def ocrPublication(pathToMemex, citationKey, language):
# generate and create necessary paths
# path to the folder
publPath = functions.generatePublPath(pathToMemex, citationKey)
# path to the pdf file
pdfFile = os.path.join(publPath, citationKey + ".pdf")
# path to the json file
jsonFile = os.path.join(publPath, citationKey + ".json") # OCR results will be saved here
# path to the pages folder
saveToPath = os.path.join(publPath, "pages") # we will save processed images here
# generate CLEAN pdf (necessary if you added highlights and comments to your PDFs)
pdfFileTemp = removeCommentsFromPDF(pdfFile)
# first we need to check whether this publication has been already processed
if not os.path.isfile(jsonFile):
# let's make sure that saveToPath also exists
if not os.path.exists(saveToPath):
# create folder pages
os.makedirs(saveToPath)
# start process images and extract text
print("\t>>> OCR-ing: %s" % citationKey)
# create the dictionary textResults
textResults = {}
# create the list images
images = pdf2image.convert_from_path(pdfFileTemp)
# length of the list
pageTotal = len(images)
# set pageCount
pageCount = 1
# loop through the list images
for image in images:
image = image.convert('1') # binarizes image, reducing its size
# create the path for each image file
finalPath = os.path.join(saveToPath, "%04d.png" % pageCount)
# save the image
image.save(finalPath, optimize=True, quality=10)
# get the text from the image
text = pytesseract.image_to_string(image, lang=language)
# save the text to the dictionary textResults
textResults["%04d" % pageCount] = text
# write the process to terminal
print("\t\t%04d/%04d pages" % (pageCount, pageTotal))
# increase pageCount
pageCount += 1
# create the json file
with open(jsonFile, 'w', encoding='utf8') as f9:
# write textResults to the file
json.dump(textResults, f9, sort_keys=True, indent=4, ensure_ascii=False)
else: # in case JSON file already exists
print("\t>>> %s has already been OCR-ed..." % citationKey)
# delete the temporary pdf file
os.remove(pdfFileTemp)
def createIndex(pathToMemex):
bibData = functions.loadBib(settings["bib_all"])
with open(settings["template_index"], "r", encoding="utf8") as ft:
template = ft.read()
completeList = []
for k, v in bibData.items():
path = functions.generatePublPath(memexPath, k)
entry = "<tr><td><li><a href=" + "@PATHTOPUBL@/pages/DETAILS.html>" + "[@CITEKEY@]</a></td><td> @AUTHOR@</td> <td>(@DATE@)</td> - <td><i>@TITLE@</i></td></li></tr>"
entry = entry.replace("@PATHTOPUBL@", path)
entry = entry.replace("@CITEKEY@", k)
if "author" in v:
entry = entry.replace("@AUTHOR@", v["author"])
else:
entry = entry.replace("@AUTHOR@", "MISSING")
if "year" in v:
entry = entry.replace("@DATE@", v["year"])
else:
entry = entry.replace("@DATE@", "MISSING")
if "title" in v:
entry = entry.replace("@TITLE@", v["title"])
else:
entry = entry.replace("@TITLE@", "MISSING")
completeList.append(entry)
content = "\n<ul>\n%s\n</ul>" % "\n".join(sorted(completeList))
content = content.replace("{", "")
content = content.replace("}", "")
toc = formatSearches(pathToMemex)
template = template.replace("@SEARCHES@", toc)
template = template.replace(
"@PUBLICATIONS@", publTemplate.replace("@TABLECONTENTS@", content))
with open(os.path.join(pathToMemex, "searchesInterface.html"),
"w",
encoding="utf8") as f9:
f9.write(template)
def generateMemexStartingPages(pathToMemex):
# load index template
with open(settings["template_index"], "r", encoding="utf8") as ft:
template = ft.read()
# add index.html
with open(settings["content_index"], "r", encoding="utf8") as fi:
indexData = fi.read()
with open(os.path.join(pathToMemex, "index.html"), "w", encoding="utf8") as f9:
f9.write(template.replace("@MAINCONTENT@", indexData))
# load bibliographical data for processing
publicationDic = {} # key = citationKey; value = recordDic
for subdir, dirs, files in os.walk(pathToMemex):
for file in files:
if file.endswith(".bib"):
pathWhereBibIs = os.path.join(subdir, file)
tempDic = functions.loadBib(pathWhereBibIs)
publicationDic.update(tempDic)
# generate data for the main CONTENTS
singleItemTemplate = '<li><a href="@RELATIVEPATH@/pages/DETAILS.html">[@CITATIONKEY@]</a> @AUTHOROREDITOR@ (@DATE@) - <i>@TITLE@</i></li>'
contentsList = []
for citeKey,bibRecord in publicationDic.items():
relativePath = functions.generatePublPath(pathToMemex, citeKey).replace(pathToMemex, "")
authorOrEditor = "[No data]"
if "editor" in bibRecord:
authorOrEditor = bibRecord["editor"]
if "author" in bibRecord:
authorOrEditor = bibRecord["author"]
if "date" in bibRecord:
date = bibRecord["date"]
else:
print("nodate")
date = bibRecord["date"][:4]
title = bibRecord["title"]
# forming a record
recordToAdd = singleItemTemplate
recordToAdd = recordToAdd.replace("@RELATIVEPATH@", relativePath)
recordToAdd = recordToAdd.replace("@CITATIONKEY@", citeKey)
recordToAdd = recordToAdd.replace("@AUTHOROREDITOR@", authorOrEditor)
recordToAdd = recordToAdd.replace("@DATE@", date)
recordToAdd = recordToAdd.replace("@TITLE@", title)
recordToAdd = recordToAdd.replace("{", "").replace("}", "")
contentsList.append(recordToAdd)
contents = "\n<ul>\n%s\n</ul>" % "\n".join(sorted(contentsList))
mainContent = "<h1>CONTENTS of MEMEX</h1>\n\n" + contents
# save the CONTENTS page
with open(os.path.join(pathToMemex, "contents.html"), "w", encoding="utf8") as f9:
f9.write(template.replace("@MAINCONTENT@", mainContent))
def generateDoclLink(bibTexCode, pageVal, distance):
pathToPubl = functions.generatePublPath(settings["path_to_memex"], bibTexCode)
bib = functions.loadBib(os.path.join(pathToPubl, "%s.bib" % bibTexCode))
bib = bib[bibTexCode]
author = "N.d."
if "editor" in bib:
author = bib["editor"]
if "author" in bib:
author = bib["author"]
reference = "%s (%s). <i>%s</i>" % (author, bib["date"][:4], bib["title"])
search = unicodedata.normalize('NFKD', reference).encode('ascii','ignore')
search = " <div class='hidden'>%s</div>" % search
if pageVal == 0: # link to the start of the publication
htmlLink = os.path.join(pathToPubl.replace(settings["path_to_memex"], "../../../../"), "pages", "DETAILS.html")
htmlLink = "<a href='%s'><i>read</i></a>" % (htmlLink)
page = ""
startPage = 0
else:
startPage = pageVal - 5
endPage = pageVal
if startPage == 0:
startPage += 1
htmlLink = os.path.join(pathToPubl.replace(settings["path_to_memex"], "../../../../"), "pages", "%04d.html" % startPage)
htmlLink = "<a href='%s'><i>read</i></a>" % (htmlLink)
page = ", pdfPp. %d-%d</i></a>" % (startPage, endPage)
publicationInfo = reference + page + search
publicationInfo = publicationInfo.replace("{", "").replace("}", "")
singleItemTemplate = '<tr><td>%s</td><td>%f</td><td data-order="%s%05d">%s</td></tr>' % (htmlLink, distance, bibTexCode, startPage, publicationInfo)
return(singleItemTemplate)
def checkPageNumbers(bib, bibTexCode, startPage):
page = 0
if "pages" in bib.keys():
bibPages = functions.prettifyBib(bib["pages"])
bibPagesList = list(bibPages.split("--"))
bibPagesList = [int(i) for i in bibPagesList]
pathToPubl = functions.generatePublPath(memexPath, bibTexCode)
jsonFile = os.path.join(pathToPubl, "%s.json" % bibTexCode)
with open(jsonFile) as jsonData:
ocred = json.load(jsonData)
pNumList = ocred.keys()
if len(pNumList) > (bibPagesList[1] - bibPagesList[0] + 1):
if startPage == 1:
page = "TITLE"
else:
page = startPage + bibPagesList[0] - 2
else:
page = startPage + bibPagesList[0] - 1
else:
page = startPage
return (page)
def processAllClouds(filename):
docData = json.load(open(filename, "r", encoding="utf8"))
for k, v in docData.items():
savePath = functions.generatePublPath(memexPath, k)
savePath = savePath + "\\" + k
if v:
createwordCloud(savePath, k)
def formatPublList(
pathToMemex
): #define a function for the formatting of the publications
ocrFiles = functions.dicOfRelevantFiles(
pathToMemex,
settings["ocr_results"]) #take the files with the OCRed pages
bibFiles = functions.dicOfRelevantFiles(pathToMemex,
".bib") #take the bibFiles
contentsList = [] #create an empty list
for key, value in ocrFiles.items(): #loop through the OCRed pages
if key in bibFiles: #search for the key in the bibFile
bibRecord = functions.loadBib(
bibFiles[key]) #load the bibliographical data for this item
bibRecord = bibRecord[key] #take the key
relativePath = functions.generatePublPath(
pathToMemex,
key).replace(pathToMemex,
"") #take the relative path to the publication
authorOrEditor = "[No data]" #take no information on the author as default setting
if "editor" in bibRecord: #check if there is information about the editor
authorOrEditor = bibRecord["editor"] #insert it
if "author" in bibRecord: #check if there is information about the author
authorOrEditor = bibRecord["author"] #insert it
date = bibRecord["year"][:4] #insert the year of the publication
title = bibRecord["title"] #insert the title
# formatting template
citeKey = '<div class="ID">[%s]</div>' % key #take the citeKey
publication = '%s (%s) <i>%s</i>' % (
authorOrEditor, date, title
) #take the information about the publication and format it
search = unicodedata.normalize('NFKD', publication).encode(
'ascii', 'ignore'
) #replace diacritical characters with their ascii equivalents
publication += " <div class='hidden'>%s</div>" % search #repeat the information and hide it
link = '<a href="%s/pages/DETAILS.html"><i>read</i></a>' % relativePath #add the link to the details page of each publication
singleItemTemplate = '<tr><td>%s</td><td>%s %s</td></tr>' % (
link, citeKey, publication
) #collect the information in a single template
recordToAdd = singleItemTemplate.replace("{", "").replace(
"}", "") #remove curly brackets
contentsList.append(
recordToAdd) #add the single records to the content list
contents = "\n".join(sorted(contentsList)) #join the sorted content list
final = publicationsTemplate.replace(
"@TABLECONTENTS@", contents
) #replace the wildcard in the template with the actual content
return (final) #return this variable
def ocrPublication(
pathToMemex, citationKey, language
): ## ocr function takes path, citationkey and language as argument
publPath = functions.generatePublPath(
pathToMemex, citationKey
) ## generates path that gets us to the file with the citekey name
pdfFile = os.path.join(publPath, citationKey + ".pdf") ## generates pdf
jsonFile = os.path.join(publPath,
citationKey + ".json") ## generates json file
saveToPath = os.path.join(
publPath, "pages") ## creates new folder for all the ocr-ed pages
if not os.path.isfile(
jsonFile
): ## checks if there is a json file to see if it has been ocr-ed already
if not os.path.exists(
saveToPath): ## if not it makes one and starts the process
os.makedirs(saveToPath)
print(
"\t>>> OCR-ing: %s" % citationKey
) ## shows us that it is ocr-ing the pdf and the citationkey of that one
textResults = {} ## creates dictionary for results
images = pdf2image.convert_from_path(
pdfFile) ## creates the images of the single pages in the pdf
pageTotal = len(
images
) ## to know how many pages have been processed; always adds 1
pageCount = 1
for image in images: ## loops through the images
text = pytesseract.image_to_string(
image,
lang=language) ## analyses the string with the given language
textResults["%04d" % pageCount] = text
image = image.convert('1') # binarizes image, reducing its size
finalPath = os.path.join(
saveToPath,
"%04d.png" % pageCount) ## saves the pages into pages folder
image.save(finalPath, optimize=True, quality=10)
print("\t\t%04d/%04d pages" % (pageCount, pageTotal))
pageCount += 1
with open(jsonFile, 'w', encoding='utf8') as f9:
json.dump(textResults,
f9,
sort_keys=True,
indent=4,
ensure_ascii=False) ## dumps results into json file
else:
print("\t>>> %s has already been OCR-ed..." % citationKey
) ## if it finds the json file in the beginning it prints this
def processAllclouds(filename):
docData = json.load(open(filename, "r",
encoding="utf8")) ## loads tfidf file
for k, v in docData.items(): ###loop through the file
savePath = functions.generatePublPath(memexPath,
k) ##create path for file
savePath = savePath + "\\" + k
if v:
createWordCloud(savePath, v) ### create wordcloud
def ocrPublication(citationKey, language, pageLimit):
# generate and create necessary paths
publPath = functions.generatePublPath(settings["path_to_memex"],
citationKey)
pdfFile = os.path.join(publPath, citationKey + ".pdf")
jsonFile = os.path.join(publPath, citationKey +
".json") # OCR results will be saved here
saveToPath = os.path.join(publPath,
"pages") # we will save processed images here
# first we need to check whether this publication has been already processed
if not os.path.isfile(jsonFile):
# let's make sure that saveToPath also exists
if not os.path.exists(saveToPath):
os.makedirs(saveToPath)
# start process images and extract text
print("\t>>> OCR-ing: %s" % citationKey)
textResults = {}
images = pdf2image.convert_from_path(pdfFile)
pageTotal = len(images)
pageCount = 1
if pageTotal <= int(pageLimit):
for image in images:
text = pytesseract.image_to_string(image, lang=language)
textResults["%04d" % pageCount] = text
image = image.convert(
'1') # binarizes image, reducing its size
finalPath = os.path.join(saveToPath, "%04d.png" % pageCount)
image.save(finalPath, optimize=True, quality=10)
print("\t\t%04d/%04d pages" % (pageCount, pageTotal))
pageCount += 1
with open(jsonFile, 'w', encoding='utf8') as f9:
json.dump(textResults,
f9,
sort_keys=True,
indent=4,
ensure_ascii=False)
else:
print(
"\t%d: the length of the publication exceeds current limit (%d)"
% (pageTotal, pageLimit))
print(
"\tIncrease `page_limit` in settings to process this publication."
)
else: # in case JSON file already exists
print("\t>>> %s has already been OCR-ed..." % citationKey)
def generateReferenceSimple(bibTexCode):
pathToPubl = functions.generatePublPath(settings["path_to_memex"], bibTexCode)
bib = functions.loadBib(os.path.join(pathToPubl, "%s.bib" % bibTexCode))
bib = bib[bibTexCode]
author = "N.d."
if "editor" in bib:
author = bib["editor"]
if "author" in bib:
author = bib["author"]
reference = "%s (%s). <i>%s</i>" % (author, bib["date"][:4], bib["title"])
reference = reference.replace("{", "").replace("}", "")
return(reference)
def genConnectedTexts(citeKey):
similarities = json.load(
open("cosineTableDic_filtered.txt", "r", encoding="utf8"))
contentTemp = "<tr><td><i><a href='@link@'>read</a></i></td><td>@Sim@</td><td>@Publication@</td></tr>"
if similarities:
temp = similarities[citeKey]
content = ""
for k, v in temp.items():
content = content + contentTemp.replace("@Publication@", k)
content = content.replace("@Sim@", str(v))
link = "..\\..\\..\\..\\." + functions.generatePublPath(
memexPath, k) + "\\pages\\DETAILS.html"
content = content.replace("@link@", link)
return (content)
def formatPublList(pathToMemex):
ocrFiles = functions.dicOfRelevantFiles(pathToMemex,
settings["ocr_results"])
bibFiles = functions.dicOfRelevantFiles(pathToMemex, ".bib")
contentsList = []
for key, value in ocrFiles.items():
if key in bibFiles:
bibRecord = functions.loadBib(bibFiles[key])
bibRecord = bibRecord[key]
relativePath = functions.generatePublPath(pathToMemex,
key).replace(
pathToMemex, "")
authorOrEditor = "[No data]"
if "editor" in bibRecord:
authorOrEditor = bibRecord["editor"]
if "author" in bibRecord:
authorOrEditor = bibRecord["author"]
date = "nodate"
if "year" in bibRecord:
date = bibRecord["year"]
title = bibRecord["title"]
# formatting template
citeKey = '<div class="ID">[%s]</div>' % key
publication = '%s (%s) <i>%s</i>' % (authorOrEditor, date, title)
search = unicodedata.normalize('NFKD', publication).encode(
'ascii', 'ignore')
publication += " <div class='hidden'>%s</div>" % search
link = '<a href="%s/pages/DETAILS.html"><i>read</i></a>' % relativePath
singleItemTemplate = '<tr><td>%s</td><td>%s %s</td></tr>' % (
link, citeKey, publication)
recordToAdd = singleItemTemplate.replace("{", "").replace("}", "")
contentsList.append(recordToAdd)
contents = "\n".join(sorted(contentsList))
final = publicationsTemplate.replace("@TABLECONTENTS@", contents)
return (final)
def generateDoclLink(bibTexCode, pageVal, distance):
pathToPubl = functions.generatePublPath(memexPath, bibTexCode)
bib = functions.loadBib(os.path.join(pathToPubl, "%s.bib" % bibTexCode))
bib = bib[bibTexCode]
author = "N.d."
if "editor" in bib:
author = bib["editor"]
if "author" in bib:
author = bib["author"]
reference = "%s (%s). <i>%s</i>" % (author, bib["date"][:4], bib["title"])
search = unicodedata.normalize('NFKD', reference).encode('ascii', 'ignore')
search = " <div class='hidden'>%s</div>" % search
if pageVal == 0: # link to the start of the publication
htmlLink = os.path.join(pathToPubl.replace(memexPath, "../../../../"),
"pages", "DETAILS.html")
htmlLink = "<a href='{0}'>[{1}]</a>".format(htmlLink, bibTexCode)
page = ""
startPage = 0
else:
startPage = pageVal - 5
endPage = pageVal
if startPage == 0:
startPage += 1
realStartPage = checkPageNumbers(bib, bibTexCode, startPage)
realEndPage = checkPageNumbers(bib, bibTexCode, endPage)
htmlLink = os.path.join(pathToPubl.replace(memexPath, "../../../../"),
"pages", "%04d.html" % startPage)
htmlLink = "<a href='{0}'>[{1},{2}]</a>".format(
htmlLink, bibTexCode, realStartPage)
page = ", pp. {0}-{1}</i></a>".format(realStartPage, realEndPage)
publicationInfo = reference + page + search
publicationInfo = publicationInfo.replace("{", "").replace("}", "")
singleItemTemplate = '<tr><td data-order="{1}{2:05d}"><div class="ID">{3}</div> {4}</td><td>{0:f}</td></tr>'.format(
distance, bibTexCode, startPage, htmlLink, publicationInfo)
return (singleItemTemplate)
