Mercurial > repos > iuc > fileidentification

annotate fileidentification.xml @ 1:639d81cf8ac8 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/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit 54a29e12e7c71367b28f1dea4fb6458590b0ca92
author iuc
date Fri, 31 Oct 2025 13:50:27 +0000
parents ff7cec6bc518
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
1 <tool id="fileidentification" name="File Format Identification" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.1">
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
2 <description>Check multimedia files if they are corrupt or duplicated</description>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
3 <macros><import>macros.xml</import></macros>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
4 <expand macro="requirements"/>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
5 <command detect_errors="exit_code"><![CDATA[
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
6 unzip '$input' -d input_dir &&
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
7 /app/.venv/bin/python /app/identify.py ./input_dir &&
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
8 /app/.venv/bin/python /app/identify.py ./input_dir --inspect > results.txt
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
9 ]]></command>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
10 <inputs>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
11 <param type="data" name="input" format="zip" label="ZIP containing the files to be analysed"/>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
12 </inputs>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
13 <outputs>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
14 <data name="out" format="txt" from_work_dir="results.txt" label="${tool.name} on ${on_string}"/>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
15 </outputs>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
16 <tests>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
17 <test expect_num_outputs="1">
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
18 <param name="input" value="test-data.zip"/>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
19 <output name="out" ftype="txt" file="output_results_linux_gh_action.txt"/>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
20 </test>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
21 </tests>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
22 <help><![CDATA[
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
23 Do you have a huge number of multimedia files and you don't know if they are corrupt,
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
24 or if they have the correct extension?
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
25 This tool:
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
26
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
27 - gives you an overview of what file types there are
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
28 - checks if the extension of the files match their content
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
29 - checks if there are any duplicates
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
30 - checks if the content of the files is intact
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
31
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
32 Input: A ZIP containing the files to be analysed (may be a nested folder structure)
1
639d81cf8ac8 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit 54a29e12e7c71367b28f1dea4fb6458590b0ca92
iuc
parents: 0
diff changeset
33
0
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
34 Output: A report in plain text form
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
35
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
36 A possible use case are digital preservation workflows,
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
37 where you want to make sure that you only preserve high-quality files for the future.
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
38
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
39 Supported file types: A wide range of image formats (pixel and vector), videos, audios, pdf, MS Office.
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
40
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
41 Note: The original fileidentification tool is more feature-rich.
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
42 In particular, it offers bulk conversion of files, which is currently not supported on Galaxy.
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
43
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
44 Find more information in `the GitHub repo <https://github.com/dasch-swiss/fileidentification>`_.
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
45 ]]></help>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
46 <citations>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
47 <citation type="bibtex">
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
48 @misc{githubfileidentification,
1
639d81cf8ac8 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit 54a29e12e7c71367b28f1dea4fb6458590b0ca92
iuc
parents: 0
diff changeset
49 author = {{DaSCH, Swiss National Data and Service Center for the Humanities}},
0
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
50 year = {2025},
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
51 title = {Fileidentification - A CLI to Identify Multimedia File Formats and Bulk Convert Files},
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
52 journal = {GitHub repository},
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
53 url = {https://github.com/dasch-swiss/fileidentification},
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
54 }</citation>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
55 </citations>
ff7cec6bc518 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
56 </tool>