Update pages

Streamlit/lang/text_PDFtoTSV.csv

@@ -29,11 +29,11 @@ en,warning,"Warning ! Multiple languages have been detected at the source : "
 en,warning2,"The following languages have been detected : "
 
 
-fr,globalWarning, "Attention ! Plusieurs langues ont été détectées entre vos pdf ! Les langues suivantes ont été détectées : "
-en,globalWarning,"Warning ! Multiple languages have been detected for your pdfs file ! The following languages have been detected : "
+fr,globalWarning, "Attention ! Plusieurs langues ont été détectées entre vos pdf !\nLes langues suivantes ont été détectées : "
+en,globalWarning,"Warning ! Multiple languages have been detected for your pdfs file !\nThe following languages have been detected : "
 
 
-fr,advice,"Cela pourrait affecter massivement l'analyse de GarganText. Vous pouvez régler ça en traduisant avec l'outil TsvTranslator."
+fr,advice,"Cela pourrait affecter massivement l'analyse de GarganText.\nVous pouvez régler ça en traduisant avec l'outil TsvTranslator."
 en,advice,"This could massively affect the analysis of Gargantext.\nYou can correct this by translation with the TsvTranslator tool."
 
 

Streamlit/pages/PDF_to_TSV.py

@@ -3,22 +3,23 @@ Streamlit Application
 Nicolas Atrax
 """
 
-import streamlit as st
-import pandas as pd
-import chardet
-import re
-from datetime import date
-import codecs
-import os
-import tempfile
-import zipfile
 import shutil
+import zipfile
+import tempfile
+import os
+import codecs
+from datetime import date
+import re
+import chardet
+import pandas as pd
+import streamlit as st
 from lib.tika.tika import parser
 from lib.langdetect.langdetect import detect
 from lib.langdetect.langdetect.lang_detect_exception import LangDetectException
 import src.basic as tmp
 os.environ['TIKA_SERVER_JAR'] = 'https://repo1.maven.org/maven2/org/apache/tika/tika-server/1.19/tika-server-1.19.jar'
 
+
 tmp.base("PDFtoTSV")
 
 # Tool Code Start
@@ -83,7 +84,7 @@ def detectMultipleLanguages(languages, fileName):
             detected += l + " : " + str(languages[l]) + "%"
             valuable.append(l)
     if len(valuable) > 1:
-        st.session_state.warning += st.session_state.general_text_dict['warning'] + \
+        st.session_state.warning += st.session_state.general_text_dict['warning'] + "\"" + \
             fileName + "\" !\n"
         st.session_state.warning += st.session_state.general_text_dict['warning2'] + \
             detected + " \n"
@@ -96,9 +97,9 @@ def detectMultiplePdfLanguages():
     languages = []
     for l in st.session_state.pdfLanguages.values():
         if l not in languages and len(languages) == 1:
-            st.write(st.session_state.general_text_dict['globalWarning'])
-            st.write(str(st.session_state.pdfLanguages))
-            st.write(st.session_state.general_text_dict['advice'])
+            st.error(st.session_state.general_text_dict['globalWarning'])
+            st.error(str(st.session_state.pdfLanguages))
+            st.error(st.session_state.general_text_dict['advice'])
             return
         if len(languages) == 0:
             languages.append(l)
@@ -193,24 +194,6 @@ def extractAllPDF(zipDir, zipFile):
             if ".pdf" in info.filename:
                 zipRef.extract(info, zipDir)
 
-
-def convertAllPDF(zipFile, zipDir):
-
-    pdfLanguages = {}
-    tsv = "authors\tsource\tpublication_year\tpublication_month\tpublication_day\ttitle\tabstract\n"
-    with tempfile.TemporaryDirectory() as pdfDir:
-        st.session_state.dir = pdfDir
-        extractAllPDF(zipDir, zipFile)
-        for file in os.listdir(zipDir):
-            if ".pdf" in file:
-                tmp, languages = txtToTSV(
-                    file, zipDir + '/' + file, pdfDir)
-                tsv += "\n" + tmp
-
-        with open(pdfDir + "/final.tsv", "w", encoding='utf-8-sig') as file:
-            file.write(tsv)
-        shutil.make_archive(zipDir + "/PDFCompilation", 'zip', pdfDir)
-
 # Tool Code End
 
 
@@ -306,7 +289,8 @@ if st.session_state.page == 3:
     shutil.make_archive(st.session_state.zipDir.name +
                         "/PDFCompilation", 'zip', st.session_state.pdfDir.name)
     with open(st.session_state.zipDir.name + "/PDFCompilation.zip", 'rb') as zip:
-        st.write(st.session_state.warning)
+        if st.session_state.warning != "":
+            st.error(st.session_state.warning)
         detectMultiplePdfLanguages()
         st.write(st.session_state.general_text_dict['new_file'])
         st.download_button("PDFCompilation.zip",

Streamlit/pages/PDF_to_TXT.py

@@ -3,6 +3,8 @@ Streamlit Application
 Nicolas Atrax
 """
 
+import src.basic as tmp
+from lib.tika.tika import parser
 import streamlit as st
 import pandas as pd
 import chardet
@@ -11,8 +13,6 @@ from datetime import date
 import codecs
 import os
 import tempfile
-from lib.tika.tika import parser
-import src.basic as tmp
 os.environ['TIKA_SERVER_JAR'] = 'https://repo1.maven.org/maven2/org/apache/tika/tika-server/1.19/tika-server-1.19.jar'
 
 tmp.base("PDFtoTXT")

Streamlit/pages/TXT_to_TSV.py

@@ -61,7 +61,7 @@ def detectMultipleLanguages(languages, fileName):
             detected += l + " : " + str(languages[l]) + "%"
             valuable.append(l)
     if len(valuable) > 1:
-        st.session_state.warning += st.session_state.general_text_dict['warning'] + \
+        st.session_state.warning += st.session_state.general_text_dict['warning'] + "\"" + \
             fileName + "\" !\n"
         st.session_state.warning += st.session_state.general_text_dict['warning2'] + \
             detected + " \n"
@@ -145,6 +145,9 @@ form = st.form('api')
 if 'page' not in st.session_state:
     st.session_state.page = 0
 
+if 'warning' not in st.session_state:
+    st.session_state.warning = ""
+
 
 def setSubmit():
     st.session_state.submit = True
@@ -193,4 +196,6 @@ if st.session_state.page == 1:
     name = st.session_state.file.name.split('.')[0] + '.tsv'
     st.write(st.session_state.general_text_dict['new_file'])
     st.session_state.submit = False
+    if st.session_state.warning != "":
+        st.error(st.session_state.warning)
     st.download_button(name, txt, name, on_click=setPage())