Merge pull request 'Match wiki pages by address so names with spaces are the same page' (#64) from mil-006-wiki-title-identity into main

Reviewed-on: #64

.gitea/scoped_workflows/publish-wiki.yml

@@ -142,9 +142,27 @@ jobs:
               return owner, repo
 
 
+          def page_key(title):
+              """Return the identity of a page: Gitea stores a space as a hyphen.
+
+              The page "Home da" is the file Home-da.md and its address is Home-da, so
+              both spellings must name the same page.
+              """
+              return str(title).replace(" ", "-")
+
+
           def read_pages(wiki_dir):
-              """Return {page title: content} for every Markdown file in wiki_dir."""
+              """Return {page key: content} for every Markdown file in wiki_dir."""
-              pages = {path.stem: path.read_bytes() for path in sorted(wiki_dir.glob("*.md"))}
+              pages = {}
+              for path in sorted(wiki_dir.glob("*.md")):
+                  key = page_key(path.stem)
+                  if key in pages:
+                      raise WorkflowError(
+                          "configuration",
+                          f"Two files in {wiki_dir} name the wiki page {key}; a space and "
+                          "a hyphen are the same in a page name.",
+                      )
+                  pages[key] = path.read_bytes()
               if not pages:
                   # Publishing an empty directory would delete the whole wiki.
                   raise WorkflowError(
@@ -154,7 +172,10 @@ jobs:
 
 
           def list_wiki_titles(wiki_url, headers, send):
-              """Return the titles of the pages that exist in the wiki.
+              """Return the keys of the pages that exist in the wiki.
+
+              The key is the address Gitea reports (sub_url), or the title with its
+              spaces replaced by hyphens.
 
               Gitea answers 404 for a wiki that has never been written to; that is an
               empty wiki, not a failure.
@@ -171,7 +192,11 @@ jobs:
                       raise
                   if not isinstance(batch, list):
                       raise WorkflowError("api", "Gitea returned an invalid wiki page list.")
-                  titles.update(str(item.get("title", "")) for item in batch)
+                  titles.update(
+                      urllib.parse.unquote(str(item.get("sub_url") or ""))
+                      or page_key(item.get("title", ""))
+                      for item in batch
+                  )
                   if len(batch) < PAGE_LIMIT:
                       return titles
                   page += 1

tests/test_publish_wiki.py

@@ -67,6 +67,27 @@ class TestReadPages:
             publish_wiki.read_pages(tmp_path)
 
 
+class TestPageKey:
+    @pytest.mark.parametrize(
+        ("name", "key"),
+        [("Home", "Home"), ("Home da", "Home-da"), ("Home-da", "Home-da"), ("Home.da", "Home.da"),
+         ("AI Prompt Template ms", "AI-Prompt-Template-ms"), ("_Sidebar", "_Sidebar")],
+    )
+    def test_a_space_and_a_hyphen_are_the_same_page(self, publish_wiki, name, key):
+        assert publish_wiki.page_key(name) == key
+
+    def test_file_names_with_spaces_and_hyphens_are_keyed_the_same(self, publish_wiki, tmp_path):
+        (tmp_path / "Home da.md").write_bytes(b"hjem")
+        (tmp_path / "_Sidebar.md").write_bytes(b"menu")
+        assert publish_wiki.read_pages(tmp_path) == {"Home-da": b"hjem", "_Sidebar": b"menu"}
+
+    def test_two_files_for_one_page_are_refused(self, publish_wiki, tmp_path):
+        (tmp_path / "Home da.md").write_bytes(b"one")
+        (tmp_path / "Home-da.md").write_bytes(b"two")
+        with pytest.raises(publish_wiki.WorkflowError, match="name the wiki page Home-da"):
+            publish_wiki.read_pages(tmp_path)
+
+
 class FakeGitea:
     """Answers like the Gitea repository and wiki endpoints."""
 
@@ -84,7 +105,7 @@ class FakeGitea:
         if url.startswith(f"{WIKI_URL}/pages"):
             if not self.wiki_initialised:
                 raise self.error("configuration", "404")
-            return [{"title": title} for title in self.wiki]
+            return [{"title": key.replace("-", " "), "sub_url": key} for key in self.wiki]
         if method == "POST" and url == f"{WIKI_URL}/new":
             self.wiki[body["title"]] = body["content_base64"]
             return None
@@ -265,6 +286,64 @@ class TestPublish:
         assert gitea.wiki == {"Home": b64("keep me")}
 
 
+class TestPageIdentity:
+    """A wiki that already has pages named with spaces, as Gitea stores them."""
+
+    def test_a_file_named_with_a_space_updates_the_existing_page(
+        self, publish_wiki, environment
+    ):
+        (environment / "Home.md").unlink()
+        (environment / "Credentials.md").unlink()
+        (environment / ".publish").write_text("", encoding="utf-8")
+        (environment / "Home da.md").write_text("hjem v2", encoding="utf-8")
+        gitea = FakeGitea(publish_wiki, wiki={"Home-da": b64("hjem v1")})
+
+        assert run_main(publish_wiki, gitea) == 0
+
+        assert gitea.wiki == {"Home-da": b64("hjem v2")}
+        assert [call[0] for call in gitea.calls].count("POST") == 0
+        assert ("PATCH", f"{WIKI_URL}/page/Home-da") in [(c[0], c[1]) for c in gitea.calls]
+
+    def test_identical_pages_with_spaces_are_a_no_op(self, publish_wiki, environment):
+        (environment / "Home.md").unlink()
+        (environment / "Credentials.md").unlink()
+        (environment / "Home da.md").write_text("hjem", encoding="utf-8")
+        (environment / "_Sidebar.md").write_text("menu", encoding="utf-8")
+        gitea = FakeGitea(
+            publish_wiki, wiki={"Home-da": b64("hjem"), "_Sidebar": b64("menu")}
+        )
+
+        assert run_main(publish_wiki, gitea) == 0
+
+        assert gitea.writes == []
+
+    def test_prune_does_not_delete_a_page_that_is_in_the_folder_under_another_spelling(
+        self, publish_wiki, environment
+    ):
+        (environment / "Home.md").unlink()
+        (environment / "Credentials.md").unlink()
+        (environment / "Install ms.md").write_text("pasang", encoding="utf-8")
+        gitea = FakeGitea(
+            publish_wiki, wiki={"Install-ms": b64("pasang"), "Old-page": b64("x")}
+        )
+
+        assert run_main(publish_wiki, gitea) == 0
+
+        assert gitea.wiki == {"Install-ms": b64("pasang")}
+
+    def test_the_address_wins_over_the_title_and_is_decoded(self, publish_wiki):
+        def listing(url, headers=None, **kwargs):
+            return [
+                {"title": "Whatever", "sub_url": "Real-Address"},
+                {"title": "Only title"},
+                {"title": "Encoded", "sub_url": "Caf%C3%A9"},
+            ]
+
+        keys = publish_wiki.list_wiki_titles(WIKI_URL, {}, listing)
+
+        assert keys == {"Real-Address", "Only-title", "Café"}
+
+
 class TestDescribeToken:
     def test_recognises_a_gitea_token_shape(self, publish_wiki):
         description = publish_wiki.describe_token("a1b2c3d4e5" * 4)