fix(tools): decode saved non-UTF-8 pages by their declared charset (#690)

* fix(tools): decode saved non-UTF-8 pages by their declared charset

fetch_page.py saves a body exactly as the server sent it, but its readers,
posting_guard.py --html and fetch_page.py --text, decoded the file as UTF-8
with replacement. A posting served in EUC-KR, Shift_JIS or windows-1252
reached the integrity gate and the scorer as replacement characters.

Valid UTF-8 still wins, so any page that decoded cleanly before decodes to the
same string. Bytes that are not valid UTF-8 now fall back to the charset the
page declares (UTF-16 BOM, then <meta charset> or http-equiv Content-Type in
the first 1024 bytes), mapped to the codec browsers use for that label. Missing
or unknown labels keep the previous UTF-8-with-replacement result.

* changelog: place the #690 entry under [Unreleased]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_fetch_page.py

@@ -30,6 +30,11 @@ PAGE = (
     "<noscript>noscript text</noscript><svg><text>svg text</text></svg>"
     "</body></html>"
 )
+KOREAN_PAGE = (
+    '<html><head><meta http-equiv="Content-Type" content="text/html; charset=euc-kr">'
+    "<title>채용공고</title></head><body><h1>백엔드 개발자 채용</h1></body></html>"
+)
+CONTENT_TYPES = {"/euc-kr.html": "text/html; charset=euc-kr"}
 
 
 class _Handler(http.server.BaseHTTPRequestHandler):
@@ -37,6 +42,9 @@ class _Handler(http.server.BaseHTTPRequestHandler):
         if self.path == "/ok.html":
             body = PAGE.encode("utf-8")
             self.send_response(200)
+        elif self.path == "/euc-kr.html":
+            body = KOREAN_PAGE.encode("cp949")
+            self.send_response(200)
         elif self.path == "/forbidden":
             body = b"<html><body>denied</body></html>"
             self.send_response(403)
@@ -54,7 +62,7 @@ class _Handler(http.server.BaseHTTPRequestHandler):
         else:
             body = b"nope"
             self.send_response(404)
-        self.send_header("Content-Type", "text/html; charset=utf-8")
+        self.send_header("Content-Type", CONTENT_TYPES.get(self.path, "text/html; charset=utf-8"))
         self.send_header("Content-Length", str(len(body)))
         self.end_headers()
         self.wfile.write(body)
@@ -152,6 +160,14 @@ class Fetching(FetchPageFixture):
         for leaked in ("alert(", "color:red", "hidden comment", "noscript text", "svg text", "<p>"):
             self.assertNotIn(leaked, text)
 
+    def test_text_decodes_a_page_by_its_declared_charset(self):
+        code, out, err = self.run_main(f"{self.base}/euc-kr.html", "--out", str(self.out), "--text")
+        self.assertEqual(code, 0, err)
+        self.assertEqual(self.out.read_bytes(), KOREAN_PAGE.encode("cp949"))
+        text = out.split("--- text ---", 1)[1]
+        self.assertIn("백엔드 개발자 채용", text)
+        self.assertNotIn("\ufffd", text)
+
     def test_max_chars_caps_text(self):
         code, out, err = self.run_main(
             f"{self.base}/ok.html", "--out", str(self.out), "--text", "--max-chars", "7"

tests/test_page_decode.py

@@ -0,0 +1,82 @@
+"""tools/page_decode.py decodes a saved page by the charset it declares.
+
+Why this test exists: fetch_page.py saves bodies as the server sent them, and
+posting_guard.py --html and fetch_page.py --text used to decode every file as
+UTF-8 with replacement. A posting served in EUC-KR (job.incruit.com serves its
+postings that way) reached the gate and the scorer as replacement characters.
+These tests pin that declared legacy charsets are honoured, and that anything
+which decoded cleanly before still decodes to exactly the same string.
+"""
+import sys
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(REPO_ROOT / "tools"))
+from page_decode import decode_page, declared_codec  # noqa: E402
+
+
+def page(body: str, head: str = "") -> str:
+    return f"<!doctype html><html><head>{head}<title>Posting</title></head><body>{body}</body></html>"
+
+
+class LegacyCharsets(unittest.TestCase):
+    def test_http_equiv_euc_kr_is_read_as_cp949(self):
+        # 똠 is outside strict EUC-KR; browsers read the euc-kr label as CP949.
+        text = page("<h1>백엔드 개발자 채용</h1><p>똠방각하 우대</p>",
+                    '<meta http-equiv="Content-Type" content="text/html; charset=euc-kr">')
+        decoded = decode_page(text.encode("cp949"))
+        self.assertIn("백엔드 개발자 채용", decoded)
+        self.assertIn("똠방각하", decoded)
+        self.assertNotIn("�", decoded)
+
+    def test_meta_charset_shift_jis(self):
+        text = page("<h1>データエンジニア募集</h1>", '<meta charset="Shift_JIS">')
+        self.assertIn("データエンジニア募集", decode_page(text.encode("cp932")))
+
+    def test_iso_8859_1_label_is_read_as_windows_1252(self):
+        text = page("<p>Løn: 50.000 € om måneden</p>", "<meta charset=iso-8859-1>")
+        self.assertIn("Løn: 50.000 € om måneden", decode_page(text.encode("cp1252")))
+
+    def test_windows_1251_cyrillic(self):
+        text = page("<p>Инженер данных</p>", '<meta charset="windows-1251">')
+        self.assertIn("Инженер данных", decode_page(text.encode("cp1251")))
+
+    def test_utf16_byte_order_mark(self):
+        text = page("<p>Ingeniør</p>")
+        self.assertIn("Ingeniør", decode_page(text.encode("utf-16")))
+
+
+class UnchangedBehaviour(unittest.TestCase):
+    def test_valid_utf8_is_unchanged(self):
+        raw = page("<p>Ingeniør søges, 백엔드, データ</p>").encode("utf-8")
+        self.assertEqual(decode_page(raw), raw.decode("utf-8", errors="replace"))
+
+    def test_valid_utf8_wins_over_a_wrong_meta_label(self):
+        # Browsers would follow a utf-8 HTTP header here; the saved file does not
+        # keep headers, so valid UTF-8 has to win over a stale <meta>.
+        raw = page("<p>Café</p>", '<meta charset="iso-8859-1">').encode("utf-8")
+        self.assertIn("Café", decode_page(raw))
+
+    def test_utf8_bom_is_kept_for_the_invisible_character_count(self):
+        raw = b"\xef\xbb\xbf" + page("<p>Plain posting.</p>").encode("utf-8")
+        self.assertTrue(decode_page(raw).startswith(""))
+
+    def test_undeclared_legacy_bytes_fall_back_to_utf8_with_replacement(self):
+        raw = page("<p>Café</p>").encode("latin-1")
+        self.assertEqual(decode_page(raw), raw.decode("utf-8", errors="replace"))
+
+    def test_unknown_and_unsafe_labels_are_ignored(self):
+        for label in ("x-unknown", "utf-7", "utf-16"):
+            raw = page("<p>Café</p>", f'<meta charset="{label}">').encode("latin-1")
+            with self.subTest(label=label):
+                self.assertIsNone(declared_codec(raw))
+                self.assertEqual(decode_page(raw), raw.decode("utf-8", errors="replace"))
+
+    def test_meta_after_the_prescan_window_is_ignored(self):
+        raw = (" " * 1100 + page("<p>Café</p>", '<meta charset="windows-1252">')).encode("cp1252")
+        self.assertIsNone(declared_codec(raw))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_posting_guard.py

@@ -228,6 +228,37 @@ class InputHandling(GuardFixture):
         self.assertEqual(code, 0, err)
         self.assertIn("Caf� manager wanted", self.text_of(out))
 
+    def test_html_mode_reads_a_page_saved_in_its_declared_charset(self):
+        # job.incruit.com serves postings as EUC-KR; fetch_page.py saves the bytes as sent.
+        page = (
+            '<html><head><meta http-equiv="Content-Type" content="text/html; charset=euc-kr">'
+            "</head><body><h1>백엔드 개발자 채용</h1><p>Python, SQL 경력 3년 이상</p></body></html>"
+        )
+        p = self.write("page.html", page.encode("cp949"))
+        code, out, err = self.run_main("--in", str(p), "--html", "--json")
+        self.assertEqual(code, 0, err)
+        self.assertIn("백엔드 개발자 채용", self.text_of(out))
+        self.assertNotIn("\ufffd", self.text_of(out))
+
+    def test_html_mode_scans_a_legacy_cyrillic_page_for_homoglyphs(self):
+        # Cyrillic о and а inside Latin words, saved as windows-1251.
+        page = (
+            '<html><head><meta charset="windows-1251"></head>'
+            "<body><p>Join Nоvo Nаrdisk as an engineer.</p></body></html>"
+        )
+        p = self.write("page.html", page.encode("cp1251"))
+        code, out, err = self.run_main("--in", str(p), "--html", "--json")
+        self.assertEqual(code, 0, err)
+        self.assertEqual(len(self.findings_of(out)["homoglyph_runs"]), 2)
+        self.assertIn("⚠", out.splitlines()[0])
+
+    def test_html_mode_keeps_valid_utf8_when_meta_names_another_charset(self):
+        page = '<html><head><meta charset="iso-8859-1"></head><body><p>Café manager</p></body></html>'
+        p = self.write("page.html", page)
+        code, out, err = self.run_main("--in", str(p), "--html", "--json")
+        self.assertEqual(code, 0, err)
+        self.assertIn("Café manager", self.text_of(out))
+
     def test_missing_in_file_exits_2(self):
         code, out, err = self.run_main("--in", str(self.tmp / "nope.txt"))
         self.assertEqual(code, 2)