update mirri folder

mirri/io/parsers/mirri_excel.py

@@ -37,14 +37,14 @@ TRUEFALSE_TRANSLATOR = {
 }
 
 
-def parse_mirri_excel(fhand, version="20200601"):
-    if version == "20200601":
-        return _parse_mirri_v20200601(fhand)
+def parse_mirri_excel(fhand, version=""):
+    if version == "5.1.2":
+        return _parse_mirri_v12052023(fhand)            
     else:
-        raise NotImplementedError("Only version 20200601 is implemented")
+        raise NotImplementedError("Only version is 5.1.2 implemented")
 
 
-def _parse_mirri_v20200601(fhand):
+def _parse_mirri_v12052023(fhand):
     fhand.seek(0)
     file_content = BytesIO(fhand.read())
     wb = load_workbook(filename=file_content, read_only=True, data_only=True)
@@ -64,7 +64,6 @@ def _parse_mirri_v20200601(fhand):
 
     return {"strains": strains, "growth_media": growth_media}
 
-
 def index_list_by(list_, id_):
     return {str(item[id_]): item for item in list_}
 
@@ -125,7 +124,7 @@ def parse_strains(wb, locations, growth_media, markers, publications,
     publications = index_list_by_attr(publications, 'id')
     markers = index_markers(markers)
 
-    for strain_row in workbook_sheet_reader(wb, STRAINS, "Accession number"):
+    for strain_row in workbook_sheet_reader(wb, STRAINS, "accessionNumber"):
         strain = StrainMirri()
         strain_id = None
         label = None
@@ -140,7 +139,7 @@ def parse_strains(wb, locations, growth_media, markers, publications,
                 collection, number = value.split(" ", 1)
                 value = StrainId(collection=collection, number=number)
                 rsetattr(strain, attribute, value)
-
+                
             elif attribute == "restriction_on_use":
                 rsetattr(strain, attribute, RESTRICTION_USE_TRANSLATOR[value])
             elif attribute == "nagoya_protocol":
@@ -202,9 +201,19 @@ def parse_strains(wb, locations, growth_media, markers, publications,
                 items = value.split(";")
                 strain.collect.location.latitude = float(items[0])
                 strain.collect.location.longitude = float(items[1])
+                strain.collect.location.precision = float(items[2])
+                strain.collect.location.altitude = float(items[3])
+                if len(items) > 4:
+                    strain.collect.location.coord_uncertainty = items[4]
+                    
+            elif attribute == "collect.site.links":
+                items = value.split(";")
+                strain.collect.site.links.nameSite = str(items[0])
+                strain.collect.site.links.urlSite = str(items[1])
+                rsetattr(strain, attribute, value.split(";")) #ver o separador
                 if len(items) > 2:
-                    strain.collect.location.coord_uncertainty = items[2]
-
+                    strain.collect.site.links.site_uncertainty = items[2]
+                        
             elif attribute == "collect.location":
                 location = locations[value]
                 if 'Country' in location and location['Country']:

mirri/io/writers/mirri_excel.py

@@ -50,11 +50,10 @@ PUB_HEADERS = [pb["label"] for pb in PUBLICATION_FIELDS]
 
 
 def write_mirri_excel(path, strains, growth_media, version):
-    if version == "20200601":
-        _write_mirri_excel_20200601(path, strains, growth_media)
+    if version == "5.1.2":
+        _write_mirri_excel_12052023(path, strains, growth_media)
 
-
-def _write_mirri_excel_20200601(path, strains, growth_media):
+def _write_mirri_excel_12052023(path, strains, growth_media):
     wb = Workbook()
 
     write_markers_sheet(wb)
@@ -104,7 +103,7 @@ def _write_mirri_excel_20200601(path, strains, growth_media):
     redimension_cell_width(pub_sheet)
 
     # write sexual states
-    sex_sheet = wb.create_sheet("Sexual states")
+    sex_sheet = wb.create_sheet("Sexual state")
     for sex_state in sorted(list(sexual_states)):
         sex_sheet.append([sex_state])
     redimension_cell_width(sex_sheet)
@@ -121,7 +120,6 @@ def _write_mirri_excel_20200601(path, strains, growth_media):
     del wb["Sheet"]
     wb.save(str(path))
 
-
 def _deserialize_strains(strains, locations, growth_media_indexes,
                          publications, sexual_states, genomic_markers):
     for strain in strains:
@@ -189,10 +187,21 @@ def _deserialize_strains(strains, locations, growth_media_indexes,
             elif attribute == "collect.location.coords":
                 lat = strain.collect.location.latitude
                 long = strain.collect.location.longitude
-                if lat is not None and long is not None:
-                    value = f"{lat};{long}"
+                alt = strain.collect.location.altitude 
+                prec = strain.collect.location.precision
+                if lat is not None and long is not None and prec is not None and alt is not None:
+                    value = f"{lat};{long};{prec};{alt}"
                 else:
-                    value = None
+                    value = None     
+            elif attribute == "collect.site.links":
+                name = strain.collect.site.links.nameSite
+                url = strain.collect.site.links.urlSite
+                value = rgetattr(strain, attribute)
+                value = ";".join(value)
+                if name is not None and url is not None:
+                    value = f"{name};{url}"
+                else:
+                    value = None        
 
             elif attribute == "collect.location":
                 location = strain.collect.location