- galaxy-dev - lists.galaxyproject.org

Major updates to Galaxy feature set
by Nate Coraor 15 Apr '09

15 Apr '09

Hi, We've recently been maintaining two separate branches of the Galaxy code base, since significant new features were in progress. Some of you may have already seen these features, namely, dataset security and libraries. All of these changes have now been incorporated in to our main branch. We spared you the 589 change emails that would've been sent, so if you are interested in everything that's changed, see the source at: http://www.bx.psu.edu/hg/galaxy/ Please note that if you update your local instance of Galaxy, significant database changes are required. We've added support for the SQLAlchemy Migrate extension so database upgrades should now be relatively painless, but please back up your database before upgrading. As always, any problems can be discussed here or reported to galaxy-bugs(a)bx.psu.edu. Thanks, --nate

1 0

Tools with multiple output files in galaxy
by svalbard colaco 13 Apr '09

13 Apr '09

Hi all, I had a tool integrated in galaxy storing multiple output files in a folder, Any pointers on how to display these multiple output files in the history panel ? Have got to know how to display for tools giving single onput files as shown in the tutorial. Have also come across some parameter in one of the forum on $outputfiles.files_path , will that help me ? Any pointers in this regard will be of great help. Thanking you'll Regards, sv.

1 0

[hg] galaxy 1746: Re-fix the default test port...
by Greg Von Kuster 09 Apr '09

09 Apr '09

details: http://www.bx.psu.edu/hg/galaxy/rev/1c923b889e90 changeset: 1746:1c923b889e90 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Fri Mar 27 16:55:34 2009 -0400 description: Re-fix the default test port... 1 file(s) affected in this change: test/functional/__init__.py diffs (12 lines): diff -r 6c555b0460f1 -r 1c923b889e90 test/functional/__init__.py --- a/test/functional/__init__.py Fri Mar 27 16:37:49 2009 -0400 +++ b/test/functional/__init__.py Fri Mar 27 16:55:34 2009 -0400 @@ -24,7 +24,7 @@ # server (for running the tests against a running instance) default_galaxy_test_host = "localhost" -default_galaxy_test_port = "9879" +default_galaxy_test_port = "9999" default_galaxy_locales = 'en' galaxy_test_file_dir = "test-data" server = None

1 0

[hg] galaxy 1748: Apply i18n fixes from Takashi Hatakeyama and M...
by Greg Von Kuster 09 Apr '09

09 Apr '09

details: http://www.bx.psu.edu/hg/galaxy/rev/09763a5f6ac6 changeset: 1748:09763a5f6ac6 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Thu Apr 09 09:00:58 2009 -0400 description: Apply i18n fixes from Takashi Hatakeyama and Mitsuteru Nakao. 4 file(s) affected in this change: lib/galaxy/datatypes/data.py lib/galaxy/jobs/__init__.py lib/galaxy/tools/__init__.py lib/galaxy/web/controllers/root.py diffs (51 lines): diff -r e2be1e679ab1 -r 09763a5f6ac6 lib/galaxy/datatypes/data.py --- a/lib/galaxy/datatypes/data.py Fri Apr 03 13:25:01 2009 -0400 +++ b/lib/galaxy/datatypes/data.py Thu Apr 09 09:00:58 2009 -0400 @@ -121,7 +121,7 @@ line = line.strip() if not line: continue - out.append( '<tr><td>%s</td></tr>' % escape( unicode( line, 'utf-8' ) ) ) + out.append( '<tr><td>%s</td></tr>' % escape( unicode( line ) ) ) out.append( '</table>' ) out = "".join( out ) except Exception, exc: diff -r e2be1e679ab1 -r 09763a5f6ac6 lib/galaxy/jobs/__init__.py --- a/lib/galaxy/jobs/__init__.py Fri Apr 03 13:25:01 2009 -0400 +++ b/lib/galaxy/jobs/__init__.py Thu Apr 09 09:00:58 2009 -0400 @@ -472,7 +472,10 @@ elif dataset.has_data(): # Only set metadata values if they are missing... dataset.set_meta( overwrite = False ) - dataset.set_peek() + if self.tool.is_multi_byte: + dataset.set_multi_byte_peek() + else: + dataset.set_peek() else: dataset.blurb = "empty" dataset.flush() diff -r e2be1e679ab1 -r 09763a5f6ac6 lib/galaxy/tools/__init__.py --- a/lib/galaxy/tools/__init__.py Fri Apr 03 13:25:01 2009 -0400 +++ b/lib/galaxy/tools/__init__.py Thu Apr 09 09:00:58 2009 -0400 @@ -288,6 +288,8 @@ if not self.version: # For backward compatibility, some tools may not have versions yet. self.version = "1.0.0" + # Support multi-byte tools + self.is_multi_byte = util.string_as_bool( root.get( "is_multi_byte", False ) ) # Type of tool self.tool_type = root.get( "tool_type", None ) # data_source tool diff -r e2be1e679ab1 -r 09763a5f6ac6 lib/galaxy/web/controllers/root.py --- a/lib/galaxy/web/controllers/root.py Fri Apr 03 13:25:01 2009 -0400 +++ b/lib/galaxy/web/controllers/root.py Thu Apr 09 09:00:58 2009 -0400 @@ -104,7 +104,7 @@ if data.state != state: rval[id] = { "state": data.state, - "html": trans.fill_template( "root/history_item.mako", data=data, hid=data.hid ) + "html": unicode( trans.fill_template( "root/history_item.mako", data=data, hid=data.hid ), 'utf-8' ) } return rval

1 0

[hg] galaxy 1747: Added a new option to specify minimum match va...
by Greg Von Kuster 09 Apr '09

09 Apr '09

details: http://www.bx.psu.edu/hg/galaxy/rev/e2be1e679ab1 changeset: 1747:e2be1e679ab1 user: guru date: Fri Apr 03 13:25:01 2009 -0400 description: Added a new option to specify minimum match value in the liftOver tool. 2 file(s) affected in this change: tools/extract/liftOver_wrapper.py tools/extract/liftOver_wrapper.xml diffs (69 lines): diff -r 1c923b889e90 -r e2be1e679ab1 tools/extract/liftOver_wrapper.py --- a/tools/extract/liftOver_wrapper.py Fri Mar 27 16:55:34 2009 -0400 +++ b/tools/extract/liftOver_wrapper.py Fri Apr 03 13:25:01 2009 -0400 @@ -12,20 +12,24 @@ sys.stderr.write(msg) sys.exit() -if len( sys.argv ) != 6: - stop_err( "USAGE: prog input out_file1 out_file2 input_dbkey output_dbkey" ) +if len( sys.argv ) != 7: + stop_err( "USAGE: prog input out_file1 out_file2 input_dbkey output_dbkey minMatch" ) infile = sys.argv[1] outfile1 = sys.argv[2] outfile2 = sys.argv[3] in_dbkey = sys.argv[4] mapfilepath = sys.argv[5] - +minMatch = sys.argv[6] +try: + assert float(minMatch) +except: + minMatch = 0.1 #ensure dbkey is set if in_dbkey == "?": stop_err( "Input dataset genome build unspecified, click the pencil icon in the history item to specify it." ) -cmd_line = "liftOver " + infile + " " + mapfilepath + " " + outfile1 + " " + outfile2 + " > /dev/null 2>&1" +cmd_line = "liftOver -minMatch=" + minMatch + " " + infile + " " + mapfilepath + " " + outfile1 + " " + outfile2 + " > /dev/null 2>&1" if not os.path.isfile( mapfilepath ): stop_err( "%s mapping is not currently available." % ( mapfilepath.split('/')[-1].split('.')[0] ) ) diff -r 1c923b889e90 -r e2be1e679ab1 tools/extract/liftOver_wrapper.xml --- a/tools/extract/liftOver_wrapper.xml Fri Mar 27 16:55:34 2009 -0400 +++ b/tools/extract/liftOver_wrapper.xml Fri Apr 03 13:25:01 2009 -0400 @@ -1,11 +1,11 @@ <tool id="liftOver1" name="Convert genome coordinates"> <description> between assemblies and genomes</description> - <command interpreter="python">liftOver_wrapper.py $input "$out_file1" "$out_file2" $dbkey $to_dbkey</command> + <command interpreter="python">liftOver_wrapper.py $input "$out_file1" "$out_file2" $dbkey $to_dbkey $minMatch</command> <inputs> <param format="interval" name="input" type="data" label="Convert coordinates of"> <validator type="unspecified_build" /> <validator type="dataset_metadata_in_file" filename="liftOver.loc" metadata_name="dbkey" metadata_column="0" message="Liftover mappings are currently not available for the specified build." /> - </param> + </param> <param name="to_dbkey" type="select" label="To"> <options from_file="liftOver.loc"> <column name="name" index="1"/> @@ -13,7 +13,8 @@ <column name="dbkey" index="0"/> <filter type="data_meta" ref="input" key="dbkey" column="0" /> </options> - </param> + </param> + <param name="minMatch" size="10" type="float" value="0.10" label="Minimum ratio of bases that must remap" /> </inputs> <outputs> <data format="input" name="out_file1" /> @@ -26,7 +27,8 @@ <tests> <test> <param name="input" value="5.bed" dbkey="hg18" ftype="bed" /> - <param name="to_dbkey" value="/depot/data2/galaxy/hg18/liftOver/hg18ToPanTro2.over.chain" /> + <param name="to_dbkey" value="/depot/data2/galaxy/hg18/liftOver/hg18ToPanTro2.over.chain" /> + <param name="misMatch" value="0.95" /> <output name="out_file1" file="5_liftover_mapped.bed"/> <output name="out_file2" file="5_liftover_unmapped.bed"/> </test>

1 0

[hg] galaxy 1745: i18n fix for build_from_current_history.mako t...
by Greg Von Kuster 27 Mar '09

27 Mar '09

details: http://www.bx.psu.edu/hg/galaxy/rev/6c555b0460f1 changeset: 1745:6c555b0460f1 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Fri Mar 27 16:37:49 2009 -0400 description: i18n fix for build_from_current_history.mako template. 1 file(s) affected in this change: templates/workflow/build_from_current_history.mako diffs (9 lines): diff -r e5e5280775c3 -r 6c555b0460f1 templates/workflow/build_from_current_history.mako --- a/templates/workflow/build_from_current_history.mako Thu Mar 26 09:43:02 2009 -0400 +++ b/templates/workflow/build_from_current_history.mako Fri Mar 27 16:37:49 2009 -0400 @@ -1,4 +1,4 @@ -<% _ = t.gettext %> +<% _=n_ %>  <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">

1 0

[hg] galaxy 1744: merging from central
by Greg Von Kuster 27 Mar '09

27 Mar '09

details: http://www.bx.psu.edu/hg/galaxy/rev/e5e5280775c3 changeset: 1744:e5e5280775c3 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Thu Mar 26 09:43:02 2009 -0400 description: merging from central 1 file(s) affected in this change: test/functional/__init__.py diffs (12 lines): diff -r c8bf73ed4594 -r e5e5280775c3 test/functional/__init__.py --- a/test/functional/__init__.py Thu Mar 26 09:34:05 2009 -0400 +++ b/test/functional/__init__.py Thu Mar 26 09:43:02 2009 -0400 @@ -24,7 +24,7 @@ # server (for running the tests against a running instance) default_galaxy_test_host = "localhost" -default_galaxy_test_port = "9999" +default_galaxy_test_port = "9879" default_galaxy_locales = 'en' galaxy_test_file_dir = "test-data" server = None

1 0

[hg] galaxy 1743: i18n fix: dataset.info should not be translate...
by Greg Von Kuster 26 Mar '09

26 Mar '09

details: http://www.bx.psu.edu/hg/galaxy/rev/c8bf73ed4594 changeset: 1743:c8bf73ed4594 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Thu Mar 26 09:34:05 2009 -0400 description: i18n fix: dataset.info should not be translated since it will generally not have an entry in the catalog. Wormbase fixes: URL to main site corrected, and all supported builds added to gbrowse_build_sites.txt. 4 file(s) affected in this change: templates/root/history_common.mako tool-data/shared/gbrowse/gbrowse_build_sites.txt tools/data_source/wormbase.xml universe_wsgi.ini.sample diffs (58 lines): diff -r 02843f56b812 -r c8bf73ed4594 templates/root/history_common.mako --- a/templates/root/history_common.mako Wed Mar 25 11:51:30 2009 -0400 +++ b/templates/root/history_common.mako Thu Mar 26 09:34:05 2009 -0400 @@ -51,7 +51,7 @@ The job creating this dataset was cancelled before completion. </div> %elif data_state == "empty": - <div>${_('No data: ')}<i>${_(data.display_info())}</i></div> + <div>${_('No data: ')}<i>${data.display_info()}</i></div> %elif data_state == "ok": <div> ${data.blurb}, @@ -63,7 +63,7 @@ <span class="${data.dbkey}">${_(data.dbkey)}</span> %endif </div> - <div class="info">${_('Info: ')}${_(data.display_info())} </div> + <div class="info">${_('Info: ')}${data.display_info()}</div> <div> %if data.has_data: <a href="${h.url_for( action='display', id=data.id, tofile='yes', toext=data.ext )}" target="_blank">save</a> diff -r 02843f56b812 -r c8bf73ed4594 tool-data/shared/gbrowse/gbrowse_build_sites.txt --- a/tool-data/shared/gbrowse/gbrowse_build_sites.txt Wed Mar 25 11:51:30 2009 -0400 +++ b/tool-data/shared/gbrowse/gbrowse_build_sites.txt Thu Mar 26 09:34:05 2009 -0400 @@ -1,5 +1,3 @@ -#Harvested from http://www.wormbase.org/db/seq/gbrowse/wormbase/ -#wormbase http://gvk.bx.psu.edu/cgi-bin/gbrowse/volvox? briggsae,briggsae_cb25,brugia,elegans,elegans_gmap,elegans_pmap,fly,fly31,nGASP,nGASP_submissions,remanei,wormbase,ws77,yeast_chr1 -#Harvested from http://flybase.bio.indiana.edu/cgi-bin/gbrowse/dmel/ -#flybase http://flybase.bio.indiana.edu/cgi-bin/gbrowse/dmel/ dana,dere,dgri,dmel,dmoj,dper,dpse,dsec,dsim,dvir,dwil,dyak,dmelstocks -elegans http://brie3.cshl.edu:9000/db/seq/gbrowse/elegans/ cb1,cb2,cb3,ce1,ce2,ce3,ce4 \ No newline at end of file +# wormbase sites / supported genomes +main http://www.wormbase.org/db/seq/gbgff/c_elegans/ c_elegans,c_briggsae,c_remanei,c_brenneri,c_japonica,p_pristionchus,b_malayi +test http://dev.wormbase.org/db/seq/gbrowse/c_elegans/ c_elegans,c_briggsae,c_remanei,c_brenneri,c_japonica,p_pristionchus,b_malayi diff -r 02843f56b812 -r c8bf73ed4594 tools/data_source/wormbase.xml --- a/tools/data_source/wormbase.xml Wed Mar 25 11:51:30 2009 -0400 +++ b/tools/data_source/wormbase.xml Thu Mar 26 09:34:05 2009 -0400 @@ -2,7 +2,7 @@ <tool name="Wormbase" id="wormbase" tool_type="data_source" URL_method="post"> <description>server</description> <command interpreter="python">data_source.py $output</command> - <inputs action="http://www.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" target="_top"> + <inputs action="http://www.wormbase.org/db/seq/gbgff/c_elegans/" check_values="false" target="_top"> <display>go to Wormbase server $GALAXY_URL</display> <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=wormbase" /> </inputs> diff -r 02843f56b812 -r c8bf73ed4594 universe_wsgi.ini.sample --- a/universe_wsgi.ini.sample Wed Mar 25 11:51:30 2009 -0400 +++ b/universe_wsgi.ini.sample Thu Mar 26 09:34:05 2009 -0400 @@ -115,7 +115,7 @@ # Comma separated list of UCSC / gbrowse browsers to use for viewing ucsc_display_sites = main,test,archaea -gbrowse_display_sites = c_elegans,c_briggsae,c_remanei,c_brenneri,c_japonica,p_pristionchus,b_malayi +gbrowse_display_sites = main,test # Serving static files (needed if running standalone) static_enabled = True

1 0

[hg] galaxy 1742: i18n fixes: uploading binary files now works a...
by Greg Von Kuster 25 Mar '09

25 Mar '09

details: http://www.bx.psu.edu/hg/galaxy/rev/02843f56b812 changeset: 1742:02843f56b812 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Wed Mar 25 11:51:30 2009 -0400 description: i18n fixes: uploading binary files now works again, multi-byte character files are no longer set as binary, file peek now supports multi-byte characters. 7 file(s) affected in this change: eggs.ini lib/galaxy/datatypes/data.py lib/galaxy/datatypes/sniff.py lib/galaxy/model/__init__.py lib/galaxy/tools/actions/upload.py lib/galaxy/util/__init__.py lib/galaxy/web/framework/__init__.py diffs (686 lines): diff -r affd3085eee3 -r 02843f56b812 eggs.ini --- a/eggs.ini Fri Mar 20 02:49:30 2009 -0400 +++ b/eggs.ini Wed Mar 25 11:51:30 2009 -0400 @@ -48,6 +48,7 @@ WebOb = 0.8.5 wsgiref = 0.1.2 Babel = 0.9.4 +wchartype = 0.1 ; extra version information [tags] @@ -94,3 +95,4 @@ WebOb = http://pypi.python.org/packages/source/W/WebOb/WebOb-0.8.5.tar.gz wsgiref = http://pypi.python.org/packages/source/w/wsgiref/wsgiref-0.1.2.zip Babel = http://ftp.edgewall.com/pub/babel/Babel-0.9.4.zip +wchartype = http://ginstrom.com/code/wchartype-0.1.zip diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/datatypes/data.py --- a/lib/galaxy/datatypes/data.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/datatypes/data.py Wed Mar 25 11:51:30 2009 -0400 @@ -109,7 +109,7 @@ else: dataset.peek = 'file does not exist' dataset.blurb = 'file purged from disk' - def display_peek(self, dataset): + def display_peek(self, dataset ): """Create HTML table, used for displaying peek""" out = ['<table cellspacing="0" cellpadding="3">'] try: @@ -121,7 +121,7 @@ line = line.strip() if not line: continue - out.append( '<tr><td>%s</td></tr>' % escape( line ) ) + out.append( '<tr><td>%s</td></tr>' % escape( unicode( line, 'utf-8' ) ) ) out.append( '</table>' ) out = "".join( out ) except Exception, exc: @@ -190,7 +190,6 @@ except: log.exception('Function %s is referred to in datatype %s for displaying as type %s, but is not accessible' % (self.supported_display_apps[type]['file_function'], self.__class__.__name__, type) ) return "This display type (%s) is not implemented for this datatype (%s)." % ( type, dataset.ext) - def get_display_links(self, dataset, type, app, base_url, **kwd): """Returns a list of tuples of (name, link) for a particular display type """ try: @@ -199,21 +198,17 @@ except: log.exception('Function %s is referred to in datatype %s for generating links for type %s, but is not accessible' % (self.supported_display_apps[type]['links_function'], self.__class__.__name__, type) ) return [] - def get_converter_types(self, original_dataset, datatypes_registry): """Returns available converters by type for this dataset""" return datatypes_registry.get_converters_by_datatype(original_dataset.ext) - def find_conversion_destination( self, dataset, accepted_formats, datatypes_registry, **kwd ): """Returns ( target_ext, exisiting converted dataset )""" return datatypes_registry.find_conversion_destination_for_dataset_by_extensions( dataset, accepted_formats, **kwd ) - def convert_dataset(self, trans, original_dataset, target_type, return_output = False, visible = True ): """This function adds a job to the queue to convert a dataset to another type. Returns a message about success/failure.""" converter = trans.app.datatypes_registry.get_converter_by_target_type( original_dataset.ext, target_type ) if converter is None: raise "A converter does not exist for %s to %s." % ( original_dataset.ext, target_type ) - #Generate parameter dictionary params = {} #determine input parameter name and add to params @@ -223,31 +218,24 @@ input_name = key break params[input_name] = original_dataset - #Run converter, job is dispatched through Queue converted_dataset = converter.execute( trans, incoming = params, set_output_hid = visible ) - if len(params) > 0: trans.log_event( "Converter params: %s" % (str(params)), tool_id=converter.id ) - if not visible: for name, value in converted_dataset.iteritems(): value.visible = False - if return_output: return converted_dataset return "The file conversion of %s on data %s has been added to the Queue." % (converter.name, original_dataset.hid) - def before_edit( self, dataset ): """This function is called on the dataset before metadata is edited.""" pass - def after_edit( self, dataset ): """This function is called on the dataset after metadata is edited.""" dataset.clear_associated_files( metadata_safe = True ) class Text( Data ): - def write_from_stream(self, dataset, stream): """Writes data from a stream""" # write it twice for now @@ -265,30 +253,36 @@ line = line.strip() + '\n' fp.write(line) fp.close() - def set_raw_data(self, dataset, data): """Saves the data on the disc""" fd, temp_name = tempfile.mkstemp() os.write(fd, data) os.close(fd) - # rewrite the file with unix newlines fp = open(dataset.file_name, 'wt') for line in file(temp_name, "U"): line = line.strip() + '\n' fp.write(line) fp.close() - os.remove( temp_name ) - def get_mime(self): """Returns the mime type of the datatype""" return 'text/plain' - def set_peek( self, dataset, line_count=None ): 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.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + def set_multi_byte_peek( self, dataset, line_count=None ): + 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=True ) if line_count is None: dataset.blurb = "%s lines" % util.commaify( str( get_line_count( dataset.file_name ) ) ) else: @@ -340,7 +334,7 @@ return out return '??? bytes' -def get_file_peek( file_name, WIDTH=256, LINE_COUNT=5 ): +def get_file_peek( file_name, is_multi_byte=False, WIDTH=256, LINE_COUNT=5 ): """ Returns the first LINE_COUNT lines wrapped to WIDTH @@ -350,12 +344,12 @@ """ lines = [] count = 0 - file_type = '' + file_type = None data_checked = False for line in file( file_name ): - line = line[ :WIDTH ] - if not data_checked and line: - data_checked = True + line = line[:WIDTH] + 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: file_type = 'gzipped' break @@ -364,14 +358,17 @@ if ord( char ) > 128: file_type = 'binary' break + data_checked = True + if file_type in [ 'gzipped', 'binary' ]: + break lines.append( line ) if count == LINE_COUNT: break count += 1 - if file_type: - text = "%s file" %file_type + if file_type in [ 'gzipped', 'binary' ]: + text = "%s file" % file_type else: - text = '\n'.join( lines ) + text = unicode( '\n'.join( lines ), 'utf-8' ) return text def get_line_count(file_name): diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/datatypes/sniff.py --- a/lib/galaxy/datatypes/sniff.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/datatypes/sniff.py Wed Mar 25 11:51:30 2009 -0400 @@ -1,8 +1,9 @@ """ File format detector """ -import logging, sys, os, csv, tempfile, shutil, re +import logging, sys, os, csv, tempfile, shutil, re, zipfile import registry +from galaxy import util log = logging.getLogger(__name__) @@ -13,18 +14,43 @@ return full_path def stream_to_file( stream, suffix='', prefix='', dir=None, text=False ): - """ - Writes a stream to a temporary file, returns the temporary file's name - """ + """Writes a stream to a temporary file, returns the temporary file's name""" fd, temp_name = tempfile.mkstemp( suffix=suffix, prefix=prefix, dir=dir, text=text ) + CHUNK_SIZE = 1048576 + data_checked = False + is_compressed = False + is_binary = False + is_multi_byte = False while 1: - chunk = stream.read(1048576) + chunk = stream.read( CHUNK_SIZE ) if not chunk: break - # TODO: does this work on binary files? - os.write( fd, chunk.encode( "utf-8" ) ) - os.close(fd) - return temp_name + if not data_checked: + # See if we're uploading a compressed file + if zipfile.is_zipfile( temp_name ): + is_compressed = True + else: + magic_check = chunk[:2] + if magic_check == util.gzip_magic: + is_compressed = True + if not is_compressed: + # See if we have a multi-byte character file + chars = chunk[:100] + is_multi_byte = util.is_multi_byte( chars ) + if not is_multi_byte: + for char in chars: + if ord( char ) > 128: + is_binary = True + break + data_checked = True + if not is_compressed and not is_binary: + os.write( fd, chunk.encode( "utf-8" ) ) + else: + # Compressed files must be encoded after they are uncompressed in the upload utility, + # while binary files should not be encoded at all. + os.write( fd, chunk ) + os.close( fd ) + return temp_name, is_multi_byte def convert_newlines( fname ): """ @@ -94,7 +120,7 @@ # Return number of lines in file. return i + 1 -def get_headers(fname, sep, count=60): +def get_headers( fname, sep, count=60, is_multi_byte=False ): """ Returns a list with the first 'count' lines split by 'sep' @@ -105,12 +131,16 @@ headers = [] for idx, line in enumerate(file(fname)): line = line.rstrip('\n\r') + if is_multi_byte: + # TODO: fix this - sep is never found in line + line = unicode( line, 'utf-8' ) + sep = sep.encode( 'utf-8' ) headers.append( line.split(sep) ) if idx == count: break return headers -def is_column_based(fname, sep='\t', skip=0): +def is_column_based( fname, sep='\t', skip=0, is_multi_byte=False ): """ Checks whether the file is column based with respect to a separator (defaults to tab separator). @@ -138,9 +168,8 @@ >>> is_column_based(fname) True """ - headers = get_headers(fname, sep) + headers = get_headers( fname, sep, is_multi_byte=is_multi_byte ) count = 0 - if not headers: return False for hdr in headers[skip:]: @@ -156,7 +185,7 @@ return False return True -def guess_ext( fname, sniff_order=None ): +def guess_ext( fname, sniff_order=None, is_multi_byte=False ): """ Returns an extension that can be used in the datatype factory to generate a data for the 'fname' file @@ -220,20 +249,28 @@ return datatype.file_ext except: pass - headers = get_headers( fname, None ) - is_binary = True - for hdr in headers: - for char in hdr: - try: - if not ord(char) > 128: - is_binary = False - except: - is_binary = False + is_binary = False + if is_multi_byte: + is_binary = False + else: + for hdr in headers: + for char in hdr: + if len( char ) > 1: + for c in char: + if ord( c ) > 128: + is_binary = True + break + elif ord( char ) > 128: + is_binary = True + break + if is_binary: + break + if is_binary: break if is_binary: return 'data' #default binary data type file extension - if is_column_based( fname, '\t', 1): + if is_column_based( fname, '\t', 1, is_multi_byte=is_multi_byte ): return 'tabular' #default tabular data type file extension return 'txt' #default text data type file extension diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/model/__init__.py --- a/lib/galaxy/model/__init__.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/model/__init__.py Wed Mar 25 11:51:30 2009 -0400 @@ -245,6 +245,8 @@ return datatypes_registry.get_mimetype_by_extension( self.extension.lower() ) def set_peek( self ): return self.datatype.set_peek( self ) + def set_multi_byte_peek( self ): + return self.datatype.set_multi_byte_peek( self ) def init_meta( self, copy_from=None ): return self.datatype.init_meta( self, copy_from=copy_from ) def set_meta( self, **kwd ): diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/tools/actions/upload.py --- a/lib/galaxy/tools/actions/upload.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/tools/actions/upload.py Wed Mar 25 11:51:30 2009 -0400 @@ -23,6 +23,7 @@ file_type = incoming['file_type'] dbkey = incoming['dbkey'] url_paste = incoming['url_paste'] + is_multi_byte = False space_to_tab = False if 'space_to_tab' in incoming: if incoming['space_to_tab'] not in ["None", None]: @@ -49,7 +50,7 @@ file_name = file_name.split( '\\' )[-1] file_name = file_name.split( '/' )[-1] try: - data_list.append( self.add_file( trans, data_file.local_filename, file_name, file_type, dbkey, space_to_tab=space_to_tab ) ) + data_list.append( self.add_file( trans, data_file.local_filename, file_name, file_type, is_multi_byte, dbkey, space_to_tab=space_to_tab ) ) except Exception, e: log.exception( 'exception in add_file using datafile.local_filename %s: %s' % ( data_file.local_filename, str( e ) ) ) self.remove_tempfile( data_file.local_filename ) @@ -59,13 +60,13 @@ file_name = file_name.split( '\\' )[-1] file_name = file_name.split( '/' )[-1] try: - temp_name = sniff.stream_to_file( data_file.file, prefix='upload' ) + temp_name, is_multi_byte = sniff.stream_to_file( data_file.file, prefix='upload' ) except Exception, e: log.exception( 'exception in sniff.stream_to_file using file %s: %s' % ( data_file.filename, str( e ) ) ) self.remove_tempfile( temp_name ) return self.upload_empty( trans, job, "Error:", str( e ) ) try: - data_list.append( self.add_file( trans, temp_name, file_name, file_type, dbkey, space_to_tab=space_to_tab ) ) + data_list.append( self.add_file( trans, temp_name, file_name, file_type, is_multi_byte, dbkey, space_to_tab=space_to_tab ) ) except Exception, e: log.exception( 'exception in add_file using file temp_name %s: %s' % ( str( temp_name ), str( e ) ) ) self.remove_tempfile( temp_name ) @@ -77,13 +78,13 @@ line = line.rstrip( '\r\n' ) if line: try: - temp_name = sniff.stream_to_file( urllib.urlopen( line ), prefix='url_paste' ) + temp_name, is_multi_byte = sniff.stream_to_file( urllib.urlopen( line ), prefix='url_paste' ) except Exception, e: log.exception( 'exception in sniff.stream_to_file using url_paste %s: %s' % ( url_paste, str( e ) ) ) self.remove_tempfile( temp_name ) return self.upload_empty( trans, job, "Error:", str( e ) ) try: - data_list.append( self.add_file( trans, temp_name, line, file_type, dbkey, info="uploaded url", space_to_tab=space_to_tab ) ) + data_list.append( self.add_file( trans, temp_name, line, file_type, is_multi_byte, dbkey, info="uploaded url", space_to_tab=space_to_tab ) ) except Exception, e: log.exception( 'exception in add_file using url_paste temp_name %s: %s' % ( str( temp_name ), str( e ) ) ) self.remove_tempfile( temp_name ) @@ -97,13 +98,13 @@ break if is_valid: try: - temp_name = sniff.stream_to_file( StringIO.StringIO( url_paste ), prefix='strio_url_paste' ) + temp_name, is_multi_byte = sniff.stream_to_file( StringIO.StringIO( url_paste ), prefix='strio_url_paste' ) except Exception, e: log.exception( 'exception in sniff.stream_to_file using StringIO.StringIO( url_paste ) %s: %s' % ( url_paste, str( e ) ) ) self.remove_tempfile( temp_name ) return self.upload_empty( trans, job, "Error:", str( e ) ) try: - data_list.append( self.add_file( trans, temp_name, 'Pasted Entry', file_type, dbkey, info="pasted entry", space_to_tab=space_to_tab ) ) + data_list.append( self.add_file( trans, temp_name, 'Pasted Entry', file_type, is_multi_byte, dbkey, info="pasted entry", space_to_tab=space_to_tab ) ) except Exception, e: log.exception( 'exception in add_file using StringIO.StringIO( url_paste ) temp_name %s: %s' % ( str( temp_name ), str( e ) ) ) self.remove_tempfile( temp_name ) @@ -144,85 +145,87 @@ trans.log_event( 'job id %d ended with errors, err_msg: %s' % ( job.id, err_msg ), tool_id=job.tool_id ) return dict( output=data ) - def add_file( self, trans, temp_name, file_name, file_type, dbkey, info=None, space_to_tab=False ): + def add_file( self, trans, temp_name, file_name, file_type, is_multi_byte, dbkey, info=None, space_to_tab=False ): data_type = None + ext = '' # See if we have an empty file if not os.path.getsize( temp_name ) > 0: raise BadFileException( "you attempted to upload an empty file." ) - # See if we have a gzipped file, which, if it passes our restrictions, - # we'll decompress on the fly. - is_gzipped, is_valid = self.check_gzip( temp_name ) - if is_gzipped and not is_valid: - raise BadFileException( "you attempted to upload an inappropriate file." ) - elif is_gzipped and is_valid: - #We need to decompress the temp_name file - CHUNK_SIZE = 2**20 # 1Mb - fd, uncompressed = tempfile.mkstemp() - gzipped_file = gzip.GzipFile( temp_name ) - while 1: - try: - chunk = gzipped_file.read( CHUNK_SIZE ) - except IOError: + if is_multi_byte: + ext = sniff.guess_ext( temp_name, is_multi_byte=True ) + else: + if not data_type: + # See if we have a gzipped file, which, if it passes our restrictions, + # we'll decompress on the fly. + is_gzipped, is_valid = self.check_gzip( temp_name ) + if is_gzipped and not is_valid: + raise BadFileException( "you attempted to upload an inappropriate file." ) + elif is_gzipped and is_valid: + #We need to decompress the temp_name file + CHUNK_SIZE = 2**20 # 1Mb + fd, uncompressed = tempfile.mkstemp() + gzipped_file = gzip.GzipFile( temp_name ) + while 1: + try: + chunk = gzipped_file.read( CHUNK_SIZE ) + except IOError: + os.close( fd ) + os.remove( uncompressed ) + raise BadFileException( 'problem decompressing gzipped data.' ) + if not chunk: + break + os.write( fd, chunk.encode( "utf-8" ) ) os.close( fd ) - os.remove( uncompressed ) - raise BadFileException( 'problem decompressing gzipped data.' ) - if not chunk: - break - os.write( fd, chunk ) - os.close( fd ) - gzipped_file.close() - # Replace the gzipped file with the decompressed file - shutil.move( uncompressed, temp_name ) - file_name = file_name.rstrip( '.gz' ) - data_type = 'gzip' - ext = '' - if not data_type: - # See if we have a zip archive - is_zipped, is_valid, test_ext = self.check_zip( temp_name ) - if is_zipped and not is_valid: - raise BadFileException( "you attempted to upload an inappropriate file." ) - elif is_zipped and is_valid: - # Currently, we force specific tools to handle this case. We also require the user - # to manually set the incoming file_type - if ( test_ext == 'ab1' or test_ext == 'scf' ) and file_type != 'binseq.zip': - raise BadFileException( "Invalid 'File Format' for archive consisting of binary files - use 'Binseq.zip'." ) - elif test_ext == 'txt' and file_type != 'txtseq.zip': - raise BadFileException( "Invalid 'File Format' for archive consisting of text files - use 'Txtseq.zip'." ) - if not ( file_type == 'binseq.zip' or file_type == 'txtseq.zip' ): - raise BadFileException( "you must manually set the 'File Format' to either 'Binseq.zip' or 'Txtseq.zip' when uploading zip files." ) - data_type = 'zip' - ext = file_type - if not data_type: - if self.check_binary( temp_name ): - parts = file_name.split( "." ) - if len( parts ) > 1: - ext = parts[1].strip().lower() - if not( ext == 'ab1' or ext == 'scf' ): - raise BadFileException( "you attempted to upload an inappropriate file." ) - if ext == 'ab1' and file_type != 'ab1': - raise BadFileException( "you must manually set the 'File Format' to 'Ab1' when uploading ab1 files." ) - elif ext == 'scf' and file_type != 'scf': - raise BadFileException( "you must manually set the 'File Format' to 'Scf' when uploading scf files." ) - data_type = 'binary' - if not data_type: - # We must have a text file - if self.check_html( temp_name ): - raise BadFileException( "you attempted to upload an inappropriate file." ) - if data_type != 'binary' and data_type != 'zip': - if space_to_tab: - self.line_count = sniff.convert_newlines_sep2tabs( temp_name ) - else: - self.line_count = sniff.convert_newlines( temp_name ) - if file_type == 'auto': - ext = sniff.guess_ext( temp_name, sniff_order=trans.app.datatypes_registry.sniff_order ) - else: - ext = file_type - data_type = ext - + gzipped_file.close() + # Replace the gzipped file with the decompressed file + shutil.move( uncompressed, temp_name ) + file_name = file_name.rstrip( '.gz' ) + data_type = 'gzip' + if not data_type: + # See if we have a zip archive + is_zipped, is_valid, test_ext = self.check_zip( temp_name ) + if is_zipped and not is_valid: + raise BadFileException( "you attempted to upload an inappropriate file." ) + elif is_zipped and is_valid: + # Currently, we force specific tools to handle this case. We also require the user + # to manually set the incoming file_type + if ( test_ext == 'ab1' or test_ext == 'scf' ) and file_type != 'binseq.zip': + raise BadFileException( "Invalid 'File Format' for archive consisting of binary files - use 'Binseq.zip'." ) + elif test_ext == 'txt' and file_type != 'txtseq.zip': + raise BadFileException( "Invalid 'File Format' for archive consisting of text files - use 'Txtseq.zip'." ) + if not ( file_type == 'binseq.zip' or file_type == 'txtseq.zip' ): + raise BadFileException( "you must manually set the 'File Format' to either 'Binseq.zip' or 'Txtseq.zip' when uploading zip files." ) + data_type = 'zip' + ext = file_type + if not data_type: + if self.check_binary( temp_name ): + parts = file_name.split( "." ) + if len( parts ) > 1: + ext = parts[1].strip().lower() + if not( ext == 'ab1' or ext == 'scf' ): + raise BadFileException( "you attempted to upload an inappropriate file." ) + if ext == 'ab1' and file_type != 'ab1': + raise BadFileException( "you must manually set the 'File Format' to 'Ab1' when uploading ab1 files." ) + elif ext == 'scf' and file_type != 'scf': + raise BadFileException( "you must manually set the 'File Format' to 'Scf' when uploading scf files." ) + data_type = 'binary' + if not data_type: + # We must have a text file + if self.check_html( temp_name ): + raise BadFileException( "you attempted to upload an inappropriate file." ) + if data_type != 'binary' and data_type != 'zip': + if space_to_tab: + self.line_count = sniff.convert_newlines_sep2tabs( temp_name ) + else: + self.line_count = sniff.convert_newlines( temp_name ) + if file_type == 'auto': + ext = sniff.guess_ext( temp_name, sniff_order=trans.app.datatypes_registry.sniff_order ) + else: + ext = file_type + data_type = ext if info is None: info = 'uploaded %s file' %data_type - - data = trans.app.model.HistoryDatasetAssociation( history = trans.history, extension = ext, create_dataset = True ) + data = trans.app.model.HistoryDatasetAssociation( history=trans.history, extension=ext, create_dataset=True ) data.name = file_name data.dbkey = dbkey data.info = info @@ -233,19 +236,25 @@ data.init_meta() if self.line_count is not None: try: - data.set_peek( line_count=self.line_count ) + if is_multi_byte: + data.set_multi_byte_peek( line_count=self.line_count ) + else: + data.set_peek( line_count=self.line_count ) except: + if is_multi_byte: + data.set_multi_byte_peek() + else: + data.set_peek() + else: + if is_multi_byte: + data.set_multi_byte_peek() + else: data.set_peek() - else: - data.set_peek() - - # validate incomming data - """ - Commented by greg on 3/14/07 - for error in data.datatype.validate( data ): - data.add_validation_error( - model.ValidationError( message=str( error ), err_type=error.__class__.__name__, attributes=util.object_to_string( error.__dict__ ) ) ) - """ + # validate incoming data + # Commented by greg on 3/14/07 + # for error in data.datatype.validate( data ): + # data.add_validation_error( + # model.ValidationError( message=str( error ), err_type=error.__class__.__name__, attributes=util.object_to_string( error.__dict__ ) ) ) if data.missing_meta(): data.datatype.set_meta( data ) dbkey_to_store = dbkey @@ -319,6 +328,8 @@ lineno += 1 line = line.strip() if line: + if util.is_multi_byte( line ): + return False for char in line: if ord( char ) > 128: if chunk is None: diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/util/__init__.py --- a/lib/galaxy/util/__init__.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/util/__init__.py Wed Mar 25 11:51:30 2009 -0400 @@ -14,10 +14,33 @@ pkg_resources.require( 'elementtree' ) from elementtree import ElementTree +pkg_resources.require( "wchartype" ) +import wchartype + log = logging.getLogger(__name__) _lock = threading.RLock() gzip_magic = '\037\213' + +def is_multi_byte( chars ): + for char in chars: + try: + char = unicode( char ) + except Exception, e: + # Probably binary + log.exception( e ) + return False + if wchartype.is_asian( char ) or \ + wchartype.is_full_width( char ) or \ + wchartype.is_kanji( char ) or \ + wchartype.is_hiragana( char ) or \ + wchartype.is_katakana( char ) or \ + wchartype.is_half_katakana( char ) or \ + wchartype.is_hangul( char ) or \ + wchartype.is_full_digit( char ) or \ + wchartype.is_full_letter( char ): + return True + return False def synchronized(func): """This wrapper will serialize access to 'func' to a single thread. Use it as a decorator.""" diff -r affd3085eee3 -r 02843f56b812 lib/galaxy/web/framework/__init__.py --- a/lib/galaxy/web/framework/__init__.py Fri Mar 20 02:49:30 2009 -0400 +++ b/lib/galaxy/web/framework/__init__.py Wed Mar 25 11:51:30 2009 -0400 @@ -466,8 +466,7 @@ return self.fill_template_mako( filename, **kwargs ) else: template = Template( file=os.path.join(self.app.config.template_path, filename), - searchList=[kwargs, self.template_context, dict(caller=self, t=self, h=webhelpers, util=util, request=self.request, response=self.response, app=self.app)], - output_encoding='utf-8' ) + searchList=[kwargs, self.template_context, dict(caller=self, t=self, h=webhelpers, util=util, request=self.request, response=self.response, app=self.app)] ) return str( template ) def fill_template_mako( self, filename, **kwargs ): template = self.webapp.mako_template_lookup.get_template( filename ) @@ -481,8 +480,7 @@ Fill in a template, putting any keyword arguments on the context. """ template = Template( source=template_string, - searchList=[context or kwargs, dict(caller=self)], - output_encoding='utf-8' ) + searchList=[context or kwargs, dict(caller=self)] ) return str(template) class FormBuilder( object ):

1 0

[hg] galaxy 1741: Fixes for i18n support - all charsets set to u...
by Greg Von Kuster 20 Mar '09

20 Mar '09

details: http://www.bx.psu.edu/hg/galaxy/rev/affd3085eee3 changeset: 1741:affd3085eee3 user: Greg Von Kuster <greg(a)bx.psu.edu> date: Fri Mar 20 02:49:30 2009 -0400 description: Fixes for i18n support - all charsets set to utf-8, now able to paste multi-byte chars in upload form, templates use utf-8 as output_charset, other miscellaneous fixes. 21 file(s) affected in this change: lib/galaxy/datatypes/sniff.py lib/galaxy/tools/actions/upload.py lib/galaxy/util/__init__.py lib/galaxy/web/controllers/ucsc_proxy.py lib/galaxy/web/framework/__init__.py lib/galaxy/web/framework/base.py lib/galaxy/webapps/reports/templates/base_panels.mako lib/galaxy/webapps/reports/templates/masthead.mako scripts/paster.py templates/base.mako templates/base_panels.mako templates/dataset/errors.tmpl templates/dataset/validation.tmpl templates/root/history.mako templates/root/masthead.mako templates/root/tool_menu.mako templates/tool_executed.mako templates/tool_form.mako templates/workflow/build_from_current_history.mako tools/data_source/wormbase.xml tools/data_source/wormbase_test.xml diffs (440 lines): diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/datatypes/sniff.py --- a/lib/galaxy/datatypes/sniff.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/datatypes/sniff.py Fri Mar 20 02:49:30 2009 -0400 @@ -21,7 +21,8 @@ chunk = stream.read(1048576) if not chunk: break - os.write(fd, chunk) + # TODO: does this work on binary files? + os.write( fd, chunk.encode( "utf-8" ) ) os.close(fd) return temp_name diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/tools/actions/upload.py --- a/lib/galaxy/tools/actions/upload.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/tools/actions/upload.py Fri Mar 20 02:49:30 2009 -0400 @@ -105,7 +105,7 @@ try: data_list.append( self.add_file( trans, temp_name, 'Pasted Entry', file_type, dbkey, info="pasted entry", space_to_tab=space_to_tab ) ) except Exception, e: - log.excception( 'exception in add_file using StringIO.StringIO( url_paste ) temp_name %s: %s' % ( str( temp_name ), str( e ) ) ) + log.exception( 'exception in add_file using StringIO.StringIO( url_paste ) temp_name %s: %s' % ( str( temp_name ), str( e ) ) ) self.remove_tempfile( temp_name ) return self.upload_empty( trans, job, "Error:", str( e ) ) else: @@ -146,12 +146,11 @@ def add_file( self, trans, temp_name, file_name, file_type, dbkey, info=None, space_to_tab=False ): data_type = None - # See if we have an empty file if not os.path.getsize( temp_name ) > 0: raise BadFileException( "you attempted to upload an empty file." ) - - # See if we have a gzipped file, which, if it passes our restrictions, we'll decompress on the fly. + # See if we have a gzipped file, which, if it passes our restrictions, + # we'll decompress on the fly. is_gzipped, is_valid = self.check_gzip( temp_name ) if is_gzipped and not is_valid: raise BadFileException( "you attempted to upload an inappropriate file." ) @@ -176,7 +175,7 @@ shutil.move( uncompressed, temp_name ) file_name = file_name.rstrip( '.gz' ) data_type = 'gzip' - + ext = '' if not data_type: # See if we have a zip archive is_zipped, is_valid, test_ext = self.check_zip( temp_name ) @@ -193,30 +192,28 @@ raise BadFileException( "you must manually set the 'File Format' to either 'Binseq.zip' or 'Txtseq.zip' when uploading zip files." ) data_type = 'zip' ext = file_type - if not data_type: if self.check_binary( temp_name ): - ext = file_name.split( "." )[1].strip().lower() - if not( ext == 'ab1' or ext == 'scf' ): - raise BadFileException( "you attempted to upload an inappropriate file." ) - if ext == 'ab1' and file_type != 'ab1': - raise BadFileException( "you must manually set the 'File Format' to 'Ab1' when uploading ab1 files." ) - elif ext == 'scf' and file_type != 'scf': - raise BadFileException( "you must manually set the 'File Format' to 'Scf' when uploading scf files." ) + parts = file_name.split( "." ) + if len( parts ) > 1: + ext = parts[1].strip().lower() + if not( ext == 'ab1' or ext == 'scf' ): + raise BadFileException( "you attempted to upload an inappropriate file." ) + if ext == 'ab1' and file_type != 'ab1': + raise BadFileException( "you must manually set the 'File Format' to 'Ab1' when uploading ab1 files." ) + elif ext == 'scf' and file_type != 'scf': + raise BadFileException( "you must manually set the 'File Format' to 'Scf' when uploading scf files." ) data_type = 'binary' - if not data_type: # We must have a text file if self.check_html( temp_name ): raise BadFileException( "you attempted to upload an inappropriate file." ) - if data_type != 'binary' and data_type != 'zip': if space_to_tab: self.line_count = sniff.convert_newlines_sep2tabs( temp_name ) else: self.line_count = sniff.convert_newlines( temp_name ) if file_type == 'auto': - log.debug("In upload, in if file_type == 'auto':") ext = sniff.guess_ext( temp_name, sniff_order=trans.app.datatypes_registry.sniff_order ) else: ext = file_type @@ -312,7 +309,6 @@ if chunk is None: temp.close() return False - def check_binary( self, temp_name, chunk=None ): if chunk is None: temp = open( temp_name, "U" ) diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/util/__init__.py --- a/lib/galaxy/util/__init__.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/util/__init__.py Fri Mar 20 02:49:30 2009 -0400 @@ -107,9 +107,9 @@ def sanitize_param(value): """Clean incoming parameters (strings or lists)""" - if type(value) == type('x'): + if isinstance( value, basestring ): return sanitize_text(value) - elif type(value) == type([]): + elif isinstance( value, list ): return map(sanitize_text, value) else: raise Exception, 'Unknown parameter type' diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/web/controllers/ucsc_proxy.py --- a/lib/galaxy/web/controllers/ucsc_proxy.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/web/controllers/ucsc_proxy.py Fri Mar 20 02:49:30 2009 -0400 @@ -121,7 +121,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="/static/style/base.css" rel="stylesheet" type="text/css" /> <script language="javascript" type="text/javascript"> function changeTarget(target) diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/web/framework/__init__.py --- a/lib/galaxy/web/framework/__init__.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/web/framework/__init__.py Fri Mar 20 02:49:30 2009 -0400 @@ -87,7 +87,8 @@ self.mako_template_lookup = mako.lookup.TemplateLookup( directories = [ galaxy_app.config.template_path ] , module_directory = galaxy_app.config.template_cache, - collection_size = 500 ) + collection_size = 500, + output_encoding = 'utf-8' ) # Security helper self.security = galaxy_app.security def handle_controller_exception( self, e, trans, **kwargs ): @@ -131,7 +132,7 @@ # Default to English locales = 'en' t = Translations.load( dirname='locale', locales=locales, domain='ginga' ) - self.template_context.update ( dict( _=t.gettext, n_=t.gettext, N_=t.ngettext ) ) + self.template_context.update ( dict( _=t.ugettext, n_=t.ugettext, N_=t.ungettext ) ) @property def sa_session( self ): """ @@ -465,10 +466,12 @@ return self.fill_template_mako( filename, **kwargs ) else: template = Template( file=os.path.join(self.app.config.template_path, filename), - searchList=[kwargs, self.template_context, dict(caller=self, t=self, h=webhelpers, util=util, request=self.request, response=self.response, app=self.app)] ) + searchList=[kwargs, self.template_context, dict(caller=self, t=self, h=webhelpers, util=util, request=self.request, response=self.response, app=self.app)], + output_encoding='utf-8' ) return str( template ) def fill_template_mako( self, filename, **kwargs ): template = self.webapp.mako_template_lookup.get_template( filename ) + template.output_encoding = 'utf-8' data = dict( caller=self, t=self, trans=self, h=webhelpers, util=util, request=self.request, response=self.response, app=self.app ) data.update( self.template_context ) data.update( kwargs ) @@ -477,7 +480,9 @@ """ Fill in a template, putting any keyword arguments on the context. """ - template = Template( source=template_string, searchList=[context or kwargs, dict(caller=self)] ) + template = Template( source=template_string, + searchList=[context or kwargs, dict(caller=self)], + output_encoding='utf-8' ) return str(template) class FormBuilder( object ): diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/web/framework/base.py --- a/lib/galaxy/web/framework/base.py Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/web/framework/base.py Fri Mar 20 02:49:30 2009 -0400 @@ -14,8 +14,10 @@ pkg_resources.require( "Paste" ) pkg_resources.require( "Routes" ) pkg_resources.require( "flup" ) +pkg_resources.require( "WebOb" ) import routes +import webob # We will use some very basic HTTP/wsgi utilities from the paste library from paste.request import parse_headers, get_cookies, parse_formvars @@ -212,7 +214,7 @@ else: return None -class Request( object ): +class Request( webob.Request ): """ Encapsulates an HTTP request. """ @@ -220,26 +222,24 @@ """ Create a new request wrapping the WSGI environment `environ` """ - self.environ = environ + ## self.environ = environ + webob.Request.__init__( self, environ, charset='utf-8', decode_param_names=False ) # Properties that are computed and cached on first use @lazy_property def remote_host( self ): try: - return socket.gethostbyname( self.environ['REMOTE_ADDR'] ) + return socket.gethostbyname( self.remote_addr ) except socket.error: - return self.environ['REMOTE_ADDR'] - @lazy_property - def headers( self ): - return dict( parse_headers( self.environ ) ) + return self.remote_addr @lazy_property def cookies( self ): return get_cookies( self.environ ) @lazy_property def base( self ): - return ( self.scheme + "://" + self.environ['HTTP_HOST'] ) - @lazy_property - def params( self ): - return parse_formvars( self.environ ) + return ( self.scheme + "://" + self.host ) + ## @lazy_property + ## def params( self ): + ## return parse_formvars( self.environ ) @lazy_property def path( self ): return self.environ['SCRIPT_NAME'] + self.environ['PATH_INFO'] @@ -247,15 +247,15 @@ def browser_url( self ): return self.base + self.path # Descriptors that map properties to the associated environment - scheme = WSGIEnvironmentProperty( 'wsgi.url_scheme' ) - remote_addr = WSGIEnvironmentProperty( 'REMOTE_ADDR' ) + ## scheme = WSGIEnvironmentProperty( 'wsgi.url_scheme' ) + ## remote_addr = WSGIEnvironmentProperty( 'REMOTE_ADDR' ) remote_port = WSGIEnvironmentProperty( 'REMOTE_PORT' ) - method = WSGIEnvironmentProperty( 'REQUEST_METHOD' ) - script_name = WSGIEnvironmentProperty( 'SCRIPT_NAME' ) + ## method = WSGIEnvironmentProperty( 'REQUEST_METHOD' ) + ## script_name = WSGIEnvironmentProperty( 'SCRIPT_NAME' ) protocol = WSGIEnvironmentProperty( 'SERVER_PROTOCOL' ) - query_string = WSGIEnvironmentProperty( 'QUERY_STRING' ) - path_info = WSGIEnvironmentProperty( 'PATH_INFO' ) - + ## query_string = WSGIEnvironmentProperty( 'QUERY_STRING' ) + ## path_info = WSGIEnvironmentProperty( 'PATH_INFO' ) + class Response( object ): """ Describes an HTTP response. Currently very simple since the actual body @@ -298,7 +298,7 @@ return "%d %s" % ( exception.code, exception.title ) else: return self.status - + # ---- Utilities ------------------------------------------------------------ CHUNK_SIZE = 2**16 diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/webapps/reports/templates/base_panels.mako --- a/lib/galaxy/webapps/reports/templates/base_panels.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/webapps/reports/templates/base_panels.mako Fri Mar 20 02:49:30 2009 -0400 @@ -31,7 +31,7 @@ <html lang="en"> <head> <title>${self.title()}</title> - <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> ${self.javascripts()} ${self.stylesheets()} </head> diff -r a5a995ca3abc -r affd3085eee3 lib/galaxy/webapps/reports/templates/masthead.mako --- a/lib/galaxy/webapps/reports/templates/masthead.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/lib/galaxy/webapps/reports/templates/masthead.mako Fri Mar 20 02:49:30 2009 -0400 @@ -2,7 +2,7 @@ <html> <head> <title>Galaxy</title> - <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <link href="${h.url_for('/static/style/masthead.css')}" rel="stylesheet" type="text/css" /> </head> diff -r a5a995ca3abc -r affd3085eee3 scripts/paster.py --- a/scripts/paster.py Thu Mar 19 21:41:06 2009 -0400 +++ b/scripts/paster.py Fri Mar 20 02:49:30 2009 -0400 @@ -7,7 +7,6 @@ import os, sys -sys.setdefaultencoding( 'utf_8' ) assert sys.version_info[:2] >= ( 2, 4 ) new_path = [ os.path.join( os.getcwd(), "lib" ) ] diff -r a5a995ca3abc -r affd3085eee3 templates/base.mako --- a/templates/base.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/base.mako Fri Mar 20 02:49:30 2009 -0400 @@ -4,7 +4,7 @@ <head> <title>a ${self.title()}</title> -<meta http-equiv="Content-Type" content="text/html; charset=${_('iso-8859-1')}" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> ${self.stylesheets()} ${self.javascripts()} </head> diff -r a5a995ca3abc -r affd3085eee3 templates/base_panels.mako --- a/templates/base_panels.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/base_panels.mako Fri Mar 20 02:49:30 2009 -0400 @@ -42,7 +42,7 @@ <html> <head> <title>${self.title()}</title> - <meta http-equiv="Content-Type" content="text/html; charset=${_('iso-8859-1')}" /> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> ${self.javascripts()} ${self.stylesheets()} </head> diff -r a5a995ca3abc -r affd3085eee3 templates/dataset/errors.tmpl --- a/templates/dataset/errors.tmpl Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/dataset/errors.tmpl Fri Mar 20 02:49:30 2009 -0400 @@ -2,7 +2,7 @@ <html> <head> <title>Dataset generation errors</title> - <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="/static/style/base.css" rel="stylesheet" type="text/css" /> <style> pre diff -r a5a995ca3abc -r affd3085eee3 templates/dataset/validation.tmpl --- a/templates/dataset/validation.tmpl Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/dataset/validation.tmpl Fri Mar 20 02:49:30 2009 -0400 @@ -3,7 +3,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="/static/style/base.css" rel="stylesheet" type="text/css" /> <script type="text/javascript" src="/static/universe.js">var dummy1=0;</script> </head> diff -r a5a995ca3abc -r affd3085eee3 templates/root/history.mako --- a/templates/root/history.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/root/history.mako Fri Mar 20 02:49:30 2009 -0400 @@ -11,7 +11,7 @@  %endif -<meta http-equiv="Content-Type" content="text/html; charset=${_('iso-8859-1')}" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <meta http-equiv="Pragma" content="no-cache"> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <link href="${h.url_for('/static/style/history.css')}" rel="stylesheet" type="text/css" /> diff -r a5a995ca3abc -r affd3085eee3 templates/root/masthead.mako --- a/templates/root/masthead.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/root/masthead.mako Fri Mar 20 02:49:30 2009 -0400 @@ -5,7 +5,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=${_('iso-8859-1')}" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <link href="${h.url_for('/static/style/masthead.css')}" rel="stylesheet" type="text/css" /> </head> diff -r a5a995ca3abc -r affd3085eee3 templates/root/tool_menu.mako --- a/templates/root/tool_menu.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/root/tool_menu.mako Fri Mar 20 02:49:30 2009 -0400 @@ -49,7 +49,7 @@ <html> <head> <title>${_('Galaxy Tools')}</title> - <meta http-equiv="Content-Type" content="text/html; charset=${_('iso-8859-1')}" /> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <link href="${h.url_for('/static/style/tool_menu.css')}" rel="stylesheet" type="text/css" /> diff -r a5a995ca3abc -r affd3085eee3 templates/tool_executed.mako --- a/templates/tool_executed.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/tool_executed.mako Fri Mar 20 02:49:30 2009 -0400 @@ -3,7 +3,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <script type="text/javascript"> var inside_galaxy_frameset = false; diff -r a5a995ca3abc -r affd3085eee3 templates/tool_form.mako --- a/templates/tool_form.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/tool_form.mako Fri Mar 20 02:49:30 2009 -0400 @@ -9,7 +9,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> <script type='text/javascript' src="${h.url_for('/static/scripts/jquery.js')}"> </script> <script type="text/javascript"> diff -r a5a995ca3abc -r affd3085eee3 templates/workflow/build_from_current_history.mako --- a/templates/workflow/build_from_current_history.mako Thu Mar 19 21:41:06 2009 -0400 +++ b/templates/workflow/build_from_current_history.mako Fri Mar 20 02:49:30 2009 -0400 @@ -6,7 +6,7 @@ <head> <title>Galaxy</title> -<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> +<meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <link href="${h.url_for('/static/style/history.css')}" rel="stylesheet" type="text/css" /> <link href="${h.url_for('/static/style/base.css')}" rel="stylesheet" type="text/css" /> diff -r a5a995ca3abc -r affd3085eee3 tools/data_source/wormbase.xml --- a/tools/data_source/wormbase.xml Thu Mar 19 21:41:06 2009 -0400 +++ b/tools/data_source/wormbase.xml Fri Mar 20 02:49:30 2009 -0400 @@ -2,7 +2,7 @@ <tool name="Wormbase" id="wormbase" tool_type="data_source" URL_method="post"> <description>server</description> <command interpreter="python">data_source.py $output</command> - <inputs action="http://www.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" method="get" target="_top"> + <inputs action="http://www.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" target="_top"> <display>go to Wormbase server $GALAXY_URL</display> <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=wormbase" /> </inputs> diff -r a5a995ca3abc -r affd3085eee3 tools/data_source/wormbase_test.xml --- a/tools/data_source/wormbase_test.xml Thu Mar 19 21:41:06 2009 -0400 +++ b/tools/data_source/wormbase_test.xml Fri Mar 20 02:49:30 2009 -0400 @@ -2,7 +2,7 @@ <tool name="Wormbase" id="wormbase_test" tool_type="data_source" URL_method="post"> <description>test server</description> <command interpreter="python">data_source.py $output</command> - <inputs action="http://dev.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" method="get" target="_top"> + <inputs action="http://dev.wormbase.org/db/seq/gbrowse/c_elegans/" check_values="false" target="_top"> <display>go to Wormbase test server $GALAXY_URL</display> <param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=wormbase_test" /> </inputs>

1 0