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 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): #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
prevPage = "" #there is no previous page
elif k == "0001": #if the page is the first page of the record
nextPage = "0002.html" #the next page is the second page of the record
prevPage = "DETAILS.html" #the previous page is the Details page
elif o == len(orderedPages)-1: #if the page is the last page of the record
nextPage = "" #there is no next page
prevPage = orderedPages[o-1] + ".html" #the previous page is the penultimate page of the record
else: #for all other pages
nextPage = orderedPages[o+1] + ".html" #the next page is the page behind in the record
prevPage = orderedPages[o-1] + ".html" #the previous page is the page before in the record
pageTemp = pageTemp.replace("@NEXTPAGEHTML@", nextPage) #replace the wildcard with a link to the page assigned in the lines before
pageTemp = pageTemp.replace("@PREVIOUSPAGEHTML@", prevPage) #replace the Previouspagehtml item with a link to the page assigned in the lines before
pagePath = os.path.join(pathToBibFile.replace(citeKey+".bib", ""), "pages", "%s.html" % k) #create a filepath to each page in the pages-folder of each publication
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp) #create and save each page in that pages folder
###########################################################
# FUNCTIONS TESTING #######################################
###########################################################
functions.memexStatusUpdates(settings["path_to_memex"], ".html") #execute the memexStatusUpdates-function
def processAllRecords(pathToMemex):
files = functions.dicOfRelevantFiles(pathToMemex, ".bib") #take the bibFiles
for citeKey, pathToBibFile in files.items(): #loop through them
if os.path.exists(pathToBibFile.replace(".bib", ".json")): #search for files with json extension
generatePublicationInterface(citeKey, pathToBibFile) #execute the previous function
processAllRecords(settings["path_to_memex"]) #execute the overall function
exec(open("6_Interface_IndexPage.py").read())
prevPage = ""
elif k == "0001":
nextPage = "0002.html"
prevPage = "DETAILS.html"
elif o == len(orderedPages)-1:
nextPage = ""
prevPage = orderedPages[o-1] + ".html"
else:
nextPage = orderedPages[o+1] + ".html"
prevPage = orderedPages[o-1] + ".html"
pageTemp = pageTemp.replace("@NEXTPAGEHTML@", nextPage)
pageTemp = pageTemp.replace("@PREVIOUSPAGEHTML@", prevPage)
pagePath = os.path.join(pathToBibFile.replace(citeKey+".bib", ""), "pages", "%s.html" % k)
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
###########################################################
# FUNCTIONS TESTING #######################################
###########################################################
functions.memexStatusUpdates(settings["path_to_memex"], ".html")
def processAllRecords(pathToMemex):
files = functions.dicOfRelevantFiles(pathToMemex, ".bib")
for citeKey, pathToBibFile in files.items():
if os.path.exists(pathToBibFile.replace(".bib", ".json")):
generatePublicationInterface(citeKey, pathToBibFile)
processAllRecords(settings["path_to_memex"])
exec(open("9_Interface_IndexPage.py").read())
else:
nextPage = orderedPages[o + 1] + ".html"
prevPage = orderedPages[o - 1] + ".html"
pageTemp = pageTemp.replace("@NEXTPAGEHTML@", nextPage)
pageTemp = pageTemp.replace("@PREVIOUSPAGEHTML@", prevPage)
pagePath = os.path.join(
pathToBibFile.replace(citeKey + ".bib", ""), "pages",
"%s.html" % k)
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
###########################################################
# PROCESS ALL RECORDS #####################################
###########################################################
functions.memexStatusUpdates(memexPath, ".html")
def processAllRecords():
relDic = functions.dicOfRelevantFiles(memexPath, "bib")
for k, v in relDic.items():
generatePublicationInterface(k[:-1], v)
processAllRecords()
exec(open("7_IndexPage.py").read())