From 3ce9f8635870cc7e3853271acf49ff9315a19508 Mon Sep 17 00:00:00 2001 From: Greg Von Kuster Date: Wed, 11 Jul 2007 18:03:39 +0000 Subject: [PATCH] Fixed a weakness in sniff where all whitespace on lines were stripped, in some cases eliminating desired blank columns. --- lib/galaxy/datatypes/sniff.py | 7 +++++-- lib/galaxy/datatypes/test/test_ensembl.tab | 8 ++++++++ 2 files changed, 13 insertions(+), 2 deletions(-) create mode 100644 lib/galaxy/datatypes/test/test_ensembl.tab diff --git a/lib/galaxy/datatypes/sniff.py b/lib/galaxy/datatypes/sniff.py index 5b64f66c3fe..13fb6be8303 100644 --- a/lib/galaxy/datatypes/sniff.py +++ b/lib/galaxy/datatypes/sniff.py @@ -81,7 +81,7 @@ def get_headers(fname, sep, count=30): """ headers = [] for idx, line in enumerate(file(fname)): - line = line.strip() + line = line.rstrip('\n\r') if idx == count: break headers.append( line.split(sep) ) @@ -105,8 +105,11 @@ def is_column_based(fname, sep='\t'): False >>> is_column_based(fname, sep=' ') True + >>> fname = get_test_fname('test_ensembl.tab') + >>> is_column_based(fname) + True """ - headers = get_headers(fname, sep=sep) + headers = get_headers(fname, sep=sep) if not headers: return False diff --git a/lib/galaxy/datatypes/test/test_ensembl.tab b/lib/galaxy/datatypes/test/test_ensembl.tab new file mode 100644 index 00000000000..3fe4f8032b7 --- /dev/null +++ b/lib/galaxy/datatypes/test/test_ensembl.tab @@ -0,0 +1,8 @@ +Ensembl Gene ID Ensembl Transcript ID Chicken Ensembl Gene ID Orthology Type +ENSOANG00000013952 ENSOANT00000021996 ENSGALG00000012404 ortholog_one2one +ENSOANG00000013954 ENSOANT00000021998 ENSGALG00000012401 ortholog_one2one +ENSOANG00000013954 ENSOANT00000021999 ENSGALG00000012401 ortholog_one2one +ENSOANG00000013954 ENSOANT00000022000 ENSGALG00000012401 ortholog_one2one +ENSOANG00000013955 ENSOANT00000022001 +ENSOANG00000013955 ENSOANT00000022002 +ENSOANG00000013956 ENSOANT00000022005 ENSGALG00000012400