def processAllRecordsSTR(pathToMemex):
files = functions.dicOfRelevantFiles(pathToMemex, ".bib")
citeKeys = list(files.keys())
random.shuffle(citeKeys)
for citeKey in citeKeys:
print(citeKey)
bibData = functions.loadBib(files[citeKey])
if "pagetotal" in bibData:
pageTotal = int(bibData["pagetotal"])
if pageTotal <= int(settings["page_limit"]):
language = functions.identifyLanguage(bibData[citeKey], "eng")
ocrPublication(citeKey, language, settings["page_limit"])
else:
language = functions.identifyLanguage(bibData[citeKey], "eng")
ocrPublication(citeKey, language, settings["page_limit"])
functions.memexStatusUpdates(settings["path_to_memex"], ".pdf")
functions.memexStatusUpdates(settings["path_to_memex"], ".bib")
functions.memexStatusUpdates(settings["path_to_memex"], ".png")
functions.memexStatusUpdates(settings["path_to_memex"], ".json")
def processAllRecords(bibDataFile):
bibData = functions.loadBib(bibDataFile)
keys = list(bibData.keys())
random.shuffle(keys)
for key in keys:
bibRecord = bibData[key]
functions.processBibRecord(settings["path_to_memex"], bibRecord)
language = functions.identifyLanguage(bibRecord["rCite"], "eng")
ocrPublication(bibRecord["rCite"], language)
functions.memexStatusUpdates(settings["path_to_memex"], ".pdf")
functions.memexStatusUpdates(settings["path_to_memex"], ".bib")
functions.memexStatusUpdates(settings["path_to_memex"], ".png")
functions.memexStatusUpdates(settings["path_to_memex"], ".json")
def processAllRecords(bibDataFile):
# load the bib file as dictionary using the function from previous step
bibData = functions.loadBib(bibDataFile)
# save the keys of the dictionary bibData as a list
keys = list(bibData.keys())
random.shuffle(keys)
print
print(str(keys))
# in a loop, process each key from the list keys (i.e. each record by citation key)
for key in keys:
bibRecord = bibData[key]
# run the function from the previous step that creates a path with pdf and bib files, if not already there
functions.processBibRecord(settings["path_to_memex"], bibRecord)
language = functions.identifyLanguage(bibRecord, "eng")
# run the function that saves ocr-ed text as json files and created .png images for each page
ocrPublication(bibRecord["rCite"], language)
def processAllRecords(bibDataFile): #defines a functions for all the records
bibData = functions.loadBib(
bibDataFile) #loops through key-value-pairs in the bibData-dictionary
keys = list(bibData.keys()) #keys from the list
random.shuffle(keys) #randomizes the OCRing
for key in keys: #loops through the keys
bibRecord = bibData[key] #adds a key to the bibData
functions.processBibRecord(settings["path_to_memex"],
bibRecord) #assigns a new parameter
language = functions.identifyLanguage(
bibRecord["rCite"],
"eng") #identifies a language, assigns the "eng"
ocrPublication(bibRecord["rCite"], language, int(
settings["page_limit"])) #sets a page limit, if there is such
functions.memexStatusUpdates(settings["path_to_memex"],
".pdf") #creates a pdf
functions.memexStatusUpdates(settings["path_to_memex"],
".bib") #creates a bib
functions.memexStatusUpdates(settings["path_to_memex"],
".png") #creates a png
functions.memexStatusUpdates(settings["path_to_memex"],
".json") #creates a jsonfile