Merge pull request #278 from xxyzz/dl

Fix `dl` HTML tags can't have other HTML children bug

README.md

@@ -53,22 +53,14 @@ cd wikitextprocessor
 python -m venv .venv
 source .venv/bin/activate
 python -m pip install -U pip
-python -m pip install --use-pep517 .
+python -m pip install -e .
 ```
 
-Alternatively, you can install from pypi.org:
-
-```
-python -m pip install wikitextprocessor
-```
-
-If you are installing wiktextract from source, you also need to install wikitextprocessor from source separately; otherwise, a newer wiktextract version will be installed alongside an older pypi version of wikitextprocessor, which will not work out.
-
 ### Running tests
 
 This package includes tests written using the `unittest` framework.
 The test dependencies can be installed with command
-`python -m pip install --use-pep517 -e ".[dev]"`.
+`python -m pip install -e .[dev]`.
 
 To run the tests, use the following command in the top-level directory:
 

src/wikitextprocessor/wikihtml.py

@@ -60,7 +60,7 @@
     "del": {"parents": ["phrasing"], "content": ["phrasing"]},
     "dfn": {"parents": ["phrasing"], "content": ["phrasing"]},
     "div": {"parents": ["flow", "dl"], "content": ["flow"]},
-    "dl": {"parents": ["flow"], "content": []},
+    "dl": {"parents": ["flow"], "content": ["flow"]},
     "dt": {
         "parents": ["dl", "div"],
         "close-next": ["dd", "dt"],

tests/test_parser.py

@@ -2903,6 +2903,23 @@ def test_html_end_tag_slash_after_attr(self):
         self.assertEqual(root.children[2], "\n")
         self.assertEqual(root.children[3].kind, NodeKind.LIST)
 
+    def test_zh_x_html(self):
+        # https://zh.wiktionary.org/wiki/大家
+        # https://zh.wiktionary.org/wiki/Template:Zh-x
+        self.ctx.start_page("大家")
+        root = self.ctx.parse(
+            """<dl class="zhusex"><span lang="zh-Hant" class="Hant">example text</span><dd>translation text</dd></dl>"""  # noqa: E501
+        )
+        span_text = ""
+        dd_text = ""
+        for dl_tag in root.find_html("dl"):
+            for span_tag in dl_tag.find_html("span"):
+                span_text = span_tag.children[0]
+            for dd_tag in dl_tag.find_html("dd"):
+                dd_text = dd_tag.children[0]
+        self.assertEqual(span_text, "example text")
+        self.assertEqual(dd_text, "translation text")
+
 
 # XXX implement <nowiki/> marking for links, templates
 #  - https://en.wikipedia.org/wiki/Help:Wikitext#Nowiki