[galaxy-commits] commit/galaxy-central: 25 new changesets

</div><div class=3D'row'><label>Summary</label><br><input type=3D'text' cl= ass=3D'wym_summary' value=3D'' size=3D'40' /></div><div class=3D'row'><labe= l>Number Of Rows<br></label><input type=3D'text' class=3D'wym_rows' value= =3D'3' size=3D'3' /></div><div class=3D'row'><label>Number Of Cols<br></lab= el><input type=3D'text' class=3D'wym_cols' value=3D'2' size=3D'3' /></div>"= ,{Insert:function(){var o=3D$(a._options.rowsSelector).val();var r=3D$(a._o=

<p class=3D'title'>Embedded Galaxy "+j.singular+" '"+p+"'</p><p class=3D'c= ontent'> [Do not edit this bloc= k; Galaxy will fill it in with the annotated "+j.singular.toLowerCase()+" w= hen it is displayed.] </p></div></p= ";a.insert(" ");a.insert(o);$("#"+n,a._doc.body).each(function(){var = q=3Dtrue;while(q){var r=3D$(this).prev();if(r.length!=3D0&&jQuery.trim(r.te= xt())=3D=3D""){r.remove()}else{q=3Dfalse}}})});hide_modal()},Cancel:functio= n(){hide_modal()}})}})}if(i=3D=3DGalaxy.DIALOG_ANNOTATE_HISTORY){$.ajax({ur= l:list_histories_for_selection_url,data:{},error:function(){alert("Grid ref= resh failed")},success:function(k){show_modal("Insert Link to History",k,{A= nnotate:function(){var l=3Dnew Array();$("input[name=3Did]:checked").each(f= unction(){var m=3D$(this).val();$.ajax({url:get_history_annotation_table_ur= l,data:{id:m},error:function(){alert("Grid refresh failed")},success:functi= on(n){a.insert(n);init_galaxy_elts(a)}})});hide_modal()},Cancel:function(){= hide_modal()}})}})}};$(function(){$(document).ajaxError(function(i,g){var h= =3Dg.responseText||g.statusText||"Could not connect to server";show_modal("= Server error",h,{"Ignore error":hide_modal});return false});$("[name=3Dpage= _content]").wymeditor({skin:"galaxy",basePath:editor_base_path,iframeBasePa=

</tr><tr height=3D'100%'><td><div class=3D'wym_area_main' style=3D'height:= 100%;'>"+WYMeditor.IFRAME+WYMeditor.STATUS+"</div></div></td></tr></table>= ",toolsItems:[{name:"Bold",title:"Strong",css:"wym_tools_strong"},{name:"It= alic",title:"Emphasis",css:"wym_tools_emphasis"},{name:"Superscript",title:= "Superscript",css:"wym_tools_superscript"},{name:"Subscript",title:"Subscri=

</td></tr></table>",toolsItems:[{name:"Bold",title:"Strong",css:"wym_tools= _strong"},{name:"Italic",title:"Emphasis",css:"wym_tools_emphasis"},{name:"= Superscript",title:"Superscript",css:"wym_tools_superscript"},{name:"Subscr= ipt",title:"Subscript",css:"wym_tools_subscript"},{name:"InsertOrderedList"= ,title:"Ordered_List",css:"wym_tools_ordered_list"},{name:"InsertUnorderedL= ist",title:"Unordered_List",css:"wym_tools_unordered_list"},{name:"Indent",=

25 new commits in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/commits/0a37731994c9/ Changeset: 0a37731994c9 User: saketkc Date: 2013-06-19 08:51:46 Summary: Adding a small check to skip the assertion of tagNumber being an integer for VCF4.1 files. I am not sure if there are better ways or beter checks that can be implemen= ted to do this. So, this should require discussions. The description of ##INFO and ##FORMAT tag as given on [http://www.1000genomes.org/wiki/Analysis/Variant%20Call%20Format/vcf-varia= nt-call-format-version-41] is : ##INFO=3D<ID=3DID,Number=3Dnumber,Type=3Dtype,Description=3D=E2=80=9Ddescri= ption=E2=80=9D> Possible Types for INFO fields are: Integer, Float, Flag, Character, and St= ring. The Number entry is an Integer that describes the number of values that can= be included with the INFO field. For example, if the INFO field contains a single number, then this value sh= ould be 1; if the INFO field describes a pair of numbers, then this value should be 2 = and so on. If the field has one value per alternate allele then this value should be '= A'; if the field has one value for each possible genotype (more relevant to the= FORMAT tags) then this value should be 'G'. If the number of possible values varies, is unknown, or is unbounded, then = this value should be '.'. The 'Flag' type indicates that the INFO field does not contain a Value entr= y, and hence the Number should be 0 in this case. The Description value must be surrounded by double-quote= s. Double-quote character can be escaped with backslash (\") and backslash as = \\. Affected #: 1 file diff -r 81a2bb351c1a0f545a1f69b5514a29d96eb4575a -r 0a37731994c91fd59d2d31f= 79156abb58cc76d75 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/ebdaa310677b/ Changeset: ebdaa310677b User: saketkc Date: 2013-06-19 08:52:22 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 170dd4c157b8b5e010804ba4a1ef3b5da08fa49d -r ebdaa310677b57337f5fcc0= aa2ac475379bf271c tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/493bee44220a/ Changeset: 493bee44220a User: saketkc Date: 2013-06-20 05:58:14 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 36d9e5bcd2cbcd5b34b2ae0e7839a71a55350011 -r 493bee44220a54f4d0595bf= 3fd49efdf8a8795bd tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/a52434fb61a8/ Changeset: a52434fb61a8 User: saketkc Date: 2013-06-20 18:32:29 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 7362302b2c638d377931fa710d40ba2f86f25dba -r a52434fb61a8968735ed1b5= 03b6a5b2b253963ea tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/b1bb5b64dd8e/ Changeset: b1bb5b64dd8e User: saketkc Date: 2013-06-20 18:58:11 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 13b5283f964cfa7364b653f2c578b4d7cc27c6e5 -r b1bb5b64dd8eb871451b6bd= 489cc26a6c08dbb7e tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/caa8fd7a0dcf/ Changeset: caa8fd7a0dcf User: saketkc Date: 2013-06-20 19:02:55 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 89e7db1cd8098fd6191ab3b4af92e4af32e4c651 -r caa8fd7a0dcf279fec70c3d= 1581296610fc6f636 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/adb63b769897/ Changeset: adb63b769897 User: saketkc Date: 2013-06-21 07:01:54 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r cf58e35b3a973311ab291e90b501c6f4bc31b6d3 -r adb63b769897f2d2f34b935= d1a9597df6d1a9cdf tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/b092c9d9a17b/ Changeset: b092c9d9a17b User: saketkc Date: 2013-06-21 12:18:18 Summary: Automated merge with ssh://bitbucket.org/saketkc/galaxy-central Affected #: 1 file diff -r adb63b769897f2d2f34b935d1a9597df6d1a9cdf -r b092c9d9a17b448e5cb7249= 828dbcd90ab27f1f1 lib/galaxy/workflow/modules.py --- a/lib/galaxy/workflow/modules.py +++ b/lib/galaxy/workflow/modules.py @@ -246,8 +246,8 @@ return module_factory.from_dict(trans, from_json_string(st= ep.config), secure=3DFalse) module =3D Class( trans, tool_id ) module.state =3D galaxy.tools.DefaultToolState() - if step.tool_version and (step.tool_version !=3D tool.version= ): - module.version_changes.append("%s: using version '%s' inst= ead of version '%s' indicated in this workflow." % (tool_id, tool.version, = step.tool_version)) + if step.tool_version and (step.tool_version !=3D module.tool.v= ersion): + module.version_changes.append("%s: using version '%s' inst= ead of version '%s' indicated in this workflow." % (tool_id, module.tool.ve= rsion, step.tool_version)) module.state.inputs =3D module.tool.params_from_strings( step.= tool_inputs, trans.app, ignore_errors=3DTrue ) module.errors =3D step.tool_errors # module.post_job_actions =3D step.post_job_actions https://bitbucket.org/galaxy/galaxy-central/commits/46f4beebb766/ Changeset: 46f4beebb766 User: saketkc Date: 2013-06-22 12:02:56 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 4f7b7e4ca213498824d5fba7526676ddf976b823 -r 46f4beebb766fd75edb59bc= 3598342ef95775af9 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/1ff57c7a9deb/ Changeset: 1ff57c7a9deb User: saketkc Date: 2013-06-26 21:44:43 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 62 files diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/binary.py --- a/lib/galaxy/datatypes/binary.py +++ b/lib/galaxy/datatypes/binary.py @@ -267,25 +267,25 @@ # bam does not use '#' to indicate comments/headers - we need to strip= out those headers from the std. providers #TODO:?? seems like there should be an easier way to do/inherit this -= metadata.comment_char? #TODO: incorporate samtools options to control output: regions first, = then flags, etc. - @dataproviders.decorators.dataprovider_factory( 'line' ) + @dataproviders.decorators.dataprovider_factory( 'line', dataproviders.= line.FilteredLineDataProvider.settings ) def line_dataprovider( self, dataset, **settings ): samtools_source =3D dataproviders.dataset.SamtoolsDataProvider( da= taset ) settings[ 'comment_char' ] =3D '@' return dataproviders.line.FilteredLineDataProvider( samtools_sourc= e, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'regex-line' ) + @dataproviders.decorators.dataprovider_factory( 'regex-line', dataprov= iders.line.RegexLineDataProvider.settings ) def regex_line_dataprovider( self, dataset, **settings ): samtools_source =3D dataproviders.dataset.SamtoolsDataProvider( da= taset ) settings[ 'comment_char' ] =3D '@' return dataproviders.line.RegexLineDataProvider( samtools_source, = **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'column' ) + @dataproviders.decorators.dataprovider_factory( 'column', dataprovider= s.column.ColumnarDataProvider.settings ) def column_dataprovider( self, dataset, **settings ): samtools_source =3D dataproviders.dataset.SamtoolsDataProvider( da= taset ) settings[ 'comment_char' ] =3D '@' return dataproviders.column.ColumnarDataProvider( samtools_source,= **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'map' ) + @dataproviders.decorators.dataprovider_factory( 'map', dataproviders.c= olumn.MapDataProvider.settings ) def map_dataprovider( self, dataset, **settings ): samtools_source =3D dataproviders.dataset.SamtoolsDataProvider( da= taset ) settings[ 'comment_char' ] =3D '@' @@ -293,30 +293,30 @@ =20 # these can't be used directly - may need BamColumn, BamMap (Bam metad= ata -> column/map) # OR - see genomic_region_dataprovider - #@dataproviders.decorators.dataprovider_factory( 'dataset-column' ) + #@dataproviders.decorators.dataprovider_factory( 'dataset-column', dat= aproviders.column.ColumnarDataProvider.settings ) #def dataset_column_dataprovider( self, dataset, **settings ): # settings[ 'comment_char' ] =3D '@' # return super( Sam, self ).dataset_column_dataprovider( dataset, *= *settings ) =20 - #@dataproviders.decorators.dataprovider_factory( 'dataset-map' ) + #@dataproviders.decorators.dataprovider_factory( 'dataset-map', datapr= oviders.column.MapDataProvider.settings ) #def dataset_map_dataprovider( self, dataset, **settings ): # settings[ 'comment_char' ] =3D '@' # return super( Sam, self ).dataset_map_dataprovider( dataset, **se= ttings ) =20 - @dataproviders.decorators.dataprovider_factory( 'header' ) + @dataproviders.decorators.dataprovider_factory( 'header', dataprovider= s.line.RegexLineDataProvider.settings ) def header_dataprovider( self, dataset, **settings ): # in this case we can use an option of samtools view to provide ju= st what we need (w/o regex) samtools_source =3D dataproviders.dataset.SamtoolsDataProvider( da= taset, '-H' ) return dataproviders.line.RegexLineDataProvider( samtools_source, = **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'id-seq-qual' ) + @dataproviders.decorators.dataprovider_factory( 'id-seq-qual', datapro= viders.column.MapDataProvider.settings ) def id_seq_qual_dataprovider( self, dataset, **settings ): settings[ 'indeces' ] =3D [ 0, 9, 10 ] settings[ 'column_types' ] =3D [ 'str', 'str', 'str' ] settings[ 'column_names' ] =3D [ 'id', 'seq', 'qual' ] return self.map_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', data= providers.column.ColumnarDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): # GenomicRegionDataProvider currently requires a dataset as source= - may not be necc. #TODO:?? consider (at least) the possible use of a kwarg: metadata= _source (def. to source.dataset), @@ -330,7 +330,7 @@ settings[ 'column_types' ] =3D [ 'str', 'int', 'int' ] return self.column_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', = dataproviders.column.MapDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'indeces' ] =3D [ 2, 3, 3 ] settings[ 'column_types' ] =3D [ 'str', 'int', 'int' ] diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/data.py --- a/lib/galaxy/datatypes/data.py +++ b/lib/galaxy/datatypes/data.py @@ -593,7 +593,6 @@ Base dataprovider factory for all datatypes that returns the prope= r provider for the given `data_format` or raises a `NoProviderAvailable`. """ - #TODO:?? is this handling super class providers? if self.has_dataprovider( data_format ): return self.dataproviders[ data_format ]( self, dataset, **set= tings ) raise dataproviders.exceptions.NoProviderAvailable( self, data_for= mat ) @@ -603,12 +602,12 @@ dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.base.DataProvider( dataset_source, **settings= ) =20 - @dataproviders.decorators.dataprovider_factory( 'chunk' ) + @dataproviders.decorators.dataprovider_factory( 'chunk', dataproviders= .chunk.ChunkDataProvider.settings ) def chunk_dataprovider( self, dataset, **settings ): dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.chunk.ChunkDataProvider( dataset_source, **se= ttings ) =20 - @dataproviders.decorators.dataprovider_factory( 'chunk64' ) + @dataproviders.decorators.dataprovider_factory( 'chunk64', dataprovide= rs.chunk.Base64ChunkDataProvider.settings ) def chunk64_dataprovider( self, dataset, **settings ): dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.chunk.Base64ChunkDataProvider( dataset_source= , **settings ) @@ -785,7 +784,7 @@ split =3D classmethod(split) =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'line' ) + @dataproviders.decorators.dataprovider_factory( 'line', dataproviders.= line.FilteredLineDataProvider.settings ) def line_dataprovider( self, dataset, **settings ): """ Returns an iterator over the dataset's lines (that have been `stri= p`ed) @@ -794,7 +793,7 @@ dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.line.FilteredLineDataProvider( dataset_source= , **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'regex-line' ) + @dataproviders.decorators.dataprovider_factory( 'regex-line', dataprov= iders.line.RegexLineDataProvider.settings ) def regex_line_dataprovider( self, dataset, **settings ): """ Returns an iterator over the dataset's lines diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/base.py --- a/lib/galaxy/datatypes/dataproviders/base.py +++ b/lib/galaxy/datatypes/dataproviders/base.py @@ -22,8 +22,13 @@ =20 icorporate existing visualization/dataproviders some of the sources (esp. in datasets) don't need to be re-created +YAGNI: InterleavingMultiSourceDataProvider, CombiningMultiSourceDataProvid= er =20 -YAGNI: InterleavingMultiSourceDataProvider, CombiningMultiSourceDataProvid= er +datasets API entry point: + kwargs should be parsed from strings 2 layers up (in the DatasetsAPI) = - that's the 'proper' place for that. + but how would it know how/what to parse if it doesn't have access to t= he classes used in the provider? + Building a giant list by sweeping all possible dprov classes doesn= 't make sense + For now - I'm burying them in the class __init__s - but I don't like t= hat """ =20 import logging @@ -31,6 +36,31 @@ =20 =20 # ------------------------------------------------------------------------= ----- base classes +class HasSettings( type ): + """ + Metaclass for data providers that allows defining and inheriting + a dictionary named 'settings'. + + Useful for allowing class level access to expected variable types + passed to class `__init__` functions so they can be parsed from a quer= y string. + """ + # yeah - this is all too acrobatic + def __new__( cls, name, base_classes, attributes ): + settings =3D {} + # get settings defined in base classes + for base_class in base_classes: + base_settings =3D getattr( base_class, 'settings', None ) + if base_settings: + settings.update( base_settings ) + # get settings defined in this class + new_settings =3D attributes.pop( 'settings', None ) + if new_settings: + settings.update( new_settings ) + attributes[ 'settings' ] =3D settings + return type.__new__( cls, name, base_classes, attributes ) + + +# ------------------------------------------------------------------------= ----- base classes class DataProvider( object ): """ Base class for all data providers. Data providers: @@ -39,6 +69,12 @@ (c) do not allow write methods (but otherwise implement the other file object interface metho= ds) """ + # a definition of expected types for keyword arguments sent to __init__ + # useful for controlling how query string dictionaries can be parsed= into correct types for __init__ + # empty in this base class + __metaclass__ =3D HasSettings + settings =3D {} + def __init__( self, source, **kwargs ): """ :param source: the source that this iterator will loop over. @@ -130,13 +166,16 @@ - `num_valid_data_read`: how many data have been returned from `fi= lter`. - `num_data_returned`: how many data has this provider yielded. """ + # not useful here - we don't want functions over the query string + #settings.update({ 'filter_fn': 'function' }) + def __init__( self, source, filter_fn=3DNone, **kwargs ): """ :param filter_fn: a lambda or function that will be passed a datum= and return either the (optionally modified) datum or None. """ super( FilteredDataProvider, self ).__init__( source, **kwargs ) - self.filter_fn =3D filter_fn + self.filter_fn =3D filter_fn if hasattr( filter_fn, '__call__' ) e= lse None # count how many data we got from the source self.num_data_read =3D 0 # how many valid data have we gotten from the source @@ -179,6 +218,12 @@ =20 Useful for grabbing sections from a source (e.g. pagination). """ + # define the expected types of these __init__ arguments so they can be= parsed out from query strings + settings =3D { + 'limit' : 'int', + 'offset': 'int' + } + #TODO: may want to squash this into DataProvider def __init__( self, source, offset=3D0, limit=3DNone, **kwargs ): """ diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/chunk.py --- a/lib/galaxy/datatypes/dataproviders/chunk.py +++ b/lib/galaxy/datatypes/dataproviders/chunk.py @@ -26,6 +26,10 @@ """ MAX_CHUNK_SIZE =3D 2**16 DEFAULT_CHUNK_SIZE =3D MAX_CHUNK_SIZE + settings =3D { + 'chunk_index' : 'int', + 'chunk_size' : 'int' + } =20 #TODO: subclass from LimitedOffsetDataProvider? # see web/framework/base.iterate_file, util/__init__.file_reader, and = datatypes.tabular @@ -38,8 +42,8 @@ (gen. in bytes). """ super( ChunkDataProvider, self ).__init__( source, **kwargs ) - self.chunk_size =3D chunk_size - self.chunk_pos =3D chunk_index * self.chunk_size + self.chunk_size =3D int( chunk_size ) + self.chunk_pos =3D int( chunk_index ) * self.chunk_size =20 def validate_source( self, source ): """ diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/column.py --- a/lib/galaxy/datatypes/dataproviders/column.py +++ b/lib/galaxy/datatypes/dataproviders/column.py @@ -29,6 +29,14 @@ the same number of columns as the number of indeces asked for (even if= they are filled with None). """ + settings =3D { + 'indeces' : 'list:int', + 'column_count' : 'int', + 'column_types' : 'list:str', + 'parse_columns' : 'bool', + 'deliminator' : 'str' + } + def __init__( self, source, indeces=3DNone, column_count=3DNone, column_types=3DNone, parsers=3DNone, pars= e_columns=3DTrue, deliminator=3D'\t', **kwargs ): @@ -91,11 +99,11 @@ # how/whether to parse each column value self.parsers =3D {} if parse_columns: - self.parsers =3D self._get_default_parsers() + self.parsers =3D self.get_default_parsers() # overwrite with user desired parsers self.parsers.update( parsers or {} ) =20 - def _get_default_parsers( self ): + def get_default_parsers( self ): """ Return parser dictionary keyed for each columnar type (as defined in datatypes). @@ -132,7 +140,7 @@ #'gffstrand': # -, +, ?, or '.' for None, etc. } =20 - def _parse_value( self, val, type ): + def parse_value( self, val, type ): """ Attempt to parse and return the given value based on the given typ= e. =20 @@ -153,7 +161,7 @@ return None return val =20 - def _get_column_type( self, index ): + def get_column_type( self, index ): """ Get the column type for the parser from `self.column_types` or `No= ne` if the type is unavailable. @@ -165,18 +173,18 @@ except IndexError, ind_err: return None =20 - def _parse_column_at_index( self, columns, parser_index, index ): + def parse_column_at_index( self, columns, parser_index, index ): """ Get the column type for the parser from `self.column_types` or `No= ne` if the type is unavailable. """ try: - return self._parse_value( columns[ index ], self._get_column_t= ype( parser_index ) ) + return self.parse_value( columns[ index ], self.get_column_typ= e( parser_index ) ) # if a selected index is not within columns, return None except IndexError, index_err: return None =20 - def _parse_columns_from_line( self, line ): + def parse_columns_from_line( self, line ): """ Returns a list of the desired, parsed columns. :param line: the line to parse @@ -188,13 +196,13 @@ selected_indeces =3D self.selected_column_indeces or list( xrange(= len( all_columns ) ) ) parsed_columns =3D [] for parser_index, column_index in enumerate( selected_indeces ): - parsed_columns.append( self._parse_column_at_index( all_column= s, parser_index, column_index ) ) + parsed_columns.append( self.parse_column_at_index( all_columns= , parser_index, column_index ) ) return parsed_columns =20 def __iter__( self ): parent_gen =3D super( ColumnarDataProvider, self ).__iter__() for line in parent_gen: - columns =3D self._parse_columns_from_line( line ) + columns =3D self.parse_columns_from_line( line ) yield columns =20 #TODO: implement column filters here and not below - flatten hierarchy @@ -223,6 +231,10 @@ .. note: that the subclass constructors are passed kwargs - so they're params (limit, offset, etc.) are also applicable here. """ + settings =3D { + 'column_names' : 'list:str', + } + def __init__( self, source, column_names=3DNone, **kwargs ): """ :param column_names: an ordered list of strings that will be used = as the keys diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/dataset.py --- a/lib/galaxy/datatypes/dataproviders/dataset.py +++ b/lib/galaxy/datatypes/dataproviders/dataset.py @@ -141,7 +141,7 @@ """ # metadata columns are 1-based indeces column =3D getattr( self.dataset.metadata, name ) - return ( column - 1 ) if isinstance( column, int ) else None + return ( column - 1 ) if ( isinstance( column, int ) and column > = 0 ) else None =20 def get_genomic_region_indeces( self, check=3DFalse ): """ @@ -271,6 +271,12 @@ """ # dictionary keys when named_columns=3DTrue COLUMN_NAMES =3D [ 'chrom', 'start', 'end' ] + settings =3D { + 'chrom_column' : 'int', + 'start_column' : 'int', + 'end_column' : 'int', + 'named_columns' : 'bool', + } =20 def __init__( self, dataset, chrom_column=3DNone, start_column=3DNone,= end_column=3DNone, named_columns=3DFalse, **kwargs ): """ @@ -333,6 +339,14 @@ 'chrom', 'start', 'end' (and 'strand' and 'name' if available). """ COLUMN_NAMES =3D [ 'chrom', 'start', 'end', 'strand', 'name' ] + settings =3D { + 'chrom_column' : 'int', + 'start_column' : 'int', + 'end_column' : 'int', + 'strand_column' : 'int', + 'name_column' : 'int', + 'named_columns' : 'bool', + } =20 def __init__( self, dataset, chrom_column=3DNone, start_column=3DNone,= end_column=3DNone, strand_column=3DNone, name_column=3DNone, named_columns= =3DFalse, **kwargs ): @@ -349,25 +363,40 @@ dataset_source =3D DatasetDataProvider( dataset ) =20 # get genomic indeces and add strand and name + self.column_names =3D [] + indeces =3D [] + #TODO: this is sort of involved and oogly if chrom_column =3D=3D None: chrom_column =3D dataset_source.get_metadata_column_index_by_n= ame( 'chromCol' ) + if chrom_column !=3D None: + self.column_names.append( 'chrom' ) + indeces.append( chrom_column ) if start_column =3D=3D None: start_column =3D dataset_source.get_metadata_column_index_by_n= ame( 'startCol' ) + if start_column !=3D None: + self.column_names.append( 'start' ) + indeces.append( start_column ) if end_column =3D=3D None: end_column =3D dataset_source.get_metadata_column_index_by_nam= e( 'endCol' ) + if end_column !=3D None: + self.column_names.append( 'end' ) + indeces.append( end_column ) if strand_column =3D=3D None: strand_column =3D dataset_source.get_metadata_column_index_by_= name( 'strandCol' ) + if strand_column !=3D None: + self.column_names.append( 'strand' ) + indeces.append( strand_column ) if name_column =3D=3D None: name_column =3D dataset_source.get_metadata_column_index_by_na= me( 'nameCol' ) - indeces =3D [ chrom_column, start_column, end_column, strand_colum= n, name_column ] + if name_column !=3D None: + self.column_names.append( 'name' ) + indeces.append( name_column ) + kwargs.update({ 'indeces' : indeces }) - if not kwargs.get( 'column_types', None ): kwargs.update({ 'column_types' : dataset_source.get_metadata_c= olumn_types( indeces=3Dindeces ) }) =20 self.named_columns =3D named_columns - if self.named_columns: - self.column_names =3D self.COLUMN_NAMES =20 super( IntervalDataProvider, self ).__init__( dataset_source, **kw= args ) =20 @@ -390,6 +419,10 @@ sequence: <joined lines of nucleotide/amino data> } """ + settings =3D { + 'ids' : 'list:str', + } + def __init__( self, source, ids=3DNone, **kwargs ): """ :param ids: optionally return only ids (and sequences) that are in= this list. @@ -419,6 +452,10 @@ sequence: <joined lines of nucleotide/amino data> } """ + settings =3D { + 'ids' : 'list:str', + } + def __init__( self, source, ids=3DNone, **kwargs ): """ :param ids: optionally return only ids (and sequences) that are in= this list. @@ -445,6 +482,10 @@ Class that returns chrom, pos, data from a wiggle source. """ COLUMN_NAMES =3D [ 'chrom', 'pos', 'value' ] + settings =3D { + 'named_columns' : 'bool', + 'column_names' : 'list:str', + } =20 def __init__( self, source, named_columns=3DFalse, column_names=3DNone= , **kwargs ): """ @@ -483,6 +524,10 @@ Class that returns chrom, pos, data from a wiggle source. """ COLUMN_NAMES =3D [ 'chrom', 'pos', 'value' ] + settings =3D { + 'named_columns' : 'bool', + 'column_names' : 'list:str', + } =20 def __init__( self, source, chrom, start, end, named_columns=3DFalse, = column_names=3DNone, **kwargs ): """ diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/decorators.py --- a/lib/galaxy/datatypes/dataproviders/decorators.py +++ b/lib/galaxy/datatypes/dataproviders/decorators.py @@ -87,17 +87,40 @@ # log.debug( '\t\t ', fn.__doc__ ) return cls =20 -def dataprovider_factory( name ): +def dataprovider_factory( name, settings=3DNone ): """ - Wraps a class method and marks it as a dataprovider factory. + Wraps a class method and marks it as a dataprovider factory and create= s a + function to parse query strings to __init__ arguments as the + `parse_query_string_settings` attribute of the factory function. + + An example use of the `parse_query_string_settings`: + ..example:: + kwargs =3D dataset.datatype.dataproviders[ provider ].parse_query_stri= ng_settings( query_kwargs ) + return list( dataset.datatype.dataprovider( dataset, provider, **kwarg= s ) ) =20 :param name: what name/key to register the factory under in `cls.datap= roviders` - :param type: any hashable var + :type name: any hashable var + :param settings: dictionary containing key/type pairs for parsing quer= y strings + to __init__ arguments + :type settings: dictionary """ + #TODO:?? use *args for settings allowing mulitple dictionaries + # make a function available through the name->provider dispatch to par= se query strings + # callable like: + # settings_dict =3D dataproviders[ provider_name ].parse_query_string_= settings( query_kwargs ) + #TODO: ugh - overly complicated but the best I could think of + def parse_query_string_settings( query_kwargs ): + return _parse_query_string_settings( query_kwargs, settings ) + #log.debug( 'dataprovider:', name ) def named_dataprovider_factory( func ): #log.debug( 'named_dataprovider_factory:', name, '->', func.__name= __ ) setattr( func, _DATAPROVIDER_METHOD_NAME_KEY, name ) + + setattr( func, 'parse_query_string_settings', parse_query_string_s= ettings ) + setattr( func, 'settings', settings ) + #TODO: I want a way to inherit settings from the previous provider= ( this_name ) instead of defining over and over + #log.debug( '\t setting:', getattr( func, _DATAPROVIDER_METHOD_NAM= E_KEY ) ) @wraps( func ) def wrapped_dataprovider_factory( self, *args, **kwargs ): @@ -105,3 +128,38 @@ return func( self, *args, **kwargs ) return wrapped_dataprovider_factory return named_dataprovider_factory + +def _parse_query_string_settings( query_kwargs, settings=3DNone ): + """ + Parse the values in `query_kwargs` from strings to the proper types + listed in the same key in `settings`. + """ + def list_from_query_string( s ): + # assume csv + return s.split( ',' ) + + parsers =3D { + 'int' : int, + 'float' : float, + 'bool' : bool, + 'list:str' : lambda s: list_from_query_string( s ), + 'list:int' : lambda s: [ int( i ) for i in list_from_query_string= ( s ) ], + } + settings =3D settings or {} + # yay! yet another set of query string parsers! <-- sarcasm + # work through the keys in settings finding matching keys in query_kwa= rgs + # if found in both, get the expected/needed type from settings and s= tore the new parsed value + # if we can't parse it (no parser, bad value), delete the key from q= uery_kwargs so the provider will use the defaults + for key in settings: + if key in query_kwargs: + #TODO: this would be the place to sanitize any strings + query_value =3D query_kwargs[ key ] + needed_type =3D settings[ key ] + try: + query_kwargs[ key ] =3D parsers[ needed_type ]( query_valu= e ) + except ( KeyError, ValueError ): + del query_kwargs[ key ] + + #TODO:?? do we want to remove query_kwarg entries NOT in settings? + return query_kwargs + diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/dataproviders/line.py --- a/lib/galaxy/datatypes/dataproviders/line.py +++ b/lib/galaxy/datatypes/dataproviders/line.py @@ -27,6 +27,12 @@ to return. """ DEFAULT_COMMENT_CHAR =3D '#' + settings =3D { + 'string_lines' : 'bool', + 'provide_blank' : 'bool', + 'comment_char' : 'str', + } + def __init__( self, source, strip_lines=3DTrue, provide_blank=3DFalse,= comment_char=3DDEFAULT_COMMENT_CHAR, **kwargs ): """ :param strip_lines: remove whitespace from the beginning an ending @@ -78,6 +84,11 @@ .. note:: the regex matches are effectively OR'd (if **any** regex mat= ches the line it is considered valid and will be provided). """ + settings =3D { + 'regex_list' : 'list:str', + 'invert' : 'bool', + } + def __init__( self, source, regex_list=3DNone, invert=3DFalse, **kwarg= s ): """ :param regex_list: list of strings or regular expression strings t= hat will diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/interval.py --- a/lib/galaxy/datatypes/interval.py +++ b/lib/galaxy/datatypes/interval.py @@ -334,20 +334,24 @@ return None =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): return dataproviders.dataset.GenomicRegionDataProvider( dataset, *= *settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.genomic_region_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'interval' ) + @dataproviders.decorators.dataprovider_factory( 'interval', + dataproviders.dataset.= IntervalDataProvider.settings ) def interval_dataprovider( self, dataset, **settings ): return dataproviders.dataset.IntervalDataProvider( dataset, **sett= ings ) =20 - @dataproviders.decorators.dataprovider_factory( 'interval-map' ) + @dataproviders.decorators.dataprovider_factory( 'interval-map', + dataproviders.dataset.= IntervalDataProvider.settings ) def interval_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.interval_dataprovider( dataset, **settings ) @@ -809,20 +813,24 @@ =20 # ------------- Dataproviders # redefine bc super is Tabular - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): return dataproviders.dataset.GenomicRegionDataProvider( dataset, 0= , 3, 4, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.genomic_region_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'interval' ) + @dataproviders.decorators.dataprovider_factory( 'interval', + dataproviders.dataset.= IntervalDataProvider.settings ) def interval_dataprovider( self, dataset, **settings ): return dataproviders.dataset.IntervalDataProvider( dataset, 0, 3, = 4, 6, 2, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'interval-map' ) + @dataproviders.decorators.dataprovider_factory( 'interval-map', + dataproviders.dataset.= IntervalDataProvider.settings ) def interval_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.interval_dataprovider( dataset, **settings ) @@ -1193,12 +1201,12 @@ return resolution =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'wiggle' ) + @dataproviders.decorators.dataprovider_factory( 'wiggle', dataprovider= s.dataset.WiggleDataProvider.settings ) def wiggle_dataprovider( self, dataset, **settings ): dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.dataset.WiggleDataProvider( dataset_source, *= *settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'wiggle-map' ) + @dataproviders.decorators.dataprovider_factory( 'wiggle-map', dataprov= iders.dataset.WiggleDataProvider.settings ) def wiggle_map_dataprovider( self, dataset, **settings ): dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) settings[ 'named_columns' ] =3D True diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/sequence.py --- a/lib/galaxy/datatypes/sequence.py +++ b/lib/galaxy/datatypes/sequence.py @@ -15,8 +15,6 @@ from galaxy import util from sniff import * =20 -from galaxy.datatypes import dataproviders - import pkg_resources pkg_resources.require("simplejson") import simplejson @@ -399,15 +397,6 @@ f.close() _count_split =3D classmethod(_count_split) =20 - def provider( self, dataset, data_format, **settings ): - from galaxy.dataproviders import dataset as dataset_providers - - if data_format =3D=3D 'id_seq': - source =3D dataset_providers.DatasetDataProvider( dataset ) - return dataset_providers.FastaDataProvider( source, **settings= ) - - return super( Fasta, self ).provider( dataset, data_format, **sett= ings ) - =20 class csFasta( Sequence ): """ Class representing the SOLID Color-Space sequence ( csfasta ) """ diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/sniff.py --- a/lib/galaxy/datatypes/sniff.py +++ b/lib/galaxy/datatypes/sniff.py @@ -6,6 +6,7 @@ from galaxy import util from galaxy.datatypes.checkers import * from encodings import search_function as encodings_search_function +from binary import Binary =20 log =3D logging.getLogger(__name__) =20 diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/datatypes/tabular.py --- a/lib/galaxy/datatypes/tabular.py +++ b/lib/galaxy/datatypes/tabular.py @@ -345,26 +345,25 @@ return vizs =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'column' ) + @dataproviders.decorators.dataprovider_factory( 'column', dataprovider= s.column.ColumnarDataProvider.settings ) def column_dataprovider( self, dataset, **settings ): """Uses column settings that are passed in""" - print 'Tabular.comment_char:', settings.get( 'comment_char', None ) - dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.column.ColumnarDataProvider( dataset_source, = **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'dataset-column' ) + @dataproviders.decorators.dataprovider_factory( 'dataset-column', + dataproviders.column.C= olumnarDataProvider.settings ) def dataset_column_dataprovider( self, dataset, **settings ): """Attempts to get column settings from dataset.metadata""" return dataproviders.dataset.DatasetColumnarDataProvider( dataset,= **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'map' ) + @dataproviders.decorators.dataprovider_factory( 'map', dataproviders.c= olumn.MapDataProvider.settings ) def map_dataprovider( self, dataset, **settings ): """Uses column settings that are passed in""" dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) return dataproviders.column.MapDataProvider( dataset_source, **set= tings ) =20 - @dataproviders.decorators.dataprovider_factory( 'dataset-map' ) + @dataproviders.decorators.dataprovider_factory( 'dataset-map', datapro= viders.column.MapDataProvider.settings ) def dataset_map_dataprovider( self, dataset, **settings ): """Attempts to get column settings from dataset.metadata""" return dataproviders.dataset.DatasetMapDataProvider( dataset, **se= ttings ) @@ -502,55 +501,58 @@ # ------------- Dataproviders # sam does not use '#' to indicate comments/headers - we need to strip= out those headers from the std. providers #TODO:?? seems like there should be an easier way to do this - metadat= a.comment_char? - @dataproviders.decorators.dataprovider_factory( 'line' ) + @dataproviders.decorators.dataprovider_factory( 'line', dataproviders.= line.FilteredLineDataProvider.settings ) def line_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).line_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'regex-line' ) + @dataproviders.decorators.dataprovider_factory( 'regex-line', dataprov= iders.line.RegexLineDataProvider.settings ) def regex_line_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).regex_line_dataprovider( dataset, **sett= ings ) =20 - @dataproviders.decorators.dataprovider_factory( 'column' ) + @dataproviders.decorators.dataprovider_factory( 'column', dataprovider= s.column.ColumnarDataProvider.settings ) def column_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).column_dataprovider( dataset, **settings= ) =20 - @dataproviders.decorators.dataprovider_factory( 'dataset-column' ) + @dataproviders.decorators.dataprovider_factory( 'dataset-column', + dataproviders.column.C= olumnarDataProvider.settings ) def dataset_column_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).dataset_column_dataprovider( dataset, **= settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'map' ) + @dataproviders.decorators.dataprovider_factory( 'map', dataproviders.c= olumn.MapDataProvider.settings ) def map_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).map_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'dataset-map' ) + @dataproviders.decorators.dataprovider_factory( 'dataset-map', datapro= viders.column.MapDataProvider.settings ) def dataset_map_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return super( Sam, self ).dataset_map_dataprovider( dataset, **set= tings ) =20 - @dataproviders.decorators.dataprovider_factory( 'header' ) + @dataproviders.decorators.dataprovider_factory( 'header', dataprovider= s.line.RegexLineDataProvider.settings ) def header_dataprovider( self, dataset, **settings ): dataset_source =3D dataproviders.dataset.DatasetDataProvider( data= set ) headers_source =3D dataproviders.line.RegexLineDataProvider( datas= et_source, regex_list=3D[ '^@' ] ) return dataproviders.line.RegexLineDataProvider( headers_source, *= *settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'id-seq-qual' ) + @dataproviders.decorators.dataprovider_factory( 'id-seq-qual', map_dat= aprovider.settings ) def id_seq_qual_dataprovider( self, dataset, **settings ): # provided as an example of a specified column map (w/o metadata) settings[ 'indeces' ] =3D [ 0, 9, 10 ] settings[ 'column_names' ] =3D [ 'id', 'seq', 'qual' ] return self.map_dataprovider( dataset, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return dataproviders.dataset.GenomicRegionDataProvider( dataset, 2= , 3, 3, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'comment_char' ] =3D '@' return dataproviders.dataset.GenomicRegionDataProvider( dataset, 2= , 3, 3, True, **settings ) @@ -621,11 +623,13 @@ return False =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): return dataproviders.dataset.GenomicRegionDataProvider( dataset, *= *settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.genomic_region_dataprovider( dataset, **settings ) @@ -668,11 +672,13 @@ dataset.metadata.sample_names =3D line.split()[ 9: ] =20 # ------------- Dataproviders - @dataproviders.decorators.dataprovider_factory( 'genomic-region' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_dataprovider( self, dataset, **settings ): return dataproviders.dataset.GenomicRegionDataProvider( dataset, 0= , 1, 1, **settings ) =20 - @dataproviders.decorators.dataprovider_factory( 'genomic-region-map' ) + @dataproviders.decorators.dataprovider_factory( 'genomic-region-map', + dataproviders.dataset.= GenomicRegionDataProvider.settings ) def genomic_region_map_dataprovider( self, dataset, **settings ): settings[ 'named_columns' ] =3D True return self.genomic_region_dataprovider( dataset, **settings ) diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/visualization/data_providers/registry.py --- a/lib/galaxy/visualization/data_providers/registry.py +++ b/lib/galaxy/visualization/data_providers/registry.py @@ -32,7 +32,7 @@ "bigwig": genome.BigWigDataProvider, "bigbed": genome.BigBedDataProvider, =20 - "column": ColumnDataProvider + "column_with_stats": ColumnDataProvider } =20 def get_data_provider( self, trans, name=3DNone, source=3D'data', raw= =3DFalse, original_dataset=3DNone ): diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/visualization/registry.py --- a/lib/galaxy/visualization/registry.py +++ b/lib/galaxy/visualization/registry.py @@ -15,22 +15,27 @@ log =3D logging.getLogger( __name__ ) =20 __TODO__ =3D """ - BUGS: - anon users clicking a viz link gets 'must be' msg in galaxy_main (= w/ masthead) - should not show visualizations (no icon)? - newick files aren't being sniffed prop? - datatype is txt +BUGS: + anon users clicking a viz link gets 'must be' msg in galaxy_main (w/ m= asthead) + should not show visualizations (no icon)? + newick files aren't being sniffed prop? - datatype is txt =20 - have parsers create objects instead of dicts - allow data_sources with no model_class but have tests (isAdmin, etc.) - maybe that's an instance of User model_class? - some confused vocabulary in docs, var names - tests: - anding, grouping, not - data_sources: - lists of - add description element to visualization. +have parsers create objects instead of dicts +allow data_sources with no model_class but have tests (isAdmin, etc.) + maybe that's an instance of User model_class? +some confused vocabulary in docs, var names +tests: + anding, grouping, not +data_sources: + lists of +add description element to visualization. + +TESTS to add: + has dataprovider + user is admin """ =20 +# ------------------------------------------------------------------- the = registry class VisualizationsRegistry( object ): """ Main responsibilities are: @@ -93,6 +98,45 @@ """ self.listings =3D VisualizationsConfigParser.parse( self.configura= tion_filepath ) =20 + def get_visualization( self, trans, visualization_name, target_object = ): + """ + Return data to build a url to the visualization with the given + `visualization_name` if it's applicable to `target_object` or + `None` if it's not. + """ + # a little weird to pass trans because this registry is part of th= e trans.app + listing_data =3D self.listings.get( visualization_name, None ) + if not listing_data: + return None + + data_sources =3D listing_data[ 'data_sources' ] + for data_source in data_sources: + # currently a model class is required + model_class =3D data_source[ 'model_class' ] + if not isinstance( target_object, model_class ): + continue + + # tests are optional - default is the above class test + tests =3D data_source[ 'tests' ] + if tests and not self.is_object_applicable( trans, target_obje= ct, tests ): + continue + + param_data =3D data_source[ 'to_params' ] + url =3D self.get_visualization_url( trans, target_object, visu= alization_name, param_data ) + link_text =3D listing_data.get( 'link_text', None ) + if not link_text: + # default to visualization name, titlecase, and replace un= derscores + link_text =3D visualization_name.title().replace( '_', ' '= ) + render_location =3D listing_data.get( 'render_location' ) + # remap some of these vars for direct use in ui.js, PopupMenu = (e.g. text->html) + return { + 'href' : url, + 'html' : link_text, + 'target': render_location + } + + return None + # -- building links to visualizations from objects -- def get_visualizations( self, trans, target_object ): """ @@ -100,36 +144,11 @@ the urls to call in order to render the visualizations. """ #TODO:?? a list of objects? YAGNI? - # a little weird to pass trans because this registry is part of th= e trans.app applicable_visualizations =3D [] - for vis_name, listing_data in self.listings.items(): - - data_sources =3D listing_data[ 'data_sources' ] - for data_source in data_sources: - # currently a model class is required - model_class =3D data_source[ 'model_class' ] - if not isinstance( target_object, model_class ): - continue - - # tests are optional - default is the above class test - tests =3D data_source[ 'tests' ] - if tests and not self.is_object_applicable( trans, target_= object, tests ): - continue - - param_data =3D data_source[ 'to_params' ] - url =3D self.get_visualization_url( trans, target_object, = vis_name, param_data ) - link_text =3D listing_data.get( 'link_text', None ) - if not link_text: - # default to visualization name, titlecase, and replac= e underscores - link_text =3D vis_name.title().replace( '_', ' ' ) - render_location =3D listing_data.get( 'render_location' ) - # remap some of these vars for direct use in ui.js, PopupM= enu (e.g. text->html) - applicable_visualizations.append({ - 'href' : url, - 'html' : link_text, - 'target': render_location - }) - + for vis_name in self.listings: + url_data =3D self.get_visualization( trans, vis_name, target_o= bject ) + if url_data: + applicable_visualizations.append( url_data ) return applicable_visualizations =20 def is_object_applicable( self, trans, target_object, data_source_test= s ): @@ -151,10 +170,11 @@ # convert datatypes to their actual classes (for use w= ith isinstance) test_result =3D trans.app.datatypes_registry.get_datat= ype_class_by_name( test_result ) if not test_result: - # warn if can't find class, but continue + # warn if can't find class, but continue (with oth= er tests) log.warn( 'visualizations_registry cannot find cla= ss (%s) for applicability test', test_result ) continue =20 + #NOTE: tests are OR'd, if any test passes - the visualization = can be applied if test_fn( target_object, test_result ): #log.debug( 'test passed' ) return True diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/webapps/galaxy/api/datasets.py --- a/lib/galaxy/webapps/galaxy/api/datasets.py +++ b/lib/galaxy/webapps/galaxy/api/datasets.py @@ -6,6 +6,7 @@ from galaxy.web.base.controller import BaseAPIController, UsesVisualizatio= nMixin, UsesHistoryDatasetAssociationMixin from galaxy.web.base.controller import UsesHistoryMixin from galaxy.web.framework.helpers import is_true +from galaxy.datatypes import dataproviders =20 import logging log =3D logging.getLogger( __name__ ) @@ -217,10 +218,24 @@ return msg =20 registry =3D trans.app.data_provider_registry + # allow the caller to specifiy which provider is used - if provider and provider in registry.dataset_type_name_to_data_pro= vider: - data_provider =3D registry.dataset_type_name_to_data_provider[= provider ]( dataset ) - # or have it look up by datatype + # pulling from the original providers if possible, then the new = providers + if provider: + if provider in registry.dataset_type_name_to_data_provider: + data_provider =3D registry.dataset_type_name_to_data_provi= der[ provider ]( dataset ) + + elif dataset.datatype.has_dataprovider( provider ): + kwargs =3D dataset.datatype.dataproviders[ provider ].pars= e_query_string_settings( kwargs ) + # use dictionary to allow more than the data itself to be = returned (data totals, other meta, etc.) + return { + 'data': list( dataset.datatype.dataprovider( dataset, = provider, **kwargs ) ) + } + + else: + raise dataproviders.exceptions.NoProviderAvailable( datase= t.datatype, provider ) + + # no provider name: look up by datatype else: data_provider =3D registry.get_data_provider( trans, raw=3DTru= e, original_dataset=3Ddataset ) =20 diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/webapps/galaxy/api/tool_shed_repositories.py --- a/lib/galaxy/webapps/galaxy/api/tool_shed_repositories.py +++ b/lib/galaxy/webapps/galaxy/api/tool_shed_repositories.py @@ -179,6 +179,11 @@ # Get the information about the Galaxy components (e.g., tool pane= section, tool config file, etc) that will contain the repository informati= on. install_repository_dependencies =3D payload.get( 'install_reposito= ry_dependencies', False ) install_tool_dependencies =3D payload.get( 'install_tool_dependenc= ies', False ) + if install_tool_dependencies: + if trans.app.config.tool_dependency_dir is None: + no_tool_dependency_dir_message =3D "Tool dependencies can = be automatically installed only if you set the value of your 'tool_dependen= cy_dir' " + no_tool_dependency_dir_message +=3D "setting in your Galax= y configuration file (universe_wsgi.ini) and restart your Galaxy server." + raise HTTPBadRequest( detail=3Dno_tool_dependency_dir_mess= age ) new_tool_panel_section =3D payload.get( 'new_tool_panel_section_la= bel', '' ) shed_tool_conf =3D payload.get( 'shed_tool_conf', None ) if shed_tool_conf: @@ -211,13 +216,8 @@ tool_path=3Dtool_path, tool_shed_url=3Dtool_shed_url ) # Create the tool_shed_repository database records and gather addi= tional information for repository installation. - created_or_updated_tool_shed_repositories, tool_panel_section_keys= , repo_info_dicts, filtered_repo_info_dicts, message =3D \ + created_or_updated_tool_shed_repositories, tool_panel_section_keys= , repo_info_dicts, filtered_repo_info_dicts =3D \ repository_util.handle_tool_shed_repositories( trans, installa= tion_dict, using_api=3DTrue ) - if message and len( repo_info_dicts ) =3D=3D 1: - # We're attempting to install a single repository that has alr= eady been installed into this Galaxy instance. - log.error( message, exc_info=3DTrue ) - trans.response.status =3D 500 - return dict( status=3D'error', error=3Dmessage ) if created_or_updated_tool_shed_repositories: # Build the dictionary of information necessary for installing= the repositories. installation_dict =3D dict( created_or_updated_tool_shed_repos= itories=3Dcreated_or_updated_tool_shed_repositories, @@ -266,11 +266,7 @@ acti= on=3D'show', id= =3Dtrans.security.encode_id( tool_shed_repository.id ) ) installed_tool_shed_repositories.append( tool_shed_rep= ository_dict ) - elif message: - log.error( message, exc_info=3DTrue ) - trans.response.status =3D 500 - return dict( status=3D'error', error=3Dmessage ) - elif not created_or_updated_tool_shed_repositories and not message: + else: # We're attempting to install more than 1 repository, and all = of them have already been installed. return dict( status=3D'error', error=3D'All repositories that = you are attempting to install have been previously installed.' ) # Display the list of installed repositories. diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/galaxy/webapps/galaxy/controllers/admin_toolshed.py --- a/lib/galaxy/webapps/galaxy/controllers/admin_toolshed.py +++ b/lib/galaxy/webapps/galaxy/controllers/admin_toolshed.py @@ -155,7 +155,8 @@ def browse_tool_dependency( self, trans, **kwd ): message =3D kwd.get( 'message', '' ) status =3D kwd.get( 'status', 'done' ) - tool_dependency =3D tool_dependency_util.get_tool_dependency( tran= s, kwd[ 'id' ] ) + tool_dependency_ids =3D tool_dependency_util.get_tool_dependency_i= ds( as_string=3DFalse, **kwd ) + tool_dependency =3D tool_dependency_util.get_tool_dependency( tran= s, tool_dependency_ids[ 0 ] ) if tool_dependency.in_error_state: message =3D "This tool dependency is not installed correctly (= see the <b>Tool dependency installation error</b> below). " message +=3D "Choose <b>Uninstall this tool dependency</b> fro= m the <b>Repository Actions</b> menu, correct problems " @@ -482,9 +483,7 @@ def install_tool_dependencies( self, trans, **kwd ): message =3D kwd.get( 'message', '' ) status =3D kwd.get( 'status', 'done' ) - tool_dependency_ids =3D util.listify( kwd.get( 'tool_dependency_id= s', None ) ) - if not tool_dependency_ids: - tool_dependency_ids =3D util.listify( kwd.get( 'id', None ) ) + tool_dependency_ids =3D tool_dependency_util.get_tool_dependency_i= ds( as_string=3DFalse, **kwd ) tool_dependencies =3D [] for tool_dependency_id in tool_dependency_ids: tool_dependency =3D tool_dependency_util.get_tool_dependency( = trans, tool_dependency_id ) @@ -731,11 +730,11 @@ kwd[ 'status' ] =3D 'error' installed_tool_dependencies_select_field =3D suc.build_tool_depend= encies_select_field( trans, = tool_shed_repository=3Dtool_shed_repository, - = name=3D'tool_dependency_ids', + = name=3D'inst_td_ids', = uninstalled=3DFalse ) uninstalled_tool_dependencies_select_field =3D suc.build_tool_depe= ndencies_select_field( trans, = tool_shed_repository=3Dtool_shed_repository, - = name=3D'tool_dependency_ids', + = name=3D'uninstalled_tool_dependency_ids', = uninstalled=3DTrue ) return trans.fill_template( '/admin/tool_shed_repository/manage_re= pository_tool_dependencies.mako', repository=3Dtool_shed_repository, @@ -886,15 +885,8 @@ tool_panel_section=3Dtool_panel_sect= ion, tool_path=3Dtool_path, tool_shed_url=3Dtool_shed_url ) - created_or_updated_tool_shed_repositories, tool_panel_section_= keys, repo_info_dicts, filtered_repo_info_dicts, message =3D \ + created_or_updated_tool_shed_repositories, tool_panel_section_= keys, repo_info_dicts, filtered_repo_info_dicts =3D \ repository_util.handle_tool_shed_repositories( trans, inst= allation_dict, using_api=3DFalse ) - if message and len( repo_info_dicts ) =3D=3D 1: - # We're undoubtedly attempting to install a repository tha= t has been previously installed. - return trans.response.send_redirect( web.url_for( controll= er=3D'admin_toolshed', - action= =3D'browse_repositories', - message= =3Dmessage, - status= =3D'error' ) ) - if created_or_updated_tool_shed_repositories: installation_dict =3D dict( created_or_updated_tool_shed_r= epositories=3Dcreated_or_updated_tool_shed_repositories, filtered_repo_info_dicts=3Dfilte= red_repo_info_dicts, @@ -1128,7 +1120,7 @@ reposi= tory_dependencies=3Drepository_dependencies ) repo_info_dicts.append( repo_info_dict ) # Make sure all tool_shed_repository records exist. - created_or_updated_tool_shed_repositories, tool_panel_section_keys= , repo_info_dicts, filtered_repo_info_dicts, message =3D \ + created_or_updated_tool_shed_repositories, tool_panel_section_keys= , repo_info_dicts, filtered_repo_info_dicts =3D \ repository_dependency_util.create_repository_dependency_object= s( trans=3Dtrans, = tool_path=3Dtool_path, = tool_shed_url=3Dtool_shed_url, @@ -1175,6 +1167,18 @@ initiate_repository_installation_ids= =3Dencoded_repository_ids, reinstalling=3DTrue ) =20 + @web.expose + @web.require_admin + def repair_repository( self, trans, **kwd ): + """ + Inspect the repository dependency hierarchy for a specified reposi= tory and attempt to make sure they are all properly installed as well as + each repository's tool dependencies. + """ + message =3D kwd.get( 'message', '' ) + status =3D kwd.get( 'status', 'done' ) + repository_id =3D kwd[ 'id' ] + tool_shed_repository =3D suc.get_installed_tool_shed_repository( t= rans, repository_id ) + @web.json def repository_installation_status_updates( self, trans, ids=3DNone, s= tatus_list=3DNone ): # Avoid caching @@ -1517,7 +1521,7 @@ def uninstall_tool_dependencies( self, trans, **kwd ): message =3D kwd.get( 'message', '' ) status =3D kwd.get( 'status', 'done' ) - tool_dependency_ids =3D util.listify( kwd.get( 'tool_dependency_id= s', None ) ) + tool_dependency_ids =3D tool_dependency_util.get_tool_dependency_i= ds( as_string=3DFalse, **kwd ) if not tool_dependency_ids: tool_dependency_ids =3D util.listify( kwd.get( 'id', None ) ) tool_dependencies =3D [] diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/galaxy_install/repository_util.py --- a/lib/tool_shed/galaxy_install/repository_util.py +++ b/lib/tool_shed/galaxy_install/repository_util.py @@ -358,7 +358,7 @@ tool_panel_section =3D installation_dict[ 'tool_panel_section' ] tool_path =3D installation_dict[ 'tool_path' ] tool_shed_url =3D installation_dict[ 'tool_shed_url' ] - created_or_updated_tool_shed_repositories, tool_panel_section_keys, re= po_info_dicts, filtered_repo_info_dicts, message =3D \ + created_or_updated_tool_shed_repositories, tool_panel_section_keys, re= po_info_dicts, filtered_repo_info_dicts =3D \ repository_dependency_util.create_repository_dependency_objects( t= rans=3Dtrans, t= ool_path=3Dtool_path, t= ool_shed_url=3Dtool_shed_url, @@ -368,11 +368,7 @@ n= o_changes_checked=3Dno_changes_checked, t= ool_panel_section=3Dtool_panel_section, n= ew_tool_panel_section=3Dnew_tool_panel_section ) - if message and len( repo_info_dicts ) =3D=3D 1 and not using_api: - installed_tool_shed_repository =3D created_or_updated_tool_shed_re= positories[ 0 ] - message +=3D 'Click <a href=3D"%s">here</a> to manage the reposito= ry. ' % \ - ( web.url_for( controller=3D'admin_toolshed', action=3D'manage= _repository', id=3Dtrans.security.encode_id( installed_tool_shed_repository= .id ) ) ) - return created_or_updated_tool_shed_repositories, tool_panel_section_k= eys, repo_info_dicts, filtered_repo_info_dicts, message + return created_or_updated_tool_shed_repositories, tool_panel_section_k= eys, repo_info_dicts, filtered_repo_info_dicts =20 def initiate_repository_installation( trans, installation_dict ): # The following installation_dict entries are all required. diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/galaxy_install/tool_dependencies/common_uti= l.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/common_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/common_util.py @@ -216,7 +216,7 @@ return os.path.abspath( file_path ) raise ValueError( 'Could not find path to file %s' % os.path.abspath( = os.path.join( file_path, file_name ) ) ) =20 -def url_download( install_dir, downloaded_file_name, download_url ): +def url_download( install_dir, downloaded_file_name, download_url, extract= =3DTrue ): file_path =3D os.path.join( install_dir, downloaded_file_name ) src =3D None dst =3D None @@ -236,7 +236,22 @@ src.close() if dst: dst.close() - return os.path.abspath( file_path ) + if extract: + if istar( file_path ): + # <action type=3D"download_by_url">http://sourceforge.net/proj= ects/samtools/files/samtools/0.1.18/samtools-0.1.18.tar.bz2</action> + extract_tar( file_path, install_dir ) + dir =3D tar_extraction_directory( install_dir, downloaded_file= _name ) + elif isjar( file_path ): + dir =3D os.path.curdir + elif iszip( file_path ): + # <action type=3D"download_by_url">http://downloads.sourceforg= e.net/project/picard/picard-tools/1.56/picard-tools-1.56.zip</action> + zip_archive_extracted =3D extract_zip( file_path, install_dir ) + dir =3D zip_extraction_directory( install_dir, downloaded_file= _name ) + else: + dir =3D install_dir + else: + dir =3D install_dir + return dir =20 def zip_extraction_directory( file_path, file_name ): """Try to return the correct extraction directory.""" diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/galaxy_install/tool_dependencies/fabric_uti= l.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/fabric_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/fabric_util.py @@ -180,19 +180,7 @@ downloaded_filename =3D action_dict[ 'target_filen= ame' ] else: downloaded_filename =3D os.path.split( url )[ -1 ] - downloaded_file_path =3D common_util.url_download( wor= k_dir, downloaded_filename, url ) - if common_util.istar( downloaded_file_path ): - # <action type=3D"download_by_url">http://sourcefo= rge.net/projects/samtools/files/samtools/0.1.18/samtools-0.1.18.tar.bz2</ac= tion> - common_util.extract_tar( downloaded_file_path, wor= k_dir ) - dir =3D common_util.tar_extraction_directory( work= _dir, downloaded_filename ) - elif common_util.isjar( downloaded_file_path ): - dir =3D os.path.curdir - elif common_util.iszip( downloaded_file_path ): - # <action type=3D"download_by_url">http://download= s.sourceforge.net/project/picard/picard-tools/1.56/picard-tools-1.56.zip</a= ction> - zip_archive_extracted =3D common_util.extract_zip(= downloaded_file_path, work_dir ) - dir =3D common_util.zip_extraction_directory( work= _dir, downloaded_filename ) - else: - dir =3D os.path.curdir + dir =3D common_util.url_download( work_dir, downloaded= _filename, url, extract=3DTrue ) elif action_type =3D=3D 'shell_command': # <action type=3D"shell_command">git clone --recursive= git://github.com/ekg/freebayes.git</action> # Eliminate the shell_command clone action so remainin= g actions can be processed correctly. @@ -206,7 +194,7 @@ # Download a single file to the working directory. filtered_actions =3D actions[ 1: ] url =3D action_dict[ 'url' ] - if action_dict[ 'target_filename' ]: + if 'target_filename' in action_dict: # Sometimes compressed archives extracts their con= tent to a folder other than the default defined file name. Using this # attribute will ensure that the file name is set = appropriately and can be located after download, decompression and extracti= on. filename =3D action_dict[ 'target_filename' ] @@ -227,10 +215,10 @@ if not os.path.exists( full_path_to_dir ): os.makedirs( full_path_to_dir ) # The package has been down-loaded, so we can now perform = all of the actions defined for building it. - with lcd( dir ): - for action_tup in filtered_actions: + for action_tup in filtered_actions: + current_dir =3D os.path.abspath( os.path.join( work_di= r, dir ) ) + with lcd( current_dir ): action_type, action_dict =3D action_tup - current_dir =3D os.path.abspath( os.path.join( wor= k_dir, dir ) ) if action_type =3D=3D 'make_directory': common_util.make_directory( full_path=3Daction= _dict[ 'full_path' ] ) elif action_type =3D=3D 'move_directory_files': @@ -316,13 +304,20 @@ if return_code: return elif action_type =3D=3D 'download_file': - # Download a single file to the current direct= ory. + # Download a single file to the current workin= g directory. url =3D action_dict[ 'url' ] - if action_dict[ 'target_filename' ]: + if 'target_filename' in action_dict: filename =3D action_dict[ 'target_filename= ' ] else: filename =3D url.split( '/' )[ -1 ] - common_util.url_download( current_dir, filenam= e, url ) + extract =3D action_dict.get( 'extract', False ) + common_util.url_download( current_dir, filenam= e, url, extract=3Dextract ) + elif action_type =3D=3D 'change_directory': + target_directory =3D os.path.realpath( os.path= .join( current_dir, action_dict[ 'directory' ] ) ) + if target_directory.startswith( os.path.realpa= th( current_dir ) ) and os.path.exists( target_directory ): + dir =3D target_directory + else: + log.error( 'Invalid or nonexistent directo= ry %s specified, ignoring change_directory action.', target_directory ) =20 def log_results( command, fabric_AttributeString, file_path ): """ diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/galaxy_install/tool_dependencies/install_ut= il.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/install_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/install_util.py @@ -13,6 +13,7 @@ from tool_shed.util import xml_util from galaxy.model.orm import and_ from galaxy.web import url_for +from galaxy.util import asbool =20 log =3D logging.getLogger( __name__ ) =20 @@ -390,15 +391,19 @@ # <action type=3D"download_by_url">http://sourceforge.net/proj= ects/samtools/files/samtools/0.1.18/samtools-0.1.18.tar.bz2</action> if action_elem.text: action_dict[ 'url' ] =3D action_elem.text - if 'target_filename' in action_elem.attrib: - action_dict[ 'target_filename' ] =3D action_elem.attri= b[ 'target_filename' ] + target_filename =3D action_elem.get( 'target_filename', No= ne ) + if target_filename: + action_dict[ 'target_filename' ] =3D target_filename else: continue elif action_type =3D=3D 'download_file': # <action type=3D"download_file">http://effectors.org/download= /version/TTSS_GUI-1.0.1.jar</action> if action_elem.text: action_dict[ 'url' ] =3D action_elem.text - action_dict[ 'target_filename' ] =3D action_elem.attrib.ge= t( 'target_filename', None ) + target_filename =3D action_elem.get( 'target_filename', No= ne ) + if target_filename: + action_dict[ 'target_filename' ] =3D target_filename + action_dict[ 'extract' ] =3D asbool( action_elem.get( 'ext= ract', False ) ) else: continue elif action_type =3D=3D 'make_directory': @@ -407,6 +412,12 @@ action_dict[ 'full_path' ] =3D evaluate_template( action_e= lem.text ) else: continue + elif action_type =3D=3D 'change_directory': + # <action type=3D"change_directory">PHYLIP-3.6b</action> + if action_elem.text: + action_dict[ 'directory' ] =3D action_elem.text + else: + continue elif action_type in [ 'move_directory_files', 'move_file' ]: # <action type=3D"move_file"> # <source>misc/some_file</source> diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/util/repository_dependency_util.py --- a/lib/tool_shed/util/repository_dependency_util.py +++ b/lib/tool_shed/util/repository_dependency_util.py @@ -103,7 +103,6 @@ the dependency relationships between installed repositories. This met= hod is called when new repositories are being installed into a Galaxy instance and when uninstalled repositories are being reinstalled. """ - message =3D '' # The following list will be maintained within this method to contain = all created or updated tool shed repositories, including repository depende= ncies # that may not be installed. all_created_or_updated_tool_shed_repositories =3D [] @@ -241,7 +240,7 @@ filtered_repo_info_dicts.append( repo_info_dict ) # Build repository dependency relationships even if the user chose to = not install repository dependencies. build_repository_dependency_relationships( trans, all_repo_info_dicts,= all_created_or_updated_tool_shed_repositories ) - return created_or_updated_tool_shed_repositories, tool_panel_section_k= eys, all_repo_info_dicts, filtered_repo_info_dicts, message + return created_or_updated_tool_shed_repositories, tool_panel_section_k= eys, all_repo_info_dicts, filtered_repo_info_dicts =20 def generate_message_for_invalid_repository_dependencies( metadata_dict ): """Return the error message associated with an invalid repository depe= ndency for display in the caller.""" diff -r 46f4beebb766fd75edb59bc3598342ef95775af9 -r 1ff57c7a9debe0ced8bd216= a33789218190f1f47 lib/tool_shed/util/tool_dependency_util.py --- a/lib/tool_shed/util/tool_dependency_util.py +++ b/lib/tool_shed/util/tool_dependency_util.py @@ -220,9 +220,16 @@ =20 def get_tool_dependency_ids( as_string=3DFalse, **kwd ): tool_dependency_id =3D kwd.get( 'tool_dependency_id', None ) - tool_dependency_ids =3D util.listify( kwd.get( 'tool_dependency_ids', = None ) ) - if not tool_dependency_ids: - tool_dependency_ids =3D util.listify( kwd.get( 'id', None ) ) + if 'tool_dependency_ids' in kwd: + tool_dependency_ids =3D util.listify( kwd[ 'tool_dependency_ids' ]= ) + elif 'id' in kwd: + tool_dependency_ids =3D util.listify( kwd[ 'id' ] ) + elif 'inst_td_ids' in kwd: + tool_dependency_ids =3D util.listify( kwd[ 'inst_td_ids' ] ) + elif 'uninstalled_tool_dependency_ids' in kwd: + tool_dependency_ids =3D util.listify( kwd[ 'uninstalled_tool_depen= dency_ids' ] ) + else: + tool_dependency_ids =3D [] if tool_dependency_id and tool_dependency_id not in tool_dependency_id= s: tool_dependency_ids.append( tool_dependency_id ) if as_string: This diff is so big that we needed to truncate the remainder. https://bitbucket.org/galaxy/galaxy-central/commits/f1e5dfbbea46/ Changeset: f1e5dfbbea46 User: saketkc Date: 2013-06-27 06:35:20 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 3fa9df444b4b81f94b1c42a033c685a6e23827be -r f1e5dfbbea46f0957ce4849= 4996444eb61f4a818 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/7e13235ae59a/ Changeset: 7e13235ae59a User: saketkc Date: 2013-06-28 07:00:22 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r b89b721a0b3db47cdeddef35f03ce4c2ffcb47b5 -r 7e13235ae59a1fb5eaa795c= 0797b4afa38001a38 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/8a88c559d596/ Changeset: 8a88c559d596 User: saketkc Date: 2013-06-29 11:41:22 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 019ad31c3c2502005846dadc5c0457bbb6f80712 -r 8a88c559d5961d41c630b8e= 2dd1dafe6f275b9b2 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/13dc3f5865da/ Changeset: 13dc3f5865da User: saketkc Date: 2013-07-01 22:14:34 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 2cabbf3687634090fbbc024726f15f43db4ff314 -r 13dc3f5865da864c3823b31= df455b5f6f1acb9f3 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/868bfd34f465/ Changeset: 868bfd34f465 User: saketkc Date: 2013-07-09 10:41:15 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 86efa5ac1fae6fb46e7af9804e036a7ab44b0e26 -r 868bfd34f465dc1b6176d02= fce93baecf3129279 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/f8c0c28b902e/ Changeset: f8c0c28b902e User: saketkc Date: 2013-07-10 21:30:38 Summary: vcfclass change merged Affected #: 1 file diff -r 4cc057df762c219406af27dd04ac725a07a5a6eb -r f8c0c28b902ecad5821ece5= 5030a9e7d02f779cf tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/4ff5c8a3ff34/ Changeset: 4ff5c8a3ff34 User: saketkc Date: 2013-07-24 20:59:58 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r b42dfe74e237ea7f9c77059e427db92d9859bc67 -r 4ff5c8a3ff347824b430c99= 3303f2d97d907e2ed tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/28bad82d523b/ Changeset: 28bad82d523b User: saketkc Date: 2013-07-25 15:07:54 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 2abd0819d354d3d11182297c7206408d299f0d16 -r 28bad82d523b2053fa69c70= 301de69a74e57f323 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/a360e1b7b506/ Changeset: a360e1b7b506 User: saketkc Date: 2013-07-31 15:48:50 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 951e853b0bcd2c62cedee0b95d46c9e36ab6c605 -r a360e1b7b506450385be74b= 2c6b7762d3e794bbd tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/79ae7df72fba/ Changeset: 79ae7df72fba User: saketkc Date: 2013-08-02 19:20:58 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 24 files diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c .hgignore --- a/.hgignore +++ b/.hgignore @@ -85,6 +85,7 @@ .coverage htmlcov run_unit_tests.html +test/unit/**.log =20 # Project files *.kpf diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/datatypes/binary.py --- a/lib/galaxy/datatypes/binary.py +++ b/lib/galaxy/datatypes/binary.py @@ -475,6 +475,9 @@ =20 def sniff(self, filename): try: + # All twobit files start with a 16-byte header. If the file is= smaller than 16 bytes, it's obviously not a valid twobit file. + if os.path.getsize(filename) < 16: + return False input =3D file(filename) magic =3D struct.unpack(">L", input.read(TWOBIT_MAGIC_SIZE))[0] if magic =3D=3D TWOBIT_MAGIC_NUMBER or magic =3D=3D TWOBIT_MAG= IC_NUMBER_SWAP: diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/tools/parameters/basic.py --- a/lib/galaxy/tools/parameters/basic.py +++ b/lib/galaxy/tools/parameters/basic.py @@ -1514,8 +1514,8 @@ NOTE: This is wasteful since dynamic options and dataset collection happens twice (here and when generating HTML).=20 """ - # Can't look at history in workflow mode - if trans is None or trans.workflow_building_mode: + # Can't look at history in workflow mode. Tool shed has no histori= es. + if trans is None or trans.workflow_building_mode or trans.webapp.n= ame =3D=3D 'tool_shed': return DummyDataset() assert trans is not None, "DataToolParameter requires a trans" history =3D trans.get_history() diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/visualization/data_providers/genome.py --- a/lib/galaxy/visualization/data_providers/genome.py +++ b/lib/galaxy/visualization/data_providers/genome.py @@ -13,6 +13,7 @@ from galaxy.util.json import from_json_string from bx.interval_index_file import Indexes from bx.bbi.bigwig_file import BigWigFile +from bx.bbi.bigbed_file import BigBedFile from galaxy.util.lrucache import LRUCache from galaxy.visualization.data_providers.basic import BaseDataProvider from galaxy.visualization.data_providers.cigar import get_ref_based_read_s= eq_and_cigar @@ -861,14 +862,14 @@ """ Returns an iterator that provides data in the region chrom:start-e= nd """ - start, end =3D int(start), int(end) + start, end =3D int( start ), int( end ) orig_data_filename =3D self.original_dataset.file_name index_filename =3D self.converted_dataset.file_name =20 # Attempt to open the BAM file with index bamfile =3D csamtools.Samfile( filename=3Dorig_data_filename, mode= =3D'rb', index_filename=3Dindex_filename ) try: - data =3D bamfile.fetch(start=3Dstart, end=3Dend, reference=3Dc= hrom) + data =3D bamfile.fetch( start=3Dstart, end=3Dend, reference=3D= chrom ) except ValueError, e: # Try alternative chrom naming. chrom =3D _convert_between_ucsc_and_ensemble_naming( chrom ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/webapps/galaxy/api/histories.py --- a/lib/galaxy/webapps/galaxy/api/histories.py +++ b/lib/galaxy/webapps/galaxy/api/histories.py @@ -1,5 +1,7 @@ """ API operations on a history. + +.. seealso:: :class:`galaxy.model.History` """ =20 import pkg_resources @@ -21,17 +23,28 @@ @web.expose_api_anonymous def index( self, trans, deleted=3D'False', **kwd ): """ - GET /api/histories - GET /api/histories/deleted - Displays a collection (list) of histories. + index( trans, deleted=3D'False' ) + * GET /api/histories: + return undeleted histories for the current user + * GET /api/histories/deleted: + return deleted histories for the current user + .. note:: Anonymous users are allowed to get their current history + + :type deleted: boolean + :param deleted: if True, show only deleted histories, if False, n= on-deleted + + :rtype: list + :returns: list of dictionaries containing summary history inform= ation """ #TODO: query (by name, date, etc.) rval =3D [] deleted =3D string_as_bool( deleted ) try: if trans.user: - query =3D trans.sa_session.query(trans.app.model.History )= .filter_by( user=3Dtrans.user, deleted=3Ddeleted ).order_by( - desc(trans.app.model.History.table.c.update_time)).all= () + query =3D ( trans.sa_session.query( trans.app.model.Histor= y ) + .filter_by( user=3Dtrans.user, deleted=3Ddelet= ed ) + .order_by( desc( trans.app.model.History.table= .c.update_time ) ) + .all() ) for history in query: item =3D history.get_api_value(value_mapper=3D{'id':tr= ans.security.encode_id}) item['url'] =3D url_for( 'history', id=3Dtrans.securit= y.encode_id( history.id ) ) @@ -52,11 +65,25 @@ =20 @web.expose_api_anonymous def show( self, trans, id, deleted=3D'False', **kwd ): + # oh, sphinx - you bastard """ - GET /api/histories/{encoded_history_id} - GET /api/histories/deleted/{encoded_history_id} - GET /api/histories/most_recently_used - Displays information about a history. + show( trans, id, deleted=3D'False' ) + * GET /api/histories/{id}: + return the history with ``id`` + * GET /api/histories/deleted/{id}: + return the deleted history with ``id`` + * GET /api/histories/most_recently_used: + return the most recently used history + .. note:: Anonymous users are allowed to get their current history + + :type id: an encoded id string + :param id: the encoded id of the history to query or the str= ing 'most_recently_used' + :type deleted: boolean + :param deleted: if True, allow information on a deleted history t= o be shown. + + :rtype: dictionary + :returns: detailed history information from + :func:`galaxy.web.base.controller.UsesHistoryDatasetAssociatio= nMixin.get_history_dict` """ #TODO: GET /api/histories/{encoded_history_id}?as_archive=3DTrue #TODO: GET /api/histories/s/{username}/{slug} @@ -94,8 +121,16 @@ @web.expose_api def create( self, trans, payload, **kwd ): """ - POST /api/histories - Creates a new history. + create( trans, payload ) + * POST /api/histories: + create a new history + + :type payload: dict + :param payload: (optional) dictionary structure containing: + * name: the new history's name + =20 + :rtype: dict + :returns: element view of new history """ hist_name =3D None if payload.get( 'name', None ): @@ -115,8 +150,24 @@ @web.expose_api def delete( self, trans, id, **kwd ): """ - DELETE /api/histories/{encoded_history_id} - Deletes a history + delete( self, trans, id, **kwd ) + * DELETE /api/histories/{id} + delete the history with the given ``id`` + .. note:: Currently does not stop any active jobs in the history. + + :type id: str + :param id: the encoded id of the history to delete + :type kwd: dict + :param kwd: (optional) dictionary structure containing: + =20 + * payload: a dictionary itself containing: + * purge: if True, purge the history and all of it's HDAs + + :rtype: dict + :returns: an error object if an error occurred or a dictionary c= ontaining: + * id: the encoded id of the history, + * deleted: if the history was marked as deleted, + * purged: if the history was purged """ history_id =3D id # a request body is optional here @@ -175,8 +226,15 @@ @web.expose_api def undelete( self, trans, id, **kwd ): """ - POST /api/histories/deleted/{encoded_history_id}/undelete - Undeletes a history + undelete( self, trans, id, **kwd ) + * POST /api/histories/deleted/{id}/undelete: + undelete history (that hasn't been purged) with the given ``id= `` + + :type id: str + :param id: the encoded id of the history to undelete + + :rtype: str + :returns: 'OK' if the history was undeleted """ history_id =3D id history =3D self.get_history( trans, history_id, check_ownership= =3DTrue, check_accessible=3DFalse, deleted=3DTrue ) @@ -188,8 +246,21 @@ @web.expose_api def update( self, trans, id, payload, **kwd ): """ - PUT /api/histories/{encoded_history_id} - Changes an existing history. + update( self, trans, id, payload, **kwd ) + * PUT /api/histories/{id} + updates the values for the history with the given ``id`` + + :type id: str + :param id: the encoded id of the history to undelete + :type payload: dict + :param payload: a dictionary containing any or all the + fields in :func:`galaxy.model.History.get_api_value` and/or th= e following: + =20 + * annotation: an annotation for the history + + :rtype: dict + :returns: an error object if an error occurred or a dictionary c= ontaining + any values that were different from the original and, therefor= e, updated """ #TODO: PUT /api/histories/{encoded_history_id} payload =3D { ratin= g: rating } (w/ no security checks) try: @@ -255,6 +326,6 @@ raise ValueError( 'annotation must be a string or unic= ode: %s' %( str( type( val ) ) ) ) validated_payload[ 'annotation' ] =3D sanitize_html( val, = 'utf-8' ) elif key not in valid_but_uneditable_keys: - raise AttributeError( 'unknown key: %s' %( str( key ) ) ) + pass + #log.warn( 'unknown key: %s', str( key ) ) return validated_payload - diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/webapps/galaxy/api/history_contents.py --- a/lib/galaxy/webapps/galaxy/api/history_contents.py +++ b/lib/galaxy/webapps/galaxy/api/history_contents.py @@ -15,21 +15,27 @@ @web.expose_api_anonymous def index( self, trans, history_id, ids=3DNone, **kwd ): """ - GET /api/histories/{encoded_history_id}/contents - Displays a collection (list) of history contents (HDAs) + index( self, trans, history_id, ids=3DNone, **kwd ) + * GET /api/histories/{history_id}/contents + return a list of HDA data for the history with the given ``id`` + .. note:: Anonymous users are allowed to get their current history= contents =20 - :param history_id: an encoded id string of the `History` to search - :param ids: (optional) a comma separated list of encoded `HDA` ids - - If Ids is not given, index returns a list of *summary* json object= s for - every `HDA` associated with the given `history_id`. - See _summary_hda_dict. + If Ids is not given, index returns a list of *summary* objects for + every HDA associated with the given `history_id`. =20 If ids is given, index returns a *more complete* json object for e= ach HDA in the ids list. =20 - Note: Anonymous users are allowed to get their current history con= tents - (generally useful for browser UI access of the api) + :type history_id: str + :param history_id: encoded id string of the HDA's History + :type ids: str + :param ids: (optional) a comma separated list of encoded `= HDA` ids + + :rtype: list + :returns: dictionaries containing summary or detailed HDA inform= ation + .. seealso:: + :func:`_summary_hda_dict` and + :func:`galaxy.web.base.controller.UsesHistoryDatasetAssociatio= nMixin.get_hda_dict` """ rval =3D [] try: @@ -78,13 +84,13 @@ #TODO: move to model or Mixin def _summary_hda_dict( self, trans, history_id, hda ): """ - Returns a dictionary based on the HDA in .. _summary form:: - { - 'id' : < the encoded dataset id >, - 'name' : < currently only returns 'file' >, - 'type' : < name of the dataset >, - 'url' : < api url to retrieve this datasets full data >, - } + Returns a dictionary based on the HDA in summary form:: + { + 'id' : < the encoded dataset id >, + 'name' : < currently only returns 'file' >, + 'type' : < name of the dataset >, + 'url' : < api url to retrieve this datasets full data >, + } """ api_type =3D "file" encoded_id =3D trans.security.encode_id( hda.id ) @@ -98,8 +104,19 @@ @web.expose_api_anonymous def show( self, trans, id, history_id, **kwd ): """ - GET /api/histories/{encoded_history_id}/contents/{encoded_content_= id} - Displays information about a history content (dataset). + show( self, trans, id, history_id, **kwd ) + * GET /api/histories/{history_id}/contents/{id} + return detailed information about an HDA within a history + .. note:: Anonymous users are allowed to get their current history= contents + + :type id: str + :param ids: the encoded id of the HDA to return + :type history_id: str + :param history_id: encoded id string of the HDA's History + + :rtype: dict + :returns: dictionary containing detailed HDA information + .. seealso:: :func:`galaxy.web.base.controller.UsesHistoryDatasetA= ssociationMixin.get_hda_dict` """ hda_dict =3D {} try: @@ -135,8 +152,18 @@ @web.expose_api def create( self, trans, history_id, payload, **kwd ): """ - POST /api/histories/{encoded_history_id}/contents - Creates a new history content item (file, aka HistoryDatasetAssoci= ation). + create( self, trans, history_id, payload, **kwd ) + * POST /api/histories/{history_id}/contents + create a new HDA by copying an accessible LibraryDataset + + :type history_id: str + :param history_id: encoded id string of the new HDA's History + :type payload: dict + :param payload: dictionary structure containing:: + 'from_ld_id': the encoded id of the LibraryDataset to copy + + :rtype: dict + :returns: dictionary containing detailed information for the new= HDA """ #TODO: copy existing, accessible hda - dataset controller, copy_da= tasets #TODO: convert existing, accessible hda - model.DatasetInstance(or= hda.datatype).get_converter_types @@ -173,8 +200,24 @@ @web.expose_api def update( self, trans, history_id, id, payload, **kwd ): """ - PUT /api/histories/{encoded_history_id}/contents/{encoded_content_= id} - Changes an existing history dataset. + update( self, trans, history_id, id, payload, **kwd ) + * PUT /api/histories/{history_id}/contents/{id} + updates the values for the HDA with the given ``id`` + + :type history_id: str + :param history_id: encoded id string of the HDA's History + :type id: str + :param id: the encoded id of the history to undelete + :type payload: dict + :param payload: a dictionary containing any or all the + fields in :func:`galaxy.model.HistoryDatasetAssociation.get_ap= i_value` + and/or the following: + + * annotation: an annotation for the HDA + + :rtype: dict + :returns: an error object if an error occurred or a dictionary c= ontaining + any values that were different from the original and, therefor= e, updated """ #TODO: PUT /api/histories/{encoded_history_id} payload =3D { ratin= g: rating } (w/ no security checks) changed =3D {} @@ -251,6 +294,7 @@ raise ValueError( 'misc_info must be a string or unico= de: %s' %( str( type( val ) ) ) ) validated_payload[ 'info' ] =3D util.sanitize_html.sanitiz= e_html( val, 'utf-8' ) elif key not in valid_but_uneditable_keys: - raise AttributeError( 'unknown key: %s' %( str( key ) ) ) + pass + #log.warn( 'unknown key: %s', str( key ) ) return validated_payload =20 diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/webapps/galaxy/api/libraries.py --- a/lib/galaxy/webapps/galaxy/api/libraries.py +++ b/lib/galaxy/webapps/galaxy/api/libraries.py @@ -15,9 +15,18 @@ @web.expose_api def index( self, trans, deleted=3D'False', **kwd ): """ - GET /api/libraries - GET /api/libraries/deleted - Displays a collection (list) of libraries. + index( self, trans, deleted=3D'False', **kwd ) + * GET /api/libraries: + returns a list of summary data for libraries + * GET /api/libraries/deleted: + returns a list of summary data for deleted libraries + + :type deleted: boolean + :param deleted: if True, show only deleted libraries, if False, n= on-deleted + + :rtype: list + :returns: list of dictionaries containing library information + .. seealso:: :attr:`galaxy.model.Library.api_collection_visible_ke= ys` """ log.debug( "LibrariesController.index: enter" ) query =3D trans.sa_session.query( trans.app.model.Library ) @@ -49,9 +58,20 @@ @web.expose_api def show( self, trans, id, deleted=3D'False', **kwd ): """ - GET /api/libraries/{encoded_library_id} - GET /api/libraries/deleted/{encoded_library_id} - Displays information about a library. + show( self, trans, id, deleted=3D'False', **kwd ) + * GET /api/libraries/{id}: + returns detailed information about a library + * GET /api/libraries/deleted/{id}: + returns detailed information about a deleted library + + :type id: an encoded id string + :param id: the encoded id of the library + :type deleted: boolean + :param deleted: if True, allow information on a deleted library + + :rtype: dictionary + :returns: detailed library information + .. seealso:: :attr:`galaxy.model.Library.api_element_visible_keys` """ log.debug( "LibraryContentsController.show: enter" ) library_id =3D id @@ -75,8 +95,20 @@ @web.expose_api def create( self, trans, payload, **kwd ): """ - POST /api/libraries - Creates a new library. + create( self, trans, payload, **kwd ) + * POST /api/libraries: + create a new library + .. note:: Currently, only admin users can create libraries. + + :type payload: dict + :param payload: (optional) dictionary structure containing:: + 'name': the new library's name + 'description': the new library's description + 'synopsis': the new library's synopsis + + :rtype: dict + :returns: a dictionary containing the id, name, and 'show' url + of the new library """ if not trans.user_is_admin(): raise HTTPForbidden( detail=3D'You are not authorized to creat= e a new library.' ) @@ -102,6 +134,19 @@ =20 @web.expose_api def delete( self, trans, id, **kwd ): + """ + delete( self, trans, id, **kwd ) + * DELETE /api/histories/{id} + mark the library with the given ``id`` as deleted + .. note:: Currently, only admin users can delete libraries. + + :type id: str + :param id: the encoded id of the library to delete + + :rtype: dictionary + :returns: detailed library information + .. seealso:: :attr:`galaxy.model.Library.api_element_visible_keys` + """ if not trans.user_is_admin(): raise HTTPForbidden( detail=3D'You are not authorized to delet= e libraries.' ) try: diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/galaxy/webapps/galaxy/api/library_contents.py --- a/lib/galaxy/webapps/galaxy/api/library_contents.py +++ b/lib/galaxy/webapps/galaxy/api/library_contents.py @@ -19,8 +19,21 @@ # TODO: Add parameter to only get top level of datasets/subfolders. def index( self, trans, library_id, **kwd ): """ - GET /api/libraries/{encoded_library_id}/contents - Displays a collection (list) of library contents (files and folder= s). + index( self, trans, library_id, **kwd ) + * GET /api/libraries/{library_id}/contents: + return a list of library files and folders + + :type library_id: str + :param library_id: encoded id string of the library that contains= this item + + :rtype: list + :returns: list of dictionaries of the form: + + * id: the encoded id of the library item + * name: the 'libary path' + or relationship of the library item to the root + * type: 'file' or 'folder' + * url: the url to get detailed information on the library item """ rval =3D [] current_user_roles =3D trans.get_current_user_roles() @@ -80,8 +93,20 @@ @web.expose_api def show( self, trans, id, library_id, **kwd ): """ - GET /api/libraries/{encoded_library_id}/contents/{encoded_content_= id} - Displays information about a library content (file or folder). + show( self, trans, id, library_id, **kwd ) + * GET /api/libraries/{library_id}/contents/{id} + return information about library file or folder + + :type id: str + :param id: the encoded id of the library item to return + :type library_id: str + :param library_id: encoded id string of the library that contains= this item + + :rtype: dict + :returns: detailed library item information + .. seealso:: + :func:`galaxy.model.LibraryDataset.get_api_value` and + :attr:`galaxy.model.LibraryFolder.api_element_visible_keys` """ class_name, content_id =3D self.__decode_library_content_id( trans= , id ) if class_name =3D=3D 'LibraryFolder': @@ -93,8 +118,29 @@ @web.expose_api def create( self, trans, library_id, payload, **kwd ): """ - POST /api/libraries/{encoded_library_id}/contents - Creates a new library content item (file or folder). + create( self, trans, library_id, payload, **kwd ) + * POST /api/libraries/{library_id}/contents: + create a new library file or folder + + To copy an HDA into a library send ``create_type`` of 'file' and + the HDA's encoded id in ``from_hda_id`` (and optionally ``ldda_mes= sage``). + + :type library_id: str + :param library_id: encoded id string of the library that contains= this item + :type payload: dict + :param payload: dictionary structure containing: + =20 + * folder_id: the parent folder of the new item + * create_type: the type of item to create ('file' or 'folder') + * from_hda_id: (optional) the id of an accessible HDA to copy= into the + library + * ldda_message: (optional) the new message attribute of the LD= DA created + * extended_metadata: (optional) dub-dictionary containing any = extended + metadata to associate with the item + + :rtype: dict + :returns: a dictionary containing the id, name, + and 'show' url of the new item """ create_type =3D None if 'create_type' not in payload: @@ -195,10 +241,10 @@ =20 def _copy_hda_to_library_folder( self, trans, from_hda_id, library_id,= folder_id, ldda_message=3D'' ): """ - Copies hda `from_hda_id` to library folder `library_folder_id` opt= ionally - adding `ldda_message` to the new ldda's `message`. + Copies hda ``from_hda_id`` to library folder ``library_folder_id``= optionally + adding ``ldda_message`` to the new ldda's ``message``. =20 - `library_contents.create` will branch to this if called with 'from= _hda_id' + ``library_contents.create`` will branch to this if called with 'fr= om_hda_id' in it's payload. """ log.debug( '_copy_hda_to_library_folder: %s' %( str(( from_hda_id,= library_id, folder_id, ldda_message )) ) ) @@ -236,10 +282,23 @@ return rval =20 @web.expose_api - def update( self, trans, id, library_id, payload, **kwd ): + def update( self, trans, id, library_id, payload, **kwd ): """ - PUT /api/libraries/{encoded_library_id}/contents/{encoded_content_= type_and_id} - Sets relationships among items + update( self, trans, id, library_id, payload, **kwd ) + * PUT /api/libraries/{library_id}/contents/{id} + create a ImplicitlyConvertedDatasetAssociation + .. seealso:: :class:`galaxy.model.ImplicitlyConvertedDatasetAssoci= ation` + + :type id: str + :param id: the encoded id of the library item to return + :type library_id: str + :param library_id: encoded id string of the library that contains= this item + :type payload: dict + :param payload: dictionary structure containing:: + 'converted_dataset_id': + + :rtype: None + :returns: None """ if 'converted_dataset_id' in payload: converted_id =3D payload.pop( 'converted_dataset_id' ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/tool_shed/galaxy_install/tool_dependencies/common_uti= l.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/common_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/common_util.py @@ -8,6 +8,7 @@ import zipfile import tool_shed.util.shed_util_common as suc from galaxy.datatypes import checkers +from urllib2 import HTTPError =20 log =3D logging.getLogger( __name__ ) =20 @@ -70,6 +71,23 @@ __shellquote(env_shell_file_path= )) return cmd =20 +def download_binary_from_url( url, work_dir, install_dir ): + ''' + Download a pre-compiled binary from the specified URL. If the download= ed file is an archive, + extract it into install_dir and delete the archive. + ''' + downloaded_filename =3D os.path.split( url )[ -1 ] + try: + dir =3D url_download( work_dir, downloaded_filename, url, extract= =3DTrue ) + downloaded_filepath =3D os.path.join( work_dir, downloaded_filenam= e ) + if is_compressed( downloaded_filepath ): + os.remove( downloaded_filepath ) + move_directory_files( current_dir=3Dwork_dir, + source_dir=3Ddir, + destination_dir=3Dinstall_dir ) + return True + except HTTPError: + return False =20 def extract_tar( file_name, file_path ): if isgzip( file_name ) or isbz2( file_name ): @@ -190,6 +208,12 @@ def iszip( file_path ): return checkers.check_zip( file_path ) =20 +def is_compressed( file_path ): + if isjar( file_path ): + return False + else: + return iszip( file_path ) or isgzip( file_path ) or istar( file_pa= th ) or isbz2( file_path ) + def make_directory( full_path ): if not os.path.exists( full_path ): os.makedirs( full_path ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/tool_shed/galaxy_install/tool_dependencies/fabric_uti= l.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/fabric_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/fabric_util.py @@ -165,12 +165,29 @@ actions =3D actions_dict.get( 'actions', None ) filtered_actions =3D [] env_shell_file_paths =3D [] + # Default to false so that the install process will default to compili= ng. + binary_found =3D False if actions: with make_tmp_dir() as work_dir: with lcd( work_dir ): # The first action in the list of actions will be the one = that defines the installation process. There # are currently only two supported processes; download_by_= url and clone via a "shell_command" action type. action_type, action_dict =3D actions[ 0 ] + if action_type =3D=3D 'download_binary': + # Eliminate the download_binary action so remaining ac= tions can be processed correctly. + filtered_actions =3D actions[ 1: ] + url =3D action_dict[ 'url' ] + # Attempt to download a binary from the specified URL. + log.debug( 'Attempting to download from %s', url ) + binary_found =3D common_util.download_binary_from_url(= url, work_dir, install_dir ) + if binary_found: + # If the attempt succeeded, set the action_type to= binary_found, in order to skip any download_by_url or shell_command action= s. + actions =3D filtered_actions + action_type =3D 'binary_found' + else: + # No binary exists, or there was an error download= ing the binary from the generated URL. Proceed with the remaining actions. + del actions[ 0 ] + action_type, action_dict =3D actions[ 0 ] if action_type =3D=3D 'download_by_url': # Eliminate the download_by_url action so remaining ac= tions can be processed correctly. filtered_actions =3D actions[ 1: ] @@ -220,6 +237,9 @@ current_dir =3D os.path.abspath( os.path.join( work_di= r, dir ) ) with lcd( current_dir ): action_type, action_dict =3D action_tup + # If a binary was found, we only need to process e= nvironment variables, file permissions, and any other binary downloads. + if binary_found and action_type not in [ 'set_envi= ronment', 'chmod', 'download_binary' ]: + continue if action_type =3D=3D 'make_directory': common_util.make_directory( full_path=3Daction= _dict[ 'full_path' ] ) elif action_type =3D=3D 'move_directory_files': @@ -348,6 +368,18 @@ dir =3D target_directory.replace( os.path.= realpath( work_dir ), '' ).lstrip( '/' ) else: log.error( 'Invalid or nonexistent directo= ry %s specified, ignoring change_directory action.', target_directory ) + elif action_type =3D=3D 'chmod': + for target_file, mode in action_dict[ 'change_= modes' ]: + if os.path.exists( target_file ): + os.chmod( target_file, mode ) + elif action_type =3D=3D 'download_binary': + url =3D action_dict[ 'url' ] + binary_found =3D common_util.download_binary_f= rom_url( url, work_dir, install_dir ) + if binary_found: + log.debug( 'Successfully downloaded binary= from %s', url ) + else: + log.error( 'Unable to download binary from= %s', url ) + =20 =20 def log_results( command, fabric_AttributeString, file_path ): """ diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/tool_shed/galaxy_install/tool_dependencies/install_ut= il.py --- a/lib/tool_shed/galaxy_install/tool_dependencies/install_util.py +++ b/lib/tool_shed/galaxy_install/tool_dependencies/install_util.py @@ -1,6 +1,7 @@ import logging import os import sys +import stat import subprocess import tempfile from string import Template @@ -379,7 +380,22 @@ for action_elem in actions_elem.findall( 'action' ): action_dict =3D {} action_type =3D action_elem.get( 'type', 'shell_command' ) - if action_type =3D=3D 'shell_command': + if action_type =3D=3D 'download_binary': + platform_info_dict =3D tool_dependency_util.get_platform_info_= dict() + platform_info_dict[ 'name' ] =3D tool_dependency.name + platform_info_dict[ 'version' ] =3D tool_dependency.version + url_template_elems =3D action_elem.findall( 'url_template' ) + # Check if there are multiple url_template elements, each with= attrib entries for a specific platform. + if len( url_template_elems ) > 1: + # <base_url os=3D"darwin" extract=3D"false">http://hgdownl= oad.cse.ucsc.edu/admin/exe/macOSX.${architecture}/faToTwoBit</base_url> + # This method returns the url_elem that best matches the c= urrent platform as received from os.uname(). + # Currently checked attributes are os and architecture. + # These correspond to the values sysname and processor fro= m the Python documentation for os.uname(). + url_template_elem =3D tool_dependency_util.get_download_ur= l_for_platform( url_template_elems, platform_info_dict ) + else: + url_template_elem =3D url_template_elems[ 0 ] + action_dict[ 'url' ] =3D Template( url_template_elem.text ).sa= fe_substitute( platform_info_dict ) + elif action_type =3D=3D 'shell_command': # <action type=3D"shell_command">make</action> action_elem_text =3D evaluate_template( action_elem.text ) if action_elem_text: @@ -492,6 +508,27 @@ # lxml=3D=3D2.3.0</action> ## Manually specify contents of requirements.txt file to creat= e dynamically. action_dict[ 'requirements' ] =3D evaluate_template( action_el= em.text or 'requirements.txt' ) + elif action_type =3D=3D 'chmod': + # Change the read, write, and execute bits on a file. + file_elems =3D action_elem.findall( 'file' ) + chmod_actions =3D [] + # A unix octal mode is the sum of the following values: + # Owner: + # 400 Read 200 Write 100 Execute + # Group: + # 040 Read 020 Write 010 Execute + # World: + # 004 Read 002 Write 001 Execute + for file_elem in file_elems: + # So by the above table, owner read/write/execute and grou= p read permission would be 740. + # Python's os.chmod uses base 10 modes, convert received u= nix-style octal modes to base 10. + received_mode =3D int( file_elem.get( 'mode', 600 ), base= =3D8 ) + # For added security, ensure that the setuid and setgid bi= ts are not set. + mode =3D received_mode & ~( stat.S_ISUID | stat.S_ISGID ) + file =3D evaluate_template( file_elem.text ) + chmod_tuple =3D ( file, mode ) + chmod_actions.append( chmod_tuple ) + action_dict[ 'change_modes' ] =3D chmod_actions else: log.debug( "Unsupported action type '%s'. Not proceeding." % s= tr( action_type ) ) raise Exception( "Unsupported action type '%s' in tool depende= ncy definition." % str( action_type ) ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c lib/tool_shed/util/tool_dependency_util.py --- a/lib/tool_shed/util/tool_dependency_util.py +++ b/lib/tool_shed/util/tool_dependency_util.py @@ -39,6 +39,37 @@ tool_dependencies[ dependency_key ] =3D requirements_dict return tool_dependencies =20 +def get_download_url_for_platform( url_templates, platform_info_dict ): + ''' + Compare the dict returned by get_platform_info() with the values speci= fied in the base_url element. Return + true if and only if all defined attributes match the corresponding dic= t entries. If an entry is not + defined in the base_url element, it is assumed to be irrelevant at thi= s stage. For example, + <base_url os=3D"darwin">http://hgdownload.cse.ucsc.edu/admin/exe/macOS= X.${architecture}/faToTwoBit</base_url> + where the OS must be 'darwin', but the architecture is filled in later= using string.Template. + ''' + os_ok =3D False + architecture_ok =3D False + for url_template in url_templates: + os_name =3D url_template.get( 'os', None ) + architecture =3D url_template.get( 'architecture', None ) + if os_name: + if os_name.lower() =3D=3D platform_info_dict[ 'os' ]: + os_ok =3D True + else: + os_ok =3D False + else: + os_ok =3D True + if architecture: + if architecture.lower() =3D=3D platform_info_dict[ 'architectu= re' ]: + architecture_ok =3D True + else: + architecture_ok =3D False + else: + architecture_ok =3D True + if os_ok and architecture_ok: + return url_template + return None + def create_or_update_tool_dependency( app, tool_shed_repository, name, ver= sion, type, status, set_status=3DTrue ): # Called from Galaxy (never the tool shed) when a new repository is be= ing installed or when an uninstalled repository is being reinstalled. sa_session =3D app.model.context.current @@ -204,6 +235,14 @@ missing_tool_dependencies =3D None return tool_dependencies, missing_tool_dependencies =20 +def get_platform_info_dict(): + '''Return a dict with information about the current platform.''' + platform_dict =3D {} + sysname, nodename, release, version, machine =3D os.uname() + platform_dict[ 'os' ] =3D sysname.lower() + platform_dict[ 'architecture' ] =3D machine.lower() + return platform_dict + def get_tool_dependency( trans, id ): """Get a tool_dependency from the database via id""" return trans.sa_session.query( trans.model.ToolDependency ).get( trans= .security.decode_id( id ) ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c static/scripts/galaxy.pages.js --- a/static/scripts/galaxy.pages.js +++ b/static/scripts/galaxy.pages.js @@ -164,18 +164,19 @@ { "Make link": function() { // Get URL, name/title. - var sUrl =3D $(wym._options.hrefSelector).val(), - sName =3D $(".wym_title").val(); + var sUrl =3D $(wym._options.hrefSelector).val() || '', + sId =3D $(".wym_id").val() || '', + sName =3D $(wym._options.titleSelector).val() || '= '; =20 - if (sUrl && sName) { + if (sUrl || sId) { // Create link. wym._exec(WYMeditor.CREATE_LINK, sStamp); =20 // Set link attributes. var link =3D $("a[href=3D" + sStamp + "]", wym._do= c.body); link.attr(WYMeditor.HREF, sUrl) - .attr(WYMeditor.TITLE, $(wym._options.titleSel= ector).val()) - .attr("id", sName); + .attr(WYMeditor.TITLE, sName) + .attr("id", sId); =20 // If link's text is default (wym-...), change it = to the title. if (link.text().indexOf('wym-') =3D=3D=3D 0) { diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c static/scripts/packed/galaxy.pages.js --- a/static/scripts/packed/galaxy.pages.js +++ b/static/scripts/packed/galaxy.pages.js @@ -1,1 +1,1 @@ -var Galaxy=3D{ITEM_HISTORY:"item_history",ITEM_DATASET:"item_dataset",ITEM= _WORKFLOW:"item_workflow",ITEM_PAGE:"item_page",ITEM_VISUALIZATION:"item_vi= sualization",DIALOG_HISTORY_LINK:"link_history",DIALOG_DATASET_LINK:"link_d= ataset",DIALOG_WORKFLOW_LINK:"link_workflow",DIALOG_PAGE_LINK:"link_page",D= IALOG_VISUALIZATION_LINK:"link_visualization",DIALOG_EMBED_HISTORY:"embed_h= istory",DIALOG_EMBED_DATASET:"embed_dataset",DIALOG_EMBED_WORKFLOW:"embed_w= orkflow",DIALOG_EMBED_PAGE:"embed_page",DIALOG_EMBED_VISUALIZATION:"embed_v= isualization",DIALOG_HISTORY_ANNOTATE:"history_annotate",};function init_ga= laxy_elts(a){$(".annotation",a._doc.body).each(function(){$(this).click(fun= ction(){var b=3Da._doc.createRange();b.selectNodeContents(this);var d=3Dwin= dow.getSelection();d.removeAllRanges();d.addRange(b);var c=3D""})})}functio= n get_item_info(d){var f,c,b;switch(d){case (Galaxy.ITEM_HISTORY):f=3D"Hist= ory";c=3D"Histories";b=3D"history";item_class=3D"History";break;case (Galax= y.ITEM_DATASET):f=3D"Dataset";c=3D"Datasets";b=3D"dataset";item_class=3D"Hi= storyDatasetAssociation";break;case (Galaxy.ITEM_WORKFLOW):f=3D"Workflow";c= =3D"Workflows";b=3D"workflow";item_class=3D"StoredWorkflow";break;case (Gal= axy.ITEM_PAGE):f=3D"Page";c=3D"Pages";b=3D"page";item_class=3D"Page";break;= case (Galaxy.ITEM_VISUALIZATION):f=3D"Visualization";c=3D"Visualizations";b= =3D"visualization";item_class=3D"Visualization";break}var e=3D"list_"+c.toL= owerCase()+"_for_selection";var a=3Dlist_objects_url.replace("LIST_ACTION",= e);return{singular:f,plural:c,controller:b,iclass:item_class,list_ajax_url:= a}}function make_item_importable(a,c,b){ajax_url=3Dset_accessible_url.repla= ce("ITEM_CONTROLLER",a);$.ajax({type:"POST",url:ajax_url,data:{id:c,accessi= ble:"True"},error:function(){alert("Making "+b+" accessible failed")}})}WYM= editor.editor.prototype.dialog=3Dfunction(i,e,g){var a=3Dthis;var b=3Da.uni= queStamp();var f=3Da.selected();function h(){$("#set_link_id").click(functi= on(){$("#link_attribute_label").text("ID/Name");var k=3D$(".wym_href");k.ad= dClass("wym_id").removeClass("wym_href");if(f){k.val($(f).attr("id"))}$(thi= s).remove()})}if(i=3D=3DWYMeditor.DIALOG_LINK){if(f){$(a._options.hrefSelec= tor).val($(f).attr(WYMeditor.HREF));$(a._options.srcSelector).val($(f).attr= (WYMeditor.SRC));$(a._options.titleSelector).val($(f).attr(WYMeditor.TITLE)= );$(a._options.altSelector).val($(f).attr(WYMeditor.ALT))}var c,d;if(f){c= =3D$(f).attr("href");if(c=3D=3Dundefined){c=3D""}d=3D$(f).attr("title");if(= d=3D=3Dundefined){d=3D""}}show_modal("Create Link","<div><div><label id=3D'= link_attribute_label'>URL <span style=3D'float: right; font-size: 90%'><a h= ref=3D'#' id=3D'set_link_id'>Create in-page anchor</a></span></label><br><i= nput type=3D'text' class=3D'wym_href' value=3D'"+c+"' size=3D'40' /></div><= div><label>Title</label><br><input type=3D'text' class=3D'wym_title' value= =3D'"+d+"' size=3D'40' /></div><div>",{"Make link":function(){var l=3D$(a._= options.hrefSelector).val(),m=3D$(".wym_title").val();if(l&&m){a._exec(WYMe= ditor.CREATE_LINK,b);var k=3D$("a[href=3D"+b+"]",a._doc.body);k.attr(WYMedi= tor.HREF,l).attr(WYMeditor.TITLE,$(a._options.titleSelector).val()).attr("i= d",m);if(k.text().indexOf("wym-")=3D=3D=3D0){k.text(m)}}hide_modal()},Cance= l:function(){hide_modal()}},{},h)}if(i=3D=3DWYMeditor.DIALOG_IMAGE){if(a._s= elected_image){$(a._options.dialogImageSelector+" "+a._options.srcSelector)= .val($(a._selected_image).attr(WYMeditor.SRC));$(a._options.dialogImageSele= ctor+" "+a._options.titleSelector).val($(a._selected_image).attr(WYMeditor.= TITLE));$(a._options.dialogImageSelector+" "+a._options.altSelector).val($(= a._selected_image).attr(WYMeditor.ALT))}show_modal("Image","<div class=3D'r= ow'><label>URL</label><br><input type=3D'text' class=3D'wym_src' value=3D''= size=3D'40' /></div><div class=3D'row'><label>Alt text</label><br><input t= ype=3D'text' class=3D'wym_alt' value=3D'' size=3D'40' /></div><div class=3D= 'row'><label>Title</label><br><input type=3D'text' class=3D'wym_title' valu= e=3D'' size=3D'40' /></div>",{Insert:function(){var k=3D$(a._options.srcSel= ector).val();if(k.length>0){a._exec(WYMeditor.INSERT_IMAGE,b);$("img[src$= =3D"+b+"]",a._doc.body).attr(WYMeditor.SRC,k).attr(WYMeditor.TITLE,$(a._opt= ions.titleSelector).val()).attr(WYMeditor.ALT,$(a._options.altSelector).val= ())}hide_modal()},Cancel:function(){hide_modal()}});return}if(i=3D=3DWYMedi= tor.DIALOG_TABLE){show_modal("Table","<div class=3D'row'><label>Caption</la= bel><br><input type=3D'text' class=3D'wym_caption' value=3D'' size=3D'40' /= ptions.colsSelector).val();if(o>0&&r>0){var n=3Da._doc.createElement(WYMedi= tor.TABLE);var l=3Dnull;var q=3Dnull;var k=3D$(a._options.captionSelector).= val();var p=3Dn.createCaption();p.innerHTML=3Dk;for(x=3D0;x<o;x++){l=3Dn.in= sertRow(x);for(y=3D0;y<r;y++){l.insertCell(y)}}$(n).attr("summary",$(a._opt= ions.summarySelector).val());var m=3D$(a.findUp(a.container(),WYMeditor.MAI= N_CONTAINERS)).get(0);if(!m||!m.parentNode){$(a._doc.body).append(n)}else{$= (m).after(n)}}hide_modal()},Cancel:function(){hide_modal()}})}if(i=3D=3DGal= axy.DIALOG_HISTORY_LINK||i=3D=3DGalaxy.DIALOG_DATASET_LINK||i=3D=3DGalaxy.D= IALOG_WORKFLOW_LINK||i=3D=3DGalaxy.DIALOG_PAGE_LINK||i=3D=3DGalaxy.DIALOG_V= ISUALIZATION_LINK){var j;switch(i){case (Galaxy.DIALOG_HISTORY_LINK):j=3Dge= t_item_info(Galaxy.ITEM_HISTORY);break;case (Galaxy.DIALOG_DATASET_LINK):j= =3Dget_item_info(Galaxy.ITEM_DATASET);break;case (Galaxy.DIALOG_WORKFLOW_LI= NK):j=3Dget_item_info(Galaxy.ITEM_WORKFLOW);break;case (Galaxy.DIALOG_PAGE_= LINK):j=3Dget_item_info(Galaxy.ITEM_PAGE);break;case (Galaxy.DIALOG_VISUALI= ZATION_LINK):j=3Dget_item_info(Galaxy.ITEM_VISUALIZATION);break}$.ajax({url= :j.list_ajax_url,data:{},error:function(){alert("Failed to list "+j.plural.= toLowerCase()+" for selection")},success:function(k){show_modal("Insert Lin= k to "+j.singular,k+"<div><input id=3D'make-importable' type=3D'checkbox' c= hecked/>Make the selected "+j.plural.toLowerCase()+" accessible so that the= y can viewed by everyone.</div>",{Insert:function(){var m=3Dfalse;if($("#ma= ke-importable:checked").val()!=3D=3Dnull){m=3Dtrue}var l=3Dnew Array();$("i= nput[name=3Did]:checked").each(function(){var n=3D$(this).val();if(m){make_= item_importable(j.controller,n,j.singular)}url_template=3Dget_name_and_link= _url+n;ajax_url=3Durl_template.replace("ITEM_CONTROLLER",j.controller);$.ge= tJSON(ajax_url,function(p){a._exec(WYMeditor.CREATE_LINK,b);var o=3D$("a[hr= ef=3D"+b+"]",a._doc.body).text();if(o=3D=3D""||o=3D=3Db){a.insert("<a href= =3D'"+p.link+"'>"+j.singular+" '"+p.name+"'</a>")}else{$("a[href=3D"+b+"]",= a._doc.body).attr(WYMeditor.HREF,p.link).attr(WYMeditor.TITLE,j.singular+n)= }})});hide_modal()},Cancel:function(){hide_modal()}})}})}if(i=3D=3DGalaxy.D= IALOG_EMBED_HISTORY||i=3D=3DGalaxy.DIALOG_EMBED_DATASET||i=3D=3DGalaxy.DIAL= OG_EMBED_WORKFLOW||i=3D=3DGalaxy.DIALOG_EMBED_PAGE||i=3D=3DGalaxy.DIALOG_EM= BED_VISUALIZATION){var j;switch(i){case (Galaxy.DIALOG_EMBED_HISTORY):j=3Dg= et_item_info(Galaxy.ITEM_HISTORY);break;case (Galaxy.DIALOG_EMBED_DATASET):= j=3Dget_item_info(Galaxy.ITEM_DATASET);break;case (Galaxy.DIALOG_EMBED_WORK= FLOW):j=3Dget_item_info(Galaxy.ITEM_WORKFLOW);break;case (Galaxy.DIALOG_EMB= ED_PAGE):j=3Dget_item_info(Galaxy.ITEM_PAGE);break;case (Galaxy.DIALOG_EMBE= D_VISUALIZATION):j=3Dget_item_info(Galaxy.ITEM_VISUALIZATION);break}$.ajax(= {url:j.list_ajax_url,data:{},error:function(){alert("Failed to list "+j.plu= ral.toLowerCase()+" for selection")},success:function(k){if(i=3D=3DGalaxy.D= IALOG_EMBED_HISTORY||i=3D=3DGalaxy.DIALOG_EMBED_WORKFLOW||i=3D=3DGalaxy.DIA= LOG_EMBED_VISUALIZATION){k=3Dk+"<div><input id=3D'make-importable' type=3D'= checkbox' checked/>Make the selected "+j.plural.toLowerCase()+" accessible = so that they can viewed by everyone.</div>"}show_modal("Embed "+j.plural,k,= {Embed:function(){var l=3Dfalse;if($("#make-importable:checked").val()!=3Dn= ull){l=3Dtrue}$("input[name=3Did]:checked").each(function(){var m=3D$(this)= .val();var p=3D$("label[for=3D'"+m+"']:first").text();if(l){make_item_impor= table(j.controller,m,j.singular)}var n=3Dj.iclass+"-"+m;var o=3D"<p><div id= =3D'"+n+"' class=3D'embedded-item "+j.singular.toLowerCase()+" placeholder'= th:iframe_base_path,boxHtml:"<table class=3D'wym_box' width=3D'100%' height= =3D'100%'><tr><td><div class=3D'wym_area_top'>"+WYMeditor.TOOLS+"</div></td= pt",css:"wym_tools_subscript"},{name:"InsertOrderedList",title:"Ordered_Lis= t",css:"wym_tools_ordered_list"},{name:"InsertUnorderedList",title:"Unorder= ed_List",css:"wym_tools_unordered_list"},{name:"Indent",title:"Indent",css:= "wym_tools_indent"},{name:"Outdent",title:"Outdent",css:"wym_tools_outdent"= },{name:"Undo",title:"Undo",css:"wym_tools_undo"},{name:"Redo",title:"Redo"= ,css:"wym_tools_redo"},{name:"CreateLink",title:"Link",css:"wym_tools_link"= },{name:"Unlink",title:"Unlink",css:"wym_tools_unlink"},{name:"InsertImage"= ,title:"Image",css:"wym_tools_image"},{name:"InsertTable",title:"Table",css= :"wym_tools_table"},]});var d=3D$.wymeditors(0);var f=3Dfunction(g){show_mo= dal("Saving page","progress");$.ajax({url:save_url,type:"POST",data:{id:pag= e_id,content:d.xhtml(),annotations:JSON.stringify(new Object()),_:"true"},s= uccess:function(){g()}})};$("#save-button").click(function(){f(function(){h= ide_modal()})});$("#close-button").click(function(){var h=3Dfalse;if(h){var= g=3Dfunction(){window.onbeforeunload=3Dundefined;window.document.location= =3Dpage_list_url};show_modal("Close editor","There are unsaved changes to y= our page which will be lost.",{Cancel:hide_modal,"Save Changes":function(){= f(g)}},{"Don't Save":g})}else{window.document.location=3Dpage_list_url}});v= ar a=3D$("<div class=3D'galaxy-page-editor-button'><a id=3D'insert-galaxy-l= ink' class=3D'action-button popup' href=3D'#'>Paragraph type</a></div>");$(= ".wym_area_top").append(a);var b=3D{};$.each(d._options.containersItems,fun= ction(h,g){var i=3Dg.name;b[g.title.replace("_"," ")]=3Dfunction(){d.contai= ner(i)}});make_popupmenu(a,b);var c=3D$("<div><a id=3D'insert-galaxy-link' = class=3D'action-button popup' href=3D'#'>Insert Link to Galaxy Object</a></= div>").addClass("galaxy-page-editor-button");$(".wym_area_top").append(c);m= ake_popupmenu(c,{"Insert History Link":function(){d.dialog(Galaxy.DIALOG_HI= STORY_LINK)},"Insert Dataset Link":function(){d.dialog(Galaxy.DIALOG_DATASE= T_LINK)},"Insert Workflow Link":function(){d.dialog(Galaxy.DIALOG_WORKFLOW_= LINK)},"Insert Page Link":function(){d.dialog(Galaxy.DIALOG_PAGE_LINK)},"In= sert Visualization Link":function(){d.dialog(Galaxy.DIALOG_VISUALIZATION_LI= NK)},});var e=3D$("<div><a id=3D'embed-galaxy-object' class=3D'action-butto= n popup' href=3D'#'>Embed Galaxy Object</a></div>").addClass("galaxy-page-e= ditor-button");$(".wym_area_top").append(e);make_popupmenu(e,{"Embed Histor= y":function(){d.dialog(Galaxy.DIALOG_EMBED_HISTORY)},"Embed Dataset":functi= on(){d.dialog(Galaxy.DIALOG_EMBED_DATASET)},"Embed Workflow":function(){d.d= ialog(Galaxy.DIALOG_EMBED_WORKFLOW)},"Embed Visualization":function(){d.dia= log(Galaxy.DIALOG_EMBED_VISUALIZATION)},})}); \ No newline at end of file +var Galaxy=3D{ITEM_HISTORY:"item_history",ITEM_DATASET:"item_dataset",ITEM= _WORKFLOW:"item_workflow",ITEM_PAGE:"item_page",ITEM_VISUALIZATION:"item_vi= sualization",DIALOG_HISTORY_LINK:"link_history",DIALOG_DATASET_LINK:"link_d= ataset",DIALOG_WORKFLOW_LINK:"link_workflow",DIALOG_PAGE_LINK:"link_page",D= IALOG_VISUALIZATION_LINK:"link_visualization",DIALOG_EMBED_HISTORY:"embed_h= istory",DIALOG_EMBED_DATASET:"embed_dataset",DIALOG_EMBED_WORKFLOW:"embed_w= orkflow",DIALOG_EMBED_PAGE:"embed_page",DIALOG_EMBED_VISUALIZATION:"embed_v= isualization",DIALOG_HISTORY_ANNOTATE:"history_annotate",};function init_ga= laxy_elts(a){$(".annotation",a._doc.body).each(function(){$(this).click(fun= ction(){var b=3Da._doc.createRange();b.selectNodeContents(this);var d=3Dwin= dow.getSelection();d.removeAllRanges();d.addRange(b);var c=3D""})})}functio= n get_item_info(d){var f,c,b;switch(d){case (Galaxy.ITEM_HISTORY):f=3D"Hist= ory";c=3D"Histories";b=3D"history";item_class=3D"History";break;case (Galax= y.ITEM_DATASET):f=3D"Dataset";c=3D"Datasets";b=3D"dataset";item_class=3D"Hi= storyDatasetAssociation";break;case (Galaxy.ITEM_WORKFLOW):f=3D"Workflow";c= =3D"Workflows";b=3D"workflow";item_class=3D"StoredWorkflow";break;case (Gal= axy.ITEM_PAGE):f=3D"Page";c=3D"Pages";b=3D"page";item_class=3D"Page";break;= case (Galaxy.ITEM_VISUALIZATION):f=3D"Visualization";c=3D"Visualizations";b= =3D"visualization";item_class=3D"Visualization";break}var e=3D"list_"+c.toL= owerCase()+"_for_selection";var a=3Dlist_objects_url.replace("LIST_ACTION",= e);return{singular:f,plural:c,controller:b,iclass:item_class,list_ajax_url:= a}}function make_item_importable(a,c,b){ajax_url=3Dset_accessible_url.repla= ce("ITEM_CONTROLLER",a);$.ajax({type:"POST",url:ajax_url,data:{id:c,accessi= ble:"True"},error:function(){alert("Making "+b+" accessible failed")}})}WYM= editor.editor.prototype.dialog=3Dfunction(i,e,g){var a=3Dthis;var b=3Da.uni= queStamp();var f=3Da.selected();function h(){$("#set_link_id").click(functi= on(){$("#link_attribute_label").text("ID/Name");var k=3D$(".wym_href");k.ad= dClass("wym_id").removeClass("wym_href");if(f){k.val($(f).attr("id"))}$(thi= s).remove()})}if(i=3D=3DWYMeditor.DIALOG_LINK){if(f){$(a._options.hrefSelec= tor).val($(f).attr(WYMeditor.HREF));$(a._options.srcSelector).val($(f).attr= (WYMeditor.SRC));$(a._options.titleSelector).val($(f).attr(WYMeditor.TITLE)= );$(a._options.altSelector).val($(f).attr(WYMeditor.ALT))}var c,d;if(f){c= =3D$(f).attr("href");if(c=3D=3Dundefined){c=3D""}d=3D$(f).attr("title");if(= d=3D=3Dundefined){d=3D""}}show_modal("Create Link","<div><div><label id=3D'= link_attribute_label'>URL <span style=3D'float: right; font-size: 90%'><a h= ref=3D'#' id=3D'set_link_id'>Create in-page anchor</a></span></label><br><i= nput type=3D'text' class=3D'wym_href' value=3D'"+c+"' size=3D'40' /></div><= div><label>Title</label><br><input type=3D'text' class=3D'wym_title' value= =3D'"+d+"' size=3D'40' /></div><div>",{"Make link":function(){var m=3D$(a._= options.hrefSelector).val()||"",k=3D$(".wym_id").val()||"",n=3D$(a._options= .titleSelector).val()||"";if(m||k){a._exec(WYMeditor.CREATE_LINK,b);var l= =3D$("a[href=3D"+b+"]",a._doc.body);l.attr(WYMeditor.HREF,m).attr(WYMeditor= .TITLE,n).attr("id",k);if(l.text().indexOf("wym-")=3D=3D=3D0){l.text(n)}}hi= de_modal()},Cancel:function(){hide_modal()}},{},h)}if(i=3D=3DWYMeditor.DIAL= OG_IMAGE){if(a._selected_image){$(a._options.dialogImageSelector+" "+a._opt= ions.srcSelector).val($(a._selected_image).attr(WYMeditor.SRC));$(a._option= s.dialogImageSelector+" "+a._options.titleSelector).val($(a._selected_image= ).attr(WYMeditor.TITLE));$(a._options.dialogImageSelector+" "+a._options.al= tSelector).val($(a._selected_image).attr(WYMeditor.ALT))}show_modal("Image"= ,"<div class=3D'row'><label>URL</label><br><input type=3D'text' class=3D'wy= m_src' value=3D'' size=3D'40' /></div><div class=3D'row'><label>Alt text</l= abel><br><input type=3D'text' class=3D'wym_alt' value=3D'' size=3D'40' /></= div><div class=3D'row'><label>Title</label><br><input type=3D'text' class= =3D'wym_title' value=3D'' size=3D'40' /></div>",{Insert:function(){var k=3D= $(a._options.srcSelector).val();if(k.length>0){a._exec(WYMeditor.INSERT_IMA= GE,b);$("img[src$=3D"+b+"]",a._doc.body).attr(WYMeditor.SRC,k).attr(WYMedit= or.TITLE,$(a._options.titleSelector).val()).attr(WYMeditor.ALT,$(a._options= .altSelector).val())}hide_modal()},Cancel:function(){hide_modal()}});return= }if(i=3D=3DWYMeditor.DIALOG_TABLE){show_modal("Table","<div class=3D'row'><= label>Caption</label><br><input type=3D'text' class=3D'wym_caption' value= =3D'' size=3D'40' /></div><div class=3D'row'><label>Summary</label><br><inp= ut type=3D'text' class=3D'wym_summary' value=3D'' size=3D'40' /></div><div = class=3D'row'><label>Number Of Rows<br></label><input type=3D'text' class= =3D'wym_rows' value=3D'3' size=3D'3' /></div><div class=3D'row'><label>Numb= er Of Cols<br></label><input type=3D'text' class=3D'wym_cols' value=3D'2' s= ize=3D'3' /></div>",{Insert:function(){var o=3D$(a._options.rowsSelector).v= al();var r=3D$(a._options.colsSelector).val();if(o>0&&r>0){var n=3Da._doc.c= reateElement(WYMeditor.TABLE);var l=3Dnull;var q=3Dnull;var k=3D$(a._option= s.captionSelector).val();var p=3Dn.createCaption();p.innerHTML=3Dk;for(x=3D= 0;x<o;x++){l=3Dn.insertRow(x);for(y=3D0;y<r;y++){l.insertCell(y)}}$(n).attr= ("summary",$(a._options.summarySelector).val());var m=3D$(a.findUp(a.contai= ner(),WYMeditor.MAIN_CONTAINERS)).get(0);if(!m||!m.parentNode){$(a._doc.bod= y).append(n)}else{$(m).after(n)}}hide_modal()},Cancel:function(){hide_modal= ()}})}if(i=3D=3DGalaxy.DIALOG_HISTORY_LINK||i=3D=3DGalaxy.DIALOG_DATASET_LI= NK||i=3D=3DGalaxy.DIALOG_WORKFLOW_LINK||i=3D=3DGalaxy.DIALOG_PAGE_LINK||i= =3D=3DGalaxy.DIALOG_VISUALIZATION_LINK){var j;switch(i){case (Galaxy.DIALOG= _HISTORY_LINK):j=3Dget_item_info(Galaxy.ITEM_HISTORY);break;case (Galaxy.DI= ALOG_DATASET_LINK):j=3Dget_item_info(Galaxy.ITEM_DATASET);break;case (Galax= y.DIALOG_WORKFLOW_LINK):j=3Dget_item_info(Galaxy.ITEM_WORKFLOW);break;case = (Galaxy.DIALOG_PAGE_LINK):j=3Dget_item_info(Galaxy.ITEM_PAGE);break;case (G= alaxy.DIALOG_VISUALIZATION_LINK):j=3Dget_item_info(Galaxy.ITEM_VISUALIZATIO= N);break}$.ajax({url:j.list_ajax_url,data:{},error:function(){alert("Failed= to list "+j.plural.toLowerCase()+" for selection")},success:function(k){sh= ow_modal("Insert Link to "+j.singular,k+"<div><input id=3D'make-importable'= type=3D'checkbox' checked/>Make the selected "+j.plural.toLowerCase()+" ac= cessible so that they can viewed by everyone.</div>",{Insert:function(){var= m=3Dfalse;if($("#make-importable:checked").val()!=3D=3Dnull){m=3Dtrue}var = l=3Dnew Array();$("input[name=3Did]:checked").each(function(){var n=3D$(thi= s).val();if(m){make_item_importable(j.controller,n,j.singular)}url_template= =3Dget_name_and_link_url+n;ajax_url=3Durl_template.replace("ITEM_CONTROLLER= ",j.controller);$.getJSON(ajax_url,function(p){a._exec(WYMeditor.CREATE_LIN= K,b);var o=3D$("a[href=3D"+b+"]",a._doc.body).text();if(o=3D=3D""||o=3D=3Db= ){a.insert("<a href=3D'"+p.link+"'>"+j.singular+" '"+p.name+"'</a>")}else{$= ("a[href=3D"+b+"]",a._doc.body).attr(WYMeditor.HREF,p.link).attr(WYMeditor.= TITLE,j.singular+n)}})});hide_modal()},Cancel:function(){hide_modal()}})}})= }if(i=3D=3DGalaxy.DIALOG_EMBED_HISTORY||i=3D=3DGalaxy.DIALOG_EMBED_DATASET|= |i=3D=3DGalaxy.DIALOG_EMBED_WORKFLOW||i=3D=3DGalaxy.DIALOG_EMBED_PAGE||i=3D= =3DGalaxy.DIALOG_EMBED_VISUALIZATION){var j;switch(i){case (Galaxy.DIALOG_E= MBED_HISTORY):j=3Dget_item_info(Galaxy.ITEM_HISTORY);break;case (Galaxy.DIA= LOG_EMBED_DATASET):j=3Dget_item_info(Galaxy.ITEM_DATASET);break;case (Galax= y.DIALOG_EMBED_WORKFLOW):j=3Dget_item_info(Galaxy.ITEM_WORKFLOW);break;case= (Galaxy.DIALOG_EMBED_PAGE):j=3Dget_item_info(Galaxy.ITEM_PAGE);break;case = (Galaxy.DIALOG_EMBED_VISUALIZATION):j=3Dget_item_info(Galaxy.ITEM_VISUALIZA= TION);break}$.ajax({url:j.list_ajax_url,data:{},error:function(){alert("Fai= led to list "+j.plural.toLowerCase()+" for selection")},success:function(k)= {if(i=3D=3DGalaxy.DIALOG_EMBED_HISTORY||i=3D=3DGalaxy.DIALOG_EMBED_WORKFLOW= ||i=3D=3DGalaxy.DIALOG_EMBED_VISUALIZATION){k=3Dk+"<div><input id=3D'make-i= mportable' type=3D'checkbox' checked/>Make the selected "+j.plural.toLowerC= ase()+" accessible so that they can viewed by everyone.</div>"}show_modal("= Embed "+j.plural,k,{Embed:function(){var l=3Dfalse;if($("#make-importable:c= hecked").val()!=3Dnull){l=3Dtrue}$("input[name=3Did]:checked").each(functio= n(){var m=3D$(this).val();var p=3D$("label[for=3D'"+m+"']:first").text();if= (l){make_item_importable(j.controller,m,j.singular)}var n=3Dj.iclass+"-"+m;= var o=3D"<p><div id=3D'"+n+"' class=3D'embedded-item "+j.singular.toLowerCa= se()+" placeholder'><p class=3D'title'>Embedded Galaxy "+j.singular+" '"+p+= "'</p><p class=3D'content'> [Do= not edit this block; Galaxy will fill it in with the annotated "+j.singula= r.toLowerCase()+" when it is displayed.] = </p></div></p>";a.insert(" ");a.insert(o);$("#"+n,a._doc.body).e= ach(function(){var q=3Dtrue;while(q){var r=3D$(this).prev();if(r.length!=3D= 0&&jQuery.trim(r.text())=3D=3D""){r.remove()}else{q=3Dfalse}}})});hide_moda= l()},Cancel:function(){hide_modal()}})}})}if(i=3D=3DGalaxy.DIALOG_ANNOTATE_= HISTORY){$.ajax({url:list_histories_for_selection_url,data:{},error:functio= n(){alert("Grid refresh failed")},success:function(k){show_modal("Insert Li= nk to History",k,{Annotate:function(){var l=3Dnew Array();$("input[name=3Di= d]:checked").each(function(){var m=3D$(this).val();$.ajax({url:get_history_= annotation_table_url,data:{id:m},error:function(){alert("Grid refresh faile= d")},success:function(n){a.insert(n);init_galaxy_elts(a)}})});hide_modal()}= ,Cancel:function(){hide_modal()}})}})}};$(function(){$(document).ajaxError(= function(i,g){var h=3Dg.responseText||g.statusText||"Could not connect to s= erver";show_modal("Server error",h,{"Ignore error":hide_modal});return fals= e});$("[name=3Dpage_content]").wymeditor({skin:"galaxy",basePath:editor_bas= e_path,iframeBasePath:iframe_base_path,boxHtml:"<table class=3D'wym_box' wi= dth=3D'100%' height=3D'100%'><tr><td><div class=3D'wym_area_top'>"+WYMedito= r.TOOLS+"</div></td></tr><tr height=3D'100%'><td><div class=3D'wym_area_mai= n' style=3D'height: 100%;'>"+WYMeditor.IFRAME+WYMeditor.STATUS+"</div></div= title:"Indent",css:"wym_tools_indent"},{name:"Outdent",title:"Outdent",css:= "wym_tools_outdent"},{name:"Undo",title:"Undo",css:"wym_tools_undo"},{name:= "Redo",title:"Redo",css:"wym_tools_redo"},{name:"CreateLink",title:"Link",c= ss:"wym_tools_link"},{name:"Unlink",title:"Unlink",css:"wym_tools_unlink"},= {name:"InsertImage",title:"Image",css:"wym_tools_image"},{name:"InsertTable= ",title:"Table",css:"wym_tools_table"},]});var d=3D$.wymeditors(0);var f=3D= function(g){show_modal("Saving page","progress");$.ajax({url:save_url,type:= "POST",data:{id:page_id,content:d.xhtml(),annotations:JSON.stringify(new Ob= ject()),_:"true"},success:function(){g()}})};$("#save-button").click(functi= on(){f(function(){hide_modal()})});$("#close-button").click(function(){var = h=3Dfalse;if(h){var g=3Dfunction(){window.onbeforeunload=3Dundefined;window= .document.location=3Dpage_list_url};show_modal("Close editor","There are un= saved changes to your page which will be lost.",{Cancel:hide_modal,"Save Ch= anges":function(){f(g)}},{"Don't Save":g})}else{window.document.location=3D= page_list_url}});var a=3D$("<div class=3D'galaxy-page-editor-button'><a id= =3D'insert-galaxy-link' class=3D'action-button popup' href=3D'#'>Paragraph = type</a></div>");$(".wym_area_top").append(a);var b=3D{};$.each(d._options.= containersItems,function(h,g){var i=3Dg.name;b[g.title.replace("_"," ")]=3D= function(){d.container(i)}});make_popupmenu(a,b);var c=3D$("<div><a id=3D'i= nsert-galaxy-link' class=3D'action-button popup' href=3D'#'>Insert Link to = Galaxy Object</a></div>").addClass("galaxy-page-editor-button");$(".wym_are= a_top").append(c);make_popupmenu(c,{"Insert History Link":function(){d.dial= og(Galaxy.DIALOG_HISTORY_LINK)},"Insert Dataset Link":function(){d.dialog(G= alaxy.DIALOG_DATASET_LINK)},"Insert Workflow Link":function(){d.dialog(Gala= xy.DIALOG_WORKFLOW_LINK)},"Insert Page Link":function(){d.dialog(Galaxy.DIA= LOG_PAGE_LINK)},"Insert Visualization Link":function(){d.dialog(Galaxy.DIAL= OG_VISUALIZATION_LINK)},});var e=3D$("<div><a id=3D'embed-galaxy-object' cl= ass=3D'action-button popup' href=3D'#'>Embed Galaxy Object</a></div>").addC= lass("galaxy-page-editor-button");$(".wym_area_top").append(e);make_popupme= nu(e,{"Embed History":function(){d.dialog(Galaxy.DIALOG_EMBED_HISTORY)},"Em= bed Dataset":function(){d.dialog(Galaxy.DIALOG_EMBED_DATASET)},"Embed Workf= low":function(){d.dialog(Galaxy.DIALOG_EMBED_WORKFLOW)},"Embed Visualizatio= n":function(){d.dialog(Galaxy.DIALOG_EMBED_VISUALIZATION)},})}); \ No newline at end of file diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c static/scripts/packed/mvc/tools.js --- a/static/scripts/packed/mvc/tools.js +++ b/static/scripts/packed/mvc/tools.js @@ -1,1 +1,1 @@ -define(["libs/underscore","viz/trackster/util","mvc/data","libs/backbone/b= ackbone-relational"],function(q,a,r){var f=3DBackbone.RelationalModel.exten= d({defaults:{name:null,hidden:false},show:function(){this.set("hidden",fals= e)},hide:function(){this.set("hidden",true)},is_visible:function(){return != this.attributes.hidden}});var k=3DBackbone.RelationalModel.extend({defaults= :{name:null,label:null,type:null,value:null,num_samples:5},initialize:funct= ion(){this.attributes.html=3Dunescape(this.attributes.html)},copy:function(= ){return new k(this.toJSON())},get_samples:function(){var u=3Dthis.get("typ= e"),t=3Dnull;if(u=3D=3D=3D"number"){t=3Dd3.scale.linear().domain([this.get(= "min"),this.get("max")]).ticks(this.get("num_samples"))}else{if(u=3D=3D=3D"= select"){t=3Dq.map(this.get("options"),function(v){return v[0]})}}return t}= });var e=3Df.extend({defaults:{description:null,target:null,inputs:[]},rela= tions:[{type:Backbone.HasMany,key:"inputs",relatedModel:k,reverseRelation:{= key:"tool",includeInJSON:false}}],urlRoot:galaxy_paths.get("tool_url"),copy= :function(u){var v=3Dnew e(this.toJSON());if(u){var t=3Dnew Backbone.Collec= tion();v.get("inputs").each(function(w){if(w.get_samples()){t.push(w)}});v.= set("inputs",t)}return v},apply_search_results:function(t){(q.indexOf(t,thi= s.attributes.id)!=3D=3D-1?this.show():this.hide());return this.is_visible()= },set_input_value:function(t,u){this.get("inputs").find(function(v){return = v.get("name")=3D=3D=3Dt}).set("value",u)},set_input_values:function(u){var = t=3Dthis;q.each(q.keys(u),function(v){t.set_input_value(v,u[v])})},run:func= tion(){return this._run()},rerun:function(u,t){return this._run({action:"re= run",target_dataset_id:u.id,regions:t})},get_inputs_dict:function(){var t= =3D{};this.get("inputs").each(function(u){t[u.get("name")]=3Du.get("value")= });return t},_run:function(v){var w=3Dq.extend({tool_id:this.id,inputs:this= .get_inputs_dict()},v);var u=3D$.Deferred(),t=3Dnew a.ServerStateDeferred({= ajax_settings:{url:this.urlRoot,data:JSON.stringify(w),dataType:"json",cont= entType:"application/json",type:"POST"},interval:2000,success_fn:function(x= ){return x!=3D=3D"pending"}});$.when(t.go()).then(function(x){u.resolve(new= r.DatasetCollection().reset(x))});return u}});var i=3DBackbone.Collection.= extend({model:e});var m=3Df.extend({});var p=3Df.extend({defaults:{elems:[]= ,open:false},clear_search_results:function(){q.each(this.attributes.elems,f= unction(t){t.show()});this.show();this.set("open",false)},apply_search_resu= lts:function(u){var v=3Dtrue,t;q.each(this.attributes.elems,function(w){if(= w instanceof m){t=3Dw;t.hide()}else{if(w instanceof e){if(w.apply_search_re= sults(u)){v=3Dfalse;if(t){t.show()}}}}});if(v){this.hide()}else{this.show()= ;this.set("open",true)}}});var b=3Df.extend({defaults:{search_hint_string:"= search tools",min_chars_for_search:3,spinner_url:"",clear_btn_url:"",search= _url:"",visible:true,query:"",results:null,clear_key:27},initialize:functio= n(){this.on("change:query",this.do_search)},do_search:function(){var v=3Dth= is.attributes.query;if(v.length<this.attributes.min_chars_for_search){this.= set("results",null);return}var u=3Dv+"*";if(this.timer){clearTimeout(this.t= imer)}$("#search-clear-btn").hide();$("#search-spinner").show();var t=3Dthi= s;this.timer=3DsetTimeout(function(){$.get(t.attributes.search_url,{query:u= },function(w){t.set("results",w);$("#search-spinner").hide();$("#search-cle= ar-btn").show()},"json")},200)},clear_search:function(){this.set("query",""= );this.set("results",null)}});var j=3DBackbone.Collection.extend({url:"/too= ls",tools:new i(),parse:function(t){var u=3Dfunction(x){var w=3Dx.type;if(w= =3D=3D=3D"tool"){return new e(x)}else{if(w=3D=3D=3D"section"){var v=3Dq.map= (x.elems,u);x.elems=3Dv;return new p(x)}else{if(w=3D=3D=3D"label"){return n= ew m(x)}}}};return q.map(t,u)},initialize:function(t){this.tool_search=3Dt.= tool_search;this.tool_search.on("change:results",this.apply_search_results,= this);this.on("reset",this.populate_tools,this)},populate_tools:function(){= var t=3Dthis;t.tools=3Dnew i();this.each(function(u){if(u instanceof p){q.e= ach(u.attributes.elems,function(v){if(v instanceof e){t.tools.push(v)}})}el= se{if(u instanceof e){t.tools.push(u)}}})},clear_search_results:function(){= this.each(function(t){if(t instanceof p){t.clear_search_results()}else{t.sh= ow()}})},apply_search_results:function(){var u=3Dthis.tool_search.attribute= s.results;if(u=3D=3D=3Dnull){this.clear_search_results();return}var t=3Dnul= l;this.each(function(v){if(v instanceof m){t=3Dv;t.hide()}else{if(v instanc= eof e){if(v.apply_search_results(u)){if(t){t.show()}}}else{t=3Dnull;v.apply= _search_results(u)}}})}});var n=3DBackbone.View.extend({initialize:function= (){this.model.on("change:hidden",this.update_visible,this);this.update_visi= ble()},update_visible:function(){(this.model.attributes.hidden?this.$el.hid= e():this.$el.show())}});var h=3Dn.extend({tagName:"div",template:Handlebars= .templates.tool_link,render:function(){this.$el.append(this.template(this.m= odel.toJSON()));return this}});var c=3Dn.extend({tagName:"div",className:"t= oolPanelLabel",render:function(){this.$el.append($("<span/>").text(this.mod= el.attributes.name));return this}});var g=3Dn.extend({tagName:"div",classNa= me:"toolSectionWrapper",template:Handlebars.templates.panel_section,initial= ize:function(){n.prototype.initialize.call(this);this.model.on("change:open= ",this.update_open,this)},render:function(){this.$el.append(this.template(t= his.model.toJSON()));var t=3Dthis.$el.find(".toolSectionBody");q.each(this.= model.attributes.elems,function(u){if(u instanceof e){var v=3Dnew h({model:= u,className:"toolTitle"});v.render();t.append(v.$el)}else{if(u instanceof m= ){var w=3Dnew c({model:u});w.render();t.append(w.$el)}else{}}});return this= },events:{"click .toolSectionTitle > a":"toggle"},toggle:function(){this.mo= del.set("open",!this.model.attributes.open)},update_open:function(){(this.m= odel.attributes.open?this.$el.children(".toolSectionBody").slideDown("fast"= ):this.$el.children(".toolSectionBody").slideUp("fast"))}});var l=3DBackbon= e.View.extend({tagName:"div",id:"tool-search",className:"bar",template:Hand= lebars.templates.tool_search,events:{click:"focus_and_select","keyup :input= ":"query_changed","click #search-clear-btn":"clear"},render:function(){this= .$el.append(this.template(this.model.toJSON()));if(!this.model.is_visible()= ){this.$el.hide()}this.$el.find(".tooltip").tooltip();return this},focus_an= d_select:function(){this.$el.find(":input").focus().select()},clear:functio= n(){this.model.clear_search();this.$el.find(":input").val(this.model.attrib= utes.search_hint_string);this.focus_and_select();return false},query_change= d:function(t){if((this.model.attributes.clear_key)&&(this.model.attributes.= clear_key=3D=3D=3Dt.which)){this.clear();return false}this.model.set("query= ",this.$el.find(":input").val())}});var s=3DBackbone.View.extend({tagName:"= div",className:"toolMenu",initialize:function(){this.collection.tool_search= .on("change:results",this.handle_search_results,this)},render:function(){va= r t=3Dthis;var u=3Dnew l({model:this.collection.tool_search});u.render();t.= $el.append(u.$el);this.collection.each(function(w){if(w instanceof p){var v= =3Dnew g({model:w});v.render();t.$el.append(v.$el)}else{if(w instanceof e){= var x=3Dnew h({model:w,className:"toolTitleNoSection"});x.render();t.$el.ap= pend(x.$el)}else{if(w instanceof m){var y=3Dnew c({model:w});y.render();t.$= el.append(y.$el)}}}});t.$el.find("a.tool-link").click(function(x){var w=3D$= (this).attr("class").split(/\s+/)[0],v=3Dt.collection.tools.get(w);t.trigge= r("tool_link_click",x,v)});return this},handle_search_results:function(){va= r t=3Dthis.collection.tool_search.attributes.results;if(t&&t.length=3D=3D= =3D0){$("#search-no-results").show()}else{$("#search-no-results").hide()}}}= );var o=3DBackbone.View.extend({className:"toolForm",template:Handlebars.te= mplates.tool_form,render:function(){this.$el.children().remove();this.$el.a= ppend(this.template(this.model.toJSON()))}});var d=3DBackbone.View.extend({= className:"toolMenuAndView",initialize:function(){this.tool_panel_view=3Dne= w s({collection:this.collection});this.tool_form_view=3Dnew o()},render:fun= ction(){this.tool_panel_view.render();this.tool_panel_view.$el.css("float",= "left");this.$el.append(this.tool_panel_view.$el);this.tool_form_view.$el.h= ide();this.$el.append(this.tool_form_view.$el);var t=3Dthis;this.tool_panel= _view.on("tool_link_click",function(v,u){v.preventDefault();t.show_tool(u)}= )},show_tool:function(u){var t=3Dthis;u.fetch().done(function(){t.tool_form= _view.model=3Du;t.tool_form_view.render();t.tool_form_view.$el.show();$("#l= eft").width("650px")})}});return{Tool:e,ToolSearch:b,ToolPanel:j,ToolPanelV= iew:s,ToolFormView:o}}); \ No newline at end of file +define(["libs/underscore","viz/trackster/util","mvc/data","libs/backbone/b= ackbone-relational"],function(q,a,r){var g=3DBackbone.RelationalModel.exten= d({defaults:{name:null,hidden:false},show:function(){this.set("hidden",fals= e)},hide:function(){this.set("hidden",true)},is_visible:function(){return != this.attributes.hidden}});var c=3DBackbone.RelationalModel.extend({defaults= :{name:null,label:null,type:null,value:null,num_samples:5},initialize:funct= ion(){this.attributes.html=3Dunescape(this.attributes.html)},copy:function(= ){return new c(this.toJSON())},get_samples:function(){var u=3Dthis.get("typ= e"),t=3Dnull;if(u=3D=3D=3D"number"){t=3Dd3.scale.linear().domain([this.get(= "min"),this.get("max")]).ticks(this.get("num_samples"))}else{if(u=3D=3D=3D"= select"){t=3Dq.map(this.get("options"),function(v){return v[0]})}}return t}= });var f=3Dg.extend({defaults:{description:null,target:null,inputs:[]},rela= tions:[{type:Backbone.HasMany,key:"inputs",relatedModel:c,reverseRelation:{= key:"tool",includeInJSON:false}}],urlRoot:galaxy_paths.get("tool_url"),copy= :function(u){var v=3Dnew f(this.toJSON());if(u){var t=3Dnew Backbone.Collec= tion();v.get("inputs").each(function(w){if(w.get_samples()){t.push(w)}});v.= set("inputs",t)}return v},apply_search_results:function(t){(q.indexOf(t,thi= s.attributes.id)!=3D=3D-1?this.show():this.hide());return this.is_visible()= },set_input_value:function(t,u){this.get("inputs").find(function(v){return = v.get("name")=3D=3D=3Dt}).set("value",u)},set_input_values:function(u){var = t=3Dthis;q.each(q.keys(u),function(v){t.set_input_value(v,u[v])})},run:func= tion(){return this._run()},rerun:function(u,t){return this._run({action:"re= run",target_dataset_id:u.id,regions:t})},get_inputs_dict:function(){var t= =3D{};this.get("inputs").each(function(u){t[u.get("name")]=3Du.get("value")= });return t},_run:function(v){var w=3Dq.extend({tool_id:this.id,inputs:this= .get_inputs_dict()},v);var u=3D$.Deferred(),t=3Dnew a.ServerStateDeferred({= ajax_settings:{url:this.urlRoot,data:JSON.stringify(w),dataType:"json",cont= entType:"application/json",type:"POST"},interval:2000,success_fn:function(x= ){return x!=3D=3D"pending"}});$.when(t.go()).then(function(x){u.resolve(new= r.DatasetCollection().reset(x))});return u}});var j=3DBackbone.Collection.= extend({model:f});var m=3Dg.extend({});var p=3Dg.extend({defaults:{elems:[]= ,open:false},clear_search_results:function(){q.each(this.attributes.elems,f= unction(t){t.show()});this.show();this.set("open",false)},apply_search_resu= lts:function(u){var v=3Dtrue,t;q.each(this.attributes.elems,function(w){if(= w instanceof m){t=3Dw;t.hide()}else{if(w instanceof f){if(w.apply_search_re= sults(u)){v=3Dfalse;if(t){t.show()}}}}});if(v){this.hide()}else{this.show()= ;this.set("open",true)}}});var b=3Dg.extend({defaults:{search_hint_string:"= search tools",min_chars_for_search:3,spinner_url:"",clear_btn_url:"",search= _url:"",visible:true,query:"",results:null,clear_key:27},initialize:functio= n(){this.on("change:query",this.do_search)},do_search:function(){var v=3Dth= is.attributes.query;if(v.length<this.attributes.min_chars_for_search){this.= set("results",null);return}var u=3Dv+"*";if(this.timer){clearTimeout(this.t= imer)}$("#search-clear-btn").hide();$("#search-spinner").show();var t=3Dthi= s;this.timer=3DsetTimeout(function(){$.get(t.attributes.search_url,{query:u= },function(w){t.set("results",w);$("#search-spinner").hide();$("#search-cle= ar-btn").show()},"json")},200)},clear_search:function(){this.set("query",""= );this.set("results",null)}});var k=3DBackbone.Collection.extend({url:"/too= ls",tools:new j(),parse:function(t){var u=3Dfunction(x){var w=3Dx.type;if(w= =3D=3D=3D"tool"){return new f(x)}else{if(w=3D=3D=3D"section"){var v=3Dq.map= (x.elems,u);x.elems=3Dv;return new p(x)}else{if(w=3D=3D=3D"label"){return n= ew m(x)}}}};return q.map(t,u)},initialize:function(t){this.tool_search=3Dt.= tool_search;this.tool_search.on("change:results",this.apply_search_results,= this);this.on("reset",this.populate_tools,this)},populate_tools:function(){= var t=3Dthis;t.tools=3Dnew j();this.each(function(u){if(u instanceof p){q.e= ach(u.attributes.elems,function(v){if(v instanceof f){t.tools.push(v)}})}el= se{if(u instanceof f){t.tools.push(u)}}})},clear_search_results:function(){= this.each(function(t){if(t instanceof p){t.clear_search_results()}else{t.sh= ow()}})},apply_search_results:function(){var u=3Dthis.tool_search.attribute= s.results;if(u=3D=3D=3Dnull){this.clear_search_results();return}var t=3Dnul= l;this.each(function(v){if(v instanceof m){t=3Dv;t.hide()}else{if(v instanc= eof f){if(v.apply_search_results(u)){if(t){t.show()}}}else{t=3Dnull;v.apply= _search_results(u)}}})}});var n=3DBackbone.View.extend({initialize:function= (){this.model.on("change:hidden",this.update_visible,this);this.update_visi= ble()},update_visible:function(){(this.model.attributes.hidden?this.$el.hid= e():this.$el.show())}});var i=3Dn.extend({tagName:"div",template:Handlebars= .templates.tool_link,render:function(){this.$el.append(this.template(this.m= odel.toJSON()));return this}});var d=3Dn.extend({tagName:"div",className:"t= oolPanelLabel",render:function(){this.$el.append($("<span/>").text(this.mod= el.attributes.name));return this}});var h=3Dn.extend({tagName:"div",classNa= me:"toolSectionWrapper",template:Handlebars.templates.panel_section,initial= ize:function(){n.prototype.initialize.call(this);this.model.on("change:open= ",this.update_open,this)},render:function(){this.$el.append(this.template(t= his.model.toJSON()));var t=3Dthis.$el.find(".toolSectionBody");q.each(this.= model.attributes.elems,function(u){if(u instanceof f){var v=3Dnew i({model:= u,className:"toolTitle"});v.render();t.append(v.$el)}else{if(u instanceof m= ){var w=3Dnew d({model:u});w.render();t.append(w.$el)}else{}}});return this= },events:{"click .toolSectionTitle > a":"toggle"},toggle:function(){this.mo= del.set("open",!this.model.attributes.open)},update_open:function(){(this.m= odel.attributes.open?this.$el.children(".toolSectionBody").slideDown("fast"= ):this.$el.children(".toolSectionBody").slideUp("fast"))}});var l=3DBackbon= e.View.extend({tagName:"div",id:"tool-search",className:"bar",template:Hand= lebars.templates.tool_search,events:{click:"focus_and_select","keyup :input= ":"query_changed","click #search-clear-btn":"clear"},render:function(){this= .$el.append(this.template(this.model.toJSON()));if(!this.model.is_visible()= ){this.$el.hide()}this.$el.find(".tooltip").tooltip();return this},focus_an= d_select:function(){this.$el.find(":input").focus().select()},clear:functio= n(){this.model.clear_search();this.$el.find(":input").val(this.model.attrib= utes.search_hint_string);this.focus_and_select();return false},query_change= d:function(t){if((this.model.attributes.clear_key)&&(this.model.attributes.= clear_key=3D=3D=3Dt.which)){this.clear();return false}this.model.set("query= ",this.$el.find(":input").val())}});var s=3DBackbone.View.extend({tagName:"= div",className:"toolMenu",initialize:function(){this.collection.tool_search= .on("change:results",this.handle_search_results,this)},render:function(){va= r t=3Dthis;var u=3Dnew l({model:this.collection.tool_search});u.render();t.= $el.append(u.$el);this.collection.each(function(w){if(w instanceof p){var v= =3Dnew h({model:w});v.render();t.$el.append(v.$el)}else{if(w instanceof f){= var x=3Dnew i({model:w,className:"toolTitleNoSection"});x.render();t.$el.ap= pend(x.$el)}else{if(w instanceof m){var y=3Dnew d({model:w});y.render();t.$= el.append(y.$el)}}}});t.$el.find("a.tool-link").click(function(x){var w=3D$= (this).attr("class").split(/\s+/)[0],v=3Dt.collection.tools.get(w);t.trigge= r("tool_link_click",x,v)});return this},handle_search_results:function(){va= r t=3Dthis.collection.tool_search.attributes.results;if(t&&t.length=3D=3D= =3D0){$("#search-no-results").show()}else{$("#search-no-results").hide()}}}= );var o=3DBackbone.View.extend({className:"toolForm",template:Handlebars.te= mplates.tool_form,render:function(){this.$el.children().remove();this.$el.a= ppend(this.template(this.model.toJSON()))}});var e=3DBackbone.View.extend({= className:"toolMenuAndView",initialize:function(){this.tool_panel_view=3Dne= w s({collection:this.collection});this.tool_form_view=3Dnew o()},render:fun= ction(){this.tool_panel_view.render();this.tool_panel_view.$el.css("float",= "left");this.$el.append(this.tool_panel_view.$el);this.tool_form_view.$el.h= ide();this.$el.append(this.tool_form_view.$el);var t=3Dthis;this.tool_panel= _view.on("tool_link_click",function(v,u){v.preventDefault();t.show_tool(u)}= )},show_tool:function(u){var t=3Dthis;u.fetch().done(function(){t.tool_form= _view.model=3Du;t.tool_form_view.render();t.tool_form_view.$el.show();$("#l= eft").width("650px")})}});return{Tool:f,ToolSearch:b,ToolPanel:k,ToolPanelV= iew:s,ToolFormView:o}}); \ No newline at end of file diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c templates/webapps/tool_shed/repository/tool_form.mako --- a/templates/webapps/tool_shed/repository/tool_form.mako +++ b/templates/webapps/tool_shed/repository/tool_form.mako @@ -70,6 +70,8 @@ =20 <%def name=3D"row_for_param( prefix, param, parent_state, other_va= lues )"><% + # Disable refresh_on_change for select lists displayed in = the tool shed.=20 + param.refresh_on_change =3D False label =3D param.get_label() if isinstance( param, DataToolParameter ) or isinstance( p= aram, ColumnListParameter ) or isinstance( param, GenomeBuildParameter ): field =3D SelectField( param.name ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/install_and_test_tool_shed_repositories/functional_t= ests.py --- a/test/install_and_test_tool_shed_repositories/functional_tests.py +++ b/test/install_and_test_tool_shed_repositories/functional_tests.py @@ -6,6 +6,7 @@ =20 import os, sys, shutil, tempfile, re, string, urllib, platform from time import strftime +from ConfigParser import SafeConfigParser =20 # Assume we are run from the galaxy root directory, add lib to the python = path cwd =3D os.getcwd() @@ -73,6 +74,40 @@ default_galaxy_test_port_max =3D 10999 default_galaxy_test_host =3D '127.0.0.1' =20 +# should this serve static resources (scripts, images, styles, etc.) +STATIC_ENABLED =3D True + +def get_static_settings(): + """Returns dictionary of the settings necessary for a galaxy App + to be wrapped in the static middleware. + + This mainly consists of the filesystem locations of url-mapped + static resources. + """ + cwd =3D os.getcwd() + static_dir =3D os.path.join( cwd, 'static' ) + #TODO: these should be copied from universe_wsgi.ini + return dict( + #TODO: static_enabled needed here? + static_enabled =3D True, + static_cache_time =3D 360, + static_dir =3D static_dir, + static_images_dir =3D os.path.join( static_dir, 'images', '' ), + static_favicon_dir =3D os.path.join( static_dir, 'favicon.ico' ), + static_scripts_dir =3D os.path.join( static_dir, 'scripts', '' ), + static_style_dir =3D os.path.join( static_dir, 'june_2007_style= ', 'blue' ), + static_robots_txt =3D os.path.join( static_dir, 'robots.txt' ), + ) + +def get_webapp_global_conf(): + """Get the global_conf dictionary sent as the first argument to app_fa= ctory. + """ + # (was originally sent 'dict()') - nothing here for now except static = settings + global_conf =3D dict() + if STATIC_ENABLED: + global_conf.update( get_static_settings() ) + return global_conf + # Optionally, set the environment variable GALAXY_INSTALL_TEST_TOOL_SHEDS_= CONF # to the location of a tool sheds configuration file that includes the too= l shed # that repositories will be installed from. @@ -219,6 +254,36 @@ success =3D result.wasSuccessful() return success =20 +def generate_config_file( input_filename, output_filename, config_items ): + ''' + Generate a config file with the configuration that has been defined fo= r the embedded web application. + This is mostly relevant when setting metadata externally, since the sc= ript for doing that does not + have access to app.config. + '''=20 + cp =3D SafeConfigParser() + cp.read( input_filename ) + config_items_by_section =3D [] + for label, value in config_items: + found =3D False + # Attempt to determine the correct section for this configuration = option. + for section in cp.sections(): + if cp.has_option( section, label ): + config_tuple =3D section, label, value + config_items_by_section.append( config_tuple ) + found =3D True + continue + # Default to app:main if no section was found. + if not found: + config_tuple =3D 'app:main', label, value + config_items_by_section.append( config_tuple ) + # Replace the default values with the provided configuration. + for section, label, value in config_items_by_section: + cp.remove_option( section, label ) + cp.set( section, label, str( value ) ) + fh =3D open( output_filename, 'w' ) + cp.write( fh ) + fh.close() + def get_api_url( base, parts=3D[], params=3DNone, key=3DNone ): if 'api' in parts and parts.index( 'api' ) !=3D 0: parts.pop( parts.index( 'api' ) ) @@ -554,48 +619,64 @@ # Generate the migrated_tool_conf.xml file. migrated_tool_conf_xml =3D tool_conf_template_parser.safe_substitute( = shed_tool_path=3Dgalaxy_migrated_tool_path ) file( galaxy_migrated_tool_conf_file, 'w' ).write( migrated_tool_conf_= xml ) - + # Write the embedded web application's specific configuration to a tem= porary file. This is necessary in order for + # the external metadata script to find the right datasets. + kwargs =3D dict( admin_users =3D 'test@bx.psu.edu', + allow_user_creation =3D True, + allow_user_deletion =3D True, + allow_library_path_paste =3D True, + database_connection =3D database_connection, + datatype_converters_config_file =3D "datatype_converter= s_conf.xml.sample", + file_path =3D galaxy_file_path, + id_secret =3D galaxy_encode_secret, + job_queue_workers =3D 5, + log_destination =3D "stdout", + migrated_tools_config =3D galaxy_migrated_tool_conf_fil= e, + new_file_path =3D galaxy_tempfiles, + running_functional_tests =3D True, + shed_tool_data_table_config =3D shed_tool_data_table_co= nf_file, + shed_tool_path =3D galaxy_shed_tool_path, + template_path =3D "templates", + tool_config_file =3D ','.join( [ galaxy_tool_conf_file,= galaxy_shed_tool_conf_file ] ), + tool_data_path =3D tool_data_path, + tool_data_table_config_path =3D galaxy_tool_data_table_= conf_file, + tool_dependency_dir =3D tool_dependency_dir, + tool_path =3D tool_path, + tool_parse_help =3D False, + tool_sheds_config_file =3D galaxy_tool_sheds_conf_file, + update_integrated_tool_panel =3D False, + use_heartbeat =3D False ) + galaxy_config_file =3D os.environ.get( 'GALAXY_INSTALL_TEST_INI_FILE',= None ) + # If the user has passed in a path for the .ini file, do not overwrite= it. + if not galaxy_config_file: + galaxy_config_file =3D os.path.join( galaxy_test_tmp_dir, 'install= _test_tool_shed_repositories_wsgi.ini' ) + config_items =3D [] + for label in kwargs: + config_tuple =3D label, kwargs[ label ] + config_items.append( config_tuple ) + # Write a temporary file, based on universe_wsgi.ini.sample, using= the configuration options defined above. + generate_config_file( 'universe_wsgi.ini.sample', galaxy_config_fi= le, config_items ) + kwargs[ 'tool_config_file' ] =3D [ galaxy_tool_conf_file, galaxy_shed_= tool_conf_file ] + # Set the global_conf[ '__file__' ] option to the location of the temp= orary .ini file, which gets passed to set_metadata.sh. + kwargs[ 'global_conf' ] =3D get_webapp_global_conf() + kwargs[ 'global_conf' ][ '__file__' ] =3D galaxy_config_file # ---- Build Galaxy Application --------------------------------------= ------------=20 - global_conf =3D { '__file__' : 'universe_wsgi.ini.sample' } if not database_connection.startswith( 'sqlite://' ): kwargs[ 'database_engine_option_max_overflow' ] =3D '20' kwargs[ 'database_engine_option_pool_size' ] =3D '10' - app =3D UniverseApplication( admin_users =3D 'test@bx.psu.edu', - allow_user_creation =3D True, - allow_user_deletion =3D True, - allow_library_path_paste =3D True, - database_connection =3D database_connection, - datatype_converters_config_file =3D "dataty= pe_converters_conf.xml.sample", - file_path =3D galaxy_file_path, - global_conf =3D global_conf, - id_secret =3D galaxy_encode_secret, - job_queue_workers =3D 5, - log_destination =3D "stdout", - migrated_tools_config =3D galaxy_migrated_t= ool_conf_file, - new_file_path =3D galaxy_tempfiles, - running_functional_tests=3DTrue, - shed_tool_data_table_config =3D shed_tool_d= ata_table_conf_file, - shed_tool_path =3D galaxy_shed_tool_path, - template_path =3D "templates", - tool_config_file =3D [ galaxy_tool_conf_fil= e, galaxy_shed_tool_conf_file ], - tool_data_path =3D tool_data_path, - tool_data_table_config_path =3D galaxy_tool= _data_table_conf_file, - tool_dependency_dir =3D tool_dependency_dir, - tool_path =3D tool_path, - tool_parse_help =3D False, - tool_sheds_config_file =3D galaxy_tool_shed= s_conf_file, - update_integrated_tool_panel =3D False, - use_heartbeat =3D False, - **kwargs ) + kwargs[ 'config_file' ] =3D galaxy_config_file + app =3D UniverseApplication( **kwargs ) =20 log.info( "Embedded Galaxy application started" ) =20 # ---- Run galaxy webserver ------------------------------------------= ------------ server =3D None - webapp =3D buildapp.app_factory( dict( database_file=3Ddatabase_connec= tion ), - use_translogger=3DFalse, - static_enabled=3DFalse, - app=3Dapp ) + global_conf =3D get_webapp_global_conf() + global_conf[ 'database_file' ] =3D database_connection + webapp =3D buildapp.app_factory( global_conf, + use_translogger=3DFalse, + static_enabled=3DSTATIC_ENABLED, + app=3Dapp ) =20 # Serve the app on a specified or random port. if galaxy_test_port is not None: @@ -976,6 +1057,7 @@ repositories_passed.append( dict( name=3Dname, own= er=3Downer, changeset_revision=3Dchangeset_revision ) ) params[ 'tools_functionally_correct' ] =3D True params[ 'do_not_test' ] =3D False + params[ 'test_install_error' ] =3D False register_test_result( galaxy_tool_shed_url,=20 metadata_revision_id,=20 repository_status,=20 @@ -1027,6 +1109,7 @@ repositories_failed.append( dict( name=3Dname, own= er=3Downer, changeset_revision=3Dchangeset_revision ) ) set_do_not_test =3D not is_latest_downloadable_rev= ision( galaxy_tool_shed_url, repository_info_dict ) params[ 'tools_functionally_correct' ] =3D False + params[ 'test_install_error' ] =3D False params[ 'do_not_test' ] =3D str( set_do_not_test ) register_test_result( galaxy_tool_shed_url,=20 metadata_revision_id,=20 diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/unit/datatypes/dataproviders/tempfilecache.py --- /dev/null +++ b/test/unit/datatypes/dataproviders/tempfilecache.py @@ -0,0 +1,47 @@ + +import os +import tempfile + +import logging +logging.getLogger( __name__ ) +log =3D logging + +class TempFileCache( object ): + """ + Creates and caches tempfiles with/based-on the given contents. + """ + def __init__( self, logger=3DNone ): + if logger: + global log + log =3D logger + super( TempFileCache, self ).__init__() + self.clear() + + def clear( self ): + self.delete_tmpfiles() + self._content_dict =3D {} + + def create_tmpfile( self, contents ): + if not hasattr( self, '_content_dict' ): + self.set_up_tmpfiles() + + if contents not in self._content_dict: + # create a named tmp and write contents to it, return filename + tmpfile =3D tempfile.NamedTemporaryFile( delete=3DFalse ) + tmpfile.write( contents ) + tmpfile.close() + log.debug( 'created tmpfile.name: %s', tmpfile.name ) + self._content_dict[ contents ] =3D tmpfile.name + + else: + log.debug( '(cached): %s', self._content_dict[ contents ] ) + return self._content_dict[ contents ] + + def delete_tmpfiles( self ): + if not hasattr( self, '_content_dict' ) or not self._content_dict: + return + for tmpfile_contents in self._content_dict: + tmpfile =3D self._content_dict[ tmpfile_contents ] + if os.path.exists( tmpfile ): + log.debug( 'unlinking tmpfile: %s', tmpfile ) + os.unlink( tmpfile ) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/unit/datatypes/dataproviders/test_base_dataproviders= .py --- /dev/null +++ b/test/unit/datatypes/dataproviders/test_base_dataproviders.py @@ -0,0 +1,370 @@ +""" +Unit tests for base DataProviders. +.. seealso:: galaxy.datatypes.dataproviders.base +""" +# currently because of dataproviders.dataset importing galaxy.model this d= oesn't work +#TODO: fix imports there after dist and retry + +#TODO: fix off by ones in FilteredDataProvider counters + +import unittest +import StringIO + +import tempfilecache +import utility + +log =3D utility.set_up_filelogger( __name__ + '.log' ) + +utility.add_galaxy_lib_to_path( '/test/unit/datatypes/dataproviders' ) +from galaxy.datatypes import dataproviders + + +class BaseTestCase( unittest.TestCase ): + default_file_contents =3D """ + One + Two + Three + """ + + @classmethod + def setUpClass( cls ): + log.debug( 'CLASS %s %s', ( '_' * 40 ), cls.__name__ ) + + @classmethod + def tearDownClass( cls ): + log.debug( 'CLASS %s %s\n\n', ( '_' * 40 ), cls.__name__ ) + + def __init__( self, *args ): + unittest.TestCase.__init__( self, *args ) + self.tmpfiles =3D tempfilecache.TempFileCache( log ) + + def setUp( self ): + log.debug( 'BEGIN %s %s', ( '.' * 40 ), self._testMethodName ) + if self._testMethodDoc: + log.debug( ' """%s"""', self._testMethodDoc.strip() ) + + def tearDown( self ): + self.tmpfiles.clear() + log.debug( 'END\n' ) + + def format_tmpfile_contents( self, contents=3DNone ): + contents =3D contents or self.default_file_contents + contents =3D utility.clean_multiline_string( contents ) + log.debug( 'file contents:\n%s', contents ) + return contents + + +class Test_BaseDataProvider( BaseTestCase ): + provider_class =3D dataproviders.base.DataProvider + + def contents_provider_and_data( self, + filename=3DNone, contents=3DNone, source=3DNone, *provider_arg= s, **provider_kwargs ): + # to remove boiler plate + # returns file content string, provider used, and data list + if not filename: + contents =3D self.format_tmpfile_contents( contents ) + filename =3D self.tmpfiles.create_tmpfile( contents ) + #TODO: if filename, contents =3D=3D None + if not source: + source =3D open( filename ) + provider =3D self.provider_class( source, *provider_args, **provid= er_kwargs ) + log.debug( 'provider: %s', provider ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + return ( contents, provider, data ) + + def test_iterators( self ): + source =3D ( x for x in xrange( 1, 10 ) ) + provider =3D self.provider_class( source ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + self.assertEqual( data, [ x for x in xrange( 1, 10 ) ] ) + + source =3D [ x for x in xrange( 1, 10 ) ] + provider =3D self.provider_class( source ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + self.assertEqual( data, [ x for x in xrange( 1, 10 ) ] ) + + source =3D ( x for x in xrange( 1, 10 ) ) + provider =3D self.provider_class( source ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + self.assertEqual( data, [ x for x in xrange( 1, 10 ) ] ) + + def test_validate_source( self ): + """validate_source should throw an error if the source doesn't hav= e attr '__iter__' + """ + def non_iterator_dprov( source ): + return self.provider_class( source ) + self.assertRaises( dataproviders.exceptions.InvalidDataProviderSou= rce, + non_iterator_dprov, 'one two three' ) + self.assertRaises( dataproviders.exceptions.InvalidDataProviderSou= rce, + non_iterator_dprov, 40 ) + + def test_writemethods( self ): + """should throw an error if any write methods are called + """ + source =3D ( x for x in xrange( 1, 10 ) ) + provider =3D self.provider_class( source ) + # should throw error + def call_method( provider, method_name, *args ): + method =3D getattr( provider, method_name ) + return method( *args ) + self.assertRaises( NotImplementedError, call_method, provider, 'tr= uncate', 20 ) + self.assertRaises( NotImplementedError, call_method, provider, 'wr= ite', 'bler' ) + self.assertRaises( NotImplementedError, call_method, provider, 'wr= itelines', [ 'one', 'two' ] ) + + def test_readlines( self ): + """readlines should return all the data in list form + """ + source =3D ( x for x in xrange( 1, 10 ) ) + provider =3D self.provider_class( source ) + data =3D provider.readlines() + log.debug( 'data: %s', str( data ) ) + self.assertEqual( data, [ x for x in xrange( 1, 10 ) ] ) + + def test_stringio( self ): + """should work with StringIO + """ + contents =3D utility.clean_multiline_string( """ + One + Two + Three + """ ) + source =3D StringIO.StringIO( contents ) + provider =3D self.provider_class( source ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + # provider should call close on file + self.assertEqual( ''.join( data ), contents ) + self.assertTrue( source.closed ) + + def test_file( self ): + """should work with files + """ + ( contents, provider, data ) =3D self.contents_provider_and_data() + self.assertEqual( ''.join( data ), contents ) + # provider should call close on file + self.assertTrue( isinstance( provider.source, file ) ) + self.assertTrue( provider.source.closed ) + + +class Test_FilteredDataProvider( Test_BaseDataProvider ): + provider_class =3D dataproviders.base.FilteredDataProvider + + def assertCounters( self, provider, read, valid, returned ): + self.assertEqual( provider.num_data_read, read ) + self.assertEqual( provider.num_valid_data_read, valid ) + self.assertEqual( provider.num_data_returned, returned ) + + def test_counters( self ): + """should count: lines read, lines that passed the filter, lines r= eturned + """ + ( contents, provider, data ) =3D self.contents_provider_and_data() + self.assertCounters( provider, 3, 3, 3 ) + + def test_filter_fn( self ): + """should filter out lines using filter_fn and set counters proper= ly + based on filter + """ + def filter_ts( string ): + if string.lower().startswith( 't' ): + return None + return string + ( contents, provider, data ) =3D self.contents_provider_and_data( = filter_fn=3Dfilter_ts ) + self.assertCounters( provider, 3, 1, 1 ) + + +class Test_LimitedOffsetDataProvider( Test_FilteredDataProvider ): + provider_class =3D dataproviders.base.LimitedOffsetDataProvider + + def test_offset_1( self ): + """when offset is 1, should skip first + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = offset=3D1 ) + self.assertEqual( data, [ 'Two\n', 'Three\n' ] ) + self.assertCounters( provider, 3, 3, 2 ) + + def test_offset_all( self ): + """when offset >=3D num lines, should return empty list + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = offset=3D4 ) + self.assertEqual( data, [] ) + self.assertCounters( provider, 3, 3, 0 ) + + def test_offset_none( self ): + """when offset is 0, should return all + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = offset=3D0 ) + self.assertEqual( ''.join( data ), contents ) + self.assertCounters( provider, 3, 3, 3 ) + + def test_offset_negative( self ): + """when offset is negative, should return all + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = offset=3D-1 ) + self.assertEqual( ''.join( data ), contents ) + self.assertCounters( provider, 3, 3, 3 ) + + def test_limit_1( self ): + """when limit is one, should return first + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = limit=3D1 ) + self.assertEqual( data, [ 'One\n' ] ) + #TODO: currently reads 2 in all counters before ending + #self.assertCounters( provider, 1, 1, 1 ) + + def test_limit_all( self ): + """when limit >=3D num lines, should return all + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = limit=3D4 ) + self.assertEqual( ''.join( data ), contents ) + self.assertCounters( provider, 3, 3, 3 ) + + def test_limit_zero( self ): + """when limit >=3D num lines, should return empty list + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = limit=3D0 ) + self.assertEqual( data, [] ) + #TODO: currently reads 1 before ending + self.assertCounters( provider, 3, 0, 0 ) + + def test_limit_zero( self ): + """when limit is None, should return all + """ + ( contents, provider, data ) =3D self.contents_provider_and_data( = limit=3DNone ) + self.assertEqual( ''.join( data ), contents ) + self.assertCounters( provider, 3, 3, 3 ) + + #TODO: somehow re-use tmpfile here + def test_limit_with_offset( self ): + def limit_offset_combo( limit, offset, data_should_be, read, valid= , returned ): + ( contents, provider, data ) =3D self.contents_provider_and_da= ta( limit=3Dlimit, offset=3Doffset ) + self.assertEqual( data, data_should_be ) + #self.assertCounters( provider, read, valid, returned ) + test_data =3D [ + ( 0, 0, [], 0, 0, 0 ), + ( 1, 0, [ 'One\n' ], 1, 1, 1 ), + ( 2, 0, [ 'One\n', 'Two\n' ], 2, 2, 2 ), + ( 3, 0, [ 'One\n', 'Two\n', 'Three\n' ], 3, 3, 3 ), + ( 1, 1, [ 'Two\n' ], 1, 1, 1 ), + ( 2, 1, [ 'Two\n', 'Three\n' ], 2, 2, 2 ), + ( 3, 1, [ 'Two\n', 'Three\n' ], 2, 2, 2 ), + ( 1, 2, [ 'Three\n' ], 1, 1, 1 ), + ( 2, 2, [ 'Three\n' ], 1, 1, 1 ), + ( 3, 2, [ 'Three\n' ], 1, 1, 1 ), + ] + for test in test_data: + log.debug( 'limit_offset_combo: %s', ', '.join([ str( e ) for = e in test ]) ) + limit_offset_combo( *test ) + + def test_limit_with_offset_and_filter( self ): + def limit_offset_combo( limit, offset, data_should_be, read, valid= , returned ): + def only_ts( string ): + if not string.lower().startswith( 't' ): + return None + return string + ( contents, provider, data ) =3D self.contents_provider_and_da= ta( + limit=3Dlimit, offset=3Doffset, filter_fn=3Donly_ts ) + self.assertEqual( data, data_should_be ) + #self.assertCounters( provider, read, valid, returned ) + test_data =3D [ + ( 0, 0, [], 0, 0, 0 ), + ( 1, 0, [ 'Two\n' ], 1, 1, 1 ), + ( 2, 0, [ 'Two\n', 'Three\n' ], 2, 2, 2 ), + ( 3, 0, [ 'Two\n', 'Three\n' ], 2, 2, 2 ), + ( 1, 1, [ 'Three\n' ], 1, 1, 1 ), + ( 2, 1, [ 'Three\n' ], 1, 1, 1 ), + ( 1, 2, [], 0, 0, 0 ), + ] + for test in test_data: + log.debug( 'limit_offset_combo: %s', ', '.join([ str( e ) for = e in test ]) ) + limit_offset_combo( *test ) + + +class Test_MultiSourceDataProvider( BaseTestCase ): + provider_class =3D dataproviders.base.MultiSourceDataProvider + + def contents_and_tmpfile( self, contents=3DNone ): + #TODO: hmmmm... + contents =3D contents or self.default_file_contents + contents =3D utility.clean_multiline_string( contents ) + return ( contents, self.tmpfiles.create_tmpfile( contents ) ) + + def test_multiple_sources( self ): + # clean the following contents, write them to tmpfiles, open them, + # and pass as a list to the provider + contents =3D [ + """ + One + Two + Three + Four + Five + """, + """ + Six + Seven + Eight + Nine + Ten + """, + """ + Eleven + Twelve! (<-- http://youtu.be/JZshZp-cxKg) + """ + ] + contents =3D [ utility.clean_multiline_string( c ) for c in conten= ts ] + source_list =3D [ open( self.tmpfiles.create_tmpfile( c ) ) for c = in contents ] + + provider =3D self.provider_class( source_list ) + log.debug( 'provider: %s', provider ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + self.assertEqual( ''.join( data ), ''.join( contents) ) + + def test_multiple_compound_sources( self ): + # clean the following contents, write them to tmpfiles, open them, + # and pass as a list to the provider + contents =3D [ + """ + One + Two + Three + Four + Five + """, + """ + Six + Seven + Eight + Nine + Ten + """, + """ + Eleven + Twelve! (<-- http://youtu.be/JZshZp-cxKg) + """ + ] + contents =3D [ utility.clean_multiline_string( c ) for c in conten= ts ] + source_list =3D [ open( self.tmpfiles.create_tmpfile( c ) ) for c = in contents ] + + def no_Fs( string ): + return None if string.startswith( 'F' ) else string + def no_youtube( string ): + return None if ( 'youtu.be' in string ) else string + source_list =3D [ + dataproviders.base.LimitedOffsetDataProvider( source_list[0], = filter_fn=3Dno_Fs, limit=3D2, offset=3D1 ), + dataproviders.base.LimitedOffsetDataProvider( source_list[1], = limit=3D1, offset=3D3 ), + dataproviders.base.FilteredDataProvider( source_list[2], filte= r_fn=3Dno_youtube ), + ] + provider =3D self.provider_class( source_list ) + log.debug( 'provider: %s', provider ) + data =3D list( provider ) + log.debug( 'data: %s', str( data ) ) + self.assertEqual( ''.join( data ), 'Two\nThree\nNine\nEleven\n' ) + + +if __name__ =3D=3D '__main__': + unittest.main() diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/unit/datatypes/dataproviders/utility.py --- /dev/null +++ b/test/unit/datatypes/dataproviders/utility.py @@ -0,0 +1,45 @@ +""" +Unit test utilities. +""" + +import os +import sys +import logging +import textwrap + +def set_up_filelogger( logname, level=3Dlogging.DEBUG ): + """ + Sets up logging to a file named `logname` + (removing it first if it already exists). + + Usable with 'nosetests' to get logging msgs from failed tests + (no logfile created). + Usable with 'nosetests --nologcapture' to get logging msgs for all tes= ts + (in logfile). + """ + if os.path.exists( logname ): os.unlink( logname ) + logging.basicConfig( filename=3Dlogname, level=3Dlogging.DEBUG ) + return logging + +def add_galaxy_lib_to_path( this_dir_relative_to_root ): + """ + Adds `<galaxy>/lib` to `sys.path` given the scripts directory relative + to `<galaxy>`. + .. example:: + utility.add_galaxy_lib_to_path( '/test/unit/datatypes/dataprovider= s' ) + """ + glx_lib =3D os.path.join( os.getcwd().replace( this_dir_relative_to_ro= ot, '' ), 'lib' ) + sys.path.append( glx_lib ) + +def clean_multiline_string( multiline_string, sep=3D'\n' ): + """ + Dedent, split, remove first and last empty lines, rejoin. + """ + multiline_string =3D textwrap.dedent( multiline_string ) + string_list =3D multiline_string.split( sep ) + if not string_list[0]: + string_list =3D string_list[1:] + if not string_list[-1]: + string_list =3D string_list[:-1] + #return '\n'.join( docstrings ) + return ''.join([ ( s + '\n' ) for s in string_list ]) diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/unit/test_dataproviders.pyc Binary file test/unit/test_dataproviders.pyc has changed diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c test/unit/test_tool_loader.pyc Binary file test/unit/test_tool_loader.pyc has changed diff -r a360e1b7b506450385be74b2c6b7762d3e794bbd -r 79ae7df72fba2e141791bdb= 8fdf2bb372fa3787c tools/ngs_rna/cuffdiff_wrapper.py --- a/tools/ngs_rna/cuffdiff_wrapper.py +++ /dev/null @@ -1,241 +0,0 @@ -#!/usr/bin/env python - -# Wrapper supports Cuffdiff versions v1.3.0-v2.0 - -import optparse, os, shutil, subprocess, sys, tempfile - -def group_callback( option, op_str, value, parser ): - groups =3D [] - flist =3D [] - for arg in parser.rargs: - arg =3D arg.strip() - if arg[0] is "-": - break - elif arg[0] is ",": - groups.append(flist) - flist =3D [] - else: - flist.append(arg) - groups.append(flist) - - setattr(parser.values, option.dest, groups) - =20 -def label_callback( option, op_str, value, parser ): - labels =3D [] - for arg in parser.rargs: - arg =3D arg.strip() - if arg[0] is "-": - break - else: - labels.append(arg) - - setattr(parser.values, option.dest, labels) - -def stop_err( msg ): - sys.stderr.write( "%s\n" % msg ) - sys.exit() - =20 -# Copied from sam_to_bam.py: -def check_seq_file( dbkey, cached_seqs_pointer_file ): - seq_path =3D '' - for line in open( cached_seqs_pointer_file ): - line =3D line.rstrip( '\r\n' ) - if line and not line.startswith( '#' ) and line.startswith( 'index= ' ): - fields =3D line.split( '\t' ) - if len( fields ) < 3: - continue - if fields[1] =3D=3D dbkey: - seq_path =3D fields[2].strip() - break - return seq_path - -def __main__(): - #Parse Command Line - parser =3D optparse.OptionParser() - =20 - # Cuffdiff options. - parser.add_option( '-s', '--inner-dist-std-dev', dest=3D'inner_dist_st= d_dev', help=3D'The standard deviation for the distribution on inner distan= ces between mate pairs. The default is 20bp.' ) - parser.add_option( '-p', '--num-threads', dest=3D'num_threads', help= =3D'Use this many threads to align reads. The default is 1.' ) - parser.add_option( '-m', '--inner-mean-dist', dest=3D'inner_mean_dist'= , help=3D'This is the expected (mean) inner distance between mate pairs. \ - = For, example, for paired end runs with fragments selected at 300bp, \ - = where each end is 50bp, you should set -r to be 200. The default is 4= 5bp.') - parser.add_option( '-c', '--min-alignment-count', dest=3D'min_alignmen= t_count', help=3D'The minimum number of alignments in a locus for needed to= conduct significance testing on changes in that locus observed between sam= ples. If no testing is performed, changes in the locus are deemed not signf= icant, and the locus\' observed changes don\'t contribute to correction for= multiple testing. The default is 1,000 fragment alignments (up to 2,000 pa= ired reads).' ) - parser.add_option( '--FDR', dest=3D'FDR', help=3D'The allowed false di= scovery rate. The default is 0.05.' ) - parser.add_option( '-u', '--multi-read-correct', dest=3D'multi_read_co= rrect', action=3D"store_true", help=3D'Tells Cufflinks to do an initial est= imation procedure to more accurately weight reads mapping to multiple locat= ions in the genome') - parser.add_option( '--library-norm-method', dest=3D'library_norm_metho= d' ) - parser.add_option( '--dispersion-method', dest=3D'dispersion_method' ) - - # Advanced Options:=09 - parser.add_option( '--num-importance-samples', dest=3D'num_importance_= samples', help=3D'Sets the number of importance samples generated for each = locus during abundance estimation. Default: 1000' ) - parser.add_option( '--max-mle-iterations', dest=3D'max_mle_iterations'= , help=3D'Sets the number of iterations allowed during maximum likelihood e= stimation of abundances. Default: 5000' ) - =20 - # Wrapper / Galaxy options. - parser.add_option( '-f', '--files', dest=3D'groups', action=3D"callbac= k", callback=3Dgroup_callback, help=3D"Groups to be processed, groups are s= eparated by spaces, replicates in a group comma separated. group1_rep1,grou= p1_rep2 group2_rep1,group2_rep2, ..., groupN_rep1, groupN_rep2" ) - parser.add_option( '-A', '--inputA', dest=3D'inputA', help=3D'A transc= ript GTF file produced by cufflinks, cuffcompare, or other source.') - parser.add_option( '-1', '--input1', dest=3D'input1', help=3D'File of = RNA-Seq read alignments in the SAM format. SAM is a standard short read ali= gnment, that allows aligners to attach custom tags to individual alignments= , and Cufflinks requires that the alignments you supply have some of these = tags. Please see Input formats for more details.' ) - parser.add_option( '-2', '--input2', dest=3D'input2', help=3D'File of = RNA-Seq read alignments in the SAM format. SAM is a standard short read ali= gnment, that allows aligners to attach custom tags to individual alignments= , and Cufflinks requires that the alignments you supply have some of these = tags. Please see Input formats for more details.' ) - - # Label options - parser.add_option('-L', '--labels', dest=3D'labels', action=3D"callbac= k", callback=3Dlabel_callback, help=3D"Labels for the groups the replicates= are in.") - =20 - # Normalization options. - parser.add_option( "-N", "--quartile-normalization", dest=3D"do_normal= ization", action=3D"store_true" ) - - # Bias correction options. - parser.add_option( '-b', dest=3D'do_bias_correction', action=3D"store_= true", help=3D'Providing Cufflinks with a multifasta file via this option i= nstructs it to run our new bias detection and correction algorithm which ca= n significantly improve accuracy of transcript abundance estimates.') - parser.add_option( '', '--dbkey', dest=3D'dbkey', help=3D'The build of= the reference dataset' ) - parser.add_option( '', '--index_dir', dest=3D'index_dir', help=3D'GALA= XY_DATA_INDEX_DIR' ) - parser.add_option( '', '--ref_file', dest=3D'ref_file', help=3D'The re= ference dataset from the history' ) - - # Outputs. - parser.add_option( "--isoforms_fpkm_tracking_output", dest=3D"isoforms= _fpkm_tracking_output" ) - parser.add_option( "--genes_fpkm_tracking_output", dest=3D"genes_fpkm_= tracking_output" ) - parser.add_option( "--cds_fpkm_tracking_output", dest=3D"cds_fpkm_trac= king_output" ) - parser.add_option( "--tss_groups_fpkm_tracking_output", dest=3D"tss_gr= oups_fpkm_tracking_output" ) - parser.add_option( "--isoforms_exp_output", dest=3D"isoforms_exp_outpu= t" ) - parser.add_option( "--genes_exp_output", dest=3D"genes_exp_output" ) - parser.add_option( "--tss_groups_exp_output", dest=3D"tss_groups_exp_o= utput" ) - parser.add_option( "--cds_exp_fpkm_tracking_output", dest=3D"cds_exp_f= pkm_tracking_output" ) - parser.add_option( "--splicing_diff_output", dest=3D"splicing_diff_out= put" ) - parser.add_option( "--cds_diff_output", dest=3D"cds_diff_output" ) - parser.add_option( "--promoters_diff_output", dest=3D"promoters_diff_o= utput" ) - =20 - (options, args) =3D parser.parse_args() - =20 - # output version # of tool - try: - tmp =3D tempfile.NamedTemporaryFile().name - tmp_stdout =3D open( tmp, 'wb' ) - proc =3D subprocess.Popen( args=3D'cuffdiff --no-update-check 2>&1= ', shell=3DTrue, stdout=3Dtmp_stdout ) - tmp_stdout.close() - returncode =3D proc.wait() - stdout =3D None - for line in open( tmp_stdout.name, 'rb' ): - if line.lower().find( 'cuffdiff v' ) >=3D 0: - stdout =3D line.strip() - break - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Cuffdiff version\n' ) - =20 - # If doing bias correction, set/link to sequence file. - if options.do_bias_correction: - if options.ref_file !=3D 'None': - # Sequence data from history. - # Create symbolic link to ref_file so that index will be creat= ed in working directory. - seq_path =3D "ref.fa" - os.symlink( options.ref_file, seq_path ) - else: - # Sequence data from loc file. - cached_seqs_pointer_file =3D os.path.join( options.index_dir, = 'sam_fa_indices.loc' ) - if not os.path.exists( cached_seqs_pointer_file ): - stop_err( 'The required file (%s) does not exist.' % cache= d_seqs_pointer_file ) - # If found for the dbkey, seq_path will look something like /g= alaxy/data/equCab2/sam_index/equCab2.fa, - # and the equCab2.fa file will contain fasta sequences. - seq_path =3D check_seq_file( options.dbkey, cached_seqs_pointe= r_file ) - if seq_path =3D=3D '': - stop_err( 'No sequence data found for dbkey %s, so bias co= rrection cannot be used.' % options.dbkey ) =20 - =20 - # Build command. - =20 - # Base; always use quiet mode to avoid problems with storing log outpu= t. - cmd =3D "cuffdiff --no-update-check -q" - =20 - # Add options. - if options.library_norm_method: - cmd +=3D ( " --library-norm-method %s" % options.library_norm_meth= od ) - if options.dispersion_method: - cmd +=3D ( " --dispersion-method %s" % options.dispersion_method ) - if options.inner_dist_std_dev: - cmd +=3D ( " -s %i" % int ( options.inner_dist_std_dev ) ) - if options.num_threads: - cmd +=3D ( " -p %i" % int ( options.num_threads ) ) - if options.inner_mean_dist: - cmd +=3D ( " -m %i" % int ( options.inner_mean_dist ) ) - if options.min_alignment_count: - cmd +=3D ( " -c %i" % int ( options.min_alignment_count ) ) - if options.FDR: - cmd +=3D ( " --FDR %f" % float( options.FDR ) ) - if options.multi_read_correct: - cmd +=3D ( " -u" ) - if options.num_importance_samples: - cmd +=3D ( " --num-importance-samples %i" % int ( options.num_impo= rtance_samples ) ) - if options.max_mle_iterations: - cmd +=3D ( " --max-mle-iterations %i" % int ( options.max_mle_iter= ations ) ) - if options.do_normalization: - cmd +=3D ( " -N" ) - if options.do_bias_correction: - cmd +=3D ( " -b %s" % seq_path ) - =20 - # Add inputs. - # For replicate analysis: group1_rep1,group1_rep2 groupN_rep1,groupN_r= ep2 - if options.groups: - cmd +=3D " --labels " - for label in options.labels: - cmd +=3D '"%s",' % label - cmd =3D cmd[:-1] - - cmd +=3D " " + options.inputA + " " - - for group in options.groups: - for filename in group: - cmd +=3D filename + "," - cmd =3D cmd[:-1] + " " - else:=20 - cmd +=3D " " + options.inputA + " " + options.input1 + " " + optio= ns.input2 - =20 - # Debugging. - print cmd - - # Run command. - try: - tmp_name =3D tempfile.NamedTemporaryFile().name - tmp_stderr =3D open( tmp_name, 'wb' ) - proc =3D subprocess.Popen( args=3Dcmd, shell=3DTrue, stderr=3Dtmp_= stderr.fileno() ) - returncode =3D proc.wait() - tmp_stderr.close() - =20 - # Get stderr, allowing for case where it's very large. - tmp_stderr =3D open( tmp_name, 'rb' ) - stderr =3D '' - buffsize =3D 1048576 - try: - while True: - stderr +=3D tmp_stderr.read( buffsize ) - if not stderr or len( stderr ) % buffsize !=3D 0: - break - except OverflowError: - pass - tmp_stderr.close() - =20 - # Error checking. - if returncode !=3D 0: - raise Exception, stderr - =20 - # check that there are results in the output file - if len( open( "isoforms.fpkm_tracking", 'rb' ).read().strip() ) = =3D=3D 0: - raise Exception, 'The main output file is empty, there may be = an error with your input file or settings.' - except Exception, e: - stop_err( 'Error running cuffdiff. ' + str( e ) ) - - =20 - # Copy output files to specified files. - try: - shutil.copyfile( "isoforms.fpkm_tracking", options.isoforms_fpkm_t= racking_output ) - shutil.copyfile( "genes.fpkm_tracking", options.genes_fpkm_trackin= g_output ) - shutil.copyfile( "cds.fpkm_tracking", options.cds_fpkm_tracking_ou= tput ) - shutil.copyfile( "tss_groups.fpkm_tracking", options.tss_groups_fp= km_tracking_output ) - shutil.copyfile( "isoform_exp.diff", options.isoforms_exp_output ) - shutil.copyfile( "gene_exp.diff", options.genes_exp_output ) - shutil.copyfile( "tss_group_exp.diff", options.tss_groups_exp_outp= ut ) - shutil.copyfile( "splicing.diff", options.splicing_diff_output ) - shutil.copyfile( "cds.diff", options.cds_diff_output ) - shutil.copyfile( "cds_exp.diff", options.cds_exp_fpkm_tracking_out= put ) - shutil.copyfile( "promoters.diff", options.promoters_diff_output )= =20 - except Exception, e: - stop_err( 'Error in cuffdiff:\n' + str( e ) ) - -if __name__=3D=3D"__main__": __main__() This diff is so big that we needed to truncate the remainder. https://bitbucket.org/galaxy/galaxy-central/commits/40c9834811eb/ Changeset: 40c9834811eb User: saketkc Date: 2013-08-06 09:31:21 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r cf53a00bcf1d279072ec279e6531f211992b4f3e -r 40c9834811ebfbefb423155= 3c922ff4c44905c63 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/d33f8c5396a8/ Changeset: d33f8c5396a8 User: saketkc Date: 2013-08-07 15:21:51 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r f33c054d6d5b75ae545248d71ec559d74b4fa636 -r d33f8c5396a8825b450432a= 8c443e1592a360885 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/a968c0cae563/ Changeset: a968c0cae563 User: saketkc Date: 2013-08-28 19:15:32 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 22a4f03c1fe40dedcb7e6f11510d58ada8e9c458 -r a968c0cae5639f3be5ffdd9= 31df909c215f43a43 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/4c1eb0c91fc6/ Changeset: 4c1eb0c91fc6 User: saketkc Date: 2013-08-31 18:30:53 Summary: Automated merge with ssh://bitbucket.org/galaxy/galaxy-central Affected #: 1 file diff -r 0470feeb593f9797fa9fd19dfdac4751a7ca788b -r 4c1eb0c91fc6e3085948ef1= 6eb88d18ea626e7d3 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) https://bitbucket.org/galaxy/galaxy-central/commits/dcd9809d0239/ Changeset: dcd9809d0239 User: jgoecks Date: 2013-09-11 18:16:14 Summary: Merged in saketkc/galaxy-central (pull request #184) VCFTools Incompatible with VCF4.1 Affected #: 1 file diff -r 228f1b4066be9fc49f6f07ff6867566836134c67 -r dcd9809d0239c7dc80cec3b= 2a01d7bded4a8c088 tools/vcf_tools/vcfClass.py --- a/tools/vcf_tools/vcfClass.py +++ b/tools/vcf_tools/vcfClass.py @@ -12,12 +12,13 @@ self.hasHeader =3D True self.headerText =3D "" self.headerTitles =3D "" + self.vcfFormat =3D "" #self.headerInfoText =3D "" #self.headerFormatText =3D "" =20 # Store the info and format tags as well as the lines that describe # them in a dictionary. - self.numberDataSets =3D 0=20 + self.numberDataSets =3D 0 self.includedDataSets =3D {} self.infoHeaderTags =3D {} self.infoHeaderString =3D {} @@ -63,6 +64,7 @@ # Determine the type of information in the header line. def getHeaderLine(self, filename, writeOut): self.headerLine =3D self.filehandle.readline().rstrip("\n") + if self.headerLine.startswith("##fileformat"): success =3D self.getvcf= Format() if self.headerLine.startswith("##INFO"): success =3D self.headerInfo(w= riteOut, "info") elif self.headerLine.startswith("##FORMAT"): success =3D self.headerIn= fo(writeOut, "format") elif self.headerLine.startswith("##FILE"): success =3D self.headerFile= s(writeOut) @@ -72,6 +74,18 @@ =20 return success =20 +# Read VCF format + def getvcfFormat(self): + try: + self.vcfFormat =3D self.headerLine.split("=3D",1)[1] + self.vcfFormat =3D float( self.vcfFormat.split("VCFv",1)[1] )## = Extract the version number rather than the whole string + except IndexError: + print >> sys.stderr, "\nError parsing the fileformat" + print >> sys.stderr, "The following fileformat header is wrongly= formatted: ", self.headerLine + exit(1) + return True + + # Read information on an info field from the header line. def headerInfo(self, writeOut, lineType): tag =3D self.headerLine.split("=3D",1) @@ -93,11 +107,15 @@ # an integer or a '.' to indicate variable number of entries. if tagNumber =3D=3D ".": tagNumber =3D "variable" else: - try: tagNumber =3D int(tagNumber) - except ValueError: - print >> sys.stderr, "\nError parsing header. Problem with info t= ag:", tagID - print >> sys.stderr, "Number of fields associated with this tag is= not an integer or '.'" - exit(1) + if self.vcfFormat<4.1: + + try: + tagNumber =3D int(tagNumber) + + except ValueError: + print >> sys.stderr, "\nError parsing header. Problem with in= fo tag:", tagID + print >> sys.stderr, "Number of fields associated with this ta= g is not an integer or '.'" + exit(1) =20 if lineType =3D=3D "info": self.infoHeaderTags[tagID] =3D tagNumber, tagType, tagDescription @@ -161,7 +179,7 @@ return False =20 # If there is no header in the vcf file, close and reopen the -# file so that the first line is avaiable for parsing as a=20 +# file so that the first line is avaiable for parsing as a # vcf record. def noHeader(self, filename, writeOut): if writeOut: print >> sys.stdout, "No header lines present in", filena= me @@ -216,7 +234,7 @@ else: self.hasGenotypes =3D False =20 # Add the reference sequence to the dictionary. If it didn't previously -# exist append the reference sequence to the end of the list as well.=20 +# exist append the reference sequence to the end of the list as well. # This ensures that the order in which the reference sequences appeared # in the header can be preserved. if self.referenceSequence not in self.referenceSequences: @@ -274,7 +292,7 @@ # Check that there are as many fields as in the format field. If not, thi= s must # be because the information is not known. In this case, it is permitted = that # the genotype information is either . or ./. - if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo):=20 + if genotypeInfo[0] =3D=3D "./." or genotypeInfo[0] =3D=3D "." and le= n(self.genotypeFormats) !=3D len(genotypeInfo): self.genotypeFields[ self.samplesList[i] ] =3D "." else: if len(self.genotypeFormats) !=3D len(genotypeInfo): @@ -381,7 +399,7 @@ =20 # First check that the variant class (VC) is listed as SNP. vc =3D self.info.split("VC=3D",1) - if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1)=20 + if vc[1].find(";") !=3D -1: snp =3D vc[1].split(";",1) else: snp =3D [] snp.append(vc[1]) Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.