Only add the italic node as tag if it's between parentheses

src/wiktextract/extractor/fr/gloss.py

@@ -43,15 +43,29 @@ def extract_gloss(
                 )
 
         gloss_only_nodes = []
-        # extract italic tags
-        for node in gloss_nodes[gloss_start:]:
-            if isinstance(node, WikiNode) and node.kind == NodeKind.ITALIC:
+        tag_indexes = set()
+        for index, node in enumerate(gloss_nodes[gloss_start:], gloss_start):
+            # if an italic node is between parentheses then it's a tag, also
+            # don't add the parenthese strings to `gloss_only_nodes`
+            if (
+                isinstance(node, WikiNode)
+                and node.kind == NodeKind.ITALIC
+                and index > gloss_start
+                and isinstance(gloss_nodes[index - 1], str)
+                and gloss_nodes[index - 1].strip() == "("
+                and index + 1 < len(gloss_nodes)
+                and isinstance(gloss_nodes[index + 1], str)
+                and gloss_nodes[index + 1].strip() == ")"
+            ):
                 gloss_data["tags"].append(clean_node(wxr, None, node))
+                tag_indexes |= {index - 1, index, index + 1}
                 continue
-            elif isinstance(node, str) and node.strip() in ["(", ")"]:
-                # remove parentheses around italic node
-                continue
-            gloss_only_nodes.append(node)
+
+        gloss_only_nodes = [
+            node
+            for index, node in enumerate(gloss_nodes[gloss_start:], gloss_start)
+            if index not in tag_indexes
+        ]
         gloss_text = clean_node(wxr, gloss_data, gloss_only_nodes)
         gloss_data["glosses"] = [gloss_text]
         extract_examples(wxr, gloss_data, list_item_node)

src/wiktextract/extractor/fr/inflection.py

@@ -36,6 +36,7 @@ def extract_inflection(
     }
 )
 
+
 @dataclass
 class ColspanHeader:
     text: str
@@ -123,7 +124,9 @@ def process_inflection_table(
                             )
                         else:
                             column_headers.append(table_header_text)
-                        column_cell_index += int(table_cell.attrs.get("colspan", 1))
+                        column_cell_index += int(
+                            table_cell.attrs.get("colspan", 1)
+                        )
                     elif row_num > 0:
                         row_headers.append(table_header_text)
                         if "rowspan" in table_cell.attrs:

tests/test_fr_gloss.py

@@ -196,3 +196,22 @@ def test_italic_tag(self):
                 }
             ],
         )
+
+    def test_not_italic_tag(self):
+        # https://fr.wiktionary.org/wiki/bec-en-ciseaux
+        self.wxr.wtp.start_page("bec-en-ciseaux")
+        root = self.wxr.wtp.parse(
+            "# [[oiseau|Oiseau]] aquatique de taille moyenne du genre ''[[Rhynchops]]''."
+        )
+        page_data = [defaultdict(list)]
+        extract_gloss(self.wxr, page_data, root.children[0])
+        self.assertEqual(
+            page_data,
+            [
+                {
+                    "senses": [
+                        {"glosses": ["Oiseau aquatique de taille moyenne du genre Rhynchops."]}
+                    ]
+                }
+            ],
+        )