Add function to read the file and do basic data processing.

1 files changed, 24 insertions, 0 deletions

diff --git a/scripts/phenotypes_bulk_edit.py b/scripts/phenotypes_bulk_edit.py
index 67bf65a..cc58b02 100644
--- a/scripts/phenotypes_bulk_edit.py
+++ b/scripts/phenotypes_bulk_edit.py
@@ -3,6 +3,7 @@ import uuid
 import logging
 import argparse
 from pathlib import Path
+from typing import Iterator
 
 from gn_libs import jobs, mysqldb, sqlite3
 
@@ -68,6 +69,29 @@ def parse_args():
     return parser.parse_args()
 
 
+def read_file(filepath: Path) -> Iterator[str]:
+    """Read the file, one line at a time."""
+    with filepath.open(mode="r", encoding="utf-8") as infile:
+        count = 0
+        headers = None
+        for line in infile:
+            if line.startswith("#"): # ignore comments
+                continue;
+
+            fields = line.strip().split("\t")
+            if count == 0:
+                headers = fields
+                count = count + 1
+                continue
+
+            _dict = dict(zip(headers, fields))
+            _pheno, _xref = _dict.pop("UniqueIdentifier").split("::")
+            _dict["phenotype_id"] = _pheno.split(":")[1]
+            _dict["xref_id"] = _xref.split(":")[1]
+            yield _dict
+            count = count + 1
+
+
 def run(conn, job):
     """Process the data and update it."""
     check_ids()