opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1500 from blankenberg/peek-fix

Browse Source 
[16.01] Fix line wrapping for peek of tabular files.
This commit is contained in:
John Chilton
2016-01-29 12:49:12 -05:00
parent 685fd1560e cb09c35a07
commit 81535c5778
2 changed files with 20 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/galaxy/datatypes/data.py
+16 -4
View File
@@ -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 ):
lib/galaxy/datatypes/tabular.py
+4 -1
View File
@@ -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 ) ) )
@@ -180,6 +180,9 @@ 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 ) )