Mercurial > repos > brenninc > directory_reader_limited_by_data_table
changeset 2:3911ee1a0078 draft default tip
Uploaded
| author | brenninc |
|---|---|
| date | Fri, 17 Jun 2016 11:30:23 -0400 |
| parents | 1487421505f1 |
| children | |
| files | data_reader.xml directory_copier.py |
| diffstat | 2 files changed, 52 insertions(+), 21 deletions(-) [+] |
line wrap: on
line diff
--- a/data_reader.xml Wed Mar 23 12:08:33 2016 -0400 +++ b/data_reader.xml Fri Jun 17 11:30:23 2016 -0400 @@ -9,10 +9,13 @@ --new_ending .${directory.fields.galaxy_extension} --decompress ${directory.fields.decompress} #if $results.start - --start $results.start + --start "$results.start" #end if #if $results.last - --last $results.last + --last "$results.last" + #end if + #if $results.regex + --regex "$results.regex" #end if #end if --path ${directory.fields.path} @@ -33,6 +36,11 @@ <when value="data"> <param name="start" type="text" value="" label="String which must be at the start of each file name" /> <param name="last" type="text" value="" label="String which must be at the end of the file name (excluding the file type)" /> + <param name="regex" type="text" value="" label="Regex pattern which must somewhere in the file name (excluding the file type)" > + <sanitizer> + <valid initial="string.printable"/> + </sanitizer> + </param> </when> <when value="listing"/> </conditional> @@ -76,7 +84,20 @@ <output name="listing_fastq"> <assert_contents> <has_line line="sample1.fastq" /> - <not_has_text text="other.fasta" /> + <not_has_text text="other.fastq" /> + </assert_contents> + </output> + <output_collection name="data_collection" type="list"> + <element name="sample1" ftype="fastq" file="sample1.fastq" /> + </output_collection> + </test> + <test> + <param name="directory" value="fastq_files_id" /> + <param name="results|regex" value="le.?" /> + <output name="listing_fastq"> + <assert_contents> + <has_line line="sample1.fastq" /> + <not_has_text text="other.fastq" /> </assert_contents> </output> <output_collection name="data_collection" type="list"> @@ -107,13 +128,23 @@ Files can also be filter for the last part before the file extsentions. +Files can also be filtered by a regex pattern. +Only files that contain the regex string will be included. +This uses the python search funtion so as long as the Regex pattern is found somewhere in file name (excluding extension). + +The three filter start, last and regex if supplied work indepently, so only files that pass all supplied test will be included. + +Note: Before applying the last and regex test the ending (includig the . just before the ending are removed) + Assuming the directory has: -C01_R1_001.fasta C01_R2_001.fatsa C02_R1_001.fasta C02_R2_001.fatsa +C01_R1_001.fasta C01_R2_001.fatsa C02_R1_001.fasta C02_R2_002.fatsa -Setting start C01 will return just the C01 files: C01_R1_001.fasta C01_R2_001.fatsa +Setting start C01 will return just the C01 files: C01_R1_001.fasta C01_R2_002.fatsa Setting last R1_001 will return the read1 files: C01_R1_001.fasta C02_R1_001.fasta +Setting regex R2_00.$ will return the R2 files: C01_R2_001.fatsa C02_R2_002.fatsa + As Galaxy detects the file type based on the extension this tool will change the exstension as setup by the admin. This tool will unzip gz files if requested to by the admin,
--- a/directory_copier.py Wed Mar 23 12:08:33 2016 -0400 +++ b/directory_copier.py Fri Jun 17 11:30:23 2016 -0400 @@ -1,6 +1,7 @@ import gzip import optparse # using optparse as hydra still python 2.6 import os.path +import re import shutil import sys @@ -14,22 +15,21 @@ if options.start: if not(a_file.startswith(options.start)): return None + name = a_file[:-len(ending)] + if name.endswith("."): + name = name[:-1] if options.last: - if ending[0] == ".": - last = options.last + ending - else: - if options.last[-1] == ".": - last = options.last + ending - else: - last = options.last + "." + ending - if not(a_file.endswith(last)): + if not(name.endswith(last)): + return None + if options.regex: + pattern = re.compile(options.regex) + if pattern.search(name) is None: return None if options.new_ending: - name = a_file[:-len(ending)] if options.new_ending[0] ==".": - if name[-1] == ".": - name = name[:-1] - return name + options.new_ending + return name + options.new_ending + else: + return name + "." + options.new_ending if options.decompress: if a_file.endswith(".gz"): return a_file[:-3] @@ -46,7 +46,6 @@ def link(a_file, new_name, path): file_path = os.path.join(os.path.realpath(path), a_file) sym_path = os.path.join(os.path.realpath("output"), new_name) - #if not(os.path.exists(sym_path)): os.link(file_path, sym_path) @@ -58,7 +57,8 @@ def copy_and_link(path, options): - os.mkdir("output") + if options.decompress or options.link: + os.mkdir("output") with open(options.list, 'w') as list_file: files = os.listdir(path) files.sort() @@ -86,10 +86,10 @@ help="String that must be at the start of the file name ") parser.add_option("--last", action="store", type="string", help="String that must be the last bit of the file name before the endings") + parser.add_option("--regex", action="store", type="string", + help="Regex for file names not including the endings") parser.add_option("--new_ending", action="store", type="string", help="New ending to replace any previous ending in list and if required links or decompressions. Note: If not set decompression will auto remove the compressioned part of the ending") - #parser.add_option("--regex", action="store", type="string", - # help="Regex pattern the file name (less . ending) must match before the endings") parser.add_option("--list", action="store", type="string", help="Path to where all files should be listed. ") parser.add_option("--link", action="store_true", default=False,