From cb09c35a07e3b9f8ca7e4eb5e8d37ffacdee6253 Mon Sep 17 00:00:00 2001
From: Daniel Blankenberg <dan.blankenberg@gmail.com>
Date: Wed, 13 Jan 2016 17:28:34 -0500
Subject: [PATCH] Fix line wrapping for peek of tabular files.

---
 lib/galaxy/datatypes/data.py    | 20 ++++++++++++++++----
 lib/galaxy/datatypes/tabular.py |  5 ++++-
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 945065c4371..f74227c47e5 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -742,13 +742,13 @@ class Text( Data ):
                 data_lines += 1
         return data_lines
 
-    def set_peek( self, dataset, line_count=None, is_multi_byte=False, WIDTH=256, skipchars=None ):
+    def set_peek( self, dataset, line_count=None, is_multi_byte=False, WIDTH=256, skipchars=None, line_wrap=True ):
         """
         Set the peek.  This method is used by various subclasses of Text.
         """
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
-            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte, WIDTH=WIDTH, skipchars=skipchars )
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte, WIDTH=WIDTH, skipchars=skipchars, line_wrap=line_wrap )
             if line_count is None:
                 # See if line_count is stored in the metadata
                 if dataset.metadata.data_lines:
@@ -950,7 +950,7 @@ def get_test_fname( fname ):
     return full_path
 
 
-def get_file_peek( file_name, is_multi_byte=False, WIDTH=256, LINE_COUNT=5, skipchars=None ):
+def get_file_peek( file_name, is_multi_byte=False, WIDTH=256, LINE_COUNT=5, skipchars=None, line_wrap=True ):
     """
     Returns the first LINE_COUNT lines wrapped to WIDTH
 
@@ -971,8 +971,9 @@ def get_file_peek( file_name, is_multi_byte=False, WIDTH=256, LINE_COUNT=5, skip
     file_type = None
     data_checked = False
     temp = open( file_name, "U" )
+    last_line = ''
     while count <= LINE_COUNT:
-        line = temp.readline( WIDTH )
+        line = last_line + temp.readline( WIDTH - len( last_line ) )
         if line and not is_multi_byte and not data_checked:
             # See if we have a compressed or binary file
             if line[0:2] == util.gzip_magic:
@@ -986,6 +987,17 @@ def get_file_peek( file_name, is_multi_byte=False, WIDTH=256, LINE_COUNT=5, skip
             data_checked = True
         if file_type in [ 'gzipped', 'binary' ]:
             break
+        if not line_wrap:
+            if '\n' in line:
+                i = line.index( '\n' )
+                last_line = line[i:]
+                line = line[:i]
+            else:
+                last_line = ''
+                while True:
+                    i = temp.read(1)
+                    if not i or i == '\n':
+                        break
         skip_line = False
         for skipchar in skipchars:
             if line.startswith( skipchar ):
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 3617ed5336a..6ce28bb45a9 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -39,7 +39,7 @@ class TabularData( data.Text ):
     MetadataElement( name="delimiter", default='\t', desc="Data delimiter", readonly=True, visible=False, optional=True, no_value=[] )
 
     def set_peek( self, dataset, line_count=None, is_multi_byte=False, WIDTH=256, skipchars=None ):
-        super(TabularData, self).set_peek( dataset, line_count=line_count, is_multi_byte=is_multi_byte, WIDTH=WIDTH, skipchars=skipchars)
+        super(TabularData, self).set_peek( dataset, line_count=line_count, is_multi_byte=is_multi_byte, WIDTH=WIDTH, skipchars=skipchars, line_wrap=False )
         if dataset.metadata.comment_lines:
             dataset.blurb = "%s, %s comments" % ( dataset.blurb, util.commaify( str( dataset.metadata.comment_lines ) ) )
 
@@ -179,6 +179,9 @@ class TabularData( data.Text ):
                     out.append( '<tr><td colspan="100%%">%s</td></tr>' % escape( line ) )
                 elif line:
                     elems = line.split( dataset.metadata.delimiter )
+                    # pad shortened elems, since lines could have been truncated by width
+                    if len( elems ) < columns:
+                        elems.extend( [''] * ( columns - len( elems ) ) )
                     # we may have an invalid comment line or invalid data
                     if len( elems ) != columns:
                         out.append( '<tr><td colspan="100%%">%s</td></tr>' % escape( line ) )