stitching it all together now.

add-readings.py

@@ -2,8 +2,10 @@ import json
 import MeCab
 import re
 
-# Initialize the Tagger
+import requests
-#tagger = MeCab.Tagger()
+
+request_url = "http://127.0.0.1:19633"
+request_timeout = 10
 
 # Generate Hiragana and Katakana characters
 hiragana = tuple(chr(i) for i in range(12353, 12436)) # \u3041 - \u3094
@@ -21,12 +23,12 @@ def katakana_to_hiragana(text: str) -> str:
         for ch in text
     )
 
-def get_node_reading(node) -> str:
+# def get_node_reading(node) -> str:
-    features = node.feature.split(",")
+#     features = node.feature.split(",")
-    print()
+#     print()
-    if len(features) >= 8 and features[7] != "*":
+#     if len(features) >= 8 and features[7] != "*":
-        return katakana_to_hiragana(features[7])
+#         return katakana_to_hiragana(features[7])
-    return node.surface
+#     return node.surface
 
 def has_kanji(text: str) -> bool:
     return bool(KANJI_RE.search(text))
@@ -56,6 +58,72 @@ def annotate_phrase(text: str) -> str:
 
     return {'reading':("".join(parts)),'vocab':vocab}
 
+def elide(text: str) -> str:
+    elide_max_length = 100
+    if len(text) > elide_max_length:
+        return text[:100] + "..."
+    return text
+
+def anki_fields_term(term : str) -> dict:
+    params = {
+        "text": term,
+        "type": "term",
+        "markers": ["audio", "cloze-body-kana", "conjugation", "expression", "furigana", "furigana-plain", "glossary", "glossary-brief", "glossary-no-dictionary", "glossary-first", "glossary-first-brief", "glossary-first-no-dictionary", "part-of-speech", "phonetic-transcriptions", "pitch-accents", "pitch-accent-graphs", "pitch-accent-graphs-jj", "pitch-accent-positions", "pitch-accent-categories", "reading", "tags", "clipboard-image", "clipboard-text", "cloze-body", "cloze-prefix", "cloze-suffix", "dictionary", "dictionary-alias", "document-title", "frequencies", "frequency-harmonic-rank", "frequency-harmonic-occurrence", "frequency-average-rank", "frequency-average-occurrence", "screenshot", "search-query", "popup-selection-text", "sentence", "sentence-furigana", "sentence-furigana-plain", "url"],
+        "maxEntries": 1,
+        "includeMedia": False,
+    }
+    response = requests.post(request_url + "/ankiFields", json = params, timeout = request_timeout)
+    return json.loads(response.text)
+
+def term_entries(term :str) -> dict:
+    print("Requesting termEntries:")
+    params = {
+        "term": term,
+        "maxEntries": 1,
+        "includeMedia": False,
+    }
+    response = requests.post(request_url + "/termEntries", json = params, timeout = request_timeout)
+    return json.loads(response.text)
+
+# perhaps set up a filter parameter.
+def flatten_string(node):
+    if isinstance(node,str):
+        yield node
+    elif isinstance(node, list):
+        for item in node:
+            yield from flatten_string(item)
+    elif isinstance(node,dict):
+        if isinstance(node.get("content"), str):
+            yield node["content"]
+        else:
+            for v in node.values():
+                yield from flatten_string(v)
+
+def extract_text_by_type(node, target_type):
+    if isinstance(node,dict):
+        data = node.get("data")
+        if isinstance(data,dict) and data.get("content") == target_type:
+            yield from flatten_string(node.get("content"))
+            #yield from ",".join(node.get("content"))
+        for value in node.values():
+            yield from extract_text_by_type(value, target_type)
+    elif isinstance(node,list):
+        for item in node:
+            yield from extract_text_by_type(item,target_type)
+
+def get_glossary(word :str) -> list:
+    glossary = list()
+    dict_items = term_entries(word)
+
+    entry = next(iter(dict_items.get("dictionaryEntries",[])),None)
+    if entry:
+        definition = next(iter(entry.get("definitions",[])),None)
+        if definition:
+            def_entry = next(iter(definition.get("entries", [])),None)
+            if def_entry:
+                glossary.extend( list(extract_text_by_type(def_entry, "glossary")) )
+    return glossary[:2]
+
 #print(annotate_phrase("私は学校へ行きます"))
 
 with open("dump2.json", "r", encoding="utf-16") as f: