Add support for sankoku8

TODO.md

@@ -1,10 +1,13 @@
 ### Todo
 
 - [x] Add factory classes to reduce the amount of class import statements
+- [ ] Add dynamic import functionality to factory classes to reduce boilerplate
 - [x] Support exporting to MDict (.MDX) dictionary format
+- [x] Validate JSON schema of Yomichan terms during export
+- [ ] Add support for monokakido search keys from index files
+- [ ] Delete unneeded media from temp build directory before final export
 - [ ] Add test suite
 - [ ] Add documentation (docstrings, etc.)
-- [ ] Validate JSON schema of Yomichan terms during export
 - [ ] Add build scripts for producing program binaries
 - [ ] Validate scraped webpages after downloading
 - [ ] Log non-fatal failures to a log file instead of raising exceptions
@@ -13,7 +16,7 @@
   - [ ] [Yoji-Jukugo.com](https://yoji-jukugo.com/)
   - [ ] [実用日本語表現辞典](https://www.weblio.jp/cat/dictionary/jtnhj)
 - [ ] Support more Monokakido dictionaries
-  - [ ] 三省堂国語辞典 第8版 (SANKOKU8)
+  - [x] 三省堂国語辞典 第8版 (SANKOKU8)
   - [ ] 精選版 日本国語大辞典 (NDS)
   - [ ] 大辞泉 第2版 (DAIJISEN2)
   - [ ] 明鏡国語辞典 第3版 (MK3)

bot/crawlers/crawlers.py

@@ -39,9 +39,9 @@ class Crawler(ABC):
             self._entries.append(entry)
         print()
 
-    def make_yomichan_dictionary(self, media_dir):
+    def make_yomichan_dictionary(self, media_dir, validate):
         exporter = new_yomi_exporter(self._target)
-        exporter.export(self._entries, media_dir)
+        exporter.export(self._entries, media_dir, validate)
 
     def make_mdict_dictionary(self, media_dir, icon_file):
         exporter = new_mdict_exporter(self._target)
@@ -152,3 +152,7 @@ class Smk8Crawler(_MonokakidoCrawler):
 
 class Daijirin2Crawler(_MonokakidoCrawler):
     pass
+
+
+class Sankoku8Crawler(_MonokakidoCrawler):
+    pass

bot/crawlers/factory.py

@@ -5,6 +5,7 @@ from bot.crawlers.crawlers import JitenonYojiCrawler
 from bot.crawlers.crawlers import JitenonKotowazaCrawler
 from bot.crawlers.crawlers import Smk8Crawler
 from bot.crawlers.crawlers import Daijirin2Crawler
+from bot.crawlers.crawlers import Sankoku8Crawler
 
 
 def new_crawler(target):
@@ -14,5 +15,6 @@ def new_crawler(target):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaCrawler,
         Targets.SMK8:             Smk8Crawler,
         Targets.DAIJIRIN2:        Daijirin2Crawler,
+        Targets.SANKOKU8:         Sankoku8Crawler,
     }
     return crawler_map[target](target)

bot/data.py

@@ -37,14 +37,16 @@ def load_config():
 
 @cache
 def load_yomichan_inflection_categories():
-    file_name = os.path.join("yomichan", "inflection_categories.json")
+    file_name = os.path.join(
+        "yomichan", "inflection_categories.json")
     data = __load_json(file_name)
     return data
 
 
 @cache
 def load_yomichan_metadata():
-    file_name = os.path.join("yomichan", "index.json")
+    file_name = os.path.join(
+        "yomichan", "index.json")
     data = __load_json(file_name)
     return data
 
@@ -53,31 +55,21 @@ def load_yomichan_metadata():
 def load_variant_kanji():
     def loader(data, row):
         data[row[0]] = row[1]
-    file_name = os.path.join("entries", "variant_kanji.csv")
+    file_name = os.path.join(
+        "entries", "variant_kanji.csv")
     data = {}
     __load_csv(file_name, loader, data)
     return data
 
 
 @cache
-def load_smk8_phrase_readings():
+def load_phrase_readings(target):
     def loader(data, row):
         entry_id = (int(row[0]), int(row[1]))
         reading = row[2]
         data[entry_id] = reading
-    file_name = os.path.join("entries", "smk8", "phrase_readings.csv")
-    data = {}
-    __load_csv(file_name, loader, data)
-    return data
-
-
-@cache
-def load_daijirin2_phrase_readings():
-    def loader(data, row):
-        entry_id = (int(row[0]), int(row[1]))
-        reading = row[2]
-        data[entry_id] = reading
-    file_name = os.path.join("entries", "daijirin2", "phrase_readings.csv")
+    file_name = os.path.join(
+        "entries", target.value, "phrase_readings.csv")
     data = {}
     __load_csv(file_name, loader, data)
     return data
@@ -92,7 +84,8 @@ def load_daijirin2_kana_abbreviations():
             if abbr.strip() != "":
                 abbreviations.append(abbr)
         data[entry_id] = abbreviations
-    file_name = os.path.join("entries", "daijirin2", "kana_abbreviations.csv")
+    file_name = os.path.join(
+        "entries", "daijirin2", "kana_abbreviations.csv")
     data = {}
     __load_csv(file_name, loader, data)
     return data
@@ -100,14 +93,24 @@ def load_daijirin2_kana_abbreviations():
 
 @cache
 def load_yomichan_name_conversion(target):
-    file_name = os.path.join("yomichan", "name_conversion", f"{target.value}.json")
+    file_name = os.path.join(
+        "yomichan", "name_conversion", f"{target.value}.json")
     data = __load_json(file_name)
     return data
 
 
+@cache
+def load_yomichan_term_schema():
+    file_name = os.path.join(
+        "yomichan", "dictionary-term-bank-v3-schema.json")
+    schema = __load_json(file_name)
+    return schema
+
+
 @cache
 def load_mdict_name_conversion(target):
-    file_name = os.path.join("mdict", "name_conversion", f"{target.value}.json")
+    file_name = os.path.join(
+        "mdict", "name_conversion", f"{target.value}.json")
     data = __load_json(file_name)
     return data
 
@@ -131,7 +134,8 @@ def __load_adobe_glyphs():
                 data[code].append(character)
         else:
             data[code] = [character]
-    file_name = os.path.join("entries", "adobe", "Adobe-Japan1_sequences.txt")
+    file_name = os.path.join(
+        "entries", "adobe", "Adobe-Japan1_sequences.txt")
     data = {}
     __load_csv(file_name, loader, data, delim=';')
     return data
@@ -139,7 +143,8 @@ def __load_adobe_glyphs():
 
 @cache
 def __load_override_adobe_glyphs():
-    file_name = os.path.join("entries", "adobe", "override_glyphs.json")
+    file_name = os.path.join(
+        "entries", "adobe", "override_glyphs.json")
     json_data = __load_json(file_name)
     data = {}
     for key, val in json_data.items():

bot/entries/daijirin2.py

@@ -2,7 +2,7 @@ from bs4 import BeautifulSoup
 
 import bot.entries.expressions as Expressions
 import bot.soup as Soup
-from bot.data import load_daijirin2_phrase_readings
+from bot.data import load_phrase_readings
 from bot.data import load_daijirin2_kana_abbreviations
 from bot.entries.entry import Entry
 from bot.entries.daijirin2_preprocess import preprocess_page
@@ -221,7 +221,7 @@ class Daijirin2PhraseEntry(_BaseDaijirin2Entry):
         return expressions
 
     def _find_readings(self):
-        phrase_readings = load_daijirin2_phrase_readings()
+        phrase_readings = load_phrase_readings(self.target)
         text = phrase_readings[self.entry_id]
         alternatives = Expressions.expand_daijirin_alternatives(text)
         readings = []

bot/entries/factory.py

@@ -5,6 +5,7 @@ from bot.entries.jitenon import JitenonYojiEntry
 from bot.entries.jitenon import JitenonKotowazaEntry
 from bot.entries.smk8 import Smk8Entry
 from bot.entries.daijirin2 import Daijirin2Entry
+from bot.entries.sankoku8 import Sankoku8Entry
 
 
 def new_entry(target, page_id):
@@ -14,5 +15,6 @@ def new_entry(target, page_id):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaEntry,
         Targets.SMK8:             Smk8Entry,
         Targets.DAIJIRIN2:        Daijirin2Entry,
+        Targets.SANKOKU8:         Sankoku8Entry,
     }
     return entry_map[target](target, page_id)

bot/entries/sankoku8.py

@@ -0,0 +1,260 @@
+from bs4 import BeautifulSoup
+import bot.entries.expressions as Expressions
+import bot.soup as Soup
+from bot.entries.entry import Entry
+from bot.data import load_phrase_readings
+from bot.entries.sankoku8_preprocess import preprocess_page
+
+
+class _BaseSankoku8Entry(Entry):
+    def __init__(self, target, entry_id):
+        super().__init__(target, entry_id)
+        self.children = []
+        self.phrases = []
+        self._hyouki_name = "表記"
+        self._midashi_name = None
+        self._midashi_kana_name = None
+
+    def get_global_identifier(self):
+        parent_part = format(self.entry_id[0], '06')
+        child_part = hex(self.entry_id[1]).lstrip('0x').zfill(4).upper()
+        return f"@{self.target.value}-{parent_part}-{child_part}"
+
+    def set_page(self, page):
+        page = self.__decompose_subentries(page)
+        self._page = page
+
+    def get_page_soup(self):
+        soup = BeautifulSoup(self._page, "xml")
+        return soup
+
+    def _get_headwords(self):
+        soup = self.get_page_soup()
+        self._delete_unused_nodes(soup)
+        readings = self._find_readings(soup)
+        expressions = self._find_expressions(soup)
+        headwords = {}
+        for reading in readings:
+            headwords[reading] = []
+        if len(readings) == 1:
+            reading = readings[0]
+            if soup.find(self._midashi_name).find(self._hyouki_name) is None:
+                headwords[reading].append(reading)
+            for exp in expressions:
+                if exp not in headwords[reading]:
+                    headwords[reading].append(exp)
+        elif len(readings) > 1 and len(expressions) == 0:
+            for reading in readings:
+                headwords[reading].append(reading)
+        elif len(readings) > 1 and len(expressions) == 1:
+            if soup.find(self._midashi_name).find(self._hyouki_name) is None:
+                for reading in readings:
+                    headwords[reading].append(reading)
+            expression = expressions[0]
+            for reading in readings:
+                if expression not in headwords[reading]:
+                    headwords[reading].append(expression)
+        elif len(readings) > 1 and len(expressions) == len(readings):
+            if soup.find(self._midashi_name).find(self._hyouki_name) is None:
+                for reading in readings:
+                    headwords[reading].append(reading)
+            for idx, reading in enumerate(readings):
+                exp = expressions[idx]
+                if exp not in headwords[reading]:
+                    headwords[reading].append(exp)
+        else:
+            raise Exception()  # shouldn't happen
+        return headwords
+
+    def _add_variant_expressions(self, headwords):
+        for expressions in headwords.values():
+            Expressions.add_variant_kanji(expressions)
+            Expressions.add_fullwidth(expressions)
+            Expressions.remove_iteration_mark(expressions)
+            Expressions.add_iteration_mark(expressions)
+
+    def get_part_of_speech_tags(self):
+        if self._part_of_speech_tags is not None:
+            return self._part_of_speech_tags
+        self._part_of_speech_tags = []
+        soup = self.get_page_soup()
+        for midashi in soup.find_all([self._midashi_name, "見出部要素"]):
+            pos_group = midashi.find("品詞G")
+            if pos_group is None:
+                continue
+            for tag in pos_group.find_all("a"):
+                if tag.text not in self._part_of_speech_tags:
+                    self._part_of_speech_tags.append(tag.text)
+        return self._part_of_speech_tags
+
+    def _find_expressions(self, soup):
+        expressions = []
+        for hyouki in soup.find_all(self._hyouki_name):
+            for expression in parse_hyouki_soup(hyouki, [""]):
+                expressions.append(expression)
+        return expressions
+
+    def _find_readings(self, soup):
+        midasi_kana = soup.find(self._midashi_kana_name)
+        readings = parse_hyouki_soup(midasi_kana, [""])
+        return readings
+
+    def __decompose_subentries(self, page):
+        soup = BeautifulSoup(page, features="xml")
+        subentry_parameters = [
+            [Sankoku8ChildEntry, ["子項目"], self.children],
+            [Sankoku8PhraseEntry, ["句項目"], self.phrases],
+        ]
+        for x in subentry_parameters:
+            subentry_class, tags, subentry_list = x
+            for tag in tags:
+                tag_soup = soup.find(tag)
+                while tag_soup is not None:
+                    tag_soup.name = "項目"
+                    subentry_id = self.id_string_to_entry_id(tag_soup.attrs["id"])
+                    self.SUBENTRY_ID_TO_ENTRY_ID[subentry_id] = self.entry_id
+                    subentry = subentry_class(self.target, subentry_id)
+                    page = tag_soup.decode()
+                    subentry.set_page(page)
+                    subentry_list.append(subentry)
+                    tag_soup.decompose()
+                    tag_soup = soup.find(tag)
+        return soup.decode()
+
+    @staticmethod
+    def id_string_to_entry_id(id_string):
+        parts = id_string.split("-")
+        if len(parts) == 1:
+            return (int(parts[0]), 0)
+        elif len(parts) == 2:
+            # subentries have a hexadecimal part
+            return (int(parts[0]), int(parts[1], 16))
+        else:
+            raise Exception(f"Invalid entry ID: {id_string}")
+
+    @staticmethod
+    def _delete_unused_nodes(soup):
+        """Remove extra markup elements that appear in the entry
+        headword line which are not part of the entry headword"""
+        unused_nodes = [
+            "語構成", "平板", "アクセント", "表外字マーク", "表外音訓マーク",
+            "アクセント分節", "活用分節", "ルビG", "分書"
+        ]
+        for name in unused_nodes:
+            Soup.delete_soup_nodes(soup, name)
+
+
+class Sankoku8Entry(_BaseSankoku8Entry):
+    def __init__(self, target, page_id):
+        entry_id = (page_id, 0)
+        super().__init__(target, entry_id)
+        self._midashi_name = "見出部"
+        self._midashi_kana_name = "見出仮名"
+
+    def set_page(self, page):
+        page = preprocess_page(page)
+        super().set_page(page)
+
+
+class Sankoku8ChildEntry(_BaseSankoku8Entry):
+    def __init__(self, target, page_id):
+        super().__init__(target, page_id)
+        self._midashi_name = "子見出部"
+        self._midashi_kana_name = "子見出仮名"
+
+
+class Sankoku8PhraseEntry(_BaseSankoku8Entry):
+    def get_part_of_speech_tags(self):
+        # phrases do not contain these tags
+        return []
+
+    def _get_headwords(self):
+        soup = self.get_page_soup()
+        self._delete_unused_nodes(soup)
+        expressions = self._find_expressions(soup)
+        readings = self._find_readings(soup)
+        headwords = {}
+        if len(expressions) != len(readings):
+            raise Exception(f"{self.entry_id[0]}-{self.entry_id[1]}")
+        for idx, expression in enumerate(expressions):
+            reading = readings[idx]
+            if reading in headwords:
+                headwords[reading].append(expression)
+            else:
+                headwords[reading] = [expression]
+        return headwords
+
+    def _find_expressions(self, soup):
+        phrase_soup = soup.find("句表記")
+        expressions = parse_hyouki_soup(phrase_soup, [""])
+        return expressions
+
+    def _find_readings(self, soup):
+        reading_patterns = load_phrase_readings(self.target)
+        reading_pattern = reading_patterns[self.entry_id]
+        readings = parse_hyouki_pattern(reading_pattern)
+        return readings
+
+
+def parse_hyouki_soup(soup, base_exps):
+    omitted_characters = [
+        "／", "〈", "〉", "（", "）", "⦅", "⦆", "：", "…"
+    ]
+    exps = base_exps.copy()
+    for child in soup.children:
+        new_exps = []
+        if child.name == "言換G":
+            for alt in child.find_all("言換"):
+                parts = parse_hyouki_soup(alt, [""])
+                for exp in exps:
+                    for part in parts:
+                        new_exps.append(exp + part)
+        elif child.name == "補足表記":
+            alt1 = child.find("表記対象")
+            alt2 = child.find("表記内容G")
+            parts1 = parse_hyouki_soup(alt1, [""])
+            parts2 = parse_hyouki_soup(alt2, [""])
+            for exp in exps:
+                for part in parts1:
+                    new_exps.append(exp + part)
+                for part in parts2:
+                    new_exps.append(exp + part)
+        elif child.name == "省略":
+            parts = parse_hyouki_soup(child, [""])
+            for exp in exps:
+                new_exps.append(exp)
+                for part in parts:
+                    new_exps.append(exp + part)
+        elif child.name is not None:
+            new_exps = parse_hyouki_soup(child, exps)
+        else:
+            text = child.text
+            for char in omitted_characters:
+                text = text.replace(char, "")
+            for exp in exps:
+                new_exps.append(exp + text)
+        exps = new_exps.copy()
+    return exps
+
+
+def parse_hyouki_pattern(pattern):
+    replacements = {
+        "（": "<省略>（",
+        "）": "）</省略>",
+        "｛": "<補足表記><表記対象>",
+        "・": "</表記対象><表記内容G>（<表記内容>",
+        "｝": "</表記内容>）</表記内容G></補足表記>",
+        "〈": "<言換G>〈<言換>",
+        "／": "</言換>／<言換>",
+        "〉": "</言換>〉</言換G>",
+        "⦅": "<補足表記><表記対象>",
+        "＼": "</表記対象><表記内容G>⦅<表記内容>",
+        "⦆": "</表記内容>⦆</表記内容G></補足表記>",
+    }
+    markup = f"<span>{pattern}</span>"
+    for key, val in replacements.items():
+        markup = markup.replace(key, val)
+    soup = BeautifulSoup(markup, "xml")
+    hyouki_soup = soup.find("span")
+    exps = parse_hyouki_soup(hyouki_soup, [""])
+    return exps

bot/entries/sankoku8_preprocess.py

@@ -0,0 +1,28 @@
+import re
+from bs4 import BeautifulSoup
+
+from bot.data import get_adobe_glyph
+
+
+def preprocess_page(page):
+    soup = BeautifulSoup(page, features="xml")
+    __replace_glyph_codes(soup)
+    page = __strip_page(soup)
+    return page
+
+
+def __replace_glyph_codes(soup):
+    for el in soup.find_all("glyph"):
+        m = re.search(r"^glyph:([0-9]+);?$", el.attrs["style"])
+        code = int(m.group(1))
+        for geta in el.find_all(string="〓"):
+            glyph = get_adobe_glyph(code)
+            geta.replace_with(glyph)
+
+
+def __strip_page(soup):
+    koumoku = soup.find(["項目"])
+    if koumoku is not None:
+        return koumoku.decode()
+    else:
+        raise Exception(f"Primary 項目 not found in page:\n{soup.prettify()}")

bot/entries/smk8.py

@@ -2,7 +2,7 @@ from bs4 import BeautifulSoup
 
 import bot.entries.expressions as Expressions
 import bot.soup as Soup
-from bot.data import load_smk8_phrase_readings
+from bot.data import load_phrase_readings
 from bot.entries.entry import Entry
 from bot.entries.smk8_preprocess import preprocess_page
 
@@ -163,7 +163,7 @@ class Smk8ChildEntry(_BaseSmk8Entry):
 class Smk8PhraseEntry(_BaseSmk8Entry):
     def __init__(self, target, entry_id):
         super().__init__(target, entry_id)
-        self.__phrase_readings = load_smk8_phrase_readings()
+        self.__phrase_readings = load_phrase_readings(self.target)
 
     def get_part_of_speech_tags(self):
         # phrases do not contain these tags

bot/mdict/exporters/export.py

@@ -218,3 +218,8 @@ class Smk8Exporter(_MonokakidoExporter):
 class Daijirin2Exporter(_MonokakidoExporter):
     def _get_attribution(self, entries):
         return "© Sanseido Co., LTD. 2019"
+
+
+class Sankoku8Exporter(_MonokakidoExporter):
+    def _get_attribution(self, entries):
+        return "© Sanseido Co., LTD. 2021"

bot/mdict/exporters/factory.py

@@ -5,6 +5,7 @@ from bot.mdict.exporters.export import JitenonYojiExporter
 from bot.mdict.exporters.export import JitenonKotowazaExporter
 from bot.mdict.exporters.export import Smk8Exporter
 from bot.mdict.exporters.export import Daijirin2Exporter
+from bot.mdict.exporters.export import Sankoku8Exporter
 
 
 def new_mdict_exporter(target):
@@ -14,5 +15,6 @@ def new_mdict_exporter(target):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaExporter,
         Targets.SMK8:             Smk8Exporter,
         Targets.DAIJIRIN2:        Daijirin2Exporter,
+        Targets.SANKOKU8:         Sankoku8Exporter,
     }
     return exporter_map[target](target)

bot/mdict/glossary/sankoku8.py

@@ -0,0 +1,137 @@
+import re
+from bs4 import BeautifulSoup
+from bot.data import load_mdict_name_conversion
+from bot.name_conversion import convert_names
+
+
+def make_glossary(entry, media_dir):
+    soup = entry.get_page_soup()
+    __reposition_marks(soup)
+    __remove_appendix_links(soup)
+    __convert_images(soup)
+    __remove_links_without_href(soup)
+    __convert_links(soup, entry)
+    __add_parent_link(soup, entry)
+    __add_homophone_links(soup, entry)
+
+    name_conversion = load_mdict_name_conversion(entry.target)
+    convert_names(soup, name_conversion)
+
+    glossary = soup.span.decode()
+    return glossary
+
+
+def __reposition_marks(soup):
+    """These 表外字マーク symbols will be converted to rubies later, so they need to
+    be positioned after the corresponding text in order to appear correctly"""
+    for elm in soup.find_all("表外字"):
+        mark = elm.find("表外字マーク")
+        elm.append(mark)
+    for elm in soup.find_all("表外音訓"):
+        mark = elm.find("表外音訓マーク")
+        elm.append(mark)
+
+
+def __remove_appendix_links(soup):
+    """This info would be useful and nice to have, but jitenbot currently
+    isn't designed to fetch and process these appendix files. It probably
+    wouldn't be possible to include them in Yomichan, but it would definitely
+    be possible for Mdict."""
+    for elm in soup.find_all("a"):
+        if not elm.has_attr("href"):
+            continue
+        if elm.attrs["href"].startswith("appendix"):
+            elm.attrs["data-name"] = "a"
+            elm.attrs["data-href"] = elm.attrs["href"]
+            elm.name = "span"
+            del elm.attrs["href"]
+
+
+def __convert_images(soup):
+    conversions = [
+        ["svg-logo/重要語.svg", "＊"],
+        ["svg-logo/最重要語.svg", "＊＊"],
+        ["svg-logo/一般常識語.svg", "☆☆"],
+        ["svg-logo/追い込み.svg", ""],
+        ["svg-special/区切り線.svg", "|"],
+        ["svg-accent/平板.svg", "⎺"],
+        ["svg-accent/アクセント.svg", "⌝"],
+        ["svg-logo/アク.svg", "アク"],
+        ["svg-logo/丁寧.svg", "丁寧"],
+        ["svg-logo/可能.svg", "可能"],
+        ["svg-logo/尊敬.svg", "尊敬"],
+        ["svg-logo/接尾.svg", "接尾"],
+        ["svg-logo/接頭.svg", "接頭"],
+        ["svg-logo/表記.svg", "表記"],
+        ["svg-logo/謙譲.svg", "謙譲"],
+        ["svg-logo/区別.svg", "区別"],
+        ["svg-logo/由来.svg", "由来"],
+    ]
+    for conversion in conversions:
+        filename, text = conversion
+        for elm in soup.find_all("img", attrs={"src": filename}):
+            elm.attrs["data-name"] = elm.name
+            elm.attrs["data-src"] = elm.attrs["src"]
+            elm.name = "span"
+            elm.string = text
+            del elm.attrs["src"]
+
+
+def __remove_links_without_href(soup):
+    for elm in soup.find_all("a"):
+        if elm.has_attr("href"):
+            continue
+        elm.attrs["data-name"] = elm.name
+        elm.name = "span"
+
+
+def __convert_links(soup, entry):
+    for elm in soup.find_all("a"):
+        href = elm.attrs["href"].split(" ")[0]
+        if re.match(r"^#?[0-9]+(?:-[0-9A-F]{4})?$", href):
+            href = href.removeprefix("#")
+            ref_entry_id = entry.id_string_to_entry_id(href)
+            if ref_entry_id in entry.ID_TO_ENTRY:
+                ref_entry = entry.ID_TO_ENTRY[ref_entry_id]
+            else:
+                ref_entry = entry.ID_TO_ENTRY[(ref_entry_id[0], 0)]
+            gid = ref_entry.get_global_identifier()
+            elm.attrs["href"] = f"entry://{gid}"
+        elif re.match(r"^entry:", href):
+            pass
+        elif re.match(r"^https?:[\w\W]*", href):
+            pass
+        else:
+            raise Exception(f"Invalid href format: {href}")
+
+
+def __add_parent_link(soup, entry):
+    elm = soup.find("親見出相当部")
+    if elm is not None:
+        parent_entry = entry.get_parent()
+        gid = parent_entry.get_global_identifier()
+        elm.attrs["href"] = f"entry://{gid}"
+        elm.attrs["data-name"] = elm.name
+        elm.name = "a"
+
+
+def __add_homophone_links(soup, entry):
+    forward_link = ["←", entry.entry_id[0] + 1]
+    backward_link = ["→", entry.entry_id[0] - 1]
+    homophone_info_list = [
+        ["svg-logo/homophone1.svg", [forward_link]],
+        ["svg-logo/homophone2.svg", [forward_link, backward_link]],
+        ["svg-logo/homophone3.svg", [backward_link]],
+    ]
+    for homophone_info in homophone_info_list:
+        filename, link_info = homophone_info
+        for elm in soup.find_all("img", attrs={"src": filename}):
+            for info in link_info:
+                text, link_id = info
+                link_entry = entry.ID_TO_ENTRY[(link_id, 0)]
+                gid = link_entry.get_global_identifier()
+                link = BeautifulSoup("<a/>", "xml").a
+                link.string = text
+                link.attrs["href"] = f"entry://{gid}"
+                elm.append(link)
+            elm.unwrap()

bot/mdict/terms/factory.py

@@ -5,6 +5,7 @@ from bot.mdict.terms.jitenon import JitenonYojiTerminator
 from bot.mdict.terms.jitenon import JitenonKotowazaTerminator
 from bot.mdict.terms.smk8 import Smk8Terminator
 from bot.mdict.terms.daijirin2 import Daijirin2Terminator
+from bot.mdict.terms.sankoku8 import Sankoku8Terminator
 
 
 def new_terminator(target):
@@ -14,5 +15,6 @@ def new_terminator(target):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaTerminator,
         Targets.SMK8:             Smk8Terminator,
         Targets.DAIJIRIN2:        Daijirin2Terminator,
+        Targets.SANKOKU8:         Sankoku8Terminator,
     }
     return terminator_map[target](target)

bot/mdict/terms/sankoku8.py

@@ -0,0 +1,23 @@
+from bot.mdict.terms.terminator import Terminator
+from bot.mdict.glossary.sankoku8 import make_glossary
+
+
+class Sankoku8Terminator(Terminator):
+    def _glossary(self, entry):
+        if entry.entry_id in self._glossary_cache:
+            return self._glossary_cache[entry.entry_id]
+        glossary = make_glossary(entry, self._media_dir)
+        self._glossary_cache[entry.entry_id] = glossary
+        return glossary
+
+    def _link_glossary_parameters(self, entry):
+        return [
+            [entry.children, "子項目"],
+            [entry.phrases, "句項目"],
+        ]
+
+    def _subentry_lists(self, entry):
+        return [
+            entry.children,
+            entry.phrases,
+        ]

bot/targets.py

@@ -7,3 +7,4 @@ class Targets(Enum):
     JITENON_KOTOWAZA = "jitenon-kotowaza"
     SMK8 = "smk8"
     DAIJIRIN2 = "daijirin2"
+    SANKOKU8 = "sankoku8"

bot/yomichan/exporters/export.py

@@ -3,13 +3,16 @@
 import json
 import os
 import shutil
+import copy
 from pathlib import Path
 from datetime import datetime
 from abc import ABC, abstractmethod
 from platformdirs import user_documents_dir, user_cache_dir
 
+import fastjsonschema
 from bot.data import load_yomichan_metadata
 from bot.yomichan.terms.factory import new_terminator
+from bot.data import load_yomichan_term_schema
 
 
 class Exporter(ABC):
@@ -19,7 +22,7 @@ class Exporter(ABC):
         self._build_dir = None
         self._terms_per_file = 2000
 
-    def export(self, entries, image_dir):
+    def export(self, entries, image_dir, validate):
         self.__init_build_image_dir(image_dir)
         meta = load_yomichan_metadata()
         index = meta[self._target.value]["index"]
@@ -27,6 +30,8 @@ class Exporter(ABC):
         index["attribution"] = self._get_attribution(entries)
         tags = meta[self._target.value]["tags"]
         terms = self.__get_terms(entries)
+        if validate:
+            self.__validate_terms(terms)
         self.__make_dictionary(terms, index, tags)
 
     @abstractmethod
@@ -49,6 +54,14 @@ class Exporter(ABC):
         self._build_dir = build_directory
         return self._build_dir
 
+    def __get_invalid_term_dir(self):
+        cache_dir = user_cache_dir("jitenbot")
+        log_dir = os.path.join(cache_dir, "invalid_yomichan_terms")
+        if Path(log_dir).is_dir():
+            shutil.rmtree(log_dir)
+        os.makedirs(log_dir)
+        return log_dir
+
     def __init_build_image_dir(self, image_dir):
         build_dir = self._get_build_dir()
         build_img_dir = os.path.join(build_dir, self._target.value)
@@ -71,8 +84,29 @@ class Exporter(ABC):
         print()
         return terms
 
+    def __validate_terms(self, terms):
+        print("Making a copy of term data for validation...")
+        terms_copy = copy.deepcopy(terms)  # because validator will alter data!
+        term_count = len(terms_copy)
+        log_dir = self.__get_invalid_term_dir()
+        schema = load_yomichan_term_schema()
+        validator = fastjsonschema.compile(schema)
+        failure_count = 0
+        for idx, term in enumerate(terms_copy):
+            update = f"Validating term {idx+1}/{term_count}"
+            print(update, end='\r', flush=True)
+            try:
+                validator([term])
+            except fastjsonschema.JsonSchemaException:
+                failure_count += 1
+                term_file = os.path.join(log_dir, f"{idx}.json")
+                with open(term_file, "w", encoding='utf8') as f:
+                    json.dump([term], f, indent=4, ensure_ascii=False)
+        print(f"\nFinished validating with {failure_count} error{'' if failure_count == 1 else 's'}")
+        if failure_count > 0:
+            print(f"Invalid terms saved to `{log_dir}` for debugging")
+
     def __make_dictionary(self, terms, index, tags):
-        print(f"Exporting {len(terms)} Yomichan terms...")
         self.__write_term_banks(terms)
         self.__write_index(index)
         self.__write_tag_bank(tags)
@@ -80,14 +114,18 @@ class Exporter(ABC):
         self.__rm_build_dir()
 
     def __write_term_banks(self, terms):
+        print(f"Exporting {len(terms)} JSON terms")
         build_dir = self._get_build_dir()
         max_i = int(len(terms) / self._terms_per_file) + 1
         for i in range(max_i):
-            term_file = os.path.join(build_dir, f"term_bank_{i+1}.json")
-            with open(term_file, "w", encoding='utf8') as f:
             start = self._terms_per_file * i
             end = self._terms_per_file * (i + 1)
+            update = f"Writing terms to term banks {start} - {end}"
+            print(update, end='\r', flush=True)
+            term_file = os.path.join(build_dir, f"term_bank_{i+1}.json")
+            with open(term_file, "w", encoding='utf8') as f:
                 json.dump(terms[start:end], f, indent=4, ensure_ascii=False)
+        print()
 
     def __write_index(self, index):
         build_dir = self._get_build_dir()
@@ -104,6 +142,7 @@ class Exporter(ABC):
             json.dump(tags, f, indent=4, ensure_ascii=False)
 
     def __write_archive(self, filename):
+        print("Archiving data to ZIP file...")
         archive_format = "zip"
         out_dir = os.path.join(user_documents_dir(), "jitenbot", "yomichan")
         if not Path(out_dir).is_dir():
@@ -151,19 +190,22 @@ class JitenonKotowazaExporter(_JitenonExporter):
     pass
 
 
-class Smk8Exporter(Exporter):
+class _MonokakidoExporter(Exporter):
     def _get_revision(self, entries):
         timestamp = datetime.now().strftime("%Y-%m-%d")
         return f"{self._target.value};{timestamp}"
 
+
+class Smk8Exporter(_MonokakidoExporter):
     def _get_attribution(self, entries):
         return "© Sanseido Co., LTD. 2020"
 
 
-class Daijirin2Exporter(Exporter):
-    def _get_revision(self, entries):
-        timestamp = datetime.now().strftime("%Y-%m-%d")
-        return f"{self._target.value};{timestamp}"
-
+class Daijirin2Exporter(_MonokakidoExporter):
     def _get_attribution(self, entries):
         return "© Sanseido Co., LTD. 2019"
+
+
+class Sankoku8Exporter(_MonokakidoExporter):
+    def _get_attribution(self, entries):
+        return "© Sanseido Co., LTD. 2021"

bot/yomichan/exporters/factory.py

@@ -5,6 +5,7 @@ from bot.yomichan.exporters.export import JitenonYojiExporter
 from bot.yomichan.exporters.export import JitenonKotowazaExporter
 from bot.yomichan.exporters.export import Smk8Exporter
 from bot.yomichan.exporters.export import Daijirin2Exporter
+from bot.yomichan.exporters.export import Sankoku8Exporter
 
 
 def new_yomi_exporter(target):
@@ -14,5 +15,6 @@ def new_yomi_exporter(target):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaExporter,
         Targets.SMK8:             Smk8Exporter,
         Targets.DAIJIRIN2:        Daijirin2Exporter,
+        Targets.SANKOKU8:         Sankoku8Exporter,
     }
     return exporter_map[target](target)

bot/yomichan/glossary/icons.py

@@ -26,6 +26,27 @@ def make_monochrome_fill_rectangle(path, text):
         f.write(svg)
 
 
+@cache
+def make_accent(path):
+    svg = __svg_accent()
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(svg)
+
+
+@cache
+def make_heiban(path):
+    svg = __svg_heiban()
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(svg)
+
+
+@cache
+def make_red_char(path, char):
+    svg = __svg_red_character(char)
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(svg)
+
+
 def __calculate_svg_ratio(path):
     with open(path, "r", encoding="utf-8") as f:
         xml = f.read()
@@ -82,3 +103,30 @@ def __svg_masked_rectangle(text):
           fill='black' mask='url(#a)'/>
 </svg>"""
     return svg.strip()
+
+
+def __svg_heiban():
+    svg = f"""
+<svg viewBox='0 0 210 300' xmlns='http://www.w3.org/2000/svg' version='1.1'>
+    <rect width='210' height='30' fill='red'/>
+</svg>"""
+    return svg.strip()
+
+
+def __svg_accent():
+    svg = f"""
+<svg viewBox='0 0 150 300' xmlns='http://www.w3.org/2000/svg' version='1.1'>
+    <rect width='150' height='30' fill='red'/>
+    <rect width='30' height='150' x='120' fill='red'/>
+</svg>"""
+    return svg.strip()
+
+
+def __svg_red_character(char):
+    svg = f"""
+<svg viewBox='0 0 300 300' xmlns='http://www.w3.org/2000/svg' version='1.1'>
+    <text text-anchor='middle' x='50%' y='50%' dy='.37em'
+          font-family='sans-serif' font-size='300px'
+          fill='red'>{char}</text>
+</svg>"""
+    return svg.strip()

bot/yomichan/glossary/sankoku8.py

@@ -0,0 +1,344 @@
+import re
+import os
+from bs4 import BeautifulSoup
+
+import bot.yomichan.glossary.icons as Icons
+from bot.data import load_yomichan_name_conversion
+from bot.yomichan.glossary.gloss import make_gloss
+from bot.name_conversion import convert_names
+
+
+def make_glossary(entry, media_dir):
+    soup = entry.get_page_soup()
+    __remove_glyph_styles(soup)
+    __reposition_marks(soup)
+    __remove_links_without_href(soup)
+    __remove_appendix_links(soup)
+    __convert_links(soup, entry)
+    __add_parent_link(soup, entry)
+    __add_homophone_links(soup, entry)
+    __convert_images_to_text(soup)
+    __text_parens_to_images(soup, media_dir)
+    __replace_icons(soup, media_dir)
+    __replace_accent_symbols(soup, media_dir)
+    __convert_gaiji(soup, media_dir)
+    __convert_graphics(soup, media_dir)
+    __convert_number_icons(soup, media_dir)
+
+    name_conversion = load_yomichan_name_conversion(entry.target)
+    convert_names(soup, name_conversion)
+
+    gloss = make_gloss(soup.span)
+    glossary = [gloss]
+    return glossary
+
+
+def __remove_glyph_styles(soup):
+    """The css_parser library will emit annoying warning messages
+    later if it sees these glyph character styles"""
+    for elm in soup.find_all("glyph"):
+        if elm.has_attr("style"):
+            elm["data-style"] = elm.attrs["style"]
+            del elm.attrs["style"]
+
+
+def __reposition_marks(soup):
+    """These マーク symbols will be converted to rubies later, so they need to
+    be positioned after the corresponding text in order to appear correctly"""
+    for elm in soup.find_all("表外字"):
+        mark = elm.find("表外字マーク")
+        elm.append(mark)
+    for elm in soup.find_all("表外音訓"):
+        mark = elm.find("表外音訓マーク")
+        elm.append(mark)
+
+
+def __remove_links_without_href(soup):
+    for elm in soup.find_all("a"):
+        if elm.has_attr("href"):
+            continue
+        elm.attrs["data-name"] = elm.name
+        elm.name = "span"
+
+
+def __remove_appendix_links(soup):
+    for elm in soup.find_all("a"):
+        if elm.attrs["href"].startswith("appendix"):
+            elm.unwrap()
+
+
+def __convert_links(soup, entry):
+    for elm in soup.find_all("a"):
+        href = elm.attrs["href"].split(" ")[0]
+        href = href.removeprefix("#")
+        if not re.match(r"^[0-9]+(?:-[0-9A-F]{4})?$", href):
+            raise Exception(f"Invalid href format: {href}")
+        ref_entry_id = entry.id_string_to_entry_id(href)
+        if ref_entry_id in entry.ID_TO_ENTRY:
+            ref_entry = entry.ID_TO_ENTRY[ref_entry_id]
+        else:
+            ref_entry = entry.ID_TO_ENTRY[(ref_entry_id[0], 0)]
+        expression = ref_entry.get_first_expression()
+        elm.attrs["href"] = f"?query={expression}&wildcards=off"
+
+
+def __add_parent_link(soup, entry):
+    elm = soup.find("親見出相当部")
+    if elm is not None:
+        parent_entry = entry.get_parent()
+        expression = parent_entry.get_first_expression()
+        elm.attrs["href"] = f"?query={expression}&wildcards=off"
+        elm.name = "a"
+
+
+def __add_homophone_links(soup, entry):
+    forward_link = ["←", entry.entry_id[0] + 1]
+    backward_link = ["→", entry.entry_id[0] - 1]
+    homophone_info_list = [
+        ["svg-logo/homophone1.svg", [forward_link]],
+        ["svg-logo/homophone2.svg", [forward_link, backward_link]],
+        ["svg-logo/homophone3.svg", [backward_link]],
+    ]
+    for homophone_info in homophone_info_list:
+        filename, link_info = homophone_info
+        for elm in soup.find_all("img", attrs={"src": filename}):
+            for info in link_info:
+                text, link_id = info
+                link_entry = entry.ID_TO_ENTRY[(link_id, 0)]
+                expression = link_entry.get_first_expression()
+                link = BeautifulSoup("<a/>", "xml").a
+                link.string = text
+                link.attrs["href"] = f"?query={expression}&wildcards=off"
+                elm.append(link)
+            elm.unwrap()
+
+
+def __convert_images_to_text(soup):
+    conversions = [
+        ["svg-logo/重要語.svg", "＊", "vertical-align: super; font-size: 0.6em"],
+        ["svg-logo/最重要語.svg", "＊＊", "vertical-align: super; font-size: 0.6em"],
+        ["svg-logo/一般常識語.svg", "☆☆", "vertical-align: super; font-size: 0.6em"],
+        ["svg-logo/追い込み.svg", "", ""],
+        ["svg-special/区切り線.svg", "|", ""],
+    ]
+    for conversion in conversions:
+        filename, text, style = conversion
+        for elm in soup.find_all("img", attrs={"src": filename}):
+            if text == "":
+                elm.unwrap()
+                continue
+            if style != "":
+                elm.attrs["style"] = style
+            elm.attrs["data-name"] = elm.name
+            elm.attrs["data-src"] = elm.attrs["src"]
+            elm.name = "span"
+            elm.string = text
+            del elm.attrs["src"]
+
+
+def __text_parens_to_images(soup, media_dir):
+    for elm in soup.find_all("red"):
+        char = elm.text
+        if char not in ["（", "）"]:
+            continue
+        filename = f"red_{char}.svg"
+        path = os.path.join(media_dir, filename)
+        Icons.make_red_char(path, char)
+        ratio = Icons.calculate_ratio(path)
+        img = BeautifulSoup("<img/>", "xml").img
+        img.attrs = {
+            "height": 1.0,
+            "width": ratio,
+            "sizeUnits": "em",
+            "collapsible": False,
+            "collapsed": False,
+            "background": False,
+            "appearance": "auto",
+            "path": f"{os.path.basename(media_dir)}/{filename}",
+        }
+        elm.attrs["data-name"] = elm.name
+        elm.name = "span"
+        elm.string = ""
+        elm.append(img)
+        elm.attrs["style"] = "vertical-align: text-bottom;"
+
+
+def __replace_icons(soup, media_dir):
+    cls_to_appearance = {
+        "default": "monochrome",
+        "fill": "monochrome",
+        "red": "auto",
+        "redfill": "auto",
+        "none": "monochrome",
+    }
+    icon_info_list = [
+        ["svg-logo/アク.svg", "アク", "default"],
+        ["svg-logo/丁寧.svg", "丁寧", "default"],
+        ["svg-logo/可能.svg", "可能", "default"],
+        ["svg-logo/尊敬.svg", "尊敬", "default"],
+        ["svg-logo/接尾.svg", "接尾", "default"],
+        ["svg-logo/接頭.svg", "接頭", "default"],
+        ["svg-logo/表記.svg", "表記", "default"],
+        ["svg-logo/謙譲.svg", "謙譲", "default"],
+        ["svg-logo/区別.svg", "区別", "redfill"],
+        ["svg-logo/由来.svg", "由来", "redfill"],
+        ["svg-logo/人.svg", "", "none"],
+        ["svg-logo/他.svg", "", "none"],
+        ["svg-logo/動.svg", "", "none"],
+        ["svg-logo/名.svg", "", "none"],
+        ["svg-logo/句.svg", "", "none"],
+        ["svg-logo/派.svg", "", "none"],
+        ["svg-logo/自.svg", "", "none"],
+        ["svg-logo/連.svg", "", "none"],
+        ["svg-logo/造.svg", "", "none"],
+        ["svg-logo/造2.svg", "", "none"],
+        ["svg-logo/造3.svg", "", "none"],
+        ["svg-logo/百科.svg", "", "none"],
+    ]
+    for icon_info in icon_info_list:
+        src, text, cls = icon_info
+        for elm in soup.find_all("img", attrs={"src": src}):
+            path = media_dir
+            for part in src.split("/"):
+                path = os.path.join(path, part)
+            __make_rectangle(path, text, cls)
+            ratio = Icons.calculate_ratio(path)
+            img = BeautifulSoup("<img/>", "xml").img
+            img.attrs = {
+                "height": 1.0,
+                "width": ratio,
+                "sizeUnits": "em",
+                "collapsible": False,
+                "collapsed": False,
+                "background": False,
+                "appearance": cls_to_appearance[cls],
+                "title": elm.attrs["alt"] if elm.has_attr("alt") else "",
+                "path": f"{os.path.basename(media_dir)}/{src}",
+            }
+            elm.name = "span"
+            elm.clear()
+            elm.append(img)
+            elm.attrs["style"] = "vertical-align: text-bottom; margin-right: 0.25em;"
+
+
+def __replace_accent_symbols(soup, media_dir):
+    accent_info_list = [
+        ["svg-accent/平板.svg", Icons.make_heiban],
+        ["svg-accent/アクセント.svg", Icons.make_accent],
+    ]
+    for info in accent_info_list:
+        src, write_svg_function = info
+        for elm in soup.find_all("img", attrs={"src": src}):
+            path = media_dir
+            for part in src.split("/"):
+                path = os.path.join(path, part)
+            write_svg_function(path)
+            ratio = Icons.calculate_ratio(path)
+            img = BeautifulSoup("<img/>", "xml").img
+            img.attrs = {
+                "height": 1.0,
+                "width": ratio,
+                "sizeUnits": "em",
+                "collapsible": False,
+                "collapsed": False,
+                "background": False,
+                "appearance": "auto",
+                "path": f"{os.path.basename(media_dir)}/{src}",
+            }
+            elm.name = "span"
+            elm.clear()
+            elm.append(img)
+            elm.attrs["style"] = "vertical-align: text-bottom;"
+
+
+def __convert_gaiji(soup, media_dir):
+    for elm in soup.find_all("img"):
+        if not elm.has_attr("src"):
+            continue
+        src = elm.attrs["src"]
+        if src.startswith("graphics"):
+            continue
+        path = media_dir
+        for part in src.split("/"):
+            if part.strip() == "":
+                continue
+            path = os.path.join(path, part)
+        ratio = Icons.calculate_ratio(path)
+        img = BeautifulSoup("<img/>", "xml").img
+        img.attrs = {
+            "height": 1.0,
+            "width": ratio,
+            "sizeUnits": "em",
+            "collapsible": False,
+            "collapsed": False,
+            "background": False,
+            "appearance": "monochrome",
+            "title": elm.attrs["alt"] if elm.has_attr("alt") else "",
+            "path": f"{os.path.basename(media_dir)}/{src}",
+        }
+        elm.name = "span"
+        elm.clear()
+        elm.append(img)
+        elm.attrs["style"] = "vertical-align: text-bottom;"
+
+
+def __convert_graphics(soup, media_dir):
+    for elm in soup.find_all("img"):
+        if not elm.has_attr("src"):
+            continue
+        src = elm.attrs["src"]
+        if not src.startswith("graphics"):
+            continue
+        elm.attrs = {
+            "collapsible": True,
+            "collapsed": True,
+            "title": elm.attrs["alt"] if elm.has_attr("alt") else "",
+            "path": f"{os.path.basename(media_dir)}/{src}",
+            "src": src,
+        }
+
+
+def __convert_number_icons(soup, media_dir):
+    for elm in soup.find_all("大語義番号"):
+        if elm.find_parent("a") is None:
+            filename = f"{elm.text}-fill.svg"
+            appearance = "monochrome"
+            path = os.path.join(media_dir, filename)
+            __make_rectangle(path, elm.text, "fill")
+        else:
+            filename = f"{elm.text}-bluefill.svg"
+            appearance = "auto"
+            path = os.path.join(media_dir, filename)
+            __make_rectangle(path, elm.text, "bluefill")
+        ratio = Icons.calculate_ratio(path)
+        img = BeautifulSoup("<img/>", "xml").img
+        img.attrs = {
+            "height": 1.0,
+            "width": ratio,
+            "sizeUnits": "em",
+            "collapsible": False,
+            "collapsed": False,
+            "background": False,
+            "appearance": appearance,
+            "title": elm.text,
+            "path": f"{os.path.basename(media_dir)}/{filename}",
+        }
+        elm.name = "span"
+        elm.clear()
+        elm.append(img)
+        elm.attrs["style"] = "vertical-align: text-bottom; margin-right: 0.25em;"
+
+
+def __make_rectangle(path, text, cls):
+    if cls == "none":
+        pass
+    elif cls == "fill":
+        Icons.make_monochrome_fill_rectangle(path, text)
+    elif cls == "red":
+        Icons.make_rectangle(path, text, "red", "white", "red")
+    elif cls == "redfill":
+        Icons.make_rectangle(path, text, "red", "red", "white")
+    elif cls == "bluefill":
+        Icons.make_rectangle(path, text, "blue", "blue", "white")
+    else:
+        Icons.make_rectangle(path, text, "black", "transparent", "black")

bot/yomichan/terms/factory.py

@@ -5,6 +5,7 @@ from bot.yomichan.terms.jitenon import JitenonYojiTerminator
 from bot.yomichan.terms.jitenon import JitenonKotowazaTerminator
 from bot.yomichan.terms.smk8 import Smk8Terminator
 from bot.yomichan.terms.daijirin2 import Daijirin2Terminator
+from bot.yomichan.terms.sankoku8 import Sankoku8Terminator
 
 
 def new_terminator(target):
@@ -14,5 +15,6 @@ def new_terminator(target):
         Targets.JITENON_KOTOWAZA: JitenonKotowazaTerminator,
         Targets.SMK8:             Smk8Terminator,
         Targets.DAIJIRIN2:        Daijirin2Terminator,
+        Targets.SANKOKU8:         Sankoku8Terminator,
     }
     return terminator_map[target](target)

bot/yomichan/terms/sankoku8.py

@@ -0,0 +1,47 @@
+from bot.entries.sankoku8 import Sankoku8PhraseEntry as PhraseEntry
+
+from bot.yomichan.terms.terminator import Terminator
+from bot.yomichan.glossary.sankoku8 import make_glossary
+from bot.yomichan.grammar import sudachi_rules, tags_to_rules
+
+
+class Sankoku8Terminator(Terminator):
+    def __init__(self, target):
+        super().__init__(target)
+
+    def _definition_tags(self, entry):
+        return ""
+
+    def _inflection_rules(self, entry, expression):
+        if isinstance(entry, PhraseEntry):
+            return sudachi_rules(expression)
+        pos_tags = entry.get_part_of_speech_tags()
+        if len(pos_tags) == 0:
+            return sudachi_rules(expression)
+        else:
+            return tags_to_rules(expression, pos_tags, self._inflection_categories)
+
+    def _glossary(self, entry):
+        if entry.entry_id in self._glossary_cache:
+            return self._glossary_cache[entry.entry_id]
+        glossary = make_glossary(entry, self._image_dir)
+        self._glossary_cache[entry.entry_id] = glossary
+        return glossary
+
+    def _sequence(self, entry):
+        return entry.entry_id[0] * 100000 + entry.entry_id[1]
+
+    def _term_tags(self, entry):
+        return ""
+
+    def _link_glossary_parameters(self, entry):
+        return [
+            [entry.children, "子"],
+            [entry.phrases, "句"]
+        ]
+
+    def _subentry_lists(self, entry):
+        return [
+            entry.children,
+            entry.phrases,
+        ]

data/mdict/css/sankoku8.css

@@ -0,0 +1,611 @@
+
+@font-face {
+    font-family: jpgothic;
+    src: local("Noto Sans CJK JP"), local("IPAexGothic"), local("Source Han Sans JP");
+}
+
+@font-face {
+    font-family: jpmincho;
+    src: local("Noto Serif CJK JP"), local("IPAexMincho"), local("IPAmjMincho"), local("Source Han Serif JP"), local("HanaMinA"), local("HanaMinB");
+}
+
+@font-face {
+    font-family: jpkyokasho;
+    src: local("A-OTF Kyoukasho ICA Pro R"), local("DFKyoKaSho-W4");
+}
+
+body {
+    margin: 0em 1em;
+    line-height: 1.5em;
+    font-family: jpmincho, serif;
+    font-size: 1.2em;
+}
+
+span[data-name="entry-index"] > a {
+    display: none;
+}
+
+span[data-name="項目"] {
+    display: block;
+    /*max-width: 39em;*/
+}
+
+span[data-name="見出部"] {
+    display: block;
+}
+
+span[data-name="見出仮名"] {
+    font-family: jpgothic, sans-serif;
+    font-weight: bold;
+}
+
+span[data-name="見出仮名"].アンチック {
+    font-family: jpmincho, serif;
+}
+
+span[data-name="表記G"] {
+    margin-left: 0.25em;
+}
+
+span[data-name="専門G"] {
+    margin-right: 0.25em;
+}
+
+span[data-name="常用漢字"] {
+    font-family: jpmincho, serif;
+}
+
+span[data-name="教育漢字"] {
+    font-family: jpkyokasho, jpmincho, serif;
+    color: green;
+}
+
+span[data-name="解説部"],
+span[data-name="子解説部"],
+span[data-name="句解説部"] {
+    display: block;
+    margin-left: 1em;
+}
+
+span[data-name="大語義"] {
+    display: block;
+}
+
+span[data-name="大語義"] + span[data-name="大語義"] {
+    margin-top: 0.5em;
+}
+
+span[data-name="大語義番号"] {
+    margin-right: 0.25em;
+    padding: 0.1em;
+    font-family: jpgothic, sans-serif;
+    font-size: 0.8em;
+    font-weight: bold;
+    color: white;
+    background-color: gray;
+    border-radius: 0.2em;
+}
+
+a span[data-name="大語義番号"] {
+    background-color: blue;
+    text-decoration-color: blue;
+}
+
+span[data-name="語義番号"] {
+    margin-right: 0.25em;
+}
+
+span[data-name="参照語義番号"] {
+    margin-left: 0.1em;
+}
+
+span[data-name="参照語義番号"]>span[data-name="語義番号"] {
+    margin-right: 0.1em;
+}
+
+span[data-name="参照語義番号"]:first-child {
+    margin-left: 0em;
+}
+
+span[data-name="語義"] {
+    display: block;
+}
+
+span[data-name="副義"] {
+    display: block;
+    margin-left: 1.0em;
+}
+
+span[data-name="注記語義"] {
+    margin-left: 0.5em;
+}
+
+span[data-name="語釈"] {
+}
+
+span[data-name="用例G"] {
+    display: block;
+    /*margin-left: 1.25em;*/
+}
+
+span[data-name="百科"] span[data-name="用例G"] {
+    display: inline;
+}
+
+span[data-name="注記"] span[data-name="用例G"] {
+    display: inline;
+}
+
+span[data-name="用例"] {
+}
+
+span[data-name="見出相当部"] {
+    margin-left: 0.125em;
+    margin-right: 0.125em;
+}
+
+span[data-name="ルビG"] {
+    font-size: 0.7em;
+    font-weight: normal;
+    vertical-align: 0.5em;
+    -webkit-user-select: none;
+}
+
+span[data-name="名詞形G"],
+span[data-name="動詞形G"],
+span[data-name="自動詞形G"],
+span[data-name="他動詞形G"],
+span[data-name="可能形G"],
+span[data-name="人G"],
+span[data-name="名詞人形G"] {
+    display: block;
+}
+
+span[data-name="語義"] span[data-name="名詞形G"],
+span[data-name="語義"] span[data-name="動詞形G"],
+span[data-name="語義"] span[data-name="自動詞形G"],
+span[data-name="語義"] span[data-name="他動詞形G"],
+span[data-name="語義"] span[data-name="可能形G"],
+span[data-name="語義"] span[data-name="人G"] {
+    display: inline;
+}
+
+span[data-name="副義"] span[data-name="名詞形G"],
+span[data-name="副義"] span[data-name="動詞形G"],
+span[data-name="副義"] span[data-name="自動詞形G"],
+span[data-name="副義"] span[data-name="他動詞形G"],
+span[data-name="副義"] span[data-name="可能形G"],
+span[data-name="副義"] span[data-name="人G"] {
+    display: inline;
+}
+
+span[data-name="注記"] span[data-name="名詞形G"],
+span[data-name="注記"] span[data-name="動詞形G"],
+span[data-name="注記"] span[data-name="自動詞形G"],
+span[data-name="注記"] span[data-name="他動詞形G"],
+span[data-name="注記"] span[data-name="可能形G"],
+span[data-name="注記"] span[data-name="人G"] {
+    display: inline;
+}
+
+span[data-name="共通"] span[data-name="名詞形G"],
+span[data-name="共通"] span[data-name="動詞形G"],
+span[data-name="共通"] span[data-name="自動詞形G"],
+span[data-name="共通"] span[data-name="他動詞形G"],
+span[data-name="共通"] span[data-name="可能形G"],
+span[data-name="共通"] span[data-name="人G"] {
+    display: inline;
+}
+
+span[data-name="名詞形G"] span[data-name="用例G"],
+span[data-name="動詞形G"] span[data-name="用例G"],
+span[data-name="自動詞形G"] span[data-name="用例G"],
+span[data-name="他動詞形G"] span[data-name="用例G"],
+span[data-name="可能形G"] span[data-name="用例G"],
+span[data-name="人G"] span[data-name="用例G"] {
+    display: inline;
+}
+
+span[data-name="参照G"] {
+    display: inline;
+}
+
+span[data-name="参照矢印"] {
+    margin-right: 0.25em;
+}
+
+span[data-name="参照"] {
+}
+
+span[data-name="子項目"] {
+    display: block;
+    margin-top: 0.5em;
+}
+
+span[data-name="子見出部"] {
+    display: block;
+    /* text-indent: -1em; */
+}
+
+span[data-name="子見出仮名"] {
+    font-family: jpgothic, sans-serif;
+    font-weight: bold;
+}
+
+span[data-name="親見出省略"] {
+    font-family: jpgothic, sans-serif;
+}
+
+span[data-name="句項目"] {
+    display: block;
+    margin-top: 0.5em;
+}
+
+span[data-name="句見出部"] {
+    display: block;
+    /* text-indent: -1em; */
+}
+
+span[data-name="句表記"] {
+    font-family: jpgothic, sans-serif;
+    font-weight: bold;
+}
+
+span[data-name="対義語G"] {
+}
+
+span[data-name="派生語G"] {
+    display: block;
+}
+
+span[data-name="謙譲形G"] {
+    display: block;
+}
+
+span[data-name="共通"] {
+    display: block;
+}
+
+span[data-name="共通ロゴ"] {
+    color: red;
+    margin-right: 0.25em;
+}
+
+span[data-name="rank1"] a,
+span[data-name="rank2"] a,
+span[data-name="rank3"] a,
+span[data-name="表外字マーク"] a,
+span[data-name="表外音訓マーク"] a,
+span[data-name="省略形"] a,
+span[data-name="熟字訓"] a,
+span[data-name="原籍"] a,
+span[data-name="品詞"] a,
+span[data-name="専門"] a,
+span[data-name="使用域"] a,
+span[data-name="rect"] a {
+    color: black;
+    border-top-style: none;
+}
+
+span[data-name="共通ロゴ"] a {
+    color: red;
+    border-top-style: none;
+}
+
+span[data-name="rect"].red a {
+    color: red;
+}
+
+a {
+    text-decoration: none;
+    padding-top: 0.04em;
+    /* border-top: solid 1px blue; */
+}
+
+a.appendix {
+    color: black;
+    text-decoration: none;
+    border-top-style: none;
+}
+
+a.black {
+    color: black;
+}
+
+span[data-name="カット"] {
+    display: block;
+    width: 75%;
+    margin-top: 1em;
+    margin-left: auto;
+    margin-right: auto;
+}
+
+span[data-name="カット"] img {
+    max-height: 200px;
+    max-width: 600px;
+}
+
+span[data-name="イタリック"] {
+    font-style: italic;
+}
+
+span[data-name="ボールド"] {
+    font-weight: bold;
+}
+
+span[data-name="色版"] {
+    color: red;
+}
+
+/* 独自定義 */
+
+span[data-name="rect"] {
+    margin-left: 0.25em;
+    margin-right: 0.25em;
+    padding: 0.1em;
+    font-size: 0.8em;
+    border-width: 0.04em;
+    border-style: solid;
+    border-color: black;
+    word-break: keep-all;
+    border-radius: 0.1em;
+}
+
+span[data-name="rect"].fill {
+    color: white;
+    border-style: none;
+    background-color: gray;
+}
+
+span[data-name="rect"].red {
+    color: red;
+    border-color: red;
+}
+
+span[data-name="red"] {
+    color: red;
+}
+
+span[data-name="glyph"] {
+    font-family: jpmincho, serif;
+}
+
+span[data-name="gaiji"] {
+    width: 1em;
+}
+
+span[data-name="frac"] {
+    width: 2em;
+}
+
+img.logo {
+    display: gaiji;
+    margin-right: 0.25em;
+    height: 1em;
+    text-combine-horizontal: all;
+}
+
+.logo-red {
+    height: 1em;
+    color: red;
+}
+
+span[data-name="平板"] .logo-red {
+    margin-left: 0.1em;
+}
+
+img.区切り線 {
+    display: gaiji;
+    height: 1em;
+    padding: 0 0.3em 0 0.05em;
+    color: gray;
+    text-combine-horizontal: all;
+}
+
+/* ＊, ＊＊, and ☆☆ symbols */
+span[data-src^="svg-logo"].rank {
+    font-size: 0.65em;
+    vertical-align: super;
+}
+
+img.gaiji {
+    display: gaiji;
+    height: 1em;
+    text-combine-horizontal: all;
+}
+
+img.svg {
+    zoom: 250%;
+}
+
+span[data-name="表外字マーク"] {
+    font-size: 0.5em;
+    vertical-align: 1em;
+    -webkit-user-select: none;
+}
+
+span[data-name="表外音訓マーク"] {
+    font-size: 0.5em;
+    vertical-align: 1em;
+    -webkit-user-select: none;
+}
+
+span[data-name="表外字ロゴ"],
+span[data-name="表外音訓ロゴ"] {
+    margin: 0em 0.5em;
+    font-size: 0.5em;
+}
+
+span[data-name="アクセント"] {
+}
+
+span[data-name="アクセント表記"] {
+    font-family: jpgothic, sans-serif;
+    font-weight: bold;
+    font-size: 0.85em;
+}
+
+span[data-name="横"] {
+    text-combine-horizontal: all 1;
+}
+
+span[data-name="縦中横"] {
+    text-combine-horizontal: all;
+}
+
+span[data-name="分子"],
+span[data-name="分母"] {
+    text-combine-horizontal: all;
+}
+
+span[data-name="英"],
+span[data-name="回転"] {
+    writing-mode: horizontal-tb;
+}
+
+span[data-name="i"] {
+    font-family: "Times New Roman";
+    font-style: italic;
+}
+
+span[data-name="横"] span[data-name="sub"] {
+    font-size: 0.7em;
+    vertical-align: 0.35em;
+}
+
+span[data-name="kanbun"] {
+    font-size: 0.5em;
+    vertical-align: -1em;
+}
+
+span[data-name="歴史仮名"] {
+    font-size: 0.7em;
+    vertical-align: 0.5em;
+    -webkit-user-select: none;
+}
+
+span[data-name="品詞G"] {
+    /* margin-left: 0.25em; */
+}
+
+span[data-name="ロゴ"] {
+    margin-right: 0.25em;
+}
+
+span[data-name="割書"] {
+    /*display: warichu;*/
+    /*font-size: 0.5em;*/
+}
+
+span[data-name="尊敬形G"],
+span[data-name="謙譲形G"],
+span[data-name="丁寧形G"] {
+    display: block;
+}
+
+span[data-name="百科"],
+span[data-name="由来"],
+span[data-name="区別"],
+span[data-name="アクセント注記"] {
+    display: block;
+}
+
+span[data-name="表記情報"] {
+    display: block;
+}
+
+span[data-name="別見出"] {
+    font-family: jpmincho, serif;
+    font-weight: bold;
+}
+
+span[data-name="読み"] {
+    font-size: 0.7em;
+}
+
+span[data-name="歴史仮名"]:before,
+span[data-name="ルビ"]:before {
+    content: "(";
+}
+
+span[data-name="歴史仮名"]:after,
+span[data-name="ルビ"]:after {
+    content: ")";
+}
+
+div[data-child-links] {
+    padding-left: 1em;
+}
+
+div[data-child-links] ul {
+    margin: 0;
+    padding-left: 2em;
+}
+
+div[data-child-links] span {
+    padding: 0.1em;
+    font-family: jpgothic, sans-serif;
+    font-size: 0.8em;
+    color: white;
+    border-width: 0.05em;
+    border-style: none;
+    border-color: black;
+    border-radius: 0.2em;
+    word-break: keep-all;
+}
+
+div[data-child-links="子項目"] span {
+    background-color: rgb(153, 42, 103);
+}
+
+div[data-child-links="句項目"] span {
+    background-color: rgb(176, 127, 57);
+}
+
+
+/* Replacements for vertical SVG icons */
+span[data-src="svg-logo/区別.svg"],
+span[data-src="svg-logo/由来.svg"] {
+    font-family: jpgothic, sans-serif;
+    margin-left: 0.25em;
+    margin-right: 0.25em;
+    padding: 0em 0.1em 0.1em 0.1em;
+    font-size: 0.8em;
+    word-break: keep-all;
+    border-radius: 0.2em;
+    border-style: none;
+    color: white;
+    background-color: red;
+}
+
+span[data-src="svg-logo/アク.svg"],
+span[data-src="svg-logo/丁寧.svg"],
+span[data-src="svg-logo/可能.svg"],
+span[data-src="svg-logo/尊敬.svg"],
+span[data-src="svg-logo/表記.svg"],
+span[data-src="svg-logo/謙譲.svg"],
+span[data-src="svg-logo/接尾.svg"],
+span[data-src="svg-logo/接頭.svg"] {
+    margin-left: 0.25em;
+    margin-right: 0.25em;
+    padding: 0em 0.1em 0.1em 0.1em;
+    font-size: 0.8em;
+    word-break: keep-all;
+    border-width: 0.1em;
+    border-style: solid;
+    border-radius: 0.2em;
+}
+
+span[data-src="svg-logo/アク.svg"],
+span[data-src="svg-logo/丁寧.svg"],
+span[data-src="svg-logo/可能.svg"],
+span[data-src="svg-logo/尊敬.svg"],
+span[data-src="svg-logo/表記.svg"],
+span[data-src="svg-logo/謙譲.svg"] {
+    font-family: jpgothic, sans-serif;
+}
+
+span[data-src="svg-logo/接尾.svg"],
+span[data-src="svg-logo/接頭.svg"] {
+    font-family: jpmincho, serif;
+}

data/mdict/description/sankoku8.mdx.description.html

@@ -0,0 +1,7 @@
+三省堂国語辞典　第八版
+<br><br>
+https://www.monokakido.jp/ja/dictionaries/sankoku8/index.html
+<br><br>
+{{revision}}
+<br><br>
+{{attribution}}

data/mdict/name_conversion/sankoku8.json

@@ -0,0 +1,22 @@
+{
+    "a": {},
+    "br": {},
+    "img": {},
+    "div": {},
+    "span": {},
+    "small": {},
+    "sup": {},
+    "sub": {},
+    "表外字": {
+        "name": "ruby"
+    },
+    "表外字マーク": {
+        "name": "rt"
+    },
+    "表外音訓": {
+        "name": "ruby"
+    },
+    "表外音訓マーク": {
+        "name": "rt"
+    }
+}

data/mdict/title/sankoku8.mdx.title.html

@@ -0,0 +1 @@
+三省堂国語辞典　第八版

data/yomichan/dictionary-term-bank-v3-schema.json

@@ -0,0 +1,474 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "definitions": {
+        "structuredContent": {
+            "oneOf": [
+                {
+                    "type": "string",
+                    "description": "Represents a text node."
+                },
+                {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/structuredContent",
+                        "description": "An array of child content."
+                    }
+                },
+                {
+                    "type": "object",
+                    "oneOf": [
+                        {
+                            "type": "object",
+                            "description": "Empty tags.",
+                            "required": [
+                                "tag"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "const": "br"
+                                },
+                                "data": {
+                                    "$ref": "#/definitions/structuredContentData"
+                                }
+                            }
+                        },
+                        {
+                            "type": "object",
+                            "description": "Generic container tags.",
+                            "required": [
+                                "tag"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "enum": ["ruby", "rt", "rp", "table", "thead", "tbody", "tfoot", "tr"]
+                                },
+                                "content": {
+                                    "$ref": "#/definitions/structuredContent"
+                                },
+                                "data": {
+                                    "$ref": "#/definitions/structuredContentData"
+                                },
+                                "lang": {
+                                    "type": "string",
+                                    "description": "Defines the language of an element in the format defined by RFC 5646."
+                                }
+                            }
+                        },
+                        {
+                            "type": "object",
+                            "description": "Table tags.",
+                            "required": [
+                                "tag"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "enum": ["td", "th"]
+                                },
+                                "content": {
+                                    "$ref": "#/definitions/structuredContent"
+                                },
+                                "data": {
+                                    "$ref": "#/definitions/structuredContentData"
+                                },
+                                "colSpan": {
+                                    "type": "integer",
+                                    "minimum": 1
+                                },
+                                "rowSpan": {
+                                    "type": "integer",
+                                    "minimum": 1
+                                },
+                                "style": {
+                                    "$ref": "#/definitions/structuredContentStyle"
+                                },
+                                "lang": {
+                                    "type": "string",
+                                    "description": "Defines the language of an element in the format defined by RFC 5646."
+                                }
+                            }
+                        },
+                        {
+                            "type": "object",
+                            "description": "Container tags supporting configurable styles.",
+                            "required": [
+                                "tag"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "enum": ["span", "div", "ol", "ul", "li"]
+                                },
+                                "content": {
+                                    "$ref": "#/definitions/structuredContent"
+                                },
+                                "data": {
+                                    "$ref": "#/definitions/structuredContentData"
+                                },
+                                "style": {
+                                    "$ref": "#/definitions/structuredContentStyle"
+                                },
+                                "lang": {
+                                    "type": "string",
+                                    "description": "Defines the language of an element in the format defined by RFC 5646."
+                                }
+                            }
+                        },
+                        {
+                            "type": "object",
+                            "description": "Image tag.",
+                            "required": [
+                                "tag",
+                                "path"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "const": "img"
+                                },
+                                "data": {
+                                    "$ref": "#/definitions/structuredContentData"
+                                },
+                                "path": {
+                                    "type": "string",
+                                    "description": "Path to the image file in the archive."
+                                },
+                                "width": {
+                                    "type": "number",
+                                    "description": "Preferred width of the image.",
+                                    "minimum": 0
+                                },
+                                "height": {
+                                    "type": "number",
+                                    "description": "Preferred width of the image.",
+                                    "minimum": 0
+                                },
+                                "title": {
+                                    "type": "string",
+                                    "description": "Hover text for the image."
+                                },
+                                "pixelated": {
+                                    "type": "boolean",
+                                    "description": "Whether or not the image should appear pixelated at sizes larger than the image's native resolution.",
+                                    "default": false
+                                },
+                                "imageRendering": {
+                                    "type": "string",
+                                    "description": "Controls how the image is rendered. The value of this field supersedes the pixelated field.",
+                                    "enum": ["auto", "pixelated", "crisp-edges"],
+                                    "default": "auto"
+                                },
+                                "appearance": {
+                                    "type": "string",
+                                    "description": "Controls the appearance of the image. The \"monochrome\" value will mask the opaque parts of the image using the current text color.",
+                                    "enum": ["auto", "monochrome"],
+                                    "default": "auto"
+                                },
+                                "background": {
+                                    "type": "boolean",
+                                    "description": "Whether or not a background color is displayed behind the image.",
+                                    "default": true
+                                },
+                                "collapsed": {
+                                    "type": "boolean",
+                                    "description": "Whether or not the image is collapsed by default.",
+                                    "default": false
+                                },
+                                "collapsible": {
+                                    "type": "boolean",
+                                    "description": "Whether or not the image can be collapsed.",
+                                    "default": false
+                                },
+                                "verticalAlign": {
+                                    "type": "string",
+                                    "description": "The vertical alignment of the image.",
+                                    "enum": ["baseline", "sub", "super", "text-top", "text-bottom", "middle", "top", "bottom"]
+                                },
+                                "sizeUnits": {
+                                    "type": "string",
+                                    "description": "The units for the width and height.",
+                                    "enum": ["px", "em"]
+                                }
+                            }
+                        },
+                        {
+                            "type": "object",
+                            "description": "Link tag.",
+                            "required": [
+                                "tag",
+                                "href"
+                            ],
+                            "additionalProperties": false,
+                            "properties": {
+                                "tag": {
+                                    "type": "string",
+                                    "const": "a"
+                                },
+                                "content": {
+                                    "$ref": "#/definitions/structuredContent"
+                                },
+                                "href": {
+                                    "type": "string",
+                                    "description": "The URL for the link. URLs starting with a ? are treated as internal links to other dictionary content.",
+                                    "pattern": "^(?:https?:|\\?)[\\w\\W]*"
+                                },
+                                "lang": {
+                                    "type": "string",
+                                    "description": "Defines the language of an element in the format defined by RFC 5646."
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        },
+        "structuredContentData": {
+            "type": "object",
+            "description": "Generic data attributes that should be added to the element.",
+            "additionalProperties": {
+                "type": "string"
+            }
+        },
+        "structuredContentStyle": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+                "fontStyle": {
+                    "type": "string",
+                    "enum": ["normal", "italic"],
+                    "default": "normal"
+                },
+                "fontWeight": {
+                    "type": "string",
+                    "enum": ["normal", "bold"],
+                    "default": "normal"
+                },
+                "fontSize": {
+                    "type": "string",
+                    "default": "medium"
+                },
+                "textDecorationLine": {
+                    "oneOf": [
+                        {
+                            "type": "string",
+                            "enum": ["none", "underline", "overline", "line-through"],
+                            "default": "none"
+                        },
+                        {
+                            "type": "array",
+                            "items": {
+                                "type": "string",
+                                "enum": ["underline", "overline", "line-through"],
+                                "default": "none"
+                            }
+                        }
+                    ]
+                },
+                "verticalAlign": {
+                    "type": "string",
+                    "enum": ["baseline", "sub", "super", "text-top", "text-bottom", "middle", "top", "bottom"],
+                    "default": "baseline"
+                },
+                "textAlign": {
+                    "type": "string",
+                    "enum": ["start", "end", "left", "right", "center", "justify", "justify-all", "match-parent"],
+                    "default": "start"
+                },
+                "marginTop": {
+                    "type": "number",
+                    "default": 0
+                },
+                "marginLeft": {
+                    "type": "number",
+                    "default": 0
+                },
+                "marginRight": {
+                    "type": "number",
+                    "default": 0
+                },
+                "marginBottom": {
+                    "type": "number",
+                    "default": 0
+                },
+                "listStyleType": {
+                    "type": "string",
+                    "default": "disc"
+                }
+            }
+        }
+    },
+    "type": "array",
+    "description": "Data file containing term information.",
+    "items": {
+        "type": "array",
+        "description": "Information about a single term.",
+        "minItems": 8,
+        "additionalItems": false,
+        "items": [
+            {
+                "type": "string",
+                "description": "The text for the term."
+            },
+            {
+                "type": "string",
+                "description": "Reading of the term, or an empty string if the reading is the same as the term."
+            },
+            {
+                "type": ["string", "null"],
+                "description": "String of space-separated tags for the definition. An empty string is treated as no tags."
+            },
+            {
+                "type": "string",
+                "description": "String of space-separated rule identifiers for the definition which is used to validate delinflection. Valid rule identifiers are: v1: ichidan verb; v5: godan verb; vs: suru verb; vk: kuru verb; adj-i: i-adjective. An empty string corresponds to words which aren't inflected, such as nouns."
+            },
+            {
+                "type": "number",
+                "description": "Score used to determine popularity. Negative values are more rare and positive values are more frequent. This score is also used to sort search results."
+            },
+            {
+                "type": "array",
+                "description": "Array of definitions for the term.",
+                "items": {
+                    "oneOf": [
+                        {
+                            "type": "string",
+                            "description": "Single definition for the term."
+                        },
+                        {
+                            "type": "object",
+                            "description": "Single detailed definition for the term.",
+                            "required": [
+                                "type"
+                            ],
+                            "properties": {
+                                "type": {
+                                    "type": "string",
+                                    "description": "The type of the data for this definition.",
+                                    "enum": ["text", "image", "structured-content"]
+                                }
+                            },
+                            "oneOf": [
+                                {
+                                    "required": [
+                                        "type",
+                                        "text"
+                                    ],
+                                    "additionalProperties": false,
+                                    "properties": {
+                                        "type": {
+                                            "type": "string",
+                                            "const": "text"
+                                        },
+                                        "text": {
+                                            "type": "string",
+                                            "description": "Single definition for the term."
+                                        }
+                                    }
+                                },
+                                {
+                                    "required": [
+                                        "type",
+                                        "content"
+                                    ],
+                                    "additionalProperties": false,
+                                    "properties": {
+                                        "type": {
+                                            "type": "string",
+                                            "const": "structured-content"
+                                        },
+                                        "content": {
+                                            "$ref": "#/definitions/structuredContent",
+                                            "description": "Single definition for the term using a structured content object."
+                                        }
+                                    }
+                                },
+                                {
+                                    "required": [
+                                        "type",
+                                        "path"
+                                    ],
+                                    "additionalProperties": false,
+                                    "properties": {
+                                        "type": {
+                                            "type": "string",
+                                            "const": "image"
+                                        },
+                                        "path": {
+                                            "type": "string",
+                                            "description": "Path to the image file in the archive."
+                                        },
+                                        "width": {
+                                            "type": "integer",
+                                            "description": "Preferred width of the image.",
+                                            "minimum": 1
+                                        },
+                                        "height": {
+                                            "type": "integer",
+                                            "description": "Preferred width of the image.",
+                                            "minimum": 1
+                                        },
+                                        "title": {
+                                            "type": "string",
+                                            "description": "Hover text for the image."
+                                        },
+                                        "description": {
+                                            "type": "string",
+                                            "description": "Description of the image."
+                                        },
+                                        "pixelated": {
+                                            "type": "boolean",
+                                            "description": "Whether or not the image should appear pixelated at sizes larger than the image's native resolution.",
+                                            "default": false
+                                        },
+                                        "imageRendering": {
+                                            "type": "string",
+                                            "description": "Controls how the image is rendered. The value of this field supersedes the pixelated field.",
+                                            "enum": ["auto", "pixelated", "crisp-edges"],
+                                            "default": "auto"
+                                        },
+                                        "appearance": {
+                                            "type": "string",
+                                            "description": "Controls the appearance of the image. The \"monochrome\" value will mask the opaque parts of the image using the current text color.",
+                                            "enum": ["auto", "monochrome"],
+                                            "default": "auto"
+                                        },
+                                        "background": {
+                                            "type": "boolean",
+                                            "description": "Whether or not a background color is displayed behind the image.",
+                                            "default": true
+                                        },
+                                        "collapsed": {
+                                            "type": "boolean",
+                                            "description": "Whether or not the image is collapsed by default.",
+                                            "default": false
+                                        },
+                                        "collapsible": {
+                                            "type": "boolean",
+                                            "description": "Whether or not the image can be collapsed.",
+                                            "default": true
+                                        }
+                                    }
+                                }
+                            ]
+                        }
+                    ]
+                }
+            },
+            {
+                "type": "integer",
+                "description": "Sequence number for the term. Terms with the same sequence number can be shown together when the \"resultOutputMode\" option is set to \"merge\"."
+            },
+            {
+                "type": "string",
+                "description": "String of space-separated tags for the term. An empty string is treated as no tags."
+            }
+        ]
+    }
+}

data/yomichan/index.json

@@ -56,5 +56,16 @@
             ["子", "name", 0, "子項目", 0],
             ["句", "expression", 0, "句項目", 0]
         ]
+    },
+    "sankoku8": {
+        "index": {
+            "title": "三省堂国語辞典　第八版",
+            "sequenced": true,
+            "format": 3
+        },
+        "tags": [
+            ["子", "name", 0, "子項目", 0],
+            ["句", "expression", 0, "句項目", 0]
+        ]
     }
 }

data/yomichan/inflection_categories.json

@@ -25,5 +25,13 @@
         "keiyoushi": ["形"],
         "kahen": ["カ変"],
         "sudachi": ["助動", "接尾", "枕詞", "連体", "連語"]
+    },
+    "sankoku8": {
+        "sahen": ["サ", "サ型"],
+        "godan": ["上二", "下二", "下二型", "四","四型", "五", "五型", "特殊型", "マス","マス型"],
+        "ichidan": ["上一", "下一", "下一型"],
+        "keiyoushi": ["形", "形型"],
+        "kahen": ["カ"],
+        "sudachi": []
     }
 }

data/yomichan/name_conversion/sankoku8.json

@@ -0,0 +1,495 @@
+{
+    "a": {},
+    "br": {},
+    "img": {},
+    "div": {},
+    "span": {},
+    "ruby": {},
+    "rt": {},
+    "small": {
+        "name": "span",
+        "style": "vertical-align: super; font-size: 0.65em; font-weight: normal; margin-right: 0.25em;",
+        "procedures": [
+            {
+                "procedure_name": "wrap",
+                "parameters": {
+                    "l_wrap": "(",
+                    "r_wrap": ")"
+                }
+            }
+        ]
+    },
+    "sup": {
+        "name": "span",
+        "style": "vertical-align: super; font-size: 0.65em;"
+    },
+    "sub": {
+        "name": "span",
+        "style": "vertical-align: sub; font-size: 0.65em;"
+    },
+    "表外字": {
+        "name": "ruby"
+    },
+    "表外字マーク": {
+        "name": "rt"
+    },
+    "表外音訓": {
+        "name": "ruby"
+    },
+    "表外音訓マーク": {
+        "name": "rt"
+    },
+    "語構成": {
+        "name": "span",
+        "style": "margin-right: 0.5em;"
+    },
+    "分書": {
+        "name": "span",
+        "style": "margin-right: 0.5em;"
+    },
+    "見出仮名": {
+        "name": "span",
+        "style": "font-weight: bold;"
+    },
+    "解説部": {
+        "name": "div"
+    },
+    "子解説部": {
+        "name": "div"
+    },
+    "句解説部": {
+        "name": "div"
+    },
+    "大語義": {
+        "name": "div"
+    },
+    "語義": {
+        "name": "div"
+    },
+    "副義": {
+        "name": "div",
+        "style": "margin-left: 1.0em;"
+    },
+    "注記語義": {
+        "name": "span",
+        "style": "margin-left: 0.5em;"
+    },
+    "用例G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "百科",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "名詞形G",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "動詞形G",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "自動詞形G",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "他動詞形G",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "可能形G",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "人G",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "見出相当部": {
+        "name": "span",
+        "style": "margin-left: 0.125em; margin-right: 0.125em;"
+    },
+    "ルビG": {
+        "name": "span",
+        "style": "vertical-align: super; font-size: 0.65em; font-weight: normal;"
+    },
+    "名詞人形G": {
+        "name": "div"
+    },
+    "名詞形G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "動詞形G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "自動詞形G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "他動詞形G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "可能形G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "人G": {
+        "name": "div",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "語義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "副義",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "注記",
+                    "key": "name",
+                    "value": "span"
+                }
+            },
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "共通",
+                    "key": "name",
+                    "value": "span"
+                }
+            }
+        ]
+    },
+    "参照矢印": {
+        "name": "span",
+        "style": "margin-right: 0.25em;"
+    },
+    "子見出仮名": {
+        "name": "span",
+        "style": "font-weight: bold;"
+    },
+    "句表記": {
+        "name": "span",
+        "style": "font-weight: bold;"
+    },
+    "派生語G": {
+        "name": "div"
+    },
+    "謙譲形G": {
+        "name": "div"
+    },
+    "共通": {
+        "name": "div"
+    },
+    "イタリック": {
+        "name": "span",
+        "style": "font-style: italic;"
+    },
+    "ボールド": {
+        "name": "span",
+        "style": "font-weight: bold;"
+    },
+    "アクセント表記": {
+        "name": "span",
+        "style": "font-weight: bold; font-size: 0.85em;"
+    },
+    "i": {
+        "name": "span",
+        "style": "font-style: italic;"
+    },
+    "sub": {
+        "name": "span",
+        "style": "font-size: 0.7em; vertical-align: sub;",
+        "procedures": [
+            {
+                "procedure_name": "has_parent",
+                "parameters": {
+                    "parent_name": "横",
+                    "key": "style",
+                    "value": "font-size: 0.7em; vertical-align: super;"
+                }
+            }
+        ]
+    },
+    "kanbun": {
+        "name": "span",
+        "style": "font-size: 0.5em; vertical-align: sub;"
+    },
+    "ロゴ": {
+        "name": "span",
+        "style": "margin-right: 0.25em"
+    },
+    "尊敬形G": {
+        "name": "div"
+    },
+    "謙譲形G": {
+        "name": "div"
+    },
+    "丁寧形G": {
+        "name": "div"
+    },
+    "百科": {
+        "name": "div"
+    },
+    "由来": {
+        "name": "div"
+    },
+    "区別": {
+        "name": "div"
+    },
+    "アクセント注記": {
+        "name": "div"
+    },
+    "表記情報": {
+        "name": "div"
+    },
+    "別見出": {
+        "name": "span",
+        "style": "font-weight: bold;"
+    },
+    "読み": {
+        "name": "span",
+        "style": "font-size: 0.7em;"
+    },
+    "歴史仮名": {
+        "name": "span",
+        "style": "vertical-align: super; font-size: 0.65em; font-weight: normal;",
+        "procedures": [
+            {
+                "procedure_name": "wrap",
+                "parameters": {
+                    "l_wrap": "(",
+                    "r_wrap": ")"
+                }
+            }
+        ]
+    },
+    "ルビ": {
+        "name": "span",
+        "procedures": [
+            {
+                "procedure_name": "wrap",
+                "parameters": {
+                    "l_wrap": "(",
+                    "r_wrap": ")"
+                }
+            }
+        ]
+    }
+}

jitenbot.py

@@ -68,14 +68,19 @@ def parse_args(target_names):
         help="path to icon file to be used with MDict",
         type=filename,
     )
+    parser.add_argument(
+        "--no-mdict-export",
+        help="skip export of dictionary data to MDict format",
+        action='store_true',
+    )
     parser.add_argument(
         "--no-yomichan-export",
         help="skip export of dictionary data to Yomichan format",
         action='store_true',
     )
     parser.add_argument(
-        "--no-mdict-export",
-        help="skip export of dictionary data to MDict format",
+        "--validate-yomichan-terms",
+        help="validate JSON structure of exported Yomichan dictionary terms",
         action='store_true',
     )
     args = parser.parse_args()
@@ -108,9 +113,11 @@ def main():
     crawler.collect_pages(args.page_dir)
     crawler.read_pages()
     if not args.no_yomichan_export:
-        crawler.make_yomichan_dictionary(args.media_dir)
+        crawler.make_yomichan_dictionary(
+            args.media_dir, args.validate_yomichan_terms)
     if not args.no_mdict_export:
-        crawler.make_mdict_dictionary(args.media_dir, args.mdict_icon)
+        crawler.make_mdict_dictionary(
+            args.media_dir, args.mdict_icon)
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1,15 +1,20 @@
+attrs==23.1.0
 beautifulsoup4==4.12.2
 bs4==0.0.1
 certifi==2022.12.7
 charset-normalizer==3.1.0
 css-parser==1.0.8
+fastjsonschema==2.17.1
 html5lib==1.1
 idna==3.4
+jsonschema-specifications==2023.6.1
 lxml==4.9.2
 mdict-utils==1.3.12
 Pillow==9.5.0
 platformdirs==3.5.0
+referencing==0.29.1
 requests==2.29.0
+rpds-py==0.8.10
 six==1.16.0
 soupsieve==2.4.1
 SudachiDict-full==20230110

run_all.sh

@@ -1,3 +1,7 @@
+#!/bin/sh
+
+python -m unittest discover -s tests
+
 python jitenbot.py jitenon-kokugo
 python jitenbot.py jitenon-yoji
 python jitenbot.py jitenon-kotowaza
@@ -11,3 +15,8 @@ python jitenbot.py daijirin2 \
        --media-dir  monokakido/DAIJIRIN2/media \
        --page-dir   monokakido/DAIJIRIN2/pages \
        --mdict-icon monokakido/DAIJIRIN2/DAIJIRIN2-76@3x.png
+
+python jitenbot.py sankoku8 \
+       --media-dir  monokakido/SANKOKU8/media \
+       --page-dir   monokakido/SANKOKU8/pages \
+       --mdict-icon monokakido/SANKOKU8/SANKOKU8-76@3x.png

tests/test_sankoku_phrases.py

@@ -0,0 +1,47 @@
+import unittest
+from bot.entries.sankoku8 import parse_hyouki_pattern
+from bs4 import BeautifulSoup
+
+
+class TestSankokuPhrases(unittest.TestCase):
+    def test_sankoku_phrases1(self):
+        pattern = '耳にたこ（ができる）'
+        exps = parse_hyouki_pattern(pattern)
+        self.assertEqual(len(exps), 2)
+        self.assertIn("耳にたこ", exps)
+        self.assertIn("耳にたこができる", exps)
+
+    def test_sankoku_phrases2(self):
+        pattern = '一斑を〈見て／もって〉全豹を〈卜す／推す〉'
+        exps = parse_hyouki_pattern(pattern)
+        self.assertEqual(len(exps), 4)
+        self.assertIn("一斑を見て全豹を卜す", exps)
+        self.assertIn("一斑を見て全豹を推す", exps)
+        self.assertIn("一斑をもって全豹を卜す", exps)
+        self.assertIn("一斑をもって全豹を推す", exps)
+
+    def test_sankoku_phrases3(self):
+        pattern = '｛かじ・舵｝を切る'
+        exps = parse_hyouki_pattern(pattern)
+        self.assertEqual(len(exps), 2)
+        self.assertIn("かじを切る", exps)
+        self.assertIn("舵を切る", exps)
+
+    def test_sankoku_phrases4(self):
+        pattern = '重箱の隅を（⦅ようじ＼楊枝⦆で）〈つつく／ほじくる〉'
+        exps = parse_hyouki_pattern(pattern)
+        self.assertEqual(len(exps), 6)
+        self.assertIn("重箱の隅をつつく", exps)
+        self.assertIn("重箱の隅をようじでつつく", exps)
+        self.assertIn("重箱の隅を楊枝でつつく", exps)
+        self.assertIn("重箱の隅をほじくる", exps)
+        self.assertIn("重箱の隅をようじでほじくる", exps)
+        self.assertIn("重箱の隅を楊枝でほじくる", exps)
+
+    def test_sankoku_phrases5(self):
+        pattern = '群盲象を〈｛な・撫｝でる／評する〉'
+        exps = parse_hyouki_pattern(pattern)
+        self.assertEqual(len(exps), 3)
+        self.assertIn("群盲象をなでる", exps)
+        self.assertIn("群盲象を撫でる", exps)
+        self.assertIn("群盲象を評する", exps)