mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-31 10:03:07 +00:00
23ff32cc42
* first pass on partition_xml * add option to keep xml tags * added tests for xml * fix filename * update filenames * remove outdated readme * add xml to auto * version and changelog * update readme and docs * pass through include_metadata * update include_metadata description * add README back in * linting, linting, linting * more linting * spooled to bytes doesnt need to be a tuple * Add tests for newly supported filetypes * Correct metadata filetype * doc typo Co-authored-by: qued <64741807+qued@users.noreply.github.com> * typo fix Co-authored-by: qued <64741807+qued@users.noreply.github.com> * typo fix Co-authored-by: qued <64741807+qued@users.noreply.github.com> * keep_xml_tags -> xml_keep_tags --------- Co-authored-by: Alan Bertl <alan@unstructured.io> Co-authored-by: qued <64741807+qued@users.noreply.github.com>
28 lines
669 B
XML
28 lines
669 B
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<factbook>
|
|
<country>
|
|
<name>United States</name>
|
|
<capital>Washington, DC</capital>
|
|
<leader>Joe Biden</leader>
|
|
<sport>Baseball</sport>
|
|
</country>
|
|
<country>
|
|
<name>Canada</name>
|
|
<capital>Ottawa</capital>
|
|
<leader>Justin Trudeau</leader>
|
|
<sport>Hockey</sport>
|
|
</country>
|
|
<country>
|
|
<name>France</name>
|
|
<capital>Paris</capital>
|
|
<leader>Emmanuel Macron</leader>
|
|
<sport>Soccer</sport>
|
|
</country>
|
|
<country>
|
|
<name>Trinidad & Tobado</name>
|
|
<capital>Port of Spain</capital>
|
|
<leader>Keith Rowley</leader>
|
|
<sport>Track & Field</sport>
|
|
</country>
|
|
</factbook>
|