[ku] extract "kîte" hyphenation template (#1522)

Author: xxyzz

src/wiktextract/extractor/ku/sound.py

@@ -18,6 +18,7 @@ def extract_sound_section(
 def extract_sound_list_item(
     wxr: WiktextractContext, word_entry: WordEntry, list_item: WikiNode
 ) -> None:
+    raw_tags = []
     for node in list_item.children:
         if isinstance(node, TemplateNode):
             if node.template_name in ["ku-IPA", "IPA-ku"]:
@@ -26,6 +27,12 @@ def extract_sound_list_item(
                 extract_deng_template(wxr, word_entry, node)
             elif node.template_name == "ku-kîte":
                 extract_ku_kîte(wxr, word_entry, node)
+            elif node.template_name == "kîte":
+                extract_kîte_template(wxr, word_entry, node, raw_tags)
+            elif node.template_name.endswith("."):
+                raw_tag = clean_node(wxr, None, node).removesuffix(":")
+                if raw_tag != "":
+                    raw_tags.append(raw_tag)
         elif isinstance(node, WikiNode) and node.kind == NodeKind.LIST:
             for child_list_item in node.find_child(NodeKind.LIST_ITEM):
                 extract_sound_list_item(wxr, word_entry, child_list_item)
@@ -90,3 +97,23 @@ def extract_ku_kîte(
                     Hyphenation(parts=hyphenation.split("·"))
                 )
             break
+
+
+def extract_kîte_template(
+    wxr: WiktextractContext,
+    word_entry: WordEntry,
+    t_node: TemplateNode,
+    raw_tags: list[str],
+):
+    expanded_node = wxr.wtp.parse(
+        wxr.wtp.node_to_wikitext(t_node), expand_all=True
+    )
+    lang_code = clean_node(wxr, None, t_node.template_parameters.get(1, ""))
+    for span in expanded_node.find_html(
+        "span", attr_name="lang", attr_value=lang_code
+    ):
+        h_str = clean_node(wxr, None, span)
+        if h_str != "":
+            h_data = Hyphenation(parts=h_str.split("‧"), raw_tags=raw_tags)
+            translate_raw_tags(h_data)
+            word_entry.hyphenations.append(h_data)

tests/test_ku_sound.py

@@ -86,3 +86,33 @@ def test_ku_kîte(self):
         self.assertEqual(
             page_data[0]["hyphenations"], [{"parts": ["lê", "ker"]}]
         )
+
+    def test_kîte(self):
+        self.wxr.wtp.add_page("Şablon:ziman", 10, "Latînî")
+        self.wxr.wtp.add_page(
+            "Şablon:pj.", 10, '<span style="font-size:95%;">Pirjimar:</span>'
+        )
+        self.wxr.wtp.add_page(
+            "Şablon:kîte",
+            10,
+            """{{#switch:{{{nivîsna}}}
+| 1 = <span class="Latn" lang="la">-{fā‧bu‧lae}-</span>
+| #default = [[kîte|Kîtekirin]]: <span class="Latn" lang="la">-{fā‧bu‧la}-</span>
+}}""",
+        )
+        data = parse_page(
+            self.wxr,
+            "fabula",
+            """== {{ziman|la}} ==
+=== Bilêvkirin ===
+* {{kîte|la|fā|bu|la}} {{pj.}} {{kîte|la|fā|bu|lae|nivîsna=1}}
+=== Navdêr ===
+# [[efsane]]""",
+        )
+        self.assertEqual(
+            data[0]["hyphenations"],
+            [
+                {"parts": ["fā", "bu", "la"]},
+                {"parts": ["fā", "bu", "lae"], "tags": ["plural"]},
+            ],
+        )