[FEAT] Ajout de REPEC parser, format RIS.

gargantext/constants.py

@@ -128,7 +128,7 @@ LANGUAGES = {
 
 
 from gargantext.util.parsers import \
-    EuropressParser, RISParser, PubmedParser, ISIParser, CSVParser, ISTexParser, CernParser
+    EuropressParser, RISParser, PubmedParser, ISIParser, CSVParser, ISTexParser, CernParser, RepecParser
 
 def resourcetype(name):
     '''
@@ -208,6 +208,12 @@ RESOURCETYPES = [
          #~ "base_url": "http://api.scoap3.org/search?",
     },
 
+    # type 11
+    {   'name': 'REPEC (RIS format)',
+        'parser': RepecParser,
+        'default_language': 'en',
+    },
+
 ]
 
 # linguistic extraction parameters ---------------------------------------------

gargantext/util/parsers/Ris.py

@@ -18,11 +18,12 @@ class RISParser(Parser):
         b"ER":  {"type": "delimiter"},
         b"TI":  {"type": "hyperdata", "key": "title", "separator": " "},
         b"ST":  {"type": "hyperdata", "key": "subtitle", "separator": " "},
-        b"AU":  {"type": "hyperdata", "key": "authors", "separator": ", "},
+        b"AU":  {"type": "hyperdata", "key": "authors", "separator": "\n"},
         b"T2":  {"type": "hyperdata", "key": "journal"},
         b"UR":  {"type": "hyperdata", "key": "doi"},
         b"PY":  {"type": "hyperdata", "key": "publication_year"},
         b"PD":  {"type": "hyperdata", "key": "publication_month"},
+        b"N1":  {"type": "hyperdata", "key": "references", "separator": ", "},
         b"LA":  {"type": "hyperdata", "key": "language_iso2"},
         b"AB":  {"type": "hyperdata", "key": "abstract", "separator": " "},
         b"WC":  {"type": "hyperdata", "key": "fields"},

gargantext/util/parsers/Ris_repec.py

+from ._Parser import Parser
+
+from gargantext.util.languages import languages
+
+#from admin.utils import PrintException
+
+class RepecParser(Parser):
+
+#    def __init__(self, language_cache=None):
+#
+#        #super(Parser, self).__init__()
+#        #super(Parser, self).__init__()
+#        self._languages_cache = LanguagesCache() if language_cache is None else language_cache
+
+
+    _begin = 6
+    _parameters = {
+        b"ER":  {"type": "delimiter"},
+        b"T1":  {"type": "hyperdata", "key": "title", "separator": " "},
+        b"ST":  {"type": "hyperdata", "key": "subtitle", "separator": " "},
+        b"A1":  {"type": "hyperdata", "key": "authors", "separator": "\n"},
+        b"JO":  {"type": "hyperdata", "key": "journal"},
+        b"UR":  {"type": "hyperdata", "key": "doi"},
+        b"Y1":  {"type": "hyperdata", "key": "publication_year"},
+        b"PD":  {"type": "hyperdata", "key": "publication_month"},
+        b"N1":  {"type": "hyperdata", "key": "references", "separator": ", "},
+        b"LA":  {"type": "hyperdata", "key": "language_iso2"},
+        b"N2":  {"type": "hyperdata", "key": "abstract", "separator": " "},
+        b"WC":  {"type": "hyperdata", "key": "fields"},
+    }
+
+    def parse(self, file):
+
+        hyperdata = {}
+        last_key = None
+        last_values = []
+        # browse every line of the file
+        for line in file:
+            if len(line) > 2 :
+                # extract the parameter key
+                parameter_key = line[:2]
+                if parameter_key != b'  ' and parameter_key != last_key:
+                    if last_key in self._parameters:
+                        # translate the parameter key
+                        parameter = self._parameters[last_key]
+                        if parameter["type"] == "hyperdata":
+                            separator = parameter["separator"] if "separator" in parameter else ""
+                            if parameter["key"] == "publication_year":
+                                hyperdata[parameter["key"]] = separator.join(last_values)[:4]
+                            else:
+                                hyperdata[parameter["key"]] = separator.join(last_values)
+                        elif parameter["type"] == "delimiter":
+                            if 'language_fullname' not in hyperdata.keys():
+                                if 'language_iso3' not in hyperdata.keys():
+                                    if 'language_iso2' not in hyperdata.keys():
+                                        hyperdata['language_iso2'] = 'en'
+                            yield hyperdata
+                            hyperdata = {}
+                    last_key = parameter_key
+                    last_values = []
+                try:
+                    last_values.append(line[self._begin:-1].decode())
+                except Exception as error:
+                    print(error)
+        # if a hyperdata object is left in memory, yield it as well
+        if hyperdata:
+            yield hyperdata

gargantext/util/parsers/_Parser.py

@@ -67,19 +67,19 @@ class Parser:
                 date_string = hyperdata[prefix + "_year"]
                 key = prefix + "_month"
                 if key in hyperdata:
-                    date_string += " " + hyperdata[key]
+                    date_string += " " + hyperdata.get(key, "01")
                     key = prefix + "_day"
                     if key in hyperdata:
-                        date_string += " " + hyperdata[key]
+                        date_string += " " + hyperdata.get(key, "01")
                         key = prefix + "_hour"
                         if key in hyperdata:
-                            date_string += " " + hyperdata[key]
+                            date_string += " " + hyperdata.get(key, "01")
                             key = prefix + "_minute"
                             if key in hyperdata:
-                                date_string += ":" + hyperdata[key]
+                                date_string += ":" + hyperdata.get(key, "01")
                                 key = prefix + "_second"
                                 if key in hyperdata:
-                                    date_string += ":" + hyperdata[key]
+                                    date_string += ":" + hyperdata.get(key, "01")
                 try:
                     hyperdata[prefix + "_date"] = dateutil.parser.parse(date_string).strftime("%Y-%m-%d %H:%M:%S")
                 except Exception as error:
@@ -90,13 +90,13 @@ class Parser:
 
                     except Exception as error:
                         try:
-                            print(error)
+                            print("error line 93", error)
                             # FIXME Date format:  1994 SPR
                             # By default, we take the year only
                             hyperdata[prefix + "_date"] = date_parser.parse(str(date_string)[:4]).strftime("%Y-%m-%d %H:%M:%S")
 
                         except Exception as error:
-                            print(error)
+                            print("error line 99", error)
         else:
             print("WARNING: Date unknown at _Parser level, using now()")
             hyperdata['publication_date'] = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
@@ -113,7 +113,7 @@ class Parser:
             hyperdata[prefix + "_hour"]      = date.strftime("%H")
             hyperdata[prefix + "_minute"]    = date.strftime("%M")
             hyperdata[prefix + "_second"]    = date.strftime("%S")
-        print(hyperdata['publication_date'])
+        print("line 116", hyperdata['publication_date'])
         # finally, return the transformed result!
         return hyperdata
 

gargantext/util/parsers/__init__.py

 from .Ris       import RISParser
+from .Ris_repec import RepecParser
 from .Isi       import ISIParser
 # from .Jstor import JstorParser
 # from .Zotero import ZoteroParser