From a86633121cd92e37b2353f4bba8f2c37fa970d05 Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Fri, 1 Jan 2021 12:27:00 +0000
Subject: genbank-fetch-ids.py

---
 workflows/pull-data/genbank/README.md |  2 +-
 workflows/pull-data/genbank/utils.py  | 62 +++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+), 1 deletion(-)
 create mode 100644 workflows/pull-data/genbank/utils.py

diff --git a/workflows/pull-data/genbank/README.md b/workflows/pull-data/genbank/README.md
index f442b5d..d7c294b 100644
--- a/workflows/pull-data/genbank/README.md
+++ b/workflows/pull-data/genbank/README.md
@@ -4,7 +4,7 @@
 # --- get list of IDs already in PubSeq
 sparql-fetch-ids > pubseq_ids.txt
 # --- get list of missing genbank IDs
-genbank-fetch-ids --skip pubseq_ids.txt > genbank_ids.txt
+genbank-fetch-ids.py --skip pubseq_ids.txt > genbank_ids.txt
 # --- fetch XML
 update-from-genbank.py --ids genbank_ids.txt --outdir ~/tmp/genbank
 # --- Transform to YAML and FASTA
diff --git a/workflows/pull-data/genbank/utils.py b/workflows/pull-data/genbank/utils.py
new file mode 100644
index 0000000..3efc67a
--- /dev/null
+++ b/workflows/pull-data/genbank/utils.py
@@ -0,0 +1,62 @@
+import os
+
+def is_integer(string_to_check):
+    try:
+        int(string_to_check)
+        return True
+    except ValueError:
+        return False
+
+def chunks(lst, n):
+    for i in range(0, len(lst), n):
+        yield lst[i:i + n]
+
+def check_and_get_ontology_dictionaries(dir_ontology_dictionaries):
+    # Check duplicated entry looking at all dictionaries
+    field_to_term_to_uri_dict = {}
+
+    path_dict_xxx_csv_list = [os.path.join(dir_ontology_dictionaries, name_xxx_csv) for name_xxx_csv in
+                              os.listdir(dir_ontology_dictionaries) if name_xxx_csv.endswith('.csv')]
+
+    for path_dict_xxx_csv in path_dict_xxx_csv_list:
+        print('Read {}'.format(path_dict_xxx_csv))
+
+        with open(path_dict_xxx_csv) as f:
+            for line in f:
+                if len(line.split(',')) > 2:
+                    term, uri = line.strip('\n').split('",')
+                else:
+                    term, uri = line.strip('\n').split(',')
+
+                term = term.strip('"')
+
+                if term in field_to_term_to_uri_dict:
+                    print('Warning: in the dictionaries there are more entries for the same term ({}).'.format(term))
+                    continue
+
+                field_to_term_to_uri_dict[term] = uri
+
+    # Prepare separated dictionaries (to avoid, for example, that a valid IRI for species is accepted as specimen)
+    field_to_term_to_uri_dict = {}
+
+    for path_dict_xxx_csv in path_dict_xxx_csv_list:
+        field = os.path.basename(path_dict_xxx_csv).split('.')[0]
+
+        field_to_term_to_uri_dict[field] = {}
+
+        with open(path_dict_xxx_csv) as f:
+            for line in f:
+                if len(line.split(',')) > 2:
+                    term, uri = line.strip('\n').split('",')
+                else:
+                    term, uri = line.strip('\n').split(',')
+
+                term = term.strip('"')
+
+                if term in field_to_term_to_uri_dict[field]:
+                    print('Warning: in the {} dictionary there are more entries for the same term ({}).'.format(field, term))
+                    continue
+
+                field_to_term_to_uri_dict[field][term] = uri
+
+    return field_to_term_to_uri_dict
\ No newline at end of file
-- 
cgit v1.2.3