msantos/CCG_mirri_utils
1
0
Fork 0
forked from MIRRI/mirri_utils
Code Pull Requests Activity

update mirri folder

Browse Source
This commit is contained in:
denisaborgesccg
2023-07-24 12:10:38 +01:00
parent f93ba27f81
commit 7338930c72
11 changed files with 830 additions and 362 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mirri/io/parsers/mirri_excel.py
+19 -10
View File
@@ -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']: