[galaxy-dev] [hg] galaxy 1708: Change History.copy() back to use datasets rat...

15 Jan 2009

details:   http://www.bx.psu.edu/hg/galaxy/rev/78c2f403cb43
changeset: 1708:78c2f403cb43
user:      Greg Von Kuster <greg@bx.psu.edu>
date:      Thu Jan 15 10:49:01 2009 -0500
description:
Change History.copy() back to use datasets rather than active_datasets.  Add checks in set_peek() to properly set peek on purged datasets.  Fixes sharing a history that contains purged datasets.

9 file(s) affected in this change:

lib/galaxy/datatypes/data.py
lib/galaxy/datatypes/genetics.py
lib/galaxy/datatypes/images.py
lib/galaxy/datatypes/interval.py
lib/galaxy/datatypes/qualityscore.py
lib/galaxy/datatypes/sequence.py
lib/galaxy/datatypes/xml.py
lib/galaxy/model/__init__.py
tools/data_source/echo.xml

diffs (441 lines):

diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/data.py

--- a/lib/galaxy/datatypes/data.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/data.py	Thu Jan 15 10:49:01 2009 -0500
@@ -103,8 +103,12 @@
         return False
     def set_peek( self, dataset ):
         """Set the peek and blurb text"""
-        dataset.peek  = ''
-        dataset.blurb = 'data'
+        if not dataset.dataset.purged:
+            dataset.peek = ''
+            dataset.blurb = 'data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         """Create HTML table, used for displaying peek"""
         out = ['<table cellspacing="0" cellpadding="3">']
@@ -275,19 +279,27 @@
         return 'text/plain'
    
     def set_peek( self, dataset, line_count=None ):
-        dataset.peek  = get_file_peek( dataset.file_name )
-        if line_count is None:
-            dataset.blurb = "%s lines" % util.commaify( str( get_line_count( dataset.file_name ) ) )
+        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 )
+            if line_count is None:
+                dataset.blurb = "%s lines" % util.commaify( str( get_line_count( dataset.file_name ) ) )
+            else:
+                dataset.blurb = "%s lines" % util.commaify( str( line_count ) )
         else:
-            dataset.blurb = "%s lines" % util.commaify( str( line_count ) )
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
 class Binary( Data ):
     """Binary data"""
-
     def set_peek( self, dataset ):
         """Set the peek and blurb text"""
-        dataset.peek  = 'binary data'
-        dataset.blurb = 'data'
+        if not dataset.dataset.purged:
+            dataset.peek = 'binary data'
+            dataset.blurb = 'data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
 def get_test_fname( fname ):
     """Returns test data filename"""
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/genetics.py
--- a/lib/galaxy/datatypes/genetics.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/genetics.py	Thu Jan 15 10:49:01 2009 -0500
@@ -43,11 +43,14 @@
     
     def set_peek( self, dataset ):
         """Set the peek and blurb text"""
-        dataset.peek  = data.get_file_peek( dataset.file_name )
-        ## dataset.peek  = self.make_html_table( dataset.peek )
-        dataset.blurb = util.commaify( str( data.get_line_count( dataset.file_name ) ) ) + " rows"
-        #i don't think set_meta should not be called here, it should be called separately
-        self.set_meta( dataset )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            dataset.blurb = util.commaify( str( data.get_line_count( dataset.file_name ) ) ) + " rows"
+            #i don't think set_meta should not be called here, it should be called separately
+            self.set_meta( dataset )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
         
     def get_estimated_display_viewport( self, dataset ):
         """Return a chrom, start, stop tuple for viewing a file."""
@@ -130,8 +133,12 @@
     file_ext="snpmatrix"
 
     def set_peek( self, dataset ):
-        dataset.peek  = "Binary RGenetics file"
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek  = "Binary RGenetics file"
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def sniff( self, filename ):
         """
         """
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/images.py
--- a/lib/galaxy/datatypes/images.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/images.py	Thu Jan 15 10:49:01 2009 -0500
@@ -14,9 +14,13 @@
     """Class describing an ab1 binary sequence file"""
     file_ext = "ab1"
     def set_peek( self, dataset ):
-        export_url = "/history_add_to?"+urlencode({'history_id':dataset.history_id,'ext':'ab1','name':'ab1 sequence','info':'Sequence file','dbkey':dataset.dbkey})
-        dataset.peek  = "Binary ab1 sequence file"
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            export_url = "/history_add_to?" + urlencode({'history_id':dataset.history_id,'ext':'ab1','name':'ab1 sequence','info':'Sequence file','dbkey':dataset.dbkey})
+            dataset.peek  = "Binary ab1 sequence file"
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
@@ -27,9 +31,13 @@
     """Class describing an scf binary sequence file"""
     file_ext = "scf"
     def set_peek( self, dataset ):
-        export_url = "/history_add_to?"+urlencode({'history_id':dataset.history_id,'ext':'scf','name':'scf sequence','info':'Sequence file','dbkey':dataset.dbkey})
-        dataset.peek  = "Binary scf sequence file" 
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            export_url = "/history_add_to?" + urlencode({'history_id':dataset.history_id,'ext':'scf','name':'scf sequence','info':'Sequence file','dbkey':dataset.dbkey})
+            dataset.peek  = "Binary scf sequence file" 
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
@@ -40,10 +48,14 @@
     """Class describing a zip archive of binary sequence files"""
     file_ext = "binseq.zip"
     def set_peek( self, dataset ):
-        zip_file = zipfile.ZipFile( dataset.file_name, "r" )
-        num_files = len( zip_file.namelist() )
-        dataset.peek  = "Archive of %s binary sequence files" % ( str( num_files ) )
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            zip_file = zipfile.ZipFile( dataset.file_name, "r" )
+            num_files = len( zip_file.namelist() )
+            dataset.peek  = "Archive of %s binary sequence files" % ( str( num_files ) )
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
@@ -57,10 +69,14 @@
     """Class describing a zip archive of text sequence files"""
     file_ext = "txtseq.zip"
     def set_peek( self, dataset ):
-        zip_file = zipfile.ZipFile( dataset.file_name, "r" )
-        num_files = len( zip_file.namelist() )
-        dataset.peek  = "Archive of %s text sequence files" % ( str( num_files ) )
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            zip_file = zipfile.ZipFile( dataset.file_name, "r" )
+            num_files = len( zip_file.namelist() )
+            dataset.peek  = "Archive of %s text sequence files" % ( str( num_files ) )
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
@@ -73,8 +89,12 @@
 class Image( data.Data ):
     """Class describing an image"""
     def set_peek( self, dataset ):
-        dataset.peek  = 'Image in %s format' % dataset.extension
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = 'Image in %s format' % dataset.extension
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
 def create_applet_tag_peek( class_name, archive, params ):
     text = """
@@ -104,18 +124,22 @@
     """Class describing a GMAJ Applet"""
     file_ext = "gmaj.zip"
     def set_peek( self, dataset ):
-        params = {
-        "bundle":"display?id=%s&tofile=yes&toext=.zip" % dataset.id,
-        "buttonlabel": "Launch GMAJ",
-        "nobutton": "false",
-        "urlpause" :"100",
-        "debug": "false",
-        "posturl": "history_add_to?%s" % urlencode( { 'history_id': dataset.history_id, 'ext': 'maf', 'name': 'GMAJ Output on data %s' % dataset.hid, 'info': 'Added by GMAJ', 'dbkey': dataset.dbkey } )
-        }
-        class_name = "edu.psu.bx.gmaj.MajApplet.class"
-        archive = "/static/gmaj/gmaj.jar"
-        dataset.peek = create_applet_tag_peek( class_name, archive, params )
-        dataset.blurb = 'GMAJ Multiple Alignment Viewer'
+        if not dataset.dataset.purged:
+            params = {
+            "bundle":"display?id=%s&tofile=yes&toext=.zip" % dataset.id,
+            "buttonlabel": "Launch GMAJ",
+            "nobutton": "false",
+            "urlpause" :"100",
+            "debug": "false",
+            "posturl": "history_add_to?%s" % urlencode( { 'history_id': dataset.history_id, 'ext': 'maf', 'name': 'GMAJ Output on data %s' % dataset.hid, 'info': 'Added by GMAJ', 'dbkey': dataset.dbkey } )
+            }
+            class_name = "edu.psu.bx.gmaj.MajApplet.class"
+            archive = "/static/gmaj/gmaj.jar"
+            dataset.peek = create_applet_tag_peek( class_name, archive, params )
+            dataset.blurb = 'GMAJ Multiple Alignment Viewer'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
@@ -147,8 +171,12 @@
     """Class describing an html file"""
     file_ext = "html"
     def set_peek( self, dataset ):
-        dataset.peek  = "HTML file"
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = "HTML file"
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def get_mime(self):
         """Returns the mime type of the datatype"""
         return 'text/html'
@@ -176,17 +204,21 @@
     """Class describing a LAJ Applet"""
     file_ext = "laj"
     def set_peek( self, dataset ):
-        params = {
-        "alignfile1": "display?id=%s" % dataset.id,
-        "buttonlabel": "Launch LAJ",
-        "title": "LAJ in Galaxy",
-        "posturl": "history_add_to?%s" % urlencode( { 'history_id': dataset.history_id, 'ext': 'lav', 'name': 'LAJ Output', 'info': 'Added by LAJ', 'dbkey': dataset.dbkey } ),
-        "noseq": "true"
-        }
-        class_name = "edu.psu.cse.bio.laj.LajApplet.class"
-        archive = "/static/laj/laj.jar"
-        dataset.peek = create_applet_tag_peek( class_name, archive, params )
-        dataset.blurb = 'LAJ Multiple Alignment Viewer'
+        if not dataset.dataset.purged:
+            params = {
+            "alignfile1": "display?id=%s" % dataset.id,
+            "buttonlabel": "Launch LAJ",
+            "title": "LAJ in Galaxy",
+            "posturl": "history_add_to?%s" % urlencode( { 'history_id': dataset.history_id, 'ext': 'lav', 'name': 'LAJ Output', 'info': 'Added by LAJ', 'dbkey': dataset.dbkey } ),
+            "noseq": "true"
+            }
+            class_name = "edu.psu.cse.bio.laj.LajApplet.class"
+            archive = "/static/laj/laj.jar"
+            dataset.peek = create_applet_tag_peek( class_name, archive, params )
+            dataset.blurb = 'LAJ Multiple Alignment Viewer'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def display_peek(self, dataset):
         try:
             return dataset.peek
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/interval.py
--- a/lib/galaxy/datatypes/interval.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/interval.py	Thu Jan 15 10:49:01 2009 -0500
@@ -59,11 +59,15 @@
     
     def set_peek( self, dataset, line_count=None ):
         """Set the peek and blurb text"""
-        dataset.peek  = data.get_file_peek( dataset.file_name )
-        if line_count is None:
-            dataset.blurb = "%s regions" % util.commaify( str( data.get_line_count( dataset.file_name ) ) )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            if line_count is None:
+                dataset.blurb = "%s regions" % util.commaify( str( data.get_line_count( dataset.file_name ) ) )
+            else:
+                dataset.blurb = "%s regions" % util.commaify( str( line_count ) )
         else:
-            dataset.blurb = "%s regions" % util.commaify( str( line_count ) )
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     
     def set_meta( self, dataset, overwrite = True, first_line_is_header = False, **kwd ):
         Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 0 )
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/qualityscore.py
--- a/lib/galaxy/datatypes/qualityscore.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/qualityscore.py	Thu Jan 15 10:49:01 2009 -0500
@@ -16,11 +16,15 @@
     file_ext = "qual"
     
     def set_peek( self, dataset, line_count=None ):
-        dataset.peek  = data.get_file_peek( dataset.file_name )
-        if line_count is None:
-            dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            if line_count is None:
+                dataset.blurb = data.nice_size( dataset.get_size() )
+            else:
+                dataset.blurb = "%s lines, Quality score file" % util.commaify( str( line_count ) )
         else:
-            dataset.blurb = "%s lines, Quality score file" % util.commaify( str( line_count ) )
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     
     def display_peek(self, dataset):
         try:
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/sequence.py
--- a/lib/galaxy/datatypes/sequence.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/sequence.py	Thu Jan 15 10:49:01 2009 -0500
@@ -31,8 +31,12 @@
     file_ext = "fasta"
 
     def set_peek( self, dataset ):
-        dataset.peek = data.get_file_peek( dataset.file_name )
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
     def sniff( self, filename ):
         """
@@ -86,8 +90,12 @@
     file_ext = "csfasta"
     
     def set_peek( self, dataset ):
-        dataset.peek = data.get_file_peek( dataset.file_name )
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
     def sniff( self, filename ):
         """
@@ -108,8 +116,12 @@
     file_ext = "fastqsolexa"
 
     def set_peek( self, dataset ):
-        dataset.peek = data.get_file_peek( dataset.file_name )
-        dataset.blurb = data.nice_size( dataset.get_size() )
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
 
     def sniff( self, filename ):
         """
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/datatypes/xml.py
--- a/lib/galaxy/datatypes/xml.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/datatypes/xml.py	Thu Jan 15 10:49:01 2009 -0500
@@ -12,8 +12,12 @@
     file_ext = "blastxml"
     def set_peek( self, dataset ):
         """Set the peek and blurb text"""
-        dataset.peek  = data.get_file_peek( dataset.file_name )
-        dataset.blurb = 'NCBI Blast XML data'
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name )
+            dataset.blurb = 'NCBI Blast XML data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
     def sniff( self, filename ):
         """
         Determines whether the file is blastxml
diff -r 4cf0aa26070f -r 78c2f403cb43 lib/galaxy/model/__init__.py
--- a/lib/galaxy/model/__init__.py	Thu Jan 15 10:42:22 2009 -0500
+++ b/lib/galaxy/model/__init__.py	Thu Jan 15 10:49:01 2009 -0500
@@ -287,14 +287,26 @@
         return self.datatype.find_conversion_destination( self, accepted_formats, datatypes_registry, **kwd )
     
     def copy( self, copy_children = False, parent_id = None ):
-        des = HistoryDatasetAssociation( hid=self.hid, name=self.name, info=self.info, blurb=self.blurb, peek=self.peek, extension=self.extension, dbkey=self.dbkey, dataset = self.dataset, visible=self.visible, deleted=self.deleted, parent_id=parent_id, copied_from_history_dataset_association = self )
+        des = HistoryDatasetAssociation( hid=self.hid,
+                                         name=self.name,
+                                         info=self.info,
+                                         blurb=self.blurb,
+                                         peek=self.peek,
+                                         extension=self.extension,
+                                         dbkey=self.dbkey,
+                                         dataset=self.dataset,
+                                         visible=self.visible,
+                                         deleted=self.deleted,
+                                         parent_id=parent_id,
+                                         copied_from_history_dataset_association=self )
         des.flush()
         des.set_size()
         des.metadata = self.metadata #need to set after flushed, as MetadataFiles require dataset.id
         if copy_children:
             for child in self.children:
                 child_copy = child.copy( copy_children = copy_children, parent_id = des.id )
-        des.set_peek() #in some instances peek relies on dataset_id, i.e. gmaj.zip for viewing MAFs
+        # In some instances peek relies on dataset_id ( e.g., gmaj.zip for viewing MAFs )
+        des.set_peek()
         des.flush()
         return des
 
@@ -376,7 +388,7 @@
         des.flush()
         des.name = self.name
         des.user_id = self.user_id
-        for data in self.active_datasets:
+        for data in self.datasets:
             new_data = data.copy( copy_children = True )
             des.add_dataset( new_data )
             new_data.flush()
diff -r 4cf0aa26070f -r 78c2f403cb43 tools/data_source/echo.xml
--- a/tools/data_source/echo.xml	Thu Jan 15 10:42:22 2009 -0500
+++ b/tools/data_source/echo.xml	Thu Jan 15 10:49:01 2009 -0500
@@ -6,14 +6,18 @@
 		echoes parameters  
 	</description>
 	
-	<command interpreter="python">echo.py $input $output </command>
+	<command interpreter="python">echo.py $input $database $output </command>
 
 	<inputs>
 		<param format="tabular" name="input" type="data" label="Input stuff"/>
+        <param type="select" name="database" label="Database">
+            <option value="alignseq.loc">Human (hg18)</option>
+            <option value="faseq.loc">Fly (dm3)</option>
+        </param>
 	</inputs>
 
 	<outputs>
-		<data format="input" name="output" />
+		<data format="input" name="output" label="Blat on ${database.value_label}" />
 	</outputs>
 
 </tool>

    