Skip to content

(bugfix) Fix a bug where a tree where a level split in two and expect… #32

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
PonteIneptique merged 1 commit into from
Apr 22, 2026
Merged

(bugfix) Fix a bug where a tree where a level split in two and expect… #32

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions dapytains/tei/citeStructure.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,12 +284,14 @@ def find_refs_from_branches(

unsorted = []
for s in structure:
unsorted.extend(
[
(f"{prefix}{s.delim}{value}", s)
for value in xpath_proc.evaluate(f"{xpath_prefix}{s.xpath}")
]
)
results = xpath_proc.evaluate(f"{xpath_prefix}{s.xpath}")
if results is not None:
unsorted.extend(
[
(f"{prefix}{s.delim}{value}", s)
for value in results
]
)

unsorted = [
_simple_node(ref, self.generate_xpath(ref), struct)
Expand Down
41 changes: 41 additions & 0 deletions tests/tei/uneven_parent_level.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
<TEI xmlns="http://www.tei-c.org/ns/1.0">
<teiHeader>
<encodingDesc>
<refsDecl>
<citeStructure unit="book" match="//body/div" use="@n">
<citeStructure unit="verse" match="ab" use="position()" delim=":"/>
<citeStructure unit="chapter" match="div" use="position()" delim=" ">
<citeStructure unit="bloup" match="l" use="position()" delim="#"/>
</citeStructure>
</citeStructure>
</refsDecl>
</encodingDesc>
</teiHeader>
<text>
<body>
<div n="Luke">
<div>
<l>Text 1</l>
</div>
<ab>
<l>Text 2</l>
<l>Text 3</l>
</ab>
</div>
<div n="Mark">
<ab>
<div>Text A</div>
<div>Text B</div>
<l>Text C</l>
<div>Text D</div>
</ab>
<ab>
<div>Text A</div>
<div>Text B</div>
<l>Text C</l>
<div>Text D</div>
</ab>
</div>
</body>
</text>
</TEI>
15 changes: 15 additions & 0 deletions tests/test_tei.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import os.path

import pytest

from dapytains.tei.citeStructure import CitableUnit
from dapytains.tei.document import Document
from lxml.etree import tostring

Expand Down Expand Up @@ -252,3 +254,16 @@ def test_xml_entity():
' </text>\n'
'</TEI>')


def _flat_refs(refs: list[CitableUnit]) -> list[str]:
data = []
for ref in refs:
data.append(ref.ref)
data.extend(_flat_refs(ref.children))
return data


def test_ref_parsing_uneven_tree():
"""Test that a level that can contain data is not missed"""
doc = Document(f"{local_dir}/uneven_parent_level.xml")
assert _flat_refs(doc.get_reffs()) == ['Luke', 'Luke 1', 'Luke 1#1', 'Luke:1', 'Mark', 'Mark:1', 'Mark:2']
Loading