From 992866e1670acbdcbb17380b4626a09975306356 Mon Sep 17 00:00:00 2001
From: Afonso Coutinho <afonso@omelhorsite.pt>
Date: Wed, 3 Jun 2026 05:28:38 +0100
Subject: [PATCH] fix: document library language facet undercounts text
 documents (#1758)

---
 routes/document_routes.py                     | 17 ++++++++++-
 tests/test_document_library_language_facet.py | 28 +++++++++++++++++++
 2 files changed, 44 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_document_library_language_facet.py

diff --git a/routes/document_routes.py b/routes/document_routes.py
index baf84b2..5625df8 100644
--- a/routes/document_routes.py
+++ b/routes/document_routes.py
@@ -15,6 +15,21 @@ from src.auth_helpers import get_current_user
 logger = logging.getLogger(__name__)
 
 
+def _aggregate_language_facets(lang_rows):
+    """Sum document counts per display language for the library facet.
+
+    NULL-language and explicit "text" rows share the "text" bucket (the
+    language filter treats them as one), so they must be ADDED. The old dict
+    comprehension keyed both to "text", silently overwriting one group and
+    undercounting the facet versus what the filter actually returns.
+    """
+    out = {}
+    for lang, cnt in lang_rows:
+        key = lang or "text"
+        out[key] = out.get(key, 0) + cnt
+    return out
+
+
 
 from routes.document_helpers import (
     DocumentCreate, DocumentUpdate, DocumentPatch,
@@ -258,7 +273,7 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
             )
             lang_q = _owner_session_filter(lang_q, user)
             lang_rows = lang_q.group_by(Document.language).all()
-            languages = {lang or "text": cnt for lang, cnt in lang_rows}
+            languages = _aggregate_language_facets(lang_rows)
 
             # Session count (owner-filtered)
             sc_q = (
diff --git a/tests/test_document_library_language_facet.py b/tests/test_document_library_language_facet.py
new file mode 100644
index 0000000..ee23eb4
--- /dev/null
+++ b/tests/test_document_library_language_facet.py
@@ -0,0 +1,28 @@
+"""Library language facet must SUM NULL-language and "text" docs.
+
+documents_library built the facet with {lang or "text": cnt ...}, so a
+NULL-language row and an explicit "text" row both keyed "text" and one
+silently overwrote the other. The language FILTER treats NULL and "text"
+as a single bucket ((language == None) | (language == "text")), so the
+facet count must add them, otherwise clicking the facet returns more docs
+than the count promised.
+"""
+from routes.document_routes import _aggregate_language_facets
+
+
+def test_null_and_text_are_summed():
+    rows = [(None, 3), ("text", 2), ("python", 5)]
+    assert _aggregate_language_facets(rows) == {"text": 5, "python": 5}
+
+
+def test_only_null():
+    assert _aggregate_language_facets([(None, 4)]) == {"text": 4}
+
+
+def test_distinct_languages_preserved():
+    rows = [("python", 2), ("javascript", 7), ("text", 1)]
+    assert _aggregate_language_facets(rows) == {"python": 2, "javascript": 7, "text": 1}
+
+
+def test_empty():
+    assert _aggregate_language_facets([]) == {}