Mercurial > repos > iuc > fileidentification

annotate fileidentification.xml @ 0:aae476ce9dc3 draft

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 bb234555cae70fdd9be475415855a7a03c4139df
author iuc
date Thu, 30 Oct 2025 16:52:16 +0000
parents
children c08a138f5824
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
aae476ce9dc3 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">
aae476ce9dc3 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>
aae476ce9dc3 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>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
4 <expand macro="requirements"/>
aae476ce9dc3 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[
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
6 unzip '$input' -d input_dir &&
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
7 /app/.venv/bin/python /app/identify.py ./input_dir &&
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
8 /app/.venv/bin/python /app/identify.py ./input_dir --inspect > results.txt
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
9 ]]></command>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
10 <inputs>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
11 <param type="data" name="input" format="zip" label="ZIP containing the files to be analysed"/>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
12 </inputs>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
13 <outputs>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
14 <data name="out" format="txt" from_work_dir="results.txt" label="${tool.name} on ${on_string}"/>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
15 </outputs>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
16 <tests>
aae476ce9dc3 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">
aae476ce9dc3 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"/>
aae476ce9dc3 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"/>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
20 </test>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
21 </tests>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
22 <help><![CDATA[
aae476ce9dc3 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,
aae476ce9dc3 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?
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
25 This tool:
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
26
aae476ce9dc3 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
aae476ce9dc3 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
aae476ce9dc3 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
aae476ce9dc3 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
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
31
aae476ce9dc3 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)
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
33 Output: A report in plain text form
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
34
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
35 A possible use case are digital preservation workflows,
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
36 where you want to make sure that you only preserve high-quality files for the future.
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
37
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
38 Supported file types: A wide range of image formats (pixel and vector), videos, audios, pdf, MS Office.
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
39
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
40 Note: The original fileidentification tool is more feature-rich.
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
41 In particular, it offers bulk conversion of files, which is currently not supported on Galaxy.
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
42
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
43 Find more information in `the GitHub repo <https://github.com/dasch-swiss/fileidentification>`_.
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
44 ]]></help>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
45 <citations>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
46 <citation type="bibtex">
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
47 @misc{githubfileidentification,
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
48 author = {Swiss National Data and Service Center for the Humanities},
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
49 year = {2025},
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
50 title = {Fileidentification - A CLI to Identify Multimedia File Formats and Bulk Convert Files},
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
51 publisher = {GitHub},
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
52 journal = {GitHub repository},
aae476ce9dc3 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},
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
54 }</citation>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
55 </citations>
aae476ce9dc3 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/fileidentification commit bb234555cae70fdd9be475415855a7a03c4139df
iuc
parents:
diff changeset
56 </tool>