[th] extract "ja-x" and "quote-*" example template

src/wiktextract/extractor/th/example.py

@@ -4,19 +4,30 @@
 
 from ...page import clean_node
 from ...wxr_context import WiktextractContext
+from ..ruby import extract_ruby
 from .models import Example, Sense
 from .tags import translate_raw_tags
 
 
 def extract_example_list_item(
-    wxr: WiktextractContext, sense: Sense, list_item: WikiNode
+    wxr: WiktextractContext,
+    sense: Sense,
+    list_item: WikiNode,
+    ref: str = "",
 ) -> None:
     for node in list_item.children:
         if isinstance(node, TemplateNode):
             if node.template_name in ["ux", "usex", "ko-usex"]:
                 extract_ux_template(wxr, sense, node)
             elif node.template_name in ["zh-x", "zh-usex"]:
                 extract_template_zh_x(wxr, sense, node)
+            elif node.template_name in ["ja-x", "ja-usex"]:
+                extract_template_ja_usex(wxr, sense, node, ref)
+            elif node.template_name.startswith("quote-"):
+                ref = extract_quote_template(wxr, sense, node)
+        elif isinstance(node, WikiNode) and node.kind == NodeKind.LIST:
+            for child_list_item in node.find_child(NodeKind.LIST_ITEM):
+                extract_example_list_item(wxr, sense, child_list_item, ref)
 
 
 def extract_ux_template(
@@ -130,3 +141,67 @@ def extract_zh_x_no_dl_tag(
                     examples.append(example)
 
     return examples
+
+
+def extract_quote_template(
+    wxr: WiktextractContext,
+    sense: Sense,
+    t_node: TemplateNode,
+) -> str:
+    ref = ""
+    if all(
+        arg not in t_node.template_parameters for arg in ["text", "passage", 7]
+    ):
+        ref = clean_node(wxr, sense, t_node)
+    else:
+        expanded_node = wxr.wtp.parse(
+            wxr.wtp.node_to_wikitext(t_node), expand_all=True
+        )
+        example = Example(text="")
+        for span_tag in expanded_node.find_html_recursively("span"):
+            span_class = span_tag.attrs.get("class", "")
+            if "cited-source" == span_class:
+                example.ref = clean_node(wxr, None, span_tag)
+            elif "e-quotation" in span_class:
+                example.text = clean_node(wxr, None, span_tag)
+            elif "e-translation" in span_class:
+                example.translation = clean_node(wxr, None, span_tag)
+        for i_tag in expanded_node.find_html_recursively(
+            "i", attr_name="class", attr_value="e-transliteration"
+        ):
+            example.roman = clean_node(wxr, None, i_tag)
+            break
+        if example.text != "":
+            sense.examples.append(example)
+        clean_node(wxr, sense, expanded_node)
+
+    return ref
+
+
+def extract_template_ja_usex(
+    wxr: WiktextractContext, sense: Sense, t_node: TemplateNode, ref: str
+) -> None:
+    expanded_node = wxr.wtp.parse(
+        wxr.wtp.node_to_wikitext(t_node), expand_all=True
+    )
+    example = Example(text="", ref=ref)
+    for span_tag in expanded_node.find_html(
+        "span", attr_name="class", attr_value="Jpan"
+    ):
+        ruby_data, node_without_ruby = extract_ruby(wxr, span_tag)
+        example.text = clean_node(wxr, None, node_without_ruby)
+        example.ruby = ruby_data
+    for span_tag in expanded_node.find_html_recursively(
+        "span", attr_name="class", attr_value="tr"
+    ):
+        example.roman = clean_node(wxr, None, span_tag)
+    example.translation = clean_node(
+        wxr, None, t_node.template_parameters.get(3, "")
+    )
+    example.literal_meaning = clean_node(
+        wxr, None, t_node.template_parameters.get("lit", "")
+    )
+    if example.text != "":
+        sense.examples.append(example)
+        for link_node in expanded_node.find_child(NodeKind.LINK):
+            clean_node(wxr, sense, link_node)

src/wiktextract/extractor/th/tags.py

@@ -0,0 +1,26 @@
+from .models import WordEntry
+
+EXAMPLE_TAGS = {
+    # แม่แบบ:zh-x, มอดูล:zh-usex/data
+    "MSC": "Modern Standard Chinese",
+    "Pinyin": "Pinyin",
+    "trad.": "Traditional Chinese",
+    "simp.": "Simplified Chinese",
+}
+
+
+TAGS = {**EXAMPLE_TAGS}
+
+
+def translate_raw_tags(data: WordEntry) -> None:
+    raw_tags = []
+    for raw_tag in data.raw_tags:
+        if raw_tag in TAGS and hasattr(data, "tags"):
+            tr_tag = TAGS[raw_tag]
+            if isinstance(tr_tag, str):
+                data.tags.append(tr_tag)
+            elif isinstance(tr_tag, list):
+                data.tags.extend(tr_tag)
+        else:
+            raw_tags.append(raw_tag)
+    data.raw_tags = raw_tags

tests/test_th_example.py

@@ -128,8 +128,7 @@ def test_zh_x_two_text_lines(self):
         self.wxr.wtp.add_page(
             "แม่แบบ:zh-x",
             10,
-            """<dl class="zhusex"><span lang="zh-Hant" class="Hant">[[請#Chinese|請]]<b>大家</b>[[保持#Chinese|保持]][[安靜#Chinese|安靜]]。</span> <span style="color:darkgreen; font-size:x-small;">&#91;[[w:Standard Chinese|MSC]], <i>[[w:Traditional Chinese|trad.]]</i>&#93;</span><br><span lang="zh-Hans" class="Hans">[[请#Chinese|请]]<b>大家</b>[[保持#Chinese|保持]][[安静#Chinese|安静]]。</span> <span style="color:darkgreen; font-size:x-small;">&#91;[[w:Standard Chinese|MSC]], <i>[[w:Simplified Chinese|simp.]]</i>&#93;</span><dd><span lang="zh-Latn" style="color:#404D52"><i>Qǐng <b>dàjiā</b> bǎochí ānjìng.</i></span> <span style="color:darkgreen; font-size:x-small;">&#91;Pinyin&#93;</span></dd><dd>'''ทุกคน'''กรุณาเงียบ</dd></dl>[[Category:ศัพท์ภาษาจีนกลางที่มีตัวอย่างการใช้]]
-""",
+            """<dl class="zhusex"><span lang="zh-Hant" class="Hant">[[請#Chinese|請]]<b>大家</b>[[保持#Chinese|保持]][[安靜#Chinese|安靜]]。</span> <span style="color:darkgreen; font-size:x-small;">&#91;[[w:Standard Chinese|MSC]], <i>[[w:Traditional Chinese|trad.]]</i>&#93;</span><br><span lang="zh-Hans" class="Hans">[[请#Chinese|请]]<b>大家</b>[[保持#Chinese|保持]][[安静#Chinese|安静]]。</span> <span style="color:darkgreen; font-size:x-small;">&#91;[[w:Standard Chinese|MSC]], <i>[[w:Simplified Chinese|simp.]]</i>&#93;</span><dd><span lang="zh-Latn" style="color:#404D52"><i>Qǐng <b>dàjiā</b> bǎochí ānjìng.</i></span> <span style="color:darkgreen; font-size:x-small;">&#91;Pinyin&#93;</span></dd><dd>'''ทุกคน'''กรุณาเงียบ</dd></dl>[[Category:ศัพท์ภาษาจีนกลางที่มีตัวอย่างการใช้]]""",
         )
         page_data = parse_page(
             self.wxr,
@@ -170,3 +169,69 @@ def test_zh_x_two_text_lines(self):
                 ],
             },
         )
+
+    def test_ja_x(self):
+        self.wxr.wtp.add_page(
+            "แม่แบบ:quote-book",
+            10,
+            """<div class="citation-whole"><span class="cited-source">'''1990''' มิถุนายน 15,  [[w:Rumiko Takahashi|Takahashi, Rumiko]],  “[[:แม่แบบ:jaru]] &#91;PART.5 Snatching the Scroll of Secrets&#93;”, in  <cite>[[:แม่แบบ:wj]]</cite> &#91;<cite>[[w:Ranma ½|Ranma ½]]</cite>&#93;, volume 11 (fiction), Tokyo&#58; Shogakukan, <small>[[Special:BookSources/4-09-122431-8|→ISBN]]</small>, page 72:[[Category:ศัพท์ภาษาญี่ปุ่นที่มีการยกข้อความ|大00宀07]]</span><dl><dd></dd></dl></div>""",
+        )
+        self.wxr.wtp.add_page(
+            "แม่แบบ:ja-usex",
+            10,
+            """<span lang="ja" class="Jpan"><ruby>日<rp>(</rp><rt>にっ</rt><rp>)</rp></ruby><ruby>本<rp>(</rp><rt>ぽん</rt><rp>)</rp></ruby>の<ruby>山<rp>(</rp><rt>さん</rt><rp>)</rp></ruby><ruby>中<rp>(</rp><rt>ちゅう</rt><rp>)</rp></ruby>に…'''シロクマ'''がいるか—————っ‼</span><dl><dd><i><span class="tr">Nippon no sanchū ni… '''shirokuma''' ga iru ka—————'‼</span></i></dd><dd>ทำไมถึงมี...หมีขั้วโลกบนภูเขาญี่ปุ่นได้⁉</dd></dl>[[Category:ศัพท์ภาษาญี่ปุ่นที่มีตัวอย่างการใช้|大00宀07]]""",
+        )
+        self.wxr.wtp.add_page(
+            "แม่แบบ:syn of",
+            10,
+            "คำพ้องความของ 北極熊 (ฮกเกียวกุงุมะ, “หมีขั้วโลก”)",
+        )
+        page_data = parse_page(
+            self.wxr,
+            "白熊",
+            """== ภาษาญี่ปุ่น ==
+=== คำนาม ===
+{{ja-noun|しろくま|シロクマ}}
+
+# {{syn of|ja|北極熊|tr=ฮกเกียวกุงุมะ||หมีขั้วโลก}}
+#* {{quote-book|ja
+|| |{{wj|らんま1/2|らんま½}}
+|| 72
+| last=Takahashi
+| first=Rumiko
+| authorlink=Rumiko Takahashi
+| chapter={{jaru|[ＰＡＲＴ] (パート).５　[秘] (ひ) [伝] (でん) [書] (しょ) を[奪] (うば) え}}
+| trans-chapter=PART.5 Snatching the Scroll of Secrets
+| trans-title={{w|Ranma ½}}
+| genre=fiction
+| location=Tokyo
+| publisher=Shogakukan
+| date=Jun 15 1990
+| volume=11
+| isbn=4-09-122431-8}}
+#*: {{ja-usex|日%本の山%中に…'''シロクマ'''がいるか—————っ‼|^にっ%ぽん の さん%ちゅう に… '''シロクマ''' が いる か—————っ‼|ทำไมถึงมี...หมีขั้วโลกบนภูเขาญี่ปุ่นได้⁉}}""",
+        )
+        self.assertEqual(
+            page_data[0]["senses"][0],
+            {
+                "categories": [
+                    "ศัพท์ภาษาญี่ปุ่นที่มีการยกข้อความ",
+                    "ศัพท์ภาษาญี่ปุ่นที่มีตัวอย่างการใช้",
+                ],
+                "glosses": ["คำพ้องความของ 北極熊 (ฮกเกียวกุงุมะ, “หมีขั้วโลก”)"],
+                "examples": [
+                    {
+                        "text": "日本の山中に…シロクマがいるか—————っ‼",
+                        "roman": "Nippon no sanchū ni… shirokuma ga iru ka—————'‼",
+                        "translation": "ทำไมถึงมี...หมีขั้วโลกบนภูเขาญี่ปุ่นได้⁉",
+                        "ruby": [
+                            ("日", "にっ"),
+                            ("本", "ぽん"),
+                            ("山", "さん"),
+                            ("中", "ちゅう"),
+                        ],
+                        "ref": "1990 มิถุนายน 15, Takahashi, Rumiko, “:แม่แบบ:jaru [PART.5 Snatching the Scroll of Secrets]”, in :แม่แบบ:wj [Ranma ½], volume 11 (fiction), Tokyo: Shogakukan, →ISBN, page 72:",
+                    }
+                ],
+            },
+        )