add page from convertion

Conversion/ToTSV/risCorpusToTSV/risCorpusToTsv.py

@@ -66,7 +66,7 @@ with open(path, 'r') as corpus :
 			day = tmp[2]
 		else:
 			if doc.__contains__('year'):
-				year = doc['year']
+				year = doc['year'].replace('/','').replace('.','')
 			else:
 				year = str(date.today().year)
 

Streamlit/lang/text_GarganTextJsonToTSV.csv

@@ -3,7 +3,7 @@ fr,title,"# Json Vers TSV"
 en,title,"# Json To TSV"
 
 fr,text,"Transforme un corpus Json venant de Gargantext en TSV pour GarganText"
-en,text,"Transform a Json corpus fron GarganText to a TSV file for GarganText"
+en,text,"Transform a Json corpus from GarganText to a TSV file for GarganText"
 
 fr,file,"Choisir un fichier"
 en,file,"Choose a file"

Streamlit/lang/text_PubMedToGarganText.csv

+locale,key,value
+fr,title,"# Pubmed Vers GarganText"
+en,title,"# Pubmed To GarganText"
+
+fr,text,"Transforme un corpus pubmed en TSV pour GarganText"
+en,text,"Transform a pubmed corpus to a TSV file for GarganText"
+
+fr,file,"Choisir un fichier"
+en,file,"Choose a file"
+
+fr,new_file,"Télécharge ton fichier TSV :"
+en,new_file,"Download your TSV file:"
+
+fr,error,"Erreur : le fichier n'est pas valide"
+en,error,"Error : the file isn't valid"
\ No newline at end of file

Streamlit/lang/text_RisToGarganText.csv

+locale,key,value
+fr,title,"# Ris Vers GarganText"
+en,title,"# Ris To GarganText"
+
+fr,text,"Transforme un corpus ris en TSV pour GarganText"
+en,text,"Transform a ris corpus to a TSV file for GarganText"
+
+fr,file,"Choisir un fichier"
+en,file,"Choose a file"
+
+fr,new_file,"Télécharge ton fichier TSV :"
+en,new_file,"Download your TSV file:"
+
+fr,error,"Erreur : le fichier n'est pas valide"
+en,error,"Error : the file isn't valid"
\ No newline at end of file

Streamlit/pages/Pubmed_To_GarganText.py

+"""
+Streamlit Application
+Loïc Chapron
+"""
+
+import streamlit as st
+import pandas as pd
+import nbib
+import re
+import calendar
+
+st.image('img/gargantool_banner.jpg')
+
+st.markdown("""
+        <style>
+               .block-container {
+                    padding-top: 2rem;
+                    padding-bottom: 0rem;
+                    padding-left: 1rem;
+                    padding-right: 1rem;
+                }
+        </style>
+        """, unsafe_allow_html=True)
+
+def load_bundle(lang):
+    df = pd.read_csv("lang/text_PubMedToGarganText.csv")
+    df = df.query(f"locale == '{lang}'")
+
+    tmp = {}
+    for i in range(len(df)):
+        tmp[df.key.to_list()[i]] = df.value.to_list()[i]
+    return tmp
+
+def update_lang():
+    st.session_state.general_text_dict = load_bundle(st.session_state.general_lang_dict[st.session_state.general_language])
+
+if 'general_session_page' not in st.session_state.keys():
+    st.session_state.general_lang_dict = {'Français' : 'fr', 'English': 'en'}
+    st.session_state.general_text_dict = load_bundle('fr')
+    st.session_state.general_language = 'Français'
+    st.session_state.general_session_page = 'PubMedToGarganText'
+elif st.session_state.general_session_page != 'PubMedToGarganText':
+	st.session_state.general_text_dict = load_bundle(st.session_state.general_lang_dict[st.session_state.general_language])
+	st.session_state.general_session_page = 'PubMedToGarganText'
+	for key in st.session_state.keys():
+		if 'general_' not in key:
+			del st.session_state[key]
+
+
+st.selectbox('Langue', list(st.session_state.general_lang_dict.keys()), list(st.session_state.general_lang_dict.keys()).index(st.session_state.general_language),key='general_language', on_change=update_lang)
+
+
+
+def read_file(file):
+    docs = nbib.read(file.read().decode('utf-8'))
+    output = "title\tsource\tpublication_year\tpublication_month\tpublication_day\tabstract\tauthors\tweight\n"
+
+    for doc in docs :
+
+        keys = doc.keys()
+
+        if len(list(set(['title','publication_date','authors']) & set(keys))) < 3 :
+            continue
+
+        if 'journal' in keys :
+            source = doc['journal']
+        else :
+            source = ""	
+            
+        if 'abstract' in keys :
+            abstract = doc['abstract']
+        else :
+            abstract = ""
+
+        title = doc['title']
+        date = doc['publication_date'].split(' ')
+        year = date[0]
+        if len(date) > 1:
+            try:
+                month = list(calendar.month_abbr).index(date[1])
+            except Exception as e:
+                month = '1'
+        else:
+            month = '1'
+        
+        if len(date) > 2:
+            day = date[2]
+        else:
+            day = '1'
+
+        abstract = re.sub('\"', "", abstract).replace("\t", "")
+        title = re.sub('\"', "", title).replace("\t", "")
+
+        authors_lst = []
+
+        for author in doc['authors'] :
+
+            authors_lst.append((author['author']).replace(',',''))
+
+        authors = ','.join(authors_lst)
+
+        row = str(title) + "\t" + "scopus" + "\t" + year + "\t" + str(month) + "\t" + str(day) + "\t" + abstract + "\t" + authors + "\t" + str(1) + "\n"
+        
+        output += row
+    return output
+
+st.write(st.session_state.general_text_dict['title'])
+st.write(st.session_state.general_text_dict['text'])
+file = st.file_uploader(st.session_state.general_text_dict['file'],type=["txt"],key='file')
+
+if file:
+	try:
+		name = file.name.split('.')[0] + '.csv'
+		st.write(st.session_state.general_text_dict['new_file'])
+		
+		st.download_button(name, read_file(file), name)
+	except Exception as e:
+		st.write(st.session_state.general_text_dict['error'])
+		print(e)
+	file.close()

Streamlit/pages/Ris_To_GarganText.py

+"""
+Streamlit Application
+Loïc Chapron
+"""
+
+import streamlit as st
+import pandas as pd
+import rispy 
+from datetime import date
+
+st.image('img/gargantool_banner.jpg')
+
+st.markdown("""
+        <style>
+               .block-container {
+                    padding-top: 2rem;
+                    padding-bottom: 0rem;
+                    padding-left: 1rem;
+                    padding-right: 1rem;
+                }
+        </style>
+        """, unsafe_allow_html=True)
+
+def load_bundle(lang):
+    df = pd.read_csv("lang/text_RisToGarganText.csv")
+    df = df.query(f"locale == '{lang}'")
+
+    tmp = {}
+    for i in range(len(df)):
+        tmp[df.key.to_list()[i]] = df.value.to_list()[i]
+    return tmp
+
+def update_lang():
+    st.session_state.general_text_dict = load_bundle(st.session_state.general_lang_dict[st.session_state.general_language])
+
+if 'general_session_page' not in st.session_state.keys():
+    st.session_state.general_lang_dict = {'Français' : 'fr', 'English': 'en'}
+    st.session_state.general_text_dict = load_bundle('fr')
+    st.session_state.general_language = 'Français'
+    st.session_state.general_session_page = 'RisToGarganText'
+elif st.session_state.general_session_page != 'RisToGarganText':
+	st.session_state.general_text_dict = load_bundle(st.session_state.general_lang_dict[st.session_state.general_language])
+	st.session_state.general_session_page = 'RisToGarganText'
+	for key in st.session_state.keys():
+		if 'general_' not in key:
+			del st.session_state[key]
+
+
+st.selectbox('Langue', list(st.session_state.general_lang_dict.keys()), list(st.session_state.general_lang_dict.keys()).index(st.session_state.general_language),key='general_language', on_change=update_lang)
+
+
+
+def read_file(file):
+    output = "title\tsource\tpublication_year\tpublication_month\tpublication_day\tabstract\tauthors\tweight\n"
+
+
+    docs = rispy.loads(file.read().decode('utf-8'))
+       
+    for doc in docs :
+        keys = doc.keys()
+        
+        if 'secondary_title' in keys :
+            source = doc['secondary_title']
+        else :
+            source = ""
+
+        if 'abstract' in keys :
+            abstract = doc['abstract']
+        else :
+            abstract = ""			
+        title = doc['title']
+
+        month = '1'
+        day = '1'
+        if doc.__contains__('date'):
+            tmp = doc['date'].split("/")
+            year = tmp[0]
+            month = tmp[1]
+            day = tmp[2]
+        else:
+            if doc.__contains__('year'):
+                year = doc['year'].replace('/','').replace('.','')
+            else:
+                year = str(date.today().year)
+
+        if doc.__contains__('authors'):
+            authors = ';'.join(doc['authors'])
+        else:
+            authors = ""
+            
+
+        row = str(title) + "\t" + str(source) + "\t" + year + "\t" + month + "\t" + day + "\t" + abstract + "\t" + authors + "\t" + str(1) + "\n"
+          
+        output += row
+    return output
+
+st.write(st.session_state.general_text_dict['title'])
+st.write(st.session_state.general_text_dict['text'])
+file = st.file_uploader(st.session_state.general_text_dict['file'],type=["ris"],key='file')
+
+if file:
+	try:
+		name = file.name.split('.')[0] + '.csv'
+		st.write(st.session_state.general_text_dict['new_file'])
+		
+		st.download_button(name, read_file(file), name)
+	except Exception as e:
+		st.write(st.session_state.general_text_dict['error'])
+		print(e)
+	file.close()
\ No newline at end of file