From f9f10d4f8f04f216cffd4c408680048e60895120 Mon Sep 17 00:00:00 2001
From: Enzo Simonnet <enzosim@laposte.net>
Date: Wed, 17 Jan 2024 15:14:54 -0500
Subject: [PATCH] =?UTF-8?q?version=20finalis=C3=A9e?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
src/wiktextract_wrapper.py | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/src/wiktextract_wrapper.py b/src/wiktextract_wrapper.py
index b3761d8..3703823 100644
--- a/src/wiktextract_wrapper.py
+++ b/src/wiktextract_wrapper.py
@@ -30,8 +30,9 @@ class Wiktextract:
#print(json.dumps(result), "\n\n\n")
converted_result = self.convert(result)
- print(json.dumps(converted_result))
- return json.dumps(converted_result)
+ print("Conv result: ", json.dumps(converted_result, ensure_ascii=False, indent=2))
+
+ return converted_result
#return result
def convert(self, data_format1):
@@ -47,7 +48,7 @@ class Wiktextract:
}
],
"id": f"{pos.get('lang_code', '')}-{index}.{pos.get('pos', '')}.{pos.get('word', '')}",
- f"{pos.get('pos', '')}": {
+ f"{pos.get('word', '')}": {
"pos": pos.get("pos", ""),
"pronunciations": [],
"senses": {}
@@ -68,16 +69,16 @@ class Wiktextract:
"url": pron.get("mp3_url", pron.get("ogg_url", ""))
}
pronunciation["sounds"].append(sound)
- transformed_pos[pos.get('pos', '')]['pronunciations'].append(pronunciation)
+ transformed_pos[pos.get('word', '')]['pronunciations'].append(pronunciation)
pron_counter += 1
# Iterate through senses in the entry
for sense_index, sense in enumerate(pos.get("senses", []), start=1):
sense_id = f"{pos.get('lang_code', '')}-{index}.{pos.get('pos', '')}.{pos.get('word', '')}_{pos.get('pos', '')}{sense_index}"
- transformed_pos[pos.get('pos', '')]["senses"][sense_id] = {
+ transformed_pos[pos.get('word', '')]["senses"][sense_id] = {
"Definitions": [
{
- "id": f"{pos.get('lang_code', '')}-{pos.get('word', '')}{pos.get('pos', '')}_def{index}",
+ "id": f"{pos.get('lang_code', '')}-{pos.get('word', '')}_{pos.get('pos', '')}_def{index}",
"lang": pos.get('lang_code', ''),
"definition": gloss
} for index, gloss in enumerate(sense.get('glosses', []) + sense.get('raw_glosses', []), start=1)
@@ -109,6 +110,9 @@ if __name__ == "__main__":
args = parser.parse_args()
if args.entry != None:
wkstrkt = Wiktextract(args.wikt_language, args.word_language)
- print(wkstrkt.parse_page(args.entry))
+ result = wkstrkt.parse_page(args.entry)
+ print(json.dumps(result, ensure_ascii=False))
else:
print("{'err':'You need to specify a word'}")
+
+
--
GitLab