def fileuploadIMG(UPLOAD_FOLDER, OUTPUT_FOLDER, settings, filename):
#try:
columnNumber = int(settings[2])
if not os.path.exists(ocropy + "/processedFiles/"):
os.makedirs(ocropy + "/processedFiles/")
#check if pdf
pdfFlag = False
im = 0
if '.' in filename and filename.rsplit('.', 1)[1] in set(['pdf']):
pdfFlag = True
else:
#check if image is valid
im = Image.open(UPLOAD_FOLDER + filename)
im = im.getcolors()
if pdfFlag or im == None or len(im) != 0:
#process the image file extract text of it
prepareIMG(UPLOAD_FOLDER, OUTPUT_FOLDER, filename, columnNumber)
#stop if no text found
if os.path.exists(ocropy + "/processedFiles/"+filename+'/ocrWdummy.txt'):
p = subprocess.Popen(["./citeExtract.pl -m extract_citations " + ocropy +"/processedFiles/" +filename+"/ocrWdummy.txt", LOCDB + "tmp/" + filename +"_ParsIMG.xml"],shell=True,stdout=subprocess.PIPE,cwd=parsCit)
parscitstring= p.communicate()[0]
with open("tmp/" + filename + "_ParsIMG.xml", 'w') as f:
f.write(parscitstring)
outputxmlsoup = createBibstruct(filename)
#delete tmp files
os.remove("tmp/" + filename+'_ParsIMG.xml')
#with open(OUTPUT_FOLDER + "Output" + filename +'.xml','w') as xmlf:
# xmlf.write(outputxmlsoup.encode('utf-8'))
with open(ocropy + "/processedFiles/" + filename + '/xmloutput.xml','w') as xmlf:
xmlf.write(outputxmlsoup.encode('utf-8'))
copyfile(ocropy + "/processedFiles/" + filename + "/xmloutput.xml", OUTPUT_FOLDER + filename + "/Output" + filename + ".xml")
copyfile(ocropy + "/processedFiles/" + filename + "/temp.html", OUTPUT_FOLDER + filename + "/filenameTemp.html")
copyfile(ocropy + "/processedFiles/" + filename + "/tempcorrection.html", OUTPUT_FOLDER + filename + "/filenameTempcorrection.html")
#uncomment to remove tmp data images
shutil.rmtree(ocropy + "/processedFiles/" + filename)
settings = []
settings.append("IMG")
settings.append(columnNumber)
writeLog(filename, settings, True)
#writeCorrect(filename)
os.remove(UPLOAD_FOLDER + filename)
outputfile = OUTPUT_FOLDER + filename + "/Output" + filename+'.xml'
outputfilename = filename.replace(filename.split("_")[0], "")[1:]
if os.path.exists(outputfile):
print "Finished inputfile : " + outputfilename
else:
print "Error inputfile : " + outputfilename
def fileuploadText(UPLOAD_FOLDER, OUTPUT_FOLDER, settings, filename):
#checks the file extension and preprocesses the file based on it
if "True" in settings[1]:
Txt_Dummy = True
else:
Txt_Dummy = False
prepareText(UPLOAD_FOLDER, Txt_Dummy, filename)
mode = "extract_meta"
if Txt_Dummy:
mode = "extract_citations"
p = subprocess.Popen([
"./citeExtract.pl -m" + mode + " " + LOCDB + "tmp/" + filename +
"_Textdummy.txt ", LOCDB + "tmp/" + filename + "_ParsText.xml"
],
shell=True,
stdout=subprocess.PIPE,
cwd=parsCit)
parscitstring = p.communicate()[0]
with open("tmp/" + filename + "_ParsText.xml", 'w') as f:
f.write(parscitstring)
outputxmlsoup = createBibstruct(filename)
if filename[-3:].lower() == "pdf":
output_grobid = processfileGrobid(UPLOAD_FOLDER, filename)
xmltags3 = output_grobid.find_all('BibStructured')
algotag3 = outputxmlsoup.algorithm
for curr in xmltags3:
algotag3.append(curr)
os.system("mv " + LOCDB + "tmp/" + filename + '_Textdummy.txt ' + LOCDB +
"processed-files/" + filename + '_Textdummy.txt')
os.system("mv " + LOCDB + "tmp/" + filename + '_ParsText.txt ' + LOCDB +
"processed-files/" + filename + '_ParsText.txt')
os.makedirs(OUTPUT_FOLDER + filename)
with open(OUTPUT_FOLDER + filename + "/Output" + filename + '.xml',
'w') as xmlf:
xmlf.write(outputxmlsoup.encode('utf-8'))
settings = []
settings.append("TXT")
settings.append(Txt_Dummy)
writeLog(filename, settings, True)
os.remove(UPLOAD_FOLDER + filename)
os.makedirs(OUTPUT_FOLDER + filename)
outputfile = OUTPUT_FOLDER + filename + "/Output" + filename + '.xml'
outputfilename = filename.replace(filename.split("_")[0], "")[1:]
if os.path.exists(outputfile):
print "Finished inputfile : " + outputfilename
writeUserLog("Finished inputfile : " + outputfilename)
else:
print "Error inputfile : " + outputfilename
writeUserLog("Error inputfile : " + outputfilename)
def fileupload():
#checks the upload and stores it to the upload folder
if request.method == 'POST':
if 'files' not in request.files:
flash('No file part')
return redirect(request.url)
#requested files and pdf mode are retrieved from flask
fileList = request.files.getlist('files')
if request.form.get('pdfFlag'):
Settings[0] = "IMG"
else:
Settings[0] = "TXT"
if request.form.get('Txt_Dummy'):
Settings[1] = "True"
else:
Settings[1] = "False"
#if request.form.get('colBool'):
#Settings[2] = str(int(request.form.get('colNumb')) - 1)
#else:
#Settings[2] = "0"
autoview = False
if request.form.get('autoviewResults'):
autoview = True
filenameFP_List = []
filenameString = ""
for uploadedFile in fileList:
if uploadedFile.filename == '':
flash('No selected inputfile')
return redirect(request.url)
if uploadedFile and check_file_extension(uploadedFile.filename,
ALLOWED_EXTENSIONS):
filenameFP = secure_filename(uploadedFile.filename)
print 'Uploaded inputfile : ' + filenameFP
writeUserLog("Uploaded inputfile : " + filenameFP)
#adding timestamp
ts = datetime.now().strftime('%Y%m%d%H%M%S')
filenameFP = ts + "_" + filenameFP
writeLog(filenameFP, Settings, False)
uploadedFile.save(os.path.join(UPLOAD_FOLDER, filenameFP))
filenameFP_List.append(filenameFP)
filenameString += filenameFP + "\n"
processFile(UPLOAD_FOLDER, OUTPUT_FOLDER, MAX_PROCESSES, Settings,
filenameFP_List)
#sync process
result = createResultView(OUTPUT_FOLDER, filenameFP_List)
return Response(result, content_type='text/xml; charset=utf-8')
if autoview:
return render_template("form_submitocr.html",
waiting="1",
filesText=filenameString)
else:
return updateHTML()
return "Error"
def fileuploadText(UPLOAD_FOLDER, OUTPUT_FOLDER, settings, filename):
#try:
#checks the file extension and preprocesses the file based on it
if "True" in settings[1]:
Txt_Dummy = True
else:
Txt_Dummy = False
prepareText(UPLOAD_FOLDER, Txt_Dummy, filename)
mode = "extract_meta"
if Txt_Dummy:
mode = "extract_citations"
p = subprocess.Popen([
"./citeExtract.pl -m" + mode + " " + LOCDB + "tmp/" + filename +
"_Textdummy.txt ", LOCDB + "tmp/" + filename + "_ParsText.xml"
],
shell=True,
stdout=subprocess.PIPE,
cwd=parsCit)
parscitstring = p.communicate()[0]
with open("tmp/" + filename + "_ParsText.xml", 'w') as f:
f.write(parscitstring)
outputxmlsoup = createBibstruct(filename)
#delete tmp files
os.remove("tmp/" + filename + '_Textdummy.txt')
os.remove("tmp/" + filename + '_ParsText.xml')
with open(OUTPUT_FOLDER + "Output" + filename + '.xml', 'w') as xmlf:
xmlf.write(outputxmlsoup.encode('utf-8'))
settings = []
settings.append("TXT")
settings.append(Txt_Dummy)
writeLog(filename, settings, True)
#writeCorrect(filename)
os.remove(UPLOAD_FOLDER + filename)
#create output folder for image file
if not os.path.exists(OUTPUT_FOLDER + filename):
os.makedirs(OUTPUT_FOLDER + filename + "/")
#outputfile = OUTPUT_FOLDER + "Output" + filename+'.xml'
outputfile = output_folder + filename + '/Output' + filename + ".xml"
outputfilename = filename.replace(filename.split("_")[0], "")[1:]
if os.path.exists(outputfile):
print "Finished inputfile : " + outputfilename
else:
print "Error inputfile : " + outputfilename
def fileupload():
print ""
print ""
print "----------------------------------------"
print "request: ", request
print "request.files: ", request.files
print "request.url: ", request.url
print "request.form: ", request.form
print "----------------------------------------"
print ""
print ""
#checks the upload and stores it to the upload folder
if request.method == 'POST':
if 'files' not in request.files:
flash('No file part')
return redirect(request.url)
#requested files and pdf mode are retrieved from flask
fileList = request.files.getlist('files')
if request.form.get('pdfFlag'):
Settings[0] = "IMG"
else:
Settings[0] = "TXT"
if request.form.get('Txt_Dummy'):
Settings[1] = "True"
else:
Settings[1] = "False"
if request.form.get('colBool'):
Settings[2] = str(int(request.form.get('colNumb')) - 1)
else:
Settings[2] = "0"
filenameFP_List = []
for uploadedFile in fileList:
if uploadedFile.filename == '':
flash('No selected inputfile')
return redirect(request.url)
if uploadedFile and check_file_extension(uploadedFile.filename,
ALLOWED_EXTENSIONS):
filenameFP = secure_filename(uploadedFile.filename)
print 'Uploaded inputfile : ' + filenameFP
#adding timestamp
ts = datetime.now().strftime('%m%d%H%M%S')
filenameFP = ts + "_" + filenameFP
writeLog(filenameFP, Settings, False)
uploadedFile.save(os.path.join(UPLOAD_FOLDER, filenameFP))
filenameFP_List.append(filenameFP)
processFile(UPLOAD_FOLDER, OUTPUT_FOLDER, MAX_PROCESSES, Settings,
filenameFP_List)
return mergeOutputXML(OUTPUT_FOLDER, filenameFP_List)
#return redirect("/")
return "Error"
def fileuploadXML(UPLOAD_FOLDER, OUTPUT_FOLDER, filename):
#open input file
with open(UPLOAD_FOLDER + filename, 'r') as f:
xmlsoup = bs.BeautifulSoup(f.read(), 'xml')
prepareXML(xmlsoup, filename)
p = subprocess.Popen([
"./citeExtract.pl -m extract_citations " + LOCDB + "tmp/" + filename +
"_XMLdummy.txt ", LOCDB + "tmp/" + filename + "_ParsXML.xml"
],
shell=True,
stdout=subprocess.PIPE,
cwd=parsCit)
parscitstring = p.communicate()[0]
with open("tmp/" + filename + "_ParsXML.xml", 'w') as f:
f.write(parscitstring)
outputxmlsoup = createBibstruct(xmlsoup, filename)
#delete tmp files
os.remove("tmp/" + filename + '_XMLdummy.txt')
os.remove("tmp/" + filename + '_ParsXML.xml')
os.makedirs(OUTPUT_FOLDER + filename)
with open(OUTPUT_FOLDER + filename + "/Output" + filename + '.xml',
'w') as xmlf:
xmlf.write(outputxmlsoup.encode('utf-8'))
settings = []
settings.append("XML")
writeLog(filename, settings, True)
#writeCorrect(filename)
os.remove(UPLOAD_FOLDER + filename)
outputfile = OUTPUT_FOLDER + filename + "/Output" + filename + '.xml'
outputfilename = filename.replace(filename.split("_")[0], "")[1:]
if os.path.exists(outputfile):
print "Finished inputfile : " + outputfilename
writeUserLog("Finished inputfile : " + outputfilename)
else:
print "Error inputfile : " + outputfilename
writeUserLog("Error inputfile : " + outputfilename)
def fileupload():
if debugMode.lower() == "yes":
print ""
print "####################################"
print "In fileupload()"
print "####################################"
print ""
#checks the upload request parameters and stores it to the upload folder
if request.method == 'POST':
if 'files' not in request.files:
flash('No file part')
return redirect(request.url)
#requested files and pdf mode are retrieved from flask
fileList = request.files.getlist('files')
if request.form.get('pdfFlag'):
Settings[0] = "IMG"
else:
Settings[0] = "TXT"
if request.form.get('Txt_Dummy'):
Settings[1] = "True"
else:
Settings[1] = "False"
autoview = False
if request.form.get('autoviewResults'):
autoview = True
filenameFP_List = []
filenameString = ""
for uploadedFile in fileList:
if uploadedFile.filename == '':
flash('No selected inputfile')
return redirect(request.url)
if uploadedFile and check_file_extension(uploadedFile.filename,
ALLOWED_EXTENSIONS):
filenameFP = secure_filename(uploadedFile.filename)
print 'Uploaded inputfile : ' + filenameFP
print ""
writeUserLog("Uploaded inputfile : " + filenameFP)
#adding timestamp
ts = datetime.now().strftime('%Y%m%d%H%M%S')
filenameFP = ts + "_" + filenameFP
writeLog(filenameFP, Settings, False)
uploadedFile.save(
os.path.join(LOCDB + UPLOAD_FOLDER, filenameFP))
filenameFP_List.append(filenameFP)
filenameString += filenameFP + "\n"
else:
return "Error: Invalid file extension..."
try:
job = q.enqueue_call(func=processFile,
args=(
UPLOAD_FOLDER,
OUTPUT_FOLDER,
MAX_PROCESSES,
Settings,
filenameFP_List,
),
result_ttl=8000,
timeout=80000)
print(job.get_id())
return job.get_id()
#sync process
filenameFP_List = natsort.natsorted(filenameFP_List)
result = createResultView(OUTPUT_FOLDER, filenameFP_List)
return Response(result, content_type='text/xml; charset=utf-8')
except:
return "An Error occured during file processing..."
if autoview:
return render_template("form_submitocr.html",
waiting="1",
filesText=filenameString)
else:
return updateHTML()
return "Error"
def fileuploadXML(UPLOAD_FOLDER, OUTPUT_FOLDER, filename):
mapOutputsoup = None
imgOutputXmlSoup = None
#open input file
with open(UPLOAD_FOLDER + filename, 'r') as f:
xmlsoup = bs.BeautifulSoup(f.read(), 'xml')
response = False
if filename[-3:].lower() == "xml":
prepareXML(xmlsoup, filename)
else:
response = prepareHTML(xmlsoup, filename)
if response == True:
mapOutputsoup = mapHTML(xmlsoup, filename)
p = subprocess.Popen([
"./citeExtract.pl -m extract_citations " + LOCDB + "tmp/" + filename +
"_XMLdummy.txt ", LOCDB + "tmp/" + filename + "_ParsXML.xml"
],
shell=True,
stdout=subprocess.PIPE,
cwd=parsCit)
parscitstring = p.communicate()[0]
with open("tmp/" + filename + "_ParsXML.xml", 'w') as f:
f.write(parscitstring)
if filename[:-3].lower() == "xml":
outputxmlsoup = createBibstruct(xmlsoup, filename)
else:
outputxmlsoup = createBibstructHTML(filename)
if mapOutputsoup != None:
bibtags2 = mapOutputsoup.find_all('BibStructured')
algotag2 = outputxmlsoup.algorithm
for currtag in bibtags2:
algotag2.append(currtag)
if imgOutputXmlSoup != None:
bibtags2 = imgOutputXmlSoup.find_all('BibStructured')
algotag2 = outputxmlsoup.algorithm
for currtag in bibtags2:
algotag2.append(currtag)
os.system("mv " + LOCDB + "tmp/" + filename + '_XMLdummy.txt ' + LOCDB +
"processed-files/" + filename + '_XMLdummy.txt')
os.system("mv " + LOCDB + "tmp/" + filename + '_ParsXML.xml ' + LOCDB +
"processed-files/" + filename + '_ParsXML.xml')
os.makedirs(LOCDB + OUTPUT_FOLDER + filename)
with open(LOCDB + OUTPUT_FOLDER + filename + "/Output" + filename + '.xml',
'w') as xmlf:
xmlf.write(outputxmlsoup.encode('utf-8'))
settings = []
settings.append("XML")
writeLog(filename, settings, True)
os.remove(UPLOAD_FOLDER + filename)
outputfile = OUTPUT_FOLDER + filename + "/Output" + filename + '.xml'
outputfilename = filename.replace(filename.split("_")[0], "")[1:]
if os.path.exists(outputfile):
print "Finished inputfile : " + outputfilename
writeUserLog("Finished inputfile : " + outputfilename)
else:
print "Error inputfile : " + outputfilename
writeUserLog("Error inputfile : " + outputfilename)