Merge pull request #952 from xxyzz/pt

[pt, it] add "source" field and translate some tags

src/wiktextract/extractor/it/tags.py

@@ -75,7 +75,7 @@
     "chimica industriale": "chemistry",
     "chirurgia": "surgery",
     "cinematografia": "cinematography",
-    "colori": "color",
+    "colore": "color",
     "commercio": "commerce",
     # "composti organici": "",
     # "composti inorganici": "",
@@ -191,8 +191,30 @@
     "volgare": "vulgar",
 }
 
+# https://it.wiktionary.org/wiki/Categoria:Template_ambito
+GLOSS_LIST_TEMPATE_TAGS = {
+    "accrescitivo": "augmentative",  # Template:Accr
+    "colloquiale": "colloquial",  # Template:Coll
+    "diminutivo": "diminutive",  # Template:Dim
+    "per estensione": "broadly",  # Template:Est
+    "senso figurato": "figuratively",  # Template:Fig
+    "letteralmente": "literally",  # Template:Lett
+    "peggiorativo": "pejorative",  # Template:Pegg
+    "riferito solo a persone": "person",  # Template:Pers
+    "per sineddoche": "synecdoche",  # Template:Sndc
+    "specialmente al plurale": ["especially", "in-plural"],  # Template:Spec pl
+    "spregiativo": "pejorative",  # Template:Spreg
+    "vezzeggiativo": "endearing",  # Template:Vezz
+    "volgare": "vulgar",  # Template:Vulg
+}
+
 
-TAGS = {**TABLE_TAGS, **FORM_LINE_TEMPLATE_TAGS, **TERM_TEMPLATE_TAGS}
+TAGS = {
+    **TABLE_TAGS,
+    **FORM_LINE_TEMPLATE_TAGS,
+    **TERM_TEMPLATE_TAGS,
+    **GLOSS_LIST_TEMPATE_TAGS,
+}
 
 
 def translate_raw_tags(data: WordEntry) -> None:

src/wiktextract/extractor/pt/linkage.py

@@ -71,14 +71,21 @@ def extract_linkage_section(
     linkage_type: str,
     sense: str,
     sense_index: int,
+    source: str,
 ) -> None:
     for node in level_node.children:
         if isinstance(node, TemplateNode) and node.template_name == "fraseini":
             sense, sense_index = extract_fraseini_template(wxr, node)
         elif isinstance(node, WikiNode) and node.kind == NodeKind.LIST:
             for list_item in node.find_child(NodeKind.LIST_ITEM):
                 extract_linkage_list_item(
-                    wxr, word_entry, list_item, linkage_type, sense, sense_index
+                    wxr,
+                    word_entry,
+                    list_item,
+                    linkage_type,
+                    sense,
+                    sense_index,
+                    source,
                 )
 
 
@@ -104,6 +111,7 @@ def extract_linkage_list_item(
     linkage_type: str,
     sense: str,
     sense_index: int,
+    source: str,
 ) -> None:
     linkage_words = []
     raw_tags = []
@@ -161,6 +169,7 @@ def extract_linkage_list_item(
                             linkage_type,
                             sense,
                             sense_index,
+                            source,
                         )
         elif isinstance(node, str):
             m = re.search(r"\((.+)\)", node)
@@ -169,7 +178,11 @@ def extract_linkage_list_item(
 
     for word in linkage_words:
         linkage = Linkage(
-            word=word, sense=sense, sense_index=sense_index, raw_tags=raw_tags
+            word=word,
+            sense=sense,
+            sense_index=sense_index,
+            raw_tags=raw_tags,
+            source=source,
         )
         translate_raw_tags(linkage)
         getattr(word_entry, linkage_type).append(linkage)
@@ -206,4 +219,5 @@ def extract_wikisaurus_page(
                     linkage_type,
                     sense,
                     sense_index,
+                    page_title,
                 )

src/wiktextract/extractor/pt/models.py

@@ -50,6 +50,7 @@ class Linkage(PortugueseBaseModel):
     sense_index: int = Field(
         default=0, ge=0, description="Number of the definition, start from 1"
     )
+    source: str = ""
 
 
 class Sound(PortugueseBaseModel):

src/wiktextract/extractor/pt/page.py

@@ -50,6 +50,7 @@ def parse_section(
             LINKAGE_SECTIONS[title_text],
             "",
             0,
+            "",
         )
     elif title_text == "Etimologia":
         extract_etymology_section(wxr, page_data, level_node)