list.append(row2['filename'])
botsglobal.logger.debug(u'Merge and envelope: editype: %(editype)s, messagetype: %(messagetype)s, %(nrmessages)s messages',ta_info)
envelope(ta_info,filename_list)
ta_info['filesize'] = os.path.getsize(botslib.abspathdata(ta_info['filename'])) #get filesize
except:
txt = botslib.txtexc()
ta_tofile.update(statust=ERROR,errortext=txt)
else:
ta_tofile.update(statust=OK,**ta_info)
def extractpdf(ta_from,endstatus,**argv):
''' Try to extract text content of a PDF file to a csv.
You know this is not a great idea, right? But we'll do the best we can anyway!
Page and line numbers are added to each row.
Columns and rows are based on the x and y coordinates of each text element within tolerance allowed.
Multiple text elements may combine to make one field, some PDFs have every character separated!
You may need to experiment with x_group and y_group values, but defaults seem ok for most files.
Output csv is UTF-8 encoded - The csv module doesn't directly support reading and writing Unicode
If the PDF is just an image, all bets are off. Maybe try OCR, good luck with that!
Mike Griffin 14/12/2011
'''
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams, LTContainer, LTText, LTTextBox
import csv
class CsvConverter(TextConverter):
def __init__(self, *args, **kwargs):
TextConverter.__init__(self, *args, **kwargs)
def receive_layout(self, ltpage):
# recursively get every text element and it's coordinates
def render(item):
if isinstance(item, LTContainer):
for child in item:
render(child)
elif isinstance(item, LTText):
(unused1,unused2,x,y) = item.bbox
# group the y values (rows) within group tolerance
for v in yv:
if y > v-y_group and y < v+y_group:
y = v
yv.append(y)
line = lines[int(-y)]
line[x] = item.get_text().encode('utf-8')
from collections import defaultdict
lines = defaultdict(lambda : {})
yv = []
render(ltpage)
lineid = 0
for y in sorted(lines.keys()):
line = lines[y]
lineid += 1
csvdata = [ltpage.pageid,lineid] # first 2 columns are page and line numbers
# group the x values (fields) within group tolerance
p = 0
field_txt = ''
for x in sorted(line.keys()):
gap = x - p
if p > 0 and gap > x_group:
csvdata.append(field_txt)
field_txt = ''
field_txt += line[x]
p = x
csvdata.append(field_txt)
csvout.writerow(csvdata)
if lineid == 0:
raise botslib.InMessageError(_(u'PDF text extraction failed, it may contain just image(s)?'))
#get some optional parameters
x_group = argv.get('x_group',10) # group text closer than this as one field
y_group = argv.get('y_group',5) # group lines closer than this as one line
password = argv.get('password','')
quotechar = argv.get('quotechar','"')
field_sep = argv.get('field_sep',',')
escape = argv.get('escape','\\')
charset = argv.get('charset','utf-8')
if not escape:
doublequote = True
else:
doublequote = False
try:
pdf_stream = botslib.opendata(ta_from.filename, 'rb')
ta_to = ta_from.copyta(status=endstatus)
tofilename = unicode(ta_to.idta)
csv_stream = botslib.opendata(tofilename,'wb')
csvout = csv.writer(csv_stream, quotechar=quotechar, delimiter=field_sep, doublequote=doublequote, escapechar=escape)
# Process PDF
rsrcmgr = PDFResourceManager(caching=True)
device = CsvConverter(rsrcmgr, csv_stream, codec=charset)
process_pdf(rsrcmgr, device, pdf_stream, pagenos=set(), password=password, caching=True, check_extractable=True)
device.close()
pdf_stream.close()
csv_stream.close()
filesize = os.path.getsize(botslib.abspathdata(tofilename))
ta_to.update(statust=OK,filename=tofilename,filesize=filesize) #update outmessage transaction with ta_info;
botsglobal.logger.debug(_(u' File written: "%(tofilename)s".'),{'tofilename':tofilename})
except:
txt = botslib.txtexc()
botsglobal.logger.error(_(u'PDF extraction failed, may not be a PDF file? Error:\n%(txt)s'),{'txt':txt})
raise botslib.InMessageError(_(u'PDF extraction failed, may not be a PDF file? Error:\n%(txt)s'),{'txt':txt})
def extractexcel(ta_from,endstatus,**argv):
''' extract excel file.
editype & messagetype are unchanged.
'''
#***functions used by extractexcel
#-------------------------------------------------------------------------------
def read_xls(infilename):
# Read excel first sheet into a 2-d array
book = xlrd.open_workbook(infilename)
sheet = book.sheet_by_index(0)
formatter = lambda(t,v): format_excelval(book,t,v,False)
xlsdata = []
for row in range(sheet.nrows):
(types, values) = (sheet.row_types(row), sheet.row_values(row))
xlsdata.append(map(formatter, zip(types, values)))
return xlsdata
#-------------------------------------------------------------------------------
def dump_csv(xlsdata, tofilename):
stream = botslib.opendata(tofilename, 'wb')
csvout = csv.writer(stream, quotechar=quotechar, delimiter=field_sep, doublequote=doublequote, escapechar=escape)
csvout.writerows( map(utf8ize, xlsdata) )
stream.close()
#-------------------------------------------------------------------------------
def format_excelval(book, type, value, wanttupledate):
# Clean up the incoming excel data for some data types
returnrow = []
if type == 2:
if value == int(value):
value = int(value)
elif type == 3:
datetuple = xlrd.xldate_as_tuple(value, book.datemode)
value = datetuple if wanttupledate else tupledate_to_isodate(datetuple)
elif type == 5:
value = xlrd.error_text_from_code[value]
return value
#-------------------------------------------------------------------------------
def tupledate_to_isodate(tupledate):
# Turns a gregorian (year, month, day, hour, minute, nearest_second) into a
# standard YYYY-MM-DDTHH:MM:SS ISO date.
(y,m,d, hh,mm,ss) = tupledate
nonzero = lambda n: n != 0
date = "%04d-%02d-%02d" % (y,m,d) if filter(nonzero, (y,m,d)) else ''
time = "T%02d:%02d:%02d" % (hh,mm,ss) if filter(nonzero, (hh,mm,ss)) or not date else ''
return date+time
#-------------------------------------------------------------------------------
def utf8ize(l):
# Make string-like things into utf-8, leave other things alone
return [unicode(s).encode(charset) if hasattr(s,'encode') else s for s in l]
#***end functions used by extractexcel
import xlrd
import csv
#get parameters for csv-format; defaults are as the csv defaults (in grammar.py)
charset = argv.get('charset',"utf-8")
quotechar = argv.get('quotechar',"'")
field_sep = argv.get('field_sep',':')
escape = argv.get('escape','')
if escape:
doublequote = False
else:
doublequote = True
try:
infilename = botslib.abspathdata(ta_from.filename)
xlsdata = read_xls(infilename)
ta_to = ta_from.copyta(status=endstatus)
tofilename = str(ta_to.idta)
dump_csv(xlsdata,tofilename)
ta_to.update(statust=OK,filename=tofilename) #update outmessage transaction with ta_info;
botsglobal.logger.debug(_(u' File written: "%s".'),tofilename)
except:
txt = botslib.txtexc()
botsglobal.logger.error(_(u'Excel extraction failed, may not be an Excel file? Error:\n%s'),txt)
raise botslib.InMessageError(_(u'Excel extraction failed, may not be an Excel file? Error:\n$error'),error=txt)
def filelist2absolutepaths(self):
""" utility function; some classes need absolute filenames eg for xml-including"""
return [botslib.abspathdata(filename) for filename in self.ta_list]
def filelist2absolutepaths(self):
''' utility function; some classes need absolute filenames eg for xml-including'''
return [botslib.abspathdata(filename) for filename in self.ta_list]
