Mercurial > repos > immport-devteam > check_headers

changeset 1:05440ef97f8b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ImmPortDB/immport-galaxy-tools/tree/master/flowtools/check_headers commit 14d780f8710fb0962a85c262d0689a9551f4f8e1"
author azomics
date Tue, 14 Jul 2020 09:46:31 -0400
parents e88c99a4fb36
children
files check_headers/getHeaders.py check_headers/getHeaders.xml check_headers/test-data/input1.txt check_headers/test-data/input2.txt check_headers/test-data/input3.txt check_headers/test-data/output.tabular getHeaders.py getHeaders.xml test-data/input1.txt test-data/input2.txt test-data/input3.txt test-data/output.tabular
diffstat 12 files changed, 178 insertions(+), 150 deletions(-) [+]
line wrap: on
line diff
--- a/check_headers/getHeaders.py	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,50 +0,0 @@
-#!/usr/bin/env python
-######################################################################
-#                  Copyright (c) 2016 Northrop Grumman.
-#                          All rights reserved.
-######################################################################
-from __future__ import print_function
-import sys
-
-from argparse import ArgumentParser
-
-
-def print_headers(files, filenames, outfile):
-    with open(outfile, "w") as outf:
-        for i, eachfile in enumerate(files):
-            with open(eachfile, "r") as ef:
-                headers = ef.readline()
-                outf.write("\t".join([filenames[i], headers]))
-    return
-
-
-if __name__ == "__main__":
-    parser = ArgumentParser(
-             prog="GetHeaders",
-             description="Gets the headers of all files in given set.")
-
-    parser.add_argument(
-            '-i',
-            dest="input_files",
-            required=True,
-            action='append',
-            help="File location for the text files.")
-
-    parser.add_argument(
-            '-n',
-            dest="file_names",
-            required=True,
-            action='append',
-            help="File names.")
-
-    parser.add_argument(
-            '-o',
-            dest="output_file",
-            required=True,
-            help="Name of the output file.")
-
-    args = parser.parse_args()
-    input_files = [f for f in args.input_files]
-    file_names = [fn for fn in args.file_names]
-    print_headers(input_files, file_names, args.output_file)
-    sys.exit(0)
--- a/check_headers/getHeaders.xml	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,67 +0,0 @@
-<tool id="get_headers" name="Check headers" version="1.1">
-  <description>of any set of flowtext files.</description>
-  <stdio>
-    <exit_code range="1:" />
-  </stdio>
-  <command><![CDATA[
-    python $__tool_directory__/getHeaders.py -o "${output_file}"
- #for $f in $input#
-    -i "${f}"
-    -n "${f.name}"
- #end for#
-  ]]>
-  </command>
-  <inputs>
-    <param format="flowtext" name="input" type="data_collection" collection_type="list" label="Text files Collection"/>
-  </inputs>
-  <outputs>
-    <data format="tabular" name="output_file" label="Headers of files in ${input.name}"/>
-  </outputs>
-  <tests>
-    <test>
-      <param name="input">
-        <collection type="list">
-          <element name="input1.txt" value="input1.txt"/>
-          <element name="input2.txt" value="input2.txt"/>
-          <element name="input3.txt" value="input3.txt"/>
-        </collection>
-      </param>
-      <output name="output_file" file="output.tabular"/>
-    </test>
-  </tests>
-  <help><![CDATA[
-   This tool returns a table of the headers of a set of text files.
-
------
-
-**Input files**
-
-This tool requires collections of txt, flowtext or tabular files as input.
-
-**Output file**
-
-The output file is a table listing the headers for each file.
-
------
-
-**Example**
-
-*File1*::
-
-   Marker1 Marker2 Marker3
-   34      45      12
-   33      65      10
-
-*File2*::
-
-   Marker4 Marker5 Marker3
-   19      62      98
-   12      36      58
-
-*Output*::
-
-   File1 Marker1 Marker2 Marker3
-   File2 Marker4 Marker5 Marker3
-  ]]>
-  </help>
-</tool>
--- a/check_headers/test-data/input1.txt	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,10 +0,0 @@
-Forward Scatter	Side Scatter	FITC CD4	PE CCR3	PP CD8	APC CCR4
-449	157	551	129	169	292
-894	1023	199	277	320	227
-262	73	437	69	0	146
-340	115	509	268	0	74
-316	76	50	0	60	129
-394	144	83	138	335	194
-383	139	499	0	0	224
-800	1023	239	284	288	280
-388	97	534	111	83	177
--- a/check_headers/test-data/input2.txt	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,10 +0,0 @@
-Forward Scatter	Side Scatter	FITC CD4	PE CXCR3	PP CD8	APC CCR5
-363	76	550	200	0	127
-372	126	519	44	51	148
-1023	1023	289	401	362	254
-770	1023	175	361	225	237
-384	111	525	121	0	138
-602	578	385	286	222	131
-788	1023	216	310	270	294
-420	211	552	479	0	62
-668	1019	73	193	227	132
--- a/check_headers/test-data/input3.txt	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,10 +0,0 @@
-Forward Scatter	Side Scatter	FITC CD4	PE CD25	PP CD3	APC CD45RA
-289	56	438	0	626	480
-352	153	30	147	483	386
-383	190	156	228	734	408
-261	62	432	121	598	555
-451	120	537	338	568	201
-373	104	3	110	621	584
-418	105	561	0	610	562
-358	185	0	292	641	327
-733	970	139	227	293	259
--- a/check_headers/test-data/output.tabular	Mon Feb 27 12:41:17 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,3 +0,0 @@
-input1.txt	Forward Scatter	Side Scatter	FITC CD4	PE CCR3	PP CD8	APC CCR4
-input2.txt	Forward Scatter	Side Scatter	FITC CD4	PE CXCR3	PP CD8	APC CCR5
-input3.txt	Forward Scatter	Side Scatter	FITC CD4	PE CD25	PP CD3	APC CD45RA
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/getHeaders.py	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+######################################################################
+#                  Copyright (c) 2016 Northrop Grumman.
+#                          All rights reserved.
+######################################################################
+#
+# Version 1.2 - May 2018
+# added leeway for files with different nb of headers
+#
+
+
+import sys
+
+from argparse import ArgumentParser
+
+
+def print_headers(files, filenames, outfile):
+    header_table = {}
+    for i, eachfile in enumerate(files):
+        with open(eachfile, "r") as ef:
+            headers = ef.readline().strip()
+            header_table[filenames[i]] = headers.split("\t")
+
+    h = 0
+    for f in header_table:
+        j = len(header_table[f]) + 1
+        if j > h:
+            h = j
+
+    idx = [str(x) for x in range(1, h)]
+
+    with open(outfile, "w") as outf:
+        outf.write("Index\t")
+        outf.write("\t".join(idx) + "\n")
+        for f in header_table:
+            if len(header_table[f]) < h:
+                for k in range(len(header_table[f]), h-1):
+                    header_table[f].append("")
+                sys.stderr.write(str(len(header_table[f])))
+            outf.write(f + "\t")
+            outf.write("\t".join(header_table[f]) + "\n")
+    return
+
+
+if __name__ == "__main__":
+    parser = ArgumentParser(
+             prog="GetHeaders",
+             description="Gets the headers of all files in given set.")
+
+    parser.add_argument(
+            '-i',
+            dest="input_files",
+            required=True,
+            action='append',
+            help="File location for the text files.")
+
+    parser.add_argument(
+            '-n',
+            dest="file_names",
+            required=True,
+            action='append',
+            help="File names.")
+
+    parser.add_argument(
+            '-o',
+            dest="output_file",
+            required=True,
+            help="Name of the output file.")
+
+    args = parser.parse_args()
+    input_files = [f for f in args.input_files]
+    file_names = [fn for fn in args.file_names]
+    print_headers(input_files, file_names, args.output_file)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/getHeaders.xml	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,71 @@
+<tool id="get_headers" name="Check headers" version="1.1+galaxy0" profile="18.01">
+  <description>of any set of flowtext files</description>
+  <requirements>
+    <requirement type="package" version="3.8.3">python</requirement>
+  </requirements>
+  <stdio>
+    <exit_code range="1:" />
+  </stdio>
+  <command><![CDATA[
+ python3 '$__tool_directory__/getHeaders.py' -o '${output_file}'
+ #for $f in $input
+    -i '${f}'
+    -n '${f.name}'
+ #end for
+  ]]>
+  </command>
+  <inputs>
+    <param format="flowtext,tabular,txt" name="input" type="data_collection" collection_type="list" label="Text files Collection"/>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="output_file" label="Headers of files in ${input.name}"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input">
+        <collection type="list">
+          <element name="input1.txt" value="input1.txt"/>
+          <element name="input2.txt" value="input2.txt"/>
+          <element name="input3.txt" value="input3.txt"/>
+        </collection>
+      </param>
+      <output name="output_file" file="output.tabular" lines_diff="4"/>
+    </test>
+  </tests>
+  <help><![CDATA[
+   This tool returns a table of the headers of a set of text files.
+
+-----
+
+**Input files**
+
+This tool requires collections of txt, flowtext or tabular files as input.
+
+**Output file**
+
+The output file is a table listing the headers for each file.
+
+-----
+
+**Example**
+
+*File1*::
+
+   Marker1 Marker2 Marker3
+   34      45      12
+   33      65      10
+
+*File2*::
+
+   Marker4 Marker5 Marker3
+   19      62      98
+   12      36      58
+
+*Output*::
+
+   Index 1       2       3
+   File1 Marker1 Marker2 Marker3
+   File2 Marker4 Marker5 Marker3
+  ]]>
+  </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input1.txt	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,10 @@
+Forward Scatter	Side Scatter	FITC CD4	PE CCR3	PP CD8	APC CCR4
+449	157	551	129	169	292
+894	1023	199	277	320	227
+262	73	437	69	0	146
+340	115	509	268	0	74
+316	76	50	0	60	129
+394	144	83	138	335	194
+383	139	499	0	0	224
+800	1023	239	284	288	280
+388	97	534	111	83	177
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input2.txt	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,10 @@
+Forward Scatter	Side Scatter	FITC CD4	PE CXCR3	PP CD8	APC CCR5
+363	76	550	200	0	127
+372	126	519	44	51	148
+1023	1023	289	401	362	254
+770	1023	175	361	225	237
+384	111	525	121	0	138
+602	578	385	286	222	131
+788	1023	216	310	270	294
+420	211	552	479	0	62
+668	1019	73	193	227	132
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input3.txt	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,10 @@
+Forward Scatter	Side Scatter	FITC CD4	PE CD25	PP CD3	APC CD45RA
+289	56	438	0	626	480
+352	153	30	147	483	386
+383	190	156	228	734	408
+261	62	432	121	598	555
+451	120	537	338	568	201
+373	104	3	110	621	584
+418	105	561	0	610	562
+358	185	0	292	641	327
+733	970	139	227	293	259
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output.tabular	Tue Jul 14 09:46:31 2020 -0400
@@ -0,0 +1,4 @@
+Index	1	2	3	4	5	6
+input3.txt	Forward Scatter	Side Scatter	FITC CD4	PE CD25	PP CD3	APC CD45RA
+input2.txt	Forward Scatter	Side Scatter	FITC CD4	PE CXCR3	PP CD8	APC CCR5
+input1.txt	Forward Scatter	Side Scatter	FITC CD4	PE CCR3	PP CD8	APC CCR4