| Previous changeset 2:d150ac3d853d (2019-08-28) Next changeset 4:0850f2dfba13 (2019-10-09) |
|
Commit message:
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_to_collection commit 8d069684e155d2f5b6fae06d14d98ce41321da53" |
|
modified:
split_file_to_collection.py split_file_to_collection.xml |
|
added:
test-data/chr_000000.txt test-data/chr_000001.txt test-data/chr_000002.txt test-data/chr_000003.txt test-data/chr_000004.txt test-data/chr_000005.txt test-data/chr_000006.txt test-data/chr_000007.txt test-data/chr_000008.txt test-data/chr_000009.txt test-data/chr_000010.txt test-data/chr_000011.txt test-data/chr_000012.txt test-data/chr_000013.txt test-data/chr_000014.txt test-data/chr_000015.txt test-data/chr_000016.txt test-data/chr_000017.txt test-data/chr_000018.txt test-data/chr_000019.txt test-data/chr_000020.txt test-data/chr_000021.txt test-data/chr_000022.txt test-data/chr_000023.txt test-data/karyotype.txt |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a split_file_to_collection.py --- a/split_file_to_collection.py Wed Aug 28 10:55:25 2019 -0400 +++ b/split_file_to_collection.py Tue Sep 10 12:31:15 2019 -0400 |
| [ |
| @@ -140,7 +140,7 @@ new_file_base = [custom_new_file_name, custom_new_file_ext] newfiles = [ - open(out_dir + "/" + new_file_base[0] + "_" + str(count) + new_file_base[1], "w") + open(os.path.join(out_dir, "%s_%06d%s" % (new_file_base[0], count, new_file_base[1])) , "w") for count in range(0, numnew) ] @@ -159,7 +159,7 @@ # keep track in loop of number of records in each file # only used in batch records_in_file = 0 - + # open file with open(in_file, "r") as file: record = "" |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a split_file_to_collection.xml --- a/split_file_to_collection.xml Wed Aug 28 10:55:25 2019 -0400 +++ b/split_file_to_collection.xml Tue Sep 10 12:31:15 2019 -0400 |
| [ |
| b'@@ -50,8 +50,8 @@\n --id_column \'$split_parms.split_by.id_col\'\n --match \'$split_parms.split_by.match_regex\'\n --sub \'$split_parms.split_by.sub_regex\'\n- #else \n- --numnew \'$split_parms.split_by.numnew\' \n+ #else\n+ --numnew \'$split_parms.split_by.numnew\'\n #if $split_parms.split_by.select_allocate.allocate == "random":\n --rand\n --seed \'$split_parms.split_by.rand.seed\'\n@@ -190,10 +190,10 @@\n <param name="select_split_by" value="row"/>\n <param name="top" value="2"/>\n <param name="numnew" value="2"/>\n- <param name="newfilenames" value="test"/> \n+ <param name="newfilenames" value="test"/>\n <output_collection name="list_output_tab" type="list">\n- <element name="test_0.tabular" file="test_0.tabular" ftype="tabular"/>\n- <element name="test_1.tabular" file="test_1.tabular" ftype="tabular"/>\n+ <element name="test_000000.tabular" file="test_0.tabular" ftype="tabular"/>\n+ <element name="test_000001.tabular" file="test_1.tabular" ftype="tabular"/>\n </output_collection>\n </test>\n <test>\n@@ -203,10 +203,44 @@\n <param name="top" value="2"/>\n <param name="numnew" value="2"/>\n <param name="newfilenames" value="batch_tab"/>\n- <param name="allocate" value="batch"/> \n+ <param name="allocate" value="batch"/>\n <output_collection name="list_output_tab" type="list">\n- <element name="batch_tab_0.tabular" file="batch_tab_0.tabular" ftype="tabular"/>\n- <element name="batch_tab_1.tabular" file="batch_tab_1.tabular" ftype="tabular"/>\n+ <element name="batch_tab_000000.tabular" file="batch_tab_0.tabular" ftype="tabular"/>\n+ <element name="batch_tab_000001.tabular" file="batch_tab_1.tabular" ftype="tabular"/>\n+ </output_collection>\n+ </test>\n+ <test>\n+ <param name="select_ftype" value="txt"/>\n+ <param name="input" value="karyotype.txt" ftype="txt"/>\n+ <param name="numnew" value="24"/>\n+ <param name="newfilenames" value="chr"/>\n+ <param name="allocate" value="batch"/>\n+\n+ <output_collection name="list_output_txt" type="list">\n+ <element name="chr_000000.txt" file="chr_000000.txt" ftype="txt"/>\n+ <element name="chr_000001.txt" file="chr_000001.txt" ftype="txt"/>\n+ <element name="chr_000002.txt" file="chr_000002.txt" ftype="txt"/>\n+ <element name="chr_000003.txt" file="chr_000003.txt" ftype="txt"/>\n+ <element name="chr_000004.txt" file="chr_000004.txt" ftype="txt"/>\n+ <element name="chr_000005.txt" file="chr_000005.txt" ftype="txt"/>\n+ <element name="chr_000006.txt" file="chr_000006.txt" ftype="txt"/>\n+ <element name="chr_000007.txt" file="chr_000007.txt" ftype="txt"/>\n+ <element name="chr_000008.txt" file="chr_000008.txt" ftype="txt"/>\n+ <element name="chr_000009.txt" file="chr_000009.txt" ftype="txt"/>\n+ <element name="chr_000010.txt" file="chr_000010.txt" ftype="txt"/>\n+ <element name="chr_000011.txt" file="chr_000011.txt" ftype="txt"/>\n+ <element name="chr_000012.txt" file="chr_000012.txt" ftype="txt"/>\n+ <element name="chr_000013.txt" file="chr_000013.txt" ftype="txt"/>\n+ <element name="chr_000014.txt" file="chr_000014.txt" ftype="txt"/>\n+ <element name="chr_000015.txt" file="chr_000015.txt" ftype="txt"/>\n+ <element name="chr_000016.txt" file="chr_000016.txt" ftype="txt"/>\n+ <element name="chr_000017.txt" file="chr_000017.txt" ftype'..b'am name="newfilenames" value="rand"/>\n <param name="allocate" value="random"/>\n- <param name="seed" value="1010"/> \n+ <param name="seed" value="1010"/>\n <output_collection name="list_output_generic" type="list">\n- <element name="rand_0" file="rand_0.fasta" ftype="fasta"/>\n- <element name="rand_1" file="rand_1.fasta" ftype="fasta"/>\n+ <element name="rand_000000" file="rand_0.fasta" ftype="fasta"/>\n+ <element name="rand_000001" file="rand_1.fasta" ftype="fasta"/>\n </output_collection>\n </test>\n <test>\n@@ -320,27 +354,27 @@\n <param name="newfilenames" value="mol"/>\n <param name="allocate" value="batch"/>\n <output_collection name="list_output_generic" type="list">\n- <element name="mol_0" file="mol_0.sdf" ftype="sdf"/>\n- <element name="mol_1" file="mol_1.sdf" ftype="sdf"/>\n- <element name="mol_2" file="mol_2.sdf" ftype="sdf"/>\n+ <element name="mol_000000" file="mol_0.sdf" ftype="sdf"/>\n+ <element name="mol_000001" file="mol_1.sdf" ftype="sdf"/>\n+ <element name="mol_000002" file="mol_2.sdf" ftype="sdf"/>\n </output_collection>\n </test>\n </tests>\n <help><![CDATA[\n **Split file into a dataset collection**\n \n-This tool splits a data sets consisting of records into multiple data sets within a collection. \n+This tool splits a data sets consisting of records into multiple data sets within a collection.\n A record can be for instance simply a line, a FASTA sequence (header + sequence), a FASTQ sequence\n (headers + sequence + qualities), etc. The important property is that the begin of a new record\n-can be speciefied by a regular expression, e.g. ".*" for lines, ">.*" for FASTA, or "@.*" for FASTQ. \n-The tool has presets for text, tabular data sets (which are split by line), FASTA, FASTQ, and MGF. \n-For other data types the text delimiting records can be specified manually using the generic splitter. \n+can be speciefied by a regular expression, e.g. ".*" for lines, ">.*" for FASTA, or "@.*" for FASTQ.\n+The tool has presets for text, tabular data sets (which are split by line), FASTA, FASTQ, and MGF.\n+For other data types the text delimiting records can be specified manually using the generic splitter.\n \n-If splitting by line (or by some other item, like a FASTA entry or an MGF record, the splitting can be either done alternating, in original record order, or at random. \n+If splitting by line (or by some other item, like a FASTA entry or an MGF record, the splitting can be either done alternating, in original record order, or at random.\n \n If t records are to be distributed to n new data sets, then the i-th record goes to data set\n \n-* floor(i / t * n) (for batch), \n+* floor(i / t * n) (for batch),\n * i % n (for alternating), or\n * a random data set\n \n@@ -368,11 +402,11 @@\n 4 2 1 1\n = === === ====\n \n-Note that there are no guarantees when splitting at random that every result file will be non-empty, so downstream tools should be able to gracefully handle empty files. \n+Note that there are no guarantees when splitting at random that every result file will be non-empty, so downstream tools should be able to gracefully handle empty files.\n \n If a tabular file is used as input, you may choose to split by line or by column. If split by column, a new file is created for each unique value in the column.\n In addition, (Python) regular expressions may be used to transform the value in the column to a new value. Caution should be used with this feature, as it could transform all values to the same value, or other unexpected behavior.\n-The default regular expression uses each value in the column without modifying it. \n+The default regular expression uses each value in the column without modifying it.\n ]]></help>\n <citations>\n <citation type="bibtex">\n' |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000000.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000000.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr1 1 0 247249719 chr1 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000001.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000001.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr2 2 0 242951149 chr2 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000002.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000002.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr3 3 0 199501827 chr3 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000003.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000003.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr4 4 0 191273063 chr4 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000004.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000004.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr5 5 0 180857866 chr5 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000005.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000005.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr6 6 0 170899992 chr6 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000006.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000006.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr7 7 0 158821424 chr7 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000007.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000007.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr8 8 0 146274826 chr8 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000008.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000008.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr9 9 0 140273252 chr9 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000009.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000009.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr10 10 0 135374737 chr10 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000010.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000010.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr11 11 0 134452384 chr11 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000011.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000011.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr12 12 0 132349534 chr12 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000012.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000012.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr13 13 0 114142980 chr13 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000013.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000013.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr14 14 0 106368585 chr14 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000014.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000014.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr15 15 0 100338915 chr15 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000015.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000015.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr16 16 0 88827254 chr16 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000016.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000016.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr17 17 0 78774742 chr17 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000017.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000017.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr18 18 0 76117153 chr18 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000018.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000018.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr19 19 0 63811651 chr19 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000019.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000019.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr20 20 0 62435964 chr20 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000020.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000020.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr21 21 0 46944323 chr21 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000021.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000021.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chr22 22 0 49691432 chr22 |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000022.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000022.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chrX x 0 154913754 chrx |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/chr_000023.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/chr_000023.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,1 @@ +chr - chrY y 0 57772954 chry |
| b |
| diff -r d150ac3d853d -r 2ddc36385d7a test-data/karyotype.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/karyotype.txt Tue Sep 10 12:31:15 2019 -0400 |
| b |
| @@ -0,0 +1,24 @@ +chr - chr1 1 0 247249719 chr1 +chr - chr2 2 0 242951149 chr2 +chr - chr3 3 0 199501827 chr3 +chr - chr4 4 0 191273063 chr4 +chr - chr5 5 0 180857866 chr5 +chr - chr6 6 0 170899992 chr6 +chr - chr7 7 0 158821424 chr7 +chr - chr8 8 0 146274826 chr8 +chr - chr9 9 0 140273252 chr9 +chr - chr10 10 0 135374737 chr10 +chr - chr11 11 0 134452384 chr11 +chr - chr12 12 0 132349534 chr12 +chr - chr13 13 0 114142980 chr13 +chr - chr14 14 0 106368585 chr14 +chr - chr15 15 0 100338915 chr15 +chr - chr16 16 0 88827254 chr16 +chr - chr17 17 0 78774742 chr17 +chr - chr18 18 0 76117153 chr18 +chr - chr19 19 0 63811651 chr19 +chr - chr20 20 0 62435964 chr20 +chr - chr21 21 0 46944323 chr21 +chr - chr22 22 0 49691432 chr22 +chr - chrX x 0 154913754 chrx +chr - chrY y 0 57772954 chry |