From e68096a7800af66e07f557c28b9de8c241f0ce8e Mon Sep 17 00:00:00 2001
From: Chris Coutinho <chris@coutinho.io>
Date: Fri, 5 Jun 2026 03:24:13 +0200
Subject: [PATCH] test(review): correct the junk-layer test comment

The high ocr_frac is driven by each segment being shorter than MIN_PAGE_CHARS
(needs_ocr), not by text quality; quality drives bad_text_layer separately.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 tests/unit/test_doc_classifier.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tests/unit/test_doc_classifier.py b/tests/unit/test_doc_classifier.py
index 587e1caa..d875a04b 100644
--- a/tests/unit/test_doc_classifier.py
+++ b/tests/unit/test_doc_classifier.py
@@ -188,8 +188,9 @@ def test_classify_from_text_no_pages_routes_fast():
 
 
 def test_classify_from_text_junk_layer_flags_bad_text_layer():
-    # Non-zero chars but low quality on every page (high ocr_frac) -> ocr +
-    # bad_text_layer (gated on ocr_frac, matching classify_pdf).
+    # Each short segment (<MIN_PAGE_CHARS) sets needs_ocr -> high ocr_frac, and
+    # total_chars>0 with mean_quality<MIN_TEXT_QUALITY (no-whitespace junk scores
+    # 0.0) -> bad_text_layer (gated on ocr_frac, matching classify_pdf).
     text = "x1y2zx1y2z"
     c = clf.classify_from_text(
         text,