From 9882df54c3244173ba470b01d1300d403834237f Mon Sep 17 00:00:00 2001
From: Martijn Vermaat <martijn@vermaat.name>
Date: Wed, 22 Oct 2014 12:40:48 +0200
Subject: [PATCH] Fix importing transcript mappings from UCSC database
Fixes #9
---
CHANGES.rst | 2 ++
mutalyzer/mapping.py | 10 ++++------
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/CHANGES.rst b/CHANGES.rst
index d72b5425..e938eed4 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -17,6 +17,8 @@ Release date to be decided.
<https://git.lumc.nl/mutalyzer/mutalyzer/merge_requests/25>`_).
- Don't crash on mail errors in the batch scheduler (`GitLab#30
<https://git.lumc.nl/mutalyzer/mutalyzer/issues/30>`_).
+- Fix importing transcript mappings from UCSC database (`GitLab#9
+ <https://git.lumc.nl/mutalyzer/mutalyzer/issues/9>`_).
Version 2.0.3
diff --git a/mutalyzer/mapping.py b/mutalyzer/mapping.py
index 11e05899..ba4d1110 100644
--- a/mutalyzer/mapping.py
+++ b/mutalyzer/mapping.py
@@ -789,17 +789,15 @@ class Converter(object) :
#Converter
-# Todo: This seems broken at the moment.
-# Todo: Correct handling of string encodings.
def import_from_ucsc_by_gene(assembly, gene):
"""
Import transcript mappings for a gene from the UCSC.
-
- .. todo: Also report how much was added/updated.
"""
connection = MySQLdb.connect(user='genome',
host='genome-mysql.cse.ucsc.edu',
- db=assembly.alias)
+ db=assembly.alias,
+ charset='utf8',
+ use_unicode=True)
query = """
SELECT DISTINCT
@@ -811,7 +809,7 @@ def import_from_ucsc_by_gene(assembly, gene):
AND acc = mrnaAcc
AND name2 = %s
"""
- parameters = gene
+ parameters = gene,
cursor = connection.cursor()
cursor.execute(query, parameters)
--
GitLab