18-07

io/parsers/mirri_excel.py

@@ -19,12 +19,6 @@ from mirri.settings import (COMMERCIAL_USE_WITH_AGREEMENT, GENOMIC_INFO,
                             NAGOYA_PROBABLY_SCOPE, NO_RESTRICTION,
                             ONLY_RESEARCH, ONTOBIOTOPE,
                             PUBLICATION_FIELDS, STRAINS, SUBTAXAS)
-from mirri.settings_v1 import (COMMERCIAL_USE_WITH_AGREEMENT, GENOMIC_INFO,
-                            GROWTH_MEDIA, LITERATURE_SHEET, LOCATIONS,
-                            MIRRI_FIELDS, NAGOYA_DOCS_AVAILABLE, NAGOYA_NO_RESTRICTIONS,
-                            NAGOYA_PROBABLY_SCOPE, NO_RESTRICTION,
-                            ONLY_RESEARCH, ONTOBIOTOPE,
-                            PUBLICATION_FIELDS, STRAINS, SUBTAXAS)
 from mirri.utils import get_country_from_name
 
 RESTRICTION_USE_TRANSLATOR = {
@@ -44,34 +38,12 @@ TRUEFALSE_TRANSLATOR = {
 
 
 def parse_mirri_excel(fhand, version=""):
-    if version == "20200602":
-        return _parse_mirri_v20200601(fhand)
-    elif version == "12052023":
+    if version == "5.1.2":
         return _parse_mirri_v12052023(fhand)            
     else:
-        raise NotImplementedError("Only versions 20200601 and 12052023 are implemented")
+        raise NotImplementedError("Only version is 5.1.2 implemented")
 
 
-def _parse_mirri_v20200601(fhand):
-    fhand.seek(0)
-    file_content = BytesIO(fhand.read())
-    wb = load_workbook(filename=file_content, read_only=True, data_only=True)
-
-    locations = workbook_sheet_reader(wb, LOCATIONS)
-    ontobiotopes = workbook_sheet_reader(wb, ONTOBIOTOPE)
-
-    growth_media = list(parse_growth_media(wb))
-
-    markers = workbook_sheet_reader(wb, GENOMIC_INFO)
-
-    publications = list(parse_publications(wb))
-
-    strains = parse_strains(wb, locations=locations,  growth_media=growth_media,
-                            markers=markers, publications=publications,
-                            ontobiotopes=ontobiotopes)
-
-    return {"strains": strains, "growth_media": growth_media}
-
 def _parse_mirri_v12052023(fhand):
     fhand.seek(0)
     file_content = BytesIO(fhand.read())

io/writers/mirri_excel.py

@@ -5,7 +5,6 @@ from openpyxl.workbook.workbook import Workbook
 
 from mirri import rgetattr
 from mirri.settings import GROWTH_MEDIA, MIRRI_FIELDS, DATA_DIR, PUBLICATION_FIELDS
-from mirri.settings_v1 import GROWTH_MEDIA, MIRRI_FIELDS, DATA_DIR, PUBLICATION_FIELDS
 from mirri.io.parsers.mirri_excel import NAGOYA_TRANSLATOR, RESTRICTION_USE_TRANSLATOR
 
 INITIAL_SEXUAL_STATES = [
@@ -51,81 +50,9 @@ 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 == "12052023":
+    if version == "5.1.2":
         _write_mirri_excel_12052023(path, strains, growth_media)
 
-    
-def _write_mirri_excel_20200601(path, strains, growth_media):
-    wb = Workbook()
-
-    write_markers_sheet(wb)
-
-    ontobiotope_path = DATA_DIR / "ontobiotopes.csv"
-    write_ontobiotopes(wb, ontobiotope_path)
-
-    write_growth_media(wb, growth_media)
-    growth_media_indexes = [str(gm.acronym) for gm in growth_media]
-
-    locations = {}
-    publications = {}
-    sexual_states = set(deepcopy(INITIAL_SEXUAL_STATES))
-    genomic_markers = {}
-    strains_data = _deserialize_strains(strains, locations, growth_media_indexes,
-                                        publications, sexual_states, genomic_markers)
-    strains_data = list(strains_data)
-
-    # write strain to generate indexed data
-    strain_sheet = wb.create_sheet("Strains")
-    strain_sheet.append([field["label"] for field in MIRRI_FIELDS])
-    for strain_row in strains_data:
-        strain_sheet.append(strain_row)
-    redimension_cell_width(strain_sheet)
-
-    # write locations
-    loc_sheet = wb.create_sheet("Geographic origin")
-    loc_sheet.append(["ID", "Country", "Region", "City", "Locality"])
-    for index, loc_index in enumerate(locations.keys()):
-        location = locations[loc_index]
-        row = [index, location.country, location.state, location.municipality,
-               loc_index]
-        loc_sheet.append(row)
-    redimension_cell_width(loc_sheet)
-
-    # write publications
-    pub_sheet = wb.create_sheet("Literature")
-    pub_sheet.append(PUB_HEADERS)
-    for publication in publications.values():
-        row = []
-        for pub_field in PUBLICATION_FIELDS:
-            # if pub_field['attribute'] == 'id':
-            #     value = index
-            value = getattr(publication, pub_field['attribute'], None)
-            row.append(value)
-        pub_sheet.append(row)
-    redimension_cell_width(pub_sheet)
-
-    # write 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)
-
-    # write genetic markers
-    markers_sheet = wb.create_sheet("Genomic information")
-    markers_sheet.append(['Strain AN', 'Marker', 'INSDC AN', 'Sequence'])
-    for strain_id, markers in genomic_markers.items():
-        for marker in markers:
-            row = [strain_id, marker.marker_type, marker.marker_id, marker.marker_seq]
-            markers_sheet.append(row)
-    redimension_cell_width(markers_sheet)
-
-    del wb["Sheet"]
-    wb.save(str(path))
-
-
 def _write_mirri_excel_12052023(path, strains, growth_media):
     wb = Workbook()