Agrega script 00: completar diccionario con HebrewStrong.xml

00_completar_diccionario.py

@@ -0,0 +1,114 @@
+# -*- coding: utf-8 -*-
+"""
+00_completar_diccionario.py
+Descarga el lexico completo de Strong hebreo (HebrewStrong.xml, dominio
+publico, proyecto Open Scriptures) y completa dictionary_hebrew_spanish.json
+con las entradas que falten (los ~700 H#### que tu diccionario actual no
+tiene). NO pisa nada que ya tengas: si una clave ya existe (con o sin
+"translation_es"), se deja intacta.
+
+Requisitos:
+    pip install requests
+
+Uso (en la carpeta pdf-reader/, junto a dictionary_hebrew_spanish.json):
+    python 00_completar_diccionario.py
+
+Corre ANTES de 01_traducir_diccionario.py.
+"""
+import json
+import re
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+import requests
+
+BASE_DIR = Path(__file__).parent
+DICT_PATH = BASE_DIR / "dictionary_hebrew_spanish.json"
+
+URL = "https://raw.githubusercontent.com/openscriptures/HebrewLexicon/master/HebrewStrong.xml"
+
+
+def descargar_xml():
+    print("Descargando HebrewStrong.xml...")
+    r = requests.get(URL, timeout=60)
+    r.raise_for_status()
+    return r.text
+
+
+def texto_de(el):
+    if el is None:
+        return ""
+    return "".join(el.itertext()).strip()
+
+
+def parsear(xml_text):
+    # El id puede venir como "H1" o (en variantes) sin la H; normalizamos.
+    root = ET.fromstring(xml_text)
+    entradas = {}
+    for entry in root.findall("entry"):
+        eid = entry.get("id") or ""
+        eid = eid.strip()
+        if not eid:
+            continue
+        if not eid.startswith("H"):
+            eid = "H" + eid
+
+        w = entry.find("w")
+        lemma = (w.text or "").strip() if w is not None else ""
+        xlit = w.get("xlit", "") if w is not None else ""
+
+        meaning_el = entry.find("meaning")
+        usage_el = entry.find("usage")
+        source_el = entry.find("source")
+
+        meaning = texto_de(meaning_el)
+        usage = texto_de(usage_el)
+        source = texto_de(source_el)
+
+        definition_en = meaning if meaning else usage
+
+        translation = ""
+        if meaning_el is not None:
+            primer_def = meaning_el.find("def")
+            if primer_def is not None and primer_def.text:
+                translation = primer_def.text.strip()
+        if not translation:
+            translation = re.split(r"[;,]", definition_en)[0].strip()
+        if not translation:
+            translation = usage.rstrip(".").strip()
+
+        entradas[eid] = {
+            "lemma": lemma,
+            "translation": translation,
+            "transliteration": xlit,
+            "root": "",
+            "definition_en": definition_en,
+            "note": source,
+        }
+    return entradas
+
+
+def main():
+    with open(DICT_PATH, "r", encoding="utf-8") as f:
+        actual = json.load(f)
+
+    xml_text = descargar_xml()
+    completas = parsear(xml_text)
+
+    agregadas = 0
+    for k, v in completas.items():
+        if k not in actual:
+            actual[k] = v
+            agregadas += 1
+
+    tmp = DICT_PATH.with_suffix(".tmp")
+    with open(tmp, "w", encoding="utf-8") as f:
+        json.dump(actual, f, ensure_ascii=False, indent=2)
+    tmp.replace(DICT_PATH)
+
+    print(f"Entradas nuevas agregadas: {agregadas}")
+    print(f"Total de entradas en el diccionario ahora: {len(actual)}")
+
+
+if __name__ == "__main__":
+    main()