[it] extract tag data from "Term" template in gloss list

and add more section templates
tatuylonen · Dec 11, 2024 · e948032 · e948032
1 parent b64f6dc
commit e948032
Show file tree

Hide file tree

Showing 4 changed files with 22 additions and 4 deletions.
diff --git a/src/wiktextract/extractor/it/analyze_template.py b/src/wiktextract/extractor/it/analyze_template.py
@@ -67,7 +67,7 @@
     "Template:-uso-",
     "Template:-var-",
     "Template:-alter-",
-    "Template:-chat-",
+    "Template:-chat-",  # pos
     "Template:-coni-",
     "Template:-decl-",
     "Template:-der-",
@@ -76,6 +76,13 @@
     "Template:-pron-",
     "Template:-prov-",
     "Template:-trascrizione-",  # pos
+    # https://it.wiktionary.org/wiki/Categoria:Template_vocabolo
+    "Template:-etim-",
+    "Template:-trad-",
+    "Template:-ant-",
+    "Template:-cod-",  # pos
+    "Template:-carhi-",  # pos
+    "Template:-quote-",
 }
 
 

diff --git a/src/wiktextract/extractor/it/pos.py b/src/wiktextract/extractor/it/pos.py
@@ -1,4 +1,4 @@
-from wikitextprocessor import LevelNode, NodeKind, WikiNode
+from wikitextprocessor import LevelNode, NodeKind, TemplateNode, WikiNode
 
 from ...page import clean_node
 from ...wxr_context import WiktextractContext
@@ -35,7 +35,15 @@ def extract_gloss_list_item(
     gloss_nodes = []
     sense = Sense()
     for node in list_item.children:
-        if not (isinstance(node, WikiNode) and node.kind == NodeKind.LIST):
+        if isinstance(node, TemplateNode):
+            match node.template_name:
+                case "Term":
+                    raw_tag = clean_node(wxr, sense, node).strip("() \n")
+                    if raw_tag != "":
+                        sense.raw_tags.append(raw_tag)
+                case _:
+                    gloss_nodes.append(node)
+        elif not (isinstance(node, WikiNode) and node.kind == NodeKind.LIST):
             gloss_nodes.append(node)
     gloss_str = clean_node(wxr, sense, gloss_nodes)
     if gloss_str != "":

diff --git a/src/wiktextract/extractor/it/section_titles.py b/src/wiktextract/extractor/it/section_titles.py
@@ -59,4 +59,6 @@
         "pos": "abbrev",
         "tags": ["abbreviation"],
     },
+    "Codice / Simbolo": {"pos": "symbol"},
+    "Carattere hiragana": {"pos": "character", "tags": ["hiragana"]},
 }
diff --git a/tests/test_it_gloss.py b/tests/test_it_gloss.py
@@ -46,7 +46,8 @@ def test_gloss_list(self):
                     "pos_title": "Sostantivo",
                     "senses": [
                         {
-                            "glosses": ["(mammalogia) animale"],
+                            "glosses": ["animale"],
+                            "raw_tags": ["mammalogia"],
                             "categories": ["Mammalogia-IT"],
                         }
                     ],