[UPDATE] merge conflict

init/sql/drop_db.sh

+
+export PGPASSWORD=C8kdcUrAQy66U 
+
+psql -U gargantua -d gargandb -f drop_db.sql

init/sql/rename_metadata.sql

+
+ALTER TABLE node_node RENAME metadata TO hyperdata ;
+
+ALTER TABLE node_metadata RENAME TO node_hyperdata ;
+
+ALTER TABLE node_node_metadata RENAME TO node_node_hyperdata ;
+ALTER TABLE node_node_hyperdata RENAME metadata_id TO  hyperdata_id ;
+

node/models.py

@@ -306,7 +306,6 @@ class Node(CTENode):
         self.hyperdata['Processing'] = 0
         self.save()
 
-
 class Node_Hyperdata(models.Model):
     node        = models.ForeignKey(Node, on_delete=models.CASCADE)
     hyperdata    = models.ForeignKey(Hyperdata)

parsing/FileParsers/EuropressFileParser.py

@@ -8,7 +8,7 @@ import dateutil.parser
 from .FileParser import FileParser
 from ..NgramsExtractors import *
 
-
+from admin.utils import PrintException
 
 class EuropressFileParser(FileParser):
 
@@ -29,8 +29,8 @@ class EuropressFileParser(FileParser):
         if encoding != "utf-8":
             try:
                 contents = contents.decode("latin1", errors='replace').encode(codif)
-            except Exception as error:
-                print(error)
+            except:
+                PrintException()
 #                try:
 #                    contents = contents.decode(encoding, errors='replace').encode(codif)
 #                except Exception as error:
@@ -40,7 +40,7 @@ class EuropressFileParser(FileParser):
             html_parser = etree.HTMLParser(encoding=codif)
             html = etree.fromstring(contents, html_parser)
 
-            try:
+            try :
 
                 format_europresse = 50
                 html_articles = html.xpath('/html/body/table/tbody')
@@ -51,15 +51,15 @@ class EuropressFileParser(FileParser):
                     if len(html_articles) < 1:
                         format_europresse = 1
                         html_articles = html.xpath('//div[@id="docContain"]')
-            except Exception as error:
-                print(error)
+            except :
+                PrintException()
 
-            if format_europresse == 50:
+            if format_europresse == 50 :
                 name_xpath      = "./tr/td/span[@class = 'DocPublicationName']"
-                header_xpath = "//span[@class = 'DocHeader']"
+                header_xpath    = "./tr/td/span[@class = 'DocHeader']"
                 title_xpath     = "string(./tr/td/span[@class = 'TitreArticleVisu'])"
                 text_xpath      = "./tr/td/descendant-or-self::*[not(self::span[@class='DocHeader'])]/text()"
-            elif format_europresse == 1:
+            elif format_europresse == 1 :
                 name_xpath      = "//span[@class = 'DocPublicationName']"
                 header_xpath    = "//span[@class = 'DocHeader']"
                 title_xpath     = "string(//div[@class = 'titreArticleVisu'])"
@@ -79,8 +79,8 @@ class EuropressFileParser(FileParser):
                 doi_xpath  = "//span[@id='ucPubliC_lblNodoc']/text()"
 
 
-        except Exception as error:
-            print(error)
+        except Exception as error :
+            PrintException()
 
         # parse all the articles, one by one
         try:
@@ -99,7 +99,18 @@ class EuropressFileParser(FileParser):
                             else:
                                 hyperdata['journal'] = name.text.encode(codif)
 
+                    countbis = 0
+
                     for header in html_article.xpath(header_xpath):
+#                        print(count)
+#                        countbis += 1
+
+#                        try:
+#                            print('109', hyperdata['publication_date'])
+#                        except:
+#                            print('no date yet')
+#                            pass
+
                         try:
                             text = header.text
                             #print("header", text)
@@ -145,12 +156,10 @@ class EuropressFileParser(FileParser):
                                         hyperdata['publication_date'] = datetime.strptime(text, '%d %B %Y')
                                         # hyperdata['publication_date'] = dateutil.parser.parse(text)
                                     except Exception as error:
-                                        print(error)
-                                        print(text)
+                                        print(error, text)
                                         pass
 
 
-                        
                         if test_date_en is not None:
                             localeEncoding = "en_GB.UTF-8"
                             locale.setlocale(locale.LC_ALL, localeEncoding)
@@ -168,6 +177,13 @@ class EuropressFileParser(FileParser):
                         if test_page is not None:
                             hyperdata['page'] = test_page.group(1).encode(codif)
 
+#                    try:
+#                        print('183', hyperdata['publication_date'])
+#                    except:
+#                        print('no date yet')
+#                        pass
+#
+
                     hyperdata['title'] = html_article.xpath(title_xpath).encode(codif)
                     hyperdata['abstract']  = html_article.xpath(text_xpath)
 
@@ -215,7 +231,7 @@ class EuropressFileParser(FileParser):
                     hyperdata['publication_year']  = hyperdata['publication_date'].strftime('%Y')
                     hyperdata['publication_month'] = hyperdata['publication_date'].strftime('%m')
                     hyperdata['publication_day']  = hyperdata['publication_date'].strftime('%d')
-                    hyperdata.pop('publication_date')
+                    #hyperdata.pop('publication_date')
 
                     if len(hyperdata['abstract'])>0 and format_europresse == 50:
                         hyperdata['doi'] = str(hyperdata['abstract'][-9])

parsing/FileParsers/FileParser.py

 import collections
+import datetime
 import dateutil.parser
 import zipfile
 import chardet
+import re
 
 from ..Caches import LanguagesCache
 
 
+DEFAULT_DATE = datetime.datetime(datetime.MINYEAR, 1, 1)
+
+
 class FileParser:
     """Base class for performing files parsing depending on their type.
     """
@@ -29,6 +34,21 @@ class FileParser:
         """
 
         # First, check the split dates...
+        date_string = hyperdata.get('publication_date_to_parse', None)
+        if date_string is not None:
+            date_string = re.sub(r'\/\/+', '', date_string)
+            date_string = re.sub(r'undefined', '', date_string)
+            try:
+                hyperdata['publication' + "_date"] = dateutil.parser.parse(
+                    date_string,
+                    default=DEFAULT_DATE
+                ).strftime("%Y-%m-%d %H:%M:%S")
+            except:
+                print('Parser Zotero, Date not parsed for:', date_string)
+                hyperdata['publication_date'] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+
+        elif hyperdata.get('publication_year', None) is not None:
             prefixes = [key[:-5] for key in hyperdata.keys() if key[-5:] == "_year"]
             for prefix in prefixes:
                 date_string = hyperdata[prefix + "_year"]
@@ -51,11 +71,15 @@ class FileParser:
                     hyperdata[prefix + "_date"] = dateutil.parser.parse(date_string).strftime("%Y-%m-%d %H:%M:%S")
                 except:
                     pass
+        else:
+            hyperdata['publication_date'] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 
         # ...then parse all the "date" fields, to parse it into separate elements
         prefixes = [key[:-5] for key in hyperdata.keys() if key[-5:] == "_date"]
         for prefix in prefixes:
             date = dateutil.parser.parse(hyperdata[prefix + "_date"])
+            #print(date)
+
             hyperdata[prefix + "_year"]      = date.strftime("%Y")
             hyperdata[prefix + "_month"]     = date.strftime("%m")
             hyperdata[prefix + "_day"]       = date.strftime("%d")
@@ -65,6 +89,7 @@ class FileParser:
 
         # finally, return the transformed result!
         return hyperdata
+        print(hyperdata['publication_date'])
 
     def format_hyperdata_languages(self, hyperdata):
         """format the languages found in the hyperdata."""

parsing/FileParsers/RisFileParser.py

@@ -3,6 +3,8 @@ from .FileParser import FileParser
 
 from ..Caches import LanguagesCache
 
+from admin.utils import PrintException
+
 class RisFileParser(FileParser):
 
     def __init__(self, language_cache=None):
@@ -57,5 +59,11 @@ class RisFileParser(FileParser):
                     print(error)
         # if a hyperdata object is left in memory, yield it as well
         if hyperdata:
+#            try:
+#                if hyperdata['date_to_parse']:
+#                    print(hyperdata['date_to_parse'])
+#            except:
+#                pass
+#
             #print(hyperdata['title'])
             yield hyperdata

parsing/FileParsers/ZoteroFileParser.py

+from .RisFileParser import RisFileParser
+
+from ..Caches import LanguagesCache
+
+class ZoteroFileParser(RisFileParser):
+    def __init__(self):
+        super(RisFileParser, self).__init__()
+
+        self._begin = 6
+
+        self._parameters = {
+            b"ER":  {"type": "delimiter"},
+            b"TI":  {"type": "hyperdata", "key": "title", "separator": " "},
+            b"AU":  {"type": "hyperdata", "key": "authors", "separator": ", "},
+            b"UR":  {"type": "hyperdata", "key": "doi"},
+            b"DA":  {"type": "hyperdata", "key": "publication_date_to_parse"},
+            b"PY":  {"type": "hyperdata", "key": "publication_year"},
+            b"PD":  {"type": "hyperdata", "key": "publication_month"},
+            b"LA":  {"type": "hyperdata", "key": "language_iso2"},
+            b"AB":  {"type": "hyperdata", "key": "abstract", "separator": " "},
+            b"WC":  {"type": "hyperdata", "key": "fields"},
+        }
+

parsing/FileParsers/__init__.py

 from .RisFileParser import RisFileParser
 from .IsiFileParser import IsiFileParser
 from .JstorFileParser import JstorFileParser
+from .ZoteroFileParser import ZoteroFileParser
 from .PubmedFileParser import PubmedFileParser
 from .EuropressFileParser import EuropressFileParser
 from .ISText import ISText

parsing/parsers_config.py

@@ -4,12 +4,11 @@ parsers = {
         'Pubmed (xml format)'               : PubmedFileParser,
         'Web of Science (ISI format)'       : IsiFileParser,
         'Scopus (RIS format)'               : RisFileParser,
-        'Zotero (RIS format)'               : JstorFileParser,
+        'Zotero (RIS format)'               : ZoteroFileParser,
         'Jstor (RIS format)'                : JstorFileParser,
         #'Europress'                        : EuropressFileParser,
         'Europress (French)'                : EuropressFileParser,
         'Europress (English)'               : EuropressFileParser,
         'CSVParser'                : CSVParser,
-        
     }