def generateContentPage():
# #
####
#### Pseudocode:
#### funkion:
#### template öffnen
#### @PATHTOPUBL@, [@CITEKEY@], @AUTHOR@ (@DATE@) @TITLE@ + Link zur details(.html) des Textes
#### dictionary mit diesen variablen
#### loop um jeweils einen citekey/text/
#### Input: citekey,Path zum file, usw. -> Output Liste
###
# load individual bib record
# bibFile = pathToBibFile
#bibDic = functions.loadBib(bibFile)
#bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
####
#pageTemp = template
#pageTemp = pageTemp.replace("@PATHTOPUBL@", v)
#pageTemp = pageTemp.replace("@CITEKEY@", v)
#pageTemp = pageTemp.replace("@AUTHOR@", v)
#pageTemp = pageTemp.replace("@DATE@", v)
#pageTemp = pageTemp.replace("@TITLE@", v)
detailfileDic = functions.generatePageLinks(pNums)
### # load page template # wir brauchen template_index.html
with open(settings["template_index"], "r", encoding="utf8") as ft:
template = ft.read()
# load page template
#with open(settings["template_page"], "r", encoding="utf8") as ft:
#template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile)
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
orderedPages = list(detailfileDic.keys())
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v)
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
def generateContents (...):
#generate a list of publications with links
#join it with the index page template
# shoud look like this: <li><a href="@PATHTOPUBL@/pages/DETAILS.html">[@CITEKEY@]</a> @AUTHOR@ (@DATE@) - <i>@TITLE@</i></li>
#load the bib file to get all the values
# load the index template file
# write the <li> etc. into the content
# replace @author with author etc.
# open as contents.html
# #
####
#### Pseudocode:
#### funkion:
#### template öffnen
#### @PATHTOPUBL@, [@CITEKEY@], @AUTHOR@ (@DATE@) @TITLE@ + Link zur details(.html) des Textes
#### dictionary mit diesen variablen
#### loop um jeweils einen citekey/text/
#### Input: citekey,Path zum file, usw. -> Output Liste
###
# load individual bib record
# bibFile = pathToBibFile
#bibDic = functions.loadBib(bibFile)
#bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
####
# pageTemp = template
# pageTemp = pageTemp.replace("@PATHTOPUBL@", v)
#pageTemp = pageTemp.replace("@CITEKEY@", v)
#pageTemp = pageTemp.replace("@AUTHOR@", v)
#pageTemp = pageTemp.replace("@DATE@", v)
#pageTemp = pageTemp.replace("@TITLE@", v)
detailfileDic = functions.generatePageLinks(pNums)
### # load page template # wir brauchen template_index.html
with open(settings["template_index"], "r", encoding="utf8") as ft:
template = ft.read()
# load page template
#with open(settings["template_page"], "r", encoding="utf8") as ft:
#template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile)
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
orderedPages = list(detailfileDic.keys())
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v)
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
def generatePublicationInterface(citeKey, pathToBibFile):
print("=" * 80)
print(citeKey)
jsonFile = pathToBibFile.replace(".bib", ".json")
with open(jsonFile, encoding="utf8") as jsonData:
ocred = json.load(jsonData)
pNums = ocred.keys()
pageDic = functions.generatePageLinks(pNums)
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile)
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
orderedPages = list(pageDic.keys())
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v)
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
if k != "DETAILS":
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@", "%s.png" % k)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else:
mainElement = bibForHTML.replace("\n", "<br> ")
mainElement = '<div class="bib">%s</div>' % mainElement
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">'
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
if k == "DETAILS":
nextPage = "0001.html"
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)
def generatePublicationInterface(citeKey, pathToBibFile):
print("="*80)
print(citeKey) #print the citeKey of the publication
jsonFile = pathToBibFile.replace(".bib", ".json") #take the bibFile
with open(jsonFile, encoding="utf8") as jsonData:
ocred = json.load(jsonData) #load the bibFile
pNums = ocred.keys() #take the citation keys
pageDic = functions.generatePageLinks(pNums) #load the function which generates links to all pages in a publication
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read() #load the page template
# load individual bib record
bibFile = pathToBibFile #take the pathToBibFile
bibDic = functions.loadBib(bibFile) #load the loadBib-function which loads the bibTex data into a dictionary
bibForHTML = bibText.prettifyBib(bibDic[citeKey]["complete"]) #load the prettifyBib-function to make the bib record more readable (taking the complete bib record)
orderedPages = list(pageDic.keys()) #create a list of keys to get all page numbers
for o in range(0, len(orderedPages)): #loop through the pages
#print(o)
k = orderedPages[o] #take the number of the page as key
v = pageDic[orderedPages[o]] #take the links to the other pages as value
pageTemp = template #assign the page template to a temporary variable
pageTemp = pageTemp.replace("@PAGELINKS@", v) #replace the Pagelinks item with the links to the other pages
pageTemp = pageTemp.replace("@PATHTOFILE@", "") #replace the Pathtofile item with a blank
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey) #replace the Citationkey item with the citation key
emptyResults = '<tr><td><i>%s</i></td><td><i>%s</i></td><td><i>%s</i></td></tr>' #create a template for the similarity values
if k != "DETAILS": #if the page is not the details page
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace("@PAGEFILE@", "%s.png" % k) #takes the .png-file of the OCRed text of this page
pageKey = citeKey+"_%05d" % roundUp(int(k), 5) #take the citationKey and the pageNumbers
#print(pageKey)
if pageKey in pageConnData: #check if there are any similar pageclusters
formattedResults = "\n".join(pageConnData[pageKey]) #add them
#input(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data") #add that there are no similar pageclusters
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults) #replace the wildcard in the template with the actual values for simliar texts
mainElement += ocrTemplate.replace("@OCREDCONTENTTEMP@", ocred[k].replace("\n", "<br>")) #replace the wildcard in the template with the OCRed text of the page
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement) #repace the wildcard with the added actual values
else: #if the page is the details page
reference = generateReferenceSimple(citeKey) #take the information about the publication we've generated
mainElement = "<h3>%s</h3>\n\n" % reference #add it as a header
bibElement = '<div class="bib">%s</div>' % bibForHTML.replace("\n", "<br> ") #take the bibliogaphical data
bibElement = generalTemplate.replace("@ELEMENTCONTENT@", bibElement) #replace the wildcard in the general template with the bibliographical data
bibElement = bibElement.replace("@ELEMENTHEADER@", "BibTeX Bibliographical Record") #add a meaningful description
mainElement += bibElement + "\n\n" #add a new line
wordCloud = '\n<img src="../' + citeKey + '_wCloud.jpg" width="100%" alt="wordcloud">' #take the wordcloud we've generated
wordCloud = generalTemplate.replace("@ELEMENTCONTENT@", wordCloud) #replace the wildcard in the general template with the wordcloud
wordCloud = wordCloud.replace("@ELEMENTHEADER@", "WordCloud of Keywords (<i>tf-idf</i>)") #add a meaningful description
mainElement += wordCloud + "\n\n" #add a new line
if citeKey in publConnData: #check if there are any similar texts
formattedResults = "\n".join(publConnData[citeKey]) #add them
#input(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data") #add that there are non similar texts
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults) #replace the wildcard in the template with the actual information about similar texts
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement) #replace the wildcard in the pagetemplate with the added content
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
if k == "DETAILS": #if the page is the Details page
nextPage = "0001.html" #the next page is the first page of the record
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
def generatePublicationInterface(
citeKey,
pathToBibFile): # function takes a citation key and path to bib file
print("=" * 80)
print(citeKey)
jsonFile = pathToBibFile.replace(".bib", ".json")
with open(jsonFile,
encoding="utf8") as jsonData: #add encoding to not get error;
ocred = json.load(jsonData)
pNums = ocred.keys()
pageDic = functions.generatePageLinks(
pNums
) # number of pages of each publication;links to make it navigatable
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile) #loads entire bib
bibForHTML = functions.prettifyBib(
bibDic[citeKey]
["complete"]) #makes the bib file look better for this view
orderedPages = list(
pageDic.keys()) #list of all keys and pagenummers from page dic
for o in range(
0,
len(orderedPages)): #long loop that creates every single page
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template # take a template
pageTemp = pageTemp.replace("@PAGELINKS@",
v) # replace values in template
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
if k != "DETAILS": #one page is different than the rest;this for regular
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@", "%s.png" % k)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else: # if pages is details.html
mainElement = bibForHTML.replace("\n", "<br> ")
mainElement = '<div class="bib">%s</div>' % mainElement # class for changes in style sheet
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">' #wordcloud we will generate in the next class
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@ #links to next and previous page; and when we are on the last it stops
if k == "DETAILS":
nextPage = "0001.html"
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) ##find replace in template
pageTemp = pageTemp.replace("@PREVIOUSPAGEHTML@", prevPage)
pagePath = os.path.join(pathToBibFile.replace(
citeKey + ".bib", ""), "pages",
"%s.html" % k) # saves the actual page
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
def generatePublicationInterface(citeKey, pathToBibFile):
print("="*80)
print(citeKey)
jsonFile = pathToBibFile.replace(".bib", ".json")
with open(jsonFile, "r", encoding ="utf8") as jsonData:
ocred = json.load(jsonData)
pNums = ocred.keys()
pageDic = functions.generatePageLinks(pNums)
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile)
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
orderedPages = list(pageDic.keys())
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
#input(k)
v = pageDic[orderedPages[o]]
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v)
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
emptyResults = '<tr><td><i>%s</i></td><td><i>%s</i></td><td><i>%s</i></td></tr>'
if k != "DETAILS":
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace("@PAGEFILE@", "%s.png" % k)
pageKey = citeKey+"_%05d" % roundUp(int(k), 5)
#print(pageKey)
if pageKey in pageConnData:
formattedResults = "\n".join(pageConnData[pageKey])
#input(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data")
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults)
mainElement += ocrTemplate.replace("@OCREDCONTENTTEMP@", ocred[k].replace("\n", "<br>"))
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
else:
reference = generateReferenceSimple(citeKey)
mainElement = "<h3>%s</h3>\n\n" % reference
bibElement = '<div class="bib">%s</div>' % bibForHTML.replace("\n", "<br> ")
bibElement = generalTemplate.replace("@ELEMENTCONTENT@", bibElement)
bibElement = bibElement.replace("@ELEMENTHEADER@", "BibTeX Bibliographical Record")
mainElement += bibElement + "\n\n"
wordCloud = '\n<img src="../' + citeKey + '_wCloud.jpg" width="100%" alt="wordcloud">'
wordCloud = generalTemplate.replace("@ELEMENTCONTENT@", wordCloud)
wordCloud = wordCloud.replace("@ELEMENTHEADER@", "WordCloud of Keywords (<i>tf-idf</i>)")
mainElement += wordCloud + "\n\n"
if citeKey in publConnData:
formattedResults = "\n".join(publConnData[citeKey])
#input(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data")
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
if k == "DETAILS":
nextPage = "0001.html"
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)
def generatePublicationInterface(citeKey, pathToBibFile):
print("=" * 80)
print(citeKey)
jsonFile = pathToBibFile.replace(".bib", ".json")
with open(jsonFile) as jsonData:
ocred = json.load(jsonData)
pNums = ocred.keys()
pageDic = functions.generatePageLinks(pNums)
# load page template
with open(settings["template_page"], "r",
encoding="utf8") as ft: #add encoding to avoid error
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile) #loads entire bib
bibForHTML = functions.prettifyBib(
bibDic[citeKey]["complete"]) #structures the file
orderedPages = list(
pageDic.keys()) # generates list of all the keys and pgnumbers
for o in range(0, len(orderedPages)): #loop to create pages
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v) #take a template
pageTemp = pageTemp.replace("@PATHTOFILE@",
"") #replace the values
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
if k != "DETAILS": # for regular pages; one page is different from the others
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@", "%s.png" % k)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else: # if the page is html
mainElement = bibForHTML.replace("\n", "<br> ")
mainElement = '<div class="bib">%s</div>' % mainElement
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">'
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@ #link to previous/ next pag; stop on last page
if k == "DETAILS":
nextPage = "0001.html"
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) #saves the origin page
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
def generatePublicationInterface(citeKey, pathToBibFile):
print("=" * 80)
print(citeKey)
######################
#SINGLE PUBLICATION#
######################
jsonFile = pathToBibFile.replace(".bib", ".json")
with open(jsonFile) as jsonData:
ocred = json.load(jsonData)
pNums = ocred.keys()
pageDic = functions.generatePageLinks(pNums)
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile)
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
orderedPages = list(pageDic.keys())
for o in range(
0,
len(orderedPages)): #loop through pages of individual bib file
#print(o)
k = orderedPages[o] #page number
v = pageDic[orderedPages[o]] #page
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v)
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
if k != "DETAILS":
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@", "%s.png" % k)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else:
mainElement = bibForHTML.replace("\n", "<br> ")
mainElement = '<div class="bib">%s</div>' % mainElement
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">'
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
if k == "DETAILS":
nextPage = "0001.html"
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)
######################
#INDEX#
######################
#load templates for index page
with open(settings["template_index"], "r", encoding="utf8") as ti:
template_i = ti.read()
with open(settings["content_index"], "r", encoding="utf8") as ci:
content_i = ci.read()
pageTemp_i = template_i
pageTemp_i = pageTemp_i.replace(
"@MAINCONTENT@", content_i
) #use content.html to create index content by replacing the string @MAINCONTENT@
#set path for index page of Memex
pagePath_i = settings["path_to_index"]
with open(pagePath_i, "w", encoding="utf8") as f1:
f1.write(pageTemp_i)
######################
#CONTENT#
#hint: <li><a href="@PATHTOPUBL@/pages/DETAILS.html">[@CITEKEY@]</a> @AUTHOR@ (@DATE@) - <i>@TITLE@</i></li>
######################
#what I have so far, provides only one link in the sidenavgation to the detail page of one publication
print(pathToBibFile)
detailPage = pathToBibFile.replace("/" + citeKey + ".bib", "")
detailPage = detailPage.replace("/_data", "")
print(detailPage)
pageTemp_c = pageTemp_i.replace("@CITEKEY@", citeKey)
pageTemp_c = pageTemp_i.replace("@PATHTOPUBL@", detailPage)
#set path for content page of Memex
pagePath_c = settings["path_to_content"]
with open(pagePath_c, "w", encoding="utf8") as f2:
f2.write(pageTemp_c)
def generatePublicationInterface(citeKey, pathToBibFile):
print("=" * 80)
print(citeKey)
######################
#SINGLE PUBLICATION#
######################
jsonFile = pathToBibFile.replace(".bib", ".json") #get JSON files
with open(jsonFile) as jsonData:
ocred = json.load(jsonData) #open file
pNums = ocred.keys() #get pages of publication
pageDic = functions.generatePageLinks(pNums) #use pre-defined function
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile) #use pre-defined function
print(bibDic)
bibForHTML = functions.prettifyBib(
bibDic[citeKey]["complete"]) #use pre-defined function
orderedPages = list(pageDic.keys()) #make list of pages
authorOrEditor = "[No data]"
if "editor" in bibDic[citeKey]:
authorOrEditor = bibDic[citeKey]["editor"]
if "author" in bibDic[citeKey]:
authorOrEditor = bibDic[citeKey]["author"]
date = "unidentified"
if "year" in bibDic[citeKey]:
date = bibDic[citeKey]["year"]
for o in range(
0,
len(orderedPages)): #loop through pages of individual bib file
#print(o)
k = orderedPages[o] #page number
v = pageDic[orderedPages[o]] #page
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@",
v) #replace pattern with page
pageTemp = pageTemp.replace("@PATHTOFILE@",
"") #replace pattern with empty string
pageTemp = pageTemp.replace(
"@CITATIONKEY@", citeKey) #replace pattern with publication ID
wCloud = '\n<img src="../@WCLOUD@" width="100%" alt="wordcloud">'.replace(
"@WCLOUD@", "%s.jpg" % citeKey)
pageTemp = pageTemp.replace("@WORD_CLOUD@", wCloud)
pageTemp = pageTemp.replace("@PUB_AUTHOR@", authorOrEditor)
pageTemp = pageTemp.replace("@PUB_YEAR@", date)
pageTemp = pageTemp.replace(
"@PUB_TITLE@",
bibDic[citeKey]["title"].replace("{", "").replace("}", ""))
if k != "DETAILS": #if not set to overview page
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@",
"%s.png" % k) #use ocred page as main element
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else:
mainElement = bibForHTML.replace("\n", "<br> ")
mainElement = '<div class="bib">%s</div>' % mainElement
#mainElement += '\n<img src="../@WCLOUD@" width="100%" alt="wordcloud">'.replace("@WCLOUD@", "%s.jpg" % citeKey)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
#set order of the page layout
if k == "DETAILS":
nextPage = "0001.html"
prevPage = "" #no previous page
elif k == "0001":
nextPage = "0002.html"
prevPage = "DETAILS.html" #set previous page because it is not a serial number
elif o == len(orderedPages) - 1: #take care of special case
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: #set path for individual pages
f9.write(pageTemp)
def generatePublicationInterface(
citeKey, pathToBibFile): # Function generates the HTML pages.
# Uses citeKey and pathToBibFile as 2 arguments
print("=" * 80)
print(citeKey)
jsonFile = pathToBibFile.replace(
".bib",
".json") # Loads JSON file, gets path by replacing .bib extension
# with .json extension
with open(jsonFile) as jsonData:
ocred = json.load(jsonData)
pNums = ocred.keys() # Generates page links
pageDic = functions.generatePageLinks(
pNums) # Page dictionary creates a table of contents with a unique
# name for each of the publications, creating links (making
# it navigable). It's the panel on the left.
# Loads page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# Loads individual bib record (can use the functions that have already been written)
bibFile = pathToBibFile
bibDic = functions.loadBib(
bibFile) #LoadBib loads the entire bibliography or a single record
bibforHTML = functions.prettifyBib(
bibDic[citeKey]["complete"]) # Makes the bib file look better for
# this view, removing curly brackets and
# unnecessary fields (it's a simple find
# and replace).
orderedPages = list(
pageDic.keys()
) # Creates a list of all the keys to generate page numbers, taken from
# the page dictionary generated from the function above.
# This is just a long loop that creates every single page.
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
pageTemp = template # Takes a template
pageTemp = pageTemp.replace(
"@PAGELINKS@",
v) # Replaces all of the items in the template with
# different values, creating an individual page for
# every page in the publication.
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
pageTemp = pageTemp.replace("@CITATIONKEY@", citekey)
# This concerns the DETAILS page
if k != "DETAILS": # All of the pages are numbered, except for the initial page
mainElement = '<ing src="@PAGEFILE@" width="100%" alt=">'.replace(
"@PAGEFILE@", "%s.png" % k)
# These are the regular pages
pageTemp = pageTemp.replace(
"@MAINELEMENT@",
mainElement) # Replaces it with the main element
pageTemp = pageTemp.replace("@OCREDCONTENT@", ocred[k].replace(
"\n", "<br>")) # Removes the OCR
else: # When the page is 'DETAILS'
mainElement = bibForHTML.replace(
"\n", "<br> ") # DETAILS page has a HTML
mainElement = '<div class="bib">%s</div>' % mainElement # Inserts element into a specific class
# NB: class and div tags in HTML correspond to the stylesheet specifications
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">' # Word cloud element
pageTemp = pageTemp.replace(
"@MAINELEMENT@",
mainElement) # Replaces main element with the element
# that was formed before
pageTemp = pageTemp.replace("@OCREDCONTENT@",
"") # Removes the OCR content
# Creates links to the 'previous' and 'next' pages.
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
if k == "DETAILS": # When on the first page 'DETAILS', you won't have the one before it
nextPage = "0001.html"
prevPage = "" # Creates an empty element for the previous page that doesn't exist
elif k == "0001": # When on page 1,...
nextPage = "0002.html"
prevPage = "DETAILS.html" # ... the page before it will be DETAILS.
elif o == len(orderedPages) - 1: # When on the last page,...
nextPage = "" # ... there won't be a next page
prevPage = orderedPages[o - 1] + ".html"
else: # Regular pages
nextPage = orderedPages[
o + 1] + ".html" # Adds 1 for the next page
prevPage = orderedPages[
o - 1] + ".html" # Subtracts 1 for previous page
pageTemp = pageTemp.replace(
"@NEXTPAGEHTML@", nextPage) # Find and replace, which replaces
# the next value with a given value
pageTemp = pageTemp.replace(
"@PREVIOUSPAGEHTML@", prevPage) # Replaces previous value with
# a given value.
pagePath = os.path.join(
pathToBibFile.replace(citeKey + ".bib", ""), "pages",
"%s.html" % k)
# Saves the actual page.
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
def generatePublicationInterface(citeKey, pathToBibFile):
print("="*80)
print(citeKey)
######################
#SINGLE PUBLICATION#
######################
jsonFile = pathToBibFile.replace(".bib", ".json") #get JSON files
with open(jsonFile) as jsonData:
ocred = json.load(jsonData) #open file
pNums = ocred.keys() #get pages of publication
pageDic = functions.generatePageLinks(pNums) #use pre-defined function
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
bibDic = functions.loadBib(bibFile) #use pre-defined function
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"]) #use pre-defined function
orderedPages = list(pageDic.keys()) #make list of pages
authorOrEditor = "[No data]"
if "editor" in bibDic[citeKey]:
authorOrEditor = bibDic[citeKey]["editor"]
if "author" in bibDic[citeKey]:
authorOrEditor = bibDic[citeKey]["author"]
date = "nodate"
if "year" in bibDic[citeKey]:
date = bibDic[citeKey]["year"]
for o in range(0, len(orderedPages)): #loop through pages of individual bib file
#print(o)
k = orderedPages[o] #page number
v = pageDic[orderedPages[o]] #page
pageTemp = template
pageTemp = pageTemp.replace("@PAGELINKS@", v) #replace pattern with page
pageTemp = pageTemp.replace("@PATHTOFILE@", "") #replace pattern with empty string
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey) #replace pattern with publication ID
wCloud = '\n<img src="../@WCLOUD@" width="100%" alt="wordcloud">'.replace("@WCLOUD@", "%s.jpg" % citeKey)
pageTemp = pageTemp.replace("@WORD_CLOUD@", wCloud)
pageTemp = pageTemp.replace("@PUB_AUTHOR@", authorOrEditor)
pageTemp = pageTemp.replace("@PUB_YEAR@", date)
pageTemp = pageTemp.replace("@PUB_TITLE@", bibDic[citeKey]["title"].replace("{", "").replace("}", ""))
emptyResults = '<tr><td><i>%s</i></td><td><i>%s</i></td><td><i>%s</i></td></tr>'
if k != "DETAILS": #if not set to overview page
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace("@PAGEFILE@", "%s.png" % k) #use ocred page as main element
pageKey = citeKey+"__%04d" % roundUp(int(k), 4)
#print("pagekey: ", pageKey)
if pageKey in pageConnData:
print("pagekey found: ", pageKey)
formattedResults = "\n".join(pageConnData[pageKey])
print(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data")
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults)
mainElement += ocrTemplate.replace("@OCREDCONTENTTEMP@", ocred[k].replace("\n", "<br>"))
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
else:
#reference = generateReferenceSimple(citeKey)
reference = "OVERVIEW"
mainElement = "<h4><font color=#8baad1><center>%s</center></font></h4>\n\n" % reference
bibElement = '<div class="bib">%s</div>' % bibForHTML.replace("\n", "<br> ")
bibElement = generalTemplate.replace("@ELEMENTCONTENT@", bibElement)
bibElement = bibElement.replace("@ELEMENTHEADER@", "BibTeX Bibliographical Record")
mainElement += bibElement + "\n\n"
wordCloud = '\n<img src="../' + citeKey + '.jpg" width="100%" alt="wordcloud">'
wordCloud = generalTemplate.replace("@ELEMENTCONTENT@", wordCloud)
wordCloud = wordCloud.replace("@ELEMENTHEADER@", "WordCloud of Keywords (<i>tf-idf</i>)")
mainElement += wordCloud + "\n\n"
if citeKey in publConnData:
formattedResults = "\n".join(publConnData[citeKey])
#input(formattedResults)
else:
formattedResults = emptyResults % ("no data", "no data", "no data")
mainElement += connectionsTemplate.replace("@CONNECTEDTEXTSTEMP@", formattedResults)
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
#set order of the page layout
if k == "DETAILS":
nextPage = "0001.html"
prevPage = "" #no previous page
elif k == "0001":
nextPage = "0002.html"
prevPage = "DETAILS.html" #set previous page because it is not a serial number
elif o == len(orderedPages)-1: #take care of special case
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: #set path for individual pages
f9.write(pageTemp)
def generatePublicationInterface(citeKey, pathToBibFile):
print("=" * 80)
print(citeKey)
# replace file extension
jsonFile = pathToBibFile.replace(".bib", ".json")
# open json file
with open(jsonFile) as jsonData:
# save the content from the json file to ocred (string)
ocred = json.load(jsonData)
# save page numbers to pNums
pNums = ocred.keys()
# call the function generatePageLinks with pNums as input value and save the return value to pageDic
pageDic = functions.generatePageLinks(pNums)
# load page template
with open(settings["template_page"], "r", encoding="utf8") as ft:
template = ft.read()
# load individual bib record
bibFile = pathToBibFile
# call the function loadBib with bibFile as input value and save the return value to bibDic
bibDic = functions.loadBib(bibFile)
# call the function prettifyBib with bibDic[citeKey]["complete"] as input value and save the return value to bibForHTML
bibForHTML = functions.prettifyBib(bibDic[citeKey]["complete"])
# create a list with the keys oft the dictionary pageDic and save it to orderedPages
orderedPages = list(pageDic.keys())
# loop: start = 0; end = number of elements in the list orderedPages
for o in range(0, len(orderedPages)):
#print(o)
k = orderedPages[o]
v = pageDic[orderedPages[o]]
# save template to pageTemp
pageTemp = template
# replace @MAINCONTENT@ with v
pageTemp = pageTemp.replace("@PAGELINKS@", v)
# replace @PATHTOFILE@ with ""
pageTemp = pageTemp.replace("@PATHTOFILE@", "")
# replace @CITATIONKEY@ with citeKey
pageTemp = pageTemp.replace("@CITATIONKEY@", citeKey)
if k != "DETAILS": # normal page
# png: replace @PAGEFILE@ with name of the image
mainElement = '<img src="@PAGEFILE@" width="100%" alt="">'.replace(
"@PAGEFILE@", "%s.png" % k)
# replace @MAINELEMENT@ with mainElement
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
# replace @OCREDCONTENT@ with the ocred text (replace "\n" by "<br>")
pageTemp = pageTemp.replace("@OCREDCONTENT@",
ocred[k].replace("\n", "<br>"))
else: # detail page
# save the detail text (bib file) to mainElement
mainElement = bibForHTML.replace("\n", "<br> ")
# add html to detail text
mainElement = '<div class="bib">%s</div>' % mainElement
# add image workcloud
mainElement += '\n<img src="wordcloud.jpg" width="100%" alt="wordcloud">'
# replace @MAINELEMENT@ with mainElement
pageTemp = pageTemp.replace("@MAINELEMENT@", mainElement)
# replace @OCREDCONTENT@ with ""
pageTemp = pageTemp.replace("@OCREDCONTENT@", "")
# @NEXTPAGEHTML@ and @PREVIOUSPAGEHTML@
# detail page
if k == "DETAILS":
nextPage = "0001.html"
# no previous page
prevPage = ""
# first page of publication
elif k == "0001":
nextPage = "0002.html"
# previous page = detail page
prevPage = "DETAILS.html"
# last page of publication
elif o == len(orderedPages) - 1:
# no next page
nextPage = ""
# prevPage: page - 1
prevPage = orderedPages[o - 1] + ".html"
# "normal" page of publication
else:
# nextPage: page + 1
nextPage = orderedPages[o + 1] + ".html"
# prevPage: page - 1
prevPage = orderedPages[o - 1] + ".html"
# replace @NEXTPAGEHTML@ with nextPage
pageTemp = pageTemp.replace("@NEXTPAGEHTML@", nextPage)
# replace @PREVIOUSPAGEHTML@ with prevPage
pageTemp = pageTemp.replace("@PREVIOUSPAGEHTML@", prevPage)
# path to html pages
pagePath = os.path.join(
pathToBibFile.replace(citeKey + ".bib", ""), "pages",
"%s.html" % k)
# create html pages
with open(pagePath, "w", encoding="utf8") as f9:
f9.write(pageTemp)
