Merge pull request #342 from rmz-oz/fix-encoded-hash-in-document-uri

Keep encoded # in ZIM paths when building document URIs

Author: benoit74

CHANGELOG.md

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Carry a script's top-level `const`, `let` and `class` declarations across the wombat block, so other scripts on the page can still see them (#329)
 - Keep a rewritten `<script>`'s original `src` in `__wb_orig_src`, so wombat can return it from `getAttribute("src")` and bundlers that identify chunks by it (Next.js/Turbopack, Vite) still work (openzim/warc2zim#473)
+- Keep URL-encoded `#` characters of the path or querystring when rewriting document URIs, instead of dropping everything after them (#341)
 
 ## [5.4.1] - 2026-07-31
 

src/zimscraperlib/rewriting/url_rewriting.py

@@ -312,7 +312,9 @@ def get_document_uri(self, item_path: ZimPath, item_fragment: str) -> str:
         URI.
 
         """
-        item_parts = urlsplit(item_path.value)
+        # a ZIM path is never URL-encoded, so a `#` in it is a literal character
+        # (e.g. coming from a `%23` in original URL) and not a fragment delimiter
+        item_parts = urlsplit(item_path.value, allow_fragments=False)
 
         # item_path is both path + querystring, both will be url-encoded in the document
         # so that readers consider them as a whole and properly pass them to libzim

tests/rewriting/test_url_rewriting.py

@@ -206,6 +206,39 @@ def test_missing_zim_paths(
                 ["kiwix.org/a/article/foo.html?foo=b?ar"],
                 False,
             ),
+            (
+                "https://kiwix.org/a/article/document.html",
+                "foo%23bar.html",  # a path with an encoded # char
+                RewriteResult(
+                    "https://kiwix.org/a/article/foo%23bar.html",
+                    "foo%23bar.html",
+                    ZimPath("kiwix.org/a/article/foo#bar.html"),
+                ),
+                ["kiwix.org/a/article/foo#bar.html"],
+                False,
+            ),
+            (
+                "https://kiwix.org/a/article/document.html",
+                "foo%23bar.html#anchor1",  # encoded # char followed by a fragment
+                RewriteResult(
+                    "https://kiwix.org/a/article/foo%23bar.html#anchor1",
+                    "foo%23bar.html#anchor1",
+                    ZimPath("kiwix.org/a/article/foo#bar.html"),
+                ),
+                ["kiwix.org/a/article/foo#bar.html"],
+                False,
+            ),
+            (
+                "https://kiwix.org/a/article/document.html",
+                "foo.html?foo=b%23ar",  # a query string with an encoded # char
+                RewriteResult(
+                    "https://kiwix.org/a/article/foo.html?foo=b%23ar",
+                    "foo.html%3Ffoo=b%23ar",
+                    ZimPath("kiwix.org/a/article/foo.html?foo=b#ar"),
+                ),
+                ["kiwix.org/a/article/foo.html?foo=b#ar"],
+                False,
+            ),
             (
                 "https://kiwix.org/a/article/document.html",
                 "fo%o.html",